diff --git "a/log/log-train-2022-05-03-11-40-27-3" "b/log/log-train-2022-05-03-11-40-27-3"
new file mode 100644--- /dev/null
+++ "b/log/log-train-2022-05-03-11-40-27-3"
@@ -0,0 +1,14399 @@
+2022-05-03 11:40:27,487 INFO [train.py:775] (3/8) Training started
+2022-05-03 11:40:27,487 INFO [train.py:785] (3/8) Device: cuda:3
+2022-05-03 11:40:27,489 INFO [train.py:794] (3/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.14', 'k2-build-type': 'Debug', 'k2-with-cuda': True, 'k2-git-sha1': '1b29f0a946f50186aaa82df46a59f492ade9692b', 'k2-git-date': 'Tue Apr 12 20:46:49 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.1+cu111', 'torch-cuda-available': True, 'torch-cuda-version': '11.1', 'python-version': '3.8', 'icefall-git-branch': 'spgi', 'icefall-git-sha1': 'e2e5c77-dirty', 'icefall-git-date': 'Mon May 2 14:38:25 2022', 'icefall-path': '/exp/draj/mini_scale_2022/icefall', 'k2-path': '/exp/draj/mini_scale_2022/k2/k2/python/k2/__init__.py', 'lhotse-path': '/exp/draj/mini_scale_2022/lhotse/lhotse/__init__.py', 'hostname': 'r8n04', 'IP address': '10.1.8.4'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 20, 'start_epoch': 0, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless2/exp/v2'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'initial_lr': 0.003, 'lr_batches': 5000, 'lr_epochs': 4, 'context_size': 2, 'prune_range': 5, 'lm_scale': 0.25, 'am_scale': 0.0, 'simple_loss_scale': 0.5, 'seed': 42, 'print_diagnostics': False, 'save_every_n': 8000, 'keep_last_k': 10, 'use_fp16': True, 'manifest_dir': PosixPath('data/manifests'), 'enable_musan': True, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'max_duration': 200, 'num_buckets': 30, 'on_the_fly_feats': False, 'shuffle': True, 'num_workers': 8, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'blank_id': 0, 'vocab_size': 500}
+2022-05-03 11:40:27,489 INFO [train.py:796] (3/8) About to create model
+2022-05-03 11:40:27,839 INFO [train.py:800] (3/8) Number of model parameters: 78648040
+2022-05-03 11:40:33,459 INFO [train.py:806] (3/8) Using DDP
+2022-05-03 11:40:34,136 INFO [asr_datamodule.py:321] (3/8) About to get SPGISpeech train cuts
+2022-05-03 11:40:34,140 INFO [asr_datamodule.py:179] (3/8) About to get Musan cuts
+2022-05-03 11:40:35,979 INFO [asr_datamodule.py:184] (3/8) Enable MUSAN
+2022-05-03 11:40:35,979 INFO [asr_datamodule.py:207] (3/8) Enable SpecAugment
+2022-05-03 11:40:35,979 INFO [asr_datamodule.py:208] (3/8) Time warp factor: 80
+2022-05-03 11:40:35,979 INFO [asr_datamodule.py:221] (3/8) About to create train dataset
+2022-05-03 11:40:35,979 INFO [asr_datamodule.py:234] (3/8) Using DynamicBucketingSampler.
+2022-05-03 11:40:36,377 INFO [asr_datamodule.py:242] (3/8) About to create train dataloader
+2022-05-03 11:40:36,377 INFO [asr_datamodule.py:326] (3/8) About to get SPGISpeech dev cuts
+2022-05-03 11:40:36,378 INFO [asr_datamodule.py:274] (3/8) About to create dev dataset
+2022-05-03 11:40:36,527 INFO [asr_datamodule.py:289] (3/8) About to create dev dataloader
+2022-05-03 11:41:08,011 INFO [train.py:715] (3/8) Epoch 0, batch 0, loss[loss=3.357, simple_loss=6.715, pruned_loss=5.809, over 4869.00 frames.], tot_loss[loss=3.357, simple_loss=6.715, pruned_loss=5.809, over 4869.00 frames.], batch size: 13, lr: 3.00e-03
+2022-05-03 11:41:08,404 INFO [distributed.py:874] (3/8) Reducer buckets have been rebuilt in this iteration.
+2022-05-03 11:41:46,315 INFO [train.py:715] (3/8) Epoch 0, batch 50, loss[loss=0.4083, simple_loss=0.8166, pruned_loss=6.726, over 4782.00 frames.], tot_loss[loss=1.338, simple_loss=2.676, pruned_loss=6.475, over 219213.39 frames.], batch size: 14, lr: 3.00e-03
+2022-05-03 11:42:25,576 INFO [train.py:715] (3/8) Epoch 0, batch 100, loss[loss=0.3668, simple_loss=0.7335, pruned_loss=6.631, over 4771.00 frames.], tot_loss[loss=0.8233, simple_loss=1.647, pruned_loss=6.581, over 386414.20 frames.], batch size: 17, lr: 3.00e-03
+2022-05-03 11:43:04,757 INFO [train.py:715] (3/8) Epoch 0, batch 150, loss[loss=0.3687, simple_loss=0.7375, pruned_loss=6.639, over 4982.00 frames.], tot_loss[loss=0.6338, simple_loss=1.268, pruned_loss=6.593, over 517230.15 frames.], batch size: 24, lr: 3.00e-03
+2022-05-03 11:43:43,122 INFO [train.py:715] (3/8) Epoch 0, batch 200, loss[loss=0.3371, simple_loss=0.6741, pruned_loss=6.712, over 4764.00 frames.], tot_loss[loss=0.5353, simple_loss=1.071, pruned_loss=6.584, over 618013.90 frames.], batch size: 16, lr: 3.00e-03
+2022-05-03 11:44:22,063 INFO [train.py:715] (3/8) Epoch 0, batch 250, loss[loss=0.3385, simple_loss=0.677, pruned_loss=6.668, over 4803.00 frames.], tot_loss[loss=0.4747, simple_loss=0.9495, pruned_loss=6.592, over 695472.47 frames.], batch size: 21, lr: 3.00e-03
+2022-05-03 11:45:01,535 INFO [train.py:715] (3/8) Epoch 0, batch 300, loss[loss=0.3465, simple_loss=0.693, pruned_loss=6.824, over 4901.00 frames.], tot_loss[loss=0.4347, simple_loss=0.8694, pruned_loss=6.604, over 757606.68 frames.], batch size: 19, lr: 3.00e-03
+2022-05-03 11:45:41,187 INFO [train.py:715] (3/8) Epoch 0, batch 350, loss[loss=0.2861, simple_loss=0.5722, pruned_loss=6.633, over 4975.00 frames.], tot_loss[loss=0.4073, simple_loss=0.8145, pruned_loss=6.623, over 806105.28 frames.], batch size: 15, lr: 3.00e-03
+2022-05-03 11:46:19,550 INFO [train.py:715] (3/8) Epoch 0, batch 400, loss[loss=0.3463, simple_loss=0.6925, pruned_loss=6.687, over 4974.00 frames.], tot_loss[loss=0.3853, simple_loss=0.7705, pruned_loss=6.633, over 843478.83 frames.], batch size: 25, lr: 3.00e-03
+2022-05-03 11:46:58,907 INFO [train.py:715] (3/8) Epoch 0, batch 450, loss[loss=0.3199, simple_loss=0.6397, pruned_loss=6.661, over 4637.00 frames.], tot_loss[loss=0.3697, simple_loss=0.7395, pruned_loss=6.644, over 871890.37 frames.], batch size: 13, lr: 2.99e-03
+2022-05-03 11:47:38,000 INFO [train.py:715] (3/8) Epoch 0, batch 500, loss[loss=0.3264, simple_loss=0.6529, pruned_loss=6.657, over 4926.00 frames.], tot_loss[loss=0.3562, simple_loss=0.7123, pruned_loss=6.643, over 894728.84 frames.], batch size: 39, lr: 2.99e-03
+2022-05-03 11:48:17,106 INFO [train.py:715] (3/8) Epoch 0, batch 550, loss[loss=0.3269, simple_loss=0.6539, pruned_loss=6.816, over 4873.00 frames.], tot_loss[loss=0.3455, simple_loss=0.6911, pruned_loss=6.645, over 911806.18 frames.], batch size: 16, lr: 2.99e-03
+2022-05-03 11:48:55,927 INFO [train.py:715] (3/8) Epoch 0, batch 600, loss[loss=0.3209, simple_loss=0.6418, pruned_loss=6.744, over 4935.00 frames.], tot_loss[loss=0.3366, simple_loss=0.6732, pruned_loss=6.659, over 924944.14 frames.], batch size: 29, lr: 2.99e-03
+2022-05-03 11:49:35,147 INFO [train.py:715] (3/8) Epoch 0, batch 650, loss[loss=0.2642, simple_loss=0.5284, pruned_loss=6.685, over 4752.00 frames.], tot_loss[loss=0.3251, simple_loss=0.6502, pruned_loss=6.677, over 935874.10 frames.], batch size: 19, lr: 2.99e-03
+2022-05-03 11:50:14,494 INFO [train.py:715] (3/8) Epoch 0, batch 700, loss[loss=0.2823, simple_loss=0.5645, pruned_loss=6.879, over 4829.00 frames.], tot_loss[loss=0.3139, simple_loss=0.6278, pruned_loss=6.7, over 943661.30 frames.], batch size: 30, lr: 2.99e-03
+2022-05-03 11:50:52,997 INFO [train.py:715] (3/8) Epoch 0, batch 750, loss[loss=0.2645, simple_loss=0.529, pruned_loss=6.75, over 4851.00 frames.], tot_loss[loss=0.3018, simple_loss=0.6035, pruned_loss=6.712, over 950227.79 frames.], batch size: 30, lr: 2.98e-03
+2022-05-03 11:51:32,778 INFO [train.py:715] (3/8) Epoch 0, batch 800, loss[loss=0.2607, simple_loss=0.5213, pruned_loss=6.731, over 4925.00 frames.], tot_loss[loss=0.2902, simple_loss=0.5804, pruned_loss=6.717, over 955311.81 frames.], batch size: 23, lr: 2.98e-03
+2022-05-03 11:52:12,741 INFO [train.py:715] (3/8) Epoch 0, batch 850, loss[loss=0.2545, simple_loss=0.509, pruned_loss=6.777, over 4859.00 frames.], tot_loss[loss=0.2793, simple_loss=0.5586, pruned_loss=6.715, over 959256.83 frames.], batch size: 22, lr: 2.98e-03
+2022-05-03 11:52:51,635 INFO [train.py:715] (3/8) Epoch 0, batch 900, loss[loss=0.2343, simple_loss=0.4686, pruned_loss=6.746, over 4823.00 frames.], tot_loss[loss=0.2696, simple_loss=0.5391, pruned_loss=6.711, over 962067.51 frames.], batch size: 27, lr: 2.98e-03
+2022-05-03 11:53:30,228 INFO [train.py:715] (3/8) Epoch 0, batch 950, loss[loss=0.254, simple_loss=0.508, pruned_loss=6.729, over 4826.00 frames.], tot_loss[loss=0.2605, simple_loss=0.5209, pruned_loss=6.71, over 964561.10 frames.], batch size: 25, lr: 2.97e-03
+2022-05-03 11:54:09,539 INFO [train.py:715] (3/8) Epoch 0, batch 1000, loss[loss=0.1947, simple_loss=0.3893, pruned_loss=6.598, over 4750.00 frames.], tot_loss[loss=0.2522, simple_loss=0.5043, pruned_loss=6.713, over 966195.29 frames.], batch size: 19, lr: 2.97e-03
+2022-05-03 11:54:48,898 INFO [train.py:715] (3/8) Epoch 0, batch 1050, loss[loss=0.1863, simple_loss=0.3726, pruned_loss=6.561, over 4919.00 frames.], tot_loss[loss=0.2445, simple_loss=0.4889, pruned_loss=6.713, over 966731.02 frames.], batch size: 29, lr: 2.97e-03
+2022-05-03 11:55:27,464 INFO [train.py:715] (3/8) Epoch 0, batch 1100, loss[loss=0.2297, simple_loss=0.4595, pruned_loss=6.828, over 4807.00 frames.], tot_loss[loss=0.2384, simple_loss=0.4768, pruned_loss=6.713, over 968244.10 frames.], batch size: 21, lr: 2.96e-03
+2022-05-03 11:56:07,471 INFO [train.py:715] (3/8) Epoch 0, batch 1150, loss[loss=0.1976, simple_loss=0.3951, pruned_loss=6.74, over 4818.00 frames.], tot_loss[loss=0.2318, simple_loss=0.4637, pruned_loss=6.714, over 968528.45 frames.], batch size: 26, lr: 2.96e-03
+2022-05-03 11:56:47,805 INFO [train.py:715] (3/8) Epoch 0, batch 1200, loss[loss=0.1987, simple_loss=0.3975, pruned_loss=6.658, over 4763.00 frames.], tot_loss[loss=0.2266, simple_loss=0.4533, pruned_loss=6.714, over 970178.02 frames.], batch size: 18, lr: 2.96e-03
+2022-05-03 11:57:28,431 INFO [train.py:715] (3/8) Epoch 0, batch 1250, loss[loss=0.2105, simple_loss=0.421, pruned_loss=6.699, over 4843.00 frames.], tot_loss[loss=0.2223, simple_loss=0.4446, pruned_loss=6.715, over 970713.57 frames.], batch size: 34, lr: 2.95e-03
+2022-05-03 11:58:07,328 INFO [train.py:715] (3/8) Epoch 0, batch 1300, loss[loss=0.1828, simple_loss=0.3656, pruned_loss=6.651, over 4928.00 frames.], tot_loss[loss=0.2173, simple_loss=0.4347, pruned_loss=6.712, over 970936.87 frames.], batch size: 18, lr: 2.95e-03
+2022-05-03 11:58:47,742 INFO [train.py:715] (3/8) Epoch 0, batch 1350, loss[loss=0.1827, simple_loss=0.3654, pruned_loss=6.598, over 4995.00 frames.], tot_loss[loss=0.2136, simple_loss=0.4272, pruned_loss=6.712, over 972061.78 frames.], batch size: 14, lr: 2.95e-03
+2022-05-03 11:59:28,704 INFO [train.py:715] (3/8) Epoch 0, batch 1400, loss[loss=0.1914, simple_loss=0.3828, pruned_loss=6.627, over 4790.00 frames.], tot_loss[loss=0.211, simple_loss=0.4219, pruned_loss=6.718, over 972320.20 frames.], batch size: 17, lr: 2.94e-03
+2022-05-03 12:00:09,323 INFO [train.py:715] (3/8) Epoch 0, batch 1450, loss[loss=0.213, simple_loss=0.4261, pruned_loss=6.782, over 4881.00 frames.], tot_loss[loss=0.2081, simple_loss=0.4163, pruned_loss=6.716, over 971691.64 frames.], batch size: 16, lr: 2.94e-03
+2022-05-03 12:00:48,849 INFO [train.py:715] (3/8) Epoch 0, batch 1500, loss[loss=0.1945, simple_loss=0.389, pruned_loss=6.819, over 4797.00 frames.], tot_loss[loss=0.2042, simple_loss=0.4084, pruned_loss=6.71, over 971793.51 frames.], batch size: 24, lr: 2.94e-03
+2022-05-03 12:01:29,917 INFO [train.py:715] (3/8) Epoch 0, batch 1550, loss[loss=0.1854, simple_loss=0.3708, pruned_loss=6.554, over 4993.00 frames.], tot_loss[loss=0.2016, simple_loss=0.4031, pruned_loss=6.707, over 973304.43 frames.], batch size: 14, lr: 2.93e-03
+2022-05-03 12:02:11,264 INFO [train.py:715] (3/8) Epoch 0, batch 1600, loss[loss=0.1778, simple_loss=0.3556, pruned_loss=6.6, over 4855.00 frames.], tot_loss[loss=0.1983, simple_loss=0.3967, pruned_loss=6.696, over 972763.67 frames.], batch size: 20, lr: 2.93e-03
+2022-05-03 12:02:51,029 INFO [train.py:715] (3/8) Epoch 0, batch 1650, loss[loss=0.1939, simple_loss=0.3879, pruned_loss=6.703, over 4981.00 frames.], tot_loss[loss=0.1969, simple_loss=0.3938, pruned_loss=6.694, over 972512.85 frames.], batch size: 25, lr: 2.92e-03
+2022-05-03 12:03:32,799 INFO [train.py:715] (3/8) Epoch 0, batch 1700, loss[loss=0.1879, simple_loss=0.3758, pruned_loss=6.616, over 4695.00 frames.], tot_loss[loss=0.1945, simple_loss=0.389, pruned_loss=6.691, over 971963.73 frames.], batch size: 15, lr: 2.92e-03
+2022-05-03 12:04:14,548 INFO [train.py:715] (3/8) Epoch 0, batch 1750, loss[loss=0.1917, simple_loss=0.3833, pruned_loss=6.629, over 4742.00 frames.], tot_loss[loss=0.1927, simple_loss=0.3853, pruned_loss=6.688, over 972384.78 frames.], batch size: 16, lr: 2.91e-03
+2022-05-03 12:04:56,016 INFO [train.py:715] (3/8) Epoch 0, batch 1800, loss[loss=0.1817, simple_loss=0.3634, pruned_loss=6.659, over 4902.00 frames.], tot_loss[loss=0.1916, simple_loss=0.3832, pruned_loss=6.682, over 972629.22 frames.], batch size: 29, lr: 2.91e-03
+2022-05-03 12:05:36,572 INFO [train.py:715] (3/8) Epoch 0, batch 1850, loss[loss=0.1858, simple_loss=0.3716, pruned_loss=6.685, over 4749.00 frames.], tot_loss[loss=0.1896, simple_loss=0.3793, pruned_loss=6.675, over 972129.17 frames.], batch size: 19, lr: 2.91e-03
+2022-05-03 12:06:18,609 INFO [train.py:715] (3/8) Epoch 0, batch 1900, loss[loss=0.1778, simple_loss=0.3557, pruned_loss=6.598, over 4787.00 frames.], tot_loss[loss=0.1869, simple_loss=0.3739, pruned_loss=6.669, over 972522.67 frames.], batch size: 18, lr: 2.90e-03
+2022-05-03 12:07:00,145 INFO [train.py:715] (3/8) Epoch 0, batch 1950, loss[loss=0.1888, simple_loss=0.3776, pruned_loss=6.554, over 4970.00 frames.], tot_loss[loss=0.1852, simple_loss=0.3704, pruned_loss=6.667, over 972754.64 frames.], batch size: 14, lr: 2.90e-03
+2022-05-03 12:07:38,869 INFO [train.py:715] (3/8) Epoch 0, batch 2000, loss[loss=0.1776, simple_loss=0.3552, pruned_loss=6.604, over 4986.00 frames.], tot_loss[loss=0.1834, simple_loss=0.3668, pruned_loss=6.666, over 971752.22 frames.], batch size: 33, lr: 2.89e-03
+2022-05-03 12:08:19,991 INFO [train.py:715] (3/8) Epoch 0, batch 2050, loss[loss=0.1967, simple_loss=0.3933, pruned_loss=6.885, over 4874.00 frames.], tot_loss[loss=0.1833, simple_loss=0.3666, pruned_loss=6.665, over 972220.36 frames.], batch size: 16, lr: 2.89e-03
+2022-05-03 12:09:00,591 INFO [train.py:715] (3/8) Epoch 0, batch 2100, loss[loss=0.1664, simple_loss=0.3327, pruned_loss=6.64, over 4971.00 frames.], tot_loss[loss=0.1819, simple_loss=0.3638, pruned_loss=6.665, over 972440.56 frames.], batch size: 33, lr: 2.88e-03
+2022-05-03 12:09:41,205 INFO [train.py:715] (3/8) Epoch 0, batch 2150, loss[loss=0.1736, simple_loss=0.3472, pruned_loss=6.724, over 4967.00 frames.], tot_loss[loss=0.1819, simple_loss=0.3639, pruned_loss=6.669, over 972736.23 frames.], batch size: 15, lr: 2.88e-03
+2022-05-03 12:10:20,500 INFO [train.py:715] (3/8) Epoch 0, batch 2200, loss[loss=0.169, simple_loss=0.3379, pruned_loss=6.619, over 4854.00 frames.], tot_loss[loss=0.1802, simple_loss=0.3604, pruned_loss=6.669, over 972068.69 frames.], batch size: 32, lr: 2.87e-03
+2022-05-03 12:11:01,489 INFO [train.py:715] (3/8) Epoch 0, batch 2250, loss[loss=0.1849, simple_loss=0.3697, pruned_loss=6.718, over 4942.00 frames.], tot_loss[loss=0.1797, simple_loss=0.3593, pruned_loss=6.668, over 972203.14 frames.], batch size: 39, lr: 2.86e-03
+2022-05-03 12:11:42,771 INFO [train.py:715] (3/8) Epoch 0, batch 2300, loss[loss=0.1665, simple_loss=0.3329, pruned_loss=6.609, over 4989.00 frames.], tot_loss[loss=0.1793, simple_loss=0.3585, pruned_loss=6.671, over 972538.92 frames.], batch size: 20, lr: 2.86e-03
+2022-05-03 12:12:22,379 INFO [train.py:715] (3/8) Epoch 0, batch 2350, loss[loss=0.1821, simple_loss=0.3643, pruned_loss=6.767, over 4929.00 frames.], tot_loss[loss=0.1778, simple_loss=0.3555, pruned_loss=6.666, over 972755.47 frames.], batch size: 21, lr: 2.85e-03
+2022-05-03 12:13:03,123 INFO [train.py:715] (3/8) Epoch 0, batch 2400, loss[loss=0.1633, simple_loss=0.3265, pruned_loss=6.686, over 4847.00 frames.], tot_loss[loss=0.1766, simple_loss=0.3532, pruned_loss=6.668, over 972083.84 frames.], batch size: 13, lr: 2.85e-03
+2022-05-03 12:13:43,810 INFO [train.py:715] (3/8) Epoch 0, batch 2450, loss[loss=0.1858, simple_loss=0.3716, pruned_loss=6.693, over 4924.00 frames.], tot_loss[loss=0.1767, simple_loss=0.3534, pruned_loss=6.669, over 972910.84 frames.], batch size: 18, lr: 2.84e-03
+2022-05-03 12:14:24,674 INFO [train.py:715] (3/8) Epoch 0, batch 2500, loss[loss=0.1809, simple_loss=0.3617, pruned_loss=6.671, over 4968.00 frames.], tot_loss[loss=0.1763, simple_loss=0.3525, pruned_loss=6.67, over 972023.61 frames.], batch size: 39, lr: 2.84e-03
+2022-05-03 12:15:03,906 INFO [train.py:715] (3/8) Epoch 0, batch 2550, loss[loss=0.1879, simple_loss=0.3758, pruned_loss=6.71, over 4973.00 frames.], tot_loss[loss=0.1754, simple_loss=0.3508, pruned_loss=6.67, over 972507.07 frames.], batch size: 14, lr: 2.83e-03
+2022-05-03 12:15:44,623 INFO [train.py:715] (3/8) Epoch 0, batch 2600, loss[loss=0.1912, simple_loss=0.3825, pruned_loss=6.618, over 4947.00 frames.], tot_loss[loss=0.1747, simple_loss=0.3495, pruned_loss=6.665, over 972403.24 frames.], batch size: 35, lr: 2.83e-03
+2022-05-03 12:16:25,708 INFO [train.py:715] (3/8) Epoch 0, batch 2650, loss[loss=0.1662, simple_loss=0.3325, pruned_loss=6.677, over 4827.00 frames.], tot_loss[loss=0.1742, simple_loss=0.3483, pruned_loss=6.665, over 972401.51 frames.], batch size: 15, lr: 2.82e-03
+2022-05-03 12:17:08,084 INFO [train.py:715] (3/8) Epoch 0, batch 2700, loss[loss=0.1766, simple_loss=0.3531, pruned_loss=6.637, over 4866.00 frames.], tot_loss[loss=0.1729, simple_loss=0.3458, pruned_loss=6.656, over 972392.38 frames.], batch size: 16, lr: 2.81e-03
+2022-05-03 12:17:48,873 INFO [train.py:715] (3/8) Epoch 0, batch 2750, loss[loss=0.1604, simple_loss=0.3208, pruned_loss=6.755, over 4844.00 frames.], tot_loss[loss=0.1726, simple_loss=0.3451, pruned_loss=6.654, over 971436.10 frames.], batch size: 15, lr: 2.81e-03
+2022-05-03 12:18:29,709 INFO [train.py:715] (3/8) Epoch 0, batch 2800, loss[loss=0.1749, simple_loss=0.3499, pruned_loss=6.515, over 4851.00 frames.], tot_loss[loss=0.1718, simple_loss=0.3437, pruned_loss=6.651, over 971671.39 frames.], batch size: 20, lr: 2.80e-03
+2022-05-03 12:19:10,256 INFO [train.py:715] (3/8) Epoch 0, batch 2850, loss[loss=0.2016, simple_loss=0.4032, pruned_loss=6.771, over 4811.00 frames.], tot_loss[loss=0.172, simple_loss=0.344, pruned_loss=6.652, over 972169.92 frames.], batch size: 24, lr: 2.80e-03
+2022-05-03 12:19:49,110 INFO [train.py:715] (3/8) Epoch 0, batch 2900, loss[loss=0.1639, simple_loss=0.3279, pruned_loss=6.663, over 4839.00 frames.], tot_loss[loss=0.1707, simple_loss=0.3414, pruned_loss=6.643, over 972363.47 frames.], batch size: 15, lr: 2.79e-03
+2022-05-03 12:20:29,365 INFO [train.py:715] (3/8) Epoch 0, batch 2950, loss[loss=0.1672, simple_loss=0.3344, pruned_loss=6.591, over 4830.00 frames.], tot_loss[loss=0.1702, simple_loss=0.3403, pruned_loss=6.643, over 971428.68 frames.], batch size: 12, lr: 2.78e-03
+2022-05-03 12:21:11,358 INFO [train.py:715] (3/8) Epoch 0, batch 3000, loss[loss=0.8311, simple_loss=0.3316, pruned_loss=6.653, over 4897.00 frames.], tot_loss[loss=0.2059, simple_loss=0.3396, pruned_loss=6.648, over 971195.80 frames.], batch size: 19, lr: 2.78e-03
+2022-05-03 12:21:11,359 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 12:21:21,129 INFO [train.py:742] (3/8) Epoch 0, validation: loss=2.223, simple_loss=0.2788, pruned_loss=2.083, over 914524.00 frames.
+2022-05-03 12:22:02,151 INFO [train.py:715] (3/8) Epoch 0, batch 3050, loss[loss=0.2545, simple_loss=0.3654, pruned_loss=0.7176, over 4808.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3424, pruned_loss=5.411, over 971191.16 frames.], batch size: 21, lr: 2.77e-03
+2022-05-03 12:22:41,556 INFO [train.py:715] (3/8) Epoch 0, batch 3100, loss[loss=0.1755, simple_loss=0.2897, pruned_loss=0.3061, over 4902.00 frames.], tot_loss[loss=0.2222, simple_loss=0.342, pruned_loss=4.319, over 971733.66 frames.], batch size: 19, lr: 2.77e-03
+2022-05-03 12:23:22,410 INFO [train.py:715] (3/8) Epoch 0, batch 3150, loss[loss=0.2138, simple_loss=0.3681, pruned_loss=0.298, over 4857.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3408, pruned_loss=3.429, over 972013.87 frames.], batch size: 20, lr: 2.76e-03
+2022-05-03 12:24:03,656 INFO [train.py:715] (3/8) Epoch 0, batch 3200, loss[loss=0.1923, simple_loss=0.339, pruned_loss=0.2282, over 4784.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3404, pruned_loss=2.727, over 971458.67 frames.], batch size: 14, lr: 2.75e-03
+2022-05-03 12:24:44,871 INFO [train.py:715] (3/8) Epoch 0, batch 3250, loss[loss=0.1949, simple_loss=0.3441, pruned_loss=0.2287, over 4819.00 frames.], tot_loss[loss=0.2074, simple_loss=0.3393, pruned_loss=2.172, over 972055.56 frames.], batch size: 27, lr: 2.75e-03
+2022-05-03 12:25:24,108 INFO [train.py:715] (3/8) Epoch 0, batch 3300, loss[loss=0.1702, simple_loss=0.3041, pruned_loss=0.1816, over 4852.00 frames.], tot_loss[loss=0.2035, simple_loss=0.3387, pruned_loss=1.738, over 972290.44 frames.], batch size: 32, lr: 2.74e-03
+2022-05-03 12:26:05,350 INFO [train.py:715] (3/8) Epoch 0, batch 3350, loss[loss=0.1668, simple_loss=0.301, pruned_loss=0.1634, over 4826.00 frames.], tot_loss[loss=0.1988, simple_loss=0.3358, pruned_loss=1.396, over 972426.91 frames.], batch size: 15, lr: 2.73e-03
+2022-05-03 12:26:46,196 INFO [train.py:715] (3/8) Epoch 0, batch 3400, loss[loss=0.1721, simple_loss=0.3072, pruned_loss=0.1852, over 4725.00 frames.], tot_loss[loss=0.1959, simple_loss=0.3349, pruned_loss=1.13, over 972566.12 frames.], batch size: 12, lr: 2.73e-03
+2022-05-03 12:27:25,312 INFO [train.py:715] (3/8) Epoch 0, batch 3450, loss[loss=0.2258, simple_loss=0.3979, pruned_loss=0.269, over 4822.00 frames.], tot_loss[loss=0.1938, simple_loss=0.3347, pruned_loss=0.9218, over 973489.45 frames.], batch size: 26, lr: 2.72e-03
+2022-05-03 12:28:06,928 INFO [train.py:715] (3/8) Epoch 0, batch 3500, loss[loss=0.1824, simple_loss=0.3285, pruned_loss=0.1814, over 4756.00 frames.], tot_loss[loss=0.1907, simple_loss=0.3322, pruned_loss=0.7582, over 972277.86 frames.], batch size: 19, lr: 2.72e-03
+2022-05-03 12:28:48,556 INFO [train.py:715] (3/8) Epoch 0, batch 3550, loss[loss=0.206, simple_loss=0.3647, pruned_loss=0.2367, over 4924.00 frames.], tot_loss[loss=0.189, simple_loss=0.3317, pruned_loss=0.6309, over 971922.29 frames.], batch size: 18, lr: 2.71e-03
+2022-05-03 12:29:29,802 INFO [train.py:715] (3/8) Epoch 0, batch 3600, loss[loss=0.1728, simple_loss=0.3161, pruned_loss=0.1474, over 4915.00 frames.], tot_loss[loss=0.1869, simple_loss=0.33, pruned_loss=0.5293, over 972744.56 frames.], batch size: 18, lr: 2.70e-03
+2022-05-03 12:30:09,007 INFO [train.py:715] (3/8) Epoch 0, batch 3650, loss[loss=0.1837, simple_loss=0.332, pruned_loss=0.1772, over 4892.00 frames.], tot_loss[loss=0.1852, simple_loss=0.3287, pruned_loss=0.4502, over 972718.45 frames.], batch size: 22, lr: 2.70e-03
+2022-05-03 12:30:50,510 INFO [train.py:715] (3/8) Epoch 0, batch 3700, loss[loss=0.1685, simple_loss=0.306, pruned_loss=0.1549, over 4897.00 frames.], tot_loss[loss=0.1848, simple_loss=0.3291, pruned_loss=0.3904, over 972359.50 frames.], batch size: 19, lr: 2.69e-03
+2022-05-03 12:31:32,098 INFO [train.py:715] (3/8) Epoch 0, batch 3750, loss[loss=0.1664, simple_loss=0.3043, pruned_loss=0.1428, over 4860.00 frames.], tot_loss[loss=0.1841, simple_loss=0.3289, pruned_loss=0.3423, over 972665.44 frames.], batch size: 20, lr: 2.68e-03
+2022-05-03 12:32:11,304 INFO [train.py:715] (3/8) Epoch 0, batch 3800, loss[loss=0.1656, simple_loss=0.3041, pruned_loss=0.1355, over 4978.00 frames.], tot_loss[loss=0.1826, simple_loss=0.3272, pruned_loss=0.3039, over 973772.85 frames.], batch size: 24, lr: 2.68e-03
+2022-05-03 12:33:05,632 INFO [train.py:715] (3/8) Epoch 0, batch 3850, loss[loss=0.1863, simple_loss=0.338, pruned_loss=0.173, over 4831.00 frames.], tot_loss[loss=0.1812, simple_loss=0.3256, pruned_loss=0.2729, over 973067.71 frames.], batch size: 27, lr: 2.67e-03
+2022-05-03 12:33:46,694 INFO [train.py:715] (3/8) Epoch 0, batch 3900, loss[loss=0.1933, simple_loss=0.3491, pruned_loss=0.1879, over 4838.00 frames.], tot_loss[loss=0.1806, simple_loss=0.325, pruned_loss=0.2498, over 972005.68 frames.], batch size: 15, lr: 2.66e-03
+2022-05-03 12:34:26,856 INFO [train.py:715] (3/8) Epoch 0, batch 3950, loss[loss=0.1843, simple_loss=0.332, pruned_loss=0.1829, over 4840.00 frames.], tot_loss[loss=0.1803, simple_loss=0.3251, pruned_loss=0.2311, over 972223.27 frames.], batch size: 13, lr: 2.66e-03
+2022-05-03 12:35:06,662 INFO [train.py:715] (3/8) Epoch 0, batch 4000, loss[loss=0.2066, simple_loss=0.37, pruned_loss=0.2166, over 4701.00 frames.], tot_loss[loss=0.1798, simple_loss=0.3247, pruned_loss=0.2165, over 972221.24 frames.], batch size: 15, lr: 2.65e-03
+2022-05-03 12:35:47,590 INFO [train.py:715] (3/8) Epoch 0, batch 4050, loss[loss=0.2243, simple_loss=0.4005, pruned_loss=0.2407, over 4872.00 frames.], tot_loss[loss=0.1799, simple_loss=0.3251, pruned_loss=0.2061, over 972436.21 frames.], batch size: 16, lr: 2.64e-03
+2022-05-03 12:36:28,806 INFO [train.py:715] (3/8) Epoch 0, batch 4100, loss[loss=0.1556, simple_loss=0.2841, pruned_loss=0.1356, over 4977.00 frames.], tot_loss[loss=0.1798, simple_loss=0.3251, pruned_loss=0.1975, over 971330.58 frames.], batch size: 35, lr: 2.64e-03
+2022-05-03 12:37:07,961 INFO [train.py:715] (3/8) Epoch 0, batch 4150, loss[loss=0.1795, simple_loss=0.3266, pruned_loss=0.1621, over 4939.00 frames.], tot_loss[loss=0.1793, simple_loss=0.3246, pruned_loss=0.1899, over 970291.39 frames.], batch size: 23, lr: 2.63e-03
+2022-05-03 12:37:49,197 INFO [train.py:715] (3/8) Epoch 0, batch 4200, loss[loss=0.1841, simple_loss=0.3366, pruned_loss=0.158, over 4908.00 frames.], tot_loss[loss=0.179, simple_loss=0.3243, pruned_loss=0.1834, over 971162.73 frames.], batch size: 19, lr: 2.63e-03
+2022-05-03 12:38:30,912 INFO [train.py:715] (3/8) Epoch 0, batch 4250, loss[loss=0.1874, simple_loss=0.3416, pruned_loss=0.166, over 4901.00 frames.], tot_loss[loss=0.1777, simple_loss=0.3224, pruned_loss=0.1768, over 971872.87 frames.], batch size: 17, lr: 2.62e-03
+2022-05-03 12:39:11,497 INFO [train.py:715] (3/8) Epoch 0, batch 4300, loss[loss=0.1795, simple_loss=0.3286, pruned_loss=0.152, over 4780.00 frames.], tot_loss[loss=0.1772, simple_loss=0.3217, pruned_loss=0.1723, over 970824.68 frames.], batch size: 17, lr: 2.61e-03
+2022-05-03 12:39:51,568 INFO [train.py:715] (3/8) Epoch 0, batch 4350, loss[loss=0.1791, simple_loss=0.3231, pruned_loss=0.1758, over 4940.00 frames.], tot_loss[loss=0.1778, simple_loss=0.3229, pruned_loss=0.1706, over 971465.55 frames.], batch size: 24, lr: 2.61e-03
+2022-05-03 12:40:33,086 INFO [train.py:715] (3/8) Epoch 0, batch 4400, loss[loss=0.168, simple_loss=0.3035, pruned_loss=0.1626, over 4870.00 frames.], tot_loss[loss=0.1771, simple_loss=0.322, pruned_loss=0.1673, over 971234.39 frames.], batch size: 16, lr: 2.60e-03
+2022-05-03 12:41:14,312 INFO [train.py:715] (3/8) Epoch 0, batch 4450, loss[loss=0.1842, simple_loss=0.3391, pruned_loss=0.1465, over 4896.00 frames.], tot_loss[loss=0.1763, simple_loss=0.3207, pruned_loss=0.1642, over 971146.95 frames.], batch size: 22, lr: 2.59e-03
+2022-05-03 12:41:53,459 INFO [train.py:715] (3/8) Epoch 0, batch 4500, loss[loss=0.1939, simple_loss=0.3507, pruned_loss=0.1851, over 4917.00 frames.], tot_loss[loss=0.1759, simple_loss=0.3199, pruned_loss=0.1623, over 970100.39 frames.], batch size: 29, lr: 2.59e-03
+2022-05-03 12:42:34,808 INFO [train.py:715] (3/8) Epoch 0, batch 4550, loss[loss=0.1437, simple_loss=0.2636, pruned_loss=0.1185, over 4981.00 frames.], tot_loss[loss=0.1751, simple_loss=0.3189, pruned_loss=0.1596, over 970135.41 frames.], batch size: 14, lr: 2.58e-03
+2022-05-03 12:43:16,361 INFO [train.py:715] (3/8) Epoch 0, batch 4600, loss[loss=0.1511, simple_loss=0.2795, pruned_loss=0.1128, over 4904.00 frames.], tot_loss[loss=0.1751, simple_loss=0.3189, pruned_loss=0.1585, over 971005.06 frames.], batch size: 22, lr: 2.57e-03
+2022-05-03 12:43:56,533 INFO [train.py:715] (3/8) Epoch 0, batch 4650, loss[loss=0.1585, simple_loss=0.2889, pruned_loss=0.1405, over 4750.00 frames.], tot_loss[loss=0.1745, simple_loss=0.3181, pruned_loss=0.1565, over 971209.75 frames.], batch size: 16, lr: 2.57e-03
+2022-05-03 12:44:36,467 INFO [train.py:715] (3/8) Epoch 0, batch 4700, loss[loss=0.1538, simple_loss=0.284, pruned_loss=0.1183, over 4792.00 frames.], tot_loss[loss=0.1743, simple_loss=0.3177, pruned_loss=0.1551, over 971021.35 frames.], batch size: 21, lr: 2.56e-03
+2022-05-03 12:45:17,605 INFO [train.py:715] (3/8) Epoch 0, batch 4750, loss[loss=0.1783, simple_loss=0.3212, pruned_loss=0.1771, over 4813.00 frames.], tot_loss[loss=0.1737, simple_loss=0.317, pruned_loss=0.1535, over 971307.49 frames.], batch size: 24, lr: 2.55e-03
+2022-05-03 12:45:58,875 INFO [train.py:715] (3/8) Epoch 0, batch 4800, loss[loss=0.1698, simple_loss=0.3127, pruned_loss=0.1348, over 4876.00 frames.], tot_loss[loss=0.1734, simple_loss=0.3166, pruned_loss=0.1521, over 971455.38 frames.], batch size: 16, lr: 2.55e-03
+2022-05-03 12:46:38,835 INFO [train.py:715] (3/8) Epoch 0, batch 4850, loss[loss=0.1798, simple_loss=0.3273, pruned_loss=0.1612, over 4968.00 frames.], tot_loss[loss=0.1733, simple_loss=0.3163, pruned_loss=0.1518, over 971993.51 frames.], batch size: 39, lr: 2.54e-03
+2022-05-03 12:47:19,640 INFO [train.py:715] (3/8) Epoch 0, batch 4900, loss[loss=0.1718, simple_loss=0.3129, pruned_loss=0.1531, over 4891.00 frames.], tot_loss[loss=0.1725, simple_loss=0.315, pruned_loss=0.1502, over 973038.12 frames.], batch size: 19, lr: 2.54e-03
+2022-05-03 12:48:01,137 INFO [train.py:715] (3/8) Epoch 0, batch 4950, loss[loss=0.1743, simple_loss=0.3141, pruned_loss=0.172, over 4791.00 frames.], tot_loss[loss=0.1719, simple_loss=0.3141, pruned_loss=0.1486, over 972800.85 frames.], batch size: 12, lr: 2.53e-03
+2022-05-03 12:48:41,421 INFO [train.py:715] (3/8) Epoch 0, batch 5000, loss[loss=0.1862, simple_loss=0.3389, pruned_loss=0.1674, over 4913.00 frames.], tot_loss[loss=0.1717, simple_loss=0.3139, pruned_loss=0.1479, over 972216.76 frames.], batch size: 29, lr: 2.52e-03
+2022-05-03 12:49:22,148 INFO [train.py:715] (3/8) Epoch 0, batch 5050, loss[loss=0.1581, simple_loss=0.2925, pruned_loss=0.1179, over 4988.00 frames.], tot_loss[loss=0.1715, simple_loss=0.3136, pruned_loss=0.1466, over 972423.23 frames.], batch size: 28, lr: 2.52e-03
+2022-05-03 12:50:05,014 INFO [train.py:715] (3/8) Epoch 0, batch 5100, loss[loss=0.1728, simple_loss=0.317, pruned_loss=0.1432, over 4809.00 frames.], tot_loss[loss=0.1712, simple_loss=0.3132, pruned_loss=0.1459, over 971976.03 frames.], batch size: 25, lr: 2.51e-03
+2022-05-03 12:50:48,213 INFO [train.py:715] (3/8) Epoch 0, batch 5150, loss[loss=0.1884, simple_loss=0.3418, pruned_loss=0.1747, over 4905.00 frames.], tot_loss[loss=0.171, simple_loss=0.313, pruned_loss=0.1455, over 972786.56 frames.], batch size: 19, lr: 2.50e-03
+2022-05-03 12:51:28,076 INFO [train.py:715] (3/8) Epoch 0, batch 5200, loss[loss=0.1912, simple_loss=0.3499, pruned_loss=0.1623, over 4955.00 frames.], tot_loss[loss=0.1704, simple_loss=0.3119, pruned_loss=0.1448, over 972917.49 frames.], batch size: 24, lr: 2.50e-03
+2022-05-03 12:52:08,692 INFO [train.py:715] (3/8) Epoch 0, batch 5250, loss[loss=0.1805, simple_loss=0.3281, pruned_loss=0.1644, over 4897.00 frames.], tot_loss[loss=0.1705, simple_loss=0.3121, pruned_loss=0.1445, over 971717.98 frames.], batch size: 19, lr: 2.49e-03
+2022-05-03 12:52:49,809 INFO [train.py:715] (3/8) Epoch 0, batch 5300, loss[loss=0.1519, simple_loss=0.2831, pruned_loss=0.1034, over 4936.00 frames.], tot_loss[loss=0.1701, simple_loss=0.3116, pruned_loss=0.143, over 971555.78 frames.], batch size: 29, lr: 2.49e-03
+2022-05-03 12:53:30,339 INFO [train.py:715] (3/8) Epoch 0, batch 5350, loss[loss=0.1664, simple_loss=0.3065, pruned_loss=0.1321, over 4953.00 frames.], tot_loss[loss=0.1697, simple_loss=0.311, pruned_loss=0.1418, over 972094.52 frames.], batch size: 21, lr: 2.48e-03
+2022-05-03 12:54:10,011 INFO [train.py:715] (3/8) Epoch 0, batch 5400, loss[loss=0.1811, simple_loss=0.3288, pruned_loss=0.1671, over 4928.00 frames.], tot_loss[loss=0.1687, simple_loss=0.3093, pruned_loss=0.1403, over 972685.53 frames.], batch size: 39, lr: 2.47e-03
+2022-05-03 12:54:50,446 INFO [train.py:715] (3/8) Epoch 0, batch 5450, loss[loss=0.1726, simple_loss=0.3133, pruned_loss=0.1596, over 4913.00 frames.], tot_loss[loss=0.1686, simple_loss=0.3092, pruned_loss=0.1399, over 973546.48 frames.], batch size: 18, lr: 2.47e-03
+2022-05-03 12:55:31,399 INFO [train.py:715] (3/8) Epoch 0, batch 5500, loss[loss=0.1839, simple_loss=0.3345, pruned_loss=0.1664, over 4820.00 frames.], tot_loss[loss=0.1692, simple_loss=0.3104, pruned_loss=0.1403, over 973373.28 frames.], batch size: 15, lr: 2.46e-03
+2022-05-03 12:56:11,117 INFO [train.py:715] (3/8) Epoch 0, batch 5550, loss[loss=0.1689, simple_loss=0.3119, pruned_loss=0.13, over 4938.00 frames.], tot_loss[loss=0.169, simple_loss=0.31, pruned_loss=0.14, over 973870.41 frames.], batch size: 24, lr: 2.45e-03
+2022-05-03 12:56:51,155 INFO [train.py:715] (3/8) Epoch 0, batch 5600, loss[loss=0.175, simple_loss=0.314, pruned_loss=0.18, over 4814.00 frames.], tot_loss[loss=0.1684, simple_loss=0.3089, pruned_loss=0.1391, over 972742.94 frames.], batch size: 14, lr: 2.45e-03
+2022-05-03 12:57:32,353 INFO [train.py:715] (3/8) Epoch 0, batch 5650, loss[loss=0.1583, simple_loss=0.2947, pruned_loss=0.1095, over 4797.00 frames.], tot_loss[loss=0.1674, simple_loss=0.3075, pruned_loss=0.137, over 971995.23 frames.], batch size: 21, lr: 2.44e-03
+2022-05-03 12:58:12,915 INFO [train.py:715] (3/8) Epoch 0, batch 5700, loss[loss=0.1996, simple_loss=0.3631, pruned_loss=0.1806, over 4918.00 frames.], tot_loss[loss=0.1675, simple_loss=0.3076, pruned_loss=0.1371, over 972013.92 frames.], batch size: 39, lr: 2.44e-03
+2022-05-03 12:58:52,121 INFO [train.py:715] (3/8) Epoch 0, batch 5750, loss[loss=0.1583, simple_loss=0.2929, pruned_loss=0.1184, over 4755.00 frames.], tot_loss[loss=0.167, simple_loss=0.3067, pruned_loss=0.1362, over 972277.04 frames.], batch size: 19, lr: 2.43e-03
+2022-05-03 12:59:33,127 INFO [train.py:715] (3/8) Epoch 0, batch 5800, loss[loss=0.1907, simple_loss=0.3414, pruned_loss=0.1999, over 4874.00 frames.], tot_loss[loss=0.1667, simple_loss=0.3063, pruned_loss=0.1353, over 972466.42 frames.], batch size: 16, lr: 2.42e-03
+2022-05-03 13:00:14,312 INFO [train.py:715] (3/8) Epoch 0, batch 5850, loss[loss=0.1712, simple_loss=0.3148, pruned_loss=0.1376, over 4860.00 frames.], tot_loss[loss=0.1665, simple_loss=0.306, pruned_loss=0.1348, over 972697.14 frames.], batch size: 20, lr: 2.42e-03
+2022-05-03 13:00:54,230 INFO [train.py:715] (3/8) Epoch 0, batch 5900, loss[loss=0.1685, simple_loss=0.3111, pruned_loss=0.13, over 4821.00 frames.], tot_loss[loss=0.1659, simple_loss=0.3052, pruned_loss=0.1335, over 971741.19 frames.], batch size: 26, lr: 2.41e-03
+2022-05-03 13:01:33,975 INFO [train.py:715] (3/8) Epoch 0, batch 5950, loss[loss=0.1415, simple_loss=0.2654, pruned_loss=0.08824, over 4708.00 frames.], tot_loss[loss=0.1652, simple_loss=0.3039, pruned_loss=0.1326, over 971611.33 frames.], batch size: 15, lr: 2.41e-03
+2022-05-03 13:02:14,772 INFO [train.py:715] (3/8) Epoch 0, batch 6000, loss[loss=0.2312, simple_loss=0.2718, pruned_loss=0.09535, over 4907.00 frames.], tot_loss[loss=0.1662, simple_loss=0.3038, pruned_loss=0.1324, over 972049.26 frames.], batch size: 17, lr: 2.40e-03
+2022-05-03 13:02:14,773 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 13:02:25,809 INFO [train.py:742] (3/8) Epoch 0, validation: loss=0.1779, simple_loss=0.2457, pruned_loss=0.05502, over 914524.00 frames.
+2022-05-03 13:03:07,305 INFO [train.py:715] (3/8) Epoch 0, batch 6050, loss[loss=0.3108, simple_loss=0.3262, pruned_loss=0.1478, over 4910.00 frames.], tot_loss[loss=0.1979, simple_loss=0.3064, pruned_loss=0.1366, over 972537.45 frames.], batch size: 17, lr: 2.39e-03
+2022-05-03 13:03:47,837 INFO [train.py:715] (3/8) Epoch 0, batch 6100, loss[loss=0.3931, simple_loss=0.3823, pruned_loss=0.202, over 4794.00 frames.], tot_loss[loss=0.22, simple_loss=0.3078, pruned_loss=0.1376, over 972727.43 frames.], batch size: 21, lr: 2.39e-03
+2022-05-03 13:04:27,368 INFO [train.py:715] (3/8) Epoch 0, batch 6150, loss[loss=0.321, simple_loss=0.3331, pruned_loss=0.1545, over 4800.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3089, pruned_loss=0.1377, over 971712.14 frames.], batch size: 21, lr: 2.38e-03
+2022-05-03 13:05:08,101 INFO [train.py:715] (3/8) Epoch 0, batch 6200, loss[loss=0.2907, simple_loss=0.3156, pruned_loss=0.1329, over 4943.00 frames.], tot_loss[loss=0.248, simple_loss=0.309, pruned_loss=0.1369, over 971815.72 frames.], batch size: 29, lr: 2.38e-03
+2022-05-03 13:05:48,912 INFO [train.py:715] (3/8) Epoch 0, batch 6250, loss[loss=0.2845, simple_loss=0.3063, pruned_loss=0.1314, over 4872.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3081, pruned_loss=0.1348, over 971457.13 frames.], batch size: 20, lr: 2.37e-03
+2022-05-03 13:06:29,111 INFO [train.py:715] (3/8) Epoch 0, batch 6300, loss[loss=0.3008, simple_loss=0.317, pruned_loss=0.1423, over 4865.00 frames.], tot_loss[loss=0.2615, simple_loss=0.308, pruned_loss=0.1338, over 971008.03 frames.], batch size: 30, lr: 2.37e-03
+2022-05-03 13:07:09,789 INFO [train.py:715] (3/8) Epoch 0, batch 6350, loss[loss=0.299, simple_loss=0.3275, pruned_loss=0.1353, over 4797.00 frames.], tot_loss[loss=0.2662, simple_loss=0.3081, pruned_loss=0.1326, over 971091.79 frames.], batch size: 21, lr: 2.36e-03
+2022-05-03 13:07:50,712 INFO [train.py:715] (3/8) Epoch 0, batch 6400, loss[loss=0.2742, simple_loss=0.2793, pruned_loss=0.1345, over 4841.00 frames.], tot_loss[loss=0.2708, simple_loss=0.3083, pruned_loss=0.1326, over 971621.47 frames.], batch size: 12, lr: 2.35e-03
+2022-05-03 13:08:30,733 INFO [train.py:715] (3/8) Epoch 0, batch 6450, loss[loss=0.2507, simple_loss=0.2931, pruned_loss=0.1042, over 4939.00 frames.], tot_loss[loss=0.2716, simple_loss=0.3067, pruned_loss=0.1306, over 972225.43 frames.], batch size: 18, lr: 2.35e-03
+2022-05-03 13:09:10,061 INFO [train.py:715] (3/8) Epoch 0, batch 6500, loss[loss=0.3279, simple_loss=0.3467, pruned_loss=0.1546, over 4951.00 frames.], tot_loss[loss=0.2728, simple_loss=0.3061, pruned_loss=0.1294, over 972059.73 frames.], batch size: 21, lr: 2.34e-03
+2022-05-03 13:09:50,931 INFO [train.py:715] (3/8) Epoch 0, batch 6550, loss[loss=0.285, simple_loss=0.3128, pruned_loss=0.1286, over 4802.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3064, pruned_loss=0.1292, over 972577.76 frames.], batch size: 25, lr: 2.34e-03
+2022-05-03 13:10:31,732 INFO [train.py:715] (3/8) Epoch 0, batch 6600, loss[loss=0.3148, simple_loss=0.3169, pruned_loss=0.1563, over 4776.00 frames.], tot_loss[loss=0.2782, simple_loss=0.3081, pruned_loss=0.13, over 972746.29 frames.], batch size: 18, lr: 2.33e-03
+2022-05-03 13:11:11,205 INFO [train.py:715] (3/8) Epoch 0, batch 6650, loss[loss=0.2412, simple_loss=0.2805, pruned_loss=0.1009, over 4817.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3072, pruned_loss=0.1286, over 972747.32 frames.], batch size: 26, lr: 2.33e-03
+2022-05-03 13:11:51,646 INFO [train.py:715] (3/8) Epoch 0, batch 6700, loss[loss=0.2219, simple_loss=0.2608, pruned_loss=0.09148, over 4938.00 frames.], tot_loss[loss=0.277, simple_loss=0.3064, pruned_loss=0.1273, over 972960.59 frames.], batch size: 29, lr: 2.32e-03
+2022-05-03 13:12:32,417 INFO [train.py:715] (3/8) Epoch 0, batch 6750, loss[loss=0.2363, simple_loss=0.2808, pruned_loss=0.09588, over 4814.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3068, pruned_loss=0.1274, over 972861.71 frames.], batch size: 26, lr: 2.31e-03
+2022-05-03 13:13:12,491 INFO [train.py:715] (3/8) Epoch 0, batch 6800, loss[loss=0.3366, simple_loss=0.3395, pruned_loss=0.1668, over 4848.00 frames.], tot_loss[loss=0.2773, simple_loss=0.3061, pruned_loss=0.1264, over 972923.90 frames.], batch size: 30, lr: 2.31e-03
+2022-05-03 13:13:52,208 INFO [train.py:715] (3/8) Epoch 0, batch 6850, loss[loss=0.2992, simple_loss=0.3322, pruned_loss=0.1331, over 4933.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3066, pruned_loss=0.1261, over 973336.28 frames.], batch size: 23, lr: 2.30e-03
+2022-05-03 13:14:32,484 INFO [train.py:715] (3/8) Epoch 0, batch 6900, loss[loss=0.2089, simple_loss=0.2619, pruned_loss=0.078, over 4988.00 frames.], tot_loss[loss=0.2789, simple_loss=0.3071, pruned_loss=0.1266, over 973584.28 frames.], batch size: 28, lr: 2.30e-03
+2022-05-03 13:15:12,909 INFO [train.py:715] (3/8) Epoch 0, batch 6950, loss[loss=0.2978, simple_loss=0.3274, pruned_loss=0.1341, over 4932.00 frames.], tot_loss[loss=0.2793, simple_loss=0.3079, pruned_loss=0.1264, over 973533.56 frames.], batch size: 18, lr: 2.29e-03
+2022-05-03 13:15:53,027 INFO [train.py:715] (3/8) Epoch 0, batch 7000, loss[loss=0.2694, simple_loss=0.3058, pruned_loss=0.1165, over 4751.00 frames.], tot_loss[loss=0.2771, simple_loss=0.3063, pruned_loss=0.1247, over 973064.42 frames.], batch size: 19, lr: 2.29e-03
+2022-05-03 13:16:33,735 INFO [train.py:715] (3/8) Epoch 0, batch 7050, loss[loss=0.2794, simple_loss=0.311, pruned_loss=0.124, over 4790.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3053, pruned_loss=0.1236, over 973446.35 frames.], batch size: 17, lr: 2.28e-03
+2022-05-03 13:17:14,921 INFO [train.py:715] (3/8) Epoch 0, batch 7100, loss[loss=0.3054, simple_loss=0.3256, pruned_loss=0.1426, over 4843.00 frames.], tot_loss[loss=0.2769, simple_loss=0.306, pruned_loss=0.1244, over 973202.64 frames.], batch size: 20, lr: 2.28e-03
+2022-05-03 13:17:55,866 INFO [train.py:715] (3/8) Epoch 0, batch 7150, loss[loss=0.3199, simple_loss=0.3365, pruned_loss=0.1516, over 4875.00 frames.], tot_loss[loss=0.2766, simple_loss=0.3061, pruned_loss=0.1239, over 972841.66 frames.], batch size: 39, lr: 2.27e-03
+2022-05-03 13:18:35,508 INFO [train.py:715] (3/8) Epoch 0, batch 7200, loss[loss=0.3182, simple_loss=0.3265, pruned_loss=0.1549, over 4854.00 frames.], tot_loss[loss=0.275, simple_loss=0.3055, pruned_loss=0.1225, over 973396.90 frames.], batch size: 20, lr: 2.27e-03
+2022-05-03 13:19:16,088 INFO [train.py:715] (3/8) Epoch 0, batch 7250, loss[loss=0.2506, simple_loss=0.2892, pruned_loss=0.106, over 4855.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3054, pruned_loss=0.1224, over 974031.69 frames.], batch size: 32, lr: 2.26e-03
+2022-05-03 13:19:55,967 INFO [train.py:715] (3/8) Epoch 0, batch 7300, loss[loss=0.2542, simple_loss=0.2973, pruned_loss=0.1056, over 4920.00 frames.], tot_loss[loss=0.2769, simple_loss=0.3069, pruned_loss=0.1236, over 974845.74 frames.], batch size: 19, lr: 2.26e-03
+2022-05-03 13:20:36,061 INFO [train.py:715] (3/8) Epoch 0, batch 7350, loss[loss=0.2796, simple_loss=0.2998, pruned_loss=0.1297, over 4780.00 frames.], tot_loss[loss=0.2768, simple_loss=0.3071, pruned_loss=0.1234, over 974604.52 frames.], batch size: 17, lr: 2.25e-03
+2022-05-03 13:21:16,434 INFO [train.py:715] (3/8) Epoch 0, batch 7400, loss[loss=0.2848, simple_loss=0.3226, pruned_loss=0.1235, over 4967.00 frames.], tot_loss[loss=0.2771, simple_loss=0.3076, pruned_loss=0.1234, over 974560.26 frames.], batch size: 15, lr: 2.24e-03
+2022-05-03 13:21:57,035 INFO [train.py:715] (3/8) Epoch 0, batch 7450, loss[loss=0.257, simple_loss=0.2907, pruned_loss=0.1117, over 4881.00 frames.], tot_loss[loss=0.276, simple_loss=0.3072, pruned_loss=0.1225, over 974707.07 frames.], batch size: 22, lr: 2.24e-03
+2022-05-03 13:22:36,836 INFO [train.py:715] (3/8) Epoch 0, batch 7500, loss[loss=0.2779, simple_loss=0.3222, pruned_loss=0.1168, over 4896.00 frames.], tot_loss[loss=0.2752, simple_loss=0.3064, pruned_loss=0.122, over 974692.62 frames.], batch size: 19, lr: 2.23e-03
+2022-05-03 13:23:16,561 INFO [train.py:715] (3/8) Epoch 0, batch 7550, loss[loss=0.3085, simple_loss=0.3462, pruned_loss=0.1354, over 4797.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3063, pruned_loss=0.1218, over 974963.97 frames.], batch size: 21, lr: 2.23e-03
+2022-05-03 13:23:57,043 INFO [train.py:715] (3/8) Epoch 0, batch 7600, loss[loss=0.2713, simple_loss=0.3126, pruned_loss=0.115, over 4987.00 frames.], tot_loss[loss=0.275, simple_loss=0.3067, pruned_loss=0.1217, over 974550.95 frames.], batch size: 28, lr: 2.22e-03
+2022-05-03 13:24:37,496 INFO [train.py:715] (3/8) Epoch 0, batch 7650, loss[loss=0.2456, simple_loss=0.3055, pruned_loss=0.09283, over 4863.00 frames.], tot_loss[loss=0.275, simple_loss=0.3068, pruned_loss=0.1216, over 974845.27 frames.], batch size: 20, lr: 2.22e-03
+2022-05-03 13:25:16,988 INFO [train.py:715] (3/8) Epoch 0, batch 7700, loss[loss=0.219, simple_loss=0.2715, pruned_loss=0.08325, over 4965.00 frames.], tot_loss[loss=0.2734, simple_loss=0.3058, pruned_loss=0.1205, over 974372.68 frames.], batch size: 15, lr: 2.21e-03
+2022-05-03 13:25:57,318 INFO [train.py:715] (3/8) Epoch 0, batch 7750, loss[loss=0.2397, simple_loss=0.2859, pruned_loss=0.09674, over 4985.00 frames.], tot_loss[loss=0.2709, simple_loss=0.3043, pruned_loss=0.1187, over 974033.83 frames.], batch size: 14, lr: 2.21e-03
+2022-05-03 13:26:38,376 INFO [train.py:715] (3/8) Epoch 0, batch 7800, loss[loss=0.2616, simple_loss=0.2944, pruned_loss=0.1143, over 4854.00 frames.], tot_loss[loss=0.2696, simple_loss=0.3037, pruned_loss=0.1177, over 973359.32 frames.], batch size: 32, lr: 2.20e-03
+2022-05-03 13:27:18,725 INFO [train.py:715] (3/8) Epoch 0, batch 7850, loss[loss=0.3152, simple_loss=0.3402, pruned_loss=0.1451, over 4938.00 frames.], tot_loss[loss=0.2704, simple_loss=0.3046, pruned_loss=0.1181, over 973976.28 frames.], batch size: 35, lr: 2.20e-03
+2022-05-03 13:27:58,876 INFO [train.py:715] (3/8) Epoch 0, batch 7900, loss[loss=0.2662, simple_loss=0.3068, pruned_loss=0.1128, over 4969.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3034, pruned_loss=0.1164, over 974115.19 frames.], batch size: 24, lr: 2.19e-03
+2022-05-03 13:28:39,525 INFO [train.py:715] (3/8) Epoch 0, batch 7950, loss[loss=0.2747, simple_loss=0.3067, pruned_loss=0.1214, over 4983.00 frames.], tot_loss[loss=0.267, simple_loss=0.3023, pruned_loss=0.1158, over 973436.29 frames.], batch size: 28, lr: 2.19e-03
+2022-05-03 13:29:22,243 INFO [train.py:715] (3/8) Epoch 0, batch 8000, loss[loss=0.2189, simple_loss=0.2741, pruned_loss=0.08192, over 4861.00 frames.], tot_loss[loss=0.267, simple_loss=0.3023, pruned_loss=0.1159, over 972865.49 frames.], batch size: 32, lr: 2.18e-03
+2022-05-03 13:30:02,106 INFO [train.py:715] (3/8) Epoch 0, batch 8050, loss[loss=0.3802, simple_loss=0.3976, pruned_loss=0.1814, over 4814.00 frames.], tot_loss[loss=0.2686, simple_loss=0.3035, pruned_loss=0.1168, over 973332.54 frames.], batch size: 25, lr: 2.18e-03
+2022-05-03 13:30:41,975 INFO [train.py:715] (3/8) Epoch 0, batch 8100, loss[loss=0.2249, simple_loss=0.2673, pruned_loss=0.09124, over 4894.00 frames.], tot_loss[loss=0.2679, simple_loss=0.3032, pruned_loss=0.1164, over 973364.08 frames.], batch size: 19, lr: 2.17e-03
+2022-05-03 13:31:22,996 INFO [train.py:715] (3/8) Epoch 0, batch 8150, loss[loss=0.2581, simple_loss=0.3044, pruned_loss=0.1059, over 4809.00 frames.], tot_loss[loss=0.2686, simple_loss=0.3038, pruned_loss=0.1167, over 973248.66 frames.], batch size: 21, lr: 2.17e-03
+2022-05-03 13:32:02,625 INFO [train.py:715] (3/8) Epoch 0, batch 8200, loss[loss=0.2578, simple_loss=0.3035, pruned_loss=0.106, over 4891.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3042, pruned_loss=0.1168, over 973109.07 frames.], batch size: 22, lr: 2.16e-03
+2022-05-03 13:32:42,133 INFO [train.py:715] (3/8) Epoch 0, batch 8250, loss[loss=0.3064, simple_loss=0.3402, pruned_loss=0.1363, over 4852.00 frames.], tot_loss[loss=0.2688, simple_loss=0.3043, pruned_loss=0.1167, over 973672.85 frames.], batch size: 30, lr: 2.16e-03
+2022-05-03 13:33:22,995 INFO [train.py:715] (3/8) Epoch 0, batch 8300, loss[loss=0.2871, simple_loss=0.3256, pruned_loss=0.1244, over 4983.00 frames.], tot_loss[loss=0.2676, simple_loss=0.3034, pruned_loss=0.1159, over 974562.86 frames.], batch size: 14, lr: 2.15e-03
+2022-05-03 13:34:03,424 INFO [train.py:715] (3/8) Epoch 0, batch 8350, loss[loss=0.2755, simple_loss=0.3127, pruned_loss=0.1191, over 4782.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3026, pruned_loss=0.1156, over 973229.40 frames.], batch size: 17, lr: 2.15e-03
+2022-05-03 13:34:43,095 INFO [train.py:715] (3/8) Epoch 0, batch 8400, loss[loss=0.2711, simple_loss=0.2994, pruned_loss=0.1214, over 4861.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3034, pruned_loss=0.1158, over 974022.95 frames.], batch size: 20, lr: 2.15e-03
+2022-05-03 13:35:23,380 INFO [train.py:715] (3/8) Epoch 0, batch 8450, loss[loss=0.3113, simple_loss=0.3316, pruned_loss=0.1456, over 4790.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3009, pruned_loss=0.1132, over 972684.28 frames.], batch size: 17, lr: 2.14e-03
+2022-05-03 13:36:04,636 INFO [train.py:715] (3/8) Epoch 0, batch 8500, loss[loss=0.2639, simple_loss=0.2977, pruned_loss=0.1151, over 4853.00 frames.], tot_loss[loss=0.2641, simple_loss=0.3007, pruned_loss=0.1137, over 972094.54 frames.], batch size: 32, lr: 2.14e-03
+2022-05-03 13:36:45,703 INFO [train.py:715] (3/8) Epoch 0, batch 8550, loss[loss=0.2554, simple_loss=0.31, pruned_loss=0.1003, over 4805.00 frames.], tot_loss[loss=0.2647, simple_loss=0.3014, pruned_loss=0.114, over 972281.99 frames.], batch size: 21, lr: 2.13e-03
+2022-05-03 13:37:25,351 INFO [train.py:715] (3/8) Epoch 0, batch 8600, loss[loss=0.2555, simple_loss=0.2972, pruned_loss=0.1069, over 4869.00 frames.], tot_loss[loss=0.2643, simple_loss=0.3009, pruned_loss=0.1139, over 971583.31 frames.], batch size: 16, lr: 2.13e-03
+2022-05-03 13:38:06,730 INFO [train.py:715] (3/8) Epoch 0, batch 8650, loss[loss=0.243, simple_loss=0.2932, pruned_loss=0.09643, over 4879.00 frames.], tot_loss[loss=0.2634, simple_loss=0.3003, pruned_loss=0.1133, over 972029.33 frames.], batch size: 16, lr: 2.12e-03
+2022-05-03 13:38:47,676 INFO [train.py:715] (3/8) Epoch 0, batch 8700, loss[loss=0.2987, simple_loss=0.3132, pruned_loss=0.1421, over 4820.00 frames.], tot_loss[loss=0.2653, simple_loss=0.3016, pruned_loss=0.1145, over 972060.71 frames.], batch size: 13, lr: 2.12e-03
+2022-05-03 13:39:27,755 INFO [train.py:715] (3/8) Epoch 0, batch 8750, loss[loss=0.2711, simple_loss=0.3086, pruned_loss=0.1168, over 4839.00 frames.], tot_loss[loss=0.2626, simple_loss=0.2998, pruned_loss=0.1127, over 972457.46 frames.], batch size: 30, lr: 2.11e-03
+2022-05-03 13:40:08,237 INFO [train.py:715] (3/8) Epoch 0, batch 8800, loss[loss=0.2577, simple_loss=0.2925, pruned_loss=0.1114, over 4755.00 frames.], tot_loss[loss=0.2639, simple_loss=0.301, pruned_loss=0.1134, over 972920.69 frames.], batch size: 16, lr: 2.11e-03
+2022-05-03 13:40:48,803 INFO [train.py:715] (3/8) Epoch 0, batch 8850, loss[loss=0.2551, simple_loss=0.2869, pruned_loss=0.1117, over 4772.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3012, pruned_loss=0.1132, over 972650.99 frames.], batch size: 18, lr: 2.10e-03
+2022-05-03 13:41:29,534 INFO [train.py:715] (3/8) Epoch 0, batch 8900, loss[loss=0.2302, simple_loss=0.2737, pruned_loss=0.09337, over 4916.00 frames.], tot_loss[loss=0.2625, simple_loss=0.3005, pruned_loss=0.1122, over 971951.76 frames.], batch size: 17, lr: 2.10e-03
+2022-05-03 13:42:09,365 INFO [train.py:715] (3/8) Epoch 0, batch 8950, loss[loss=0.3287, simple_loss=0.3467, pruned_loss=0.1553, over 4861.00 frames.], tot_loss[loss=0.262, simple_loss=0.2999, pruned_loss=0.1121, over 971431.86 frames.], batch size: 20, lr: 2.10e-03
+2022-05-03 13:42:49,916 INFO [train.py:715] (3/8) Epoch 0, batch 9000, loss[loss=0.2863, simple_loss=0.3178, pruned_loss=0.1274, over 4686.00 frames.], tot_loss[loss=0.2623, simple_loss=0.3005, pruned_loss=0.112, over 971697.15 frames.], batch size: 15, lr: 2.09e-03
+2022-05-03 13:42:49,917 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 13:43:03,384 INFO [train.py:742] (3/8) Epoch 0, validation: loss=0.1592, simple_loss=0.2426, pruned_loss=0.03794, over 914524.00 frames.
+2022-05-03 13:43:44,293 INFO [train.py:715] (3/8) Epoch 0, batch 9050, loss[loss=0.2066, simple_loss=0.2564, pruned_loss=0.07838, over 4792.00 frames.], tot_loss[loss=0.261, simple_loss=0.2995, pruned_loss=0.1112, over 971539.57 frames.], batch size: 12, lr: 2.09e-03
+2022-05-03 13:44:24,656 INFO [train.py:715] (3/8) Epoch 0, batch 9100, loss[loss=0.2619, simple_loss=0.3038, pruned_loss=0.11, over 4974.00 frames.], tot_loss[loss=0.2612, simple_loss=0.3002, pruned_loss=0.1111, over 971962.94 frames.], batch size: 24, lr: 2.08e-03
+2022-05-03 13:45:04,781 INFO [train.py:715] (3/8) Epoch 0, batch 9150, loss[loss=0.2205, simple_loss=0.2716, pruned_loss=0.08471, over 4813.00 frames.], tot_loss[loss=0.2592, simple_loss=0.2986, pruned_loss=0.1099, over 971685.46 frames.], batch size: 21, lr: 2.08e-03
+2022-05-03 13:45:44,978 INFO [train.py:715] (3/8) Epoch 0, batch 9200, loss[loss=0.2492, simple_loss=0.2919, pruned_loss=0.1033, over 4900.00 frames.], tot_loss[loss=0.2596, simple_loss=0.299, pruned_loss=0.1101, over 972434.56 frames.], batch size: 39, lr: 2.07e-03
+2022-05-03 13:46:26,065 INFO [train.py:715] (3/8) Epoch 0, batch 9250, loss[loss=0.2496, simple_loss=0.2939, pruned_loss=0.1026, over 4935.00 frames.], tot_loss[loss=0.2598, simple_loss=0.2989, pruned_loss=0.1104, over 971689.65 frames.], batch size: 21, lr: 2.07e-03
+2022-05-03 13:47:06,378 INFO [train.py:715] (3/8) Epoch 0, batch 9300, loss[loss=0.1981, simple_loss=0.2448, pruned_loss=0.07568, over 4782.00 frames.], tot_loss[loss=0.2613, simple_loss=0.2998, pruned_loss=0.1114, over 970801.58 frames.], batch size: 12, lr: 2.06e-03
+2022-05-03 13:47:45,665 INFO [train.py:715] (3/8) Epoch 0, batch 9350, loss[loss=0.308, simple_loss=0.3303, pruned_loss=0.1428, over 4638.00 frames.], tot_loss[loss=0.2591, simple_loss=0.299, pruned_loss=0.1096, over 970756.04 frames.], batch size: 13, lr: 2.06e-03
+2022-05-03 13:48:27,108 INFO [train.py:715] (3/8) Epoch 0, batch 9400, loss[loss=0.2905, simple_loss=0.3274, pruned_loss=0.1268, over 4971.00 frames.], tot_loss[loss=0.2606, simple_loss=0.3001, pruned_loss=0.1106, over 971785.03 frames.], batch size: 24, lr: 2.06e-03
+2022-05-03 13:49:07,596 INFO [train.py:715] (3/8) Epoch 0, batch 9450, loss[loss=0.2476, simple_loss=0.2873, pruned_loss=0.1039, over 4794.00 frames.], tot_loss[loss=0.2595, simple_loss=0.2993, pruned_loss=0.1099, over 971504.93 frames.], batch size: 17, lr: 2.05e-03
+2022-05-03 13:49:47,922 INFO [train.py:715] (3/8) Epoch 0, batch 9500, loss[loss=0.3218, simple_loss=0.3445, pruned_loss=0.1496, over 4873.00 frames.], tot_loss[loss=0.2573, simple_loss=0.2979, pruned_loss=0.1084, over 971388.42 frames.], batch size: 39, lr: 2.05e-03
+2022-05-03 13:50:28,006 INFO [train.py:715] (3/8) Epoch 0, batch 9550, loss[loss=0.2531, simple_loss=0.2899, pruned_loss=0.1082, over 4964.00 frames.], tot_loss[loss=0.2564, simple_loss=0.2967, pruned_loss=0.1081, over 971458.14 frames.], batch size: 24, lr: 2.04e-03
+2022-05-03 13:51:08,461 INFO [train.py:715] (3/8) Epoch 0, batch 9600, loss[loss=0.2506, simple_loss=0.2885, pruned_loss=0.1064, over 4747.00 frames.], tot_loss[loss=0.2569, simple_loss=0.2968, pruned_loss=0.1085, over 971593.57 frames.], batch size: 16, lr: 2.04e-03
+2022-05-03 13:51:48,903 INFO [train.py:715] (3/8) Epoch 0, batch 9650, loss[loss=0.2493, simple_loss=0.2933, pruned_loss=0.1026, over 4813.00 frames.], tot_loss[loss=0.2571, simple_loss=0.2971, pruned_loss=0.1086, over 972084.65 frames.], batch size: 26, lr: 2.03e-03
+2022-05-03 13:52:27,669 INFO [train.py:715] (3/8) Epoch 0, batch 9700, loss[loss=0.2538, simple_loss=0.2941, pruned_loss=0.1067, over 4978.00 frames.], tot_loss[loss=0.2586, simple_loss=0.2982, pruned_loss=0.1095, over 971407.36 frames.], batch size: 25, lr: 2.03e-03
+2022-05-03 13:53:08,237 INFO [train.py:715] (3/8) Epoch 0, batch 9750, loss[loss=0.2698, simple_loss=0.3044, pruned_loss=0.1176, over 4897.00 frames.], tot_loss[loss=0.257, simple_loss=0.2974, pruned_loss=0.1083, over 971558.94 frames.], batch size: 22, lr: 2.03e-03
+2022-05-03 13:53:47,972 INFO [train.py:715] (3/8) Epoch 0, batch 9800, loss[loss=0.236, simple_loss=0.278, pruned_loss=0.09701, over 4983.00 frames.], tot_loss[loss=0.2568, simple_loss=0.2974, pruned_loss=0.1081, over 971614.10 frames.], batch size: 28, lr: 2.02e-03
+2022-05-03 13:54:27,874 INFO [train.py:715] (3/8) Epoch 0, batch 9850, loss[loss=0.1831, simple_loss=0.232, pruned_loss=0.06707, over 4829.00 frames.], tot_loss[loss=0.2544, simple_loss=0.2952, pruned_loss=0.1068, over 971623.68 frames.], batch size: 13, lr: 2.02e-03
+2022-05-03 13:55:07,631 INFO [train.py:715] (3/8) Epoch 0, batch 9900, loss[loss=0.2333, simple_loss=0.2769, pruned_loss=0.09479, over 4749.00 frames.], tot_loss[loss=0.2539, simple_loss=0.2959, pruned_loss=0.106, over 971322.71 frames.], batch size: 19, lr: 2.01e-03
+2022-05-03 13:55:47,708 INFO [train.py:715] (3/8) Epoch 0, batch 9950, loss[loss=0.3031, simple_loss=0.3308, pruned_loss=0.1377, over 4865.00 frames.], tot_loss[loss=0.2537, simple_loss=0.2958, pruned_loss=0.1058, over 971297.21 frames.], batch size: 34, lr: 2.01e-03
+2022-05-03 13:56:27,932 INFO [train.py:715] (3/8) Epoch 0, batch 10000, loss[loss=0.2493, simple_loss=0.2909, pruned_loss=0.1038, over 4810.00 frames.], tot_loss[loss=0.2549, simple_loss=0.2965, pruned_loss=0.1066, over 971804.16 frames.], batch size: 25, lr: 2.01e-03
+2022-05-03 13:57:07,304 INFO [train.py:715] (3/8) Epoch 0, batch 10050, loss[loss=0.2223, simple_loss=0.2688, pruned_loss=0.08784, over 4976.00 frames.], tot_loss[loss=0.2531, simple_loss=0.2951, pruned_loss=0.1056, over 972138.86 frames.], batch size: 15, lr: 2.00e-03
+2022-05-03 13:57:47,854 INFO [train.py:715] (3/8) Epoch 0, batch 10100, loss[loss=0.2315, simple_loss=0.2728, pruned_loss=0.09514, over 4928.00 frames.], tot_loss[loss=0.2539, simple_loss=0.2959, pruned_loss=0.1059, over 972837.57 frames.], batch size: 18, lr: 2.00e-03
+2022-05-03 13:58:27,700 INFO [train.py:715] (3/8) Epoch 0, batch 10150, loss[loss=0.2634, simple_loss=0.3062, pruned_loss=0.1103, over 4929.00 frames.], tot_loss[loss=0.2534, simple_loss=0.2955, pruned_loss=0.1056, over 972829.31 frames.], batch size: 21, lr: 1.99e-03
+2022-05-03 13:59:07,279 INFO [train.py:715] (3/8) Epoch 0, batch 10200, loss[loss=0.2566, simple_loss=0.3044, pruned_loss=0.1044, over 4815.00 frames.], tot_loss[loss=0.2528, simple_loss=0.2952, pruned_loss=0.1052, over 972306.67 frames.], batch size: 27, lr: 1.99e-03
+2022-05-03 13:59:47,201 INFO [train.py:715] (3/8) Epoch 0, batch 10250, loss[loss=0.2112, simple_loss=0.266, pruned_loss=0.0782, over 4889.00 frames.], tot_loss[loss=0.254, simple_loss=0.2967, pruned_loss=0.1057, over 972178.63 frames.], batch size: 22, lr: 1.99e-03
+2022-05-03 14:00:28,089 INFO [train.py:715] (3/8) Epoch 0, batch 10300, loss[loss=0.2282, simple_loss=0.2696, pruned_loss=0.09343, over 4939.00 frames.], tot_loss[loss=0.2552, simple_loss=0.2976, pruned_loss=0.1063, over 971836.54 frames.], batch size: 29, lr: 1.98e-03
+2022-05-03 14:01:08,345 INFO [train.py:715] (3/8) Epoch 0, batch 10350, loss[loss=0.3142, simple_loss=0.3438, pruned_loss=0.1423, over 4940.00 frames.], tot_loss[loss=0.2561, simple_loss=0.2982, pruned_loss=0.107, over 973238.32 frames.], batch size: 21, lr: 1.98e-03
+2022-05-03 14:01:47,803 INFO [train.py:715] (3/8) Epoch 0, batch 10400, loss[loss=0.2565, simple_loss=0.2944, pruned_loss=0.1093, over 4800.00 frames.], tot_loss[loss=0.2567, simple_loss=0.2982, pruned_loss=0.1076, over 972464.10 frames.], batch size: 21, lr: 1.97e-03
+2022-05-03 14:02:28,433 INFO [train.py:715] (3/8) Epoch 0, batch 10450, loss[loss=0.2678, simple_loss=0.3007, pruned_loss=0.1175, over 4845.00 frames.], tot_loss[loss=0.2548, simple_loss=0.2968, pruned_loss=0.1064, over 972139.93 frames.], batch size: 15, lr: 1.97e-03
+2022-05-03 14:03:09,175 INFO [train.py:715] (3/8) Epoch 0, batch 10500, loss[loss=0.2953, simple_loss=0.3097, pruned_loss=0.1405, over 4958.00 frames.], tot_loss[loss=0.2552, simple_loss=0.2969, pruned_loss=0.1067, over 972144.40 frames.], batch size: 29, lr: 1.97e-03
+2022-05-03 14:03:48,865 INFO [train.py:715] (3/8) Epoch 0, batch 10550, loss[loss=0.2071, simple_loss=0.2711, pruned_loss=0.0716, over 4815.00 frames.], tot_loss[loss=0.2528, simple_loss=0.2951, pruned_loss=0.1053, over 972052.12 frames.], batch size: 21, lr: 1.96e-03
+2022-05-03 14:04:28,873 INFO [train.py:715] (3/8) Epoch 0, batch 10600, loss[loss=0.2985, simple_loss=0.3273, pruned_loss=0.1349, over 4987.00 frames.], tot_loss[loss=0.2521, simple_loss=0.2949, pruned_loss=0.1046, over 971349.23 frames.], batch size: 26, lr: 1.96e-03
+2022-05-03 14:05:09,746 INFO [train.py:715] (3/8) Epoch 0, batch 10650, loss[loss=0.273, simple_loss=0.3011, pruned_loss=0.1224, over 4792.00 frames.], tot_loss[loss=0.2511, simple_loss=0.294, pruned_loss=0.1041, over 971673.50 frames.], batch size: 17, lr: 1.96e-03
+2022-05-03 14:05:49,653 INFO [train.py:715] (3/8) Epoch 0, batch 10700, loss[loss=0.2813, simple_loss=0.308, pruned_loss=0.1273, over 4975.00 frames.], tot_loss[loss=0.2523, simple_loss=0.2945, pruned_loss=0.105, over 971084.42 frames.], batch size: 31, lr: 1.95e-03
+2022-05-03 14:06:29,544 INFO [train.py:715] (3/8) Epoch 0, batch 10750, loss[loss=0.2828, simple_loss=0.322, pruned_loss=0.1218, over 4876.00 frames.], tot_loss[loss=0.2525, simple_loss=0.2947, pruned_loss=0.1051, over 969651.04 frames.], batch size: 16, lr: 1.95e-03
+2022-05-03 14:07:09,720 INFO [train.py:715] (3/8) Epoch 0, batch 10800, loss[loss=0.252, simple_loss=0.3064, pruned_loss=0.09881, over 4807.00 frames.], tot_loss[loss=0.2506, simple_loss=0.2933, pruned_loss=0.104, over 970730.61 frames.], batch size: 21, lr: 1.94e-03
+2022-05-03 14:07:50,565 INFO [train.py:715] (3/8) Epoch 0, batch 10850, loss[loss=0.2366, simple_loss=0.2869, pruned_loss=0.09311, over 4827.00 frames.], tot_loss[loss=0.2494, simple_loss=0.2927, pruned_loss=0.1031, over 971638.12 frames.], batch size: 13, lr: 1.94e-03
+2022-05-03 14:08:30,098 INFO [train.py:715] (3/8) Epoch 0, batch 10900, loss[loss=0.2471, simple_loss=0.2967, pruned_loss=0.09881, over 4948.00 frames.], tot_loss[loss=0.2477, simple_loss=0.2917, pruned_loss=0.1018, over 971755.12 frames.], batch size: 21, lr: 1.94e-03
+2022-05-03 14:09:10,035 INFO [train.py:715] (3/8) Epoch 0, batch 10950, loss[loss=0.2097, simple_loss=0.265, pruned_loss=0.07724, over 4951.00 frames.], tot_loss[loss=0.2482, simple_loss=0.2919, pruned_loss=0.1023, over 971765.61 frames.], batch size: 29, lr: 1.93e-03
+2022-05-03 14:09:50,810 INFO [train.py:715] (3/8) Epoch 0, batch 11000, loss[loss=0.26, simple_loss=0.322, pruned_loss=0.09906, over 4829.00 frames.], tot_loss[loss=0.2472, simple_loss=0.2915, pruned_loss=0.1014, over 971078.69 frames.], batch size: 15, lr: 1.93e-03
+2022-05-03 14:10:31,098 INFO [train.py:715] (3/8) Epoch 0, batch 11050, loss[loss=0.2877, simple_loss=0.3325, pruned_loss=0.1214, over 4936.00 frames.], tot_loss[loss=0.2461, simple_loss=0.2902, pruned_loss=0.101, over 971327.69 frames.], batch size: 29, lr: 1.93e-03
+2022-05-03 14:11:11,140 INFO [train.py:715] (3/8) Epoch 0, batch 11100, loss[loss=0.2507, simple_loss=0.302, pruned_loss=0.09967, over 4785.00 frames.], tot_loss[loss=0.2469, simple_loss=0.2907, pruned_loss=0.1016, over 971039.69 frames.], batch size: 17, lr: 1.92e-03
+2022-05-03 14:11:51,015 INFO [train.py:715] (3/8) Epoch 0, batch 11150, loss[loss=0.281, simple_loss=0.3184, pruned_loss=0.1218, over 4844.00 frames.], tot_loss[loss=0.2479, simple_loss=0.2916, pruned_loss=0.1022, over 971651.91 frames.], batch size: 32, lr: 1.92e-03
+2022-05-03 14:12:31,463 INFO [train.py:715] (3/8) Epoch 0, batch 11200, loss[loss=0.2362, simple_loss=0.294, pruned_loss=0.08917, over 4825.00 frames.], tot_loss[loss=0.2468, simple_loss=0.2909, pruned_loss=0.1014, over 971490.05 frames.], batch size: 25, lr: 1.92e-03
+2022-05-03 14:13:10,940 INFO [train.py:715] (3/8) Epoch 0, batch 11250, loss[loss=0.2144, simple_loss=0.2658, pruned_loss=0.08152, over 4851.00 frames.], tot_loss[loss=0.2439, simple_loss=0.2892, pruned_loss=0.09931, over 971935.09 frames.], batch size: 20, lr: 1.91e-03
+2022-05-03 14:13:51,033 INFO [train.py:715] (3/8) Epoch 0, batch 11300, loss[loss=0.2488, simple_loss=0.2933, pruned_loss=0.1021, over 4919.00 frames.], tot_loss[loss=0.2436, simple_loss=0.2889, pruned_loss=0.09909, over 972662.61 frames.], batch size: 29, lr: 1.91e-03
+2022-05-03 14:14:31,681 INFO [train.py:715] (3/8) Epoch 0, batch 11350, loss[loss=0.2184, simple_loss=0.2776, pruned_loss=0.07963, over 4921.00 frames.], tot_loss[loss=0.2418, simple_loss=0.2878, pruned_loss=0.09793, over 972666.62 frames.], batch size: 18, lr: 1.90e-03
+2022-05-03 14:15:12,104 INFO [train.py:715] (3/8) Epoch 0, batch 11400, loss[loss=0.2576, simple_loss=0.3035, pruned_loss=0.1058, over 4749.00 frames.], tot_loss[loss=0.2429, simple_loss=0.2885, pruned_loss=0.09869, over 972708.13 frames.], batch size: 16, lr: 1.90e-03
+2022-05-03 14:15:51,354 INFO [train.py:715] (3/8) Epoch 0, batch 11450, loss[loss=0.2039, simple_loss=0.2492, pruned_loss=0.07925, over 4851.00 frames.], tot_loss[loss=0.2435, simple_loss=0.2884, pruned_loss=0.09927, over 972094.01 frames.], batch size: 20, lr: 1.90e-03
+2022-05-03 14:16:32,010 INFO [train.py:715] (3/8) Epoch 0, batch 11500, loss[loss=0.2206, simple_loss=0.2726, pruned_loss=0.08429, over 4884.00 frames.], tot_loss[loss=0.2426, simple_loss=0.2883, pruned_loss=0.09845, over 971711.53 frames.], batch size: 22, lr: 1.89e-03
+2022-05-03 14:17:12,404 INFO [train.py:715] (3/8) Epoch 0, batch 11550, loss[loss=0.1522, simple_loss=0.2117, pruned_loss=0.0463, over 4830.00 frames.], tot_loss[loss=0.2418, simple_loss=0.2878, pruned_loss=0.09791, over 972864.68 frames.], batch size: 12, lr: 1.89e-03
+2022-05-03 14:17:52,490 INFO [train.py:715] (3/8) Epoch 0, batch 11600, loss[loss=0.2363, simple_loss=0.2699, pruned_loss=0.1014, over 4936.00 frames.], tot_loss[loss=0.2432, simple_loss=0.2886, pruned_loss=0.09892, over 972311.51 frames.], batch size: 18, lr: 1.89e-03
+2022-05-03 14:18:32,569 INFO [train.py:715] (3/8) Epoch 0, batch 11650, loss[loss=0.2681, simple_loss=0.3207, pruned_loss=0.1077, over 4872.00 frames.], tot_loss[loss=0.244, simple_loss=0.2897, pruned_loss=0.09913, over 972179.90 frames.], batch size: 16, lr: 1.88e-03
+2022-05-03 14:19:13,486 INFO [train.py:715] (3/8) Epoch 0, batch 11700, loss[loss=0.2656, simple_loss=0.2999, pruned_loss=0.1157, over 4915.00 frames.], tot_loss[loss=0.2438, simple_loss=0.2897, pruned_loss=0.09894, over 971976.12 frames.], batch size: 39, lr: 1.88e-03
+2022-05-03 14:19:53,841 INFO [train.py:715] (3/8) Epoch 0, batch 11750, loss[loss=0.266, simple_loss=0.3143, pruned_loss=0.1089, over 4948.00 frames.], tot_loss[loss=0.2421, simple_loss=0.2884, pruned_loss=0.09791, over 972018.86 frames.], batch size: 23, lr: 1.88e-03
+2022-05-03 14:20:34,232 INFO [train.py:715] (3/8) Epoch 0, batch 11800, loss[loss=0.2932, simple_loss=0.3272, pruned_loss=0.1296, over 4971.00 frames.], tot_loss[loss=0.2439, simple_loss=0.2897, pruned_loss=0.09906, over 971845.98 frames.], batch size: 14, lr: 1.87e-03
+2022-05-03 14:21:14,587 INFO [train.py:715] (3/8) Epoch 0, batch 11850, loss[loss=0.2443, simple_loss=0.2862, pruned_loss=0.1012, over 4972.00 frames.], tot_loss[loss=0.2434, simple_loss=0.2898, pruned_loss=0.09848, over 972020.08 frames.], batch size: 15, lr: 1.87e-03
+2022-05-03 14:21:55,676 INFO [train.py:715] (3/8) Epoch 0, batch 11900, loss[loss=0.2047, simple_loss=0.265, pruned_loss=0.07219, over 4750.00 frames.], tot_loss[loss=0.2431, simple_loss=0.2892, pruned_loss=0.09851, over 971641.35 frames.], batch size: 12, lr: 1.87e-03
+2022-05-03 14:22:35,857 INFO [train.py:715] (3/8) Epoch 0, batch 11950, loss[loss=0.2922, simple_loss=0.3247, pruned_loss=0.1299, over 4909.00 frames.], tot_loss[loss=0.2417, simple_loss=0.2884, pruned_loss=0.09754, over 971677.42 frames.], batch size: 39, lr: 1.86e-03
+2022-05-03 14:23:15,972 INFO [train.py:715] (3/8) Epoch 0, batch 12000, loss[loss=0.2241, simple_loss=0.2746, pruned_loss=0.08682, over 4861.00 frames.], tot_loss[loss=0.2421, simple_loss=0.2883, pruned_loss=0.09794, over 971719.47 frames.], batch size: 20, lr: 1.86e-03
+2022-05-03 14:23:15,973 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 14:23:31,273 INFO [train.py:742] (3/8) Epoch 0, validation: loss=0.1516, simple_loss=0.2368, pruned_loss=0.03315, over 914524.00 frames.
+2022-05-03 14:24:11,264 INFO [train.py:715] (3/8) Epoch 0, batch 12050, loss[loss=0.2486, simple_loss=0.2987, pruned_loss=0.09927, over 4787.00 frames.], tot_loss[loss=0.2417, simple_loss=0.2883, pruned_loss=0.0976, over 972036.16 frames.], batch size: 18, lr: 1.86e-03
+2022-05-03 14:24:51,293 INFO [train.py:715] (3/8) Epoch 0, batch 12100, loss[loss=0.2116, simple_loss=0.2716, pruned_loss=0.0758, over 4978.00 frames.], tot_loss[loss=0.2428, simple_loss=0.2892, pruned_loss=0.09817, over 972035.66 frames.], batch size: 24, lr: 1.85e-03
+2022-05-03 14:25:31,591 INFO [train.py:715] (3/8) Epoch 0, batch 12150, loss[loss=0.298, simple_loss=0.3292, pruned_loss=0.1334, over 4811.00 frames.], tot_loss[loss=0.2426, simple_loss=0.2889, pruned_loss=0.09813, over 971574.18 frames.], batch size: 24, lr: 1.85e-03
+2022-05-03 14:26:11,158 INFO [train.py:715] (3/8) Epoch 0, batch 12200, loss[loss=0.2431, simple_loss=0.2937, pruned_loss=0.09627, over 4932.00 frames.], tot_loss[loss=0.2449, simple_loss=0.2908, pruned_loss=0.09955, over 970780.97 frames.], batch size: 29, lr: 1.85e-03
+2022-05-03 14:26:51,064 INFO [train.py:715] (3/8) Epoch 0, batch 12250, loss[loss=0.2579, simple_loss=0.3144, pruned_loss=0.1007, over 4956.00 frames.], tot_loss[loss=0.2438, simple_loss=0.2902, pruned_loss=0.09874, over 970995.35 frames.], batch size: 21, lr: 1.84e-03
+2022-05-03 14:27:31,547 INFO [train.py:715] (3/8) Epoch 0, batch 12300, loss[loss=0.2383, simple_loss=0.2894, pruned_loss=0.09361, over 4832.00 frames.], tot_loss[loss=0.2441, simple_loss=0.2904, pruned_loss=0.09886, over 970712.08 frames.], batch size: 12, lr: 1.84e-03
+2022-05-03 14:28:10,856 INFO [train.py:715] (3/8) Epoch 0, batch 12350, loss[loss=0.3262, simple_loss=0.3354, pruned_loss=0.1585, over 4816.00 frames.], tot_loss[loss=0.2421, simple_loss=0.2887, pruned_loss=0.09773, over 971027.45 frames.], batch size: 13, lr: 1.84e-03
+2022-05-03 14:28:50,833 INFO [train.py:715] (3/8) Epoch 0, batch 12400, loss[loss=0.244, simple_loss=0.2844, pruned_loss=0.1018, over 4980.00 frames.], tot_loss[loss=0.242, simple_loss=0.2886, pruned_loss=0.09773, over 971839.88 frames.], batch size: 15, lr: 1.83e-03
+2022-05-03 14:29:31,158 INFO [train.py:715] (3/8) Epoch 0, batch 12450, loss[loss=0.2089, simple_loss=0.2471, pruned_loss=0.08532, over 4797.00 frames.], tot_loss[loss=0.2417, simple_loss=0.2882, pruned_loss=0.09755, over 972020.43 frames.], batch size: 14, lr: 1.83e-03
+2022-05-03 14:30:11,384 INFO [train.py:715] (3/8) Epoch 0, batch 12500, loss[loss=0.2507, simple_loss=0.2955, pruned_loss=0.103, over 4815.00 frames.], tot_loss[loss=0.2434, simple_loss=0.2896, pruned_loss=0.09857, over 971617.20 frames.], batch size: 27, lr: 1.83e-03
+2022-05-03 14:30:50,305 INFO [train.py:715] (3/8) Epoch 0, batch 12550, loss[loss=0.2425, simple_loss=0.291, pruned_loss=0.09698, over 4813.00 frames.], tot_loss[loss=0.2434, simple_loss=0.2891, pruned_loss=0.09884, over 972905.96 frames.], batch size: 26, lr: 1.83e-03
+2022-05-03 14:31:30,337 INFO [train.py:715] (3/8) Epoch 0, batch 12600, loss[loss=0.2553, simple_loss=0.2934, pruned_loss=0.1086, over 4961.00 frames.], tot_loss[loss=0.2426, simple_loss=0.2887, pruned_loss=0.09822, over 971421.64 frames.], batch size: 15, lr: 1.82e-03
+2022-05-03 14:32:11,362 INFO [train.py:715] (3/8) Epoch 0, batch 12650, loss[loss=0.2525, simple_loss=0.2904, pruned_loss=0.1074, over 4987.00 frames.], tot_loss[loss=0.2424, simple_loss=0.2883, pruned_loss=0.09824, over 971984.57 frames.], batch size: 28, lr: 1.82e-03
+2022-05-03 14:32:51,083 INFO [train.py:715] (3/8) Epoch 0, batch 12700, loss[loss=0.2394, simple_loss=0.2939, pruned_loss=0.09248, over 4825.00 frames.], tot_loss[loss=0.2401, simple_loss=0.2869, pruned_loss=0.0967, over 971938.06 frames.], batch size: 27, lr: 1.82e-03
+2022-05-03 14:33:30,729 INFO [train.py:715] (3/8) Epoch 0, batch 12750, loss[loss=0.1798, simple_loss=0.2426, pruned_loss=0.05853, over 4918.00 frames.], tot_loss[loss=0.2397, simple_loss=0.2867, pruned_loss=0.09631, over 972597.80 frames.], batch size: 18, lr: 1.81e-03
+2022-05-03 14:34:11,170 INFO [train.py:715] (3/8) Epoch 0, batch 12800, loss[loss=0.1618, simple_loss=0.2098, pruned_loss=0.05692, over 4778.00 frames.], tot_loss[loss=0.2376, simple_loss=0.2857, pruned_loss=0.0947, over 972073.23 frames.], batch size: 12, lr: 1.81e-03
+2022-05-03 14:34:51,654 INFO [train.py:715] (3/8) Epoch 0, batch 12850, loss[loss=0.2225, simple_loss=0.2649, pruned_loss=0.09007, over 4962.00 frames.], tot_loss[loss=0.2369, simple_loss=0.2855, pruned_loss=0.09416, over 972808.26 frames.], batch size: 24, lr: 1.81e-03
+2022-05-03 14:35:31,479 INFO [train.py:715] (3/8) Epoch 0, batch 12900, loss[loss=0.2429, simple_loss=0.2805, pruned_loss=0.1026, over 4786.00 frames.], tot_loss[loss=0.2359, simple_loss=0.2844, pruned_loss=0.09363, over 972301.04 frames.], batch size: 12, lr: 1.80e-03
+2022-05-03 14:36:11,737 INFO [train.py:715] (3/8) Epoch 0, batch 12950, loss[loss=0.2896, simple_loss=0.3253, pruned_loss=0.127, over 4915.00 frames.], tot_loss[loss=0.2354, simple_loss=0.2838, pruned_loss=0.09345, over 971739.47 frames.], batch size: 18, lr: 1.80e-03
+2022-05-03 14:36:52,261 INFO [train.py:715] (3/8) Epoch 0, batch 13000, loss[loss=0.2737, simple_loss=0.3103, pruned_loss=0.1186, over 4932.00 frames.], tot_loss[loss=0.2359, simple_loss=0.2841, pruned_loss=0.09381, over 972669.49 frames.], batch size: 23, lr: 1.80e-03
+2022-05-03 14:37:32,727 INFO [train.py:715] (3/8) Epoch 0, batch 13050, loss[loss=0.2262, simple_loss=0.2748, pruned_loss=0.08882, over 4706.00 frames.], tot_loss[loss=0.2385, simple_loss=0.286, pruned_loss=0.09544, over 972530.36 frames.], batch size: 15, lr: 1.79e-03
+2022-05-03 14:38:12,066 INFO [train.py:715] (3/8) Epoch 0, batch 13100, loss[loss=0.2273, simple_loss=0.2814, pruned_loss=0.08655, over 4889.00 frames.], tot_loss[loss=0.2386, simple_loss=0.286, pruned_loss=0.09555, over 972385.43 frames.], batch size: 19, lr: 1.79e-03
+2022-05-03 14:38:52,497 INFO [train.py:715] (3/8) Epoch 0, batch 13150, loss[loss=0.2252, simple_loss=0.2781, pruned_loss=0.08615, over 4885.00 frames.], tot_loss[loss=0.2403, simple_loss=0.2877, pruned_loss=0.0965, over 972607.81 frames.], batch size: 22, lr: 1.79e-03
+2022-05-03 14:39:32,989 INFO [train.py:715] (3/8) Epoch 0, batch 13200, loss[loss=0.2135, simple_loss=0.2676, pruned_loss=0.07967, over 4792.00 frames.], tot_loss[loss=0.2394, simple_loss=0.2872, pruned_loss=0.09582, over 971987.44 frames.], batch size: 24, lr: 1.79e-03
+2022-05-03 14:40:12,562 INFO [train.py:715] (3/8) Epoch 0, batch 13250, loss[loss=0.2373, simple_loss=0.2878, pruned_loss=0.09347, over 4960.00 frames.], tot_loss[loss=0.2399, simple_loss=0.2877, pruned_loss=0.09606, over 972053.66 frames.], batch size: 24, lr: 1.78e-03
+2022-05-03 14:40:52,439 INFO [train.py:715] (3/8) Epoch 0, batch 13300, loss[loss=0.2717, simple_loss=0.316, pruned_loss=0.1138, over 4982.00 frames.], tot_loss[loss=0.2385, simple_loss=0.2864, pruned_loss=0.09533, over 972543.47 frames.], batch size: 24, lr: 1.78e-03
+2022-05-03 14:41:32,817 INFO [train.py:715] (3/8) Epoch 0, batch 13350, loss[loss=0.2568, simple_loss=0.299, pruned_loss=0.1073, over 4843.00 frames.], tot_loss[loss=0.2382, simple_loss=0.2861, pruned_loss=0.09512, over 972119.40 frames.], batch size: 30, lr: 1.78e-03
+2022-05-03 14:42:13,145 INFO [train.py:715] (3/8) Epoch 0, batch 13400, loss[loss=0.2208, simple_loss=0.2742, pruned_loss=0.08376, over 4955.00 frames.], tot_loss[loss=0.2388, simple_loss=0.2865, pruned_loss=0.09553, over 972922.84 frames.], batch size: 21, lr: 1.77e-03
+2022-05-03 14:42:52,941 INFO [train.py:715] (3/8) Epoch 0, batch 13450, loss[loss=0.2673, simple_loss=0.3104, pruned_loss=0.1121, over 4760.00 frames.], tot_loss[loss=0.2382, simple_loss=0.286, pruned_loss=0.09522, over 972794.08 frames.], batch size: 19, lr: 1.77e-03
+2022-05-03 14:43:33,174 INFO [train.py:715] (3/8) Epoch 0, batch 13500, loss[loss=0.2361, simple_loss=0.2872, pruned_loss=0.09248, over 4925.00 frames.], tot_loss[loss=0.2367, simple_loss=0.2852, pruned_loss=0.09414, over 973223.29 frames.], batch size: 18, lr: 1.77e-03
+2022-05-03 14:44:13,340 INFO [train.py:715] (3/8) Epoch 0, batch 13550, loss[loss=0.2733, simple_loss=0.3076, pruned_loss=0.1195, over 4928.00 frames.], tot_loss[loss=0.2365, simple_loss=0.2844, pruned_loss=0.09427, over 972380.55 frames.], batch size: 18, lr: 1.77e-03
+2022-05-03 14:44:52,789 INFO [train.py:715] (3/8) Epoch 0, batch 13600, loss[loss=0.2487, simple_loss=0.3064, pruned_loss=0.09551, over 4944.00 frames.], tot_loss[loss=0.2356, simple_loss=0.2838, pruned_loss=0.09375, over 971890.41 frames.], batch size: 29, lr: 1.76e-03
+2022-05-03 14:45:32,767 INFO [train.py:715] (3/8) Epoch 0, batch 13650, loss[loss=0.2255, simple_loss=0.2734, pruned_loss=0.08876, over 4977.00 frames.], tot_loss[loss=0.2365, simple_loss=0.2846, pruned_loss=0.09422, over 971932.20 frames.], batch size: 15, lr: 1.76e-03
+2022-05-03 14:46:12,698 INFO [train.py:715] (3/8) Epoch 0, batch 13700, loss[loss=0.2493, simple_loss=0.2999, pruned_loss=0.09934, over 4886.00 frames.], tot_loss[loss=0.2351, simple_loss=0.2837, pruned_loss=0.09331, over 972464.62 frames.], batch size: 32, lr: 1.76e-03
+2022-05-03 14:46:52,708 INFO [train.py:715] (3/8) Epoch 0, batch 13750, loss[loss=0.2366, simple_loss=0.2889, pruned_loss=0.09218, over 4816.00 frames.], tot_loss[loss=0.2369, simple_loss=0.2852, pruned_loss=0.09433, over 972189.70 frames.], batch size: 13, lr: 1.75e-03
+2022-05-03 14:47:32,535 INFO [train.py:715] (3/8) Epoch 0, batch 13800, loss[loss=0.268, simple_loss=0.3088, pruned_loss=0.1136, over 4933.00 frames.], tot_loss[loss=0.2384, simple_loss=0.2863, pruned_loss=0.09523, over 972187.57 frames.], batch size: 23, lr: 1.75e-03
+2022-05-03 14:48:12,865 INFO [train.py:715] (3/8) Epoch 0, batch 13850, loss[loss=0.2904, simple_loss=0.3093, pruned_loss=0.1357, over 4838.00 frames.], tot_loss[loss=0.238, simple_loss=0.286, pruned_loss=0.095, over 972417.26 frames.], batch size: 30, lr: 1.75e-03
+2022-05-03 14:48:53,730 INFO [train.py:715] (3/8) Epoch 0, batch 13900, loss[loss=0.2729, simple_loss=0.3143, pruned_loss=0.1158, over 4935.00 frames.], tot_loss[loss=0.2369, simple_loss=0.2853, pruned_loss=0.09422, over 972385.19 frames.], batch size: 18, lr: 1.75e-03
+2022-05-03 14:49:33,780 INFO [train.py:715] (3/8) Epoch 0, batch 13950, loss[loss=0.2806, simple_loss=0.3393, pruned_loss=0.111, over 4818.00 frames.], tot_loss[loss=0.2367, simple_loss=0.2854, pruned_loss=0.094, over 972035.94 frames.], batch size: 25, lr: 1.74e-03
+2022-05-03 14:50:14,373 INFO [train.py:715] (3/8) Epoch 0, batch 14000, loss[loss=0.2361, simple_loss=0.284, pruned_loss=0.09409, over 4829.00 frames.], tot_loss[loss=0.2352, simple_loss=0.2838, pruned_loss=0.09327, over 972354.10 frames.], batch size: 30, lr: 1.74e-03
+2022-05-03 14:50:55,235 INFO [train.py:715] (3/8) Epoch 0, batch 14050, loss[loss=0.2422, simple_loss=0.2866, pruned_loss=0.09892, over 4786.00 frames.], tot_loss[loss=0.2353, simple_loss=0.2839, pruned_loss=0.09335, over 972719.39 frames.], batch size: 17, lr: 1.74e-03
+2022-05-03 14:51:35,694 INFO [train.py:715] (3/8) Epoch 0, batch 14100, loss[loss=0.2674, simple_loss=0.3229, pruned_loss=0.1059, over 4938.00 frames.], tot_loss[loss=0.2365, simple_loss=0.2853, pruned_loss=0.09389, over 972553.41 frames.], batch size: 29, lr: 1.73e-03
+2022-05-03 14:52:16,199 INFO [train.py:715] (3/8) Epoch 0, batch 14150, loss[loss=0.2102, simple_loss=0.2566, pruned_loss=0.08195, over 4839.00 frames.], tot_loss[loss=0.2358, simple_loss=0.2848, pruned_loss=0.09339, over 971904.53 frames.], batch size: 13, lr: 1.73e-03
+2022-05-03 14:52:56,856 INFO [train.py:715] (3/8) Epoch 0, batch 14200, loss[loss=0.2316, simple_loss=0.2872, pruned_loss=0.08795, over 4909.00 frames.], tot_loss[loss=0.2351, simple_loss=0.2842, pruned_loss=0.09299, over 971893.97 frames.], batch size: 23, lr: 1.73e-03
+2022-05-03 14:53:37,708 INFO [train.py:715] (3/8) Epoch 0, batch 14250, loss[loss=0.1976, simple_loss=0.2497, pruned_loss=0.07277, over 4803.00 frames.], tot_loss[loss=0.2354, simple_loss=0.2843, pruned_loss=0.09324, over 972103.40 frames.], batch size: 17, lr: 1.73e-03
+2022-05-03 14:54:18,408 INFO [train.py:715] (3/8) Epoch 0, batch 14300, loss[loss=0.322, simple_loss=0.3484, pruned_loss=0.1478, over 4890.00 frames.], tot_loss[loss=0.2352, simple_loss=0.2841, pruned_loss=0.09316, over 971153.14 frames.], batch size: 16, lr: 1.72e-03
+2022-05-03 14:54:59,474 INFO [train.py:715] (3/8) Epoch 0, batch 14350, loss[loss=0.1736, simple_loss=0.2348, pruned_loss=0.05621, over 4768.00 frames.], tot_loss[loss=0.2348, simple_loss=0.2838, pruned_loss=0.09295, over 971198.71 frames.], batch size: 12, lr: 1.72e-03
+2022-05-03 14:55:40,712 INFO [train.py:715] (3/8) Epoch 0, batch 14400, loss[loss=0.2372, simple_loss=0.2708, pruned_loss=0.1019, over 4990.00 frames.], tot_loss[loss=0.2358, simple_loss=0.2843, pruned_loss=0.09363, over 971793.04 frames.], batch size: 31, lr: 1.72e-03
+2022-05-03 14:56:21,183 INFO [train.py:715] (3/8) Epoch 0, batch 14450, loss[loss=0.2939, simple_loss=0.3226, pruned_loss=0.1326, over 4826.00 frames.], tot_loss[loss=0.2361, simple_loss=0.2846, pruned_loss=0.0938, over 972158.10 frames.], batch size: 27, lr: 1.72e-03
+2022-05-03 14:57:01,533 INFO [train.py:715] (3/8) Epoch 0, batch 14500, loss[loss=0.2157, simple_loss=0.2599, pruned_loss=0.08572, over 4987.00 frames.], tot_loss[loss=0.2369, simple_loss=0.2852, pruned_loss=0.0943, over 971415.76 frames.], batch size: 28, lr: 1.71e-03
+2022-05-03 14:57:42,203 INFO [train.py:715] (3/8) Epoch 0, batch 14550, loss[loss=0.1876, simple_loss=0.2602, pruned_loss=0.05747, over 4865.00 frames.], tot_loss[loss=0.2363, simple_loss=0.2849, pruned_loss=0.09385, over 971608.57 frames.], batch size: 20, lr: 1.71e-03
+2022-05-03 14:58:22,166 INFO [train.py:715] (3/8) Epoch 0, batch 14600, loss[loss=0.3085, simple_loss=0.3455, pruned_loss=0.1358, over 4697.00 frames.], tot_loss[loss=0.2361, simple_loss=0.2847, pruned_loss=0.09369, over 970877.66 frames.], batch size: 15, lr: 1.71e-03
+2022-05-03 14:59:01,451 INFO [train.py:715] (3/8) Epoch 0, batch 14650, loss[loss=0.2052, simple_loss=0.2776, pruned_loss=0.06635, over 4824.00 frames.], tot_loss[loss=0.2351, simple_loss=0.2841, pruned_loss=0.09306, over 970775.20 frames.], batch size: 25, lr: 1.70e-03
+2022-05-03 14:59:41,809 INFO [train.py:715] (3/8) Epoch 0, batch 14700, loss[loss=0.2488, simple_loss=0.2949, pruned_loss=0.1013, over 4826.00 frames.], tot_loss[loss=0.2338, simple_loss=0.2828, pruned_loss=0.09243, over 970441.25 frames.], batch size: 27, lr: 1.70e-03
+2022-05-03 15:00:22,080 INFO [train.py:715] (3/8) Epoch 0, batch 14750, loss[loss=0.2351, simple_loss=0.2826, pruned_loss=0.09381, over 4898.00 frames.], tot_loss[loss=0.2339, simple_loss=0.2828, pruned_loss=0.09254, over 971001.24 frames.], batch size: 22, lr: 1.70e-03
+2022-05-03 15:01:02,115 INFO [train.py:715] (3/8) Epoch 0, batch 14800, loss[loss=0.22, simple_loss=0.2683, pruned_loss=0.08583, over 4805.00 frames.], tot_loss[loss=0.2349, simple_loss=0.2831, pruned_loss=0.09332, over 971814.95 frames.], batch size: 26, lr: 1.70e-03
+2022-05-03 15:01:41,992 INFO [train.py:715] (3/8) Epoch 0, batch 14850, loss[loss=0.2438, simple_loss=0.278, pruned_loss=0.1048, over 4969.00 frames.], tot_loss[loss=0.2327, simple_loss=0.2814, pruned_loss=0.092, over 971952.04 frames.], batch size: 14, lr: 1.69e-03
+2022-05-03 15:02:22,715 INFO [train.py:715] (3/8) Epoch 0, batch 14900, loss[loss=0.2105, simple_loss=0.2732, pruned_loss=0.0739, over 4694.00 frames.], tot_loss[loss=0.2333, simple_loss=0.2818, pruned_loss=0.09244, over 972755.04 frames.], batch size: 15, lr: 1.69e-03
+2022-05-03 15:03:02,602 INFO [train.py:715] (3/8) Epoch 0, batch 14950, loss[loss=0.1963, simple_loss=0.247, pruned_loss=0.07282, over 4831.00 frames.], tot_loss[loss=0.2319, simple_loss=0.2809, pruned_loss=0.09143, over 972793.73 frames.], batch size: 13, lr: 1.69e-03
+2022-05-03 15:03:42,034 INFO [train.py:715] (3/8) Epoch 0, batch 15000, loss[loss=0.252, simple_loss=0.2956, pruned_loss=0.1042, over 4966.00 frames.], tot_loss[loss=0.2325, simple_loss=0.2814, pruned_loss=0.09179, over 971632.29 frames.], batch size: 35, lr: 1.69e-03
+2022-05-03 15:03:42,034 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 15:03:53,632 INFO [train.py:742] (3/8) Epoch 0, validation: loss=0.1454, simple_loss=0.2314, pruned_loss=0.02968, over 914524.00 frames.
+2022-05-03 15:04:32,988 INFO [train.py:715] (3/8) Epoch 0, batch 15050, loss[loss=0.2705, simple_loss=0.3047, pruned_loss=0.1181, over 4912.00 frames.], tot_loss[loss=0.2299, simple_loss=0.2797, pruned_loss=0.09009, over 971532.89 frames.], batch size: 17, lr: 1.68e-03
+2022-05-03 15:05:13,558 INFO [train.py:715] (3/8) Epoch 0, batch 15100, loss[loss=0.255, simple_loss=0.2897, pruned_loss=0.1101, over 4891.00 frames.], tot_loss[loss=0.231, simple_loss=0.2801, pruned_loss=0.09095, over 971760.35 frames.], batch size: 17, lr: 1.68e-03
+2022-05-03 15:05:53,895 INFO [train.py:715] (3/8) Epoch 0, batch 15150, loss[loss=0.2432, simple_loss=0.2915, pruned_loss=0.09742, over 4889.00 frames.], tot_loss[loss=0.2306, simple_loss=0.2799, pruned_loss=0.09067, over 971595.98 frames.], batch size: 22, lr: 1.68e-03
+2022-05-03 15:06:33,823 INFO [train.py:715] (3/8) Epoch 0, batch 15200, loss[loss=0.2764, simple_loss=0.3342, pruned_loss=0.1093, over 4900.00 frames.], tot_loss[loss=0.232, simple_loss=0.2814, pruned_loss=0.09132, over 972346.76 frames.], batch size: 19, lr: 1.68e-03
+2022-05-03 15:07:13,390 INFO [train.py:715] (3/8) Epoch 0, batch 15250, loss[loss=0.2364, simple_loss=0.2735, pruned_loss=0.09959, over 4830.00 frames.], tot_loss[loss=0.2305, simple_loss=0.2802, pruned_loss=0.09043, over 972407.48 frames.], batch size: 30, lr: 1.67e-03
+2022-05-03 15:07:53,252 INFO [train.py:715] (3/8) Epoch 0, batch 15300, loss[loss=0.2362, simple_loss=0.2887, pruned_loss=0.09183, over 4854.00 frames.], tot_loss[loss=0.2299, simple_loss=0.2801, pruned_loss=0.08987, over 972754.15 frames.], batch size: 20, lr: 1.67e-03
+2022-05-03 15:08:33,607 INFO [train.py:715] (3/8) Epoch 0, batch 15350, loss[loss=0.2713, simple_loss=0.2936, pruned_loss=0.1245, over 4840.00 frames.], tot_loss[loss=0.233, simple_loss=0.2823, pruned_loss=0.09178, over 972913.20 frames.], batch size: 13, lr: 1.67e-03
+2022-05-03 15:09:13,456 INFO [train.py:715] (3/8) Epoch 0, batch 15400, loss[loss=0.2357, simple_loss=0.2888, pruned_loss=0.09129, over 4975.00 frames.], tot_loss[loss=0.2313, simple_loss=0.2812, pruned_loss=0.09072, over 972695.18 frames.], batch size: 28, lr: 1.67e-03
+2022-05-03 15:09:53,906 INFO [train.py:715] (3/8) Epoch 0, batch 15450, loss[loss=0.2395, simple_loss=0.2934, pruned_loss=0.09278, over 4852.00 frames.], tot_loss[loss=0.2309, simple_loss=0.2813, pruned_loss=0.09026, over 972470.25 frames.], batch size: 20, lr: 1.66e-03
+2022-05-03 15:10:33,368 INFO [train.py:715] (3/8) Epoch 0, batch 15500, loss[loss=0.2381, simple_loss=0.2863, pruned_loss=0.09497, over 4836.00 frames.], tot_loss[loss=0.2299, simple_loss=0.2806, pruned_loss=0.08956, over 972700.19 frames.], batch size: 30, lr: 1.66e-03
+2022-05-03 15:11:12,568 INFO [train.py:715] (3/8) Epoch 0, batch 15550, loss[loss=0.2663, simple_loss=0.3165, pruned_loss=0.1081, over 4793.00 frames.], tot_loss[loss=0.2304, simple_loss=0.2809, pruned_loss=0.08989, over 972246.95 frames.], batch size: 24, lr: 1.66e-03
+2022-05-03 15:11:52,062 INFO [train.py:715] (3/8) Epoch 0, batch 15600, loss[loss=0.1977, simple_loss=0.2469, pruned_loss=0.07422, over 4831.00 frames.], tot_loss[loss=0.2291, simple_loss=0.2799, pruned_loss=0.0892, over 972725.13 frames.], batch size: 30, lr: 1.66e-03
+2022-05-03 15:12:31,507 INFO [train.py:715] (3/8) Epoch 0, batch 15650, loss[loss=0.1982, simple_loss=0.2573, pruned_loss=0.06951, over 4809.00 frames.], tot_loss[loss=0.2287, simple_loss=0.2796, pruned_loss=0.08891, over 973192.21 frames.], batch size: 24, lr: 1.65e-03
+2022-05-03 15:13:11,299 INFO [train.py:715] (3/8) Epoch 0, batch 15700, loss[loss=0.2582, simple_loss=0.2923, pruned_loss=0.1121, over 4843.00 frames.], tot_loss[loss=0.2282, simple_loss=0.2793, pruned_loss=0.0886, over 973147.03 frames.], batch size: 30, lr: 1.65e-03
+2022-05-03 15:13:50,903 INFO [train.py:715] (3/8) Epoch 0, batch 15750, loss[loss=0.2042, simple_loss=0.2643, pruned_loss=0.07203, over 4759.00 frames.], tot_loss[loss=0.228, simple_loss=0.279, pruned_loss=0.0885, over 973346.83 frames.], batch size: 16, lr: 1.65e-03
+2022-05-03 15:14:30,843 INFO [train.py:715] (3/8) Epoch 0, batch 15800, loss[loss=0.198, simple_loss=0.2599, pruned_loss=0.06807, over 4836.00 frames.], tot_loss[loss=0.2275, simple_loss=0.2786, pruned_loss=0.08823, over 973259.26 frames.], batch size: 30, lr: 1.65e-03
+2022-05-03 15:15:10,662 INFO [train.py:715] (3/8) Epoch 0, batch 15850, loss[loss=0.2259, simple_loss=0.2886, pruned_loss=0.0816, over 4910.00 frames.], tot_loss[loss=0.2283, simple_loss=0.279, pruned_loss=0.08887, over 973315.12 frames.], batch size: 19, lr: 1.65e-03
+2022-05-03 15:15:50,241 INFO [train.py:715] (3/8) Epoch 0, batch 15900, loss[loss=0.2241, simple_loss=0.2843, pruned_loss=0.08198, over 4773.00 frames.], tot_loss[loss=0.2268, simple_loss=0.2778, pruned_loss=0.08792, over 973689.03 frames.], batch size: 17, lr: 1.64e-03
+2022-05-03 15:16:30,471 INFO [train.py:715] (3/8) Epoch 0, batch 15950, loss[loss=0.2435, simple_loss=0.2885, pruned_loss=0.09924, over 4655.00 frames.], tot_loss[loss=0.2287, simple_loss=0.2794, pruned_loss=0.08899, over 972937.69 frames.], batch size: 13, lr: 1.64e-03
+2022-05-03 15:17:12,822 INFO [train.py:715] (3/8) Epoch 0, batch 16000, loss[loss=0.2278, simple_loss=0.2917, pruned_loss=0.08197, over 4823.00 frames.], tot_loss[loss=0.2288, simple_loss=0.2797, pruned_loss=0.08898, over 972593.28 frames.], batch size: 26, lr: 1.64e-03
+2022-05-03 15:17:52,705 INFO [train.py:715] (3/8) Epoch 0, batch 16050, loss[loss=0.2803, simple_loss=0.2971, pruned_loss=0.1318, over 4859.00 frames.], tot_loss[loss=0.2287, simple_loss=0.2797, pruned_loss=0.08882, over 972073.29 frames.], batch size: 16, lr: 1.64e-03
+2022-05-03 15:18:33,248 INFO [train.py:715] (3/8) Epoch 0, batch 16100, loss[loss=0.2106, simple_loss=0.2749, pruned_loss=0.07317, over 4782.00 frames.], tot_loss[loss=0.2297, simple_loss=0.2802, pruned_loss=0.08957, over 972369.60 frames.], batch size: 18, lr: 1.63e-03
+2022-05-03 15:19:13,426 INFO [train.py:715] (3/8) Epoch 0, batch 16150, loss[loss=0.1884, simple_loss=0.244, pruned_loss=0.06639, over 4985.00 frames.], tot_loss[loss=0.2303, simple_loss=0.2809, pruned_loss=0.08988, over 972910.21 frames.], batch size: 14, lr: 1.63e-03
+2022-05-03 15:19:52,894 INFO [train.py:715] (3/8) Epoch 0, batch 16200, loss[loss=0.2393, simple_loss=0.2791, pruned_loss=0.09972, over 4711.00 frames.], tot_loss[loss=0.2315, simple_loss=0.2815, pruned_loss=0.0907, over 972173.11 frames.], batch size: 15, lr: 1.63e-03
+2022-05-03 15:20:32,317 INFO [train.py:715] (3/8) Epoch 0, batch 16250, loss[loss=0.2141, simple_loss=0.2573, pruned_loss=0.08547, over 4745.00 frames.], tot_loss[loss=0.2317, simple_loss=0.2819, pruned_loss=0.09079, over 972640.37 frames.], batch size: 16, lr: 1.63e-03
+2022-05-03 15:21:12,242 INFO [train.py:715] (3/8) Epoch 0, batch 16300, loss[loss=0.2068, simple_loss=0.2609, pruned_loss=0.07636, over 4783.00 frames.], tot_loss[loss=0.2307, simple_loss=0.2811, pruned_loss=0.0901, over 972333.72 frames.], batch size: 14, lr: 1.62e-03
+2022-05-03 15:21:51,666 INFO [train.py:715] (3/8) Epoch 0, batch 16350, loss[loss=0.2313, simple_loss=0.2881, pruned_loss=0.08725, over 4897.00 frames.], tot_loss[loss=0.2309, simple_loss=0.2815, pruned_loss=0.09014, over 972664.60 frames.], batch size: 22, lr: 1.62e-03
+2022-05-03 15:22:31,096 INFO [train.py:715] (3/8) Epoch 0, batch 16400, loss[loss=0.2723, simple_loss=0.3013, pruned_loss=0.1217, over 4851.00 frames.], tot_loss[loss=0.2299, simple_loss=0.281, pruned_loss=0.0894, over 972254.16 frames.], batch size: 20, lr: 1.62e-03
+2022-05-03 15:23:11,044 INFO [train.py:715] (3/8) Epoch 0, batch 16450, loss[loss=0.2391, simple_loss=0.2838, pruned_loss=0.09722, over 4941.00 frames.], tot_loss[loss=0.2287, simple_loss=0.28, pruned_loss=0.08875, over 972498.49 frames.], batch size: 29, lr: 1.62e-03
+2022-05-03 15:23:51,577 INFO [train.py:715] (3/8) Epoch 0, batch 16500, loss[loss=0.2088, simple_loss=0.2693, pruned_loss=0.07415, over 4891.00 frames.], tot_loss[loss=0.2285, simple_loss=0.2798, pruned_loss=0.08862, over 972386.91 frames.], batch size: 22, lr: 1.62e-03
+2022-05-03 15:24:31,537 INFO [train.py:715] (3/8) Epoch 0, batch 16550, loss[loss=0.2311, simple_loss=0.2899, pruned_loss=0.08614, over 4982.00 frames.], tot_loss[loss=0.2278, simple_loss=0.2794, pruned_loss=0.08813, over 972383.74 frames.], batch size: 33, lr: 1.61e-03
+2022-05-03 15:25:11,222 INFO [train.py:715] (3/8) Epoch 0, batch 16600, loss[loss=0.2222, simple_loss=0.2767, pruned_loss=0.08385, over 4928.00 frames.], tot_loss[loss=0.2278, simple_loss=0.2796, pruned_loss=0.08799, over 972379.20 frames.], batch size: 21, lr: 1.61e-03
+2022-05-03 15:25:50,675 INFO [train.py:715] (3/8) Epoch 0, batch 16650, loss[loss=0.1978, simple_loss=0.2469, pruned_loss=0.07437, over 4992.00 frames.], tot_loss[loss=0.2285, simple_loss=0.2797, pruned_loss=0.08861, over 973474.98 frames.], batch size: 20, lr: 1.61e-03
+2022-05-03 15:26:30,540 INFO [train.py:715] (3/8) Epoch 0, batch 16700, loss[loss=0.2125, simple_loss=0.263, pruned_loss=0.08095, over 4796.00 frames.], tot_loss[loss=0.2275, simple_loss=0.2793, pruned_loss=0.08791, over 973186.67 frames.], batch size: 24, lr: 1.61e-03
+2022-05-03 15:27:09,628 INFO [train.py:715] (3/8) Epoch 0, batch 16750, loss[loss=0.1902, simple_loss=0.2506, pruned_loss=0.06495, over 4770.00 frames.], tot_loss[loss=0.2285, simple_loss=0.2796, pruned_loss=0.08865, over 973093.91 frames.], batch size: 19, lr: 1.60e-03
+2022-05-03 15:27:48,776 INFO [train.py:715] (3/8) Epoch 0, batch 16800, loss[loss=0.2458, simple_loss=0.288, pruned_loss=0.1018, over 4782.00 frames.], tot_loss[loss=0.2287, simple_loss=0.2795, pruned_loss=0.08891, over 972052.35 frames.], batch size: 18, lr: 1.60e-03
+2022-05-03 15:28:28,412 INFO [train.py:715] (3/8) Epoch 0, batch 16850, loss[loss=0.2165, simple_loss=0.2715, pruned_loss=0.08073, over 4757.00 frames.], tot_loss[loss=0.2292, simple_loss=0.2803, pruned_loss=0.08908, over 971128.03 frames.], batch size: 16, lr: 1.60e-03
+2022-05-03 15:29:08,022 INFO [train.py:715] (3/8) Epoch 0, batch 16900, loss[loss=0.2102, simple_loss=0.2585, pruned_loss=0.08098, over 4702.00 frames.], tot_loss[loss=0.2272, simple_loss=0.2785, pruned_loss=0.08797, over 971266.62 frames.], batch size: 15, lr: 1.60e-03
+2022-05-03 15:29:47,261 INFO [train.py:715] (3/8) Epoch 0, batch 16950, loss[loss=0.2406, simple_loss=0.2857, pruned_loss=0.09779, over 4781.00 frames.], tot_loss[loss=0.2281, simple_loss=0.2794, pruned_loss=0.08845, over 972224.03 frames.], batch size: 14, lr: 1.60e-03
+2022-05-03 15:30:27,230 INFO [train.py:715] (3/8) Epoch 0, batch 17000, loss[loss=0.1781, simple_loss=0.2411, pruned_loss=0.0576, over 4892.00 frames.], tot_loss[loss=0.2265, simple_loss=0.2784, pruned_loss=0.08725, over 972105.37 frames.], batch size: 19, lr: 1.59e-03
+2022-05-03 15:31:07,727 INFO [train.py:715] (3/8) Epoch 0, batch 17050, loss[loss=0.2447, simple_loss=0.3025, pruned_loss=0.09343, over 4900.00 frames.], tot_loss[loss=0.2257, simple_loss=0.2782, pruned_loss=0.08665, over 972408.22 frames.], batch size: 16, lr: 1.59e-03
+2022-05-03 15:31:47,482 INFO [train.py:715] (3/8) Epoch 0, batch 17100, loss[loss=0.2251, simple_loss=0.2707, pruned_loss=0.08977, over 4754.00 frames.], tot_loss[loss=0.227, simple_loss=0.2792, pruned_loss=0.08743, over 972508.56 frames.], batch size: 16, lr: 1.59e-03
+2022-05-03 15:32:26,649 INFO [train.py:715] (3/8) Epoch 0, batch 17150, loss[loss=0.2612, simple_loss=0.3032, pruned_loss=0.1096, over 4790.00 frames.], tot_loss[loss=0.2278, simple_loss=0.2794, pruned_loss=0.08807, over 971933.29 frames.], batch size: 17, lr: 1.59e-03
+2022-05-03 15:33:06,902 INFO [train.py:715] (3/8) Epoch 0, batch 17200, loss[loss=0.2297, simple_loss=0.2882, pruned_loss=0.08561, over 4846.00 frames.], tot_loss[loss=0.2264, simple_loss=0.2785, pruned_loss=0.08716, over 971878.11 frames.], batch size: 15, lr: 1.58e-03
+2022-05-03 15:33:46,676 INFO [train.py:715] (3/8) Epoch 0, batch 17250, loss[loss=0.1903, simple_loss=0.2454, pruned_loss=0.06764, over 4985.00 frames.], tot_loss[loss=0.2265, simple_loss=0.2782, pruned_loss=0.08738, over 972155.03 frames.], batch size: 14, lr: 1.58e-03
+2022-05-03 15:34:26,232 INFO [train.py:715] (3/8) Epoch 0, batch 17300, loss[loss=0.2498, simple_loss=0.288, pruned_loss=0.1058, over 4834.00 frames.], tot_loss[loss=0.2255, simple_loss=0.2777, pruned_loss=0.0867, over 971895.50 frames.], batch size: 30, lr: 1.58e-03
+2022-05-03 15:35:06,288 INFO [train.py:715] (3/8) Epoch 0, batch 17350, loss[loss=0.2341, simple_loss=0.2847, pruned_loss=0.09177, over 4789.00 frames.], tot_loss[loss=0.2245, simple_loss=0.2766, pruned_loss=0.0862, over 971583.62 frames.], batch size: 12, lr: 1.58e-03
+2022-05-03 15:35:46,527 INFO [train.py:715] (3/8) Epoch 0, batch 17400, loss[loss=0.2832, simple_loss=0.3183, pruned_loss=0.1241, over 4867.00 frames.], tot_loss[loss=0.2251, simple_loss=0.2774, pruned_loss=0.08637, over 971714.59 frames.], batch size: 20, lr: 1.58e-03
+2022-05-03 15:36:26,419 INFO [train.py:715] (3/8) Epoch 0, batch 17450, loss[loss=0.2226, simple_loss=0.2689, pruned_loss=0.08817, over 4973.00 frames.], tot_loss[loss=0.2254, simple_loss=0.2778, pruned_loss=0.08653, over 972657.79 frames.], batch size: 15, lr: 1.57e-03
+2022-05-03 15:37:07,033 INFO [train.py:715] (3/8) Epoch 0, batch 17500, loss[loss=0.2138, simple_loss=0.2642, pruned_loss=0.0817, over 4709.00 frames.], tot_loss[loss=0.2252, simple_loss=0.2774, pruned_loss=0.0865, over 971196.24 frames.], batch size: 15, lr: 1.57e-03
+2022-05-03 15:37:47,460 INFO [train.py:715] (3/8) Epoch 0, batch 17550, loss[loss=0.2171, simple_loss=0.2629, pruned_loss=0.08568, over 4976.00 frames.], tot_loss[loss=0.2254, simple_loss=0.2775, pruned_loss=0.08669, over 972043.90 frames.], batch size: 35, lr: 1.57e-03
+2022-05-03 15:38:27,017 INFO [train.py:715] (3/8) Epoch 0, batch 17600, loss[loss=0.2304, simple_loss=0.2864, pruned_loss=0.08717, over 4881.00 frames.], tot_loss[loss=0.2258, simple_loss=0.2777, pruned_loss=0.08702, over 972002.38 frames.], batch size: 20, lr: 1.57e-03
+2022-05-03 15:39:06,935 INFO [train.py:715] (3/8) Epoch 0, batch 17650, loss[loss=0.1845, simple_loss=0.2445, pruned_loss=0.06228, over 4777.00 frames.], tot_loss[loss=0.2252, simple_loss=0.2772, pruned_loss=0.08667, over 971527.64 frames.], batch size: 14, lr: 1.57e-03
+2022-05-03 15:39:47,479 INFO [train.py:715] (3/8) Epoch 0, batch 17700, loss[loss=0.242, simple_loss=0.2945, pruned_loss=0.09477, over 4986.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2757, pruned_loss=0.08541, over 971412.46 frames.], batch size: 31, lr: 1.56e-03
+2022-05-03 15:40:27,378 INFO [train.py:715] (3/8) Epoch 0, batch 17750, loss[loss=0.238, simple_loss=0.2946, pruned_loss=0.09071, over 4892.00 frames.], tot_loss[loss=0.2236, simple_loss=0.276, pruned_loss=0.08563, over 971638.76 frames.], batch size: 19, lr: 1.56e-03
+2022-05-03 15:41:07,054 INFO [train.py:715] (3/8) Epoch 0, batch 17800, loss[loss=0.1554, simple_loss=0.2288, pruned_loss=0.04095, over 4906.00 frames.], tot_loss[loss=0.2241, simple_loss=0.2765, pruned_loss=0.08579, over 971538.32 frames.], batch size: 17, lr: 1.56e-03
+2022-05-03 15:41:47,856 INFO [train.py:715] (3/8) Epoch 0, batch 17850, loss[loss=0.2321, simple_loss=0.2812, pruned_loss=0.09143, over 4901.00 frames.], tot_loss[loss=0.2243, simple_loss=0.277, pruned_loss=0.08578, over 971151.89 frames.], batch size: 18, lr: 1.56e-03
+2022-05-03 15:42:28,480 INFO [train.py:715] (3/8) Epoch 0, batch 17900, loss[loss=0.2489, simple_loss=0.287, pruned_loss=0.1054, over 4908.00 frames.], tot_loss[loss=0.2246, simple_loss=0.2774, pruned_loss=0.08585, over 971500.80 frames.], batch size: 17, lr: 1.56e-03
+2022-05-03 15:43:07,991 INFO [train.py:715] (3/8) Epoch 0, batch 17950, loss[loss=0.2507, simple_loss=0.2986, pruned_loss=0.1014, over 4839.00 frames.], tot_loss[loss=0.2257, simple_loss=0.2783, pruned_loss=0.08661, over 971842.48 frames.], batch size: 15, lr: 1.55e-03
+2022-05-03 15:43:48,220 INFO [train.py:715] (3/8) Epoch 0, batch 18000, loss[loss=0.2261, simple_loss=0.2756, pruned_loss=0.08826, over 4818.00 frames.], tot_loss[loss=0.2249, simple_loss=0.2775, pruned_loss=0.08613, over 971301.60 frames.], batch size: 26, lr: 1.55e-03
+2022-05-03 15:43:48,221 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 15:43:57,826 INFO [train.py:742] (3/8) Epoch 0, validation: loss=0.141, simple_loss=0.228, pruned_loss=0.02706, over 914524.00 frames.
+2022-05-03 15:44:38,089 INFO [train.py:715] (3/8) Epoch 0, batch 18050, loss[loss=0.1943, simple_loss=0.2577, pruned_loss=0.06542, over 4911.00 frames.], tot_loss[loss=0.2259, simple_loss=0.2782, pruned_loss=0.0868, over 971289.62 frames.], batch size: 18, lr: 1.55e-03
+2022-05-03 15:45:18,342 INFO [train.py:715] (3/8) Epoch 0, batch 18100, loss[loss=0.2371, simple_loss=0.2876, pruned_loss=0.09325, over 4769.00 frames.], tot_loss[loss=0.2268, simple_loss=0.279, pruned_loss=0.08729, over 972072.53 frames.], batch size: 14, lr: 1.55e-03
+2022-05-03 15:45:58,158 INFO [train.py:715] (3/8) Epoch 0, batch 18150, loss[loss=0.193, simple_loss=0.2518, pruned_loss=0.06713, over 4807.00 frames.], tot_loss[loss=0.2256, simple_loss=0.2782, pruned_loss=0.08644, over 971887.55 frames.], batch size: 12, lr: 1.55e-03
+2022-05-03 15:46:37,566 INFO [train.py:715] (3/8) Epoch 0, batch 18200, loss[loss=0.2179, simple_loss=0.2637, pruned_loss=0.08601, over 4743.00 frames.], tot_loss[loss=0.2262, simple_loss=0.2785, pruned_loss=0.0869, over 971887.22 frames.], batch size: 16, lr: 1.54e-03
+2022-05-03 15:47:17,743 INFO [train.py:715] (3/8) Epoch 0, batch 18250, loss[loss=0.2139, simple_loss=0.2673, pruned_loss=0.08027, over 4705.00 frames.], tot_loss[loss=0.2249, simple_loss=0.2778, pruned_loss=0.08607, over 972071.19 frames.], batch size: 15, lr: 1.54e-03
+2022-05-03 15:47:59,026 INFO [train.py:715] (3/8) Epoch 0, batch 18300, loss[loss=0.2348, simple_loss=0.2916, pruned_loss=0.089, over 4924.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2762, pruned_loss=0.08464, over 972824.62 frames.], batch size: 23, lr: 1.54e-03
+2022-05-03 15:48:38,800 INFO [train.py:715] (3/8) Epoch 0, batch 18350, loss[loss=0.2276, simple_loss=0.2873, pruned_loss=0.08397, over 4878.00 frames.], tot_loss[loss=0.223, simple_loss=0.2761, pruned_loss=0.08495, over 973223.52 frames.], batch size: 22, lr: 1.54e-03
+2022-05-03 15:49:19,070 INFO [train.py:715] (3/8) Epoch 0, batch 18400, loss[loss=0.1935, simple_loss=0.2551, pruned_loss=0.066, over 4856.00 frames.], tot_loss[loss=0.2244, simple_loss=0.2774, pruned_loss=0.08575, over 972705.25 frames.], batch size: 20, lr: 1.54e-03
+2022-05-03 15:49:59,576 INFO [train.py:715] (3/8) Epoch 0, batch 18450, loss[loss=0.2077, simple_loss=0.2654, pruned_loss=0.07497, over 4838.00 frames.], tot_loss[loss=0.223, simple_loss=0.2763, pruned_loss=0.08482, over 971702.17 frames.], batch size: 30, lr: 1.53e-03
+2022-05-03 15:50:39,245 INFO [train.py:715] (3/8) Epoch 0, batch 18500, loss[loss=0.2751, simple_loss=0.3218, pruned_loss=0.1142, over 4792.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2746, pruned_loss=0.08342, over 971333.89 frames.], batch size: 17, lr: 1.53e-03
+2022-05-03 15:51:19,775 INFO [train.py:715] (3/8) Epoch 0, batch 18550, loss[loss=0.1836, simple_loss=0.2354, pruned_loss=0.06587, over 4828.00 frames.], tot_loss[loss=0.2211, simple_loss=0.2746, pruned_loss=0.08385, over 971521.03 frames.], batch size: 12, lr: 1.53e-03
+2022-05-03 15:52:00,080 INFO [train.py:715] (3/8) Epoch 0, batch 18600, loss[loss=0.2301, simple_loss=0.2873, pruned_loss=0.08647, over 4890.00 frames.], tot_loss[loss=0.22, simple_loss=0.2737, pruned_loss=0.08313, over 971957.57 frames.], batch size: 22, lr: 1.53e-03
+2022-05-03 15:52:40,191 INFO [train.py:715] (3/8) Epoch 0, batch 18650, loss[loss=0.2291, simple_loss=0.2832, pruned_loss=0.08746, over 4856.00 frames.], tot_loss[loss=0.2197, simple_loss=0.2734, pruned_loss=0.08302, over 971530.02 frames.], batch size: 30, lr: 1.53e-03
+2022-05-03 15:53:19,597 INFO [train.py:715] (3/8) Epoch 0, batch 18700, loss[loss=0.2044, simple_loss=0.256, pruned_loss=0.07638, over 4825.00 frames.], tot_loss[loss=0.2201, simple_loss=0.2737, pruned_loss=0.0833, over 972049.99 frames.], batch size: 15, lr: 1.52e-03
+2022-05-03 15:53:59,903 INFO [train.py:715] (3/8) Epoch 0, batch 18750, loss[loss=0.222, simple_loss=0.2761, pruned_loss=0.08396, over 4945.00 frames.], tot_loss[loss=0.22, simple_loss=0.2737, pruned_loss=0.08316, over 972216.16 frames.], batch size: 39, lr: 1.52e-03
+2022-05-03 15:54:41,173 INFO [train.py:715] (3/8) Epoch 0, batch 18800, loss[loss=0.1956, simple_loss=0.2526, pruned_loss=0.06928, over 4793.00 frames.], tot_loss[loss=0.2198, simple_loss=0.2734, pruned_loss=0.08309, over 972515.66 frames.], batch size: 14, lr: 1.52e-03
+2022-05-03 15:55:20,399 INFO [train.py:715] (3/8) Epoch 0, batch 18850, loss[loss=0.2159, simple_loss=0.2728, pruned_loss=0.07952, over 4903.00 frames.], tot_loss[loss=0.22, simple_loss=0.2734, pruned_loss=0.08326, over 972923.01 frames.], batch size: 18, lr: 1.52e-03
+2022-05-03 15:56:01,305 INFO [train.py:715] (3/8) Epoch 0, batch 18900, loss[loss=0.2001, simple_loss=0.2568, pruned_loss=0.07163, over 4838.00 frames.], tot_loss[loss=0.2206, simple_loss=0.2742, pruned_loss=0.08343, over 973786.78 frames.], batch size: 13, lr: 1.52e-03
+2022-05-03 15:56:41,738 INFO [train.py:715] (3/8) Epoch 0, batch 18950, loss[loss=0.1698, simple_loss=0.2389, pruned_loss=0.05038, over 4930.00 frames.], tot_loss[loss=0.2206, simple_loss=0.2734, pruned_loss=0.08393, over 973400.09 frames.], batch size: 23, lr: 1.52e-03
+2022-05-03 15:57:21,399 INFO [train.py:715] (3/8) Epoch 0, batch 19000, loss[loss=0.2366, simple_loss=0.2882, pruned_loss=0.09255, over 4880.00 frames.], tot_loss[loss=0.2196, simple_loss=0.2727, pruned_loss=0.08331, over 972471.19 frames.], batch size: 20, lr: 1.51e-03
+2022-05-03 15:58:01,845 INFO [train.py:715] (3/8) Epoch 0, batch 19050, loss[loss=0.2459, simple_loss=0.292, pruned_loss=0.09992, over 4900.00 frames.], tot_loss[loss=0.221, simple_loss=0.2743, pruned_loss=0.08385, over 972679.83 frames.], batch size: 19, lr: 1.51e-03
+2022-05-03 15:58:42,180 INFO [train.py:715] (3/8) Epoch 0, batch 19100, loss[loss=0.2091, simple_loss=0.2797, pruned_loss=0.06921, over 4871.00 frames.], tot_loss[loss=0.2206, simple_loss=0.2743, pruned_loss=0.08351, over 973016.64 frames.], batch size: 16, lr: 1.51e-03
+2022-05-03 15:59:22,501 INFO [train.py:715] (3/8) Epoch 0, batch 19150, loss[loss=0.199, simple_loss=0.2578, pruned_loss=0.07007, over 4815.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2737, pruned_loss=0.08364, over 972876.56 frames.], batch size: 27, lr: 1.51e-03
+2022-05-03 16:00:01,713 INFO [train.py:715] (3/8) Epoch 0, batch 19200, loss[loss=0.2014, simple_loss=0.2527, pruned_loss=0.07505, over 4824.00 frames.], tot_loss[loss=0.2199, simple_loss=0.2731, pruned_loss=0.08338, over 972482.37 frames.], batch size: 25, lr: 1.51e-03
+2022-05-03 16:00:42,577 INFO [train.py:715] (3/8) Epoch 0, batch 19250, loss[loss=0.2632, simple_loss=0.2945, pruned_loss=0.1159, over 4935.00 frames.], tot_loss[loss=0.221, simple_loss=0.2745, pruned_loss=0.08376, over 971714.80 frames.], batch size: 29, lr: 1.50e-03
+2022-05-03 16:01:23,364 INFO [train.py:715] (3/8) Epoch 0, batch 19300, loss[loss=0.2165, simple_loss=0.2672, pruned_loss=0.0829, over 4827.00 frames.], tot_loss[loss=0.2202, simple_loss=0.2737, pruned_loss=0.08332, over 971404.74 frames.], batch size: 25, lr: 1.50e-03
+2022-05-03 16:02:03,053 INFO [train.py:715] (3/8) Epoch 0, batch 19350, loss[loss=0.2186, simple_loss=0.2693, pruned_loss=0.08398, over 4972.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2741, pruned_loss=0.08367, over 971499.58 frames.], batch size: 24, lr: 1.50e-03
+2022-05-03 16:02:43,212 INFO [train.py:715] (3/8) Epoch 0, batch 19400, loss[loss=0.1803, simple_loss=0.2431, pruned_loss=0.05874, over 4691.00 frames.], tot_loss[loss=0.221, simple_loss=0.2745, pruned_loss=0.0837, over 972310.40 frames.], batch size: 15, lr: 1.50e-03
+2022-05-03 16:03:24,060 INFO [train.py:715] (3/8) Epoch 0, batch 19450, loss[loss=0.218, simple_loss=0.2622, pruned_loss=0.08697, over 4811.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2725, pruned_loss=0.08211, over 972348.35 frames.], batch size: 26, lr: 1.50e-03
+2022-05-03 16:04:03,570 INFO [train.py:715] (3/8) Epoch 0, batch 19500, loss[loss=0.2512, simple_loss=0.2955, pruned_loss=0.1035, over 4777.00 frames.], tot_loss[loss=0.2213, simple_loss=0.2748, pruned_loss=0.08393, over 971929.93 frames.], batch size: 14, lr: 1.50e-03
+2022-05-03 16:04:42,924 INFO [train.py:715] (3/8) Epoch 0, batch 19550, loss[loss=0.21, simple_loss=0.2724, pruned_loss=0.07382, over 4690.00 frames.], tot_loss[loss=0.2191, simple_loss=0.2735, pruned_loss=0.08238, over 972340.55 frames.], batch size: 15, lr: 1.49e-03
+2022-05-03 16:05:23,276 INFO [train.py:715] (3/8) Epoch 0, batch 19600, loss[loss=0.1968, simple_loss=0.2442, pruned_loss=0.07473, over 4868.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2728, pruned_loss=0.08216, over 972440.14 frames.], batch size: 16, lr: 1.49e-03
+2022-05-03 16:06:03,058 INFO [train.py:715] (3/8) Epoch 0, batch 19650, loss[loss=0.2551, simple_loss=0.3095, pruned_loss=0.1003, over 4807.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2729, pruned_loss=0.08189, over 972503.78 frames.], batch size: 26, lr: 1.49e-03
+2022-05-03 16:06:42,545 INFO [train.py:715] (3/8) Epoch 0, batch 19700, loss[loss=0.2211, simple_loss=0.2667, pruned_loss=0.08773, over 4812.00 frames.], tot_loss[loss=0.219, simple_loss=0.2728, pruned_loss=0.08257, over 971543.64 frames.], batch size: 26, lr: 1.49e-03
+2022-05-03 16:07:22,615 INFO [train.py:715] (3/8) Epoch 0, batch 19750, loss[loss=0.278, simple_loss=0.3098, pruned_loss=0.1231, over 4813.00 frames.], tot_loss[loss=0.2211, simple_loss=0.2743, pruned_loss=0.08392, over 972049.46 frames.], batch size: 27, lr: 1.49e-03
+2022-05-03 16:08:02,295 INFO [train.py:715] (3/8) Epoch 0, batch 19800, loss[loss=0.1771, simple_loss=0.2406, pruned_loss=0.05676, over 4867.00 frames.], tot_loss[loss=0.2204, simple_loss=0.2743, pruned_loss=0.08323, over 972590.70 frames.], batch size: 16, lr: 1.48e-03
+2022-05-03 16:08:42,106 INFO [train.py:715] (3/8) Epoch 0, batch 19850, loss[loss=0.1967, simple_loss=0.2638, pruned_loss=0.0648, over 4869.00 frames.], tot_loss[loss=0.2216, simple_loss=0.2756, pruned_loss=0.08382, over 972923.94 frames.], batch size: 22, lr: 1.48e-03
+2022-05-03 16:09:21,341 INFO [train.py:715] (3/8) Epoch 0, batch 19900, loss[loss=0.2352, simple_loss=0.2874, pruned_loss=0.09152, over 4795.00 frames.], tot_loss[loss=0.2206, simple_loss=0.2745, pruned_loss=0.0834, over 973492.45 frames.], batch size: 24, lr: 1.48e-03
+2022-05-03 16:10:02,118 INFO [train.py:715] (3/8) Epoch 0, batch 19950, loss[loss=0.2336, simple_loss=0.2859, pruned_loss=0.09067, over 4931.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2728, pruned_loss=0.08228, over 972779.59 frames.], batch size: 29, lr: 1.48e-03
+2022-05-03 16:10:42,168 INFO [train.py:715] (3/8) Epoch 0, batch 20000, loss[loss=0.2182, simple_loss=0.2742, pruned_loss=0.08106, over 4967.00 frames.], tot_loss[loss=0.2176, simple_loss=0.2721, pruned_loss=0.08154, over 973335.77 frames.], batch size: 15, lr: 1.48e-03
+2022-05-03 16:11:21,520 INFO [train.py:715] (3/8) Epoch 0, batch 20050, loss[loss=0.2078, simple_loss=0.2642, pruned_loss=0.07571, over 4786.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2719, pruned_loss=0.08132, over 973260.12 frames.], batch size: 18, lr: 1.48e-03
+2022-05-03 16:12:01,699 INFO [train.py:715] (3/8) Epoch 0, batch 20100, loss[loss=0.2053, simple_loss=0.2645, pruned_loss=0.07306, over 4947.00 frames.], tot_loss[loss=0.2171, simple_loss=0.272, pruned_loss=0.0811, over 973201.94 frames.], batch size: 29, lr: 1.47e-03
+2022-05-03 16:12:41,689 INFO [train.py:715] (3/8) Epoch 0, batch 20150, loss[loss=0.2837, simple_loss=0.3262, pruned_loss=0.1205, over 4964.00 frames.], tot_loss[loss=0.2168, simple_loss=0.272, pruned_loss=0.08079, over 973253.98 frames.], batch size: 39, lr: 1.47e-03
+2022-05-03 16:13:21,724 INFO [train.py:715] (3/8) Epoch 0, batch 20200, loss[loss=0.2716, simple_loss=0.2992, pruned_loss=0.122, over 4846.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2713, pruned_loss=0.0807, over 973319.17 frames.], batch size: 32, lr: 1.47e-03
+2022-05-03 16:14:01,254 INFO [train.py:715] (3/8) Epoch 0, batch 20250, loss[loss=0.2357, simple_loss=0.3019, pruned_loss=0.08479, over 4743.00 frames.], tot_loss[loss=0.2164, simple_loss=0.271, pruned_loss=0.08092, over 972887.10 frames.], batch size: 16, lr: 1.47e-03
+2022-05-03 16:14:42,004 INFO [train.py:715] (3/8) Epoch 0, batch 20300, loss[loss=0.2304, simple_loss=0.2746, pruned_loss=0.0931, over 4879.00 frames.], tot_loss[loss=0.217, simple_loss=0.2715, pruned_loss=0.08125, over 972516.77 frames.], batch size: 32, lr: 1.47e-03
+2022-05-03 16:15:21,889 INFO [train.py:715] (3/8) Epoch 0, batch 20350, loss[loss=0.2359, simple_loss=0.2739, pruned_loss=0.09893, over 4856.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2713, pruned_loss=0.0816, over 972099.66 frames.], batch size: 32, lr: 1.47e-03
+2022-05-03 16:16:00,949 INFO [train.py:715] (3/8) Epoch 0, batch 20400, loss[loss=0.1806, simple_loss=0.2421, pruned_loss=0.0596, over 4906.00 frames.], tot_loss[loss=0.217, simple_loss=0.271, pruned_loss=0.0815, over 972079.15 frames.], batch size: 18, lr: 1.46e-03
+2022-05-03 16:16:40,895 INFO [train.py:715] (3/8) Epoch 0, batch 20450, loss[loss=0.1949, simple_loss=0.2564, pruned_loss=0.06669, over 4814.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2708, pruned_loss=0.08112, over 971700.25 frames.], batch size: 21, lr: 1.46e-03
+2022-05-03 16:17:20,435 INFO [train.py:715] (3/8) Epoch 0, batch 20500, loss[loss=0.2566, simple_loss=0.3007, pruned_loss=0.1062, over 4792.00 frames.], tot_loss[loss=0.217, simple_loss=0.2712, pruned_loss=0.08137, over 972443.78 frames.], batch size: 17, lr: 1.46e-03
+2022-05-03 16:18:00,495 INFO [train.py:715] (3/8) Epoch 0, batch 20550, loss[loss=0.1965, simple_loss=0.2514, pruned_loss=0.07085, over 4943.00 frames.], tot_loss[loss=0.2178, simple_loss=0.272, pruned_loss=0.08181, over 972795.07 frames.], batch size: 21, lr: 1.46e-03
+2022-05-03 16:18:39,952 INFO [train.py:715] (3/8) Epoch 0, batch 20600, loss[loss=0.2292, simple_loss=0.2828, pruned_loss=0.0878, over 4778.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2725, pruned_loss=0.08184, over 972428.57 frames.], batch size: 14, lr: 1.46e-03
+2022-05-03 16:19:19,642 INFO [train.py:715] (3/8) Epoch 0, batch 20650, loss[loss=0.2075, simple_loss=0.2577, pruned_loss=0.07871, over 4789.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2721, pruned_loss=0.08129, over 973047.84 frames.], batch size: 17, lr: 1.46e-03
+2022-05-03 16:20:00,374 INFO [train.py:715] (3/8) Epoch 0, batch 20700, loss[loss=0.1891, simple_loss=0.2609, pruned_loss=0.05862, over 4738.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2723, pruned_loss=0.08115, over 973214.61 frames.], batch size: 16, lr: 1.45e-03
+2022-05-03 16:20:39,702 INFO [train.py:715] (3/8) Epoch 0, batch 20750, loss[loss=0.199, simple_loss=0.2702, pruned_loss=0.06397, over 4771.00 frames.], tot_loss[loss=0.2176, simple_loss=0.2724, pruned_loss=0.08141, over 973163.84 frames.], batch size: 18, lr: 1.45e-03
+2022-05-03 16:21:19,882 INFO [train.py:715] (3/8) Epoch 0, batch 20800, loss[loss=0.2046, simple_loss=0.2546, pruned_loss=0.07732, over 4892.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2712, pruned_loss=0.08082, over 973170.86 frames.], batch size: 22, lr: 1.45e-03
+2022-05-03 16:21:59,635 INFO [train.py:715] (3/8) Epoch 0, batch 20850, loss[loss=0.2089, simple_loss=0.2592, pruned_loss=0.07928, over 4814.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2703, pruned_loss=0.08049, over 972362.83 frames.], batch size: 26, lr: 1.45e-03
+2022-05-03 16:22:39,124 INFO [train.py:715] (3/8) Epoch 0, batch 20900, loss[loss=0.2169, simple_loss=0.2625, pruned_loss=0.08565, over 4817.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2698, pruned_loss=0.08074, over 972650.61 frames.], batch size: 25, lr: 1.45e-03
+2022-05-03 16:23:19,648 INFO [train.py:715] (3/8) Epoch 0, batch 20950, loss[loss=0.2647, simple_loss=0.305, pruned_loss=0.1122, over 4698.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2695, pruned_loss=0.07974, over 973188.27 frames.], batch size: 15, lr: 1.45e-03
+2022-05-03 16:24:00,679 INFO [train.py:715] (3/8) Epoch 0, batch 21000, loss[loss=0.2376, simple_loss=0.2815, pruned_loss=0.09685, over 4895.00 frames.], tot_loss[loss=0.215, simple_loss=0.2698, pruned_loss=0.08013, over 973602.47 frames.], batch size: 23, lr: 1.44e-03
+2022-05-03 16:24:00,680 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 16:24:16,219 INFO [train.py:742] (3/8) Epoch 0, validation: loss=0.1386, simple_loss=0.2255, pruned_loss=0.02581, over 914524.00 frames.
+2022-05-03 16:24:57,014 INFO [train.py:715] (3/8) Epoch 0, batch 21050, loss[loss=0.2011, simple_loss=0.2648, pruned_loss=0.06869, over 4967.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2703, pruned_loss=0.08023, over 972623.85 frames.], batch size: 14, lr: 1.44e-03
+2022-05-03 16:25:36,594 INFO [train.py:715] (3/8) Epoch 0, batch 21100, loss[loss=0.2348, simple_loss=0.2815, pruned_loss=0.09402, over 4859.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2704, pruned_loss=0.08027, over 972630.39 frames.], batch size: 20, lr: 1.44e-03
+2022-05-03 16:26:16,950 INFO [train.py:715] (3/8) Epoch 0, batch 21150, loss[loss=0.1845, simple_loss=0.248, pruned_loss=0.06053, over 4948.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2697, pruned_loss=0.07977, over 973204.77 frames.], batch size: 21, lr: 1.44e-03
+2022-05-03 16:26:56,813 INFO [train.py:715] (3/8) Epoch 0, batch 21200, loss[loss=0.225, simple_loss=0.2783, pruned_loss=0.0858, over 4775.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2704, pruned_loss=0.0801, over 973513.06 frames.], batch size: 18, lr: 1.44e-03
+2022-05-03 16:27:37,351 INFO [train.py:715] (3/8) Epoch 0, batch 21250, loss[loss=0.2654, simple_loss=0.3128, pruned_loss=0.109, over 4969.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2705, pruned_loss=0.08017, over 973606.57 frames.], batch size: 28, lr: 1.44e-03
+2022-05-03 16:28:17,119 INFO [train.py:715] (3/8) Epoch 0, batch 21300, loss[loss=0.2383, simple_loss=0.2781, pruned_loss=0.09918, over 4932.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2695, pruned_loss=0.07948, over 973294.21 frames.], batch size: 29, lr: 1.43e-03
+2022-05-03 16:28:57,541 INFO [train.py:715] (3/8) Epoch 0, batch 21350, loss[loss=0.2399, simple_loss=0.2976, pruned_loss=0.09108, over 4942.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2684, pruned_loss=0.07837, over 973688.70 frames.], batch size: 29, lr: 1.43e-03
+2022-05-03 16:29:38,275 INFO [train.py:715] (3/8) Epoch 0, batch 21400, loss[loss=0.1827, simple_loss=0.2452, pruned_loss=0.06006, over 4975.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2691, pruned_loss=0.07864, over 973208.96 frames.], batch size: 28, lr: 1.43e-03
+2022-05-03 16:30:17,946 INFO [train.py:715] (3/8) Epoch 0, batch 21450, loss[loss=0.2497, simple_loss=0.2899, pruned_loss=0.1047, over 4923.00 frames.], tot_loss[loss=0.214, simple_loss=0.2695, pruned_loss=0.07926, over 973082.04 frames.], batch size: 35, lr: 1.43e-03
+2022-05-03 16:30:57,793 INFO [train.py:715] (3/8) Epoch 0, batch 21500, loss[loss=0.2463, simple_loss=0.301, pruned_loss=0.09585, over 4782.00 frames.], tot_loss[loss=0.2141, simple_loss=0.2693, pruned_loss=0.0794, over 973375.94 frames.], batch size: 19, lr: 1.43e-03
+2022-05-03 16:31:38,005 INFO [train.py:715] (3/8) Epoch 0, batch 21550, loss[loss=0.2022, simple_loss=0.2602, pruned_loss=0.07208, over 4907.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2684, pruned_loss=0.07867, over 972146.18 frames.], batch size: 22, lr: 1.43e-03
+2022-05-03 16:32:18,465 INFO [train.py:715] (3/8) Epoch 0, batch 21600, loss[loss=0.2382, simple_loss=0.2906, pruned_loss=0.09293, over 4984.00 frames.], tot_loss[loss=0.2133, simple_loss=0.2688, pruned_loss=0.07894, over 973272.27 frames.], batch size: 15, lr: 1.42e-03
+2022-05-03 16:32:58,249 INFO [train.py:715] (3/8) Epoch 0, batch 21650, loss[loss=0.1967, simple_loss=0.2641, pruned_loss=0.06468, over 4743.00 frames.], tot_loss[loss=0.214, simple_loss=0.2692, pruned_loss=0.07934, over 972670.94 frames.], batch size: 16, lr: 1.42e-03
+2022-05-03 16:33:39,061 INFO [train.py:715] (3/8) Epoch 0, batch 21700, loss[loss=0.2034, simple_loss=0.2539, pruned_loss=0.07646, over 4862.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2698, pruned_loss=0.08, over 973101.83 frames.], batch size: 16, lr: 1.42e-03
+2022-05-03 16:34:19,206 INFO [train.py:715] (3/8) Epoch 0, batch 21750, loss[loss=0.2052, simple_loss=0.2622, pruned_loss=0.07407, over 4806.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2685, pruned_loss=0.07896, over 972417.05 frames.], batch size: 25, lr: 1.42e-03
+2022-05-03 16:34:58,788 INFO [train.py:715] (3/8) Epoch 0, batch 21800, loss[loss=0.1676, simple_loss=0.232, pruned_loss=0.05166, over 4800.00 frames.], tot_loss[loss=0.2138, simple_loss=0.269, pruned_loss=0.07926, over 971903.79 frames.], batch size: 21, lr: 1.42e-03
+2022-05-03 16:35:38,617 INFO [train.py:715] (3/8) Epoch 0, batch 21850, loss[loss=0.2141, simple_loss=0.258, pruned_loss=0.08513, over 4987.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2697, pruned_loss=0.08021, over 971285.39 frames.], batch size: 15, lr: 1.42e-03
+2022-05-03 16:36:19,092 INFO [train.py:715] (3/8) Epoch 0, batch 21900, loss[loss=0.1866, simple_loss=0.256, pruned_loss=0.0586, over 4848.00 frames.], tot_loss[loss=0.215, simple_loss=0.2697, pruned_loss=0.08018, over 971249.93 frames.], batch size: 13, lr: 1.42e-03
+2022-05-03 16:36:59,000 INFO [train.py:715] (3/8) Epoch 0, batch 21950, loss[loss=0.1847, simple_loss=0.2505, pruned_loss=0.05944, over 4754.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2697, pruned_loss=0.08079, over 972188.27 frames.], batch size: 16, lr: 1.41e-03
+2022-05-03 16:37:38,285 INFO [train.py:715] (3/8) Epoch 0, batch 22000, loss[loss=0.2032, simple_loss=0.2665, pruned_loss=0.06989, over 4811.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2698, pruned_loss=0.0803, over 972675.58 frames.], batch size: 25, lr: 1.41e-03
+2022-05-03 16:38:18,443 INFO [train.py:715] (3/8) Epoch 0, batch 22050, loss[loss=0.2387, simple_loss=0.2885, pruned_loss=0.09449, over 4947.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2698, pruned_loss=0.08056, over 972875.15 frames.], batch size: 35, lr: 1.41e-03
+2022-05-03 16:38:58,600 INFO [train.py:715] (3/8) Epoch 0, batch 22100, loss[loss=0.2137, simple_loss=0.2686, pruned_loss=0.07942, over 4785.00 frames.], tot_loss[loss=0.216, simple_loss=0.2701, pruned_loss=0.08088, over 972709.69 frames.], batch size: 17, lr: 1.41e-03
+2022-05-03 16:39:38,114 INFO [train.py:715] (3/8) Epoch 0, batch 22150, loss[loss=0.1623, simple_loss=0.2264, pruned_loss=0.0491, over 4899.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2703, pruned_loss=0.08038, over 972260.57 frames.], batch size: 17, lr: 1.41e-03
+2022-05-03 16:40:17,923 INFO [train.py:715] (3/8) Epoch 0, batch 22200, loss[loss=0.2032, simple_loss=0.2688, pruned_loss=0.06883, over 4936.00 frames.], tot_loss[loss=0.215, simple_loss=0.2704, pruned_loss=0.07983, over 972525.14 frames.], batch size: 23, lr: 1.41e-03
+2022-05-03 16:40:58,310 INFO [train.py:715] (3/8) Epoch 0, batch 22250, loss[loss=0.1857, simple_loss=0.2553, pruned_loss=0.05799, over 4809.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2706, pruned_loss=0.07934, over 972262.99 frames.], batch size: 25, lr: 1.40e-03
+2022-05-03 16:41:38,377 INFO [train.py:715] (3/8) Epoch 0, batch 22300, loss[loss=0.1728, simple_loss=0.2525, pruned_loss=0.04653, over 4963.00 frames.], tot_loss[loss=0.2141, simple_loss=0.2706, pruned_loss=0.07879, over 971747.64 frames.], batch size: 21, lr: 1.40e-03
+2022-05-03 16:42:18,079 INFO [train.py:715] (3/8) Epoch 0, batch 22350, loss[loss=0.2109, simple_loss=0.2713, pruned_loss=0.07527, over 4772.00 frames.], tot_loss[loss=0.214, simple_loss=0.2703, pruned_loss=0.0789, over 971736.18 frames.], batch size: 18, lr: 1.40e-03
+2022-05-03 16:42:58,248 INFO [train.py:715] (3/8) Epoch 0, batch 22400, loss[loss=0.2282, simple_loss=0.28, pruned_loss=0.08825, over 4905.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2695, pruned_loss=0.07877, over 971806.47 frames.], batch size: 17, lr: 1.40e-03
+2022-05-03 16:43:38,081 INFO [train.py:715] (3/8) Epoch 0, batch 22450, loss[loss=0.2321, simple_loss=0.295, pruned_loss=0.08457, over 4959.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2707, pruned_loss=0.07992, over 972571.26 frames.], batch size: 15, lr: 1.40e-03
+2022-05-03 16:44:17,444 INFO [train.py:715] (3/8) Epoch 0, batch 22500, loss[loss=0.1967, simple_loss=0.2636, pruned_loss=0.06491, over 4882.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2697, pruned_loss=0.07952, over 972009.68 frames.], batch size: 22, lr: 1.40e-03
+2022-05-03 16:44:57,226 INFO [train.py:715] (3/8) Epoch 0, batch 22550, loss[loss=0.2056, simple_loss=0.2639, pruned_loss=0.07364, over 4873.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2702, pruned_loss=0.07966, over 972483.12 frames.], batch size: 16, lr: 1.40e-03
+2022-05-03 16:45:37,437 INFO [train.py:715] (3/8) Epoch 0, batch 22600, loss[loss=0.2764, simple_loss=0.3271, pruned_loss=0.1128, over 4848.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2699, pruned_loss=0.07984, over 973090.37 frames.], batch size: 30, lr: 1.39e-03
+2022-05-03 16:46:18,079 INFO [train.py:715] (3/8) Epoch 0, batch 22650, loss[loss=0.1931, simple_loss=0.2594, pruned_loss=0.06339, over 4936.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2712, pruned_loss=0.08063, over 971665.01 frames.], batch size: 29, lr: 1.39e-03
+2022-05-03 16:46:57,295 INFO [train.py:715] (3/8) Epoch 0, batch 22700, loss[loss=0.2173, simple_loss=0.2629, pruned_loss=0.08585, over 4775.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2701, pruned_loss=0.07932, over 972333.36 frames.], batch size: 18, lr: 1.39e-03
+2022-05-03 16:47:37,376 INFO [train.py:715] (3/8) Epoch 0, batch 22750, loss[loss=0.2076, simple_loss=0.2668, pruned_loss=0.07426, over 4981.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2706, pruned_loss=0.07953, over 972562.24 frames.], batch size: 15, lr: 1.39e-03
+2022-05-03 16:48:17,858 INFO [train.py:715] (3/8) Epoch 0, batch 22800, loss[loss=0.2552, simple_loss=0.3104, pruned_loss=0.1, over 4975.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2716, pruned_loss=0.08005, over 972102.22 frames.], batch size: 39, lr: 1.39e-03
+2022-05-03 16:48:57,451 INFO [train.py:715] (3/8) Epoch 0, batch 22850, loss[loss=0.2049, simple_loss=0.2765, pruned_loss=0.06668, over 4911.00 frames.], tot_loss[loss=0.216, simple_loss=0.2716, pruned_loss=0.08016, over 972287.12 frames.], batch size: 29, lr: 1.39e-03
+2022-05-03 16:49:37,563 INFO [train.py:715] (3/8) Epoch 0, batch 22900, loss[loss=0.1689, simple_loss=0.2403, pruned_loss=0.04879, over 4793.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2706, pruned_loss=0.07923, over 972328.24 frames.], batch size: 12, lr: 1.39e-03
+2022-05-03 16:50:17,833 INFO [train.py:715] (3/8) Epoch 0, batch 22950, loss[loss=0.192, simple_loss=0.2473, pruned_loss=0.06833, over 4886.00 frames.], tot_loss[loss=0.2134, simple_loss=0.2694, pruned_loss=0.07864, over 973237.19 frames.], batch size: 19, lr: 1.38e-03
+2022-05-03 16:50:58,460 INFO [train.py:715] (3/8) Epoch 0, batch 23000, loss[loss=0.2183, simple_loss=0.2654, pruned_loss=0.08559, over 4805.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2694, pruned_loss=0.07896, over 972986.05 frames.], batch size: 21, lr: 1.38e-03
+2022-05-03 16:51:37,472 INFO [train.py:715] (3/8) Epoch 0, batch 23050, loss[loss=0.2256, simple_loss=0.2848, pruned_loss=0.08325, over 4812.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2694, pruned_loss=0.07901, over 972268.60 frames.], batch size: 13, lr: 1.38e-03
+2022-05-03 16:52:18,413 INFO [train.py:715] (3/8) Epoch 0, batch 23100, loss[loss=0.2525, simple_loss=0.2954, pruned_loss=0.1048, over 4951.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2699, pruned_loss=0.07943, over 972629.52 frames.], batch size: 39, lr: 1.38e-03
+2022-05-03 16:52:59,434 INFO [train.py:715] (3/8) Epoch 0, batch 23150, loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04324, over 4913.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2693, pruned_loss=0.07883, over 972321.58 frames.], batch size: 17, lr: 1.38e-03
+2022-05-03 16:53:39,181 INFO [train.py:715] (3/8) Epoch 0, batch 23200, loss[loss=0.1481, simple_loss=0.2128, pruned_loss=0.04167, over 4993.00 frames.], tot_loss[loss=0.213, simple_loss=0.2686, pruned_loss=0.07869, over 973288.62 frames.], batch size: 16, lr: 1.38e-03
+2022-05-03 16:54:19,750 INFO [train.py:715] (3/8) Epoch 0, batch 23250, loss[loss=0.205, simple_loss=0.2655, pruned_loss=0.07226, over 4860.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2692, pruned_loss=0.07903, over 973408.46 frames.], batch size: 32, lr: 1.38e-03
+2022-05-03 16:55:00,174 INFO [train.py:715] (3/8) Epoch 0, batch 23300, loss[loss=0.1886, simple_loss=0.248, pruned_loss=0.06457, over 4913.00 frames.], tot_loss[loss=0.2132, simple_loss=0.269, pruned_loss=0.07871, over 973765.10 frames.], batch size: 29, lr: 1.37e-03
+2022-05-03 16:55:40,656 INFO [train.py:715] (3/8) Epoch 0, batch 23350, loss[loss=0.2662, simple_loss=0.3091, pruned_loss=0.1117, over 4941.00 frames.], tot_loss[loss=0.2144, simple_loss=0.27, pruned_loss=0.0794, over 974221.79 frames.], batch size: 39, lr: 1.37e-03
+2022-05-03 16:56:21,250 INFO [train.py:715] (3/8) Epoch 0, batch 23400, loss[loss=0.1893, simple_loss=0.262, pruned_loss=0.05834, over 4901.00 frames.], tot_loss[loss=0.215, simple_loss=0.2705, pruned_loss=0.07971, over 973469.01 frames.], batch size: 22, lr: 1.37e-03
+2022-05-03 16:57:02,266 INFO [train.py:715] (3/8) Epoch 0, batch 23450, loss[loss=0.2242, simple_loss=0.2843, pruned_loss=0.08206, over 4914.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2696, pruned_loss=0.07866, over 973145.68 frames.], batch size: 23, lr: 1.37e-03
+2022-05-03 16:57:43,369 INFO [train.py:715] (3/8) Epoch 0, batch 23500, loss[loss=0.2593, simple_loss=0.2934, pruned_loss=0.1126, over 4750.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2689, pruned_loss=0.07832, over 972303.24 frames.], batch size: 16, lr: 1.37e-03
+2022-05-03 16:58:23,221 INFO [train.py:715] (3/8) Epoch 0, batch 23550, loss[loss=0.1773, simple_loss=0.2408, pruned_loss=0.05684, over 4824.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2691, pruned_loss=0.07801, over 972834.92 frames.], batch size: 27, lr: 1.37e-03
+2022-05-03 16:59:04,081 INFO [train.py:715] (3/8) Epoch 0, batch 23600, loss[loss=0.2315, simple_loss=0.2861, pruned_loss=0.08848, over 4967.00 frames.], tot_loss[loss=0.215, simple_loss=0.2708, pruned_loss=0.07964, over 973370.15 frames.], batch size: 28, lr: 1.37e-03
+2022-05-03 16:59:44,345 INFO [train.py:715] (3/8) Epoch 0, batch 23650, loss[loss=0.1757, simple_loss=0.2456, pruned_loss=0.05287, over 4943.00 frames.], tot_loss[loss=0.2141, simple_loss=0.2701, pruned_loss=0.07903, over 972636.62 frames.], batch size: 21, lr: 1.36e-03
+2022-05-03 17:00:24,466 INFO [train.py:715] (3/8) Epoch 0, batch 23700, loss[loss=0.2211, simple_loss=0.2707, pruned_loss=0.0858, over 4934.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2699, pruned_loss=0.07889, over 972825.06 frames.], batch size: 18, lr: 1.36e-03
+2022-05-03 17:01:03,657 INFO [train.py:715] (3/8) Epoch 0, batch 23750, loss[loss=0.2143, simple_loss=0.2708, pruned_loss=0.07895, over 4880.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2696, pruned_loss=0.0781, over 972373.96 frames.], batch size: 32, lr: 1.36e-03
+2022-05-03 17:01:43,658 INFO [train.py:715] (3/8) Epoch 0, batch 23800, loss[loss=0.1983, simple_loss=0.2587, pruned_loss=0.06896, over 4827.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2706, pruned_loss=0.07919, over 972347.51 frames.], batch size: 30, lr: 1.36e-03
+2022-05-03 17:02:24,141 INFO [train.py:715] (3/8) Epoch 0, batch 23850, loss[loss=0.2356, simple_loss=0.2884, pruned_loss=0.09144, over 4969.00 frames.], tot_loss[loss=0.214, simple_loss=0.2699, pruned_loss=0.07903, over 972726.87 frames.], batch size: 25, lr: 1.36e-03
+2022-05-03 17:03:03,303 INFO [train.py:715] (3/8) Epoch 0, batch 23900, loss[loss=0.1762, simple_loss=0.2404, pruned_loss=0.05599, over 4859.00 frames.], tot_loss[loss=0.2118, simple_loss=0.2685, pruned_loss=0.0775, over 973190.80 frames.], batch size: 12, lr: 1.36e-03
+2022-05-03 17:03:43,452 INFO [train.py:715] (3/8) Epoch 0, batch 23950, loss[loss=0.2051, simple_loss=0.2601, pruned_loss=0.07506, over 4911.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2692, pruned_loss=0.07864, over 972518.00 frames.], batch size: 18, lr: 1.36e-03
+2022-05-03 17:04:26,580 INFO [train.py:715] (3/8) Epoch 0, batch 24000, loss[loss=0.1931, simple_loss=0.2549, pruned_loss=0.06568, over 4814.00 frames.], tot_loss[loss=0.213, simple_loss=0.2691, pruned_loss=0.0785, over 972176.45 frames.], batch size: 13, lr: 1.35e-03
+2022-05-03 17:04:26,581 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 17:04:40,850 INFO [train.py:742] (3/8) Epoch 0, validation: loss=0.1357, simple_loss=0.2226, pruned_loss=0.02435, over 914524.00 frames.
+2022-05-03 17:05:21,167 INFO [train.py:715] (3/8) Epoch 0, batch 24050, loss[loss=0.2111, simple_loss=0.2673, pruned_loss=0.07745, over 4834.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2691, pruned_loss=0.07894, over 972445.98 frames.], batch size: 26, lr: 1.35e-03
+2022-05-03 17:06:00,591 INFO [train.py:715] (3/8) Epoch 0, batch 24100, loss[loss=0.285, simple_loss=0.3144, pruned_loss=0.1278, over 4912.00 frames.], tot_loss[loss=0.213, simple_loss=0.2688, pruned_loss=0.07864, over 972353.22 frames.], batch size: 39, lr: 1.35e-03
+2022-05-03 17:06:40,578 INFO [train.py:715] (3/8) Epoch 0, batch 24150, loss[loss=0.1914, simple_loss=0.2498, pruned_loss=0.06651, over 4808.00 frames.], tot_loss[loss=0.2118, simple_loss=0.2676, pruned_loss=0.07796, over 972384.06 frames.], batch size: 26, lr: 1.35e-03
+2022-05-03 17:07:20,599 INFO [train.py:715] (3/8) Epoch 0, batch 24200, loss[loss=0.1648, simple_loss=0.236, pruned_loss=0.04677, over 4755.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2666, pruned_loss=0.07706, over 972801.69 frames.], batch size: 19, lr: 1.35e-03
+2022-05-03 17:08:01,222 INFO [train.py:715] (3/8) Epoch 0, batch 24250, loss[loss=0.204, simple_loss=0.2671, pruned_loss=0.07042, over 4892.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2662, pruned_loss=0.07657, over 973810.88 frames.], batch size: 38, lr: 1.35e-03
+2022-05-03 17:08:40,831 INFO [train.py:715] (3/8) Epoch 0, batch 24300, loss[loss=0.1935, simple_loss=0.2415, pruned_loss=0.07272, over 4850.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2671, pruned_loss=0.07729, over 974237.67 frames.], batch size: 32, lr: 1.35e-03
+2022-05-03 17:09:21,010 INFO [train.py:715] (3/8) Epoch 0, batch 24350, loss[loss=0.1883, simple_loss=0.2517, pruned_loss=0.06247, over 4687.00 frames.], tot_loss[loss=0.211, simple_loss=0.2674, pruned_loss=0.07724, over 973171.82 frames.], batch size: 15, lr: 1.35e-03
+2022-05-03 17:10:01,416 INFO [train.py:715] (3/8) Epoch 0, batch 24400, loss[loss=0.2172, simple_loss=0.2681, pruned_loss=0.08321, over 4908.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2668, pruned_loss=0.07682, over 972897.81 frames.], batch size: 17, lr: 1.34e-03
+2022-05-03 17:10:40,936 INFO [train.py:715] (3/8) Epoch 0, batch 24450, loss[loss=0.1489, simple_loss=0.2199, pruned_loss=0.03894, over 4936.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2672, pruned_loss=0.07686, over 972613.64 frames.], batch size: 21, lr: 1.34e-03
+2022-05-03 17:11:21,047 INFO [train.py:715] (3/8) Epoch 0, batch 24500, loss[loss=0.2255, simple_loss=0.2668, pruned_loss=0.09209, over 4788.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2672, pruned_loss=0.07707, over 971988.11 frames.], batch size: 17, lr: 1.34e-03
+2022-05-03 17:12:01,317 INFO [train.py:715] (3/8) Epoch 0, batch 24550, loss[loss=0.1705, simple_loss=0.2292, pruned_loss=0.05591, over 4904.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2672, pruned_loss=0.07703, over 972495.97 frames.], batch size: 17, lr: 1.34e-03
+2022-05-03 17:12:41,511 INFO [train.py:715] (3/8) Epoch 0, batch 24600, loss[loss=0.2088, simple_loss=0.2709, pruned_loss=0.0734, over 4759.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2681, pruned_loss=0.07739, over 971980.63 frames.], batch size: 19, lr: 1.34e-03
+2022-05-03 17:13:20,989 INFO [train.py:715] (3/8) Epoch 0, batch 24650, loss[loss=0.2022, simple_loss=0.2633, pruned_loss=0.0705, over 4913.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2671, pruned_loss=0.07664, over 972187.42 frames.], batch size: 18, lr: 1.34e-03
+2022-05-03 17:14:01,415 INFO [train.py:715] (3/8) Epoch 0, batch 24700, loss[loss=0.2354, simple_loss=0.2953, pruned_loss=0.08771, over 4775.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2677, pruned_loss=0.07679, over 971387.21 frames.], batch size: 17, lr: 1.34e-03
+2022-05-03 17:14:42,117 INFO [train.py:715] (3/8) Epoch 0, batch 24750, loss[loss=0.1969, simple_loss=0.2625, pruned_loss=0.06559, over 4818.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2677, pruned_loss=0.07676, over 971252.10 frames.], batch size: 25, lr: 1.33e-03
+2022-05-03 17:15:21,170 INFO [train.py:715] (3/8) Epoch 0, batch 24800, loss[loss=0.2064, simple_loss=0.2706, pruned_loss=0.07114, over 4956.00 frames.], tot_loss[loss=0.2104, simple_loss=0.267, pruned_loss=0.07686, over 971760.31 frames.], batch size: 35, lr: 1.33e-03
+2022-05-03 17:16:01,308 INFO [train.py:715] (3/8) Epoch 0, batch 24850, loss[loss=0.213, simple_loss=0.2638, pruned_loss=0.08117, over 4801.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2674, pruned_loss=0.07706, over 971504.77 frames.], batch size: 21, lr: 1.33e-03
+2022-05-03 17:16:41,586 INFO [train.py:715] (3/8) Epoch 0, batch 24900, loss[loss=0.221, simple_loss=0.2834, pruned_loss=0.07928, over 4752.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2671, pruned_loss=0.07672, over 972066.47 frames.], batch size: 19, lr: 1.33e-03
+2022-05-03 17:17:21,630 INFO [train.py:715] (3/8) Epoch 0, batch 24950, loss[loss=0.2223, simple_loss=0.2648, pruned_loss=0.08987, over 4937.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2664, pruned_loss=0.07636, over 972181.66 frames.], batch size: 29, lr: 1.33e-03
+2022-05-03 17:18:01,146 INFO [train.py:715] (3/8) Epoch 0, batch 25000, loss[loss=0.194, simple_loss=0.2461, pruned_loss=0.07093, over 4785.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2657, pruned_loss=0.07588, over 971160.42 frames.], batch size: 17, lr: 1.33e-03
+2022-05-03 17:18:41,403 INFO [train.py:715] (3/8) Epoch 0, batch 25050, loss[loss=0.1993, simple_loss=0.2684, pruned_loss=0.06512, over 4970.00 frames.], tot_loss[loss=0.2088, simple_loss=0.266, pruned_loss=0.07579, over 971540.83 frames.], batch size: 35, lr: 1.33e-03
+2022-05-03 17:19:21,100 INFO [train.py:715] (3/8) Epoch 0, batch 25100, loss[loss=0.2285, simple_loss=0.2888, pruned_loss=0.0841, over 4985.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2664, pruned_loss=0.07618, over 971682.14 frames.], batch size: 39, lr: 1.33e-03
+2022-05-03 17:20:00,597 INFO [train.py:715] (3/8) Epoch 0, batch 25150, loss[loss=0.2077, simple_loss=0.2678, pruned_loss=0.07375, over 4815.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2664, pruned_loss=0.07621, over 972376.52 frames.], batch size: 26, lr: 1.32e-03
+2022-05-03 17:20:41,129 INFO [train.py:715] (3/8) Epoch 0, batch 25200, loss[loss=0.2349, simple_loss=0.2789, pruned_loss=0.09549, over 4846.00 frames.], tot_loss[loss=0.21, simple_loss=0.2667, pruned_loss=0.07658, over 972308.11 frames.], batch size: 30, lr: 1.32e-03
+2022-05-03 17:21:21,698 INFO [train.py:715] (3/8) Epoch 0, batch 25250, loss[loss=0.2098, simple_loss=0.2687, pruned_loss=0.0754, over 4763.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2664, pruned_loss=0.07606, over 971787.18 frames.], batch size: 19, lr: 1.32e-03
+2022-05-03 17:22:02,260 INFO [train.py:715] (3/8) Epoch 0, batch 25300, loss[loss=0.156, simple_loss=0.2242, pruned_loss=0.04385, over 4931.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2674, pruned_loss=0.07674, over 972143.62 frames.], batch size: 29, lr: 1.32e-03
+2022-05-03 17:22:42,092 INFO [train.py:715] (3/8) Epoch 0, batch 25350, loss[loss=0.2189, simple_loss=0.2774, pruned_loss=0.08024, over 4955.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2677, pruned_loss=0.07696, over 971242.33 frames.], batch size: 21, lr: 1.32e-03
+2022-05-03 17:23:22,549 INFO [train.py:715] (3/8) Epoch 0, batch 25400, loss[loss=0.2119, simple_loss=0.2647, pruned_loss=0.07951, over 4888.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2681, pruned_loss=0.07732, over 971608.60 frames.], batch size: 22, lr: 1.32e-03
+2022-05-03 17:24:02,719 INFO [train.py:715] (3/8) Epoch 0, batch 25450, loss[loss=0.1719, simple_loss=0.2421, pruned_loss=0.05087, over 4820.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2675, pruned_loss=0.07684, over 972233.54 frames.], batch size: 25, lr: 1.32e-03
+2022-05-03 17:24:41,710 INFO [train.py:715] (3/8) Epoch 0, batch 25500, loss[loss=0.2278, simple_loss=0.285, pruned_loss=0.08532, over 4757.00 frames.], tot_loss[loss=0.2097, simple_loss=0.267, pruned_loss=0.07615, over 973917.54 frames.], batch size: 19, lr: 1.32e-03
+2022-05-03 17:25:22,413 INFO [train.py:715] (3/8) Epoch 0, batch 25550, loss[loss=0.2121, simple_loss=0.2598, pruned_loss=0.08218, over 4912.00 frames.], tot_loss[loss=0.2099, simple_loss=0.267, pruned_loss=0.07637, over 973575.41 frames.], batch size: 17, lr: 1.31e-03
+2022-05-03 17:26:02,026 INFO [train.py:715] (3/8) Epoch 0, batch 25600, loss[loss=0.185, simple_loss=0.2398, pruned_loss=0.06505, over 4759.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2662, pruned_loss=0.07582, over 973803.68 frames.], batch size: 14, lr: 1.31e-03
+2022-05-03 17:26:41,734 INFO [train.py:715] (3/8) Epoch 0, batch 25650, loss[loss=0.1959, simple_loss=0.249, pruned_loss=0.0714, over 4780.00 frames.], tot_loss[loss=0.2076, simple_loss=0.265, pruned_loss=0.07513, over 973025.61 frames.], batch size: 14, lr: 1.31e-03
+2022-05-03 17:27:21,448 INFO [train.py:715] (3/8) Epoch 0, batch 25700, loss[loss=0.2432, simple_loss=0.2828, pruned_loss=0.1018, over 4840.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2659, pruned_loss=0.0755, over 973164.37 frames.], batch size: 32, lr: 1.31e-03
+2022-05-03 17:28:01,730 INFO [train.py:715] (3/8) Epoch 0, batch 25750, loss[loss=0.2275, simple_loss=0.2845, pruned_loss=0.08524, over 4810.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2663, pruned_loss=0.07634, over 972734.92 frames.], batch size: 25, lr: 1.31e-03
+2022-05-03 17:28:41,508 INFO [train.py:715] (3/8) Epoch 0, batch 25800, loss[loss=0.2079, simple_loss=0.2727, pruned_loss=0.07151, over 4740.00 frames.], tot_loss[loss=0.21, simple_loss=0.2668, pruned_loss=0.07655, over 972495.13 frames.], batch size: 16, lr: 1.31e-03
+2022-05-03 17:29:20,753 INFO [train.py:715] (3/8) Epoch 0, batch 25850, loss[loss=0.1719, simple_loss=0.2351, pruned_loss=0.05429, over 4876.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2666, pruned_loss=0.07648, over 973103.98 frames.], batch size: 22, lr: 1.31e-03
+2022-05-03 17:30:01,470 INFO [train.py:715] (3/8) Epoch 0, batch 25900, loss[loss=0.2247, simple_loss=0.2706, pruned_loss=0.08945, over 4833.00 frames.], tot_loss[loss=0.209, simple_loss=0.2662, pruned_loss=0.0759, over 973290.84 frames.], batch size: 30, lr: 1.31e-03
+2022-05-03 17:30:41,208 INFO [train.py:715] (3/8) Epoch 0, batch 25950, loss[loss=0.2385, simple_loss=0.2873, pruned_loss=0.09485, over 4812.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2669, pruned_loss=0.07637, over 972773.64 frames.], batch size: 13, lr: 1.30e-03
+2022-05-03 17:31:21,225 INFO [train.py:715] (3/8) Epoch 0, batch 26000, loss[loss=0.2246, simple_loss=0.2597, pruned_loss=0.09476, over 4757.00 frames.], tot_loss[loss=0.2111, simple_loss=0.268, pruned_loss=0.07704, over 972233.71 frames.], batch size: 12, lr: 1.30e-03
+2022-05-03 17:32:01,169 INFO [train.py:715] (3/8) Epoch 0, batch 26050, loss[loss=0.21, simple_loss=0.2554, pruned_loss=0.08227, over 4788.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2675, pruned_loss=0.07671, over 972039.35 frames.], batch size: 14, lr: 1.30e-03
+2022-05-03 17:32:41,632 INFO [train.py:715] (3/8) Epoch 0, batch 26100, loss[loss=0.2101, simple_loss=0.2656, pruned_loss=0.07735, over 4782.00 frames.], tot_loss[loss=0.21, simple_loss=0.2671, pruned_loss=0.07648, over 971258.66 frames.], batch size: 14, lr: 1.30e-03
+2022-05-03 17:33:21,952 INFO [train.py:715] (3/8) Epoch 0, batch 26150, loss[loss=0.2199, simple_loss=0.2631, pruned_loss=0.08829, over 4823.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2666, pruned_loss=0.07602, over 971775.42 frames.], batch size: 15, lr: 1.30e-03
+2022-05-03 17:34:00,855 INFO [train.py:715] (3/8) Epoch 0, batch 26200, loss[loss=0.2138, simple_loss=0.2644, pruned_loss=0.08163, over 4959.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2651, pruned_loss=0.07519, over 972367.29 frames.], batch size: 35, lr: 1.30e-03
+2022-05-03 17:34:41,485 INFO [train.py:715] (3/8) Epoch 0, batch 26250, loss[loss=0.1644, simple_loss=0.2291, pruned_loss=0.04988, over 4981.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2647, pruned_loss=0.07526, over 972154.55 frames.], batch size: 14, lr: 1.30e-03
+2022-05-03 17:35:21,434 INFO [train.py:715] (3/8) Epoch 0, batch 26300, loss[loss=0.2151, simple_loss=0.2707, pruned_loss=0.07975, over 4900.00 frames.], tot_loss[loss=0.207, simple_loss=0.2642, pruned_loss=0.07488, over 970942.20 frames.], batch size: 17, lr: 1.30e-03
+2022-05-03 17:36:01,269 INFO [train.py:715] (3/8) Epoch 0, batch 26350, loss[loss=0.1984, simple_loss=0.2618, pruned_loss=0.06747, over 4893.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2643, pruned_loss=0.0747, over 971907.84 frames.], batch size: 17, lr: 1.30e-03
+2022-05-03 17:36:41,216 INFO [train.py:715] (3/8) Epoch 0, batch 26400, loss[loss=0.1862, simple_loss=0.2535, pruned_loss=0.05942, over 4913.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2653, pruned_loss=0.07521, over 972170.31 frames.], batch size: 39, lr: 1.29e-03
+2022-05-03 17:37:21,338 INFO [train.py:715] (3/8) Epoch 0, batch 26450, loss[loss=0.1663, simple_loss=0.227, pruned_loss=0.05277, over 4782.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2647, pruned_loss=0.07483, over 972091.68 frames.], batch size: 17, lr: 1.29e-03
+2022-05-03 17:38:02,047 INFO [train.py:715] (3/8) Epoch 0, batch 26500, loss[loss=0.2163, simple_loss=0.2744, pruned_loss=0.07911, over 4749.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2652, pruned_loss=0.07589, over 972259.79 frames.], batch size: 16, lr: 1.29e-03
+2022-05-03 17:38:41,408 INFO [train.py:715] (3/8) Epoch 0, batch 26550, loss[loss=0.1862, simple_loss=0.2563, pruned_loss=0.05805, over 4892.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2637, pruned_loss=0.07484, over 973145.15 frames.], batch size: 22, lr: 1.29e-03
+2022-05-03 17:39:21,083 INFO [train.py:715] (3/8) Epoch 0, batch 26600, loss[loss=0.1922, simple_loss=0.2378, pruned_loss=0.07327, over 4839.00 frames.], tot_loss[loss=0.206, simple_loss=0.2631, pruned_loss=0.07447, over 972900.93 frames.], batch size: 13, lr: 1.29e-03
+2022-05-03 17:40:01,332 INFO [train.py:715] (3/8) Epoch 0, batch 26650, loss[loss=0.2177, simple_loss=0.2592, pruned_loss=0.08809, over 4865.00 frames.], tot_loss[loss=0.207, simple_loss=0.2638, pruned_loss=0.0751, over 973665.18 frames.], batch size: 32, lr: 1.29e-03
+2022-05-03 17:40:40,793 INFO [train.py:715] (3/8) Epoch 0, batch 26700, loss[loss=0.3117, simple_loss=0.3811, pruned_loss=0.1211, over 4802.00 frames.], tot_loss[loss=0.2069, simple_loss=0.264, pruned_loss=0.07484, over 974961.72 frames.], batch size: 18, lr: 1.29e-03
+2022-05-03 17:41:20,819 INFO [train.py:715] (3/8) Epoch 0, batch 26750, loss[loss=0.2419, simple_loss=0.2947, pruned_loss=0.09458, over 4899.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2643, pruned_loss=0.07525, over 974295.24 frames.], batch size: 39, lr: 1.29e-03
+2022-05-03 17:42:01,248 INFO [train.py:715] (3/8) Epoch 0, batch 26800, loss[loss=0.1945, simple_loss=0.2554, pruned_loss=0.06678, over 4710.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2647, pruned_loss=0.07521, over 973523.36 frames.], batch size: 15, lr: 1.28e-03
+2022-05-03 17:42:41,667 INFO [train.py:715] (3/8) Epoch 0, batch 26850, loss[loss=0.1861, simple_loss=0.2463, pruned_loss=0.06299, over 4975.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2641, pruned_loss=0.07476, over 972724.97 frames.], batch size: 24, lr: 1.28e-03
+2022-05-03 17:43:21,530 INFO [train.py:715] (3/8) Epoch 0, batch 26900, loss[loss=0.2461, simple_loss=0.2953, pruned_loss=0.09846, over 4967.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2643, pruned_loss=0.07554, over 971698.53 frames.], batch size: 24, lr: 1.28e-03
+2022-05-03 17:44:02,263 INFO [train.py:715] (3/8) Epoch 0, batch 26950, loss[loss=0.2991, simple_loss=0.3502, pruned_loss=0.124, over 4879.00 frames.], tot_loss[loss=0.209, simple_loss=0.2657, pruned_loss=0.07617, over 972494.13 frames.], batch size: 22, lr: 1.28e-03
+2022-05-03 17:44:42,415 INFO [train.py:715] (3/8) Epoch 0, batch 27000, loss[loss=0.1602, simple_loss=0.2285, pruned_loss=0.04598, over 4941.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2671, pruned_loss=0.07721, over 972796.78 frames.], batch size: 23, lr: 1.28e-03
+2022-05-03 17:44:42,416 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 17:44:51,200 INFO [train.py:742] (3/8) Epoch 0, validation: loss=0.1338, simple_loss=0.2208, pruned_loss=0.02337, over 914524.00 frames.
+2022-05-03 17:45:31,268 INFO [train.py:715] (3/8) Epoch 0, batch 27050, loss[loss=0.1884, simple_loss=0.246, pruned_loss=0.0654, over 4895.00 frames.], tot_loss[loss=0.2112, simple_loss=0.2673, pruned_loss=0.07761, over 972225.70 frames.], batch size: 19, lr: 1.28e-03
+2022-05-03 17:46:10,742 INFO [train.py:715] (3/8) Epoch 0, batch 27100, loss[loss=0.287, simple_loss=0.329, pruned_loss=0.1225, over 4843.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2667, pruned_loss=0.07679, over 971666.56 frames.], batch size: 32, lr: 1.28e-03
+2022-05-03 17:46:51,328 INFO [train.py:715] (3/8) Epoch 0, batch 27150, loss[loss=0.1887, simple_loss=0.2513, pruned_loss=0.06305, over 4817.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2667, pruned_loss=0.07645, over 972320.26 frames.], batch size: 26, lr: 1.28e-03
+2022-05-03 17:47:31,709 INFO [train.py:715] (3/8) Epoch 0, batch 27200, loss[loss=0.206, simple_loss=0.2528, pruned_loss=0.07965, over 4948.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2653, pruned_loss=0.07566, over 972764.32 frames.], batch size: 39, lr: 1.28e-03
+2022-05-03 17:48:11,810 INFO [train.py:715] (3/8) Epoch 0, batch 27250, loss[loss=0.1983, simple_loss=0.2579, pruned_loss=0.06932, over 4831.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2653, pruned_loss=0.07504, over 972805.82 frames.], batch size: 15, lr: 1.27e-03
+2022-05-03 17:48:51,955 INFO [train.py:715] (3/8) Epoch 0, batch 27300, loss[loss=0.1518, simple_loss=0.2187, pruned_loss=0.04249, over 4933.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2649, pruned_loss=0.07436, over 972562.17 frames.], batch size: 21, lr: 1.27e-03
+2022-05-03 17:49:31,860 INFO [train.py:715] (3/8) Epoch 0, batch 27350, loss[loss=0.2019, simple_loss=0.2646, pruned_loss=0.06961, over 4842.00 frames.], tot_loss[loss=0.2054, simple_loss=0.264, pruned_loss=0.07339, over 973509.54 frames.], batch size: 20, lr: 1.27e-03
+2022-05-03 17:50:11,822 INFO [train.py:715] (3/8) Epoch 0, batch 27400, loss[loss=0.1408, simple_loss=0.2113, pruned_loss=0.03518, over 4774.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2637, pruned_loss=0.07299, over 973442.61 frames.], batch size: 12, lr: 1.27e-03
+2022-05-03 17:50:51,094 INFO [train.py:715] (3/8) Epoch 0, batch 27450, loss[loss=0.1988, simple_loss=0.2541, pruned_loss=0.07175, over 4825.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2635, pruned_loss=0.07271, over 973023.26 frames.], batch size: 15, lr: 1.27e-03
+2022-05-03 17:51:31,238 INFO [train.py:715] (3/8) Epoch 0, batch 27500, loss[loss=0.1642, simple_loss=0.2262, pruned_loss=0.05108, over 4768.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2638, pruned_loss=0.07298, over 972722.89 frames.], batch size: 19, lr: 1.27e-03
+2022-05-03 17:52:11,047 INFO [train.py:715] (3/8) Epoch 0, batch 27550, loss[loss=0.1939, simple_loss=0.2615, pruned_loss=0.06316, over 4888.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2644, pruned_loss=0.07369, over 972819.69 frames.], batch size: 22, lr: 1.27e-03
+2022-05-03 17:52:50,538 INFO [train.py:715] (3/8) Epoch 0, batch 27600, loss[loss=0.1986, simple_loss=0.2585, pruned_loss=0.06938, over 4833.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2634, pruned_loss=0.07346, over 973113.41 frames.], batch size: 15, lr: 1.27e-03
+2022-05-03 17:53:29,968 INFO [train.py:715] (3/8) Epoch 0, batch 27650, loss[loss=0.202, simple_loss=0.2692, pruned_loss=0.06743, over 4813.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2623, pruned_loss=0.0727, over 973388.10 frames.], batch size: 12, lr: 1.27e-03
+2022-05-03 17:54:09,969 INFO [train.py:715] (3/8) Epoch 0, batch 27700, loss[loss=0.1988, simple_loss=0.2581, pruned_loss=0.06975, over 4874.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2616, pruned_loss=0.07231, over 973443.11 frames.], batch size: 16, lr: 1.26e-03
+2022-05-03 17:54:50,341 INFO [train.py:715] (3/8) Epoch 0, batch 27750, loss[loss=0.2089, simple_loss=0.2667, pruned_loss=0.07552, over 4957.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2616, pruned_loss=0.07229, over 973312.74 frames.], batch size: 21, lr: 1.26e-03
+2022-05-03 17:55:30,105 INFO [train.py:715] (3/8) Epoch 0, batch 27800, loss[loss=0.18, simple_loss=0.2358, pruned_loss=0.0621, over 4858.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2622, pruned_loss=0.07217, over 973295.04 frames.], batch size: 20, lr: 1.26e-03
+2022-05-03 17:56:10,356 INFO [train.py:715] (3/8) Epoch 0, batch 27850, loss[loss=0.2867, simple_loss=0.3348, pruned_loss=0.1193, over 4772.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2645, pruned_loss=0.07364, over 971871.84 frames.], batch size: 18, lr: 1.26e-03
+2022-05-03 17:56:49,940 INFO [train.py:715] (3/8) Epoch 0, batch 27900, loss[loss=0.221, simple_loss=0.2936, pruned_loss=0.07424, over 4817.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2648, pruned_loss=0.07381, over 972632.37 frames.], batch size: 25, lr: 1.26e-03
+2022-05-03 17:57:29,408 INFO [train.py:715] (3/8) Epoch 0, batch 27950, loss[loss=0.1982, simple_loss=0.2683, pruned_loss=0.06402, over 4875.00 frames.], tot_loss[loss=0.2067, simple_loss=0.265, pruned_loss=0.07425, over 971965.96 frames.], batch size: 22, lr: 1.26e-03
+2022-05-03 17:58:09,430 INFO [train.py:715] (3/8) Epoch 0, batch 28000, loss[loss=0.1768, simple_loss=0.2464, pruned_loss=0.05362, over 4807.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2639, pruned_loss=0.07323, over 972267.33 frames.], batch size: 25, lr: 1.26e-03
+2022-05-03 17:58:49,656 INFO [train.py:715] (3/8) Epoch 0, batch 28050, loss[loss=0.1903, simple_loss=0.2551, pruned_loss=0.06275, over 4986.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2639, pruned_loss=0.07344, over 972111.99 frames.], batch size: 14, lr: 1.26e-03
+2022-05-03 17:59:29,707 INFO [train.py:715] (3/8) Epoch 0, batch 28100, loss[loss=0.2521, simple_loss=0.3071, pruned_loss=0.09861, over 4829.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2643, pruned_loss=0.07444, over 973124.38 frames.], batch size: 26, lr: 1.26e-03
+2022-05-03 18:00:08,962 INFO [train.py:715] (3/8) Epoch 0, batch 28150, loss[loss=0.1902, simple_loss=0.2488, pruned_loss=0.06576, over 4935.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2646, pruned_loss=0.07483, over 972835.83 frames.], batch size: 23, lr: 1.25e-03
+2022-05-03 18:00:49,198 INFO [train.py:715] (3/8) Epoch 0, batch 28200, loss[loss=0.189, simple_loss=0.2442, pruned_loss=0.06693, over 4797.00 frames.], tot_loss[loss=0.2068, simple_loss=0.264, pruned_loss=0.07478, over 972886.62 frames.], batch size: 21, lr: 1.25e-03
+2022-05-03 18:01:28,907 INFO [train.py:715] (3/8) Epoch 0, batch 28250, loss[loss=0.1778, simple_loss=0.2392, pruned_loss=0.05818, over 4917.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2637, pruned_loss=0.07466, over 973165.53 frames.], batch size: 18, lr: 1.25e-03
+2022-05-03 18:02:07,674 INFO [train.py:715] (3/8) Epoch 0, batch 28300, loss[loss=0.2085, simple_loss=0.274, pruned_loss=0.07146, over 4957.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2632, pruned_loss=0.07382, over 972726.96 frames.], batch size: 15, lr: 1.25e-03
+2022-05-03 18:02:48,208 INFO [train.py:715] (3/8) Epoch 0, batch 28350, loss[loss=0.2307, simple_loss=0.2781, pruned_loss=0.0917, over 4744.00 frames.], tot_loss[loss=0.2063, simple_loss=0.264, pruned_loss=0.07431, over 972527.02 frames.], batch size: 16, lr: 1.25e-03
+2022-05-03 18:03:27,710 INFO [train.py:715] (3/8) Epoch 0, batch 28400, loss[loss=0.2414, simple_loss=0.2881, pruned_loss=0.09734, over 4899.00 frames.], tot_loss[loss=0.207, simple_loss=0.2645, pruned_loss=0.07473, over 973068.57 frames.], batch size: 22, lr: 1.25e-03
+2022-05-03 18:04:07,957 INFO [train.py:715] (3/8) Epoch 0, batch 28450, loss[loss=0.1738, simple_loss=0.228, pruned_loss=0.05976, over 4795.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2637, pruned_loss=0.07441, over 973137.33 frames.], batch size: 12, lr: 1.25e-03
+2022-05-03 18:04:47,646 INFO [train.py:715] (3/8) Epoch 0, batch 28500, loss[loss=0.148, simple_loss=0.2072, pruned_loss=0.04445, over 4831.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2628, pruned_loss=0.07402, over 973331.43 frames.], batch size: 13, lr: 1.25e-03
+2022-05-03 18:05:28,098 INFO [train.py:715] (3/8) Epoch 0, batch 28550, loss[loss=0.1742, simple_loss=0.2311, pruned_loss=0.05869, over 4845.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2622, pruned_loss=0.0736, over 972277.76 frames.], batch size: 13, lr: 1.25e-03
+2022-05-03 18:06:07,732 INFO [train.py:715] (3/8) Epoch 0, batch 28600, loss[loss=0.1977, simple_loss=0.256, pruned_loss=0.06973, over 4983.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2629, pruned_loss=0.07397, over 972347.53 frames.], batch size: 14, lr: 1.24e-03
+2022-05-03 18:06:46,953 INFO [train.py:715] (3/8) Epoch 0, batch 28650, loss[loss=0.2097, simple_loss=0.2627, pruned_loss=0.07836, over 4788.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2625, pruned_loss=0.07344, over 972828.95 frames.], batch size: 18, lr: 1.24e-03
+2022-05-03 18:07:26,839 INFO [train.py:715] (3/8) Epoch 0, batch 28700, loss[loss=0.2086, simple_loss=0.2645, pruned_loss=0.07638, over 4843.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2628, pruned_loss=0.07391, over 972219.04 frames.], batch size: 13, lr: 1.24e-03
+2022-05-03 18:08:06,483 INFO [train.py:715] (3/8) Epoch 0, batch 28750, loss[loss=0.2274, simple_loss=0.2731, pruned_loss=0.09084, over 4830.00 frames.], tot_loss[loss=0.205, simple_loss=0.2626, pruned_loss=0.0737, over 972075.10 frames.], batch size: 26, lr: 1.24e-03
+2022-05-03 18:08:46,799 INFO [train.py:715] (3/8) Epoch 0, batch 28800, loss[loss=0.2311, simple_loss=0.3037, pruned_loss=0.07923, over 4824.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2634, pruned_loss=0.07419, over 972687.81 frames.], batch size: 25, lr: 1.24e-03
+2022-05-03 18:09:25,923 INFO [train.py:715] (3/8) Epoch 0, batch 28850, loss[loss=0.2497, simple_loss=0.2822, pruned_loss=0.1086, over 4866.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2637, pruned_loss=0.07398, over 973012.49 frames.], batch size: 32, lr: 1.24e-03
+2022-05-03 18:10:05,950 INFO [train.py:715] (3/8) Epoch 0, batch 28900, loss[loss=0.1679, simple_loss=0.2292, pruned_loss=0.05324, over 4957.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2632, pruned_loss=0.07354, over 972482.78 frames.], batch size: 14, lr: 1.24e-03
+2022-05-03 18:10:45,832 INFO [train.py:715] (3/8) Epoch 0, batch 28950, loss[loss=0.213, simple_loss=0.2757, pruned_loss=0.07514, over 4966.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2626, pruned_loss=0.07279, over 972846.34 frames.], batch size: 24, lr: 1.24e-03
+2022-05-03 18:11:24,706 INFO [train.py:715] (3/8) Epoch 0, batch 29000, loss[loss=0.1864, simple_loss=0.2532, pruned_loss=0.05983, over 4939.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2623, pruned_loss=0.07264, over 973082.37 frames.], batch size: 23, lr: 1.24e-03
+2022-05-03 18:12:05,308 INFO [train.py:715] (3/8) Epoch 0, batch 29050, loss[loss=0.2506, simple_loss=0.3032, pruned_loss=0.09898, over 4740.00 frames.], tot_loss[loss=0.204, simple_loss=0.2628, pruned_loss=0.07262, over 972748.00 frames.], batch size: 16, lr: 1.24e-03
+2022-05-03 18:12:45,439 INFO [train.py:715] (3/8) Epoch 0, batch 29100, loss[loss=0.1596, simple_loss=0.232, pruned_loss=0.04359, over 4942.00 frames.], tot_loss[loss=0.204, simple_loss=0.2628, pruned_loss=0.07258, over 972797.64 frames.], batch size: 24, lr: 1.23e-03
+2022-05-03 18:13:25,064 INFO [train.py:715] (3/8) Epoch 0, batch 29150, loss[loss=0.1708, simple_loss=0.235, pruned_loss=0.05334, over 4902.00 frames.], tot_loss[loss=0.203, simple_loss=0.2621, pruned_loss=0.07194, over 971944.49 frames.], batch size: 19, lr: 1.23e-03
+2022-05-03 18:14:04,266 INFO [train.py:715] (3/8) Epoch 0, batch 29200, loss[loss=0.2258, simple_loss=0.2689, pruned_loss=0.09131, over 4779.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2624, pruned_loss=0.07216, over 972473.01 frames.], batch size: 17, lr: 1.23e-03
+2022-05-03 18:14:44,206 INFO [train.py:715] (3/8) Epoch 0, batch 29250, loss[loss=0.201, simple_loss=0.2507, pruned_loss=0.0756, over 4860.00 frames.], tot_loss[loss=0.2031, simple_loss=0.262, pruned_loss=0.07209, over 972787.02 frames.], batch size: 13, lr: 1.23e-03
+2022-05-03 18:15:24,220 INFO [train.py:715] (3/8) Epoch 0, batch 29300, loss[loss=0.1798, simple_loss=0.2536, pruned_loss=0.05303, over 4778.00 frames.], tot_loss[loss=0.2038, simple_loss=0.263, pruned_loss=0.07231, over 972197.86 frames.], batch size: 17, lr: 1.23e-03
+2022-05-03 18:16:04,638 INFO [train.py:715] (3/8) Epoch 0, batch 29350, loss[loss=0.209, simple_loss=0.2622, pruned_loss=0.0779, over 4899.00 frames.], tot_loss[loss=0.2028, simple_loss=0.262, pruned_loss=0.07182, over 971694.15 frames.], batch size: 19, lr: 1.23e-03
+2022-05-03 18:16:44,081 INFO [train.py:715] (3/8) Epoch 0, batch 29400, loss[loss=0.2017, simple_loss=0.2709, pruned_loss=0.06629, over 4985.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2612, pruned_loss=0.07146, over 971859.16 frames.], batch size: 28, lr: 1.23e-03
+2022-05-03 18:17:23,551 INFO [train.py:715] (3/8) Epoch 0, batch 29450, loss[loss=0.2317, simple_loss=0.2757, pruned_loss=0.09378, over 4992.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2613, pruned_loss=0.07175, over 972906.62 frames.], batch size: 16, lr: 1.23e-03
+2022-05-03 18:18:03,747 INFO [train.py:715] (3/8) Epoch 0, batch 29500, loss[loss=0.1683, simple_loss=0.2387, pruned_loss=0.04895, over 4841.00 frames.], tot_loss[loss=0.203, simple_loss=0.2617, pruned_loss=0.0721, over 972565.38 frames.], batch size: 15, lr: 1.23e-03
+2022-05-03 18:18:42,858 INFO [train.py:715] (3/8) Epoch 0, batch 29550, loss[loss=0.2245, simple_loss=0.292, pruned_loss=0.07851, over 4886.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2624, pruned_loss=0.07268, over 971917.70 frames.], batch size: 22, lr: 1.23e-03
+2022-05-03 18:19:23,018 INFO [train.py:715] (3/8) Epoch 0, batch 29600, loss[loss=0.1941, simple_loss=0.2624, pruned_loss=0.06297, over 4939.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2626, pruned_loss=0.07315, over 971720.05 frames.], batch size: 21, lr: 1.22e-03
+2022-05-03 18:20:02,959 INFO [train.py:715] (3/8) Epoch 0, batch 29650, loss[loss=0.1952, simple_loss=0.2526, pruned_loss=0.06891, over 4738.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2614, pruned_loss=0.07221, over 972017.70 frames.], batch size: 16, lr: 1.22e-03
+2022-05-03 18:20:42,829 INFO [train.py:715] (3/8) Epoch 0, batch 29700, loss[loss=0.2108, simple_loss=0.2782, pruned_loss=0.07171, over 4935.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2624, pruned_loss=0.07261, over 972332.15 frames.], batch size: 21, lr: 1.22e-03
+2022-05-03 18:21:23,322 INFO [train.py:715] (3/8) Epoch 0, batch 29750, loss[loss=0.2062, simple_loss=0.2646, pruned_loss=0.07389, over 4753.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2628, pruned_loss=0.07279, over 971754.96 frames.], batch size: 19, lr: 1.22e-03
+2022-05-03 18:22:03,149 INFO [train.py:715] (3/8) Epoch 0, batch 29800, loss[loss=0.2208, simple_loss=0.2716, pruned_loss=0.08499, over 4978.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2628, pruned_loss=0.07316, over 971852.29 frames.], batch size: 28, lr: 1.22e-03
+2022-05-03 18:22:44,056 INFO [train.py:715] (3/8) Epoch 0, batch 29850, loss[loss=0.2547, simple_loss=0.304, pruned_loss=0.1027, over 4923.00 frames.], tot_loss[loss=0.205, simple_loss=0.2631, pruned_loss=0.07348, over 972054.30 frames.], batch size: 18, lr: 1.22e-03
+2022-05-03 18:23:23,987 INFO [train.py:715] (3/8) Epoch 0, batch 29900, loss[loss=0.1588, simple_loss=0.2328, pruned_loss=0.04241, over 4776.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2626, pruned_loss=0.07301, over 972272.84 frames.], batch size: 17, lr: 1.22e-03
+2022-05-03 18:24:03,886 INFO [train.py:715] (3/8) Epoch 0, batch 29950, loss[loss=0.2118, simple_loss=0.2777, pruned_loss=0.07294, over 4762.00 frames.], tot_loss[loss=0.203, simple_loss=0.2615, pruned_loss=0.07225, over 972321.71 frames.], batch size: 19, lr: 1.22e-03
+2022-05-03 18:24:43,766 INFO [train.py:715] (3/8) Epoch 0, batch 30000, loss[loss=0.1654, simple_loss=0.2302, pruned_loss=0.05031, over 4786.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2616, pruned_loss=0.07188, over 972371.80 frames.], batch size: 18, lr: 1.22e-03
+2022-05-03 18:24:43,766 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 18:25:00,380 INFO [train.py:742] (3/8) Epoch 0, validation: loss=0.1316, simple_loss=0.2189, pruned_loss=0.02213, over 914524.00 frames.
+2022-05-03 18:25:40,682 INFO [train.py:715] (3/8) Epoch 0, batch 30050, loss[loss=0.1754, simple_loss=0.2383, pruned_loss=0.05629, over 4746.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2619, pruned_loss=0.07236, over 972857.38 frames.], batch size: 16, lr: 1.22e-03
+2022-05-03 18:26:21,230 INFO [train.py:715] (3/8) Epoch 0, batch 30100, loss[loss=0.1735, simple_loss=0.2386, pruned_loss=0.05425, over 4737.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2621, pruned_loss=0.07264, over 973173.50 frames.], batch size: 16, lr: 1.21e-03
+2022-05-03 18:27:01,913 INFO [train.py:715] (3/8) Epoch 0, batch 30150, loss[loss=0.2176, simple_loss=0.2719, pruned_loss=0.0816, over 4715.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2621, pruned_loss=0.07261, over 971983.47 frames.], batch size: 15, lr: 1.21e-03
+2022-05-03 18:27:42,050 INFO [train.py:715] (3/8) Epoch 0, batch 30200, loss[loss=0.2115, simple_loss=0.2841, pruned_loss=0.06942, over 4926.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2615, pruned_loss=0.07186, over 972971.95 frames.], batch size: 29, lr: 1.21e-03
+2022-05-03 18:28:22,540 INFO [train.py:715] (3/8) Epoch 0, batch 30250, loss[loss=0.2009, simple_loss=0.2525, pruned_loss=0.07467, over 4837.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2604, pruned_loss=0.07153, over 972475.61 frames.], batch size: 13, lr: 1.21e-03
+2022-05-03 18:29:02,640 INFO [train.py:715] (3/8) Epoch 0, batch 30300, loss[loss=0.1847, simple_loss=0.2472, pruned_loss=0.06109, over 4989.00 frames.], tot_loss[loss=0.2027, simple_loss=0.261, pruned_loss=0.07216, over 973477.73 frames.], batch size: 27, lr: 1.21e-03
+2022-05-03 18:29:43,069 INFO [train.py:715] (3/8) Epoch 0, batch 30350, loss[loss=0.1774, simple_loss=0.2438, pruned_loss=0.05548, over 4865.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2602, pruned_loss=0.07148, over 973878.81 frames.], batch size: 20, lr: 1.21e-03
+2022-05-03 18:30:23,198 INFO [train.py:715] (3/8) Epoch 0, batch 30400, loss[loss=0.2091, simple_loss=0.2741, pruned_loss=0.07201, over 4883.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2594, pruned_loss=0.07105, over 974056.13 frames.], batch size: 16, lr: 1.21e-03
+2022-05-03 18:31:02,984 INFO [train.py:715] (3/8) Epoch 0, batch 30450, loss[loss=0.1552, simple_loss=0.227, pruned_loss=0.04171, over 4982.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2602, pruned_loss=0.07135, over 972741.99 frames.], batch size: 14, lr: 1.21e-03
+2022-05-03 18:31:42,722 INFO [train.py:715] (3/8) Epoch 0, batch 30500, loss[loss=0.2023, simple_loss=0.2532, pruned_loss=0.07576, over 4861.00 frames.], tot_loss[loss=0.2015, simple_loss=0.26, pruned_loss=0.07154, over 972757.45 frames.], batch size: 20, lr: 1.21e-03
+2022-05-03 18:32:22,640 INFO [train.py:715] (3/8) Epoch 0, batch 30550, loss[loss=0.1793, simple_loss=0.2487, pruned_loss=0.05491, over 4765.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2597, pruned_loss=0.07094, over 971717.11 frames.], batch size: 14, lr: 1.21e-03
+2022-05-03 18:33:01,763 INFO [train.py:715] (3/8) Epoch 0, batch 30600, loss[loss=0.2124, simple_loss=0.2808, pruned_loss=0.07198, over 4788.00 frames.], tot_loss[loss=0.1998, simple_loss=0.259, pruned_loss=0.07028, over 971902.58 frames.], batch size: 18, lr: 1.20e-03
+2022-05-03 18:33:41,702 INFO [train.py:715] (3/8) Epoch 0, batch 30650, loss[loss=0.194, simple_loss=0.2421, pruned_loss=0.07299, over 4968.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2609, pruned_loss=0.07144, over 972371.93 frames.], batch size: 14, lr: 1.20e-03
+2022-05-03 18:34:21,518 INFO [train.py:715] (3/8) Epoch 0, batch 30700, loss[loss=0.176, simple_loss=0.2369, pruned_loss=0.05759, over 4927.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2611, pruned_loss=0.07174, over 972463.24 frames.], batch size: 23, lr: 1.20e-03
+2022-05-03 18:35:01,618 INFO [train.py:715] (3/8) Epoch 0, batch 30750, loss[loss=0.1654, simple_loss=0.2259, pruned_loss=0.05249, over 4919.00 frames.], tot_loss[loss=0.2019, simple_loss=0.261, pruned_loss=0.07146, over 973316.81 frames.], batch size: 17, lr: 1.20e-03
+2022-05-03 18:35:40,969 INFO [train.py:715] (3/8) Epoch 0, batch 30800, loss[loss=0.189, simple_loss=0.2458, pruned_loss=0.06611, over 4873.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2606, pruned_loss=0.07145, over 972416.75 frames.], batch size: 20, lr: 1.20e-03
+2022-05-03 18:36:21,302 INFO [train.py:715] (3/8) Epoch 0, batch 30850, loss[loss=0.236, simple_loss=0.2757, pruned_loss=0.0981, over 4831.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2617, pruned_loss=0.07259, over 971762.35 frames.], batch size: 15, lr: 1.20e-03
+2022-05-03 18:37:01,144 INFO [train.py:715] (3/8) Epoch 0, batch 30900, loss[loss=0.1744, simple_loss=0.2393, pruned_loss=0.05478, over 4898.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2606, pruned_loss=0.07192, over 972143.90 frames.], batch size: 19, lr: 1.20e-03
+2022-05-03 18:37:40,861 INFO [train.py:715] (3/8) Epoch 0, batch 30950, loss[loss=0.2039, simple_loss=0.2626, pruned_loss=0.07258, over 4720.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2595, pruned_loss=0.07103, over 972162.57 frames.], batch size: 16, lr: 1.20e-03
+2022-05-03 18:38:20,947 INFO [train.py:715] (3/8) Epoch 0, batch 31000, loss[loss=0.2254, simple_loss=0.2746, pruned_loss=0.0881, over 4795.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2617, pruned_loss=0.07228, over 972848.63 frames.], batch size: 13, lr: 1.20e-03
+2022-05-03 18:39:00,964 INFO [train.py:715] (3/8) Epoch 0, batch 31050, loss[loss=0.2073, simple_loss=0.2714, pruned_loss=0.07159, over 4923.00 frames.], tot_loss[loss=0.2028, simple_loss=0.262, pruned_loss=0.07183, over 972242.50 frames.], batch size: 29, lr: 1.20e-03
+2022-05-03 18:39:40,375 INFO [train.py:715] (3/8) Epoch 0, batch 31100, loss[loss=0.2429, simple_loss=0.2942, pruned_loss=0.09577, over 4920.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2612, pruned_loss=0.07122, over 972465.44 frames.], batch size: 29, lr: 1.20e-03
+2022-05-03 18:40:19,532 INFO [train.py:715] (3/8) Epoch 0, batch 31150, loss[loss=0.2378, simple_loss=0.2891, pruned_loss=0.09324, over 4888.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2615, pruned_loss=0.07182, over 971920.15 frames.], batch size: 22, lr: 1.19e-03
+2022-05-03 18:40:59,611 INFO [train.py:715] (3/8) Epoch 0, batch 31200, loss[loss=0.2185, simple_loss=0.2687, pruned_loss=0.0842, over 4953.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2617, pruned_loss=0.07182, over 972089.15 frames.], batch size: 29, lr: 1.19e-03
+2022-05-03 18:41:39,407 INFO [train.py:715] (3/8) Epoch 0, batch 31250, loss[loss=0.2196, simple_loss=0.2856, pruned_loss=0.07682, over 4757.00 frames.], tot_loss[loss=0.2021, simple_loss=0.261, pruned_loss=0.07161, over 972561.01 frames.], batch size: 19, lr: 1.19e-03
+2022-05-03 18:42:18,875 INFO [train.py:715] (3/8) Epoch 0, batch 31300, loss[loss=0.1933, simple_loss=0.2585, pruned_loss=0.06404, over 4974.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2615, pruned_loss=0.07185, over 973008.20 frames.], batch size: 15, lr: 1.19e-03
+2022-05-03 18:42:59,212 INFO [train.py:715] (3/8) Epoch 0, batch 31350, loss[loss=0.1768, simple_loss=0.2515, pruned_loss=0.05101, over 4795.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2617, pruned_loss=0.07223, over 973003.65 frames.], batch size: 12, lr: 1.19e-03
+2022-05-03 18:43:38,894 INFO [train.py:715] (3/8) Epoch 0, batch 31400, loss[loss=0.1903, simple_loss=0.2553, pruned_loss=0.06267, over 4925.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2599, pruned_loss=0.07101, over 972849.03 frames.], batch size: 23, lr: 1.19e-03
+2022-05-03 18:44:18,172 INFO [train.py:715] (3/8) Epoch 0, batch 31450, loss[loss=0.1795, simple_loss=0.227, pruned_loss=0.06601, over 4902.00 frames.], tot_loss[loss=0.202, simple_loss=0.2607, pruned_loss=0.07161, over 973273.16 frames.], batch size: 17, lr: 1.19e-03
+2022-05-03 18:44:57,276 INFO [train.py:715] (3/8) Epoch 0, batch 31500, loss[loss=0.1949, simple_loss=0.2532, pruned_loss=0.06828, over 4798.00 frames.], tot_loss[loss=0.2012, simple_loss=0.26, pruned_loss=0.07122, over 973682.62 frames.], batch size: 21, lr: 1.19e-03
+2022-05-03 18:45:37,320 INFO [train.py:715] (3/8) Epoch 0, batch 31550, loss[loss=0.1792, simple_loss=0.2404, pruned_loss=0.059, over 4827.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2596, pruned_loss=0.07055, over 974774.11 frames.], batch size: 26, lr: 1.19e-03
+2022-05-03 18:46:17,102 INFO [train.py:715] (3/8) Epoch 0, batch 31600, loss[loss=0.1864, simple_loss=0.2387, pruned_loss=0.06709, over 4986.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2603, pruned_loss=0.07112, over 974594.55 frames.], batch size: 14, lr: 1.19e-03
+2022-05-03 18:46:56,334 INFO [train.py:715] (3/8) Epoch 0, batch 31650, loss[loss=0.2123, simple_loss=0.2752, pruned_loss=0.07476, over 4899.00 frames.], tot_loss[loss=0.203, simple_loss=0.2625, pruned_loss=0.07178, over 974315.63 frames.], batch size: 18, lr: 1.19e-03
+2022-05-03 18:47:36,245 INFO [train.py:715] (3/8) Epoch 0, batch 31700, loss[loss=0.2133, simple_loss=0.2711, pruned_loss=0.07775, over 4826.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2611, pruned_loss=0.07178, over 974087.18 frames.], batch size: 26, lr: 1.18e-03
+2022-05-03 18:48:16,469 INFO [train.py:715] (3/8) Epoch 0, batch 31750, loss[loss=0.2263, simple_loss=0.2787, pruned_loss=0.08698, over 4882.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2621, pruned_loss=0.07211, over 973234.51 frames.], batch size: 19, lr: 1.18e-03
+2022-05-03 18:48:56,201 INFO [train.py:715] (3/8) Epoch 0, batch 31800, loss[loss=0.2085, simple_loss=0.2744, pruned_loss=0.07124, over 4702.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2618, pruned_loss=0.07186, over 972883.43 frames.], batch size: 15, lr: 1.18e-03
+2022-05-03 18:49:35,466 INFO [train.py:715] (3/8) Epoch 0, batch 31850, loss[loss=0.1869, simple_loss=0.2501, pruned_loss=0.06182, over 4857.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2609, pruned_loss=0.07109, over 972733.50 frames.], batch size: 32, lr: 1.18e-03
+2022-05-03 18:50:15,964 INFO [train.py:715] (3/8) Epoch 0, batch 31900, loss[loss=0.1883, simple_loss=0.2646, pruned_loss=0.05598, over 4966.00 frames.], tot_loss[loss=0.201, simple_loss=0.2605, pruned_loss=0.07075, over 972585.99 frames.], batch size: 15, lr: 1.18e-03
+2022-05-03 18:50:55,671 INFO [train.py:715] (3/8) Epoch 0, batch 31950, loss[loss=0.2072, simple_loss=0.274, pruned_loss=0.07023, over 4942.00 frames.], tot_loss[loss=0.2019, simple_loss=0.261, pruned_loss=0.07134, over 972196.92 frames.], batch size: 35, lr: 1.18e-03
+2022-05-03 18:51:37,229 INFO [train.py:715] (3/8) Epoch 0, batch 32000, loss[loss=0.1772, simple_loss=0.2322, pruned_loss=0.06111, over 4846.00 frames.], tot_loss[loss=0.2023, simple_loss=0.261, pruned_loss=0.07179, over 973066.27 frames.], batch size: 30, lr: 1.18e-03
+2022-05-03 18:52:17,385 INFO [train.py:715] (3/8) Epoch 0, batch 32050, loss[loss=0.1899, simple_loss=0.2554, pruned_loss=0.0622, over 4752.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2609, pruned_loss=0.07182, over 972651.55 frames.], batch size: 19, lr: 1.18e-03
+2022-05-03 18:52:57,276 INFO [train.py:715] (3/8) Epoch 0, batch 32100, loss[loss=0.1888, simple_loss=0.2662, pruned_loss=0.05572, over 4848.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2609, pruned_loss=0.0717, over 971839.86 frames.], batch size: 30, lr: 1.18e-03
+2022-05-03 18:53:36,626 INFO [train.py:715] (3/8) Epoch 0, batch 32150, loss[loss=0.1967, simple_loss=0.264, pruned_loss=0.06471, over 4987.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2603, pruned_loss=0.07162, over 972199.04 frames.], batch size: 26, lr: 1.18e-03
+2022-05-03 18:54:15,807 INFO [train.py:715] (3/8) Epoch 0, batch 32200, loss[loss=0.192, simple_loss=0.2604, pruned_loss=0.06177, over 4755.00 frames.], tot_loss[loss=0.201, simple_loss=0.2601, pruned_loss=0.07099, over 972202.93 frames.], batch size: 19, lr: 1.18e-03
+2022-05-03 18:54:55,961 INFO [train.py:715] (3/8) Epoch 0, batch 32250, loss[loss=0.1479, simple_loss=0.2138, pruned_loss=0.04097, over 4801.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2608, pruned_loss=0.07121, over 971511.20 frames.], batch size: 14, lr: 1.17e-03
+2022-05-03 18:55:35,806 INFO [train.py:715] (3/8) Epoch 0, batch 32300, loss[loss=0.1734, simple_loss=0.2423, pruned_loss=0.05227, over 4911.00 frames.], tot_loss[loss=0.2005, simple_loss=0.26, pruned_loss=0.07048, over 972044.88 frames.], batch size: 17, lr: 1.17e-03
+2022-05-03 18:56:15,321 INFO [train.py:715] (3/8) Epoch 0, batch 32350, loss[loss=0.2429, simple_loss=0.2847, pruned_loss=0.1006, over 4855.00 frames.], tot_loss[loss=0.201, simple_loss=0.2609, pruned_loss=0.07052, over 972632.56 frames.], batch size: 15, lr: 1.17e-03
+2022-05-03 18:56:55,311 INFO [train.py:715] (3/8) Epoch 0, batch 32400, loss[loss=0.1578, simple_loss=0.2335, pruned_loss=0.04106, over 4850.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2613, pruned_loss=0.0706, over 972160.55 frames.], batch size: 20, lr: 1.17e-03
+2022-05-03 18:57:35,387 INFO [train.py:715] (3/8) Epoch 0, batch 32450, loss[loss=0.1986, simple_loss=0.2522, pruned_loss=0.07252, over 4881.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2605, pruned_loss=0.07049, over 972304.57 frames.], batch size: 32, lr: 1.17e-03
+2022-05-03 18:58:15,185 INFO [train.py:715] (3/8) Epoch 0, batch 32500, loss[loss=0.1829, simple_loss=0.239, pruned_loss=0.0634, over 4899.00 frames.], tot_loss[loss=0.201, simple_loss=0.2605, pruned_loss=0.07073, over 972062.49 frames.], batch size: 22, lr: 1.17e-03
+2022-05-03 18:58:54,506 INFO [train.py:715] (3/8) Epoch 0, batch 32550, loss[loss=0.1713, simple_loss=0.2353, pruned_loss=0.05362, over 4816.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2612, pruned_loss=0.07129, over 971128.47 frames.], batch size: 25, lr: 1.17e-03
+2022-05-03 18:59:34,022 INFO [train.py:715] (3/8) Epoch 0, batch 32600, loss[loss=0.1795, simple_loss=0.2312, pruned_loss=0.06394, over 4924.00 frames.], tot_loss[loss=0.2017, simple_loss=0.261, pruned_loss=0.07115, over 971716.86 frames.], batch size: 35, lr: 1.17e-03
+2022-05-03 19:00:13,280 INFO [train.py:715] (3/8) Epoch 0, batch 32650, loss[loss=0.2333, simple_loss=0.286, pruned_loss=0.09028, over 4773.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2598, pruned_loss=0.0705, over 971239.30 frames.], batch size: 18, lr: 1.17e-03
+2022-05-03 19:00:52,617 INFO [train.py:715] (3/8) Epoch 0, batch 32700, loss[loss=0.226, simple_loss=0.2663, pruned_loss=0.09283, over 4859.00 frames.], tot_loss[loss=0.201, simple_loss=0.2603, pruned_loss=0.07081, over 970977.93 frames.], batch size: 34, lr: 1.17e-03
+2022-05-03 19:01:32,097 INFO [train.py:715] (3/8) Epoch 0, batch 32750, loss[loss=0.1984, simple_loss=0.2595, pruned_loss=0.06869, over 4915.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2602, pruned_loss=0.07132, over 970695.52 frames.], batch size: 23, lr: 1.17e-03
+2022-05-03 19:02:12,126 INFO [train.py:715] (3/8) Epoch 0, batch 32800, loss[loss=0.1929, simple_loss=0.2654, pruned_loss=0.06021, over 4980.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2616, pruned_loss=0.07211, over 971346.13 frames.], batch size: 28, lr: 1.16e-03
+2022-05-03 19:02:51,636 INFO [train.py:715] (3/8) Epoch 0, batch 32850, loss[loss=0.1814, simple_loss=0.2352, pruned_loss=0.06374, over 4809.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2604, pruned_loss=0.07154, over 971718.05 frames.], batch size: 21, lr: 1.16e-03
+2022-05-03 19:03:31,120 INFO [train.py:715] (3/8) Epoch 0, batch 32900, loss[loss=0.1645, simple_loss=0.2271, pruned_loss=0.05093, over 4986.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2588, pruned_loss=0.07041, over 972312.05 frames.], batch size: 24, lr: 1.16e-03
+2022-05-03 19:04:11,177 INFO [train.py:715] (3/8) Epoch 0, batch 32950, loss[loss=0.1939, simple_loss=0.26, pruned_loss=0.06389, over 4924.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2586, pruned_loss=0.0703, over 971797.98 frames.], batch size: 23, lr: 1.16e-03
+2022-05-03 19:04:50,684 INFO [train.py:715] (3/8) Epoch 0, batch 33000, loss[loss=0.1448, simple_loss=0.2129, pruned_loss=0.03831, over 4944.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2584, pruned_loss=0.06919, over 971765.52 frames.], batch size: 29, lr: 1.16e-03
+2022-05-03 19:04:50,685 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 19:05:00,796 INFO [train.py:742] (3/8) Epoch 0, validation: loss=0.1303, simple_loss=0.2174, pruned_loss=0.02158, over 914524.00 frames.
+2022-05-03 19:05:40,737 INFO [train.py:715] (3/8) Epoch 0, batch 33050, loss[loss=0.229, simple_loss=0.2759, pruned_loss=0.09102, over 4976.00 frames.], tot_loss[loss=0.199, simple_loss=0.2587, pruned_loss=0.06964, over 971559.42 frames.], batch size: 24, lr: 1.16e-03
+2022-05-03 19:06:20,345 INFO [train.py:715] (3/8) Epoch 0, batch 33100, loss[loss=0.1475, simple_loss=0.2116, pruned_loss=0.04168, over 4869.00 frames.], tot_loss[loss=0.2, simple_loss=0.2598, pruned_loss=0.07012, over 972417.85 frames.], batch size: 20, lr: 1.16e-03
+2022-05-03 19:07:01,017 INFO [train.py:715] (3/8) Epoch 0, batch 33150, loss[loss=0.1928, simple_loss=0.2535, pruned_loss=0.06608, over 4847.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2597, pruned_loss=0.07043, over 972764.48 frames.], batch size: 32, lr: 1.16e-03
+2022-05-03 19:07:41,357 INFO [train.py:715] (3/8) Epoch 0, batch 33200, loss[loss=0.1977, simple_loss=0.2518, pruned_loss=0.0718, over 4706.00 frames.], tot_loss[loss=0.2009, simple_loss=0.26, pruned_loss=0.07092, over 972121.89 frames.], batch size: 15, lr: 1.16e-03
+2022-05-03 19:08:21,592 INFO [train.py:715] (3/8) Epoch 0, batch 33250, loss[loss=0.1904, simple_loss=0.2566, pruned_loss=0.06213, over 4851.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2601, pruned_loss=0.07073, over 971769.05 frames.], batch size: 20, lr: 1.16e-03
+2022-05-03 19:09:01,806 INFO [train.py:715] (3/8) Epoch 0, batch 33300, loss[loss=0.1873, simple_loss=0.2502, pruned_loss=0.06224, over 4938.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2601, pruned_loss=0.07017, over 971725.22 frames.], batch size: 23, lr: 1.16e-03
+2022-05-03 19:09:42,525 INFO [train.py:715] (3/8) Epoch 0, batch 33350, loss[loss=0.243, simple_loss=0.2881, pruned_loss=0.09892, over 4863.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2605, pruned_loss=0.0705, over 971571.02 frames.], batch size: 20, lr: 1.16e-03
+2022-05-03 19:10:22,674 INFO [train.py:715] (3/8) Epoch 0, batch 33400, loss[loss=0.2479, simple_loss=0.3037, pruned_loss=0.09607, over 4972.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2611, pruned_loss=0.07106, over 971141.21 frames.], batch size: 24, lr: 1.15e-03
+2022-05-03 19:11:02,699 INFO [train.py:715] (3/8) Epoch 0, batch 33450, loss[loss=0.1781, simple_loss=0.2477, pruned_loss=0.05431, over 4930.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2619, pruned_loss=0.07163, over 971702.07 frames.], batch size: 29, lr: 1.15e-03
+2022-05-03 19:11:43,357 INFO [train.py:715] (3/8) Epoch 0, batch 33500, loss[loss=0.1701, simple_loss=0.2242, pruned_loss=0.05806, over 4764.00 frames.], tot_loss[loss=0.202, simple_loss=0.2613, pruned_loss=0.07134, over 972328.67 frames.], batch size: 12, lr: 1.15e-03
+2022-05-03 19:12:23,711 INFO [train.py:715] (3/8) Epoch 0, batch 33550, loss[loss=0.2267, simple_loss=0.2871, pruned_loss=0.08318, over 4899.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2603, pruned_loss=0.07061, over 972225.00 frames.], batch size: 19, lr: 1.15e-03
+2022-05-03 19:13:02,894 INFO [train.py:715] (3/8) Epoch 0, batch 33600, loss[loss=0.191, simple_loss=0.247, pruned_loss=0.06747, over 4874.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2602, pruned_loss=0.07042, over 972403.87 frames.], batch size: 20, lr: 1.15e-03
+2022-05-03 19:13:43,473 INFO [train.py:715] (3/8) Epoch 0, batch 33650, loss[loss=0.2127, simple_loss=0.2733, pruned_loss=0.07609, over 4856.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2591, pruned_loss=0.06995, over 971055.89 frames.], batch size: 30, lr: 1.15e-03
+2022-05-03 19:14:23,802 INFO [train.py:715] (3/8) Epoch 0, batch 33700, loss[loss=0.2377, simple_loss=0.2852, pruned_loss=0.0951, over 4810.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2592, pruned_loss=0.0703, over 971355.68 frames.], batch size: 26, lr: 1.15e-03
+2022-05-03 19:15:03,032 INFO [train.py:715] (3/8) Epoch 0, batch 33750, loss[loss=0.2265, simple_loss=0.2803, pruned_loss=0.0863, over 4699.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2601, pruned_loss=0.07055, over 971332.44 frames.], batch size: 15, lr: 1.15e-03
+2022-05-03 19:15:42,529 INFO [train.py:715] (3/8) Epoch 0, batch 33800, loss[loss=0.2293, simple_loss=0.2706, pruned_loss=0.09394, over 4767.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2588, pruned_loss=0.06971, over 970859.99 frames.], batch size: 14, lr: 1.15e-03
+2022-05-03 19:16:22,771 INFO [train.py:715] (3/8) Epoch 0, batch 33850, loss[loss=0.1746, simple_loss=0.2416, pruned_loss=0.05382, over 4883.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2596, pruned_loss=0.07047, over 970817.92 frames.], batch size: 22, lr: 1.15e-03
+2022-05-03 19:17:02,058 INFO [train.py:715] (3/8) Epoch 0, batch 33900, loss[loss=0.171, simple_loss=0.248, pruned_loss=0.04706, over 4982.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2596, pruned_loss=0.07064, over 971045.38 frames.], batch size: 28, lr: 1.15e-03
+2022-05-03 19:17:41,113 INFO [train.py:715] (3/8) Epoch 0, batch 33950, loss[loss=0.2312, simple_loss=0.2721, pruned_loss=0.09509, over 4985.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2588, pruned_loss=0.06991, over 971179.97 frames.], batch size: 33, lr: 1.15e-03
+2022-05-03 19:18:21,103 INFO [train.py:715] (3/8) Epoch 0, batch 34000, loss[loss=0.2036, simple_loss=0.2613, pruned_loss=0.07293, over 4856.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2579, pruned_loss=0.06927, over 971516.23 frames.], batch size: 32, lr: 1.14e-03
+2022-05-03 19:19:00,963 INFO [train.py:715] (3/8) Epoch 0, batch 34050, loss[loss=0.1747, simple_loss=0.2296, pruned_loss=0.05986, over 4828.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2577, pruned_loss=0.0698, over 971955.73 frames.], batch size: 15, lr: 1.14e-03
+2022-05-03 19:19:40,627 INFO [train.py:715] (3/8) Epoch 0, batch 34100, loss[loss=0.1748, simple_loss=0.2381, pruned_loss=0.05574, over 4807.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2581, pruned_loss=0.06926, over 972189.77 frames.], batch size: 13, lr: 1.14e-03
+2022-05-03 19:20:19,825 INFO [train.py:715] (3/8) Epoch 0, batch 34150, loss[loss=0.2047, simple_loss=0.2422, pruned_loss=0.08363, over 4801.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2581, pruned_loss=0.06938, over 971860.03 frames.], batch size: 25, lr: 1.14e-03
+2022-05-03 19:20:59,752 INFO [train.py:715] (3/8) Epoch 0, batch 34200, loss[loss=0.2393, simple_loss=0.2974, pruned_loss=0.09059, over 4765.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2586, pruned_loss=0.06943, over 971853.88 frames.], batch size: 14, lr: 1.14e-03
+2022-05-03 19:21:39,296 INFO [train.py:715] (3/8) Epoch 0, batch 34250, loss[loss=0.2267, simple_loss=0.2796, pruned_loss=0.0869, over 4976.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2583, pruned_loss=0.06934, over 971140.01 frames.], batch size: 15, lr: 1.14e-03
+2022-05-03 19:22:18,599 INFO [train.py:715] (3/8) Epoch 0, batch 34300, loss[loss=0.2061, simple_loss=0.2688, pruned_loss=0.07171, over 4907.00 frames.], tot_loss[loss=0.198, simple_loss=0.258, pruned_loss=0.06897, over 971960.68 frames.], batch size: 19, lr: 1.14e-03
+2022-05-03 19:22:58,854 INFO [train.py:715] (3/8) Epoch 0, batch 34350, loss[loss=0.1757, simple_loss=0.2379, pruned_loss=0.05668, over 4791.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2585, pruned_loss=0.06965, over 972139.72 frames.], batch size: 24, lr: 1.14e-03
+2022-05-03 19:23:39,058 INFO [train.py:715] (3/8) Epoch 0, batch 34400, loss[loss=0.2058, simple_loss=0.254, pruned_loss=0.07887, over 4883.00 frames.], tot_loss[loss=0.2007, simple_loss=0.26, pruned_loss=0.07072, over 972528.27 frames.], batch size: 16, lr: 1.14e-03
+2022-05-03 19:24:18,631 INFO [train.py:715] (3/8) Epoch 0, batch 34450, loss[loss=0.2335, simple_loss=0.2724, pruned_loss=0.09726, over 4872.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2608, pruned_loss=0.0714, over 973234.06 frames.], batch size: 32, lr: 1.14e-03
+2022-05-03 19:24:57,900 INFO [train.py:715] (3/8) Epoch 0, batch 34500, loss[loss=0.2136, simple_loss=0.2659, pruned_loss=0.08065, over 4818.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2599, pruned_loss=0.07085, over 972942.16 frames.], batch size: 27, lr: 1.14e-03
+2022-05-03 19:25:38,245 INFO [train.py:715] (3/8) Epoch 0, batch 34550, loss[loss=0.1797, simple_loss=0.2482, pruned_loss=0.05558, over 4917.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2601, pruned_loss=0.07134, over 973742.29 frames.], batch size: 18, lr: 1.14e-03
+2022-05-03 19:26:17,980 INFO [train.py:715] (3/8) Epoch 0, batch 34600, loss[loss=0.2094, simple_loss=0.2721, pruned_loss=0.07341, over 4942.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2609, pruned_loss=0.07186, over 973431.65 frames.], batch size: 29, lr: 1.13e-03
+2022-05-03 19:26:57,211 INFO [train.py:715] (3/8) Epoch 0, batch 34650, loss[loss=0.2166, simple_loss=0.2691, pruned_loss=0.08205, over 4965.00 frames.], tot_loss[loss=0.2001, simple_loss=0.259, pruned_loss=0.07059, over 972944.85 frames.], batch size: 39, lr: 1.13e-03
+2022-05-03 19:27:37,738 INFO [train.py:715] (3/8) Epoch 0, batch 34700, loss[loss=0.174, simple_loss=0.2328, pruned_loss=0.05762, over 4911.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2586, pruned_loss=0.07056, over 972028.55 frames.], batch size: 17, lr: 1.13e-03
+2022-05-03 19:28:15,920 INFO [train.py:715] (3/8) Epoch 0, batch 34750, loss[loss=0.2341, simple_loss=0.3048, pruned_loss=0.08166, over 4959.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2586, pruned_loss=0.07044, over 971584.62 frames.], batch size: 24, lr: 1.13e-03
+2022-05-03 19:28:53,212 INFO [train.py:715] (3/8) Epoch 0, batch 34800, loss[loss=0.2674, simple_loss=0.3164, pruned_loss=0.1093, over 4923.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2573, pruned_loss=0.06973, over 971612.13 frames.], batch size: 18, lr: 1.13e-03
+2022-05-03 19:29:42,570 INFO [train.py:715] (3/8) Epoch 1, batch 0, loss[loss=0.1593, simple_loss=0.2175, pruned_loss=0.0506, over 4964.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2175, pruned_loss=0.0506, over 4964.00 frames.], batch size: 15, lr: 1.11e-03
+2022-05-03 19:30:21,872 INFO [train.py:715] (3/8) Epoch 1, batch 50, loss[loss=0.1935, simple_loss=0.2629, pruned_loss=0.06209, over 4816.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2572, pruned_loss=0.07065, over 218481.27 frames.], batch size: 25, lr: 1.11e-03
+2022-05-03 19:31:01,846 INFO [train.py:715] (3/8) Epoch 1, batch 100, loss[loss=0.1787, simple_loss=0.2487, pruned_loss=0.05437, over 4799.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2542, pruned_loss=0.06857, over 386106.49 frames.], batch size: 21, lr: 1.11e-03
+2022-05-03 19:31:41,280 INFO [train.py:715] (3/8) Epoch 1, batch 150, loss[loss=0.1633, simple_loss=0.239, pruned_loss=0.04383, over 4811.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2555, pruned_loss=0.06895, over 516107.82 frames.], batch size: 27, lr: 1.11e-03
+2022-05-03 19:32:20,517 INFO [train.py:715] (3/8) Epoch 1, batch 200, loss[loss=0.2089, simple_loss=0.2798, pruned_loss=0.06897, over 4850.00 frames.], tot_loss[loss=0.1963, simple_loss=0.256, pruned_loss=0.0683, over 617828.10 frames.], batch size: 32, lr: 1.11e-03
+2022-05-03 19:33:00,052 INFO [train.py:715] (3/8) Epoch 1, batch 250, loss[loss=0.2312, simple_loss=0.2641, pruned_loss=0.09919, over 4827.00 frames.], tot_loss[loss=0.1975, simple_loss=0.257, pruned_loss=0.06899, over 695947.07 frames.], batch size: 30, lr: 1.11e-03
+2022-05-03 19:33:40,735 INFO [train.py:715] (3/8) Epoch 1, batch 300, loss[loss=0.1616, simple_loss=0.2308, pruned_loss=0.04618, over 4936.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2565, pruned_loss=0.06863, over 756534.05 frames.], batch size: 21, lr: 1.11e-03
+2022-05-03 19:34:21,123 INFO [train.py:715] (3/8) Epoch 1, batch 350, loss[loss=0.247, simple_loss=0.2839, pruned_loss=0.1051, over 4846.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2576, pruned_loss=0.06908, over 804905.65 frames.], batch size: 34, lr: 1.11e-03
+2022-05-03 19:35:01,377 INFO [train.py:715] (3/8) Epoch 1, batch 400, loss[loss=0.2062, simple_loss=0.2538, pruned_loss=0.07936, over 4853.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2575, pruned_loss=0.06903, over 842318.37 frames.], batch size: 32, lr: 1.11e-03
+2022-05-03 19:35:42,057 INFO [train.py:715] (3/8) Epoch 1, batch 450, loss[loss=0.1973, simple_loss=0.2567, pruned_loss=0.06901, over 4966.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2574, pruned_loss=0.0689, over 870540.99 frames.], batch size: 35, lr: 1.11e-03
+2022-05-03 19:36:22,765 INFO [train.py:715] (3/8) Epoch 1, batch 500, loss[loss=0.1653, simple_loss=0.234, pruned_loss=0.04833, over 4856.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2568, pruned_loss=0.06873, over 892983.15 frames.], batch size: 30, lr: 1.11e-03
+2022-05-03 19:37:03,286 INFO [train.py:715] (3/8) Epoch 1, batch 550, loss[loss=0.233, simple_loss=0.2771, pruned_loss=0.09442, over 4748.00 frames.], tot_loss[loss=0.199, simple_loss=0.2582, pruned_loss=0.06988, over 910794.15 frames.], batch size: 14, lr: 1.11e-03
+2022-05-03 19:37:43,285 INFO [train.py:715] (3/8) Epoch 1, batch 600, loss[loss=0.2009, simple_loss=0.2711, pruned_loss=0.06537, over 4855.00 frames.], tot_loss[loss=0.199, simple_loss=0.2581, pruned_loss=0.06997, over 925094.47 frames.], batch size: 20, lr: 1.10e-03
+2022-05-03 19:38:23,977 INFO [train.py:715] (3/8) Epoch 1, batch 650, loss[loss=0.1998, simple_loss=0.2608, pruned_loss=0.0694, over 4854.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2582, pruned_loss=0.06958, over 935607.06 frames.], batch size: 32, lr: 1.10e-03
+2022-05-03 19:39:04,140 INFO [train.py:715] (3/8) Epoch 1, batch 700, loss[loss=0.1576, simple_loss=0.2225, pruned_loss=0.04632, over 4787.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2579, pruned_loss=0.06892, over 943739.35 frames.], batch size: 24, lr: 1.10e-03
+2022-05-03 19:39:44,117 INFO [train.py:715] (3/8) Epoch 1, batch 750, loss[loss=0.1873, simple_loss=0.2473, pruned_loss=0.0637, over 4804.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2597, pruned_loss=0.06952, over 950747.17 frames.], batch size: 21, lr: 1.10e-03
+2022-05-03 19:40:24,218 INFO [train.py:715] (3/8) Epoch 1, batch 800, loss[loss=0.1369, simple_loss=0.2078, pruned_loss=0.03302, over 4858.00 frames.], tot_loss[loss=0.2, simple_loss=0.26, pruned_loss=0.06997, over 955705.16 frames.], batch size: 20, lr: 1.10e-03
+2022-05-03 19:41:04,462 INFO [train.py:715] (3/8) Epoch 1, batch 850, loss[loss=0.195, simple_loss=0.2598, pruned_loss=0.06511, over 4777.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2594, pruned_loss=0.06962, over 959032.90 frames.], batch size: 18, lr: 1.10e-03
+2022-05-03 19:41:43,687 INFO [train.py:715] (3/8) Epoch 1, batch 900, loss[loss=0.2336, simple_loss=0.2799, pruned_loss=0.09361, over 4694.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2599, pruned_loss=0.06964, over 961497.44 frames.], batch size: 15, lr: 1.10e-03
+2022-05-03 19:42:22,969 INFO [train.py:715] (3/8) Epoch 1, batch 950, loss[loss=0.1654, simple_loss=0.231, pruned_loss=0.04984, over 4856.00 frames.], tot_loss[loss=0.2003, simple_loss=0.26, pruned_loss=0.0703, over 963613.57 frames.], batch size: 20, lr: 1.10e-03
+2022-05-03 19:43:02,563 INFO [train.py:715] (3/8) Epoch 1, batch 1000, loss[loss=0.1668, simple_loss=0.2347, pruned_loss=0.0494, over 4878.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2585, pruned_loss=0.06934, over 965185.19 frames.], batch size: 22, lr: 1.10e-03
+2022-05-03 19:43:41,900 INFO [train.py:715] (3/8) Epoch 1, batch 1050, loss[loss=0.2095, simple_loss=0.2784, pruned_loss=0.07024, over 4963.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2578, pruned_loss=0.06934, over 967533.62 frames.], batch size: 24, lr: 1.10e-03
+2022-05-03 19:44:20,965 INFO [train.py:715] (3/8) Epoch 1, batch 1100, loss[loss=0.2242, simple_loss=0.2809, pruned_loss=0.08376, over 4755.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2583, pruned_loss=0.06931, over 968049.38 frames.], batch size: 14, lr: 1.10e-03
+2022-05-03 19:45:00,271 INFO [train.py:715] (3/8) Epoch 1, batch 1150, loss[loss=0.1731, simple_loss=0.233, pruned_loss=0.0566, over 4875.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2579, pruned_loss=0.06866, over 968542.46 frames.], batch size: 32, lr: 1.10e-03
+2022-05-03 19:45:40,268 INFO [train.py:715] (3/8) Epoch 1, batch 1200, loss[loss=0.1633, simple_loss=0.2312, pruned_loss=0.04767, over 4983.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2586, pruned_loss=0.06933, over 970041.92 frames.], batch size: 25, lr: 1.10e-03
+2022-05-03 19:46:19,424 INFO [train.py:715] (3/8) Epoch 1, batch 1250, loss[loss=0.1968, simple_loss=0.2729, pruned_loss=0.06035, over 4812.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2581, pruned_loss=0.06882, over 969954.73 frames.], batch size: 25, lr: 1.10e-03
+2022-05-03 19:46:58,953 INFO [train.py:715] (3/8) Epoch 1, batch 1300, loss[loss=0.1784, simple_loss=0.2433, pruned_loss=0.05676, over 4959.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2577, pruned_loss=0.06838, over 969921.04 frames.], batch size: 15, lr: 1.09e-03
+2022-05-03 19:47:39,266 INFO [train.py:715] (3/8) Epoch 1, batch 1350, loss[loss=0.1799, simple_loss=0.2487, pruned_loss=0.05558, over 4764.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2578, pruned_loss=0.06843, over 970706.05 frames.], batch size: 19, lr: 1.09e-03
+2022-05-03 19:48:18,891 INFO [train.py:715] (3/8) Epoch 1, batch 1400, loss[loss=0.222, simple_loss=0.2649, pruned_loss=0.08961, over 4953.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2572, pruned_loss=0.06815, over 970608.09 frames.], batch size: 24, lr: 1.09e-03
+2022-05-03 19:48:58,740 INFO [train.py:715] (3/8) Epoch 1, batch 1450, loss[loss=0.1905, simple_loss=0.2469, pruned_loss=0.06698, over 4792.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2578, pruned_loss=0.06829, over 971183.58 frames.], batch size: 14, lr: 1.09e-03
+2022-05-03 19:49:38,348 INFO [train.py:715] (3/8) Epoch 1, batch 1500, loss[loss=0.1742, simple_loss=0.2386, pruned_loss=0.05493, over 4939.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2586, pruned_loss=0.06934, over 971160.58 frames.], batch size: 23, lr: 1.09e-03
+2022-05-03 19:50:17,872 INFO [train.py:715] (3/8) Epoch 1, batch 1550, loss[loss=0.1922, simple_loss=0.2489, pruned_loss=0.06776, over 4843.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2585, pruned_loss=0.06859, over 970811.10 frames.], batch size: 13, lr: 1.09e-03
+2022-05-03 19:50:57,099 INFO [train.py:715] (3/8) Epoch 1, batch 1600, loss[loss=0.2493, simple_loss=0.3011, pruned_loss=0.09869, over 4887.00 frames.], tot_loss[loss=0.1961, simple_loss=0.257, pruned_loss=0.06763, over 970630.49 frames.], batch size: 39, lr: 1.09e-03
+2022-05-03 19:51:36,397 INFO [train.py:715] (3/8) Epoch 1, batch 1650, loss[loss=0.1685, simple_loss=0.2385, pruned_loss=0.04929, over 4944.00 frames.], tot_loss[loss=0.197, simple_loss=0.2573, pruned_loss=0.0683, over 970574.61 frames.], batch size: 29, lr: 1.09e-03
+2022-05-03 19:52:16,978 INFO [train.py:715] (3/8) Epoch 1, batch 1700, loss[loss=0.2193, simple_loss=0.2702, pruned_loss=0.08417, over 4953.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2556, pruned_loss=0.06744, over 971788.15 frames.], batch size: 24, lr: 1.09e-03
+2022-05-03 19:52:56,159 INFO [train.py:715] (3/8) Epoch 1, batch 1750, loss[loss=0.1633, simple_loss=0.2365, pruned_loss=0.04504, over 4838.00 frames.], tot_loss[loss=0.195, simple_loss=0.2555, pruned_loss=0.06729, over 972396.94 frames.], batch size: 15, lr: 1.09e-03
+2022-05-03 19:53:35,893 INFO [train.py:715] (3/8) Epoch 1, batch 1800, loss[loss=0.1759, simple_loss=0.2398, pruned_loss=0.05595, over 4781.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2574, pruned_loss=0.06905, over 971983.37 frames.], batch size: 18, lr: 1.09e-03
+2022-05-03 19:54:15,256 INFO [train.py:715] (3/8) Epoch 1, batch 1850, loss[loss=0.2466, simple_loss=0.2997, pruned_loss=0.09675, over 4972.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2562, pruned_loss=0.06834, over 971874.33 frames.], batch size: 15, lr: 1.09e-03
+2022-05-03 19:54:54,775 INFO [train.py:715] (3/8) Epoch 1, batch 1900, loss[loss=0.1917, simple_loss=0.2628, pruned_loss=0.06032, over 4798.00 frames.], tot_loss[loss=0.195, simple_loss=0.255, pruned_loss=0.06746, over 973063.67 frames.], batch size: 18, lr: 1.09e-03
+2022-05-03 19:55:34,084 INFO [train.py:715] (3/8) Epoch 1, batch 1950, loss[loss=0.2158, simple_loss=0.2883, pruned_loss=0.07164, over 4879.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2557, pruned_loss=0.06759, over 973065.30 frames.], batch size: 19, lr: 1.08e-03
+2022-05-03 19:56:14,076 INFO [train.py:715] (3/8) Epoch 1, batch 2000, loss[loss=0.1508, simple_loss=0.2202, pruned_loss=0.04076, over 4758.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2558, pruned_loss=0.06735, over 972789.35 frames.], batch size: 19, lr: 1.08e-03
+2022-05-03 19:56:53,564 INFO [train.py:715] (3/8) Epoch 1, batch 2050, loss[loss=0.1831, simple_loss=0.2405, pruned_loss=0.06285, over 4833.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2553, pruned_loss=0.06699, over 972764.01 frames.], batch size: 26, lr: 1.08e-03
+2022-05-03 19:57:33,054 INFO [train.py:715] (3/8) Epoch 1, batch 2100, loss[loss=0.2085, simple_loss=0.2682, pruned_loss=0.07435, over 4862.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2554, pruned_loss=0.06696, over 972423.83 frames.], batch size: 16, lr: 1.08e-03
+2022-05-03 19:58:12,732 INFO [train.py:715] (3/8) Epoch 1, batch 2150, loss[loss=0.1718, simple_loss=0.2369, pruned_loss=0.05336, over 4859.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2555, pruned_loss=0.06731, over 972757.31 frames.], batch size: 30, lr: 1.08e-03
+2022-05-03 19:58:52,401 INFO [train.py:715] (3/8) Epoch 1, batch 2200, loss[loss=0.1947, simple_loss=0.2556, pruned_loss=0.0669, over 4983.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2561, pruned_loss=0.06749, over 972555.07 frames.], batch size: 35, lr: 1.08e-03
+2022-05-03 19:59:32,132 INFO [train.py:715] (3/8) Epoch 1, batch 2250, loss[loss=0.2013, simple_loss=0.2505, pruned_loss=0.07605, over 4824.00 frames.], tot_loss[loss=0.196, simple_loss=0.2566, pruned_loss=0.06774, over 972437.04 frames.], batch size: 26, lr: 1.08e-03
+2022-05-03 20:00:11,170 INFO [train.py:715] (3/8) Epoch 1, batch 2300, loss[loss=0.1969, simple_loss=0.2668, pruned_loss=0.06351, over 4686.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2586, pruned_loss=0.06944, over 972099.26 frames.], batch size: 15, lr: 1.08e-03
+2022-05-03 20:00:51,308 INFO [train.py:715] (3/8) Epoch 1, batch 2350, loss[loss=0.2451, simple_loss=0.2868, pruned_loss=0.1017, over 4910.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2577, pruned_loss=0.06906, over 972136.24 frames.], batch size: 17, lr: 1.08e-03
+2022-05-03 20:01:30,584 INFO [train.py:715] (3/8) Epoch 1, batch 2400, loss[loss=0.2005, simple_loss=0.2449, pruned_loss=0.07807, over 4916.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2577, pruned_loss=0.06867, over 972866.25 frames.], batch size: 17, lr: 1.08e-03
+2022-05-03 20:02:09,728 INFO [train.py:715] (3/8) Epoch 1, batch 2450, loss[loss=0.2019, simple_loss=0.2678, pruned_loss=0.06798, over 4791.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2567, pruned_loss=0.06792, over 973682.88 frames.], batch size: 18, lr: 1.08e-03
+2022-05-03 20:02:48,981 INFO [train.py:715] (3/8) Epoch 1, batch 2500, loss[loss=0.1853, simple_loss=0.2614, pruned_loss=0.05455, over 4790.00 frames.], tot_loss[loss=0.1953, simple_loss=0.256, pruned_loss=0.06732, over 972302.24 frames.], batch size: 24, lr: 1.08e-03
+2022-05-03 20:03:28,531 INFO [train.py:715] (3/8) Epoch 1, batch 2550, loss[loss=0.1853, simple_loss=0.2425, pruned_loss=0.064, over 4767.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2557, pruned_loss=0.06731, over 971494.00 frames.], batch size: 14, lr: 1.08e-03
+2022-05-03 20:04:08,262 INFO [train.py:715] (3/8) Epoch 1, batch 2600, loss[loss=0.193, simple_loss=0.2621, pruned_loss=0.06199, over 4932.00 frames.], tot_loss[loss=0.1953, simple_loss=0.256, pruned_loss=0.06723, over 971076.07 frames.], batch size: 18, lr: 1.08e-03
+2022-05-03 20:04:47,470 INFO [train.py:715] (3/8) Epoch 1, batch 2650, loss[loss=0.1888, simple_loss=0.2491, pruned_loss=0.06425, over 4949.00 frames.], tot_loss[loss=0.1965, simple_loss=0.257, pruned_loss=0.06805, over 971260.16 frames.], batch size: 39, lr: 1.07e-03
+2022-05-03 20:05:27,538 INFO [train.py:715] (3/8) Epoch 1, batch 2700, loss[loss=0.1824, simple_loss=0.2401, pruned_loss=0.06231, over 4783.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2572, pruned_loss=0.06827, over 971056.67 frames.], batch size: 14, lr: 1.07e-03
+2022-05-03 20:06:06,953 INFO [train.py:715] (3/8) Epoch 1, batch 2750, loss[loss=0.2097, simple_loss=0.2628, pruned_loss=0.07831, over 4851.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2567, pruned_loss=0.06859, over 970383.26 frames.], batch size: 32, lr: 1.07e-03
+2022-05-03 20:06:45,687 INFO [train.py:715] (3/8) Epoch 1, batch 2800, loss[loss=0.257, simple_loss=0.306, pruned_loss=0.104, over 4830.00 frames.], tot_loss[loss=0.197, simple_loss=0.2571, pruned_loss=0.06843, over 971208.55 frames.], batch size: 26, lr: 1.07e-03
+2022-05-03 20:07:25,349 INFO [train.py:715] (3/8) Epoch 1, batch 2850, loss[loss=0.1604, simple_loss=0.2382, pruned_loss=0.04127, over 4734.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2547, pruned_loss=0.06685, over 971562.99 frames.], batch size: 16, lr: 1.07e-03
+2022-05-03 20:08:05,006 INFO [train.py:715] (3/8) Epoch 1, batch 2900, loss[loss=0.2201, simple_loss=0.2704, pruned_loss=0.08489, over 4863.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2541, pruned_loss=0.06643, over 971384.16 frames.], batch size: 20, lr: 1.07e-03
+2022-05-03 20:08:44,123 INFO [train.py:715] (3/8) Epoch 1, batch 2950, loss[loss=0.1999, simple_loss=0.2568, pruned_loss=0.07149, over 4915.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2553, pruned_loss=0.06704, over 971092.06 frames.], batch size: 17, lr: 1.07e-03
+2022-05-03 20:09:22,833 INFO [train.py:715] (3/8) Epoch 1, batch 3000, loss[loss=0.186, simple_loss=0.2502, pruned_loss=0.06092, over 4788.00 frames.], tot_loss[loss=0.194, simple_loss=0.2545, pruned_loss=0.06678, over 971880.70 frames.], batch size: 14, lr: 1.07e-03
+2022-05-03 20:09:22,833 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 20:09:34,564 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.1276, simple_loss=0.2149, pruned_loss=0.0201, over 914524.00 frames.
+2022-05-03 20:10:13,438 INFO [train.py:715] (3/8) Epoch 1, batch 3050, loss[loss=0.2047, simple_loss=0.2721, pruned_loss=0.0686, over 4919.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2551, pruned_loss=0.06701, over 972136.61 frames.], batch size: 29, lr: 1.07e-03
+2022-05-03 20:10:53,453 INFO [train.py:715] (3/8) Epoch 1, batch 3100, loss[loss=0.2131, simple_loss=0.2692, pruned_loss=0.07849, over 4771.00 frames.], tot_loss[loss=0.194, simple_loss=0.2548, pruned_loss=0.06656, over 971604.61 frames.], batch size: 18, lr: 1.07e-03
+2022-05-03 20:11:32,597 INFO [train.py:715] (3/8) Epoch 1, batch 3150, loss[loss=0.2122, simple_loss=0.2845, pruned_loss=0.06995, over 4852.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2554, pruned_loss=0.06682, over 971386.18 frames.], batch size: 30, lr: 1.07e-03
+2022-05-03 20:12:11,817 INFO [train.py:715] (3/8) Epoch 1, batch 3200, loss[loss=0.2397, simple_loss=0.2809, pruned_loss=0.09923, over 4959.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2565, pruned_loss=0.06702, over 971551.86 frames.], batch size: 35, lr: 1.07e-03
+2022-05-03 20:12:51,455 INFO [train.py:715] (3/8) Epoch 1, batch 3250, loss[loss=0.183, simple_loss=0.2561, pruned_loss=0.05499, over 4755.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2559, pruned_loss=0.06676, over 971186.47 frames.], batch size: 19, lr: 1.07e-03
+2022-05-03 20:13:31,211 INFO [train.py:715] (3/8) Epoch 1, batch 3300, loss[loss=0.2245, simple_loss=0.2824, pruned_loss=0.08336, over 4920.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2563, pruned_loss=0.06725, over 971751.34 frames.], batch size: 39, lr: 1.07e-03
+2022-05-03 20:14:10,786 INFO [train.py:715] (3/8) Epoch 1, batch 3350, loss[loss=0.179, simple_loss=0.2453, pruned_loss=0.05636, over 4804.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2558, pruned_loss=0.06639, over 972067.70 frames.], batch size: 25, lr: 1.07e-03
+2022-05-03 20:14:50,063 INFO [train.py:715] (3/8) Epoch 1, batch 3400, loss[loss=0.1663, simple_loss=0.2354, pruned_loss=0.0486, over 4889.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2548, pruned_loss=0.06587, over 972165.20 frames.], batch size: 22, lr: 1.06e-03
+2022-05-03 20:15:30,688 INFO [train.py:715] (3/8) Epoch 1, batch 3450, loss[loss=0.166, simple_loss=0.229, pruned_loss=0.05157, over 4959.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2533, pruned_loss=0.06513, over 972020.62 frames.], batch size: 24, lr: 1.06e-03
+2022-05-03 20:16:09,590 INFO [train.py:715] (3/8) Epoch 1, batch 3500, loss[loss=0.234, simple_loss=0.2777, pruned_loss=0.0951, over 4875.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2541, pruned_loss=0.06549, over 971536.72 frames.], batch size: 32, lr: 1.06e-03
+2022-05-03 20:16:48,614 INFO [train.py:715] (3/8) Epoch 1, batch 3550, loss[loss=0.2194, simple_loss=0.2781, pruned_loss=0.08041, over 4882.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2548, pruned_loss=0.06592, over 972247.15 frames.], batch size: 16, lr: 1.06e-03
+2022-05-03 20:17:28,373 INFO [train.py:715] (3/8) Epoch 1, batch 3600, loss[loss=0.1881, simple_loss=0.253, pruned_loss=0.06162, over 4943.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2548, pruned_loss=0.066, over 972055.95 frames.], batch size: 23, lr: 1.06e-03
+2022-05-03 20:18:08,021 INFO [train.py:715] (3/8) Epoch 1, batch 3650, loss[loss=0.1853, simple_loss=0.2502, pruned_loss=0.06017, over 4783.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2543, pruned_loss=0.06637, over 971640.51 frames.], batch size: 14, lr: 1.06e-03
+2022-05-03 20:18:46,983 INFO [train.py:715] (3/8) Epoch 1, batch 3700, loss[loss=0.2086, simple_loss=0.258, pruned_loss=0.07962, over 4842.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2548, pruned_loss=0.06632, over 972176.30 frames.], batch size: 34, lr: 1.06e-03
+2022-05-03 20:19:25,658 INFO [train.py:715] (3/8) Epoch 1, batch 3750, loss[loss=0.2073, simple_loss=0.2707, pruned_loss=0.07194, over 4835.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2559, pruned_loss=0.06679, over 973012.13 frames.], batch size: 32, lr: 1.06e-03
+2022-05-03 20:20:05,931 INFO [train.py:715] (3/8) Epoch 1, batch 3800, loss[loss=0.2087, simple_loss=0.2655, pruned_loss=0.07595, over 4858.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2544, pruned_loss=0.0664, over 972713.57 frames.], batch size: 34, lr: 1.06e-03
+2022-05-03 20:20:44,902 INFO [train.py:715] (3/8) Epoch 1, batch 3850, loss[loss=0.1903, simple_loss=0.2694, pruned_loss=0.05562, over 4952.00 frames.], tot_loss[loss=0.1935, simple_loss=0.254, pruned_loss=0.06648, over 971838.05 frames.], batch size: 24, lr: 1.06e-03
+2022-05-03 20:21:23,755 INFO [train.py:715] (3/8) Epoch 1, batch 3900, loss[loss=0.2266, simple_loss=0.2845, pruned_loss=0.08431, over 4890.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2534, pruned_loss=0.06565, over 971235.86 frames.], batch size: 22, lr: 1.06e-03
+2022-05-03 20:22:03,281 INFO [train.py:715] (3/8) Epoch 1, batch 3950, loss[loss=0.2095, simple_loss=0.2576, pruned_loss=0.08076, over 4973.00 frames.], tot_loss[loss=0.193, simple_loss=0.2537, pruned_loss=0.06617, over 971993.77 frames.], batch size: 35, lr: 1.06e-03
+2022-05-03 20:22:42,793 INFO [train.py:715] (3/8) Epoch 1, batch 4000, loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03414, over 4985.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2543, pruned_loss=0.06616, over 972640.40 frames.], batch size: 15, lr: 1.06e-03
+2022-05-03 20:23:21,454 INFO [train.py:715] (3/8) Epoch 1, batch 4050, loss[loss=0.3489, simple_loss=0.3772, pruned_loss=0.1603, over 4869.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2553, pruned_loss=0.06716, over 973041.33 frames.], batch size: 22, lr: 1.06e-03
+2022-05-03 20:24:00,883 INFO [train.py:715] (3/8) Epoch 1, batch 4100, loss[loss=0.1961, simple_loss=0.2614, pruned_loss=0.06543, over 4858.00 frames.], tot_loss[loss=0.195, simple_loss=0.2556, pruned_loss=0.06723, over 972657.93 frames.], batch size: 30, lr: 1.05e-03
+2022-05-03 20:24:40,531 INFO [train.py:715] (3/8) Epoch 1, batch 4150, loss[loss=0.1497, simple_loss=0.2194, pruned_loss=0.03998, over 4956.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2557, pruned_loss=0.06763, over 972976.81 frames.], batch size: 29, lr: 1.05e-03
+2022-05-03 20:25:19,581 INFO [train.py:715] (3/8) Epoch 1, batch 4200, loss[loss=0.1874, simple_loss=0.241, pruned_loss=0.06695, over 4972.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2544, pruned_loss=0.06704, over 972462.47 frames.], batch size: 15, lr: 1.05e-03
+2022-05-03 20:25:58,622 INFO [train.py:715] (3/8) Epoch 1, batch 4250, loss[loss=0.2051, simple_loss=0.252, pruned_loss=0.07913, over 4911.00 frames.], tot_loss[loss=0.195, simple_loss=0.255, pruned_loss=0.06744, over 973058.96 frames.], batch size: 19, lr: 1.05e-03
+2022-05-03 20:26:38,138 INFO [train.py:715] (3/8) Epoch 1, batch 4300, loss[loss=0.1959, simple_loss=0.2558, pruned_loss=0.06805, over 4918.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2556, pruned_loss=0.06712, over 972645.16 frames.], batch size: 18, lr: 1.05e-03
+2022-05-03 20:27:17,801 INFO [train.py:715] (3/8) Epoch 1, batch 4350, loss[loss=0.1791, simple_loss=0.249, pruned_loss=0.05465, over 4977.00 frames.], tot_loss[loss=0.196, simple_loss=0.2564, pruned_loss=0.06783, over 972454.89 frames.], batch size: 25, lr: 1.05e-03
+2022-05-03 20:27:56,250 INFO [train.py:715] (3/8) Epoch 1, batch 4400, loss[loss=0.1906, simple_loss=0.2651, pruned_loss=0.05809, over 4760.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2575, pruned_loss=0.06845, over 972575.44 frames.], batch size: 18, lr: 1.05e-03
+2022-05-03 20:28:35,842 INFO [train.py:715] (3/8) Epoch 1, batch 4450, loss[loss=0.1617, simple_loss=0.22, pruned_loss=0.05174, over 4972.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2548, pruned_loss=0.0664, over 972743.44 frames.], batch size: 25, lr: 1.05e-03
+2022-05-03 20:29:15,592 INFO [train.py:715] (3/8) Epoch 1, batch 4500, loss[loss=0.1576, simple_loss=0.2237, pruned_loss=0.04579, over 4923.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2547, pruned_loss=0.06632, over 972800.91 frames.], batch size: 18, lr: 1.05e-03
+2022-05-03 20:29:54,815 INFO [train.py:715] (3/8) Epoch 1, batch 4550, loss[loss=0.2368, simple_loss=0.2898, pruned_loss=0.09193, over 4810.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2554, pruned_loss=0.06719, over 971908.06 frames.], batch size: 24, lr: 1.05e-03
+2022-05-03 20:30:33,517 INFO [train.py:715] (3/8) Epoch 1, batch 4600, loss[loss=0.2111, simple_loss=0.2689, pruned_loss=0.07661, over 4806.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2553, pruned_loss=0.06701, over 972122.53 frames.], batch size: 25, lr: 1.05e-03
+2022-05-03 20:31:13,057 INFO [train.py:715] (3/8) Epoch 1, batch 4650, loss[loss=0.1714, simple_loss=0.2384, pruned_loss=0.05224, over 4867.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2557, pruned_loss=0.06697, over 972600.21 frames.], batch size: 20, lr: 1.05e-03
+2022-05-03 20:31:52,506 INFO [train.py:715] (3/8) Epoch 1, batch 4700, loss[loss=0.1975, simple_loss=0.264, pruned_loss=0.06548, over 4845.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2548, pruned_loss=0.06647, over 972128.91 frames.], batch size: 13, lr: 1.05e-03
+2022-05-03 20:32:31,321 INFO [train.py:715] (3/8) Epoch 1, batch 4750, loss[loss=0.2303, simple_loss=0.2915, pruned_loss=0.08454, over 4976.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2543, pruned_loss=0.06629, over 971408.03 frames.], batch size: 15, lr: 1.05e-03
+2022-05-03 20:33:11,341 INFO [train.py:715] (3/8) Epoch 1, batch 4800, loss[loss=0.2125, simple_loss=0.2653, pruned_loss=0.07978, over 4983.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2544, pruned_loss=0.06635, over 971571.59 frames.], batch size: 15, lr: 1.05e-03
+2022-05-03 20:33:51,184 INFO [train.py:715] (3/8) Epoch 1, batch 4850, loss[loss=0.2047, simple_loss=0.2725, pruned_loss=0.06843, over 4896.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2537, pruned_loss=0.06548, over 972073.97 frames.], batch size: 19, lr: 1.05e-03
+2022-05-03 20:34:30,464 INFO [train.py:715] (3/8) Epoch 1, batch 4900, loss[loss=0.1919, simple_loss=0.2619, pruned_loss=0.06094, over 4769.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2531, pruned_loss=0.06529, over 972213.09 frames.], batch size: 19, lr: 1.04e-03
+2022-05-03 20:35:09,823 INFO [train.py:715] (3/8) Epoch 1, batch 4950, loss[loss=0.156, simple_loss=0.2245, pruned_loss=0.04374, over 4776.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2518, pruned_loss=0.06503, over 971867.66 frames.], batch size: 17, lr: 1.04e-03
+2022-05-03 20:35:50,158 INFO [train.py:715] (3/8) Epoch 1, batch 5000, loss[loss=0.2262, simple_loss=0.279, pruned_loss=0.08675, over 4985.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2525, pruned_loss=0.06506, over 971351.94 frames.], batch size: 31, lr: 1.04e-03
+2022-05-03 20:36:29,717 INFO [train.py:715] (3/8) Epoch 1, batch 5050, loss[loss=0.159, simple_loss=0.2311, pruned_loss=0.04344, over 4819.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2521, pruned_loss=0.06502, over 971790.62 frames.], batch size: 25, lr: 1.04e-03
+2022-05-03 20:37:08,717 INFO [train.py:715] (3/8) Epoch 1, batch 5100, loss[loss=0.1878, simple_loss=0.2485, pruned_loss=0.06354, over 4772.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2529, pruned_loss=0.06579, over 972367.23 frames.], batch size: 14, lr: 1.04e-03
+2022-05-03 20:37:48,748 INFO [train.py:715] (3/8) Epoch 1, batch 5150, loss[loss=0.2565, simple_loss=0.3007, pruned_loss=0.1061, over 4830.00 frames.], tot_loss[loss=0.193, simple_loss=0.2534, pruned_loss=0.06633, over 972826.56 frames.], batch size: 13, lr: 1.04e-03
+2022-05-03 20:38:30,129 INFO [train.py:715] (3/8) Epoch 1, batch 5200, loss[loss=0.2011, simple_loss=0.2664, pruned_loss=0.06788, over 4912.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2532, pruned_loss=0.06575, over 973032.96 frames.], batch size: 18, lr: 1.04e-03
+2022-05-03 20:39:09,105 INFO [train.py:715] (3/8) Epoch 1, batch 5250, loss[loss=0.223, simple_loss=0.2855, pruned_loss=0.0802, over 4820.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2533, pruned_loss=0.06578, over 973789.91 frames.], batch size: 15, lr: 1.04e-03
+2022-05-03 20:39:48,469 INFO [train.py:715] (3/8) Epoch 1, batch 5300, loss[loss=0.1688, simple_loss=0.2345, pruned_loss=0.05152, over 4740.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2543, pruned_loss=0.06606, over 974425.33 frames.], batch size: 16, lr: 1.04e-03
+2022-05-03 20:40:28,102 INFO [train.py:715] (3/8) Epoch 1, batch 5350, loss[loss=0.1925, simple_loss=0.2415, pruned_loss=0.07174, over 4872.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2543, pruned_loss=0.06614, over 975212.54 frames.], batch size: 32, lr: 1.04e-03
+2022-05-03 20:41:07,643 INFO [train.py:715] (3/8) Epoch 1, batch 5400, loss[loss=0.1529, simple_loss=0.2244, pruned_loss=0.0407, over 4779.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2528, pruned_loss=0.06488, over 974165.75 frames.], batch size: 14, lr: 1.04e-03
+2022-05-03 20:41:46,693 INFO [train.py:715] (3/8) Epoch 1, batch 5450, loss[loss=0.2171, simple_loss=0.2814, pruned_loss=0.07643, over 4880.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2542, pruned_loss=0.0657, over 974224.27 frames.], batch size: 22, lr: 1.04e-03
+2022-05-03 20:42:26,575 INFO [train.py:715] (3/8) Epoch 1, batch 5500, loss[loss=0.1954, simple_loss=0.2488, pruned_loss=0.07103, over 4700.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2551, pruned_loss=0.06638, over 974262.13 frames.], batch size: 15, lr: 1.04e-03
+2022-05-03 20:43:06,477 INFO [train.py:715] (3/8) Epoch 1, batch 5550, loss[loss=0.2165, simple_loss=0.2735, pruned_loss=0.07981, over 4864.00 frames.], tot_loss[loss=0.1937, simple_loss=0.255, pruned_loss=0.06623, over 974683.24 frames.], batch size: 20, lr: 1.04e-03
+2022-05-03 20:43:45,489 INFO [train.py:715] (3/8) Epoch 1, batch 5600, loss[loss=0.2301, simple_loss=0.3024, pruned_loss=0.07892, over 4784.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2559, pruned_loss=0.06653, over 973360.41 frames.], batch size: 18, lr: 1.04e-03
+2022-05-03 20:44:24,782 INFO [train.py:715] (3/8) Epoch 1, batch 5650, loss[loss=0.164, simple_loss=0.2251, pruned_loss=0.05146, over 4833.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2556, pruned_loss=0.06631, over 973640.16 frames.], batch size: 15, lr: 1.03e-03
+2022-05-03 20:45:04,548 INFO [train.py:715] (3/8) Epoch 1, batch 5700, loss[loss=0.1293, simple_loss=0.1954, pruned_loss=0.03165, over 4780.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2542, pruned_loss=0.06551, over 972922.87 frames.], batch size: 12, lr: 1.03e-03
+2022-05-03 20:45:44,078 INFO [train.py:715] (3/8) Epoch 1, batch 5750, loss[loss=0.1962, simple_loss=0.2533, pruned_loss=0.06953, over 4926.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2543, pruned_loss=0.06604, over 973131.52 frames.], batch size: 18, lr: 1.03e-03
+2022-05-03 20:46:23,088 INFO [train.py:715] (3/8) Epoch 1, batch 5800, loss[loss=0.1619, simple_loss=0.2333, pruned_loss=0.04526, over 4931.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2539, pruned_loss=0.0657, over 973448.04 frames.], batch size: 21, lr: 1.03e-03
+2022-05-03 20:47:03,040 INFO [train.py:715] (3/8) Epoch 1, batch 5850, loss[loss=0.2156, simple_loss=0.2724, pruned_loss=0.07938, over 4793.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2538, pruned_loss=0.06502, over 973695.81 frames.], batch size: 17, lr: 1.03e-03
+2022-05-03 20:47:42,850 INFO [train.py:715] (3/8) Epoch 1, batch 5900, loss[loss=0.1835, simple_loss=0.2378, pruned_loss=0.0646, over 4785.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2538, pruned_loss=0.06531, over 972755.10 frames.], batch size: 14, lr: 1.03e-03
+2022-05-03 20:48:21,972 INFO [train.py:715] (3/8) Epoch 1, batch 5950, loss[loss=0.1732, simple_loss=0.2442, pruned_loss=0.05109, over 4934.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2527, pruned_loss=0.06506, over 972378.00 frames.], batch size: 29, lr: 1.03e-03
+2022-05-03 20:49:01,785 INFO [train.py:715] (3/8) Epoch 1, batch 6000, loss[loss=0.1742, simple_loss=0.2343, pruned_loss=0.05701, over 4925.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2522, pruned_loss=0.06452, over 971887.42 frames.], batch size: 29, lr: 1.03e-03
+2022-05-03 20:49:01,786 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 20:49:14,258 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.1267, simple_loss=0.2135, pruned_loss=0.01993, over 914524.00 frames.
+2022-05-03 20:49:53,681 INFO [train.py:715] (3/8) Epoch 1, batch 6050, loss[loss=0.1926, simple_loss=0.2497, pruned_loss=0.06772, over 4906.00 frames.], tot_loss[loss=0.191, simple_loss=0.2526, pruned_loss=0.06474, over 971707.42 frames.], batch size: 17, lr: 1.03e-03
+2022-05-03 20:50:33,750 INFO [train.py:715] (3/8) Epoch 1, batch 6100, loss[loss=0.1933, simple_loss=0.2402, pruned_loss=0.07316, over 4980.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2527, pruned_loss=0.06513, over 971883.79 frames.], batch size: 14, lr: 1.03e-03
+2022-05-03 20:51:13,273 INFO [train.py:715] (3/8) Epoch 1, batch 6150, loss[loss=0.1829, simple_loss=0.241, pruned_loss=0.0624, over 4845.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2521, pruned_loss=0.06432, over 971548.56 frames.], batch size: 30, lr: 1.03e-03
+2022-05-03 20:51:51,974 INFO [train.py:715] (3/8) Epoch 1, batch 6200, loss[loss=0.1972, simple_loss=0.2727, pruned_loss=0.06084, over 4829.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2524, pruned_loss=0.06419, over 970805.26 frames.], batch size: 27, lr: 1.03e-03
+2022-05-03 20:52:32,160 INFO [train.py:715] (3/8) Epoch 1, batch 6250, loss[loss=0.1887, simple_loss=0.2431, pruned_loss=0.06713, over 4741.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2525, pruned_loss=0.06408, over 971350.66 frames.], batch size: 14, lr: 1.03e-03
+2022-05-03 20:53:11,875 INFO [train.py:715] (3/8) Epoch 1, batch 6300, loss[loss=0.1552, simple_loss=0.225, pruned_loss=0.04267, over 4696.00 frames.], tot_loss[loss=0.1899, simple_loss=0.252, pruned_loss=0.06389, over 971896.67 frames.], batch size: 15, lr: 1.03e-03
+2022-05-03 20:53:51,072 INFO [train.py:715] (3/8) Epoch 1, batch 6350, loss[loss=0.1804, simple_loss=0.2462, pruned_loss=0.05736, over 4848.00 frames.], tot_loss[loss=0.192, simple_loss=0.2533, pruned_loss=0.06533, over 973023.23 frames.], batch size: 30, lr: 1.03e-03
+2022-05-03 20:54:30,387 INFO [train.py:715] (3/8) Epoch 1, batch 6400, loss[loss=0.2313, simple_loss=0.277, pruned_loss=0.09281, over 4864.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2543, pruned_loss=0.06551, over 972901.14 frames.], batch size: 32, lr: 1.03e-03
+2022-05-03 20:55:09,939 INFO [train.py:715] (3/8) Epoch 1, batch 6450, loss[loss=0.207, simple_loss=0.251, pruned_loss=0.08148, over 4919.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2549, pruned_loss=0.06608, over 973300.55 frames.], batch size: 17, lr: 1.02e-03
+2022-05-03 20:55:49,579 INFO [train.py:715] (3/8) Epoch 1, batch 6500, loss[loss=0.2461, simple_loss=0.2893, pruned_loss=0.1014, over 4886.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2546, pruned_loss=0.06607, over 973582.14 frames.], batch size: 39, lr: 1.02e-03
+2022-05-03 20:56:28,198 INFO [train.py:715] (3/8) Epoch 1, batch 6550, loss[loss=0.1755, simple_loss=0.2347, pruned_loss=0.05811, over 4863.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2551, pruned_loss=0.06635, over 973190.44 frames.], batch size: 16, lr: 1.02e-03
+2022-05-03 20:57:08,074 INFO [train.py:715] (3/8) Epoch 1, batch 6600, loss[loss=0.2219, simple_loss=0.2817, pruned_loss=0.08099, over 4948.00 frames.], tot_loss[loss=0.194, simple_loss=0.2551, pruned_loss=0.06645, over 973089.98 frames.], batch size: 21, lr: 1.02e-03
+2022-05-03 20:57:48,546 INFO [train.py:715] (3/8) Epoch 1, batch 6650, loss[loss=0.187, simple_loss=0.2629, pruned_loss=0.05562, over 4989.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2551, pruned_loss=0.06634, over 972922.54 frames.], batch size: 28, lr: 1.02e-03
+2022-05-03 20:58:28,003 INFO [train.py:715] (3/8) Epoch 1, batch 6700, loss[loss=0.2148, simple_loss=0.2591, pruned_loss=0.08528, over 4790.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2548, pruned_loss=0.06583, over 972473.68 frames.], batch size: 14, lr: 1.02e-03
+2022-05-03 20:59:07,321 INFO [train.py:715] (3/8) Epoch 1, batch 6750, loss[loss=0.205, simple_loss=0.2574, pruned_loss=0.07632, over 4957.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2546, pruned_loss=0.06562, over 972431.25 frames.], batch size: 24, lr: 1.02e-03
+2022-05-03 20:59:47,255 INFO [train.py:715] (3/8) Epoch 1, batch 6800, loss[loss=0.2521, simple_loss=0.2957, pruned_loss=0.1043, over 4826.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2547, pruned_loss=0.06554, over 972722.87 frames.], batch size: 15, lr: 1.02e-03
+2022-05-03 21:00:26,798 INFO [train.py:715] (3/8) Epoch 1, batch 6850, loss[loss=0.2132, simple_loss=0.2702, pruned_loss=0.07815, over 4846.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2556, pruned_loss=0.06581, over 973669.03 frames.], batch size: 30, lr: 1.02e-03
+2022-05-03 21:01:05,423 INFO [train.py:715] (3/8) Epoch 1, batch 6900, loss[loss=0.2628, simple_loss=0.3218, pruned_loss=0.1019, over 4906.00 frames.], tot_loss[loss=0.1939, simple_loss=0.256, pruned_loss=0.06592, over 973559.48 frames.], batch size: 17, lr: 1.02e-03
+2022-05-03 21:01:44,712 INFO [train.py:715] (3/8) Epoch 1, batch 6950, loss[loss=0.1791, simple_loss=0.2372, pruned_loss=0.06055, over 4947.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2552, pruned_loss=0.06578, over 972873.71 frames.], batch size: 23, lr: 1.02e-03
+2022-05-03 21:02:24,793 INFO [train.py:715] (3/8) Epoch 1, batch 7000, loss[loss=0.1482, simple_loss=0.2088, pruned_loss=0.04381, over 4982.00 frames.], tot_loss[loss=0.194, simple_loss=0.2552, pruned_loss=0.06635, over 972625.64 frames.], batch size: 14, lr: 1.02e-03
+2022-05-03 21:03:03,638 INFO [train.py:715] (3/8) Epoch 1, batch 7050, loss[loss=0.1938, simple_loss=0.2612, pruned_loss=0.06319, over 4935.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2549, pruned_loss=0.06612, over 972601.03 frames.], batch size: 29, lr: 1.02e-03
+2022-05-03 21:03:42,604 INFO [train.py:715] (3/8) Epoch 1, batch 7100, loss[loss=0.2156, simple_loss=0.2606, pruned_loss=0.08532, over 4770.00 frames.], tot_loss[loss=0.194, simple_loss=0.2551, pruned_loss=0.06644, over 972143.07 frames.], batch size: 14, lr: 1.02e-03
+2022-05-03 21:04:22,593 INFO [train.py:715] (3/8) Epoch 1, batch 7150, loss[loss=0.1557, simple_loss=0.2193, pruned_loss=0.04605, over 4925.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2539, pruned_loss=0.06553, over 972648.51 frames.], batch size: 23, lr: 1.02e-03
+2022-05-03 21:05:02,517 INFO [train.py:715] (3/8) Epoch 1, batch 7200, loss[loss=0.1951, simple_loss=0.2592, pruned_loss=0.0655, over 4809.00 frames.], tot_loss[loss=0.193, simple_loss=0.2545, pruned_loss=0.06573, over 972445.19 frames.], batch size: 25, lr: 1.02e-03
+2022-05-03 21:05:41,155 INFO [train.py:715] (3/8) Epoch 1, batch 7250, loss[loss=0.1778, simple_loss=0.2456, pruned_loss=0.05501, over 4863.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2533, pruned_loss=0.06483, over 972900.49 frames.], batch size: 20, lr: 1.02e-03
+2022-05-03 21:06:21,084 INFO [train.py:715] (3/8) Epoch 1, batch 7300, loss[loss=0.2004, simple_loss=0.2663, pruned_loss=0.06722, over 4834.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2536, pruned_loss=0.065, over 971452.20 frames.], batch size: 15, lr: 1.01e-03
+2022-05-03 21:07:00,828 INFO [train.py:715] (3/8) Epoch 1, batch 7350, loss[loss=0.1698, simple_loss=0.2356, pruned_loss=0.05202, over 4894.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2541, pruned_loss=0.06559, over 972249.97 frames.], batch size: 17, lr: 1.01e-03
+2022-05-03 21:07:39,613 INFO [train.py:715] (3/8) Epoch 1, batch 7400, loss[loss=0.2266, simple_loss=0.2668, pruned_loss=0.09323, over 4987.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2542, pruned_loss=0.06569, over 972393.54 frames.], batch size: 15, lr: 1.01e-03
+2022-05-03 21:08:18,528 INFO [train.py:715] (3/8) Epoch 1, batch 7450, loss[loss=0.2563, simple_loss=0.3061, pruned_loss=0.1033, over 4954.00 frames.], tot_loss[loss=0.1927, simple_loss=0.254, pruned_loss=0.06564, over 972141.25 frames.], batch size: 23, lr: 1.01e-03
+2022-05-03 21:08:58,341 INFO [train.py:715] (3/8) Epoch 1, batch 7500, loss[loss=0.1609, simple_loss=0.2277, pruned_loss=0.04701, over 4968.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2529, pruned_loss=0.06522, over 971429.05 frames.], batch size: 24, lr: 1.01e-03
+2022-05-03 21:09:38,021 INFO [train.py:715] (3/8) Epoch 1, batch 7550, loss[loss=0.1934, simple_loss=0.2605, pruned_loss=0.06321, over 4775.00 frames.], tot_loss[loss=0.1903, simple_loss=0.252, pruned_loss=0.06431, over 972117.14 frames.], batch size: 14, lr: 1.01e-03
+2022-05-03 21:10:16,230 INFO [train.py:715] (3/8) Epoch 1, batch 7600, loss[loss=0.1687, simple_loss=0.2365, pruned_loss=0.05049, over 4849.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2525, pruned_loss=0.06448, over 972749.76 frames.], batch size: 20, lr: 1.01e-03
+2022-05-03 21:10:55,969 INFO [train.py:715] (3/8) Epoch 1, batch 7650, loss[loss=0.1973, simple_loss=0.2589, pruned_loss=0.06785, over 4914.00 frames.], tot_loss[loss=0.191, simple_loss=0.2526, pruned_loss=0.06472, over 971390.23 frames.], batch size: 35, lr: 1.01e-03
+2022-05-03 21:11:35,786 INFO [train.py:715] (3/8) Epoch 1, batch 7700, loss[loss=0.1767, simple_loss=0.228, pruned_loss=0.06274, over 4969.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2515, pruned_loss=0.06387, over 971777.53 frames.], batch size: 14, lr: 1.01e-03
+2022-05-03 21:12:14,129 INFO [train.py:715] (3/8) Epoch 1, batch 7750, loss[loss=0.1908, simple_loss=0.2482, pruned_loss=0.06671, over 4958.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2526, pruned_loss=0.0645, over 971906.26 frames.], batch size: 15, lr: 1.01e-03
+2022-05-03 21:12:53,240 INFO [train.py:715] (3/8) Epoch 1, batch 7800, loss[loss=0.2069, simple_loss=0.264, pruned_loss=0.07493, over 4746.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2538, pruned_loss=0.06526, over 971535.63 frames.], batch size: 16, lr: 1.01e-03
+2022-05-03 21:13:33,309 INFO [train.py:715] (3/8) Epoch 1, batch 7850, loss[loss=0.1751, simple_loss=0.2355, pruned_loss=0.05734, over 4975.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2531, pruned_loss=0.06506, over 971983.83 frames.], batch size: 24, lr: 1.01e-03
+2022-05-03 21:14:12,712 INFO [train.py:715] (3/8) Epoch 1, batch 7900, loss[loss=0.189, simple_loss=0.255, pruned_loss=0.06156, over 4685.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2534, pruned_loss=0.06479, over 972172.19 frames.], batch size: 15, lr: 1.01e-03
+2022-05-03 21:14:51,151 INFO [train.py:715] (3/8) Epoch 1, batch 7950, loss[loss=0.1728, simple_loss=0.241, pruned_loss=0.05231, over 4768.00 frames.], tot_loss[loss=0.1921, simple_loss=0.254, pruned_loss=0.06508, over 972038.40 frames.], batch size: 14, lr: 1.01e-03
+2022-05-03 21:15:31,258 INFO [train.py:715] (3/8) Epoch 1, batch 8000, loss[loss=0.1982, simple_loss=0.2542, pruned_loss=0.07111, over 4836.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2533, pruned_loss=0.06489, over 972155.33 frames.], batch size: 25, lr: 1.01e-03
+2022-05-03 21:16:11,047 INFO [train.py:715] (3/8) Epoch 1, batch 8050, loss[loss=0.188, simple_loss=0.2421, pruned_loss=0.06696, over 4959.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2535, pruned_loss=0.065, over 972018.18 frames.], batch size: 24, lr: 1.01e-03
+2022-05-03 21:16:50,422 INFO [train.py:715] (3/8) Epoch 1, batch 8100, loss[loss=0.1766, simple_loss=0.2452, pruned_loss=0.05404, over 4798.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2525, pruned_loss=0.06432, over 971403.60 frames.], batch size: 25, lr: 1.01e-03
+2022-05-03 21:17:28,623 INFO [train.py:715] (3/8) Epoch 1, batch 8150, loss[loss=0.1648, simple_loss=0.2361, pruned_loss=0.04678, over 4838.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2531, pruned_loss=0.0647, over 972712.55 frames.], batch size: 13, lr: 1.00e-03
+2022-05-03 21:18:08,543 INFO [train.py:715] (3/8) Epoch 1, batch 8200, loss[loss=0.1455, simple_loss=0.2084, pruned_loss=0.04128, over 4776.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2526, pruned_loss=0.06414, over 972016.55 frames.], batch size: 12, lr: 1.00e-03
+2022-05-03 21:18:48,019 INFO [train.py:715] (3/8) Epoch 1, batch 8250, loss[loss=0.1851, simple_loss=0.2456, pruned_loss=0.06233, over 4923.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2535, pruned_loss=0.0648, over 972468.20 frames.], batch size: 18, lr: 1.00e-03
+2022-05-03 21:19:26,208 INFO [train.py:715] (3/8) Epoch 1, batch 8300, loss[loss=0.1869, simple_loss=0.2365, pruned_loss=0.0686, over 4836.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2533, pruned_loss=0.06468, over 972266.28 frames.], batch size: 13, lr: 1.00e-03
+2022-05-03 21:20:06,143 INFO [train.py:715] (3/8) Epoch 1, batch 8350, loss[loss=0.2081, simple_loss=0.2611, pruned_loss=0.07759, over 4900.00 frames.], tot_loss[loss=0.1919, simple_loss=0.254, pruned_loss=0.06486, over 972961.31 frames.], batch size: 19, lr: 1.00e-03
+2022-05-03 21:20:45,728 INFO [train.py:715] (3/8) Epoch 1, batch 8400, loss[loss=0.1995, simple_loss=0.2519, pruned_loss=0.07356, over 4968.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2535, pruned_loss=0.06447, over 973608.95 frames.], batch size: 15, lr: 1.00e-03
+2022-05-03 21:21:25,101 INFO [train.py:715] (3/8) Epoch 1, batch 8450, loss[loss=0.1813, simple_loss=0.2503, pruned_loss=0.05614, over 4934.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2538, pruned_loss=0.06465, over 973479.03 frames.], batch size: 21, lr: 1.00e-03
+2022-05-03 21:22:03,496 INFO [train.py:715] (3/8) Epoch 1, batch 8500, loss[loss=0.1821, simple_loss=0.2501, pruned_loss=0.05706, over 4740.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2537, pruned_loss=0.06449, over 973341.32 frames.], batch size: 16, lr: 1.00e-03
+2022-05-03 21:22:43,393 INFO [train.py:715] (3/8) Epoch 1, batch 8550, loss[loss=0.1298, simple_loss=0.206, pruned_loss=0.02678, over 4876.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2548, pruned_loss=0.06497, over 973017.97 frames.], batch size: 16, lr: 1.00e-03
+2022-05-03 21:23:22,901 INFO [train.py:715] (3/8) Epoch 1, batch 8600, loss[loss=0.2337, simple_loss=0.3118, pruned_loss=0.07781, over 4763.00 frames.], tot_loss[loss=0.1915, simple_loss=0.254, pruned_loss=0.06454, over 972352.23 frames.], batch size: 19, lr: 1.00e-03
+2022-05-03 21:24:00,899 INFO [train.py:715] (3/8) Epoch 1, batch 8650, loss[loss=0.175, simple_loss=0.2449, pruned_loss=0.05259, over 4754.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2539, pruned_loss=0.06472, over 972334.29 frames.], batch size: 19, lr: 9.99e-04
+2022-05-03 21:24:41,121 INFO [train.py:715] (3/8) Epoch 1, batch 8700, loss[loss=0.2034, simple_loss=0.2554, pruned_loss=0.07575, over 4829.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2534, pruned_loss=0.06466, over 972126.79 frames.], batch size: 25, lr: 9.98e-04
+2022-05-03 21:25:21,114 INFO [train.py:715] (3/8) Epoch 1, batch 8750, loss[loss=0.1858, simple_loss=0.2537, pruned_loss=0.059, over 4985.00 frames.], tot_loss[loss=0.192, simple_loss=0.2535, pruned_loss=0.06519, over 972572.86 frames.], batch size: 28, lr: 9.98e-04
+2022-05-03 21:26:00,204 INFO [train.py:715] (3/8) Epoch 1, batch 8800, loss[loss=0.1896, simple_loss=0.2655, pruned_loss=0.05687, over 4850.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2529, pruned_loss=0.06493, over 972708.03 frames.], batch size: 13, lr: 9.97e-04
+2022-05-03 21:26:39,531 INFO [train.py:715] (3/8) Epoch 1, batch 8850, loss[loss=0.1561, simple_loss=0.2273, pruned_loss=0.04247, over 4786.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2529, pruned_loss=0.065, over 972574.38 frames.], batch size: 17, lr: 9.97e-04
+2022-05-03 21:27:19,648 INFO [train.py:715] (3/8) Epoch 1, batch 8900, loss[loss=0.1686, simple_loss=0.2355, pruned_loss=0.05081, over 4761.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2533, pruned_loss=0.06492, over 972930.80 frames.], batch size: 12, lr: 9.96e-04
+2022-05-03 21:27:59,351 INFO [train.py:715] (3/8) Epoch 1, batch 8950, loss[loss=0.2221, simple_loss=0.2906, pruned_loss=0.07682, over 4951.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2539, pruned_loss=0.06518, over 973254.62 frames.], batch size: 15, lr: 9.96e-04
+2022-05-03 21:28:37,780 INFO [train.py:715] (3/8) Epoch 1, batch 9000, loss[loss=0.1576, simple_loss=0.2297, pruned_loss=0.04278, over 4806.00 frames.], tot_loss[loss=0.1921, simple_loss=0.254, pruned_loss=0.06507, over 973457.07 frames.], batch size: 21, lr: 9.95e-04
+2022-05-03 21:28:37,781 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 21:28:47,501 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.1253, simple_loss=0.2125, pruned_loss=0.01906, over 914524.00 frames.
+2022-05-03 21:29:25,994 INFO [train.py:715] (3/8) Epoch 1, batch 9050, loss[loss=0.1717, simple_loss=0.2391, pruned_loss=0.05211, over 4786.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2538, pruned_loss=0.06481, over 972984.63 frames.], batch size: 13, lr: 9.94e-04
+2022-05-03 21:30:06,204 INFO [train.py:715] (3/8) Epoch 1, batch 9100, loss[loss=0.2208, simple_loss=0.2788, pruned_loss=0.08143, over 4884.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2541, pruned_loss=0.06547, over 973107.45 frames.], batch size: 16, lr: 9.94e-04
+2022-05-03 21:30:45,842 INFO [train.py:715] (3/8) Epoch 1, batch 9150, loss[loss=0.2064, simple_loss=0.2647, pruned_loss=0.0741, over 4953.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2524, pruned_loss=0.06422, over 973518.15 frames.], batch size: 21, lr: 9.93e-04
+2022-05-03 21:31:24,120 INFO [train.py:715] (3/8) Epoch 1, batch 9200, loss[loss=0.1953, simple_loss=0.2536, pruned_loss=0.06849, over 4745.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2524, pruned_loss=0.06426, over 973130.91 frames.], batch size: 19, lr: 9.93e-04
+2022-05-03 21:32:03,941 INFO [train.py:715] (3/8) Epoch 1, batch 9250, loss[loss=0.2016, simple_loss=0.2621, pruned_loss=0.07052, over 4893.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2516, pruned_loss=0.06342, over 974058.74 frames.], batch size: 19, lr: 9.92e-04
+2022-05-03 21:32:43,821 INFO [train.py:715] (3/8) Epoch 1, batch 9300, loss[loss=0.1899, simple_loss=0.2556, pruned_loss=0.06213, over 4728.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2516, pruned_loss=0.063, over 974044.37 frames.], batch size: 16, lr: 9.92e-04
+2022-05-03 21:33:22,873 INFO [train.py:715] (3/8) Epoch 1, batch 9350, loss[loss=0.1823, simple_loss=0.2531, pruned_loss=0.0558, over 4827.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2494, pruned_loss=0.06197, over 973478.82 frames.], batch size: 27, lr: 9.91e-04
+2022-05-03 21:34:02,361 INFO [train.py:715] (3/8) Epoch 1, batch 9400, loss[loss=0.1852, simple_loss=0.2488, pruned_loss=0.06083, over 4774.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2513, pruned_loss=0.06387, over 973563.86 frames.], batch size: 14, lr: 9.91e-04
+2022-05-03 21:34:42,532 INFO [train.py:715] (3/8) Epoch 1, batch 9450, loss[loss=0.1993, simple_loss=0.2692, pruned_loss=0.06475, over 4927.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2506, pruned_loss=0.06346, over 972962.07 frames.], batch size: 29, lr: 9.90e-04
+2022-05-03 21:35:22,125 INFO [train.py:715] (3/8) Epoch 1, batch 9500, loss[loss=0.214, simple_loss=0.2619, pruned_loss=0.08303, over 4681.00 frames.], tot_loss[loss=0.19, simple_loss=0.2514, pruned_loss=0.0643, over 972227.06 frames.], batch size: 15, lr: 9.89e-04
+2022-05-03 21:36:00,390 INFO [train.py:715] (3/8) Epoch 1, batch 9550, loss[loss=0.1918, simple_loss=0.2498, pruned_loss=0.06688, over 4767.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2514, pruned_loss=0.06412, over 971796.22 frames.], batch size: 18, lr: 9.89e-04
+2022-05-03 21:36:40,616 INFO [train.py:715] (3/8) Epoch 1, batch 9600, loss[loss=0.2191, simple_loss=0.2705, pruned_loss=0.08382, over 4963.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2516, pruned_loss=0.06478, over 971904.52 frames.], batch size: 35, lr: 9.88e-04
+2022-05-03 21:37:20,354 INFO [train.py:715] (3/8) Epoch 1, batch 9650, loss[loss=0.1949, simple_loss=0.2712, pruned_loss=0.05924, over 4905.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2512, pruned_loss=0.06455, over 971500.29 frames.], batch size: 17, lr: 9.88e-04
+2022-05-03 21:37:58,743 INFO [train.py:715] (3/8) Epoch 1, batch 9700, loss[loss=0.1327, simple_loss=0.2052, pruned_loss=0.03008, over 4818.00 frames.], tot_loss[loss=0.1894, simple_loss=0.251, pruned_loss=0.0639, over 970697.70 frames.], batch size: 27, lr: 9.87e-04
+2022-05-03 21:38:38,641 INFO [train.py:715] (3/8) Epoch 1, batch 9750, loss[loss=0.1845, simple_loss=0.2372, pruned_loss=0.0659, over 4828.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2514, pruned_loss=0.06365, over 970968.18 frames.], batch size: 15, lr: 9.87e-04
+2022-05-03 21:39:19,057 INFO [train.py:715] (3/8) Epoch 1, batch 9800, loss[loss=0.2281, simple_loss=0.2895, pruned_loss=0.08337, over 4978.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2511, pruned_loss=0.06374, over 971933.07 frames.], batch size: 39, lr: 9.86e-04
+2022-05-03 21:39:58,295 INFO [train.py:715] (3/8) Epoch 1, batch 9850, loss[loss=0.1714, simple_loss=0.2452, pruned_loss=0.04881, over 4959.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2515, pruned_loss=0.06354, over 972037.05 frames.], batch size: 39, lr: 9.86e-04
+2022-05-03 21:40:37,079 INFO [train.py:715] (3/8) Epoch 1, batch 9900, loss[loss=0.2182, simple_loss=0.2732, pruned_loss=0.08159, over 4903.00 frames.], tot_loss[loss=0.1901, simple_loss=0.252, pruned_loss=0.06411, over 972182.14 frames.], batch size: 19, lr: 9.85e-04
+2022-05-03 21:41:17,360 INFO [train.py:715] (3/8) Epoch 1, batch 9950, loss[loss=0.181, simple_loss=0.2382, pruned_loss=0.06193, over 4857.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2503, pruned_loss=0.06267, over 972012.73 frames.], batch size: 30, lr: 9.85e-04
+2022-05-03 21:41:57,262 INFO [train.py:715] (3/8) Epoch 1, batch 10000, loss[loss=0.2033, simple_loss=0.2673, pruned_loss=0.06965, over 4983.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2518, pruned_loss=0.06362, over 972500.12 frames.], batch size: 25, lr: 9.84e-04
+2022-05-03 21:42:36,321 INFO [train.py:715] (3/8) Epoch 1, batch 10050, loss[loss=0.2188, simple_loss=0.2743, pruned_loss=0.08165, over 4697.00 frames.], tot_loss[loss=0.188, simple_loss=0.2503, pruned_loss=0.06281, over 972382.61 frames.], batch size: 15, lr: 9.83e-04
+2022-05-03 21:43:15,952 INFO [train.py:715] (3/8) Epoch 1, batch 10100, loss[loss=0.1917, simple_loss=0.2477, pruned_loss=0.06784, over 4796.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2518, pruned_loss=0.06367, over 972854.19 frames.], batch size: 17, lr: 9.83e-04
+2022-05-03 21:43:55,967 INFO [train.py:715] (3/8) Epoch 1, batch 10150, loss[loss=0.2476, simple_loss=0.3111, pruned_loss=0.09208, over 4987.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2503, pruned_loss=0.06293, over 973154.74 frames.], batch size: 25, lr: 9.82e-04
+2022-05-03 21:44:35,078 INFO [train.py:715] (3/8) Epoch 1, batch 10200, loss[loss=0.173, simple_loss=0.2526, pruned_loss=0.04672, over 4956.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2513, pruned_loss=0.06347, over 972177.51 frames.], batch size: 21, lr: 9.82e-04
+2022-05-03 21:45:14,035 INFO [train.py:715] (3/8) Epoch 1, batch 10250, loss[loss=0.1722, simple_loss=0.2362, pruned_loss=0.05407, over 4965.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2527, pruned_loss=0.06441, over 972722.29 frames.], batch size: 15, lr: 9.81e-04
+2022-05-03 21:45:54,202 INFO [train.py:715] (3/8) Epoch 1, batch 10300, loss[loss=0.1849, simple_loss=0.2564, pruned_loss=0.05671, over 4915.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2524, pruned_loss=0.06392, over 972420.65 frames.], batch size: 18, lr: 9.81e-04
+2022-05-03 21:46:34,446 INFO [train.py:715] (3/8) Epoch 1, batch 10350, loss[loss=0.1896, simple_loss=0.2613, pruned_loss=0.05897, over 4919.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2528, pruned_loss=0.06391, over 972571.72 frames.], batch size: 23, lr: 9.80e-04
+2022-05-03 21:47:13,903 INFO [train.py:715] (3/8) Epoch 1, batch 10400, loss[loss=0.1816, simple_loss=0.2379, pruned_loss=0.06264, over 4744.00 frames.], tot_loss[loss=0.1896, simple_loss=0.252, pruned_loss=0.06359, over 972294.38 frames.], batch size: 19, lr: 9.80e-04
+2022-05-03 21:47:53,943 INFO [train.py:715] (3/8) Epoch 1, batch 10450, loss[loss=0.1854, simple_loss=0.2534, pruned_loss=0.05865, over 4798.00 frames.], tot_loss[loss=0.188, simple_loss=0.2506, pruned_loss=0.06273, over 971985.69 frames.], batch size: 21, lr: 9.79e-04
+2022-05-03 21:48:34,475 INFO [train.py:715] (3/8) Epoch 1, batch 10500, loss[loss=0.1682, simple_loss=0.2426, pruned_loss=0.04689, over 4786.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2513, pruned_loss=0.06315, over 971825.90 frames.], batch size: 21, lr: 9.79e-04
+2022-05-03 21:49:13,759 INFO [train.py:715] (3/8) Epoch 1, batch 10550, loss[loss=0.2151, simple_loss=0.2703, pruned_loss=0.07998, over 4780.00 frames.], tot_loss[loss=0.189, simple_loss=0.2517, pruned_loss=0.06317, over 971404.31 frames.], batch size: 14, lr: 9.78e-04
+2022-05-03 21:49:52,640 INFO [train.py:715] (3/8) Epoch 1, batch 10600, loss[loss=0.1676, simple_loss=0.235, pruned_loss=0.0501, over 4922.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2509, pruned_loss=0.06276, over 971933.91 frames.], batch size: 23, lr: 9.78e-04
+2022-05-03 21:50:33,174 INFO [train.py:715] (3/8) Epoch 1, batch 10650, loss[loss=0.1666, simple_loss=0.2232, pruned_loss=0.05502, over 4778.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2496, pruned_loss=0.06245, over 972669.70 frames.], batch size: 18, lr: 9.77e-04
+2022-05-03 21:51:13,724 INFO [train.py:715] (3/8) Epoch 1, batch 10700, loss[loss=0.2016, simple_loss=0.2698, pruned_loss=0.06667, over 4964.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2522, pruned_loss=0.06371, over 972366.62 frames.], batch size: 35, lr: 9.76e-04
+2022-05-03 21:51:52,988 INFO [train.py:715] (3/8) Epoch 1, batch 10750, loss[loss=0.1982, simple_loss=0.2694, pruned_loss=0.06351, over 4911.00 frames.], tot_loss[loss=0.1906, simple_loss=0.253, pruned_loss=0.06407, over 972298.71 frames.], batch size: 17, lr: 9.76e-04
+2022-05-03 21:52:32,271 INFO [train.py:715] (3/8) Epoch 1, batch 10800, loss[loss=0.2095, simple_loss=0.2656, pruned_loss=0.0767, over 4890.00 frames.], tot_loss[loss=0.19, simple_loss=0.2528, pruned_loss=0.06354, over 972677.77 frames.], batch size: 17, lr: 9.75e-04
+2022-05-03 21:53:12,728 INFO [train.py:715] (3/8) Epoch 1, batch 10850, loss[loss=0.1563, simple_loss=0.22, pruned_loss=0.04628, over 4757.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2516, pruned_loss=0.0629, over 972620.80 frames.], batch size: 12, lr: 9.75e-04
+2022-05-03 21:53:52,220 INFO [train.py:715] (3/8) Epoch 1, batch 10900, loss[loss=0.1992, simple_loss=0.2661, pruned_loss=0.06614, over 4872.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2514, pruned_loss=0.06278, over 972617.48 frames.], batch size: 16, lr: 9.74e-04
+2022-05-03 21:54:30,706 INFO [train.py:715] (3/8) Epoch 1, batch 10950, loss[loss=0.2145, simple_loss=0.253, pruned_loss=0.08796, over 4842.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2504, pruned_loss=0.06252, over 973411.06 frames.], batch size: 13, lr: 9.74e-04
+2022-05-03 21:55:10,751 INFO [train.py:715] (3/8) Epoch 1, batch 11000, loss[loss=0.2029, simple_loss=0.2622, pruned_loss=0.07187, over 4849.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2493, pruned_loss=0.0617, over 972681.25 frames.], batch size: 30, lr: 9.73e-04
+2022-05-03 21:55:50,515 INFO [train.py:715] (3/8) Epoch 1, batch 11050, loss[loss=0.1658, simple_loss=0.2435, pruned_loss=0.04405, over 4828.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2497, pruned_loss=0.06201, over 972466.44 frames.], batch size: 25, lr: 9.73e-04
+2022-05-03 21:56:29,267 INFO [train.py:715] (3/8) Epoch 1, batch 11100, loss[loss=0.1956, simple_loss=0.2667, pruned_loss=0.06228, over 4966.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2492, pruned_loss=0.06149, over 972170.59 frames.], batch size: 39, lr: 9.72e-04
+2022-05-03 21:57:08,676 INFO [train.py:715] (3/8) Epoch 1, batch 11150, loss[loss=0.1636, simple_loss=0.2239, pruned_loss=0.05165, over 4778.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2495, pruned_loss=0.06129, over 971577.60 frames.], batch size: 12, lr: 9.72e-04
+2022-05-03 21:57:48,800 INFO [train.py:715] (3/8) Epoch 1, batch 11200, loss[loss=0.1949, simple_loss=0.2569, pruned_loss=0.06646, over 4947.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2498, pruned_loss=0.0614, over 972951.19 frames.], batch size: 29, lr: 9.71e-04
+2022-05-03 21:58:28,395 INFO [train.py:715] (3/8) Epoch 1, batch 11250, loss[loss=0.2143, simple_loss=0.274, pruned_loss=0.07733, over 4949.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2514, pruned_loss=0.06285, over 972140.19 frames.], batch size: 21, lr: 9.71e-04
+2022-05-03 21:59:06,582 INFO [train.py:715] (3/8) Epoch 1, batch 11300, loss[loss=0.1794, simple_loss=0.238, pruned_loss=0.06044, over 4989.00 frames.], tot_loss[loss=0.187, simple_loss=0.2502, pruned_loss=0.06188, over 971700.22 frames.], batch size: 28, lr: 9.70e-04
+2022-05-03 21:59:46,982 INFO [train.py:715] (3/8) Epoch 1, batch 11350, loss[loss=0.2108, simple_loss=0.2751, pruned_loss=0.0733, over 4984.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2495, pruned_loss=0.06151, over 972020.26 frames.], batch size: 28, lr: 9.70e-04
+2022-05-03 22:00:26,693 INFO [train.py:715] (3/8) Epoch 1, batch 11400, loss[loss=0.1378, simple_loss=0.2052, pruned_loss=0.03519, over 4803.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2504, pruned_loss=0.06264, over 971834.16 frames.], batch size: 18, lr: 9.69e-04
+2022-05-03 22:01:04,856 INFO [train.py:715] (3/8) Epoch 1, batch 11450, loss[loss=0.1735, simple_loss=0.2511, pruned_loss=0.04794, over 4822.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2501, pruned_loss=0.06221, over 971532.09 frames.], batch size: 25, lr: 9.69e-04
+2022-05-03 22:01:44,067 INFO [train.py:715] (3/8) Epoch 1, batch 11500, loss[loss=0.1593, simple_loss=0.2199, pruned_loss=0.04934, over 4944.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2503, pruned_loss=0.06247, over 972146.65 frames.], batch size: 35, lr: 9.68e-04
+2022-05-03 22:02:23,956 INFO [train.py:715] (3/8) Epoch 1, batch 11550, loss[loss=0.2162, simple_loss=0.2717, pruned_loss=0.08031, over 4957.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2508, pruned_loss=0.06334, over 972838.86 frames.], batch size: 21, lr: 9.68e-04
+2022-05-03 22:03:03,163 INFO [train.py:715] (3/8) Epoch 1, batch 11600, loss[loss=0.2046, simple_loss=0.266, pruned_loss=0.07155, over 4871.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2503, pruned_loss=0.06339, over 973260.18 frames.], batch size: 16, lr: 9.67e-04
+2022-05-03 22:03:41,492 INFO [train.py:715] (3/8) Epoch 1, batch 11650, loss[loss=0.1926, simple_loss=0.2531, pruned_loss=0.0661, over 4857.00 frames.], tot_loss[loss=0.1895, simple_loss=0.251, pruned_loss=0.06397, over 973436.61 frames.], batch size: 38, lr: 9.67e-04
+2022-05-03 22:04:21,431 INFO [train.py:715] (3/8) Epoch 1, batch 11700, loss[loss=0.1732, simple_loss=0.232, pruned_loss=0.05721, over 4814.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2509, pruned_loss=0.06378, over 972427.34 frames.], batch size: 13, lr: 9.66e-04
+2022-05-03 22:05:01,248 INFO [train.py:715] (3/8) Epoch 1, batch 11750, loss[loss=0.162, simple_loss=0.2291, pruned_loss=0.04745, over 4793.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2508, pruned_loss=0.06354, over 972315.72 frames.], batch size: 24, lr: 9.66e-04
+2022-05-03 22:05:40,550 INFO [train.py:715] (3/8) Epoch 1, batch 11800, loss[loss=0.1485, simple_loss=0.2249, pruned_loss=0.03607, over 4975.00 frames.], tot_loss[loss=0.19, simple_loss=0.2517, pruned_loss=0.06421, over 972554.04 frames.], batch size: 28, lr: 9.65e-04
+2022-05-03 22:06:19,253 INFO [train.py:715] (3/8) Epoch 1, batch 11850, loss[loss=0.1479, simple_loss=0.2131, pruned_loss=0.04134, over 4974.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2512, pruned_loss=0.06393, over 972881.10 frames.], batch size: 14, lr: 9.65e-04
+2022-05-03 22:06:59,285 INFO [train.py:715] (3/8) Epoch 1, batch 11900, loss[loss=0.1719, simple_loss=0.2333, pruned_loss=0.05528, over 4834.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2504, pruned_loss=0.06262, over 972724.07 frames.], batch size: 15, lr: 9.64e-04
+2022-05-03 22:07:38,634 INFO [train.py:715] (3/8) Epoch 1, batch 11950, loss[loss=0.1522, simple_loss=0.2219, pruned_loss=0.04128, over 4844.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2502, pruned_loss=0.06226, over 972544.96 frames.], batch size: 26, lr: 9.63e-04
+2022-05-03 22:08:17,118 INFO [train.py:715] (3/8) Epoch 1, batch 12000, loss[loss=0.2073, simple_loss=0.2613, pruned_loss=0.0766, over 4866.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2494, pruned_loss=0.06192, over 972085.32 frames.], batch size: 32, lr: 9.63e-04
+2022-05-03 22:08:17,119 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 22:08:27,630 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.1244, simple_loss=0.2116, pruned_loss=0.01858, over 914524.00 frames.
+2022-05-03 22:09:06,363 INFO [train.py:715] (3/8) Epoch 1, batch 12050, loss[loss=0.2076, simple_loss=0.2788, pruned_loss=0.06818, over 4787.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2508, pruned_loss=0.06289, over 973065.73 frames.], batch size: 18, lr: 9.62e-04
+2022-05-03 22:09:47,001 INFO [train.py:715] (3/8) Epoch 1, batch 12100, loss[loss=0.176, simple_loss=0.2538, pruned_loss=0.04904, over 4817.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2508, pruned_loss=0.06298, over 972070.13 frames.], batch size: 21, lr: 9.62e-04
+2022-05-03 22:10:27,685 INFO [train.py:715] (3/8) Epoch 1, batch 12150, loss[loss=0.1872, simple_loss=0.2464, pruned_loss=0.064, over 4924.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2501, pruned_loss=0.0623, over 971817.96 frames.], batch size: 18, lr: 9.61e-04
+2022-05-03 22:11:06,656 INFO [train.py:715] (3/8) Epoch 1, batch 12200, loss[loss=0.1684, simple_loss=0.2365, pruned_loss=0.05012, over 4958.00 frames.], tot_loss[loss=0.1869, simple_loss=0.25, pruned_loss=0.06184, over 971494.72 frames.], batch size: 24, lr: 9.61e-04
+2022-05-03 22:11:46,559 INFO [train.py:715] (3/8) Epoch 1, batch 12250, loss[loss=0.18, simple_loss=0.2499, pruned_loss=0.05505, over 4953.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2496, pruned_loss=0.06127, over 972590.47 frames.], batch size: 21, lr: 9.60e-04
+2022-05-03 22:12:27,155 INFO [train.py:715] (3/8) Epoch 1, batch 12300, loss[loss=0.2027, simple_loss=0.2559, pruned_loss=0.07473, over 4868.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2503, pruned_loss=0.06217, over 971985.29 frames.], batch size: 32, lr: 9.60e-04
+2022-05-03 22:13:06,771 INFO [train.py:715] (3/8) Epoch 1, batch 12350, loss[loss=0.1798, simple_loss=0.2567, pruned_loss=0.05141, over 4944.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2505, pruned_loss=0.06226, over 971340.03 frames.], batch size: 21, lr: 9.59e-04
+2022-05-03 22:13:45,539 INFO [train.py:715] (3/8) Epoch 1, batch 12400, loss[loss=0.1877, simple_loss=0.2597, pruned_loss=0.05781, over 4927.00 frames.], tot_loss[loss=0.187, simple_loss=0.2501, pruned_loss=0.06195, over 971368.72 frames.], batch size: 23, lr: 9.59e-04
+2022-05-03 22:14:25,684 INFO [train.py:715] (3/8) Epoch 1, batch 12450, loss[loss=0.1832, simple_loss=0.2469, pruned_loss=0.0598, over 4817.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2506, pruned_loss=0.06225, over 972157.33 frames.], batch size: 15, lr: 9.58e-04
+2022-05-03 22:15:05,667 INFO [train.py:715] (3/8) Epoch 1, batch 12500, loss[loss=0.2127, simple_loss=0.2615, pruned_loss=0.08199, over 4751.00 frames.], tot_loss[loss=0.1884, simple_loss=0.251, pruned_loss=0.06292, over 973615.55 frames.], batch size: 16, lr: 9.58e-04
+2022-05-03 22:15:44,874 INFO [train.py:715] (3/8) Epoch 1, batch 12550, loss[loss=0.1427, simple_loss=0.2103, pruned_loss=0.03758, over 4835.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2521, pruned_loss=0.06354, over 973774.08 frames.], batch size: 13, lr: 9.57e-04
+2022-05-03 22:16:24,271 INFO [train.py:715] (3/8) Epoch 1, batch 12600, loss[loss=0.1963, simple_loss=0.2541, pruned_loss=0.06927, over 4987.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2523, pruned_loss=0.06348, over 972120.41 frames.], batch size: 20, lr: 9.57e-04
+2022-05-03 22:17:04,547 INFO [train.py:715] (3/8) Epoch 1, batch 12650, loss[loss=0.1561, simple_loss=0.221, pruned_loss=0.04557, over 4754.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2512, pruned_loss=0.06293, over 972065.46 frames.], batch size: 12, lr: 9.56e-04
+2022-05-03 22:17:43,552 INFO [train.py:715] (3/8) Epoch 1, batch 12700, loss[loss=0.1665, simple_loss=0.2323, pruned_loss=0.0503, over 4834.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2501, pruned_loss=0.06223, over 971389.79 frames.], batch size: 30, lr: 9.56e-04
+2022-05-03 22:18:22,948 INFO [train.py:715] (3/8) Epoch 1, batch 12750, loss[loss=0.2066, simple_loss=0.2597, pruned_loss=0.07673, over 4776.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2502, pruned_loss=0.06213, over 972286.89 frames.], batch size: 17, lr: 9.55e-04
+2022-05-03 22:19:03,050 INFO [train.py:715] (3/8) Epoch 1, batch 12800, loss[loss=0.1592, simple_loss=0.2251, pruned_loss=0.04664, over 4961.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2506, pruned_loss=0.06229, over 972660.31 frames.], batch size: 24, lr: 9.55e-04
+2022-05-03 22:19:42,870 INFO [train.py:715] (3/8) Epoch 1, batch 12850, loss[loss=0.2001, simple_loss=0.2574, pruned_loss=0.0714, over 4807.00 frames.], tot_loss[loss=0.189, simple_loss=0.252, pruned_loss=0.06304, over 972531.26 frames.], batch size: 21, lr: 9.54e-04
+2022-05-03 22:20:21,820 INFO [train.py:715] (3/8) Epoch 1, batch 12900, loss[loss=0.1827, simple_loss=0.2562, pruned_loss=0.05463, over 4973.00 frames.], tot_loss[loss=0.189, simple_loss=0.2518, pruned_loss=0.06314, over 971628.70 frames.], batch size: 15, lr: 9.54e-04
+2022-05-03 22:21:01,111 INFO [train.py:715] (3/8) Epoch 1, batch 12950, loss[loss=0.1748, simple_loss=0.2243, pruned_loss=0.0626, over 4935.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2512, pruned_loss=0.06271, over 972145.72 frames.], batch size: 23, lr: 9.53e-04
+2022-05-03 22:21:41,526 INFO [train.py:715] (3/8) Epoch 1, batch 13000, loss[loss=0.2033, simple_loss=0.2649, pruned_loss=0.0708, over 4701.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2513, pruned_loss=0.06279, over 972464.33 frames.], batch size: 15, lr: 9.53e-04
+2022-05-03 22:22:21,098 INFO [train.py:715] (3/8) Epoch 1, batch 13050, loss[loss=0.1797, simple_loss=0.245, pruned_loss=0.05722, over 4785.00 frames.], tot_loss[loss=0.1887, simple_loss=0.251, pruned_loss=0.06323, over 972409.68 frames.], batch size: 17, lr: 9.52e-04
+2022-05-03 22:23:01,176 INFO [train.py:715] (3/8) Epoch 1, batch 13100, loss[loss=0.191, simple_loss=0.2524, pruned_loss=0.06484, over 4887.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2509, pruned_loss=0.06324, over 972690.78 frames.], batch size: 16, lr: 9.52e-04
+2022-05-03 22:23:41,360 INFO [train.py:715] (3/8) Epoch 1, batch 13150, loss[loss=0.2106, simple_loss=0.2605, pruned_loss=0.08038, over 4959.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2514, pruned_loss=0.06357, over 972013.38 frames.], batch size: 39, lr: 9.51e-04
+2022-05-03 22:24:23,878 INFO [train.py:715] (3/8) Epoch 1, batch 13200, loss[loss=0.1947, simple_loss=0.2341, pruned_loss=0.0776, over 4896.00 frames.], tot_loss[loss=0.189, simple_loss=0.2513, pruned_loss=0.0633, over 972425.33 frames.], batch size: 19, lr: 9.51e-04
+2022-05-03 22:25:03,006 INFO [train.py:715] (3/8) Epoch 1, batch 13250, loss[loss=0.1901, simple_loss=0.2582, pruned_loss=0.06104, over 4844.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2517, pruned_loss=0.06363, over 972113.89 frames.], batch size: 30, lr: 9.51e-04
+2022-05-03 22:25:41,751 INFO [train.py:715] (3/8) Epoch 1, batch 13300, loss[loss=0.1774, simple_loss=0.2561, pruned_loss=0.04937, over 4953.00 frames.], tot_loss[loss=0.1886, simple_loss=0.251, pruned_loss=0.06305, over 971699.60 frames.], batch size: 24, lr: 9.50e-04
+2022-05-03 22:26:21,979 INFO [train.py:715] (3/8) Epoch 1, batch 13350, loss[loss=0.2019, simple_loss=0.2606, pruned_loss=0.07158, over 4801.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2499, pruned_loss=0.06236, over 971353.38 frames.], batch size: 21, lr: 9.50e-04
+2022-05-03 22:27:01,384 INFO [train.py:715] (3/8) Epoch 1, batch 13400, loss[loss=0.1605, simple_loss=0.2164, pruned_loss=0.05235, over 4755.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2497, pruned_loss=0.06246, over 971880.93 frames.], batch size: 12, lr: 9.49e-04
+2022-05-03 22:27:41,354 INFO [train.py:715] (3/8) Epoch 1, batch 13450, loss[loss=0.2135, simple_loss=0.2774, pruned_loss=0.0748, over 4848.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2505, pruned_loss=0.06289, over 971776.09 frames.], batch size: 34, lr: 9.49e-04
+2022-05-03 22:28:21,069 INFO [train.py:715] (3/8) Epoch 1, batch 13500, loss[loss=0.2194, simple_loss=0.2809, pruned_loss=0.07897, over 4866.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2512, pruned_loss=0.06294, over 972368.99 frames.], batch size: 20, lr: 9.48e-04
+2022-05-03 22:29:01,036 INFO [train.py:715] (3/8) Epoch 1, batch 13550, loss[loss=0.255, simple_loss=0.3146, pruned_loss=0.09767, over 4845.00 frames.], tot_loss[loss=0.1899, simple_loss=0.252, pruned_loss=0.06393, over 972425.89 frames.], batch size: 15, lr: 9.48e-04
+2022-05-03 22:29:39,297 INFO [train.py:715] (3/8) Epoch 1, batch 13600, loss[loss=0.2063, simple_loss=0.2601, pruned_loss=0.07628, over 4982.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2516, pruned_loss=0.0637, over 972472.07 frames.], batch size: 28, lr: 9.47e-04
+2022-05-03 22:30:18,505 INFO [train.py:715] (3/8) Epoch 1, batch 13650, loss[loss=0.1768, simple_loss=0.2404, pruned_loss=0.05657, over 4826.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2505, pruned_loss=0.06296, over 972088.41 frames.], batch size: 26, lr: 9.47e-04
+2022-05-03 22:30:58,735 INFO [train.py:715] (3/8) Epoch 1, batch 13700, loss[loss=0.2525, simple_loss=0.3008, pruned_loss=0.1021, over 4756.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2497, pruned_loss=0.06255, over 971313.94 frames.], batch size: 16, lr: 9.46e-04
+2022-05-03 22:31:38,135 INFO [train.py:715] (3/8) Epoch 1, batch 13750, loss[loss=0.1783, simple_loss=0.2435, pruned_loss=0.05651, over 4783.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2507, pruned_loss=0.06321, over 971496.23 frames.], batch size: 18, lr: 9.46e-04
+2022-05-03 22:32:17,280 INFO [train.py:715] (3/8) Epoch 1, batch 13800, loss[loss=0.1693, simple_loss=0.233, pruned_loss=0.05278, over 4838.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2508, pruned_loss=0.06326, over 971262.43 frames.], batch size: 13, lr: 9.45e-04
+2022-05-03 22:32:56,966 INFO [train.py:715] (3/8) Epoch 1, batch 13850, loss[loss=0.1846, simple_loss=0.2476, pruned_loss=0.06084, over 4990.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2505, pruned_loss=0.06325, over 971282.18 frames.], batch size: 15, lr: 9.45e-04
+2022-05-03 22:33:36,809 INFO [train.py:715] (3/8) Epoch 1, batch 13900, loss[loss=0.1692, simple_loss=0.2337, pruned_loss=0.05235, over 4857.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2504, pruned_loss=0.06293, over 971920.53 frames.], batch size: 13, lr: 9.44e-04
+2022-05-03 22:34:15,305 INFO [train.py:715] (3/8) Epoch 1, batch 13950, loss[loss=0.2431, simple_loss=0.2816, pruned_loss=0.1023, over 4915.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2502, pruned_loss=0.06331, over 972575.01 frames.], batch size: 18, lr: 9.44e-04
+2022-05-03 22:34:54,564 INFO [train.py:715] (3/8) Epoch 1, batch 14000, loss[loss=0.1696, simple_loss=0.2342, pruned_loss=0.05254, over 4780.00 frames.], tot_loss[loss=0.1895, simple_loss=0.251, pruned_loss=0.06403, over 971803.10 frames.], batch size: 14, lr: 9.43e-04
+2022-05-03 22:35:34,713 INFO [train.py:715] (3/8) Epoch 1, batch 14050, loss[loss=0.2566, simple_loss=0.3004, pruned_loss=0.1063, over 4818.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2507, pruned_loss=0.06386, over 971332.33 frames.], batch size: 25, lr: 9.43e-04
+2022-05-03 22:36:13,514 INFO [train.py:715] (3/8) Epoch 1, batch 14100, loss[loss=0.1534, simple_loss=0.2269, pruned_loss=0.03998, over 4764.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2504, pruned_loss=0.06324, over 971066.04 frames.], batch size: 17, lr: 9.42e-04
+2022-05-03 22:36:52,747 INFO [train.py:715] (3/8) Epoch 1, batch 14150, loss[loss=0.1777, simple_loss=0.2349, pruned_loss=0.0603, over 4934.00 frames.], tot_loss[loss=0.189, simple_loss=0.2511, pruned_loss=0.06348, over 971806.84 frames.], batch size: 23, lr: 9.42e-04
+2022-05-03 22:37:31,980 INFO [train.py:715] (3/8) Epoch 1, batch 14200, loss[loss=0.1863, simple_loss=0.2407, pruned_loss=0.06593, over 4921.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2497, pruned_loss=0.06237, over 971502.81 frames.], batch size: 18, lr: 9.41e-04
+2022-05-03 22:38:12,095 INFO [train.py:715] (3/8) Epoch 1, batch 14250, loss[loss=0.1474, simple_loss=0.2107, pruned_loss=0.04202, over 4647.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2495, pruned_loss=0.06237, over 971228.32 frames.], batch size: 13, lr: 9.41e-04
+2022-05-03 22:38:50,570 INFO [train.py:715] (3/8) Epoch 1, batch 14300, loss[loss=0.1649, simple_loss=0.2193, pruned_loss=0.0552, over 4825.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2491, pruned_loss=0.06167, over 970563.89 frames.], batch size: 12, lr: 9.40e-04
+2022-05-03 22:39:29,557 INFO [train.py:715] (3/8) Epoch 1, batch 14350, loss[loss=0.1579, simple_loss=0.2177, pruned_loss=0.04912, over 4782.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2502, pruned_loss=0.06206, over 972122.96 frames.], batch size: 14, lr: 9.40e-04
+2022-05-03 22:40:09,905 INFO [train.py:715] (3/8) Epoch 1, batch 14400, loss[loss=0.1848, simple_loss=0.2482, pruned_loss=0.06072, over 4787.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2504, pruned_loss=0.06224, over 972200.76 frames.], batch size: 14, lr: 9.39e-04
+2022-05-03 22:40:48,725 INFO [train.py:715] (3/8) Epoch 1, batch 14450, loss[loss=0.167, simple_loss=0.2376, pruned_loss=0.04818, over 4771.00 frames.], tot_loss[loss=0.1888, simple_loss=0.252, pruned_loss=0.06283, over 971795.00 frames.], batch size: 14, lr: 9.39e-04
+2022-05-03 22:41:28,251 INFO [train.py:715] (3/8) Epoch 1, batch 14500, loss[loss=0.171, simple_loss=0.2305, pruned_loss=0.05578, over 4705.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2521, pruned_loss=0.06317, over 972767.55 frames.], batch size: 15, lr: 9.39e-04
+2022-05-03 22:42:08,353 INFO [train.py:715] (3/8) Epoch 1, batch 14550, loss[loss=0.1849, simple_loss=0.253, pruned_loss=0.05836, over 4889.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2527, pruned_loss=0.06379, over 971614.97 frames.], batch size: 22, lr: 9.38e-04
+2022-05-03 22:42:47,866 INFO [train.py:715] (3/8) Epoch 1, batch 14600, loss[loss=0.1873, simple_loss=0.252, pruned_loss=0.06133, over 4842.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2514, pruned_loss=0.06315, over 970687.78 frames.], batch size: 15, lr: 9.38e-04
+2022-05-03 22:43:26,826 INFO [train.py:715] (3/8) Epoch 1, batch 14650, loss[loss=0.1854, simple_loss=0.2535, pruned_loss=0.05864, over 4702.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2505, pruned_loss=0.06238, over 970427.86 frames.], batch size: 15, lr: 9.37e-04
+2022-05-03 22:44:05,662 INFO [train.py:715] (3/8) Epoch 1, batch 14700, loss[loss=0.1814, simple_loss=0.2524, pruned_loss=0.05522, over 4778.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2498, pruned_loss=0.06186, over 970408.83 frames.], batch size: 17, lr: 9.37e-04
+2022-05-03 22:44:45,792 INFO [train.py:715] (3/8) Epoch 1, batch 14750, loss[loss=0.2068, simple_loss=0.2684, pruned_loss=0.07264, over 4800.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2494, pruned_loss=0.06185, over 971137.08 frames.], batch size: 25, lr: 9.36e-04
+2022-05-03 22:45:24,936 INFO [train.py:715] (3/8) Epoch 1, batch 14800, loss[loss=0.2002, simple_loss=0.2564, pruned_loss=0.072, over 4986.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2498, pruned_loss=0.06204, over 971621.19 frames.], batch size: 28, lr: 9.36e-04
+2022-05-03 22:46:04,496 INFO [train.py:715] (3/8) Epoch 1, batch 14850, loss[loss=0.2069, simple_loss=0.2607, pruned_loss=0.07655, over 4881.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2493, pruned_loss=0.06184, over 971636.80 frames.], batch size: 16, lr: 9.35e-04
+2022-05-03 22:46:43,810 INFO [train.py:715] (3/8) Epoch 1, batch 14900, loss[loss=0.191, simple_loss=0.2604, pruned_loss=0.06077, over 4788.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2497, pruned_loss=0.06157, over 971272.42 frames.], batch size: 17, lr: 9.35e-04
+2022-05-03 22:47:22,416 INFO [train.py:715] (3/8) Epoch 1, batch 14950, loss[loss=0.1729, simple_loss=0.2318, pruned_loss=0.05702, over 4814.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2499, pruned_loss=0.06168, over 971440.16 frames.], batch size: 14, lr: 9.34e-04
+2022-05-03 22:48:02,033 INFO [train.py:715] (3/8) Epoch 1, batch 15000, loss[loss=0.1672, simple_loss=0.2364, pruned_loss=0.049, over 4894.00 frames.], tot_loss[loss=0.1881, simple_loss=0.251, pruned_loss=0.06255, over 971555.96 frames.], batch size: 19, lr: 9.34e-04
+2022-05-03 22:48:02,034 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 22:48:17,508 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.1242, simple_loss=0.2115, pruned_loss=0.01842, over 914524.00 frames.
+2022-05-03 22:48:57,644 INFO [train.py:715] (3/8) Epoch 1, batch 15050, loss[loss=0.1701, simple_loss=0.2333, pruned_loss=0.05339, over 4833.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2502, pruned_loss=0.06219, over 971493.19 frames.], batch size: 26, lr: 9.33e-04
+2022-05-03 22:49:37,556 INFO [train.py:715] (3/8) Epoch 1, batch 15100, loss[loss=0.167, simple_loss=0.2357, pruned_loss=0.04917, over 4812.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2496, pruned_loss=0.06211, over 971102.79 frames.], batch size: 26, lr: 9.33e-04
+2022-05-03 22:50:18,095 INFO [train.py:715] (3/8) Epoch 1, batch 15150, loss[loss=0.1563, simple_loss=0.227, pruned_loss=0.04276, over 4784.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2505, pruned_loss=0.06245, over 971923.74 frames.], batch size: 17, lr: 9.32e-04
+2022-05-03 22:50:57,473 INFO [train.py:715] (3/8) Epoch 1, batch 15200, loss[loss=0.191, simple_loss=0.2572, pruned_loss=0.06239, over 4908.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2499, pruned_loss=0.06194, over 971930.61 frames.], batch size: 19, lr: 9.32e-04
+2022-05-03 22:51:37,953 INFO [train.py:715] (3/8) Epoch 1, batch 15250, loss[loss=0.185, simple_loss=0.2548, pruned_loss=0.05756, over 4782.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2498, pruned_loss=0.06231, over 972842.83 frames.], batch size: 17, lr: 9.32e-04
+2022-05-03 22:52:17,874 INFO [train.py:715] (3/8) Epoch 1, batch 15300, loss[loss=0.1693, simple_loss=0.2376, pruned_loss=0.05049, over 4778.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2502, pruned_loss=0.06242, over 973324.66 frames.], batch size: 17, lr: 9.31e-04
+2022-05-03 22:52:57,760 INFO [train.py:715] (3/8) Epoch 1, batch 15350, loss[loss=0.2144, simple_loss=0.2867, pruned_loss=0.071, over 4965.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2499, pruned_loss=0.06229, over 972394.93 frames.], batch size: 21, lr: 9.31e-04
+2022-05-03 22:53:37,898 INFO [train.py:715] (3/8) Epoch 1, batch 15400, loss[loss=0.1921, simple_loss=0.2523, pruned_loss=0.06593, over 4987.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2498, pruned_loss=0.0626, over 972033.49 frames.], batch size: 27, lr: 9.30e-04
+2022-05-03 22:54:18,168 INFO [train.py:715] (3/8) Epoch 1, batch 15450, loss[loss=0.1737, simple_loss=0.2387, pruned_loss=0.05432, over 4854.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2495, pruned_loss=0.06199, over 972324.89 frames.], batch size: 20, lr: 9.30e-04
+2022-05-03 22:54:58,643 INFO [train.py:715] (3/8) Epoch 1, batch 15500, loss[loss=0.1808, simple_loss=0.2421, pruned_loss=0.05976, over 4986.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2507, pruned_loss=0.06305, over 972708.43 frames.], batch size: 25, lr: 9.29e-04
+2022-05-03 22:55:37,735 INFO [train.py:715] (3/8) Epoch 1, batch 15550, loss[loss=0.1723, simple_loss=0.239, pruned_loss=0.05277, over 4785.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2499, pruned_loss=0.06253, over 972760.62 frames.], batch size: 18, lr: 9.29e-04
+2022-05-03 22:56:18,062 INFO [train.py:715] (3/8) Epoch 1, batch 15600, loss[loss=0.149, simple_loss=0.2106, pruned_loss=0.0437, over 4762.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2487, pruned_loss=0.06227, over 972206.47 frames.], batch size: 16, lr: 9.28e-04
+2022-05-03 22:56:58,352 INFO [train.py:715] (3/8) Epoch 1, batch 15650, loss[loss=0.1639, simple_loss=0.2269, pruned_loss=0.05046, over 4952.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2499, pruned_loss=0.06313, over 971799.54 frames.], batch size: 23, lr: 9.28e-04
+2022-05-03 22:57:38,272 INFO [train.py:715] (3/8) Epoch 1, batch 15700, loss[loss=0.1986, simple_loss=0.2639, pruned_loss=0.06662, over 4828.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2492, pruned_loss=0.06265, over 972106.29 frames.], batch size: 26, lr: 9.27e-04
+2022-05-03 22:58:17,911 INFO [train.py:715] (3/8) Epoch 1, batch 15750, loss[loss=0.2296, simple_loss=0.2866, pruned_loss=0.08633, over 4929.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2495, pruned_loss=0.06318, over 971468.80 frames.], batch size: 35, lr: 9.27e-04
+2022-05-03 22:58:58,193 INFO [train.py:715] (3/8) Epoch 1, batch 15800, loss[loss=0.1964, simple_loss=0.2598, pruned_loss=0.0665, over 4986.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2501, pruned_loss=0.06332, over 971178.71 frames.], batch size: 31, lr: 9.27e-04
+2022-05-03 22:59:38,877 INFO [train.py:715] (3/8) Epoch 1, batch 15850, loss[loss=0.1894, simple_loss=0.2503, pruned_loss=0.06425, over 4937.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2502, pruned_loss=0.0626, over 972076.38 frames.], batch size: 35, lr: 9.26e-04
+2022-05-03 23:00:18,432 INFO [train.py:715] (3/8) Epoch 1, batch 15900, loss[loss=0.1768, simple_loss=0.2458, pruned_loss=0.05386, over 4982.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2512, pruned_loss=0.06295, over 971608.65 frames.], batch size: 25, lr: 9.26e-04
+2022-05-03 23:00:58,071 INFO [train.py:715] (3/8) Epoch 1, batch 15950, loss[loss=0.1939, simple_loss=0.2585, pruned_loss=0.0646, over 4905.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2506, pruned_loss=0.06258, over 972052.60 frames.], batch size: 19, lr: 9.25e-04
+2022-05-03 23:01:37,501 INFO [train.py:715] (3/8) Epoch 1, batch 16000, loss[loss=0.2086, simple_loss=0.2789, pruned_loss=0.06913, over 4822.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2509, pruned_loss=0.06244, over 972041.67 frames.], batch size: 25, lr: 9.25e-04
+2022-05-03 23:02:16,258 INFO [train.py:715] (3/8) Epoch 1, batch 16050, loss[loss=0.1805, simple_loss=0.2457, pruned_loss=0.05761, over 4819.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2507, pruned_loss=0.0623, over 972783.69 frames.], batch size: 26, lr: 9.24e-04
+2022-05-03 23:02:55,584 INFO [train.py:715] (3/8) Epoch 1, batch 16100, loss[loss=0.1338, simple_loss=0.2029, pruned_loss=0.03235, over 4647.00 frames.], tot_loss[loss=0.1869, simple_loss=0.25, pruned_loss=0.06193, over 972472.03 frames.], batch size: 13, lr: 9.24e-04
+2022-05-03 23:03:35,229 INFO [train.py:715] (3/8) Epoch 1, batch 16150, loss[loss=0.1566, simple_loss=0.2282, pruned_loss=0.04253, over 4761.00 frames.], tot_loss[loss=0.1866, simple_loss=0.25, pruned_loss=0.06159, over 971939.42 frames.], batch size: 19, lr: 9.23e-04
+2022-05-03 23:04:15,419 INFO [train.py:715] (3/8) Epoch 1, batch 16200, loss[loss=0.14, simple_loss=0.2081, pruned_loss=0.03593, over 4844.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2489, pruned_loss=0.06114, over 971973.56 frames.], batch size: 13, lr: 9.23e-04
+2022-05-03 23:04:53,725 INFO [train.py:715] (3/8) Epoch 1, batch 16250, loss[loss=0.1514, simple_loss=0.2202, pruned_loss=0.04126, over 4953.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2499, pruned_loss=0.06173, over 971841.39 frames.], batch size: 24, lr: 9.22e-04
+2022-05-03 23:05:33,192 INFO [train.py:715] (3/8) Epoch 1, batch 16300, loss[loss=0.1837, simple_loss=0.2459, pruned_loss=0.06074, over 4808.00 frames.], tot_loss[loss=0.187, simple_loss=0.2504, pruned_loss=0.06186, over 972191.42 frames.], batch size: 21, lr: 9.22e-04
+2022-05-03 23:06:12,741 INFO [train.py:715] (3/8) Epoch 1, batch 16350, loss[loss=0.2496, simple_loss=0.2902, pruned_loss=0.1045, over 4956.00 frames.], tot_loss[loss=0.188, simple_loss=0.2509, pruned_loss=0.06251, over 971962.49 frames.], batch size: 35, lr: 9.22e-04
+2022-05-03 23:06:51,399 INFO [train.py:715] (3/8) Epoch 1, batch 16400, loss[loss=0.1796, simple_loss=0.238, pruned_loss=0.06056, over 4934.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2492, pruned_loss=0.06136, over 971033.72 frames.], batch size: 21, lr: 9.21e-04
+2022-05-03 23:07:30,895 INFO [train.py:715] (3/8) Epoch 1, batch 16450, loss[loss=0.1845, simple_loss=0.2466, pruned_loss=0.06121, over 4940.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2489, pruned_loss=0.06112, over 971889.78 frames.], batch size: 21, lr: 9.21e-04
+2022-05-03 23:08:10,541 INFO [train.py:715] (3/8) Epoch 1, batch 16500, loss[loss=0.1961, simple_loss=0.257, pruned_loss=0.06761, over 4768.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2497, pruned_loss=0.06186, over 971570.45 frames.], batch size: 19, lr: 9.20e-04
+2022-05-03 23:08:50,453 INFO [train.py:715] (3/8) Epoch 1, batch 16550, loss[loss=0.176, simple_loss=0.2366, pruned_loss=0.05774, over 4945.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2497, pruned_loss=0.06186, over 970850.11 frames.], batch size: 21, lr: 9.20e-04
+2022-05-03 23:09:28,844 INFO [train.py:715] (3/8) Epoch 1, batch 16600, loss[loss=0.1919, simple_loss=0.2519, pruned_loss=0.06597, over 4964.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2492, pruned_loss=0.06144, over 970942.74 frames.], batch size: 24, lr: 9.19e-04
+2022-05-03 23:10:09,002 INFO [train.py:715] (3/8) Epoch 1, batch 16650, loss[loss=0.1802, simple_loss=0.2423, pruned_loss=0.059, over 4804.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2495, pruned_loss=0.06194, over 971316.59 frames.], batch size: 21, lr: 9.19e-04
+2022-05-03 23:10:48,681 INFO [train.py:715] (3/8) Epoch 1, batch 16700, loss[loss=0.1973, simple_loss=0.2623, pruned_loss=0.06613, over 4933.00 frames.], tot_loss[loss=0.187, simple_loss=0.2501, pruned_loss=0.06196, over 971069.88 frames.], batch size: 23, lr: 9.18e-04
+2022-05-03 23:11:28,440 INFO [train.py:715] (3/8) Epoch 1, batch 16750, loss[loss=0.1643, simple_loss=0.2399, pruned_loss=0.04432, over 4884.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2498, pruned_loss=0.06157, over 972241.92 frames.], batch size: 32, lr: 9.18e-04
+2022-05-03 23:12:08,271 INFO [train.py:715] (3/8) Epoch 1, batch 16800, loss[loss=0.1633, simple_loss=0.2364, pruned_loss=0.04513, over 4932.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2489, pruned_loss=0.06083, over 971911.86 frames.], batch size: 18, lr: 9.18e-04
+2022-05-03 23:12:47,923 INFO [train.py:715] (3/8) Epoch 1, batch 16850, loss[loss=0.2103, simple_loss=0.2744, pruned_loss=0.07311, over 4770.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2491, pruned_loss=0.06112, over 972395.05 frames.], batch size: 17, lr: 9.17e-04
+2022-05-03 23:13:27,906 INFO [train.py:715] (3/8) Epoch 1, batch 16900, loss[loss=0.1915, simple_loss=0.2455, pruned_loss=0.06871, over 4751.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2493, pruned_loss=0.06196, over 972175.28 frames.], batch size: 19, lr: 9.17e-04
+2022-05-03 23:14:06,929 INFO [train.py:715] (3/8) Epoch 1, batch 16950, loss[loss=0.1872, simple_loss=0.2511, pruned_loss=0.06165, over 4970.00 frames.], tot_loss[loss=0.186, simple_loss=0.2489, pruned_loss=0.06157, over 972003.28 frames.], batch size: 35, lr: 9.16e-04
+2022-05-03 23:14:46,345 INFO [train.py:715] (3/8) Epoch 1, batch 17000, loss[loss=0.1946, simple_loss=0.2607, pruned_loss=0.06422, over 4883.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2482, pruned_loss=0.06102, over 971429.34 frames.], batch size: 16, lr: 9.16e-04
+2022-05-03 23:15:26,357 INFO [train.py:715] (3/8) Epoch 1, batch 17050, loss[loss=0.1921, simple_loss=0.265, pruned_loss=0.0596, over 4943.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2488, pruned_loss=0.06115, over 971712.29 frames.], batch size: 21, lr: 9.15e-04
+2022-05-03 23:16:05,139 INFO [train.py:715] (3/8) Epoch 1, batch 17100, loss[loss=0.1597, simple_loss=0.2231, pruned_loss=0.04818, over 4784.00 frames.], tot_loss[loss=0.1846, simple_loss=0.248, pruned_loss=0.06056, over 971272.10 frames.], batch size: 14, lr: 9.15e-04
+2022-05-03 23:16:44,846 INFO [train.py:715] (3/8) Epoch 1, batch 17150, loss[loss=0.1422, simple_loss=0.2101, pruned_loss=0.03715, over 4812.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2484, pruned_loss=0.06068, over 972201.22 frames.], batch size: 25, lr: 9.15e-04
+2022-05-03 23:17:25,478 INFO [train.py:715] (3/8) Epoch 1, batch 17200, loss[loss=0.1734, simple_loss=0.2422, pruned_loss=0.05225, over 4987.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2477, pruned_loss=0.06058, over 972686.64 frames.], batch size: 28, lr: 9.14e-04
+2022-05-03 23:18:05,275 INFO [train.py:715] (3/8) Epoch 1, batch 17250, loss[loss=0.2033, simple_loss=0.2616, pruned_loss=0.07251, over 4919.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2488, pruned_loss=0.06103, over 971851.50 frames.], batch size: 17, lr: 9.14e-04
+2022-05-03 23:18:43,786 INFO [train.py:715] (3/8) Epoch 1, batch 17300, loss[loss=0.1859, simple_loss=0.2383, pruned_loss=0.06671, over 4911.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2489, pruned_loss=0.06098, over 972574.74 frames.], batch size: 18, lr: 9.13e-04
+2022-05-03 23:19:23,810 INFO [train.py:715] (3/8) Epoch 1, batch 17350, loss[loss=0.1653, simple_loss=0.2288, pruned_loss=0.05085, over 4689.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2493, pruned_loss=0.061, over 972532.90 frames.], batch size: 15, lr: 9.13e-04
+2022-05-03 23:20:03,642 INFO [train.py:715] (3/8) Epoch 1, batch 17400, loss[loss=0.198, simple_loss=0.2548, pruned_loss=0.07063, over 4802.00 frames.], tot_loss[loss=0.1847, simple_loss=0.248, pruned_loss=0.0607, over 971593.77 frames.], batch size: 14, lr: 9.12e-04
+2022-05-03 23:20:42,913 INFO [train.py:715] (3/8) Epoch 1, batch 17450, loss[loss=0.1466, simple_loss=0.211, pruned_loss=0.04107, over 4773.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2475, pruned_loss=0.06066, over 971194.63 frames.], batch size: 18, lr: 9.12e-04
+2022-05-03 23:21:23,311 INFO [train.py:715] (3/8) Epoch 1, batch 17500, loss[loss=0.228, simple_loss=0.2767, pruned_loss=0.08965, over 4978.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2479, pruned_loss=0.06081, over 970866.04 frames.], batch size: 31, lr: 9.11e-04
+2022-05-03 23:22:03,740 INFO [train.py:715] (3/8) Epoch 1, batch 17550, loss[loss=0.2001, simple_loss=0.2607, pruned_loss=0.06982, over 4971.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2492, pruned_loss=0.06158, over 970572.14 frames.], batch size: 14, lr: 9.11e-04
+2022-05-03 23:22:44,361 INFO [train.py:715] (3/8) Epoch 1, batch 17600, loss[loss=0.1635, simple_loss=0.2425, pruned_loss=0.04219, over 4947.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2482, pruned_loss=0.06046, over 971460.74 frames.], batch size: 21, lr: 9.11e-04
+2022-05-03 23:23:24,058 INFO [train.py:715] (3/8) Epoch 1, batch 17650, loss[loss=0.1672, simple_loss=0.2439, pruned_loss=0.04521, over 4762.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2481, pruned_loss=0.06032, over 971685.44 frames.], batch size: 19, lr: 9.10e-04
+2022-05-03 23:24:04,754 INFO [train.py:715] (3/8) Epoch 1, batch 17700, loss[loss=0.1556, simple_loss=0.2335, pruned_loss=0.03885, over 4941.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2467, pruned_loss=0.05976, over 971779.03 frames.], batch size: 21, lr: 9.10e-04
+2022-05-03 23:24:44,999 INFO [train.py:715] (3/8) Epoch 1, batch 17750, loss[loss=0.1986, simple_loss=0.2509, pruned_loss=0.07314, over 4785.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2472, pruned_loss=0.06055, over 972008.37 frames.], batch size: 14, lr: 9.09e-04
+2022-05-03 23:25:24,538 INFO [train.py:715] (3/8) Epoch 1, batch 17800, loss[loss=0.2124, simple_loss=0.2686, pruned_loss=0.07808, over 4929.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2485, pruned_loss=0.06136, over 971636.37 frames.], batch size: 29, lr: 9.09e-04
+2022-05-03 23:26:04,929 INFO [train.py:715] (3/8) Epoch 1, batch 17850, loss[loss=0.1859, simple_loss=0.256, pruned_loss=0.05792, over 4903.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2492, pruned_loss=0.06152, over 972916.01 frames.], batch size: 18, lr: 9.08e-04
+2022-05-03 23:26:44,323 INFO [train.py:715] (3/8) Epoch 1, batch 17900, loss[loss=0.1629, simple_loss=0.2208, pruned_loss=0.05255, over 4875.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2485, pruned_loss=0.06088, over 972995.79 frames.], batch size: 16, lr: 9.08e-04
+2022-05-03 23:27:23,561 INFO [train.py:715] (3/8) Epoch 1, batch 17950, loss[loss=0.1749, simple_loss=0.2462, pruned_loss=0.05179, over 4937.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2487, pruned_loss=0.06109, over 973994.08 frames.], batch size: 21, lr: 9.08e-04
+2022-05-03 23:28:02,858 INFO [train.py:715] (3/8) Epoch 1, batch 18000, loss[loss=0.1593, simple_loss=0.2328, pruned_loss=0.04289, over 4828.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2482, pruned_loss=0.06112, over 973830.33 frames.], batch size: 15, lr: 9.07e-04
+2022-05-03 23:28:02,859 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-03 23:28:17,470 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.123, simple_loss=0.21, pruned_loss=0.01804, over 914524.00 frames.
+2022-05-03 23:28:56,680 INFO [train.py:715] (3/8) Epoch 1, batch 18050, loss[loss=0.1607, simple_loss=0.2355, pruned_loss=0.04291, over 4847.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2485, pruned_loss=0.06135, over 973394.75 frames.], batch size: 20, lr: 9.07e-04
+2022-05-03 23:29:37,116 INFO [train.py:715] (3/8) Epoch 1, batch 18100, loss[loss=0.2243, simple_loss=0.2915, pruned_loss=0.07854, over 4805.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2476, pruned_loss=0.06061, over 973314.79 frames.], batch size: 26, lr: 9.06e-04
+2022-05-03 23:30:16,930 INFO [train.py:715] (3/8) Epoch 1, batch 18150, loss[loss=0.1664, simple_loss=0.2336, pruned_loss=0.04964, over 4846.00 frames.], tot_loss[loss=0.1849, simple_loss=0.248, pruned_loss=0.0609, over 972871.48 frames.], batch size: 12, lr: 9.06e-04
+2022-05-03 23:30:55,300 INFO [train.py:715] (3/8) Epoch 1, batch 18200, loss[loss=0.1809, simple_loss=0.2417, pruned_loss=0.06003, over 4957.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2491, pruned_loss=0.06116, over 972448.95 frames.], batch size: 24, lr: 9.05e-04
+2022-05-03 23:31:34,986 INFO [train.py:715] (3/8) Epoch 1, batch 18250, loss[loss=0.186, simple_loss=0.2537, pruned_loss=0.05914, over 4969.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2489, pruned_loss=0.06122, over 972926.44 frames.], batch size: 15, lr: 9.05e-04
+2022-05-03 23:32:14,612 INFO [train.py:715] (3/8) Epoch 1, batch 18300, loss[loss=0.1687, simple_loss=0.2293, pruned_loss=0.05407, over 4932.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2491, pruned_loss=0.06116, over 973296.11 frames.], batch size: 29, lr: 9.05e-04
+2022-05-03 23:32:53,397 INFO [train.py:715] (3/8) Epoch 1, batch 18350, loss[loss=0.1905, simple_loss=0.2544, pruned_loss=0.06332, over 4928.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2495, pruned_loss=0.06134, over 972646.36 frames.], batch size: 21, lr: 9.04e-04
+2022-05-03 23:33:33,132 INFO [train.py:715] (3/8) Epoch 1, batch 18400, loss[loss=0.2154, simple_loss=0.2738, pruned_loss=0.07848, over 4948.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2493, pruned_loss=0.06121, over 972995.35 frames.], batch size: 24, lr: 9.04e-04
+2022-05-03 23:34:13,408 INFO [train.py:715] (3/8) Epoch 1, batch 18450, loss[loss=0.2144, simple_loss=0.2681, pruned_loss=0.08037, over 4882.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2488, pruned_loss=0.06085, over 973095.04 frames.], batch size: 38, lr: 9.03e-04
+2022-05-03 23:34:52,236 INFO [train.py:715] (3/8) Epoch 1, batch 18500, loss[loss=0.1426, simple_loss=0.2182, pruned_loss=0.03355, over 4926.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2487, pruned_loss=0.06117, over 973145.75 frames.], batch size: 21, lr: 9.03e-04
+2022-05-03 23:35:31,270 INFO [train.py:715] (3/8) Epoch 1, batch 18550, loss[loss=0.1755, simple_loss=0.2364, pruned_loss=0.05734, over 4828.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2485, pruned_loss=0.06083, over 973017.11 frames.], batch size: 13, lr: 9.03e-04
+2022-05-03 23:36:11,449 INFO [train.py:715] (3/8) Epoch 1, batch 18600, loss[loss=0.1913, simple_loss=0.2537, pruned_loss=0.06448, over 4812.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2485, pruned_loss=0.06087, over 973002.93 frames.], batch size: 21, lr: 9.02e-04
+2022-05-03 23:36:50,767 INFO [train.py:715] (3/8) Epoch 1, batch 18650, loss[loss=0.1981, simple_loss=0.2678, pruned_loss=0.06418, over 4825.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2491, pruned_loss=0.06115, over 972146.94 frames.], batch size: 26, lr: 9.02e-04
+2022-05-03 23:37:29,514 INFO [train.py:715] (3/8) Epoch 1, batch 18700, loss[loss=0.2044, simple_loss=0.2634, pruned_loss=0.07265, over 4805.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2481, pruned_loss=0.0602, over 971295.42 frames.], batch size: 25, lr: 9.01e-04
+2022-05-03 23:38:08,759 INFO [train.py:715] (3/8) Epoch 1, batch 18750, loss[loss=0.1688, simple_loss=0.2315, pruned_loss=0.0531, over 4690.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2487, pruned_loss=0.06037, over 970788.83 frames.], batch size: 15, lr: 9.01e-04
+2022-05-03 23:38:48,686 INFO [train.py:715] (3/8) Epoch 1, batch 18800, loss[loss=0.1802, simple_loss=0.2453, pruned_loss=0.05751, over 4944.00 frames.], tot_loss[loss=0.1841, simple_loss=0.248, pruned_loss=0.06012, over 971071.39 frames.], batch size: 29, lr: 9.00e-04
+2022-05-03 23:39:27,388 INFO [train.py:715] (3/8) Epoch 1, batch 18850, loss[loss=0.2058, simple_loss=0.2545, pruned_loss=0.07855, over 4778.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2482, pruned_loss=0.06079, over 971639.05 frames.], batch size: 17, lr: 9.00e-04
+2022-05-03 23:40:06,872 INFO [train.py:715] (3/8) Epoch 1, batch 18900, loss[loss=0.1515, simple_loss=0.2206, pruned_loss=0.04119, over 4933.00 frames.], tot_loss[loss=0.185, simple_loss=0.2481, pruned_loss=0.06091, over 971968.45 frames.], batch size: 21, lr: 9.00e-04
+2022-05-03 23:40:46,607 INFO [train.py:715] (3/8) Epoch 1, batch 18950, loss[loss=0.1841, simple_loss=0.2522, pruned_loss=0.05801, over 4969.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2473, pruned_loss=0.06028, over 972150.98 frames.], batch size: 15, lr: 8.99e-04
+2022-05-03 23:41:25,993 INFO [train.py:715] (3/8) Epoch 1, batch 19000, loss[loss=0.1706, simple_loss=0.231, pruned_loss=0.05503, over 4829.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2464, pruned_loss=0.05923, over 972132.09 frames.], batch size: 13, lr: 8.99e-04
+2022-05-03 23:42:05,674 INFO [train.py:715] (3/8) Epoch 1, batch 19050, loss[loss=0.2293, simple_loss=0.2818, pruned_loss=0.08836, over 4923.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2475, pruned_loss=0.05971, over 972574.82 frames.], batch size: 18, lr: 8.98e-04
+2022-05-03 23:42:44,847 INFO [train.py:715] (3/8) Epoch 1, batch 19100, loss[loss=0.1763, simple_loss=0.2333, pruned_loss=0.05969, over 4854.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2473, pruned_loss=0.05946, over 972202.17 frames.], batch size: 13, lr: 8.98e-04
+2022-05-03 23:43:24,772 INFO [train.py:715] (3/8) Epoch 1, batch 19150, loss[loss=0.1599, simple_loss=0.2263, pruned_loss=0.04676, over 4980.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2483, pruned_loss=0.0604, over 972712.44 frames.], batch size: 33, lr: 8.98e-04
+2022-05-03 23:44:03,412 INFO [train.py:715] (3/8) Epoch 1, batch 19200, loss[loss=0.1785, simple_loss=0.2448, pruned_loss=0.05613, over 4921.00 frames.], tot_loss[loss=0.185, simple_loss=0.2485, pruned_loss=0.06078, over 972880.26 frames.], batch size: 18, lr: 8.97e-04
+2022-05-03 23:44:42,697 INFO [train.py:715] (3/8) Epoch 1, batch 19250, loss[loss=0.1811, simple_loss=0.245, pruned_loss=0.05858, over 4833.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2474, pruned_loss=0.05983, over 973539.82 frames.], batch size: 15, lr: 8.97e-04
+2022-05-03 23:45:23,327 INFO [train.py:715] (3/8) Epoch 1, batch 19300, loss[loss=0.2271, simple_loss=0.2907, pruned_loss=0.08176, over 4781.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2479, pruned_loss=0.05977, over 972945.04 frames.], batch size: 18, lr: 8.96e-04
+2022-05-03 23:46:02,785 INFO [train.py:715] (3/8) Epoch 1, batch 19350, loss[loss=0.182, simple_loss=0.2407, pruned_loss=0.06164, over 4909.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2474, pruned_loss=0.05987, over 973104.13 frames.], batch size: 18, lr: 8.96e-04
+2022-05-03 23:46:41,169 INFO [train.py:715] (3/8) Epoch 1, batch 19400, loss[loss=0.1915, simple_loss=0.2435, pruned_loss=0.06975, over 4876.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2468, pruned_loss=0.05924, over 972077.43 frames.], batch size: 22, lr: 8.95e-04
+2022-05-03 23:47:20,593 INFO [train.py:715] (3/8) Epoch 1, batch 19450, loss[loss=0.1382, simple_loss=0.2008, pruned_loss=0.03779, over 4920.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2466, pruned_loss=0.05932, over 972205.50 frames.], batch size: 18, lr: 8.95e-04
+2022-05-03 23:48:00,484 INFO [train.py:715] (3/8) Epoch 1, batch 19500, loss[loss=0.1611, simple_loss=0.2269, pruned_loss=0.04766, over 4815.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2468, pruned_loss=0.0595, over 972419.21 frames.], batch size: 27, lr: 8.95e-04
+2022-05-03 23:48:39,200 INFO [train.py:715] (3/8) Epoch 1, batch 19550, loss[loss=0.1563, simple_loss=0.229, pruned_loss=0.0418, over 4975.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2467, pruned_loss=0.05939, over 973062.29 frames.], batch size: 24, lr: 8.94e-04
+2022-05-03 23:49:18,325 INFO [train.py:715] (3/8) Epoch 1, batch 19600, loss[loss=0.1786, simple_loss=0.2398, pruned_loss=0.05871, over 4864.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2462, pruned_loss=0.05932, over 971976.16 frames.], batch size: 30, lr: 8.94e-04
+2022-05-03 23:49:58,544 INFO [train.py:715] (3/8) Epoch 1, batch 19650, loss[loss=0.1513, simple_loss=0.2189, pruned_loss=0.04188, over 4794.00 frames.], tot_loss[loss=0.183, simple_loss=0.2469, pruned_loss=0.05955, over 972169.40 frames.], batch size: 24, lr: 8.93e-04
+2022-05-03 23:50:37,444 INFO [train.py:715] (3/8) Epoch 1, batch 19700, loss[loss=0.1576, simple_loss=0.2244, pruned_loss=0.04546, over 4889.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2475, pruned_loss=0.05992, over 972749.92 frames.], batch size: 19, lr: 8.93e-04
+2022-05-03 23:51:16,596 INFO [train.py:715] (3/8) Epoch 1, batch 19750, loss[loss=0.1498, simple_loss=0.2195, pruned_loss=0.04005, over 4806.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2478, pruned_loss=0.06029, over 972259.11 frames.], batch size: 25, lr: 8.93e-04
+2022-05-03 23:51:56,237 INFO [train.py:715] (3/8) Epoch 1, batch 19800, loss[loss=0.1815, simple_loss=0.2445, pruned_loss=0.05924, over 4899.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2491, pruned_loss=0.06113, over 972471.31 frames.], batch size: 17, lr: 8.92e-04
+2022-05-03 23:52:36,505 INFO [train.py:715] (3/8) Epoch 1, batch 19850, loss[loss=0.2134, simple_loss=0.2724, pruned_loss=0.07724, over 4648.00 frames.], tot_loss[loss=0.186, simple_loss=0.2493, pruned_loss=0.06134, over 971382.26 frames.], batch size: 13, lr: 8.92e-04
+2022-05-03 23:53:15,889 INFO [train.py:715] (3/8) Epoch 1, batch 19900, loss[loss=0.1667, simple_loss=0.2311, pruned_loss=0.05111, over 4809.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2485, pruned_loss=0.06123, over 971863.84 frames.], batch size: 18, lr: 8.91e-04
+2022-05-03 23:53:54,986 INFO [train.py:715] (3/8) Epoch 1, batch 19950, loss[loss=0.1862, simple_loss=0.2535, pruned_loss=0.05943, over 4833.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2486, pruned_loss=0.06115, over 972022.32 frames.], batch size: 30, lr: 8.91e-04
+2022-05-03 23:54:35,248 INFO [train.py:715] (3/8) Epoch 1, batch 20000, loss[loss=0.1914, simple_loss=0.2613, pruned_loss=0.06068, over 4818.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2478, pruned_loss=0.06051, over 972363.59 frames.], batch size: 25, lr: 8.91e-04
+2022-05-03 23:55:14,863 INFO [train.py:715] (3/8) Epoch 1, batch 20050, loss[loss=0.1897, simple_loss=0.2469, pruned_loss=0.06625, over 4776.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2477, pruned_loss=0.05989, over 972609.71 frames.], batch size: 17, lr: 8.90e-04
+2022-05-03 23:55:54,263 INFO [train.py:715] (3/8) Epoch 1, batch 20100, loss[loss=0.2399, simple_loss=0.2849, pruned_loss=0.09745, over 4835.00 frames.], tot_loss[loss=0.184, simple_loss=0.2479, pruned_loss=0.06008, over 972439.62 frames.], batch size: 15, lr: 8.90e-04
+2022-05-03 23:56:34,282 INFO [train.py:715] (3/8) Epoch 1, batch 20150, loss[loss=0.1714, simple_loss=0.2423, pruned_loss=0.05025, over 4955.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2478, pruned_loss=0.05947, over 972899.01 frames.], batch size: 21, lr: 8.89e-04
+2022-05-03 23:57:15,155 INFO [train.py:715] (3/8) Epoch 1, batch 20200, loss[loss=0.2229, simple_loss=0.2801, pruned_loss=0.08289, over 4893.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2479, pruned_loss=0.05944, over 973487.01 frames.], batch size: 19, lr: 8.89e-04
+2022-05-03 23:57:53,970 INFO [train.py:715] (3/8) Epoch 1, batch 20250, loss[loss=0.189, simple_loss=0.244, pruned_loss=0.067, over 4832.00 frames.], tot_loss[loss=0.184, simple_loss=0.2481, pruned_loss=0.05992, over 973351.80 frames.], batch size: 30, lr: 8.89e-04
+2022-05-03 23:58:33,269 INFO [train.py:715] (3/8) Epoch 1, batch 20300, loss[loss=0.2178, simple_loss=0.2712, pruned_loss=0.08217, over 4836.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2481, pruned_loss=0.06018, over 972515.20 frames.], batch size: 15, lr: 8.88e-04
+2022-05-03 23:59:13,198 INFO [train.py:715] (3/8) Epoch 1, batch 20350, loss[loss=0.1992, simple_loss=0.2613, pruned_loss=0.06852, over 4958.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2485, pruned_loss=0.06047, over 972445.93 frames.], batch size: 24, lr: 8.88e-04
+2022-05-03 23:59:51,741 INFO [train.py:715] (3/8) Epoch 1, batch 20400, loss[loss=0.1731, simple_loss=0.2275, pruned_loss=0.05937, over 4817.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2481, pruned_loss=0.06016, over 972112.44 frames.], batch size: 13, lr: 8.87e-04
+2022-05-04 00:00:31,296 INFO [train.py:715] (3/8) Epoch 1, batch 20450, loss[loss=0.1878, simple_loss=0.243, pruned_loss=0.06631, over 4634.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2477, pruned_loss=0.05977, over 972070.98 frames.], batch size: 13, lr: 8.87e-04
+2022-05-04 00:01:10,343 INFO [train.py:715] (3/8) Epoch 1, batch 20500, loss[loss=0.1616, simple_loss=0.2389, pruned_loss=0.04218, over 4785.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2477, pruned_loss=0.05962, over 971776.14 frames.], batch size: 17, lr: 8.87e-04
+2022-05-04 00:01:50,041 INFO [train.py:715] (3/8) Epoch 1, batch 20550, loss[loss=0.1748, simple_loss=0.2546, pruned_loss=0.04755, over 4885.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2477, pruned_loss=0.05961, over 972590.91 frames.], batch size: 19, lr: 8.86e-04
+2022-05-04 00:02:28,910 INFO [train.py:715] (3/8) Epoch 1, batch 20600, loss[loss=0.2262, simple_loss=0.2806, pruned_loss=0.08589, over 4814.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2475, pruned_loss=0.05913, over 972741.12 frames.], batch size: 26, lr: 8.86e-04
+2022-05-04 00:03:08,450 INFO [train.py:715] (3/8) Epoch 1, batch 20650, loss[loss=0.1635, simple_loss=0.2315, pruned_loss=0.0478, over 4742.00 frames.], tot_loss[loss=0.183, simple_loss=0.2475, pruned_loss=0.05931, over 972463.25 frames.], batch size: 16, lr: 8.85e-04
+2022-05-04 00:03:48,939 INFO [train.py:715] (3/8) Epoch 1, batch 20700, loss[loss=0.1789, simple_loss=0.2552, pruned_loss=0.05128, over 4935.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2464, pruned_loss=0.05889, over 972002.72 frames.], batch size: 23, lr: 8.85e-04
+2022-05-04 00:04:28,577 INFO [train.py:715] (3/8) Epoch 1, batch 20750, loss[loss=0.1819, simple_loss=0.2525, pruned_loss=0.05568, over 4911.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2458, pruned_loss=0.05852, over 971835.65 frames.], batch size: 18, lr: 8.85e-04
+2022-05-04 00:05:07,876 INFO [train.py:715] (3/8) Epoch 1, batch 20800, loss[loss=0.2172, simple_loss=0.2601, pruned_loss=0.0872, over 4903.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2453, pruned_loss=0.05829, over 972209.38 frames.], batch size: 16, lr: 8.84e-04
+2022-05-04 00:05:47,728 INFO [train.py:715] (3/8) Epoch 1, batch 20850, loss[loss=0.1879, simple_loss=0.2514, pruned_loss=0.06224, over 4886.00 frames.], tot_loss[loss=0.183, simple_loss=0.2468, pruned_loss=0.05962, over 972033.58 frames.], batch size: 39, lr: 8.84e-04
+2022-05-04 00:06:27,483 INFO [train.py:715] (3/8) Epoch 1, batch 20900, loss[loss=0.168, simple_loss=0.23, pruned_loss=0.05298, over 4934.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2466, pruned_loss=0.05939, over 972197.66 frames.], batch size: 23, lr: 8.83e-04
+2022-05-04 00:07:06,273 INFO [train.py:715] (3/8) Epoch 1, batch 20950, loss[loss=0.1777, simple_loss=0.2409, pruned_loss=0.05729, over 4776.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2468, pruned_loss=0.05925, over 971667.48 frames.], batch size: 12, lr: 8.83e-04
+2022-05-04 00:07:45,661 INFO [train.py:715] (3/8) Epoch 1, batch 21000, loss[loss=0.1903, simple_loss=0.2424, pruned_loss=0.06914, over 4690.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2466, pruned_loss=0.05952, over 971207.16 frames.], batch size: 15, lr: 8.83e-04
+2022-05-04 00:07:45,661 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 00:08:00,761 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.1226, simple_loss=0.2094, pruned_loss=0.01784, over 914524.00 frames.
+2022-05-04 00:08:40,111 INFO [train.py:715] (3/8) Epoch 1, batch 21050, loss[loss=0.1645, simple_loss=0.2413, pruned_loss=0.04383, over 4913.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2471, pruned_loss=0.05984, over 972078.87 frames.], batch size: 29, lr: 8.82e-04
+2022-05-04 00:09:19,947 INFO [train.py:715] (3/8) Epoch 1, batch 21100, loss[loss=0.1952, simple_loss=0.2567, pruned_loss=0.06683, over 4820.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2473, pruned_loss=0.06005, over 971843.81 frames.], batch size: 26, lr: 8.82e-04
+2022-05-04 00:09:58,320 INFO [train.py:715] (3/8) Epoch 1, batch 21150, loss[loss=0.2049, simple_loss=0.255, pruned_loss=0.07734, over 4771.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2481, pruned_loss=0.06056, over 971777.82 frames.], batch size: 18, lr: 8.81e-04
+2022-05-04 00:10:40,730 INFO [train.py:715] (3/8) Epoch 1, batch 21200, loss[loss=0.1713, simple_loss=0.251, pruned_loss=0.04579, over 4784.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2484, pruned_loss=0.06052, over 972089.51 frames.], batch size: 17, lr: 8.81e-04
+2022-05-04 00:11:20,088 INFO [train.py:715] (3/8) Epoch 1, batch 21250, loss[loss=0.1782, simple_loss=0.2398, pruned_loss=0.05832, over 4765.00 frames.], tot_loss[loss=0.184, simple_loss=0.2478, pruned_loss=0.06005, over 971448.43 frames.], batch size: 19, lr: 8.81e-04
+2022-05-04 00:11:59,258 INFO [train.py:715] (3/8) Epoch 1, batch 21300, loss[loss=0.1691, simple_loss=0.2463, pruned_loss=0.04593, over 4810.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2474, pruned_loss=0.06001, over 971675.44 frames.], batch size: 25, lr: 8.80e-04
+2022-05-04 00:12:38,145 INFO [train.py:715] (3/8) Epoch 1, batch 21350, loss[loss=0.1829, simple_loss=0.2361, pruned_loss=0.06488, over 4639.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2469, pruned_loss=0.05962, over 971745.84 frames.], batch size: 13, lr: 8.80e-04
+2022-05-04 00:13:17,800 INFO [train.py:715] (3/8) Epoch 1, batch 21400, loss[loss=0.1551, simple_loss=0.2318, pruned_loss=0.03923, over 4966.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2474, pruned_loss=0.06012, over 971443.10 frames.], batch size: 24, lr: 8.80e-04
+2022-05-04 00:13:57,966 INFO [train.py:715] (3/8) Epoch 1, batch 21450, loss[loss=0.1583, simple_loss=0.233, pruned_loss=0.04176, over 4700.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2478, pruned_loss=0.06043, over 971285.99 frames.], batch size: 15, lr: 8.79e-04
+2022-05-04 00:14:36,215 INFO [train.py:715] (3/8) Epoch 1, batch 21500, loss[loss=0.1803, simple_loss=0.2286, pruned_loss=0.06607, over 4853.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2482, pruned_loss=0.06035, over 972088.46 frames.], batch size: 15, lr: 8.79e-04
+2022-05-04 00:15:15,309 INFO [train.py:715] (3/8) Epoch 1, batch 21550, loss[loss=0.21, simple_loss=0.2699, pruned_loss=0.0751, over 4961.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2475, pruned_loss=0.05997, over 972297.13 frames.], batch size: 39, lr: 8.78e-04
+2022-05-04 00:15:54,610 INFO [train.py:715] (3/8) Epoch 1, batch 21600, loss[loss=0.1237, simple_loss=0.1851, pruned_loss=0.03116, over 4852.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2461, pruned_loss=0.05868, over 972706.36 frames.], batch size: 12, lr: 8.78e-04
+2022-05-04 00:16:33,915 INFO [train.py:715] (3/8) Epoch 1, batch 21650, loss[loss=0.1798, simple_loss=0.2385, pruned_loss=0.06055, over 4845.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2466, pruned_loss=0.05875, over 972310.08 frames.], batch size: 15, lr: 8.78e-04
+2022-05-04 00:17:12,477 INFO [train.py:715] (3/8) Epoch 1, batch 21700, loss[loss=0.1921, simple_loss=0.2508, pruned_loss=0.06667, over 4815.00 frames.], tot_loss[loss=0.182, simple_loss=0.2464, pruned_loss=0.05875, over 971925.77 frames.], batch size: 26, lr: 8.77e-04
+2022-05-04 00:17:52,133 INFO [train.py:715] (3/8) Epoch 1, batch 21750, loss[loss=0.1736, simple_loss=0.2472, pruned_loss=0.04997, over 4974.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2474, pruned_loss=0.05972, over 971610.04 frames.], batch size: 24, lr: 8.77e-04
+2022-05-04 00:18:31,689 INFO [train.py:715] (3/8) Epoch 1, batch 21800, loss[loss=0.1786, simple_loss=0.252, pruned_loss=0.05264, over 4695.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2478, pruned_loss=0.05975, over 971785.45 frames.], batch size: 15, lr: 8.76e-04
+2022-05-04 00:19:10,442 INFO [train.py:715] (3/8) Epoch 1, batch 21850, loss[loss=0.1777, simple_loss=0.2337, pruned_loss=0.06083, over 4871.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2479, pruned_loss=0.05974, over 971913.09 frames.], batch size: 32, lr: 8.76e-04
+2022-05-04 00:19:50,596 INFO [train.py:715] (3/8) Epoch 1, batch 21900, loss[loss=0.1628, simple_loss=0.2281, pruned_loss=0.04874, over 4853.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2473, pruned_loss=0.05981, over 971343.15 frames.], batch size: 13, lr: 8.76e-04
+2022-05-04 00:20:30,150 INFO [train.py:715] (3/8) Epoch 1, batch 21950, loss[loss=0.1533, simple_loss=0.2191, pruned_loss=0.04374, over 4975.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2474, pruned_loss=0.05987, over 970829.88 frames.], batch size: 14, lr: 8.75e-04
+2022-05-04 00:21:09,937 INFO [train.py:715] (3/8) Epoch 1, batch 22000, loss[loss=0.1683, simple_loss=0.2312, pruned_loss=0.05267, over 4986.00 frames.], tot_loss[loss=0.1832, simple_loss=0.247, pruned_loss=0.05968, over 971103.64 frames.], batch size: 28, lr: 8.75e-04
+2022-05-04 00:21:48,902 INFO [train.py:715] (3/8) Epoch 1, batch 22050, loss[loss=0.1787, simple_loss=0.257, pruned_loss=0.05027, over 4872.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2471, pruned_loss=0.05994, over 971439.21 frames.], batch size: 20, lr: 8.75e-04
+2022-05-04 00:22:28,892 INFO [train.py:715] (3/8) Epoch 1, batch 22100, loss[loss=0.1795, simple_loss=0.2473, pruned_loss=0.05585, over 4939.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2462, pruned_loss=0.05935, over 972371.81 frames.], batch size: 23, lr: 8.74e-04
+2022-05-04 00:23:08,222 INFO [train.py:715] (3/8) Epoch 1, batch 22150, loss[loss=0.1523, simple_loss=0.2215, pruned_loss=0.04149, over 4936.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2457, pruned_loss=0.05897, over 972678.86 frames.], batch size: 23, lr: 8.74e-04
+2022-05-04 00:23:46,647 INFO [train.py:715] (3/8) Epoch 1, batch 22200, loss[loss=0.1664, simple_loss=0.2309, pruned_loss=0.05091, over 4834.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2456, pruned_loss=0.05855, over 972437.06 frames.], batch size: 15, lr: 8.73e-04
+2022-05-04 00:24:25,885 INFO [train.py:715] (3/8) Epoch 1, batch 22250, loss[loss=0.1777, simple_loss=0.2462, pruned_loss=0.05457, over 4865.00 frames.], tot_loss[loss=0.182, simple_loss=0.2461, pruned_loss=0.05894, over 972203.54 frames.], batch size: 32, lr: 8.73e-04
+2022-05-04 00:25:05,562 INFO [train.py:715] (3/8) Epoch 1, batch 22300, loss[loss=0.1828, simple_loss=0.2535, pruned_loss=0.05608, over 4969.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2459, pruned_loss=0.05879, over 972045.01 frames.], batch size: 15, lr: 8.73e-04
+2022-05-04 00:25:45,333 INFO [train.py:715] (3/8) Epoch 1, batch 22350, loss[loss=0.1841, simple_loss=0.2406, pruned_loss=0.06378, over 4872.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2458, pruned_loss=0.05858, over 971350.08 frames.], batch size: 20, lr: 8.72e-04
+2022-05-04 00:26:24,287 INFO [train.py:715] (3/8) Epoch 1, batch 22400, loss[loss=0.1606, simple_loss=0.2176, pruned_loss=0.05181, over 4786.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2442, pruned_loss=0.058, over 971224.95 frames.], batch size: 13, lr: 8.72e-04
+2022-05-04 00:27:04,012 INFO [train.py:715] (3/8) Epoch 1, batch 22450, loss[loss=0.2051, simple_loss=0.2569, pruned_loss=0.07661, over 4943.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2433, pruned_loss=0.05758, over 971852.86 frames.], batch size: 35, lr: 8.72e-04
+2022-05-04 00:27:43,648 INFO [train.py:715] (3/8) Epoch 1, batch 22500, loss[loss=0.1887, simple_loss=0.2412, pruned_loss=0.06813, over 4876.00 frames.], tot_loss[loss=0.18, simple_loss=0.2436, pruned_loss=0.05821, over 971811.79 frames.], batch size: 16, lr: 8.71e-04
+2022-05-04 00:28:22,145 INFO [train.py:715] (3/8) Epoch 1, batch 22550, loss[loss=0.2208, simple_loss=0.2861, pruned_loss=0.07776, over 4911.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2437, pruned_loss=0.05842, over 972327.82 frames.], batch size: 18, lr: 8.71e-04
+2022-05-04 00:29:02,211 INFO [train.py:715] (3/8) Epoch 1, batch 22600, loss[loss=0.2628, simple_loss=0.2895, pruned_loss=0.118, over 4826.00 frames.], tot_loss[loss=0.181, simple_loss=0.2447, pruned_loss=0.05867, over 972262.80 frames.], batch size: 15, lr: 8.70e-04
+2022-05-04 00:29:42,706 INFO [train.py:715] (3/8) Epoch 1, batch 22650, loss[loss=0.2089, simple_loss=0.2698, pruned_loss=0.07401, over 4753.00 frames.], tot_loss[loss=0.1824, simple_loss=0.246, pruned_loss=0.05934, over 972415.88 frames.], batch size: 12, lr: 8.70e-04
+2022-05-04 00:30:22,585 INFO [train.py:715] (3/8) Epoch 1, batch 22700, loss[loss=0.2288, simple_loss=0.2813, pruned_loss=0.08817, over 4982.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2462, pruned_loss=0.05904, over 971843.55 frames.], batch size: 35, lr: 8.70e-04
+2022-05-04 00:31:00,977 INFO [train.py:715] (3/8) Epoch 1, batch 22750, loss[loss=0.1883, simple_loss=0.2502, pruned_loss=0.06318, over 4804.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2465, pruned_loss=0.05919, over 971405.69 frames.], batch size: 21, lr: 8.69e-04
+2022-05-04 00:31:41,164 INFO [train.py:715] (3/8) Epoch 1, batch 22800, loss[loss=0.1456, simple_loss=0.2123, pruned_loss=0.03946, over 4772.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2466, pruned_loss=0.05891, over 971895.34 frames.], batch size: 14, lr: 8.69e-04
+2022-05-04 00:32:20,887 INFO [train.py:715] (3/8) Epoch 1, batch 22850, loss[loss=0.146, simple_loss=0.2327, pruned_loss=0.0297, over 4930.00 frames.], tot_loss[loss=0.1825, simple_loss=0.247, pruned_loss=0.059, over 971672.30 frames.], batch size: 18, lr: 8.68e-04
+2022-05-04 00:32:59,722 INFO [train.py:715] (3/8) Epoch 1, batch 22900, loss[loss=0.1804, simple_loss=0.2487, pruned_loss=0.05599, over 4863.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2478, pruned_loss=0.05999, over 972980.34 frames.], batch size: 20, lr: 8.68e-04
+2022-05-04 00:33:39,273 INFO [train.py:715] (3/8) Epoch 1, batch 22950, loss[loss=0.1732, simple_loss=0.2438, pruned_loss=0.05132, over 4702.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2483, pruned_loss=0.06001, over 973012.92 frames.], batch size: 15, lr: 8.68e-04
+2022-05-04 00:34:19,075 INFO [train.py:715] (3/8) Epoch 1, batch 23000, loss[loss=0.2156, simple_loss=0.2691, pruned_loss=0.08104, over 4896.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2479, pruned_loss=0.05985, over 972398.50 frames.], batch size: 39, lr: 8.67e-04
+2022-05-04 00:34:57,981 INFO [train.py:715] (3/8) Epoch 1, batch 23050, loss[loss=0.1869, simple_loss=0.2538, pruned_loss=0.06002, over 4951.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2485, pruned_loss=0.0601, over 972835.02 frames.], batch size: 29, lr: 8.67e-04
+2022-05-04 00:35:37,123 INFO [train.py:715] (3/8) Epoch 1, batch 23100, loss[loss=0.1667, simple_loss=0.2367, pruned_loss=0.04834, over 4798.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2477, pruned_loss=0.05958, over 972377.60 frames.], batch size: 21, lr: 8.67e-04
+2022-05-04 00:36:16,857 INFO [train.py:715] (3/8) Epoch 1, batch 23150, loss[loss=0.1827, simple_loss=0.245, pruned_loss=0.06023, over 4825.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2478, pruned_loss=0.05918, over 971441.63 frames.], batch size: 30, lr: 8.66e-04
+2022-05-04 00:36:56,381 INFO [train.py:715] (3/8) Epoch 1, batch 23200, loss[loss=0.205, simple_loss=0.2585, pruned_loss=0.07572, over 4930.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2482, pruned_loss=0.05982, over 971761.28 frames.], batch size: 23, lr: 8.66e-04
+2022-05-04 00:37:34,616 INFO [train.py:715] (3/8) Epoch 1, batch 23250, loss[loss=0.2207, simple_loss=0.2759, pruned_loss=0.08281, over 4872.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2471, pruned_loss=0.05885, over 972360.18 frames.], batch size: 16, lr: 8.66e-04
+2022-05-04 00:38:14,195 INFO [train.py:715] (3/8) Epoch 1, batch 23300, loss[loss=0.1655, simple_loss=0.2348, pruned_loss=0.04808, over 4966.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2481, pruned_loss=0.05978, over 971738.41 frames.], batch size: 21, lr: 8.65e-04
+2022-05-04 00:38:53,771 INFO [train.py:715] (3/8) Epoch 1, batch 23350, loss[loss=0.164, simple_loss=0.2378, pruned_loss=0.0451, over 4981.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2472, pruned_loss=0.05894, over 972674.73 frames.], batch size: 14, lr: 8.65e-04
+2022-05-04 00:39:32,067 INFO [train.py:715] (3/8) Epoch 1, batch 23400, loss[loss=0.1576, simple_loss=0.2341, pruned_loss=0.04053, over 4905.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2481, pruned_loss=0.05968, over 972268.90 frames.], batch size: 19, lr: 8.64e-04
+2022-05-04 00:40:11,305 INFO [train.py:715] (3/8) Epoch 1, batch 23450, loss[loss=0.1444, simple_loss=0.2046, pruned_loss=0.04212, over 4800.00 frames.], tot_loss[loss=0.1836, simple_loss=0.248, pruned_loss=0.05959, over 972359.10 frames.], batch size: 12, lr: 8.64e-04
+2022-05-04 00:40:50,692 INFO [train.py:715] (3/8) Epoch 1, batch 23500, loss[loss=0.1742, simple_loss=0.2442, pruned_loss=0.05208, over 4965.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2475, pruned_loss=0.05966, over 972873.09 frames.], batch size: 35, lr: 8.64e-04
+2022-05-04 00:41:29,530 INFO [train.py:715] (3/8) Epoch 1, batch 23550, loss[loss=0.1918, simple_loss=0.2604, pruned_loss=0.06162, over 4798.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2461, pruned_loss=0.05854, over 972362.81 frames.], batch size: 24, lr: 8.63e-04
+2022-05-04 00:42:07,726 INFO [train.py:715] (3/8) Epoch 1, batch 23600, loss[loss=0.2662, simple_loss=0.3122, pruned_loss=0.1101, over 4739.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2467, pruned_loss=0.05886, over 972493.86 frames.], batch size: 16, lr: 8.63e-04
+2022-05-04 00:42:47,234 INFO [train.py:715] (3/8) Epoch 1, batch 23650, loss[loss=0.1619, simple_loss=0.2237, pruned_loss=0.05006, over 4805.00 frames.], tot_loss[loss=0.181, simple_loss=0.2453, pruned_loss=0.05838, over 972184.02 frames.], batch size: 13, lr: 8.63e-04
+2022-05-04 00:43:26,749 INFO [train.py:715] (3/8) Epoch 1, batch 23700, loss[loss=0.1995, simple_loss=0.2667, pruned_loss=0.06614, over 4923.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2459, pruned_loss=0.05918, over 972461.86 frames.], batch size: 19, lr: 8.62e-04
+2022-05-04 00:44:05,089 INFO [train.py:715] (3/8) Epoch 1, batch 23750, loss[loss=0.1838, simple_loss=0.2593, pruned_loss=0.05413, over 4894.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2455, pruned_loss=0.05895, over 972226.29 frames.], batch size: 22, lr: 8.62e-04
+2022-05-04 00:44:44,142 INFO [train.py:715] (3/8) Epoch 1, batch 23800, loss[loss=0.1599, simple_loss=0.2182, pruned_loss=0.05075, over 4794.00 frames.], tot_loss[loss=0.1812, simple_loss=0.245, pruned_loss=0.05868, over 972415.98 frames.], batch size: 12, lr: 8.61e-04
+2022-05-04 00:45:24,228 INFO [train.py:715] (3/8) Epoch 1, batch 23850, loss[loss=0.1584, simple_loss=0.2242, pruned_loss=0.04628, over 4841.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2456, pruned_loss=0.059, over 971638.26 frames.], batch size: 13, lr: 8.61e-04
+2022-05-04 00:46:03,791 INFO [train.py:715] (3/8) Epoch 1, batch 23900, loss[loss=0.2302, simple_loss=0.2952, pruned_loss=0.08258, over 4696.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2477, pruned_loss=0.05988, over 971041.12 frames.], batch size: 15, lr: 8.61e-04
+2022-05-04 00:46:42,609 INFO [train.py:715] (3/8) Epoch 1, batch 23950, loss[loss=0.1667, simple_loss=0.2378, pruned_loss=0.04774, over 4970.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2473, pruned_loss=0.05977, over 971157.96 frames.], batch size: 24, lr: 8.60e-04
+2022-05-04 00:47:22,329 INFO [train.py:715] (3/8) Epoch 1, batch 24000, loss[loss=0.1915, simple_loss=0.2518, pruned_loss=0.06559, over 4761.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2469, pruned_loss=0.05969, over 971079.40 frames.], batch size: 16, lr: 8.60e-04
+2022-05-04 00:47:22,330 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 00:47:34,529 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.1217, simple_loss=0.2087, pruned_loss=0.01736, over 914524.00 frames.
+2022-05-04 00:48:14,355 INFO [train.py:715] (3/8) Epoch 1, batch 24050, loss[loss=0.1607, simple_loss=0.2297, pruned_loss=0.04582, over 4892.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2469, pruned_loss=0.05962, over 971522.63 frames.], batch size: 22, lr: 8.60e-04
+2022-05-04 00:48:53,684 INFO [train.py:715] (3/8) Epoch 1, batch 24100, loss[loss=0.1998, simple_loss=0.2643, pruned_loss=0.06766, over 4844.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2468, pruned_loss=0.05991, over 971106.17 frames.], batch size: 20, lr: 8.59e-04
+2022-05-04 00:49:32,277 INFO [train.py:715] (3/8) Epoch 1, batch 24150, loss[loss=0.185, simple_loss=0.2416, pruned_loss=0.06419, over 4991.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2452, pruned_loss=0.05909, over 970764.58 frames.], batch size: 16, lr: 8.59e-04
+2022-05-04 00:50:11,571 INFO [train.py:715] (3/8) Epoch 1, batch 24200, loss[loss=0.1434, simple_loss=0.2069, pruned_loss=0.03996, over 4985.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2458, pruned_loss=0.0595, over 971443.76 frames.], batch size: 25, lr: 8.59e-04
+2022-05-04 00:50:52,250 INFO [train.py:715] (3/8) Epoch 1, batch 24250, loss[loss=0.2053, simple_loss=0.254, pruned_loss=0.07833, over 4901.00 frames.], tot_loss[loss=0.182, simple_loss=0.2456, pruned_loss=0.05925, over 971579.21 frames.], batch size: 19, lr: 8.58e-04
+2022-05-04 00:51:31,677 INFO [train.py:715] (3/8) Epoch 1, batch 24300, loss[loss=0.1788, simple_loss=0.2398, pruned_loss=0.05889, over 4698.00 frames.], tot_loss[loss=0.182, simple_loss=0.2455, pruned_loss=0.05927, over 971574.96 frames.], batch size: 15, lr: 8.58e-04
+2022-05-04 00:52:11,123 INFO [train.py:715] (3/8) Epoch 1, batch 24350, loss[loss=0.1812, simple_loss=0.248, pruned_loss=0.05727, over 4823.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2453, pruned_loss=0.05911, over 971310.65 frames.], batch size: 13, lr: 8.57e-04
+2022-05-04 00:52:51,497 INFO [train.py:715] (3/8) Epoch 1, batch 24400, loss[loss=0.2001, simple_loss=0.2573, pruned_loss=0.07145, over 4927.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2454, pruned_loss=0.05898, over 971169.27 frames.], batch size: 29, lr: 8.57e-04
+2022-05-04 00:53:30,578 INFO [train.py:715] (3/8) Epoch 1, batch 24450, loss[loss=0.1736, simple_loss=0.2318, pruned_loss=0.05774, over 4839.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2452, pruned_loss=0.05854, over 971321.48 frames.], batch size: 15, lr: 8.57e-04
+2022-05-04 00:54:09,300 INFO [train.py:715] (3/8) Epoch 1, batch 24500, loss[loss=0.1692, simple_loss=0.2473, pruned_loss=0.04557, over 4944.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2455, pruned_loss=0.05848, over 971458.93 frames.], batch size: 21, lr: 8.56e-04
+2022-05-04 00:54:48,963 INFO [train.py:715] (3/8) Epoch 1, batch 24550, loss[loss=0.2128, simple_loss=0.2791, pruned_loss=0.07324, over 4904.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2465, pruned_loss=0.05936, over 971717.86 frames.], batch size: 17, lr: 8.56e-04
+2022-05-04 00:55:29,263 INFO [train.py:715] (3/8) Epoch 1, batch 24600, loss[loss=0.1932, simple_loss=0.2593, pruned_loss=0.06358, over 4858.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2462, pruned_loss=0.05921, over 971555.18 frames.], batch size: 30, lr: 8.56e-04
+2022-05-04 00:56:08,132 INFO [train.py:715] (3/8) Epoch 1, batch 24650, loss[loss=0.1867, simple_loss=0.2583, pruned_loss=0.05756, over 4935.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2454, pruned_loss=0.05866, over 971167.42 frames.], batch size: 29, lr: 8.55e-04
+2022-05-04 00:56:47,165 INFO [train.py:715] (3/8) Epoch 1, batch 24700, loss[loss=0.1703, simple_loss=0.2355, pruned_loss=0.05255, over 4768.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2459, pruned_loss=0.05871, over 970944.92 frames.], batch size: 12, lr: 8.55e-04
+2022-05-04 00:57:27,340 INFO [train.py:715] (3/8) Epoch 1, batch 24750, loss[loss=0.2021, simple_loss=0.2621, pruned_loss=0.07099, over 4959.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2467, pruned_loss=0.05914, over 971325.18 frames.], batch size: 35, lr: 8.55e-04
+2022-05-04 00:58:06,478 INFO [train.py:715] (3/8) Epoch 1, batch 24800, loss[loss=0.2068, simple_loss=0.2672, pruned_loss=0.07316, over 4970.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2464, pruned_loss=0.05925, over 971308.59 frames.], batch size: 35, lr: 8.54e-04
+2022-05-04 00:58:45,103 INFO [train.py:715] (3/8) Epoch 1, batch 24850, loss[loss=0.1833, simple_loss=0.2449, pruned_loss=0.06082, over 4861.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2462, pruned_loss=0.05958, over 971106.27 frames.], batch size: 20, lr: 8.54e-04
+2022-05-04 00:59:25,587 INFO [train.py:715] (3/8) Epoch 1, batch 24900, loss[loss=0.177, simple_loss=0.2296, pruned_loss=0.06221, over 4797.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2452, pruned_loss=0.05878, over 971179.36 frames.], batch size: 24, lr: 8.54e-04
+2022-05-04 01:00:05,519 INFO [train.py:715] (3/8) Epoch 1, batch 24950, loss[loss=0.2009, simple_loss=0.2726, pruned_loss=0.06457, over 4872.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2454, pruned_loss=0.059, over 971199.24 frames.], batch size: 16, lr: 8.53e-04
+2022-05-04 01:00:44,290 INFO [train.py:715] (3/8) Epoch 1, batch 25000, loss[loss=0.2009, simple_loss=0.2656, pruned_loss=0.06807, over 4872.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2456, pruned_loss=0.05863, over 971700.47 frames.], batch size: 22, lr: 8.53e-04
+2022-05-04 01:01:22,933 INFO [train.py:715] (3/8) Epoch 1, batch 25050, loss[loss=0.1874, simple_loss=0.2567, pruned_loss=0.05902, over 4953.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2453, pruned_loss=0.05804, over 972207.70 frames.], batch size: 21, lr: 8.53e-04
+2022-05-04 01:02:02,855 INFO [train.py:715] (3/8) Epoch 1, batch 25100, loss[loss=0.2156, simple_loss=0.2712, pruned_loss=0.08002, over 4871.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2445, pruned_loss=0.05767, over 972250.79 frames.], batch size: 16, lr: 8.52e-04
+2022-05-04 01:02:42,031 INFO [train.py:715] (3/8) Epoch 1, batch 25150, loss[loss=0.2089, simple_loss=0.2877, pruned_loss=0.06506, over 4867.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2454, pruned_loss=0.05789, over 972969.44 frames.], batch size: 22, lr: 8.52e-04
+2022-05-04 01:03:20,871 INFO [train.py:715] (3/8) Epoch 1, batch 25200, loss[loss=0.2062, simple_loss=0.2683, pruned_loss=0.07204, over 4970.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2459, pruned_loss=0.05851, over 973138.75 frames.], batch size: 15, lr: 8.51e-04
+2022-05-04 01:04:00,096 INFO [train.py:715] (3/8) Epoch 1, batch 25250, loss[loss=0.214, simple_loss=0.2678, pruned_loss=0.08009, over 4986.00 frames.], tot_loss[loss=0.182, simple_loss=0.246, pruned_loss=0.05901, over 972992.98 frames.], batch size: 28, lr: 8.51e-04
+2022-05-04 01:04:40,223 INFO [train.py:715] (3/8) Epoch 1, batch 25300, loss[loss=0.1396, simple_loss=0.2096, pruned_loss=0.03477, over 4770.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2449, pruned_loss=0.05879, over 972970.23 frames.], batch size: 19, lr: 8.51e-04
+2022-05-04 01:05:18,874 INFO [train.py:715] (3/8) Epoch 1, batch 25350, loss[loss=0.187, simple_loss=0.2548, pruned_loss=0.05964, over 4800.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2461, pruned_loss=0.05978, over 974289.60 frames.], batch size: 21, lr: 8.50e-04
+2022-05-04 01:05:58,215 INFO [train.py:715] (3/8) Epoch 1, batch 25400, loss[loss=0.1639, simple_loss=0.2277, pruned_loss=0.04999, over 4781.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2469, pruned_loss=0.06033, over 973921.24 frames.], batch size: 18, lr: 8.50e-04
+2022-05-04 01:06:38,477 INFO [train.py:715] (3/8) Epoch 1, batch 25450, loss[loss=0.1779, simple_loss=0.2364, pruned_loss=0.05974, over 4814.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2469, pruned_loss=0.05973, over 972824.12 frames.], batch size: 27, lr: 8.50e-04
+2022-05-04 01:07:18,419 INFO [train.py:715] (3/8) Epoch 1, batch 25500, loss[loss=0.1478, simple_loss=0.2059, pruned_loss=0.04491, over 4938.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2453, pruned_loss=0.0586, over 972946.40 frames.], batch size: 23, lr: 8.49e-04
+2022-05-04 01:07:56,846 INFO [train.py:715] (3/8) Epoch 1, batch 25550, loss[loss=0.1572, simple_loss=0.2294, pruned_loss=0.04251, over 4983.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2463, pruned_loss=0.05919, over 973423.97 frames.], batch size: 15, lr: 8.49e-04
+2022-05-04 01:08:36,978 INFO [train.py:715] (3/8) Epoch 1, batch 25600, loss[loss=0.2169, simple_loss=0.2624, pruned_loss=0.08571, over 4734.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2461, pruned_loss=0.0591, over 973651.24 frames.], batch size: 16, lr: 8.49e-04
+2022-05-04 01:09:17,500 INFO [train.py:715] (3/8) Epoch 1, batch 25650, loss[loss=0.1625, simple_loss=0.2307, pruned_loss=0.04714, over 4856.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2456, pruned_loss=0.0589, over 973282.30 frames.], batch size: 20, lr: 8.48e-04
+2022-05-04 01:09:56,987 INFO [train.py:715] (3/8) Epoch 1, batch 25700, loss[loss=0.1434, simple_loss=0.1989, pruned_loss=0.04399, over 4747.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2445, pruned_loss=0.05796, over 972645.32 frames.], batch size: 12, lr: 8.48e-04
+2022-05-04 01:10:36,899 INFO [train.py:715] (3/8) Epoch 1, batch 25750, loss[loss=0.1852, simple_loss=0.2461, pruned_loss=0.06213, over 4944.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2451, pruned_loss=0.05834, over 972445.49 frames.], batch size: 21, lr: 8.48e-04
+2022-05-04 01:11:17,393 INFO [train.py:715] (3/8) Epoch 1, batch 25800, loss[loss=0.1558, simple_loss=0.2123, pruned_loss=0.04962, over 4867.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2441, pruned_loss=0.0577, over 972549.30 frames.], batch size: 13, lr: 8.47e-04
+2022-05-04 01:11:56,815 INFO [train.py:715] (3/8) Epoch 1, batch 25850, loss[loss=0.2483, simple_loss=0.2907, pruned_loss=0.103, over 4775.00 frames.], tot_loss[loss=0.181, simple_loss=0.245, pruned_loss=0.05844, over 972415.09 frames.], batch size: 14, lr: 8.47e-04
+2022-05-04 01:12:35,649 INFO [train.py:715] (3/8) Epoch 1, batch 25900, loss[loss=0.1968, simple_loss=0.2607, pruned_loss=0.06643, over 4805.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2447, pruned_loss=0.05809, over 972867.82 frames.], batch size: 25, lr: 8.47e-04
+2022-05-04 01:13:15,323 INFO [train.py:715] (3/8) Epoch 1, batch 25950, loss[loss=0.2184, simple_loss=0.2638, pruned_loss=0.08653, over 4967.00 frames.], tot_loss[loss=0.18, simple_loss=0.2443, pruned_loss=0.05786, over 972578.11 frames.], batch size: 35, lr: 8.46e-04
+2022-05-04 01:13:55,203 INFO [train.py:715] (3/8) Epoch 1, batch 26000, loss[loss=0.177, simple_loss=0.2572, pruned_loss=0.04845, over 4808.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2448, pruned_loss=0.05809, over 972573.26 frames.], batch size: 26, lr: 8.46e-04
+2022-05-04 01:14:34,093 INFO [train.py:715] (3/8) Epoch 1, batch 26050, loss[loss=0.1456, simple_loss=0.2164, pruned_loss=0.03735, over 4793.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2459, pruned_loss=0.05872, over 972427.52 frames.], batch size: 14, lr: 8.46e-04
+2022-05-04 01:15:13,490 INFO [train.py:715] (3/8) Epoch 1, batch 26100, loss[loss=0.201, simple_loss=0.2685, pruned_loss=0.06674, over 4758.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2451, pruned_loss=0.05825, over 972746.00 frames.], batch size: 18, lr: 8.45e-04
+2022-05-04 01:15:53,621 INFO [train.py:715] (3/8) Epoch 1, batch 26150, loss[loss=0.1849, simple_loss=0.2431, pruned_loss=0.06336, over 4784.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2453, pruned_loss=0.05863, over 972720.25 frames.], batch size: 18, lr: 8.45e-04
+2022-05-04 01:16:32,571 INFO [train.py:715] (3/8) Epoch 1, batch 26200, loss[loss=0.1643, simple_loss=0.2336, pruned_loss=0.04751, over 4974.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2448, pruned_loss=0.0584, over 971154.25 frames.], batch size: 39, lr: 8.44e-04
+2022-05-04 01:17:11,435 INFO [train.py:715] (3/8) Epoch 1, batch 26250, loss[loss=0.1978, simple_loss=0.2539, pruned_loss=0.07085, over 4773.00 frames.], tot_loss[loss=0.18, simple_loss=0.2442, pruned_loss=0.05791, over 970326.82 frames.], batch size: 17, lr: 8.44e-04
+2022-05-04 01:17:51,345 INFO [train.py:715] (3/8) Epoch 1, batch 26300, loss[loss=0.2064, simple_loss=0.2594, pruned_loss=0.07666, over 4791.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2439, pruned_loss=0.05778, over 970837.44 frames.], batch size: 18, lr: 8.44e-04
+2022-05-04 01:18:31,200 INFO [train.py:715] (3/8) Epoch 1, batch 26350, loss[loss=0.1879, simple_loss=0.2634, pruned_loss=0.05625, over 4752.00 frames.], tot_loss[loss=0.1798, simple_loss=0.244, pruned_loss=0.05782, over 970642.34 frames.], batch size: 19, lr: 8.43e-04
+2022-05-04 01:19:09,967 INFO [train.py:715] (3/8) Epoch 1, batch 26400, loss[loss=0.167, simple_loss=0.2473, pruned_loss=0.04333, over 4816.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2442, pruned_loss=0.05797, over 971196.44 frames.], batch size: 25, lr: 8.43e-04
+2022-05-04 01:19:49,169 INFO [train.py:715] (3/8) Epoch 1, batch 26450, loss[loss=0.1782, simple_loss=0.2366, pruned_loss=0.05986, over 4835.00 frames.], tot_loss[loss=0.18, simple_loss=0.2443, pruned_loss=0.05784, over 971464.48 frames.], batch size: 15, lr: 8.43e-04
+2022-05-04 01:20:28,923 INFO [train.py:715] (3/8) Epoch 1, batch 26500, loss[loss=0.1928, simple_loss=0.2599, pruned_loss=0.06289, over 4762.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2436, pruned_loss=0.05729, over 971880.56 frames.], batch size: 19, lr: 8.42e-04
+2022-05-04 01:21:08,262 INFO [train.py:715] (3/8) Epoch 1, batch 26550, loss[loss=0.1704, simple_loss=0.231, pruned_loss=0.05492, over 4890.00 frames.], tot_loss[loss=0.1785, simple_loss=0.243, pruned_loss=0.057, over 972079.60 frames.], batch size: 22, lr: 8.42e-04
+2022-05-04 01:21:47,632 INFO [train.py:715] (3/8) Epoch 1, batch 26600, loss[loss=0.1936, simple_loss=0.2418, pruned_loss=0.07264, over 4963.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2429, pruned_loss=0.05699, over 972341.99 frames.], batch size: 35, lr: 8.42e-04
+2022-05-04 01:22:27,676 INFO [train.py:715] (3/8) Epoch 1, batch 26650, loss[loss=0.1671, simple_loss=0.2336, pruned_loss=0.05026, over 4935.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2431, pruned_loss=0.05729, over 972555.41 frames.], batch size: 23, lr: 8.41e-04
+2022-05-04 01:23:07,626 INFO [train.py:715] (3/8) Epoch 1, batch 26700, loss[loss=0.2479, simple_loss=0.2913, pruned_loss=0.1023, over 4852.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2438, pruned_loss=0.05762, over 972669.57 frames.], batch size: 30, lr: 8.41e-04
+2022-05-04 01:23:46,598 INFO [train.py:715] (3/8) Epoch 1, batch 26750, loss[loss=0.1617, simple_loss=0.2319, pruned_loss=0.04571, over 4774.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2441, pruned_loss=0.05751, over 972459.86 frames.], batch size: 12, lr: 8.41e-04
+2022-05-04 01:24:26,590 INFO [train.py:715] (3/8) Epoch 1, batch 26800, loss[loss=0.1934, simple_loss=0.2486, pruned_loss=0.06912, over 4855.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2446, pruned_loss=0.05754, over 972863.10 frames.], batch size: 20, lr: 8.40e-04
+2022-05-04 01:25:06,136 INFO [train.py:715] (3/8) Epoch 1, batch 26850, loss[loss=0.2002, simple_loss=0.2615, pruned_loss=0.0695, over 4810.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2447, pruned_loss=0.05757, over 973025.82 frames.], batch size: 25, lr: 8.40e-04
+2022-05-04 01:25:45,418 INFO [train.py:715] (3/8) Epoch 1, batch 26900, loss[loss=0.1558, simple_loss=0.229, pruned_loss=0.04132, over 4950.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2454, pruned_loss=0.05802, over 973336.95 frames.], batch size: 24, lr: 8.40e-04
+2022-05-04 01:26:24,109 INFO [train.py:715] (3/8) Epoch 1, batch 26950, loss[loss=0.1774, simple_loss=0.2343, pruned_loss=0.0603, over 4923.00 frames.], tot_loss[loss=0.1825, simple_loss=0.247, pruned_loss=0.05899, over 972579.82 frames.], batch size: 18, lr: 8.39e-04
+2022-05-04 01:27:04,122 INFO [train.py:715] (3/8) Epoch 1, batch 27000, loss[loss=0.2142, simple_loss=0.2664, pruned_loss=0.08095, over 4987.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2471, pruned_loss=0.05894, over 972665.27 frames.], batch size: 14, lr: 8.39e-04
+2022-05-04 01:27:04,123 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 01:27:12,718 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.1212, simple_loss=0.2081, pruned_loss=0.01718, over 914524.00 frames.
+2022-05-04 01:27:53,059 INFO [train.py:715] (3/8) Epoch 1, batch 27050, loss[loss=0.162, simple_loss=0.2308, pruned_loss=0.04664, over 4686.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2461, pruned_loss=0.05843, over 972990.50 frames.], batch size: 15, lr: 8.39e-04
+2022-05-04 01:28:33,372 INFO [train.py:715] (3/8) Epoch 1, batch 27100, loss[loss=0.2165, simple_loss=0.2658, pruned_loss=0.08361, over 4773.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2458, pruned_loss=0.05859, over 973103.61 frames.], batch size: 18, lr: 8.38e-04
+2022-05-04 01:29:11,778 INFO [train.py:715] (3/8) Epoch 1, batch 27150, loss[loss=0.1851, simple_loss=0.2486, pruned_loss=0.06077, over 4782.00 frames.], tot_loss[loss=0.183, simple_loss=0.2474, pruned_loss=0.05936, over 972270.14 frames.], batch size: 14, lr: 8.38e-04
+2022-05-04 01:29:51,722 INFO [train.py:715] (3/8) Epoch 1, batch 27200, loss[loss=0.1724, simple_loss=0.2382, pruned_loss=0.05327, over 4812.00 frames.], tot_loss[loss=0.182, simple_loss=0.2463, pruned_loss=0.0588, over 972349.77 frames.], batch size: 27, lr: 8.38e-04
+2022-05-04 01:30:32,011 INFO [train.py:715] (3/8) Epoch 1, batch 27250, loss[loss=0.1764, simple_loss=0.2285, pruned_loss=0.06215, over 4813.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2458, pruned_loss=0.05843, over 972480.86 frames.], batch size: 13, lr: 8.37e-04
+2022-05-04 01:31:11,132 INFO [train.py:715] (3/8) Epoch 1, batch 27300, loss[loss=0.1985, simple_loss=0.2585, pruned_loss=0.06929, over 4865.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2457, pruned_loss=0.05857, over 972716.05 frames.], batch size: 20, lr: 8.37e-04
+2022-05-04 01:31:49,670 INFO [train.py:715] (3/8) Epoch 1, batch 27350, loss[loss=0.1711, simple_loss=0.2392, pruned_loss=0.05153, over 4883.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2445, pruned_loss=0.05801, over 972609.85 frames.], batch size: 16, lr: 8.37e-04
+2022-05-04 01:32:29,601 INFO [train.py:715] (3/8) Epoch 1, batch 27400, loss[loss=0.1736, simple_loss=0.2385, pruned_loss=0.05438, over 4857.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2448, pruned_loss=0.05753, over 973330.40 frames.], batch size: 20, lr: 8.36e-04
+2022-05-04 01:33:09,594 INFO [train.py:715] (3/8) Epoch 1, batch 27450, loss[loss=0.1754, simple_loss=0.2583, pruned_loss=0.04621, over 4803.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2451, pruned_loss=0.05761, over 973125.12 frames.], batch size: 21, lr: 8.36e-04
+2022-05-04 01:33:48,103 INFO [train.py:715] (3/8) Epoch 1, batch 27500, loss[loss=0.1921, simple_loss=0.2366, pruned_loss=0.07383, over 4877.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2437, pruned_loss=0.05703, over 972776.84 frames.], batch size: 16, lr: 8.36e-04
+2022-05-04 01:34:27,758 INFO [train.py:715] (3/8) Epoch 1, batch 27550, loss[loss=0.1972, simple_loss=0.2572, pruned_loss=0.06865, over 4949.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2434, pruned_loss=0.05654, over 972277.61 frames.], batch size: 14, lr: 8.35e-04
+2022-05-04 01:35:07,986 INFO [train.py:715] (3/8) Epoch 1, batch 27600, loss[loss=0.1539, simple_loss=0.213, pruned_loss=0.04741, over 4745.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2432, pruned_loss=0.05691, over 971926.71 frames.], batch size: 16, lr: 8.35e-04
+2022-05-04 01:35:47,294 INFO [train.py:715] (3/8) Epoch 1, batch 27650, loss[loss=0.1973, simple_loss=0.2484, pruned_loss=0.07309, over 4824.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2425, pruned_loss=0.05719, over 972080.27 frames.], batch size: 13, lr: 8.35e-04
+2022-05-04 01:36:26,733 INFO [train.py:715] (3/8) Epoch 1, batch 27700, loss[loss=0.1616, simple_loss=0.2319, pruned_loss=0.04562, over 4804.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2435, pruned_loss=0.05797, over 971653.14 frames.], batch size: 25, lr: 8.34e-04
+2022-05-04 01:37:07,281 INFO [train.py:715] (3/8) Epoch 1, batch 27750, loss[loss=0.1761, simple_loss=0.2318, pruned_loss=0.06023, over 4784.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2428, pruned_loss=0.05783, over 972164.21 frames.], batch size: 21, lr: 8.34e-04
+2022-05-04 01:37:47,068 INFO [train.py:715] (3/8) Epoch 1, batch 27800, loss[loss=0.1926, simple_loss=0.275, pruned_loss=0.0551, over 4986.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2432, pruned_loss=0.05799, over 972496.26 frames.], batch size: 27, lr: 8.34e-04
+2022-05-04 01:38:26,356 INFO [train.py:715] (3/8) Epoch 1, batch 27850, loss[loss=0.1574, simple_loss=0.2301, pruned_loss=0.04237, over 4760.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2438, pruned_loss=0.05819, over 973111.30 frames.], batch size: 19, lr: 8.33e-04
+2022-05-04 01:39:06,467 INFO [train.py:715] (3/8) Epoch 1, batch 27900, loss[loss=0.1777, simple_loss=0.2538, pruned_loss=0.05081, over 4922.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2446, pruned_loss=0.05831, over 972721.65 frames.], batch size: 29, lr: 8.33e-04
+2022-05-04 01:39:45,944 INFO [train.py:715] (3/8) Epoch 1, batch 27950, loss[loss=0.179, simple_loss=0.2445, pruned_loss=0.05675, over 4856.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2446, pruned_loss=0.05828, over 972728.32 frames.], batch size: 20, lr: 8.33e-04
+2022-05-04 01:40:25,328 INFO [train.py:715] (3/8) Epoch 1, batch 28000, loss[loss=0.1345, simple_loss=0.2124, pruned_loss=0.02833, over 4923.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2444, pruned_loss=0.05809, over 973365.08 frames.], batch size: 21, lr: 8.32e-04
+2022-05-04 01:41:04,104 INFO [train.py:715] (3/8) Epoch 1, batch 28050, loss[loss=0.1898, simple_loss=0.253, pruned_loss=0.06334, over 4897.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2443, pruned_loss=0.05815, over 973349.02 frames.], batch size: 22, lr: 8.32e-04
+2022-05-04 01:41:44,524 INFO [train.py:715] (3/8) Epoch 1, batch 28100, loss[loss=0.2097, simple_loss=0.2596, pruned_loss=0.07987, over 4876.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2446, pruned_loss=0.05821, over 972962.36 frames.], batch size: 32, lr: 8.32e-04
+2022-05-04 01:42:23,900 INFO [train.py:715] (3/8) Epoch 1, batch 28150, loss[loss=0.1707, simple_loss=0.2346, pruned_loss=0.05336, over 4950.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2448, pruned_loss=0.05844, over 973101.80 frames.], batch size: 21, lr: 8.31e-04
+2022-05-04 01:43:03,303 INFO [train.py:715] (3/8) Epoch 1, batch 28200, loss[loss=0.1895, simple_loss=0.2612, pruned_loss=0.05887, over 4877.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2448, pruned_loss=0.05838, over 972614.04 frames.], batch size: 22, lr: 8.31e-04
+2022-05-04 01:43:43,991 INFO [train.py:715] (3/8) Epoch 1, batch 28250, loss[loss=0.2105, simple_loss=0.2681, pruned_loss=0.07644, over 4763.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2457, pruned_loss=0.05877, over 972404.63 frames.], batch size: 16, lr: 8.31e-04
+2022-05-04 01:44:24,417 INFO [train.py:715] (3/8) Epoch 1, batch 28300, loss[loss=0.1835, simple_loss=0.2441, pruned_loss=0.06147, over 4850.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2458, pruned_loss=0.05874, over 972386.49 frames.], batch size: 15, lr: 8.30e-04
+2022-05-04 01:45:03,749 INFO [train.py:715] (3/8) Epoch 1, batch 28350, loss[loss=0.1828, simple_loss=0.2474, pruned_loss=0.05911, over 4880.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2465, pruned_loss=0.05934, over 972727.40 frames.], batch size: 22, lr: 8.30e-04
+2022-05-04 01:45:42,702 INFO [train.py:715] (3/8) Epoch 1, batch 28400, loss[loss=0.1821, simple_loss=0.2394, pruned_loss=0.0624, over 4881.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2458, pruned_loss=0.05921, over 972878.02 frames.], batch size: 16, lr: 8.30e-04
+2022-05-04 01:46:23,128 INFO [train.py:715] (3/8) Epoch 1, batch 28450, loss[loss=0.199, simple_loss=0.2703, pruned_loss=0.06382, over 4774.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2466, pruned_loss=0.05942, over 972514.48 frames.], batch size: 18, lr: 8.29e-04
+2022-05-04 01:47:02,714 INFO [train.py:715] (3/8) Epoch 1, batch 28500, loss[loss=0.1776, simple_loss=0.2409, pruned_loss=0.05714, over 4817.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2467, pruned_loss=0.05999, over 971696.24 frames.], batch size: 27, lr: 8.29e-04
+2022-05-04 01:47:41,715 INFO [train.py:715] (3/8) Epoch 1, batch 28550, loss[loss=0.1811, simple_loss=0.2435, pruned_loss=0.05938, over 4827.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2465, pruned_loss=0.05922, over 972319.46 frames.], batch size: 15, lr: 8.29e-04
+2022-05-04 01:48:22,002 INFO [train.py:715] (3/8) Epoch 1, batch 28600, loss[loss=0.1849, simple_loss=0.251, pruned_loss=0.05943, over 4938.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2463, pruned_loss=0.05935, over 972615.93 frames.], batch size: 39, lr: 8.28e-04
+2022-05-04 01:49:01,948 INFO [train.py:715] (3/8) Epoch 1, batch 28650, loss[loss=0.1748, simple_loss=0.2369, pruned_loss=0.05633, over 4916.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2451, pruned_loss=0.0588, over 972627.17 frames.], batch size: 18, lr: 8.28e-04
+2022-05-04 01:49:41,101 INFO [train.py:715] (3/8) Epoch 1, batch 28700, loss[loss=0.1378, simple_loss=0.2132, pruned_loss=0.03124, over 4875.00 frames.], tot_loss[loss=0.1808, simple_loss=0.245, pruned_loss=0.05832, over 973041.64 frames.], batch size: 22, lr: 8.28e-04
+2022-05-04 01:50:20,241 INFO [train.py:715] (3/8) Epoch 1, batch 28750, loss[loss=0.2109, simple_loss=0.2779, pruned_loss=0.07193, over 4912.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2447, pruned_loss=0.05812, over 973114.53 frames.], batch size: 17, lr: 8.27e-04
+2022-05-04 01:51:00,835 INFO [train.py:715] (3/8) Epoch 1, batch 28800, loss[loss=0.1827, simple_loss=0.2431, pruned_loss=0.0612, over 4696.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2449, pruned_loss=0.05797, over 972838.47 frames.], batch size: 15, lr: 8.27e-04
+2022-05-04 01:51:40,143 INFO [train.py:715] (3/8) Epoch 1, batch 28850, loss[loss=0.1511, simple_loss=0.2158, pruned_loss=0.04319, over 4980.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2441, pruned_loss=0.05722, over 972552.36 frames.], batch size: 14, lr: 8.27e-04
+2022-05-04 01:52:19,906 INFO [train.py:715] (3/8) Epoch 1, batch 28900, loss[loss=0.1404, simple_loss=0.2067, pruned_loss=0.03703, over 4894.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2439, pruned_loss=0.05729, over 972187.11 frames.], batch size: 22, lr: 8.27e-04
+2022-05-04 01:53:00,606 INFO [train.py:715] (3/8) Epoch 1, batch 28950, loss[loss=0.1738, simple_loss=0.2346, pruned_loss=0.05655, over 4803.00 frames.], tot_loss[loss=0.178, simple_loss=0.243, pruned_loss=0.05654, over 972812.55 frames.], batch size: 12, lr: 8.26e-04
+2022-05-04 01:53:40,737 INFO [train.py:715] (3/8) Epoch 1, batch 29000, loss[loss=0.1582, simple_loss=0.227, pruned_loss=0.04472, over 4790.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2429, pruned_loss=0.0566, over 972326.74 frames.], batch size: 21, lr: 8.26e-04
+2022-05-04 01:54:19,716 INFO [train.py:715] (3/8) Epoch 1, batch 29050, loss[loss=0.1707, simple_loss=0.2416, pruned_loss=0.04992, over 4869.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2436, pruned_loss=0.05672, over 972685.40 frames.], batch size: 20, lr: 8.26e-04
+2022-05-04 01:54:59,585 INFO [train.py:715] (3/8) Epoch 1, batch 29100, loss[loss=0.2136, simple_loss=0.272, pruned_loss=0.07764, over 4802.00 frames.], tot_loss[loss=0.1793, simple_loss=0.244, pruned_loss=0.0573, over 972093.80 frames.], batch size: 14, lr: 8.25e-04
+2022-05-04 01:55:40,265 INFO [train.py:715] (3/8) Epoch 1, batch 29150, loss[loss=0.1917, simple_loss=0.2496, pruned_loss=0.06691, over 4914.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2442, pruned_loss=0.05747, over 972169.54 frames.], batch size: 23, lr: 8.25e-04
+2022-05-04 01:56:22,385 INFO [train.py:715] (3/8) Epoch 1, batch 29200, loss[loss=0.1986, simple_loss=0.264, pruned_loss=0.06664, over 4964.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2448, pruned_loss=0.05822, over 971774.39 frames.], batch size: 15, lr: 8.25e-04
+2022-05-04 01:57:01,411 INFO [train.py:715] (3/8) Epoch 1, batch 29250, loss[loss=0.1929, simple_loss=0.267, pruned_loss=0.05945, over 4850.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2454, pruned_loss=0.05848, over 971712.85 frames.], batch size: 30, lr: 8.24e-04
+2022-05-04 01:57:41,959 INFO [train.py:715] (3/8) Epoch 1, batch 29300, loss[loss=0.1899, simple_loss=0.2498, pruned_loss=0.06504, over 4741.00 frames.], tot_loss[loss=0.18, simple_loss=0.2446, pruned_loss=0.05766, over 969788.99 frames.], batch size: 16, lr: 8.24e-04
+2022-05-04 01:58:22,149 INFO [train.py:715] (3/8) Epoch 1, batch 29350, loss[loss=0.1487, simple_loss=0.2219, pruned_loss=0.03773, over 4813.00 frames.], tot_loss[loss=0.1797, simple_loss=0.244, pruned_loss=0.05771, over 969826.79 frames.], batch size: 15, lr: 8.24e-04
+2022-05-04 01:59:00,688 INFO [train.py:715] (3/8) Epoch 1, batch 29400, loss[loss=0.154, simple_loss=0.2353, pruned_loss=0.03639, over 4857.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2439, pruned_loss=0.05765, over 970871.21 frames.], batch size: 20, lr: 8.23e-04
+2022-05-04 01:59:40,304 INFO [train.py:715] (3/8) Epoch 1, batch 29450, loss[loss=0.1461, simple_loss=0.2207, pruned_loss=0.03573, over 4782.00 frames.], tot_loss[loss=0.179, simple_loss=0.2433, pruned_loss=0.05733, over 971430.28 frames.], batch size: 18, lr: 8.23e-04
+2022-05-04 02:00:20,002 INFO [train.py:715] (3/8) Epoch 1, batch 29500, loss[loss=0.1815, simple_loss=0.2428, pruned_loss=0.06006, over 4923.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2436, pruned_loss=0.05776, over 971276.18 frames.], batch size: 39, lr: 8.23e-04
+2022-05-04 02:00:59,407 INFO [train.py:715] (3/8) Epoch 1, batch 29550, loss[loss=0.1467, simple_loss=0.2089, pruned_loss=0.04225, over 4846.00 frames.], tot_loss[loss=0.1777, simple_loss=0.242, pruned_loss=0.05672, over 972156.21 frames.], batch size: 13, lr: 8.22e-04
+2022-05-04 02:01:37,991 INFO [train.py:715] (3/8) Epoch 1, batch 29600, loss[loss=0.1556, simple_loss=0.2214, pruned_loss=0.04495, over 4839.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2428, pruned_loss=0.05674, over 972698.21 frames.], batch size: 30, lr: 8.22e-04
+2022-05-04 02:02:18,239 INFO [train.py:715] (3/8) Epoch 1, batch 29650, loss[loss=0.179, simple_loss=0.2326, pruned_loss=0.06271, over 4882.00 frames.], tot_loss[loss=0.1793, simple_loss=0.244, pruned_loss=0.05728, over 973374.64 frames.], batch size: 16, lr: 8.22e-04
+2022-05-04 02:02:58,330 INFO [train.py:715] (3/8) Epoch 1, batch 29700, loss[loss=0.2058, simple_loss=0.2776, pruned_loss=0.06703, over 4835.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2441, pruned_loss=0.05703, over 973783.24 frames.], batch size: 15, lr: 8.21e-04
+2022-05-04 02:03:36,328 INFO [train.py:715] (3/8) Epoch 1, batch 29750, loss[loss=0.1653, simple_loss=0.2305, pruned_loss=0.05005, over 4700.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2434, pruned_loss=0.0568, over 973132.20 frames.], batch size: 15, lr: 8.21e-04
+2022-05-04 02:04:15,634 INFO [train.py:715] (3/8) Epoch 1, batch 29800, loss[loss=0.1583, simple_loss=0.2275, pruned_loss=0.04455, over 4946.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2424, pruned_loss=0.05624, over 973015.79 frames.], batch size: 21, lr: 8.21e-04
+2022-05-04 02:04:55,049 INFO [train.py:715] (3/8) Epoch 1, batch 29850, loss[loss=0.1642, simple_loss=0.2318, pruned_loss=0.04829, over 4935.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2426, pruned_loss=0.05581, over 973521.46 frames.], batch size: 39, lr: 8.20e-04
+2022-05-04 02:05:34,427 INFO [train.py:715] (3/8) Epoch 1, batch 29900, loss[loss=0.2196, simple_loss=0.2626, pruned_loss=0.08828, over 4871.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2433, pruned_loss=0.05654, over 972500.84 frames.], batch size: 20, lr: 8.20e-04
+2022-05-04 02:06:12,927 INFO [train.py:715] (3/8) Epoch 1, batch 29950, loss[loss=0.2024, simple_loss=0.2728, pruned_loss=0.06593, over 4898.00 frames.], tot_loss[loss=0.179, simple_loss=0.2436, pruned_loss=0.05725, over 972452.97 frames.], batch size: 17, lr: 8.20e-04
+2022-05-04 02:06:52,734 INFO [train.py:715] (3/8) Epoch 1, batch 30000, loss[loss=0.152, simple_loss=0.2238, pruned_loss=0.04014, over 4806.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2432, pruned_loss=0.05705, over 972274.96 frames.], batch size: 26, lr: 8.20e-04
+2022-05-04 02:06:52,735 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 02:07:09,692 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.1207, simple_loss=0.2076, pruned_loss=0.01687, over 914524.00 frames.
+2022-05-04 02:07:50,184 INFO [train.py:715] (3/8) Epoch 1, batch 30050, loss[loss=0.1911, simple_loss=0.2562, pruned_loss=0.06293, over 4823.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2433, pruned_loss=0.05721, over 972996.33 frames.], batch size: 13, lr: 8.19e-04
+2022-05-04 02:08:29,661 INFO [train.py:715] (3/8) Epoch 1, batch 30100, loss[loss=0.184, simple_loss=0.2493, pruned_loss=0.05936, over 4962.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2441, pruned_loss=0.05735, over 973193.09 frames.], batch size: 21, lr: 8.19e-04
+2022-05-04 02:09:09,057 INFO [train.py:715] (3/8) Epoch 1, batch 30150, loss[loss=0.1617, simple_loss=0.2302, pruned_loss=0.04663, over 4792.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2444, pruned_loss=0.0577, over 973057.54 frames.], batch size: 17, lr: 8.19e-04
+2022-05-04 02:09:48,368 INFO [train.py:715] (3/8) Epoch 1, batch 30200, loss[loss=0.2137, simple_loss=0.2888, pruned_loss=0.06934, over 4992.00 frames.], tot_loss[loss=0.179, simple_loss=0.244, pruned_loss=0.05706, over 972466.66 frames.], batch size: 14, lr: 8.18e-04
+2022-05-04 02:10:28,818 INFO [train.py:715] (3/8) Epoch 1, batch 30250, loss[loss=0.1799, simple_loss=0.2452, pruned_loss=0.05727, over 4771.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2449, pruned_loss=0.05785, over 972891.73 frames.], batch size: 16, lr: 8.18e-04
+2022-05-04 02:11:08,796 INFO [train.py:715] (3/8) Epoch 1, batch 30300, loss[loss=0.2, simple_loss=0.263, pruned_loss=0.06856, over 4833.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2444, pruned_loss=0.05825, over 972625.78 frames.], batch size: 30, lr: 8.18e-04
+2022-05-04 02:11:47,709 INFO [train.py:715] (3/8) Epoch 1, batch 30350, loss[loss=0.1806, simple_loss=0.2507, pruned_loss=0.05522, over 4894.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2435, pruned_loss=0.0579, over 973076.87 frames.], batch size: 19, lr: 8.17e-04
+2022-05-04 02:12:27,772 INFO [train.py:715] (3/8) Epoch 1, batch 30400, loss[loss=0.1689, simple_loss=0.2376, pruned_loss=0.05012, over 4771.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2439, pruned_loss=0.05775, over 972414.91 frames.], batch size: 18, lr: 8.17e-04
+2022-05-04 02:13:07,264 INFO [train.py:715] (3/8) Epoch 1, batch 30450, loss[loss=0.1495, simple_loss=0.219, pruned_loss=0.03996, over 4989.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2428, pruned_loss=0.05686, over 973021.69 frames.], batch size: 16, lr: 8.17e-04
+2022-05-04 02:13:46,439 INFO [train.py:715] (3/8) Epoch 1, batch 30500, loss[loss=0.2042, simple_loss=0.2743, pruned_loss=0.06709, over 4972.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2436, pruned_loss=0.05739, over 972668.37 frames.], batch size: 14, lr: 8.16e-04
+2022-05-04 02:14:25,539 INFO [train.py:715] (3/8) Epoch 1, batch 30550, loss[loss=0.1908, simple_loss=0.2535, pruned_loss=0.06409, over 4791.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2433, pruned_loss=0.05722, over 971865.32 frames.], batch size: 24, lr: 8.16e-04
+2022-05-04 02:15:05,340 INFO [train.py:715] (3/8) Epoch 1, batch 30600, loss[loss=0.1786, simple_loss=0.251, pruned_loss=0.05312, over 4956.00 frames.], tot_loss[loss=0.1789, simple_loss=0.243, pruned_loss=0.05741, over 972313.21 frames.], batch size: 35, lr: 8.16e-04
+2022-05-04 02:15:44,803 INFO [train.py:715] (3/8) Epoch 1, batch 30650, loss[loss=0.1793, simple_loss=0.2492, pruned_loss=0.05469, over 4803.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2429, pruned_loss=0.05736, over 972581.53 frames.], batch size: 21, lr: 8.15e-04
+2022-05-04 02:16:23,385 INFO [train.py:715] (3/8) Epoch 1, batch 30700, loss[loss=0.2338, simple_loss=0.2969, pruned_loss=0.08537, over 4741.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2434, pruned_loss=0.05762, over 972487.33 frames.], batch size: 16, lr: 8.15e-04
+2022-05-04 02:17:03,634 INFO [train.py:715] (3/8) Epoch 1, batch 30750, loss[loss=0.1786, simple_loss=0.2455, pruned_loss=0.05585, over 4924.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2435, pruned_loss=0.05772, over 972958.35 frames.], batch size: 18, lr: 8.15e-04
+2022-05-04 02:17:43,205 INFO [train.py:715] (3/8) Epoch 1, batch 30800, loss[loss=0.1808, simple_loss=0.2451, pruned_loss=0.05824, over 4829.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2428, pruned_loss=0.05703, over 972637.01 frames.], batch size: 25, lr: 8.15e-04
+2022-05-04 02:18:22,129 INFO [train.py:715] (3/8) Epoch 1, batch 30850, loss[loss=0.1687, simple_loss=0.2367, pruned_loss=0.05033, over 4855.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2428, pruned_loss=0.05701, over 973060.30 frames.], batch size: 20, lr: 8.14e-04
+2022-05-04 02:19:01,713 INFO [train.py:715] (3/8) Epoch 1, batch 30900, loss[loss=0.239, simple_loss=0.2994, pruned_loss=0.08929, over 4767.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2421, pruned_loss=0.05675, over 971910.41 frames.], batch size: 16, lr: 8.14e-04
+2022-05-04 02:19:41,342 INFO [train.py:715] (3/8) Epoch 1, batch 30950, loss[loss=0.1612, simple_loss=0.2306, pruned_loss=0.04586, over 4867.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2423, pruned_loss=0.05661, over 972092.15 frames.], batch size: 20, lr: 8.14e-04
+2022-05-04 02:20:20,850 INFO [train.py:715] (3/8) Epoch 1, batch 31000, loss[loss=0.1426, simple_loss=0.2204, pruned_loss=0.03236, over 4855.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2423, pruned_loss=0.05608, over 972007.12 frames.], batch size: 16, lr: 8.13e-04
+2022-05-04 02:21:00,349 INFO [train.py:715] (3/8) Epoch 1, batch 31050, loss[loss=0.2079, simple_loss=0.2536, pruned_loss=0.08106, over 4754.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2428, pruned_loss=0.05637, over 971832.90 frames.], batch size: 16, lr: 8.13e-04
+2022-05-04 02:21:40,836 INFO [train.py:715] (3/8) Epoch 1, batch 31100, loss[loss=0.1584, simple_loss=0.2233, pruned_loss=0.04681, over 4815.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2448, pruned_loss=0.05796, over 971736.98 frames.], batch size: 12, lr: 8.13e-04
+2022-05-04 02:22:20,581 INFO [train.py:715] (3/8) Epoch 1, batch 31150, loss[loss=0.1613, simple_loss=0.2258, pruned_loss=0.04835, over 4827.00 frames.], tot_loss[loss=0.181, simple_loss=0.2455, pruned_loss=0.05827, over 972749.46 frames.], batch size: 13, lr: 8.12e-04
+2022-05-04 02:22:59,624 INFO [train.py:715] (3/8) Epoch 1, batch 31200, loss[loss=0.1516, simple_loss=0.219, pruned_loss=0.04216, over 4927.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2441, pruned_loss=0.05786, over 973111.19 frames.], batch size: 23, lr: 8.12e-04
+2022-05-04 02:23:39,857 INFO [train.py:715] (3/8) Epoch 1, batch 31250, loss[loss=0.1759, simple_loss=0.2419, pruned_loss=0.05493, over 4790.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2432, pruned_loss=0.05698, over 973212.62 frames.], batch size: 23, lr: 8.12e-04
+2022-05-04 02:24:19,619 INFO [train.py:715] (3/8) Epoch 1, batch 31300, loss[loss=0.1711, simple_loss=0.2338, pruned_loss=0.05414, over 4902.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2439, pruned_loss=0.05757, over 973363.85 frames.], batch size: 17, lr: 8.11e-04
+2022-05-04 02:24:59,059 INFO [train.py:715] (3/8) Epoch 1, batch 31350, loss[loss=0.1872, simple_loss=0.2542, pruned_loss=0.0601, over 4921.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2438, pruned_loss=0.05717, over 973700.67 frames.], batch size: 19, lr: 8.11e-04
+2022-05-04 02:25:38,857 INFO [train.py:715] (3/8) Epoch 1, batch 31400, loss[loss=0.1343, simple_loss=0.2009, pruned_loss=0.03385, over 4910.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2438, pruned_loss=0.05741, over 974291.04 frames.], batch size: 18, lr: 8.11e-04
+2022-05-04 02:26:18,863 INFO [train.py:715] (3/8) Epoch 1, batch 31450, loss[loss=0.1633, simple_loss=0.2239, pruned_loss=0.05131, over 4864.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2431, pruned_loss=0.05722, over 973616.95 frames.], batch size: 32, lr: 8.11e-04
+2022-05-04 02:26:58,728 INFO [train.py:715] (3/8) Epoch 1, batch 31500, loss[loss=0.1922, simple_loss=0.2487, pruned_loss=0.06787, over 4761.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2437, pruned_loss=0.05773, over 973158.51 frames.], batch size: 16, lr: 8.10e-04
+2022-05-04 02:27:37,228 INFO [train.py:715] (3/8) Epoch 1, batch 31550, loss[loss=0.1598, simple_loss=0.2286, pruned_loss=0.04555, over 4908.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2437, pruned_loss=0.05777, over 972824.85 frames.], batch size: 19, lr: 8.10e-04
+2022-05-04 02:28:17,413 INFO [train.py:715] (3/8) Epoch 1, batch 31600, loss[loss=0.1728, simple_loss=0.2367, pruned_loss=0.05444, over 4944.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2436, pruned_loss=0.05758, over 972558.89 frames.], batch size: 24, lr: 8.10e-04
+2022-05-04 02:28:57,085 INFO [train.py:715] (3/8) Epoch 1, batch 31650, loss[loss=0.1927, simple_loss=0.2578, pruned_loss=0.06383, over 4851.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2443, pruned_loss=0.05792, over 972467.80 frames.], batch size: 32, lr: 8.09e-04
+2022-05-04 02:29:36,999 INFO [train.py:715] (3/8) Epoch 1, batch 31700, loss[loss=0.2633, simple_loss=0.3066, pruned_loss=0.1099, over 4969.00 frames.], tot_loss[loss=0.1798, simple_loss=0.244, pruned_loss=0.05776, over 973834.39 frames.], batch size: 35, lr: 8.09e-04
+2022-05-04 02:30:16,361 INFO [train.py:715] (3/8) Epoch 1, batch 31750, loss[loss=0.1517, simple_loss=0.2087, pruned_loss=0.0473, over 4773.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2435, pruned_loss=0.05772, over 973723.37 frames.], batch size: 14, lr: 8.09e-04
+2022-05-04 02:30:56,484 INFO [train.py:715] (3/8) Epoch 1, batch 31800, loss[loss=0.1351, simple_loss=0.2082, pruned_loss=0.031, over 4930.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2428, pruned_loss=0.05701, over 974114.53 frames.], batch size: 23, lr: 8.08e-04
+2022-05-04 02:31:36,270 INFO [train.py:715] (3/8) Epoch 1, batch 31850, loss[loss=0.1883, simple_loss=0.2557, pruned_loss=0.06048, over 4946.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2432, pruned_loss=0.05701, over 974871.23 frames.], batch size: 39, lr: 8.08e-04
+2022-05-04 02:32:15,742 INFO [train.py:715] (3/8) Epoch 1, batch 31900, loss[loss=0.184, simple_loss=0.2502, pruned_loss=0.05891, over 4783.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2427, pruned_loss=0.05724, over 974207.62 frames.], batch size: 17, lr: 8.08e-04
+2022-05-04 02:32:55,106 INFO [train.py:715] (3/8) Epoch 1, batch 31950, loss[loss=0.184, simple_loss=0.2492, pruned_loss=0.05944, over 4955.00 frames.], tot_loss[loss=0.1785, simple_loss=0.243, pruned_loss=0.05702, over 973239.72 frames.], batch size: 21, lr: 8.08e-04
+2022-05-04 02:33:34,636 INFO [train.py:715] (3/8) Epoch 1, batch 32000, loss[loss=0.1507, simple_loss=0.2181, pruned_loss=0.04167, over 4820.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2434, pruned_loss=0.05682, over 972514.46 frames.], batch size: 14, lr: 8.07e-04
+2022-05-04 02:34:14,066 INFO [train.py:715] (3/8) Epoch 1, batch 32050, loss[loss=0.1866, simple_loss=0.2493, pruned_loss=0.06193, over 4975.00 frames.], tot_loss[loss=0.1797, simple_loss=0.244, pruned_loss=0.05766, over 972502.77 frames.], batch size: 24, lr: 8.07e-04
+2022-05-04 02:34:53,315 INFO [train.py:715] (3/8) Epoch 1, batch 32100, loss[loss=0.167, simple_loss=0.2367, pruned_loss=0.0486, over 4761.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2442, pruned_loss=0.05739, over 971675.75 frames.], batch size: 19, lr: 8.07e-04
+2022-05-04 02:35:32,938 INFO [train.py:715] (3/8) Epoch 1, batch 32150, loss[loss=0.144, simple_loss=0.2153, pruned_loss=0.03639, over 4779.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2441, pruned_loss=0.05671, over 971905.89 frames.], batch size: 18, lr: 8.06e-04
+2022-05-04 02:36:12,937 INFO [train.py:715] (3/8) Epoch 1, batch 32200, loss[loss=0.1505, simple_loss=0.2186, pruned_loss=0.04117, over 4802.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2427, pruned_loss=0.05594, over 971928.73 frames.], batch size: 24, lr: 8.06e-04
+2022-05-04 02:36:51,839 INFO [train.py:715] (3/8) Epoch 1, batch 32250, loss[loss=0.2254, simple_loss=0.2829, pruned_loss=0.084, over 4703.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2436, pruned_loss=0.05608, over 972951.05 frames.], batch size: 15, lr: 8.06e-04
+2022-05-04 02:37:31,251 INFO [train.py:715] (3/8) Epoch 1, batch 32300, loss[loss=0.1541, simple_loss=0.2272, pruned_loss=0.04049, over 4980.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2434, pruned_loss=0.0558, over 973186.80 frames.], batch size: 25, lr: 8.05e-04
+2022-05-04 02:38:10,686 INFO [train.py:715] (3/8) Epoch 1, batch 32350, loss[loss=0.1777, simple_loss=0.2553, pruned_loss=0.05006, over 4942.00 frames.], tot_loss[loss=0.178, simple_loss=0.244, pruned_loss=0.05595, over 973431.46 frames.], batch size: 24, lr: 8.05e-04
+2022-05-04 02:38:50,280 INFO [train.py:715] (3/8) Epoch 1, batch 32400, loss[loss=0.1751, simple_loss=0.2316, pruned_loss=0.05927, over 4804.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2437, pruned_loss=0.05623, over 973136.57 frames.], batch size: 21, lr: 8.05e-04
+2022-05-04 02:39:29,214 INFO [train.py:715] (3/8) Epoch 1, batch 32450, loss[loss=0.1592, simple_loss=0.2323, pruned_loss=0.04302, over 4780.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2443, pruned_loss=0.057, over 972515.21 frames.], batch size: 17, lr: 8.05e-04
+2022-05-04 02:40:08,857 INFO [train.py:715] (3/8) Epoch 1, batch 32500, loss[loss=0.1641, simple_loss=0.2344, pruned_loss=0.04692, over 4833.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2436, pruned_loss=0.05659, over 972779.73 frames.], batch size: 13, lr: 8.04e-04
+2022-05-04 02:40:48,375 INFO [train.py:715] (3/8) Epoch 1, batch 32550, loss[loss=0.183, simple_loss=0.2405, pruned_loss=0.06272, over 4752.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2435, pruned_loss=0.05669, over 972081.37 frames.], batch size: 16, lr: 8.04e-04
+2022-05-04 02:41:27,295 INFO [train.py:715] (3/8) Epoch 1, batch 32600, loss[loss=0.1722, simple_loss=0.2349, pruned_loss=0.05475, over 4984.00 frames.], tot_loss[loss=0.178, simple_loss=0.2427, pruned_loss=0.05665, over 972441.93 frames.], batch size: 28, lr: 8.04e-04
+2022-05-04 02:42:06,687 INFO [train.py:715] (3/8) Epoch 1, batch 32650, loss[loss=0.1835, simple_loss=0.2453, pruned_loss=0.06081, over 4873.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2439, pruned_loss=0.05744, over 971804.10 frames.], batch size: 16, lr: 8.03e-04
+2022-05-04 02:42:46,231 INFO [train.py:715] (3/8) Epoch 1, batch 32700, loss[loss=0.2088, simple_loss=0.2699, pruned_loss=0.07379, over 4823.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2436, pruned_loss=0.05785, over 971739.08 frames.], batch size: 26, lr: 8.03e-04
+2022-05-04 02:43:25,960 INFO [train.py:715] (3/8) Epoch 1, batch 32750, loss[loss=0.1874, simple_loss=0.2533, pruned_loss=0.06077, over 4792.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2432, pruned_loss=0.05731, over 971676.65 frames.], batch size: 24, lr: 8.03e-04
+2022-05-04 02:44:05,921 INFO [train.py:715] (3/8) Epoch 1, batch 32800, loss[loss=0.1961, simple_loss=0.2671, pruned_loss=0.06253, over 4925.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2438, pruned_loss=0.05719, over 972111.96 frames.], batch size: 39, lr: 8.02e-04
+2022-05-04 02:44:45,555 INFO [train.py:715] (3/8) Epoch 1, batch 32850, loss[loss=0.1841, simple_loss=0.2437, pruned_loss=0.06225, over 4753.00 frames.], tot_loss[loss=0.179, simple_loss=0.2438, pruned_loss=0.05707, over 972410.61 frames.], batch size: 16, lr: 8.02e-04
+2022-05-04 02:45:24,930 INFO [train.py:715] (3/8) Epoch 1, batch 32900, loss[loss=0.204, simple_loss=0.2605, pruned_loss=0.07376, over 4690.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2427, pruned_loss=0.05614, over 972161.16 frames.], batch size: 15, lr: 8.02e-04
+2022-05-04 02:46:04,177 INFO [train.py:715] (3/8) Epoch 1, batch 32950, loss[loss=0.191, simple_loss=0.2503, pruned_loss=0.06584, over 4932.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2426, pruned_loss=0.05603, over 972496.48 frames.], batch size: 21, lr: 8.02e-04
+2022-05-04 02:46:43,641 INFO [train.py:715] (3/8) Epoch 1, batch 33000, loss[loss=0.1585, simple_loss=0.2232, pruned_loss=0.04691, over 4981.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2427, pruned_loss=0.05616, over 972803.01 frames.], batch size: 24, lr: 8.01e-04
+2022-05-04 02:46:43,642 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 02:46:52,424 INFO [train.py:742] (3/8) Epoch 1, validation: loss=0.1208, simple_loss=0.2074, pruned_loss=0.01714, over 914524.00 frames.
+2022-05-04 02:47:32,100 INFO [train.py:715] (3/8) Epoch 1, batch 33050, loss[loss=0.157, simple_loss=0.2296, pruned_loss=0.04217, over 4824.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2434, pruned_loss=0.05668, over 972674.36 frames.], batch size: 15, lr: 8.01e-04
+2022-05-04 02:48:12,127 INFO [train.py:715] (3/8) Epoch 1, batch 33100, loss[loss=0.1402, simple_loss=0.2156, pruned_loss=0.03244, over 4987.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2433, pruned_loss=0.05651, over 973273.54 frames.], batch size: 14, lr: 8.01e-04
+2022-05-04 02:48:51,998 INFO [train.py:715] (3/8) Epoch 1, batch 33150, loss[loss=0.1832, simple_loss=0.2451, pruned_loss=0.06061, over 4979.00 frames.], tot_loss[loss=0.179, simple_loss=0.2437, pruned_loss=0.0571, over 972738.68 frames.], batch size: 28, lr: 8.00e-04
+2022-05-04 02:49:31,136 INFO [train.py:715] (3/8) Epoch 1, batch 33200, loss[loss=0.1743, simple_loss=0.2441, pruned_loss=0.05223, over 4881.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2431, pruned_loss=0.05687, over 973064.32 frames.], batch size: 22, lr: 8.00e-04
+2022-05-04 02:50:11,556 INFO [train.py:715] (3/8) Epoch 1, batch 33250, loss[loss=0.2425, simple_loss=0.2997, pruned_loss=0.09265, over 4897.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2433, pruned_loss=0.05718, over 973016.52 frames.], batch size: 19, lr: 8.00e-04
+2022-05-04 02:50:51,589 INFO [train.py:715] (3/8) Epoch 1, batch 33300, loss[loss=0.1505, simple_loss=0.2193, pruned_loss=0.04085, over 4949.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2438, pruned_loss=0.05695, over 972528.84 frames.], batch size: 35, lr: 8.00e-04
+2022-05-04 02:51:31,060 INFO [train.py:715] (3/8) Epoch 1, batch 33350, loss[loss=0.1718, simple_loss=0.2382, pruned_loss=0.05273, over 4990.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2431, pruned_loss=0.05664, over 972937.08 frames.], batch size: 25, lr: 7.99e-04
+2022-05-04 02:52:11,433 INFO [train.py:715] (3/8) Epoch 1, batch 33400, loss[loss=0.1604, simple_loss=0.2279, pruned_loss=0.04641, over 4947.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2426, pruned_loss=0.05634, over 971316.99 frames.], batch size: 29, lr: 7.99e-04
+2022-05-04 02:52:51,300 INFO [train.py:715] (3/8) Epoch 1, batch 33450, loss[loss=0.1739, simple_loss=0.2367, pruned_loss=0.05551, over 4770.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2428, pruned_loss=0.05588, over 972590.56 frames.], batch size: 14, lr: 7.99e-04
+2022-05-04 02:53:30,408 INFO [train.py:715] (3/8) Epoch 1, batch 33500, loss[loss=0.1907, simple_loss=0.2541, pruned_loss=0.0636, over 4865.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2443, pruned_loss=0.05673, over 971978.16 frames.], batch size: 22, lr: 7.98e-04
+2022-05-04 02:54:10,337 INFO [train.py:715] (3/8) Epoch 1, batch 33550, loss[loss=0.1647, simple_loss=0.2235, pruned_loss=0.05298, over 4830.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2446, pruned_loss=0.05717, over 971881.64 frames.], batch size: 30, lr: 7.98e-04
+2022-05-04 02:54:50,181 INFO [train.py:715] (3/8) Epoch 1, batch 33600, loss[loss=0.1968, simple_loss=0.263, pruned_loss=0.06528, over 4805.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2453, pruned_loss=0.05783, over 971180.37 frames.], batch size: 25, lr: 7.98e-04
+2022-05-04 02:55:29,606 INFO [train.py:715] (3/8) Epoch 1, batch 33650, loss[loss=0.1749, simple_loss=0.2421, pruned_loss=0.0539, over 4781.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2456, pruned_loss=0.05771, over 971777.77 frames.], batch size: 17, lr: 7.97e-04
+2022-05-04 02:56:08,649 INFO [train.py:715] (3/8) Epoch 1, batch 33700, loss[loss=0.1731, simple_loss=0.2407, pruned_loss=0.05273, over 4984.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2444, pruned_loss=0.05689, over 971732.93 frames.], batch size: 28, lr: 7.97e-04
+2022-05-04 02:56:47,807 INFO [train.py:715] (3/8) Epoch 1, batch 33750, loss[loss=0.1533, simple_loss=0.2262, pruned_loss=0.04019, over 4864.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2431, pruned_loss=0.05677, over 972535.34 frames.], batch size: 30, lr: 7.97e-04
+2022-05-04 02:57:27,455 INFO [train.py:715] (3/8) Epoch 1, batch 33800, loss[loss=0.2436, simple_loss=0.2959, pruned_loss=0.09563, over 4842.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2433, pruned_loss=0.05728, over 972993.72 frames.], batch size: 32, lr: 7.97e-04
+2022-05-04 02:58:06,282 INFO [train.py:715] (3/8) Epoch 1, batch 33850, loss[loss=0.1778, simple_loss=0.2472, pruned_loss=0.05427, over 4830.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2435, pruned_loss=0.05713, over 972592.35 frames.], batch size: 15, lr: 7.96e-04
+2022-05-04 02:58:45,801 INFO [train.py:715] (3/8) Epoch 1, batch 33900, loss[loss=0.1528, simple_loss=0.2265, pruned_loss=0.03958, over 4946.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2437, pruned_loss=0.05678, over 973131.36 frames.], batch size: 24, lr: 7.96e-04
+2022-05-04 02:59:25,366 INFO [train.py:715] (3/8) Epoch 1, batch 33950, loss[loss=0.1698, simple_loss=0.2517, pruned_loss=0.04396, over 4881.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2436, pruned_loss=0.05653, over 973863.97 frames.], batch size: 22, lr: 7.96e-04
+2022-05-04 03:00:05,090 INFO [train.py:715] (3/8) Epoch 1, batch 34000, loss[loss=0.1649, simple_loss=0.2405, pruned_loss=0.04472, over 4843.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2428, pruned_loss=0.05643, over 973323.40 frames.], batch size: 15, lr: 7.95e-04
+2022-05-04 03:00:44,412 INFO [train.py:715] (3/8) Epoch 1, batch 34050, loss[loss=0.1886, simple_loss=0.2509, pruned_loss=0.06313, over 4925.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2433, pruned_loss=0.05667, over 973042.07 frames.], batch size: 18, lr: 7.95e-04
+2022-05-04 03:01:23,795 INFO [train.py:715] (3/8) Epoch 1, batch 34100, loss[loss=0.1646, simple_loss=0.2304, pruned_loss=0.04945, over 4800.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2442, pruned_loss=0.05754, over 973308.49 frames.], batch size: 17, lr: 7.95e-04
+2022-05-04 03:02:03,180 INFO [train.py:715] (3/8) Epoch 1, batch 34150, loss[loss=0.1757, simple_loss=0.2414, pruned_loss=0.05506, over 4832.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2426, pruned_loss=0.05653, over 972992.60 frames.], batch size: 15, lr: 7.95e-04
+2022-05-04 03:02:42,211 INFO [train.py:715] (3/8) Epoch 1, batch 34200, loss[loss=0.1872, simple_loss=0.255, pruned_loss=0.05972, over 4956.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2428, pruned_loss=0.05631, over 973662.30 frames.], batch size: 23, lr: 7.94e-04
+2022-05-04 03:03:21,756 INFO [train.py:715] (3/8) Epoch 1, batch 34250, loss[loss=0.1375, simple_loss=0.2147, pruned_loss=0.0302, over 4815.00 frames.], tot_loss[loss=0.1779, simple_loss=0.243, pruned_loss=0.05643, over 973684.09 frames.], batch size: 26, lr: 7.94e-04
+2022-05-04 03:04:01,436 INFO [train.py:715] (3/8) Epoch 1, batch 34300, loss[loss=0.1941, simple_loss=0.2559, pruned_loss=0.06611, over 4894.00 frames.], tot_loss[loss=0.178, simple_loss=0.2432, pruned_loss=0.05644, over 973438.72 frames.], batch size: 22, lr: 7.94e-04
+2022-05-04 03:04:40,846 INFO [train.py:715] (3/8) Epoch 1, batch 34350, loss[loss=0.1708, simple_loss=0.2392, pruned_loss=0.05122, over 4903.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2429, pruned_loss=0.05619, over 972846.20 frames.], batch size: 17, lr: 7.93e-04
+2022-05-04 03:05:19,751 INFO [train.py:715] (3/8) Epoch 1, batch 34400, loss[loss=0.1554, simple_loss=0.2252, pruned_loss=0.04281, over 4882.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2434, pruned_loss=0.05645, over 972809.16 frames.], batch size: 16, lr: 7.93e-04
+2022-05-04 03:05:59,256 INFO [train.py:715] (3/8) Epoch 1, batch 34450, loss[loss=0.1552, simple_loss=0.2225, pruned_loss=0.04394, over 4961.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2416, pruned_loss=0.05508, over 972621.44 frames.], batch size: 24, lr: 7.93e-04
+2022-05-04 03:06:38,479 INFO [train.py:715] (3/8) Epoch 1, batch 34500, loss[loss=0.1732, simple_loss=0.2406, pruned_loss=0.0529, over 4901.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2426, pruned_loss=0.05611, over 972538.87 frames.], batch size: 19, lr: 7.93e-04
+2022-05-04 03:07:17,763 INFO [train.py:715] (3/8) Epoch 1, batch 34550, loss[loss=0.165, simple_loss=0.2475, pruned_loss=0.04124, over 4947.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2434, pruned_loss=0.05671, over 972025.39 frames.], batch size: 23, lr: 7.92e-04
+2022-05-04 03:07:57,340 INFO [train.py:715] (3/8) Epoch 1, batch 34600, loss[loss=0.1516, simple_loss=0.2306, pruned_loss=0.03624, over 4905.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2437, pruned_loss=0.0566, over 972901.06 frames.], batch size: 23, lr: 7.92e-04
+2022-05-04 03:08:37,227 INFO [train.py:715] (3/8) Epoch 1, batch 34650, loss[loss=0.1508, simple_loss=0.227, pruned_loss=0.03726, over 4985.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2444, pruned_loss=0.05694, over 972483.77 frames.], batch size: 24, lr: 7.92e-04
+2022-05-04 03:09:17,428 INFO [train.py:715] (3/8) Epoch 1, batch 34700, loss[loss=0.1669, simple_loss=0.2455, pruned_loss=0.04416, over 4778.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2443, pruned_loss=0.05668, over 971786.16 frames.], batch size: 18, lr: 7.91e-04
+2022-05-04 03:09:55,738 INFO [train.py:715] (3/8) Epoch 1, batch 34750, loss[loss=0.1415, simple_loss=0.2118, pruned_loss=0.03565, over 4739.00 frames.], tot_loss[loss=0.178, simple_loss=0.2436, pruned_loss=0.05621, over 971532.64 frames.], batch size: 16, lr: 7.91e-04
+2022-05-04 03:10:32,243 INFO [train.py:715] (3/8) Epoch 1, batch 34800, loss[loss=0.1872, simple_loss=0.2567, pruned_loss=0.05887, over 4881.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2435, pruned_loss=0.05594, over 972069.33 frames.], batch size: 22, lr: 7.91e-04
+2022-05-04 03:11:25,704 INFO [train.py:715] (3/8) Epoch 2, batch 0, loss[loss=0.189, simple_loss=0.241, pruned_loss=0.06848, over 4884.00 frames.], tot_loss[loss=0.189, simple_loss=0.241, pruned_loss=0.06848, over 4884.00 frames.], batch size: 32, lr: 7.59e-04
+2022-05-04 03:12:05,764 INFO [train.py:715] (3/8) Epoch 2, batch 50, loss[loss=0.1776, simple_loss=0.2404, pruned_loss=0.05736, over 4792.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2416, pruned_loss=0.0554, over 219688.25 frames.], batch size: 17, lr: 7.59e-04
+2022-05-04 03:12:46,576 INFO [train.py:715] (3/8) Epoch 2, batch 100, loss[loss=0.1824, simple_loss=0.2501, pruned_loss=0.05732, over 4757.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2409, pruned_loss=0.05564, over 386786.42 frames.], batch size: 18, lr: 7.59e-04
+2022-05-04 03:13:27,210 INFO [train.py:715] (3/8) Epoch 2, batch 150, loss[loss=0.2563, simple_loss=0.3028, pruned_loss=0.1049, over 4842.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2409, pruned_loss=0.0557, over 516250.88 frames.], batch size: 26, lr: 7.59e-04
+2022-05-04 03:14:07,253 INFO [train.py:715] (3/8) Epoch 2, batch 200, loss[loss=0.1872, simple_loss=0.2462, pruned_loss=0.0641, over 4861.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2404, pruned_loss=0.05496, over 616987.43 frames.], batch size: 32, lr: 7.58e-04
+2022-05-04 03:14:48,041 INFO [train.py:715] (3/8) Epoch 2, batch 250, loss[loss=0.185, simple_loss=0.2502, pruned_loss=0.05994, over 4990.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2413, pruned_loss=0.05494, over 694880.12 frames.], batch size: 25, lr: 7.58e-04
+2022-05-04 03:15:29,357 INFO [train.py:715] (3/8) Epoch 2, batch 300, loss[loss=0.1468, simple_loss=0.2171, pruned_loss=0.03827, over 4970.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2411, pruned_loss=0.05456, over 756046.92 frames.], batch size: 33, lr: 7.58e-04
+2022-05-04 03:16:10,299 INFO [train.py:715] (3/8) Epoch 2, batch 350, loss[loss=0.216, simple_loss=0.282, pruned_loss=0.07502, over 4786.00 frames.], tot_loss[loss=0.1744, simple_loss=0.24, pruned_loss=0.05437, over 803271.93 frames.], batch size: 18, lr: 7.57e-04
+2022-05-04 03:16:49,965 INFO [train.py:715] (3/8) Epoch 2, batch 400, loss[loss=0.1648, simple_loss=0.2298, pruned_loss=0.0499, over 4804.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2396, pruned_loss=0.05436, over 840655.77 frames.], batch size: 24, lr: 7.57e-04
+2022-05-04 03:17:30,473 INFO [train.py:715] (3/8) Epoch 2, batch 450, loss[loss=0.1768, simple_loss=0.2572, pruned_loss=0.04821, over 4929.00 frames.], tot_loss[loss=0.1756, simple_loss=0.241, pruned_loss=0.05514, over 869180.81 frames.], batch size: 23, lr: 7.57e-04
+2022-05-04 03:18:11,614 INFO [train.py:715] (3/8) Epoch 2, batch 500, loss[loss=0.1864, simple_loss=0.2486, pruned_loss=0.06212, over 4811.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2407, pruned_loss=0.05512, over 892546.86 frames.], batch size: 27, lr: 7.57e-04
+2022-05-04 03:18:51,546 INFO [train.py:715] (3/8) Epoch 2, batch 550, loss[loss=0.1494, simple_loss=0.2162, pruned_loss=0.04134, over 4811.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2403, pruned_loss=0.05504, over 910487.42 frames.], batch size: 12, lr: 7.56e-04
+2022-05-04 03:19:31,910 INFO [train.py:715] (3/8) Epoch 2, batch 600, loss[loss=0.1904, simple_loss=0.2416, pruned_loss=0.06958, over 4869.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2412, pruned_loss=0.05556, over 924326.85 frames.], batch size: 22, lr: 7.56e-04
+2022-05-04 03:20:12,750 INFO [train.py:715] (3/8) Epoch 2, batch 650, loss[loss=0.1833, simple_loss=0.241, pruned_loss=0.06276, over 4916.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2404, pruned_loss=0.05486, over 935017.94 frames.], batch size: 39, lr: 7.56e-04
+2022-05-04 03:20:53,342 INFO [train.py:715] (3/8) Epoch 2, batch 700, loss[loss=0.1938, simple_loss=0.2572, pruned_loss=0.06516, over 4695.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2415, pruned_loss=0.05584, over 944055.68 frames.], batch size: 15, lr: 7.56e-04
+2022-05-04 03:21:32,897 INFO [train.py:715] (3/8) Epoch 2, batch 750, loss[loss=0.179, simple_loss=0.2436, pruned_loss=0.05719, over 4905.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2418, pruned_loss=0.05591, over 949237.77 frames.], batch size: 19, lr: 7.55e-04
+2022-05-04 03:22:13,340 INFO [train.py:715] (3/8) Epoch 2, batch 800, loss[loss=0.1802, simple_loss=0.2475, pruned_loss=0.0565, over 4930.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2418, pruned_loss=0.05539, over 954902.38 frames.], batch size: 29, lr: 7.55e-04
+2022-05-04 03:22:53,990 INFO [train.py:715] (3/8) Epoch 2, batch 850, loss[loss=0.1664, simple_loss=0.238, pruned_loss=0.0474, over 4685.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2422, pruned_loss=0.05565, over 958400.73 frames.], batch size: 15, lr: 7.55e-04
+2022-05-04 03:23:34,283 INFO [train.py:715] (3/8) Epoch 2, batch 900, loss[loss=0.1995, simple_loss=0.2603, pruned_loss=0.06931, over 4821.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2428, pruned_loss=0.05614, over 961365.67 frames.], batch size: 21, lr: 7.55e-04
+2022-05-04 03:24:14,705 INFO [train.py:715] (3/8) Epoch 2, batch 950, loss[loss=0.1402, simple_loss=0.2116, pruned_loss=0.0344, over 4814.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2409, pruned_loss=0.05478, over 963734.78 frames.], batch size: 25, lr: 7.54e-04
+2022-05-04 03:24:55,390 INFO [train.py:715] (3/8) Epoch 2, batch 1000, loss[loss=0.1713, simple_loss=0.2361, pruned_loss=0.05327, over 4908.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2412, pruned_loss=0.05504, over 965600.14 frames.], batch size: 19, lr: 7.54e-04
+2022-05-04 03:25:36,194 INFO [train.py:715] (3/8) Epoch 2, batch 1050, loss[loss=0.1612, simple_loss=0.2363, pruned_loss=0.04305, over 4991.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2412, pruned_loss=0.05526, over 967693.40 frames.], batch size: 15, lr: 7.54e-04
+2022-05-04 03:26:15,816 INFO [train.py:715] (3/8) Epoch 2, batch 1100, loss[loss=0.1515, simple_loss=0.2206, pruned_loss=0.04126, over 4960.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2419, pruned_loss=0.05563, over 969914.14 frames.], batch size: 15, lr: 7.53e-04
+2022-05-04 03:26:56,294 INFO [train.py:715] (3/8) Epoch 2, batch 1150, loss[loss=0.1802, simple_loss=0.2413, pruned_loss=0.05956, over 4804.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2426, pruned_loss=0.05599, over 971054.13 frames.], batch size: 13, lr: 7.53e-04
+2022-05-04 03:27:37,629 INFO [train.py:715] (3/8) Epoch 2, batch 1200, loss[loss=0.1599, simple_loss=0.2266, pruned_loss=0.04656, over 4840.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2418, pruned_loss=0.05546, over 970703.23 frames.], batch size: 30, lr: 7.53e-04
+2022-05-04 03:28:18,247 INFO [train.py:715] (3/8) Epoch 2, batch 1250, loss[loss=0.1743, simple_loss=0.2509, pruned_loss=0.04882, over 4866.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2409, pruned_loss=0.05488, over 970810.62 frames.], batch size: 20, lr: 7.53e-04
+2022-05-04 03:28:57,932 INFO [train.py:715] (3/8) Epoch 2, batch 1300, loss[loss=0.1802, simple_loss=0.2525, pruned_loss=0.05393, over 4905.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2419, pruned_loss=0.0555, over 970737.68 frames.], batch size: 17, lr: 7.52e-04
+2022-05-04 03:29:38,470 INFO [train.py:715] (3/8) Epoch 2, batch 1350, loss[loss=0.2102, simple_loss=0.2662, pruned_loss=0.07709, over 4771.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2418, pruned_loss=0.05602, over 970852.38 frames.], batch size: 17, lr: 7.52e-04
+2022-05-04 03:30:19,106 INFO [train.py:715] (3/8) Epoch 2, batch 1400, loss[loss=0.1709, simple_loss=0.2393, pruned_loss=0.05126, over 4807.00 frames.], tot_loss[loss=0.1771, simple_loss=0.242, pruned_loss=0.05611, over 971244.26 frames.], batch size: 25, lr: 7.52e-04
+2022-05-04 03:30:59,073 INFO [train.py:715] (3/8) Epoch 2, batch 1450, loss[loss=0.1888, simple_loss=0.2387, pruned_loss=0.06948, over 4825.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2421, pruned_loss=0.05586, over 972158.39 frames.], batch size: 26, lr: 7.52e-04
+2022-05-04 03:31:39,476 INFO [train.py:715] (3/8) Epoch 2, batch 1500, loss[loss=0.1758, simple_loss=0.2535, pruned_loss=0.04904, over 4785.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2423, pruned_loss=0.05598, over 972593.92 frames.], batch size: 17, lr: 7.51e-04
+2022-05-04 03:32:20,459 INFO [train.py:715] (3/8) Epoch 2, batch 1550, loss[loss=0.1782, simple_loss=0.2482, pruned_loss=0.05415, over 4921.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2407, pruned_loss=0.05524, over 972521.95 frames.], batch size: 18, lr: 7.51e-04
+2022-05-04 03:33:00,534 INFO [train.py:715] (3/8) Epoch 2, batch 1600, loss[loss=0.2199, simple_loss=0.2752, pruned_loss=0.0823, over 4902.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2413, pruned_loss=0.05561, over 972566.78 frames.], batch size: 39, lr: 7.51e-04
+2022-05-04 03:33:40,352 INFO [train.py:715] (3/8) Epoch 2, batch 1650, loss[loss=0.153, simple_loss=0.2173, pruned_loss=0.04432, over 4769.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2419, pruned_loss=0.056, over 972033.22 frames.], batch size: 14, lr: 7.51e-04
+2022-05-04 03:34:21,223 INFO [train.py:715] (3/8) Epoch 2, batch 1700, loss[loss=0.1819, simple_loss=0.2514, pruned_loss=0.05619, over 4922.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2418, pruned_loss=0.05589, over 972166.61 frames.], batch size: 29, lr: 7.50e-04
+2022-05-04 03:35:02,265 INFO [train.py:715] (3/8) Epoch 2, batch 1750, loss[loss=0.1425, simple_loss=0.2247, pruned_loss=0.03013, over 4699.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2408, pruned_loss=0.05529, over 971883.90 frames.], batch size: 15, lr: 7.50e-04
+2022-05-04 03:35:42,175 INFO [train.py:715] (3/8) Epoch 2, batch 1800, loss[loss=0.1259, simple_loss=0.2005, pruned_loss=0.0257, over 4810.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2404, pruned_loss=0.05547, over 971954.07 frames.], batch size: 13, lr: 7.50e-04
+2022-05-04 03:36:22,537 INFO [train.py:715] (3/8) Epoch 2, batch 1850, loss[loss=0.1749, simple_loss=0.2457, pruned_loss=0.05202, over 4899.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2413, pruned_loss=0.05602, over 971754.02 frames.], batch size: 23, lr: 7.50e-04
+2022-05-04 03:37:03,508 INFO [train.py:715] (3/8) Epoch 2, batch 1900, loss[loss=0.1686, simple_loss=0.2375, pruned_loss=0.04987, over 4981.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2405, pruned_loss=0.05509, over 972025.39 frames.], batch size: 25, lr: 7.49e-04
+2022-05-04 03:37:44,292 INFO [train.py:715] (3/8) Epoch 2, batch 1950, loss[loss=0.1813, simple_loss=0.2482, pruned_loss=0.0572, over 4876.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2411, pruned_loss=0.05522, over 973442.35 frames.], batch size: 22, lr: 7.49e-04
+2022-05-04 03:38:24,089 INFO [train.py:715] (3/8) Epoch 2, batch 2000, loss[loss=0.1926, simple_loss=0.2551, pruned_loss=0.06507, over 4920.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2409, pruned_loss=0.05528, over 973582.19 frames.], batch size: 23, lr: 7.49e-04
+2022-05-04 03:39:04,254 INFO [train.py:715] (3/8) Epoch 2, batch 2050, loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03845, over 4912.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2422, pruned_loss=0.05612, over 974514.46 frames.], batch size: 23, lr: 7.48e-04
+2022-05-04 03:39:45,382 INFO [train.py:715] (3/8) Epoch 2, batch 2100, loss[loss=0.1748, simple_loss=0.2408, pruned_loss=0.05444, over 4754.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2422, pruned_loss=0.05649, over 973886.65 frames.], batch size: 16, lr: 7.48e-04
+2022-05-04 03:40:25,358 INFO [train.py:715] (3/8) Epoch 2, batch 2150, loss[loss=0.1798, simple_loss=0.2359, pruned_loss=0.06186, over 4916.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2414, pruned_loss=0.05584, over 973265.75 frames.], batch size: 17, lr: 7.48e-04
+2022-05-04 03:41:04,882 INFO [train.py:715] (3/8) Epoch 2, batch 2200, loss[loss=0.1925, simple_loss=0.2579, pruned_loss=0.06355, over 4983.00 frames.], tot_loss[loss=0.1761, simple_loss=0.241, pruned_loss=0.05556, over 973004.25 frames.], batch size: 35, lr: 7.48e-04
+2022-05-04 03:41:45,605 INFO [train.py:715] (3/8) Epoch 2, batch 2250, loss[loss=0.155, simple_loss=0.2247, pruned_loss=0.04265, over 4850.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2403, pruned_loss=0.05507, over 972780.00 frames.], batch size: 20, lr: 7.47e-04
+2022-05-04 03:42:26,407 INFO [train.py:715] (3/8) Epoch 2, batch 2300, loss[loss=0.1796, simple_loss=0.2393, pruned_loss=0.05994, over 4763.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2411, pruned_loss=0.05556, over 972395.28 frames.], batch size: 19, lr: 7.47e-04
+2022-05-04 03:43:05,608 INFO [train.py:715] (3/8) Epoch 2, batch 2350, loss[loss=0.1562, simple_loss=0.2269, pruned_loss=0.04271, over 4978.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2416, pruned_loss=0.05556, over 973290.59 frames.], batch size: 28, lr: 7.47e-04
+2022-05-04 03:43:48,322 INFO [train.py:715] (3/8) Epoch 2, batch 2400, loss[loss=0.1632, simple_loss=0.2428, pruned_loss=0.04175, over 4742.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2409, pruned_loss=0.05505, over 972919.96 frames.], batch size: 19, lr: 7.47e-04
+2022-05-04 03:44:29,312 INFO [train.py:715] (3/8) Epoch 2, batch 2450, loss[loss=0.187, simple_loss=0.254, pruned_loss=0.06001, over 4966.00 frames.], tot_loss[loss=0.1743, simple_loss=0.24, pruned_loss=0.05434, over 972044.71 frames.], batch size: 24, lr: 7.46e-04
+2022-05-04 03:45:09,454 INFO [train.py:715] (3/8) Epoch 2, batch 2500, loss[loss=0.1841, simple_loss=0.245, pruned_loss=0.06166, over 4800.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2395, pruned_loss=0.05414, over 972339.24 frames.], batch size: 25, lr: 7.46e-04
+2022-05-04 03:45:49,044 INFO [train.py:715] (3/8) Epoch 2, batch 2550, loss[loss=0.1686, simple_loss=0.2497, pruned_loss=0.04372, over 4990.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2392, pruned_loss=0.05387, over 973044.17 frames.], batch size: 25, lr: 7.46e-04
+2022-05-04 03:46:29,870 INFO [train.py:715] (3/8) Epoch 2, batch 2600, loss[loss=0.2158, simple_loss=0.2745, pruned_loss=0.07851, over 4789.00 frames.], tot_loss[loss=0.1735, simple_loss=0.239, pruned_loss=0.05402, over 973436.69 frames.], batch size: 21, lr: 7.46e-04
+2022-05-04 03:47:10,389 INFO [train.py:715] (3/8) Epoch 2, batch 2650, loss[loss=0.1767, simple_loss=0.236, pruned_loss=0.05868, over 4861.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2397, pruned_loss=0.05444, over 973461.65 frames.], batch size: 15, lr: 7.45e-04
+2022-05-04 03:47:49,288 INFO [train.py:715] (3/8) Epoch 2, batch 2700, loss[loss=0.1545, simple_loss=0.2176, pruned_loss=0.04569, over 4818.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2391, pruned_loss=0.05412, over 973073.22 frames.], batch size: 13, lr: 7.45e-04
+2022-05-04 03:48:29,304 INFO [train.py:715] (3/8) Epoch 2, batch 2750, loss[loss=0.1615, simple_loss=0.2278, pruned_loss=0.04756, over 4914.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2398, pruned_loss=0.05404, over 974063.16 frames.], batch size: 29, lr: 7.45e-04
+2022-05-04 03:49:10,353 INFO [train.py:715] (3/8) Epoch 2, batch 2800, loss[loss=0.1637, simple_loss=0.24, pruned_loss=0.04376, over 4786.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2403, pruned_loss=0.05432, over 973361.34 frames.], batch size: 14, lr: 7.45e-04
+2022-05-04 03:49:50,284 INFO [train.py:715] (3/8) Epoch 2, batch 2850, loss[loss=0.1677, simple_loss=0.2366, pruned_loss=0.04939, over 4895.00 frames.], tot_loss[loss=0.175, simple_loss=0.2405, pruned_loss=0.05477, over 973571.00 frames.], batch size: 19, lr: 7.44e-04
+2022-05-04 03:50:29,537 INFO [train.py:715] (3/8) Epoch 2, batch 2900, loss[loss=0.1679, simple_loss=0.2336, pruned_loss=0.05106, over 4788.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2415, pruned_loss=0.05557, over 973797.08 frames.], batch size: 14, lr: 7.44e-04
+2022-05-04 03:51:09,900 INFO [train.py:715] (3/8) Epoch 2, batch 2950, loss[loss=0.2004, simple_loss=0.2595, pruned_loss=0.07069, over 4702.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2411, pruned_loss=0.05578, over 973519.51 frames.], batch size: 15, lr: 7.44e-04
+2022-05-04 03:51:50,605 INFO [train.py:715] (3/8) Epoch 2, batch 3000, loss[loss=0.1952, simple_loss=0.2573, pruned_loss=0.06652, over 4983.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2415, pruned_loss=0.05566, over 974036.96 frames.], batch size: 14, lr: 7.44e-04
+2022-05-04 03:51:50,606 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 03:52:00,001 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1191, simple_loss=0.2058, pruned_loss=0.01615, over 914524.00 frames.
+2022-05-04 03:52:40,623 INFO [train.py:715] (3/8) Epoch 2, batch 3050, loss[loss=0.209, simple_loss=0.2554, pruned_loss=0.08127, over 4690.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2423, pruned_loss=0.05595, over 973142.85 frames.], batch size: 15, lr: 7.43e-04
+2022-05-04 03:53:19,873 INFO [train.py:715] (3/8) Epoch 2, batch 3100, loss[loss=0.1703, simple_loss=0.2404, pruned_loss=0.05007, over 4789.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2405, pruned_loss=0.05465, over 973357.80 frames.], batch size: 21, lr: 7.43e-04
+2022-05-04 03:53:59,881 INFO [train.py:715] (3/8) Epoch 2, batch 3150, loss[loss=0.1615, simple_loss=0.2165, pruned_loss=0.05321, over 4773.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2405, pruned_loss=0.05455, over 972721.10 frames.], batch size: 12, lr: 7.43e-04
+2022-05-04 03:54:40,145 INFO [train.py:715] (3/8) Epoch 2, batch 3200, loss[loss=0.2086, simple_loss=0.2729, pruned_loss=0.07211, over 4888.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2404, pruned_loss=0.05463, over 972496.23 frames.], batch size: 19, lr: 7.43e-04
+2022-05-04 03:55:19,788 INFO [train.py:715] (3/8) Epoch 2, batch 3250, loss[loss=0.1651, simple_loss=0.2241, pruned_loss=0.05309, over 4782.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2398, pruned_loss=0.05418, over 972569.03 frames.], batch size: 14, lr: 7.42e-04
+2022-05-04 03:55:59,348 INFO [train.py:715] (3/8) Epoch 2, batch 3300, loss[loss=0.1505, simple_loss=0.2105, pruned_loss=0.04522, over 4969.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2405, pruned_loss=0.05464, over 972435.88 frames.], batch size: 25, lr: 7.42e-04
+2022-05-04 03:56:39,591 INFO [train.py:715] (3/8) Epoch 2, batch 3350, loss[loss=0.2214, simple_loss=0.283, pruned_loss=0.07993, over 4783.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2418, pruned_loss=0.0554, over 972772.72 frames.], batch size: 17, lr: 7.42e-04
+2022-05-04 03:57:20,110 INFO [train.py:715] (3/8) Epoch 2, batch 3400, loss[loss=0.168, simple_loss=0.2372, pruned_loss=0.04944, over 4846.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2418, pruned_loss=0.05486, over 972282.26 frames.], batch size: 32, lr: 7.42e-04
+2022-05-04 03:57:58,925 INFO [train.py:715] (3/8) Epoch 2, batch 3450, loss[loss=0.1804, simple_loss=0.2443, pruned_loss=0.05823, over 4693.00 frames.], tot_loss[loss=0.176, simple_loss=0.2419, pruned_loss=0.05509, over 972411.70 frames.], batch size: 15, lr: 7.41e-04
+2022-05-04 03:58:38,951 INFO [train.py:715] (3/8) Epoch 2, batch 3500, loss[loss=0.1521, simple_loss=0.2106, pruned_loss=0.04678, over 4640.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2413, pruned_loss=0.05513, over 972327.42 frames.], batch size: 13, lr: 7.41e-04
+2022-05-04 03:59:19,007 INFO [train.py:715] (3/8) Epoch 2, batch 3550, loss[loss=0.1613, simple_loss=0.2374, pruned_loss=0.04258, over 4812.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2406, pruned_loss=0.05452, over 973085.11 frames.], batch size: 26, lr: 7.41e-04
+2022-05-04 03:59:58,774 INFO [train.py:715] (3/8) Epoch 2, batch 3600, loss[loss=0.1806, simple_loss=0.2428, pruned_loss=0.05919, over 4826.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2409, pruned_loss=0.05505, over 972460.61 frames.], batch size: 26, lr: 7.41e-04
+2022-05-04 04:00:37,774 INFO [train.py:715] (3/8) Epoch 2, batch 3650, loss[loss=0.1733, simple_loss=0.2434, pruned_loss=0.05153, over 4926.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2403, pruned_loss=0.05494, over 972982.43 frames.], batch size: 21, lr: 7.40e-04
+2022-05-04 04:01:18,177 INFO [train.py:715] (3/8) Epoch 2, batch 3700, loss[loss=0.163, simple_loss=0.2314, pruned_loss=0.04734, over 4771.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2404, pruned_loss=0.05486, over 972537.33 frames.], batch size: 14, lr: 7.40e-04
+2022-05-04 04:01:58,349 INFO [train.py:715] (3/8) Epoch 2, batch 3750, loss[loss=0.2327, simple_loss=0.2808, pruned_loss=0.09233, over 4874.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2404, pruned_loss=0.05485, over 972732.35 frames.], batch size: 32, lr: 7.40e-04
+2022-05-04 04:02:37,082 INFO [train.py:715] (3/8) Epoch 2, batch 3800, loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03777, over 4846.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2405, pruned_loss=0.05482, over 972536.49 frames.], batch size: 13, lr: 7.40e-04
+2022-05-04 04:03:17,274 INFO [train.py:715] (3/8) Epoch 2, batch 3850, loss[loss=0.159, simple_loss=0.2268, pruned_loss=0.04561, over 4942.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2402, pruned_loss=0.05516, over 973006.13 frames.], batch size: 23, lr: 7.39e-04
+2022-05-04 04:03:57,612 INFO [train.py:715] (3/8) Epoch 2, batch 3900, loss[loss=0.1981, simple_loss=0.2537, pruned_loss=0.07121, over 4933.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2408, pruned_loss=0.05529, over 972468.77 frames.], batch size: 23, lr: 7.39e-04
+2022-05-04 04:04:36,855 INFO [train.py:715] (3/8) Epoch 2, batch 3950, loss[loss=0.1475, simple_loss=0.2264, pruned_loss=0.03434, over 4970.00 frames.], tot_loss[loss=0.175, simple_loss=0.24, pruned_loss=0.05504, over 973278.95 frames.], batch size: 24, lr: 7.39e-04
+2022-05-04 04:05:16,461 INFO [train.py:715] (3/8) Epoch 2, batch 4000, loss[loss=0.128, simple_loss=0.1932, pruned_loss=0.03143, over 4794.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2399, pruned_loss=0.05475, over 973803.79 frames.], batch size: 12, lr: 7.39e-04
+2022-05-04 04:05:57,028 INFO [train.py:715] (3/8) Epoch 2, batch 4050, loss[loss=0.1752, simple_loss=0.2395, pruned_loss=0.05546, over 4969.00 frames.], tot_loss[loss=0.1742, simple_loss=0.24, pruned_loss=0.05423, over 973956.33 frames.], batch size: 15, lr: 7.38e-04
+2022-05-04 04:06:37,521 INFO [train.py:715] (3/8) Epoch 2, batch 4100, loss[loss=0.1734, simple_loss=0.2424, pruned_loss=0.05218, over 4908.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2404, pruned_loss=0.05433, over 974139.02 frames.], batch size: 18, lr: 7.38e-04
+2022-05-04 04:07:16,026 INFO [train.py:715] (3/8) Epoch 2, batch 4150, loss[loss=0.1619, simple_loss=0.2377, pruned_loss=0.04305, over 4931.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2414, pruned_loss=0.0551, over 974033.59 frames.], batch size: 29, lr: 7.38e-04
+2022-05-04 04:07:55,387 INFO [train.py:715] (3/8) Epoch 2, batch 4200, loss[loss=0.1634, simple_loss=0.2249, pruned_loss=0.05093, over 4920.00 frames.], tot_loss[loss=0.1751, simple_loss=0.241, pruned_loss=0.05456, over 973820.74 frames.], batch size: 18, lr: 7.38e-04
+2022-05-04 04:08:35,832 INFO [train.py:715] (3/8) Epoch 2, batch 4250, loss[loss=0.1778, simple_loss=0.2424, pruned_loss=0.05662, over 4929.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2413, pruned_loss=0.05482, over 973225.09 frames.], batch size: 23, lr: 7.37e-04
+2022-05-04 04:09:15,087 INFO [train.py:715] (3/8) Epoch 2, batch 4300, loss[loss=0.186, simple_loss=0.2547, pruned_loss=0.05862, over 4784.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2413, pruned_loss=0.05463, over 972504.34 frames.], batch size: 14, lr: 7.37e-04
+2022-05-04 04:09:54,870 INFO [train.py:715] (3/8) Epoch 2, batch 4350, loss[loss=0.1787, simple_loss=0.2456, pruned_loss=0.05588, over 4877.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2409, pruned_loss=0.05485, over 972528.39 frames.], batch size: 38, lr: 7.37e-04
+2022-05-04 04:10:34,719 INFO [train.py:715] (3/8) Epoch 2, batch 4400, loss[loss=0.1889, simple_loss=0.2375, pruned_loss=0.07019, over 4870.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2405, pruned_loss=0.05466, over 972180.22 frames.], batch size: 16, lr: 7.37e-04
+2022-05-04 04:11:14,736 INFO [train.py:715] (3/8) Epoch 2, batch 4450, loss[loss=0.1783, simple_loss=0.239, pruned_loss=0.05879, over 4969.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2404, pruned_loss=0.05458, over 972734.73 frames.], batch size: 35, lr: 7.36e-04
+2022-05-04 04:11:53,898 INFO [train.py:715] (3/8) Epoch 2, batch 4500, loss[loss=0.1513, simple_loss=0.2282, pruned_loss=0.03719, over 4764.00 frames.], tot_loss[loss=0.1746, simple_loss=0.24, pruned_loss=0.05457, over 973138.57 frames.], batch size: 19, lr: 7.36e-04
+2022-05-04 04:12:33,894 INFO [train.py:715] (3/8) Epoch 2, batch 4550, loss[loss=0.1553, simple_loss=0.2317, pruned_loss=0.0394, over 4892.00 frames.], tot_loss[loss=0.174, simple_loss=0.2398, pruned_loss=0.05414, over 973426.56 frames.], batch size: 22, lr: 7.36e-04
+2022-05-04 04:13:14,657 INFO [train.py:715] (3/8) Epoch 2, batch 4600, loss[loss=0.1472, simple_loss=0.2118, pruned_loss=0.04131, over 4802.00 frames.], tot_loss[loss=0.174, simple_loss=0.2396, pruned_loss=0.05422, over 973678.90 frames.], batch size: 21, lr: 7.36e-04
+2022-05-04 04:13:53,695 INFO [train.py:715] (3/8) Epoch 2, batch 4650, loss[loss=0.1828, simple_loss=0.2507, pruned_loss=0.05745, over 4929.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2411, pruned_loss=0.05458, over 974197.87 frames.], batch size: 29, lr: 7.35e-04
+2022-05-04 04:14:33,000 INFO [train.py:715] (3/8) Epoch 2, batch 4700, loss[loss=0.2356, simple_loss=0.3073, pruned_loss=0.08195, over 4835.00 frames.], tot_loss[loss=0.175, simple_loss=0.241, pruned_loss=0.05447, over 973198.99 frames.], batch size: 15, lr: 7.35e-04
+2022-05-04 04:15:13,200 INFO [train.py:715] (3/8) Epoch 2, batch 4750, loss[loss=0.1553, simple_loss=0.2272, pruned_loss=0.04167, over 4971.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2405, pruned_loss=0.05431, over 973003.99 frames.], batch size: 28, lr: 7.35e-04
+2022-05-04 04:15:53,744 INFO [train.py:715] (3/8) Epoch 2, batch 4800, loss[loss=0.1277, simple_loss=0.1994, pruned_loss=0.02797, over 4826.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2407, pruned_loss=0.05395, over 973170.39 frames.], batch size: 26, lr: 7.35e-04
+2022-05-04 04:16:33,019 INFO [train.py:715] (3/8) Epoch 2, batch 4850, loss[loss=0.225, simple_loss=0.2819, pruned_loss=0.08403, over 4846.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2413, pruned_loss=0.05429, over 973155.74 frames.], batch size: 34, lr: 7.34e-04
+2022-05-04 04:17:12,478 INFO [train.py:715] (3/8) Epoch 2, batch 4900, loss[loss=0.1428, simple_loss=0.2212, pruned_loss=0.03216, over 4791.00 frames.], tot_loss[loss=0.1741, simple_loss=0.24, pruned_loss=0.05413, over 972255.13 frames.], batch size: 18, lr: 7.34e-04
+2022-05-04 04:17:52,945 INFO [train.py:715] (3/8) Epoch 2, batch 4950, loss[loss=0.1417, simple_loss=0.1998, pruned_loss=0.04179, over 4695.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2398, pruned_loss=0.05444, over 972575.22 frames.], batch size: 15, lr: 7.34e-04
+2022-05-04 04:18:32,534 INFO [train.py:715] (3/8) Epoch 2, batch 5000, loss[loss=0.1953, simple_loss=0.2643, pruned_loss=0.06318, over 4780.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2406, pruned_loss=0.05513, over 972532.31 frames.], batch size: 17, lr: 7.34e-04
+2022-05-04 04:19:12,095 INFO [train.py:715] (3/8) Epoch 2, batch 5050, loss[loss=0.1792, simple_loss=0.2459, pruned_loss=0.05628, over 4990.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2417, pruned_loss=0.05556, over 971774.02 frames.], batch size: 14, lr: 7.33e-04
+2022-05-04 04:19:53,167 INFO [train.py:715] (3/8) Epoch 2, batch 5100, loss[loss=0.1912, simple_loss=0.2458, pruned_loss=0.06835, over 4915.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2416, pruned_loss=0.05542, over 971851.61 frames.], batch size: 23, lr: 7.33e-04
+2022-05-04 04:20:34,130 INFO [train.py:715] (3/8) Epoch 2, batch 5150, loss[loss=0.1539, simple_loss=0.2254, pruned_loss=0.04122, over 4982.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2409, pruned_loss=0.05467, over 971994.34 frames.], batch size: 28, lr: 7.33e-04
+2022-05-04 04:21:13,066 INFO [train.py:715] (3/8) Epoch 2, batch 5200, loss[loss=0.1801, simple_loss=0.2497, pruned_loss=0.05524, over 4841.00 frames.], tot_loss[loss=0.1764, simple_loss=0.242, pruned_loss=0.05541, over 971353.95 frames.], batch size: 30, lr: 7.33e-04
+2022-05-04 04:21:52,851 INFO [train.py:715] (3/8) Epoch 2, batch 5250, loss[loss=0.1917, simple_loss=0.2542, pruned_loss=0.06459, over 4845.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2415, pruned_loss=0.05505, over 971785.27 frames.], batch size: 30, lr: 7.32e-04
+2022-05-04 04:22:33,065 INFO [train.py:715] (3/8) Epoch 2, batch 5300, loss[loss=0.1631, simple_loss=0.2332, pruned_loss=0.04654, over 4772.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2413, pruned_loss=0.05465, over 972084.76 frames.], batch size: 14, lr: 7.32e-04
+2022-05-04 04:23:12,242 INFO [train.py:715] (3/8) Epoch 2, batch 5350, loss[loss=0.1499, simple_loss=0.2124, pruned_loss=0.04368, over 4781.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2405, pruned_loss=0.05441, over 972408.47 frames.], batch size: 17, lr: 7.32e-04
+2022-05-04 04:23:51,624 INFO [train.py:715] (3/8) Epoch 2, batch 5400, loss[loss=0.1688, simple_loss=0.2409, pruned_loss=0.04833, over 4979.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2401, pruned_loss=0.054, over 973228.12 frames.], batch size: 39, lr: 7.32e-04
+2022-05-04 04:24:32,283 INFO [train.py:715] (3/8) Epoch 2, batch 5450, loss[loss=0.1672, simple_loss=0.2326, pruned_loss=0.05084, over 4907.00 frames.], tot_loss[loss=0.174, simple_loss=0.2403, pruned_loss=0.05383, over 972516.74 frames.], batch size: 19, lr: 7.31e-04
+2022-05-04 04:25:12,072 INFO [train.py:715] (3/8) Epoch 2, batch 5500, loss[loss=0.1709, simple_loss=0.2439, pruned_loss=0.04898, over 4977.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2409, pruned_loss=0.05472, over 971651.82 frames.], batch size: 25, lr: 7.31e-04
+2022-05-04 04:25:51,708 INFO [train.py:715] (3/8) Epoch 2, batch 5550, loss[loss=0.1567, simple_loss=0.2178, pruned_loss=0.04776, over 4835.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2418, pruned_loss=0.05543, over 972386.95 frames.], batch size: 30, lr: 7.31e-04
+2022-05-04 04:26:32,205 INFO [train.py:715] (3/8) Epoch 2, batch 5600, loss[loss=0.1889, simple_loss=0.2525, pruned_loss=0.06268, over 4833.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2415, pruned_loss=0.05468, over 972454.11 frames.], batch size: 26, lr: 7.31e-04
+2022-05-04 04:27:13,268 INFO [train.py:715] (3/8) Epoch 2, batch 5650, loss[loss=0.1926, simple_loss=0.2525, pruned_loss=0.06631, over 4897.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2411, pruned_loss=0.05453, over 972749.72 frames.], batch size: 17, lr: 7.30e-04
+2022-05-04 04:27:53,176 INFO [train.py:715] (3/8) Epoch 2, batch 5700, loss[loss=0.1493, simple_loss=0.2163, pruned_loss=0.04116, over 4975.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2411, pruned_loss=0.05478, over 972940.36 frames.], batch size: 24, lr: 7.30e-04
+2022-05-04 04:28:33,027 INFO [train.py:715] (3/8) Epoch 2, batch 5750, loss[loss=0.1664, simple_loss=0.2284, pruned_loss=0.05217, over 4829.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2403, pruned_loss=0.05395, over 972146.78 frames.], batch size: 25, lr: 7.30e-04
+2022-05-04 04:29:13,947 INFO [train.py:715] (3/8) Epoch 2, batch 5800, loss[loss=0.2117, simple_loss=0.2707, pruned_loss=0.07632, over 4910.00 frames.], tot_loss[loss=0.173, simple_loss=0.2392, pruned_loss=0.05344, over 972318.73 frames.], batch size: 17, lr: 7.30e-04
+2022-05-04 04:29:55,117 INFO [train.py:715] (3/8) Epoch 2, batch 5850, loss[loss=0.1939, simple_loss=0.255, pruned_loss=0.06638, over 4860.00 frames.], tot_loss[loss=0.1718, simple_loss=0.238, pruned_loss=0.05278, over 972528.99 frames.], batch size: 20, lr: 7.29e-04
+2022-05-04 04:30:34,548 INFO [train.py:715] (3/8) Epoch 2, batch 5900, loss[loss=0.1747, simple_loss=0.2417, pruned_loss=0.05389, over 4802.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2381, pruned_loss=0.0532, over 972299.71 frames.], batch size: 24, lr: 7.29e-04
+2022-05-04 04:31:15,144 INFO [train.py:715] (3/8) Epoch 2, batch 5950, loss[loss=0.1621, simple_loss=0.2253, pruned_loss=0.04942, over 4777.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2378, pruned_loss=0.05327, over 972090.30 frames.], batch size: 14, lr: 7.29e-04
+2022-05-04 04:31:56,154 INFO [train.py:715] (3/8) Epoch 2, batch 6000, loss[loss=0.1703, simple_loss=0.2267, pruned_loss=0.05697, over 4809.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2371, pruned_loss=0.05297, over 972310.04 frames.], batch size: 12, lr: 7.29e-04
+2022-05-04 04:31:56,154 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 04:32:04,807 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1188, simple_loss=0.2054, pruned_loss=0.01614, over 914524.00 frames.
+2022-05-04 04:32:46,155 INFO [train.py:715] (3/8) Epoch 2, batch 6050, loss[loss=0.1413, simple_loss=0.216, pruned_loss=0.03337, over 4775.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2381, pruned_loss=0.05322, over 972545.06 frames.], batch size: 18, lr: 7.29e-04
+2022-05-04 04:33:25,850 INFO [train.py:715] (3/8) Epoch 2, batch 6100, loss[loss=0.1672, simple_loss=0.2209, pruned_loss=0.05673, over 4980.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2384, pruned_loss=0.05358, over 972444.49 frames.], batch size: 24, lr: 7.28e-04
+2022-05-04 04:34:05,820 INFO [train.py:715] (3/8) Epoch 2, batch 6150, loss[loss=0.1835, simple_loss=0.2562, pruned_loss=0.0554, over 4777.00 frames.], tot_loss[loss=0.174, simple_loss=0.2396, pruned_loss=0.05417, over 971970.97 frames.], batch size: 18, lr: 7.28e-04
+2022-05-04 04:34:46,208 INFO [train.py:715] (3/8) Epoch 2, batch 6200, loss[loss=0.1991, simple_loss=0.2589, pruned_loss=0.06967, over 4978.00 frames.], tot_loss[loss=0.1755, simple_loss=0.241, pruned_loss=0.05499, over 972043.49 frames.], batch size: 28, lr: 7.28e-04
+2022-05-04 04:35:26,628 INFO [train.py:715] (3/8) Epoch 2, batch 6250, loss[loss=0.2117, simple_loss=0.2692, pruned_loss=0.0771, over 4873.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2406, pruned_loss=0.05517, over 971532.81 frames.], batch size: 16, lr: 7.28e-04
+2022-05-04 04:36:05,782 INFO [train.py:715] (3/8) Epoch 2, batch 6300, loss[loss=0.1854, simple_loss=0.2574, pruned_loss=0.05667, over 4809.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2397, pruned_loss=0.05391, over 971092.75 frames.], batch size: 25, lr: 7.27e-04
+2022-05-04 04:36:46,023 INFO [train.py:715] (3/8) Epoch 2, batch 6350, loss[loss=0.1705, simple_loss=0.2392, pruned_loss=0.05088, over 4798.00 frames.], tot_loss[loss=0.173, simple_loss=0.2389, pruned_loss=0.05349, over 971076.40 frames.], batch size: 14, lr: 7.27e-04
+2022-05-04 04:37:26,523 INFO [train.py:715] (3/8) Epoch 2, batch 6400, loss[loss=0.1588, simple_loss=0.2258, pruned_loss=0.04587, over 4853.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2392, pruned_loss=0.054, over 971307.16 frames.], batch size: 20, lr: 7.27e-04
+2022-05-04 04:38:05,328 INFO [train.py:715] (3/8) Epoch 2, batch 6450, loss[loss=0.1801, simple_loss=0.2582, pruned_loss=0.05099, over 4917.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2405, pruned_loss=0.05481, over 971619.03 frames.], batch size: 23, lr: 7.27e-04
+2022-05-04 04:38:44,598 INFO [train.py:715] (3/8) Epoch 2, batch 6500, loss[loss=0.1908, simple_loss=0.2362, pruned_loss=0.07271, over 4975.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2393, pruned_loss=0.05396, over 972628.29 frames.], batch size: 14, lr: 7.26e-04
+2022-05-04 04:39:24,837 INFO [train.py:715] (3/8) Epoch 2, batch 6550, loss[loss=0.1585, simple_loss=0.2153, pruned_loss=0.05087, over 4864.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2401, pruned_loss=0.05437, over 972449.46 frames.], batch size: 13, lr: 7.26e-04
+2022-05-04 04:40:04,768 INFO [train.py:715] (3/8) Epoch 2, batch 6600, loss[loss=0.2156, simple_loss=0.2736, pruned_loss=0.07879, over 4956.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2407, pruned_loss=0.05454, over 972427.49 frames.], batch size: 15, lr: 7.26e-04
+2022-05-04 04:40:43,872 INFO [train.py:715] (3/8) Epoch 2, batch 6650, loss[loss=0.1639, simple_loss=0.2303, pruned_loss=0.04875, over 4817.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2416, pruned_loss=0.05505, over 972815.94 frames.], batch size: 26, lr: 7.26e-04
+2022-05-04 04:41:23,372 INFO [train.py:715] (3/8) Epoch 2, batch 6700, loss[loss=0.1225, simple_loss=0.1897, pruned_loss=0.02759, over 4886.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2412, pruned_loss=0.05497, over 972702.38 frames.], batch size: 12, lr: 7.25e-04
+2022-05-04 04:42:03,554 INFO [train.py:715] (3/8) Epoch 2, batch 6750, loss[loss=0.174, simple_loss=0.2368, pruned_loss=0.05562, over 4879.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2413, pruned_loss=0.05514, over 973310.56 frames.], batch size: 16, lr: 7.25e-04
+2022-05-04 04:42:41,718 INFO [train.py:715] (3/8) Epoch 2, batch 6800, loss[loss=0.1706, simple_loss=0.2451, pruned_loss=0.04802, over 4984.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2408, pruned_loss=0.0548, over 973707.26 frames.], batch size: 25, lr: 7.25e-04
+2022-05-04 04:43:20,945 INFO [train.py:715] (3/8) Epoch 2, batch 6850, loss[loss=0.1589, simple_loss=0.227, pruned_loss=0.04541, over 4867.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2409, pruned_loss=0.05447, over 973626.83 frames.], batch size: 16, lr: 7.25e-04
+2022-05-04 04:44:01,043 INFO [train.py:715] (3/8) Epoch 2, batch 6900, loss[loss=0.1794, simple_loss=0.2514, pruned_loss=0.05371, over 4834.00 frames.], tot_loss[loss=0.1752, simple_loss=0.241, pruned_loss=0.0547, over 973115.25 frames.], batch size: 27, lr: 7.24e-04
+2022-05-04 04:44:41,209 INFO [train.py:715] (3/8) Epoch 2, batch 6950, loss[loss=0.1608, simple_loss=0.2229, pruned_loss=0.04932, over 4751.00 frames.], tot_loss[loss=0.1747, simple_loss=0.241, pruned_loss=0.05425, over 972742.17 frames.], batch size: 16, lr: 7.24e-04
+2022-05-04 04:45:19,413 INFO [train.py:715] (3/8) Epoch 2, batch 7000, loss[loss=0.1586, simple_loss=0.2278, pruned_loss=0.04474, over 4782.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2408, pruned_loss=0.0543, over 973106.59 frames.], batch size: 17, lr: 7.24e-04
+2022-05-04 04:45:59,983 INFO [train.py:715] (3/8) Epoch 2, batch 7050, loss[loss=0.1588, simple_loss=0.2299, pruned_loss=0.0438, over 4762.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2396, pruned_loss=0.05327, over 972878.35 frames.], batch size: 18, lr: 7.24e-04
+2022-05-04 04:46:40,405 INFO [train.py:715] (3/8) Epoch 2, batch 7100, loss[loss=0.1716, simple_loss=0.2433, pruned_loss=0.04995, over 4820.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2408, pruned_loss=0.05423, over 972259.07 frames.], batch size: 15, lr: 7.24e-04
+2022-05-04 04:47:19,800 INFO [train.py:715] (3/8) Epoch 2, batch 7150, loss[loss=0.1544, simple_loss=0.2288, pruned_loss=0.04003, over 4945.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2409, pruned_loss=0.05443, over 972079.51 frames.], batch size: 23, lr: 7.23e-04
+2022-05-04 04:48:00,092 INFO [train.py:715] (3/8) Epoch 2, batch 7200, loss[loss=0.1742, simple_loss=0.2409, pruned_loss=0.05375, over 4887.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2408, pruned_loss=0.05407, over 971727.69 frames.], batch size: 22, lr: 7.23e-04
+2022-05-04 04:48:41,284 INFO [train.py:715] (3/8) Epoch 2, batch 7250, loss[loss=0.1855, simple_loss=0.2373, pruned_loss=0.06682, over 4897.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2397, pruned_loss=0.05377, over 972296.02 frames.], batch size: 19, lr: 7.23e-04
+2022-05-04 04:49:21,910 INFO [train.py:715] (3/8) Epoch 2, batch 7300, loss[loss=0.1765, simple_loss=0.24, pruned_loss=0.05653, over 4885.00 frames.], tot_loss[loss=0.175, simple_loss=0.2407, pruned_loss=0.05461, over 973114.31 frames.], batch size: 22, lr: 7.23e-04
+2022-05-04 04:50:01,627 INFO [train.py:715] (3/8) Epoch 2, batch 7350, loss[loss=0.1836, simple_loss=0.2431, pruned_loss=0.0621, over 4800.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2403, pruned_loss=0.05396, over 973087.09 frames.], batch size: 24, lr: 7.22e-04
+2022-05-04 04:50:42,535 INFO [train.py:715] (3/8) Epoch 2, batch 7400, loss[loss=0.1777, simple_loss=0.2333, pruned_loss=0.061, over 4978.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2408, pruned_loss=0.05468, over 973551.72 frames.], batch size: 14, lr: 7.22e-04
+2022-05-04 04:51:24,343 INFO [train.py:715] (3/8) Epoch 2, batch 7450, loss[loss=0.1504, simple_loss=0.2197, pruned_loss=0.04059, over 4797.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2407, pruned_loss=0.05436, over 974691.90 frames.], batch size: 12, lr: 7.22e-04
+2022-05-04 04:52:04,713 INFO [train.py:715] (3/8) Epoch 2, batch 7500, loss[loss=0.1605, simple_loss=0.2242, pruned_loss=0.04843, over 4915.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2399, pruned_loss=0.05397, over 974064.28 frames.], batch size: 19, lr: 7.22e-04
+2022-05-04 04:52:45,162 INFO [train.py:715] (3/8) Epoch 2, batch 7550, loss[loss=0.1626, simple_loss=0.2282, pruned_loss=0.04847, over 4848.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2396, pruned_loss=0.05391, over 973777.91 frames.], batch size: 32, lr: 7.21e-04
+2022-05-04 04:53:26,934 INFO [train.py:715] (3/8) Epoch 2, batch 7600, loss[loss=0.1721, simple_loss=0.2352, pruned_loss=0.05457, over 4871.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2397, pruned_loss=0.05379, over 973307.67 frames.], batch size: 32, lr: 7.21e-04
+2022-05-04 04:54:08,331 INFO [train.py:715] (3/8) Epoch 2, batch 7650, loss[loss=0.1831, simple_loss=0.2362, pruned_loss=0.06493, over 4824.00 frames.], tot_loss[loss=0.1741, simple_loss=0.24, pruned_loss=0.05407, over 973106.69 frames.], batch size: 13, lr: 7.21e-04
+2022-05-04 04:54:48,382 INFO [train.py:715] (3/8) Epoch 2, batch 7700, loss[loss=0.1652, simple_loss=0.2318, pruned_loss=0.04926, over 4819.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2406, pruned_loss=0.0544, over 972673.58 frames.], batch size: 13, lr: 7.21e-04
+2022-05-04 04:55:29,832 INFO [train.py:715] (3/8) Epoch 2, batch 7750, loss[loss=0.1656, simple_loss=0.2315, pruned_loss=0.04984, over 4855.00 frames.], tot_loss[loss=0.174, simple_loss=0.2401, pruned_loss=0.05393, over 973012.23 frames.], batch size: 20, lr: 7.21e-04
+2022-05-04 04:56:11,498 INFO [train.py:715] (3/8) Epoch 2, batch 7800, loss[loss=0.1889, simple_loss=0.2665, pruned_loss=0.05561, over 4853.00 frames.], tot_loss[loss=0.1739, simple_loss=0.24, pruned_loss=0.05389, over 972412.03 frames.], batch size: 32, lr: 7.20e-04
+2022-05-04 04:56:52,003 INFO [train.py:715] (3/8) Epoch 2, batch 7850, loss[loss=0.172, simple_loss=0.2384, pruned_loss=0.05281, over 4804.00 frames.], tot_loss[loss=0.1739, simple_loss=0.24, pruned_loss=0.0539, over 971663.78 frames.], batch size: 21, lr: 7.20e-04
+2022-05-04 04:57:33,357 INFO [train.py:715] (3/8) Epoch 2, batch 7900, loss[loss=0.1585, simple_loss=0.22, pruned_loss=0.04847, over 4784.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2403, pruned_loss=0.05418, over 971771.32 frames.], batch size: 18, lr: 7.20e-04
+2022-05-04 04:58:15,548 INFO [train.py:715] (3/8) Epoch 2, batch 7950, loss[loss=0.1885, simple_loss=0.2369, pruned_loss=0.07003, over 4900.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2414, pruned_loss=0.05516, over 972470.37 frames.], batch size: 17, lr: 7.20e-04
+2022-05-04 04:58:57,043 INFO [train.py:715] (3/8) Epoch 2, batch 8000, loss[loss=0.1728, simple_loss=0.235, pruned_loss=0.05526, over 4861.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2412, pruned_loss=0.05602, over 971891.77 frames.], batch size: 32, lr: 7.19e-04
+2022-05-04 04:59:37,244 INFO [train.py:715] (3/8) Epoch 2, batch 8050, loss[loss=0.1679, simple_loss=0.2243, pruned_loss=0.05575, over 4822.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2415, pruned_loss=0.0566, over 971754.39 frames.], batch size: 13, lr: 7.19e-04
+2022-05-04 05:00:18,971 INFO [train.py:715] (3/8) Epoch 2, batch 8100, loss[loss=0.1715, simple_loss=0.2376, pruned_loss=0.05266, over 4903.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2411, pruned_loss=0.05568, over 971885.55 frames.], batch size: 19, lr: 7.19e-04
+2022-05-04 05:01:00,834 INFO [train.py:715] (3/8) Epoch 2, batch 8150, loss[loss=0.1789, simple_loss=0.2417, pruned_loss=0.05803, over 4808.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2404, pruned_loss=0.05508, over 971096.14 frames.], batch size: 26, lr: 7.19e-04
+2022-05-04 05:01:41,275 INFO [train.py:715] (3/8) Epoch 2, batch 8200, loss[loss=0.1916, simple_loss=0.2483, pruned_loss=0.06748, over 4754.00 frames.], tot_loss[loss=0.1745, simple_loss=0.24, pruned_loss=0.05448, over 971562.40 frames.], batch size: 19, lr: 7.18e-04
+2022-05-04 05:02:22,249 INFO [train.py:715] (3/8) Epoch 2, batch 8250, loss[loss=0.1521, simple_loss=0.2267, pruned_loss=0.03879, over 4867.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2419, pruned_loss=0.05556, over 972175.14 frames.], batch size: 16, lr: 7.18e-04
+2022-05-04 05:03:04,361 INFO [train.py:715] (3/8) Epoch 2, batch 8300, loss[loss=0.1422, simple_loss=0.2057, pruned_loss=0.0394, over 4745.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2417, pruned_loss=0.05541, over 971356.80 frames.], batch size: 12, lr: 7.18e-04
+2022-05-04 05:03:46,079 INFO [train.py:715] (3/8) Epoch 2, batch 8350, loss[loss=0.1347, simple_loss=0.2048, pruned_loss=0.03232, over 4975.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2406, pruned_loss=0.05481, over 971866.94 frames.], batch size: 25, lr: 7.18e-04
+2022-05-04 05:04:26,322 INFO [train.py:715] (3/8) Epoch 2, batch 8400, loss[loss=0.2073, simple_loss=0.2715, pruned_loss=0.07153, over 4910.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2406, pruned_loss=0.0549, over 972236.97 frames.], batch size: 19, lr: 7.18e-04
+2022-05-04 05:05:07,475 INFO [train.py:715] (3/8) Epoch 2, batch 8450, loss[loss=0.1675, simple_loss=0.2333, pruned_loss=0.05086, over 4758.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2396, pruned_loss=0.05407, over 971618.26 frames.], batch size: 19, lr: 7.17e-04
+2022-05-04 05:05:49,561 INFO [train.py:715] (3/8) Epoch 2, batch 8500, loss[loss=0.129, simple_loss=0.1979, pruned_loss=0.03011, over 4780.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2388, pruned_loss=0.0539, over 972211.49 frames.], batch size: 12, lr: 7.17e-04
+2022-05-04 05:06:29,760 INFO [train.py:715] (3/8) Epoch 2, batch 8550, loss[loss=0.1478, simple_loss=0.2193, pruned_loss=0.03819, over 4747.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2392, pruned_loss=0.05411, over 972224.03 frames.], batch size: 16, lr: 7.17e-04
+2022-05-04 05:07:10,945 INFO [train.py:715] (3/8) Epoch 2, batch 8600, loss[loss=0.16, simple_loss=0.2319, pruned_loss=0.04408, over 4962.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2391, pruned_loss=0.05435, over 972418.12 frames.], batch size: 24, lr: 7.17e-04
+2022-05-04 05:07:52,995 INFO [train.py:715] (3/8) Epoch 2, batch 8650, loss[loss=0.1621, simple_loss=0.2312, pruned_loss=0.04644, over 4954.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2377, pruned_loss=0.05345, over 971616.72 frames.], batch size: 24, lr: 7.16e-04
+2022-05-04 05:08:34,286 INFO [train.py:715] (3/8) Epoch 2, batch 8700, loss[loss=0.1742, simple_loss=0.2449, pruned_loss=0.0517, over 4941.00 frames.], tot_loss[loss=0.1727, simple_loss=0.238, pruned_loss=0.05366, over 972009.48 frames.], batch size: 23, lr: 7.16e-04
+2022-05-04 05:09:14,827 INFO [train.py:715] (3/8) Epoch 2, batch 8750, loss[loss=0.1673, simple_loss=0.241, pruned_loss=0.04676, over 4877.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2384, pruned_loss=0.05356, over 971470.42 frames.], batch size: 16, lr: 7.16e-04
+2022-05-04 05:09:56,627 INFO [train.py:715] (3/8) Epoch 2, batch 8800, loss[loss=0.2072, simple_loss=0.2701, pruned_loss=0.07214, over 4970.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2381, pruned_loss=0.05305, over 971509.60 frames.], batch size: 15, lr: 7.16e-04
+2022-05-04 05:10:38,731 INFO [train.py:715] (3/8) Epoch 2, batch 8850, loss[loss=0.2277, simple_loss=0.2852, pruned_loss=0.08516, over 4694.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2391, pruned_loss=0.05365, over 970681.35 frames.], batch size: 15, lr: 7.15e-04
+2022-05-04 05:11:18,693 INFO [train.py:715] (3/8) Epoch 2, batch 8900, loss[loss=0.1414, simple_loss=0.212, pruned_loss=0.03539, over 4961.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2388, pruned_loss=0.05298, over 970878.78 frames.], batch size: 15, lr: 7.15e-04
+2022-05-04 05:12:00,190 INFO [train.py:715] (3/8) Epoch 2, batch 8950, loss[loss=0.1644, simple_loss=0.2368, pruned_loss=0.04601, over 4834.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2388, pruned_loss=0.05305, over 971825.07 frames.], batch size: 32, lr: 7.15e-04
+2022-05-04 05:12:42,404 INFO [train.py:715] (3/8) Epoch 2, batch 9000, loss[loss=0.2032, simple_loss=0.2524, pruned_loss=0.07701, over 4851.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2392, pruned_loss=0.05349, over 970966.00 frames.], batch size: 30, lr: 7.15e-04
+2022-05-04 05:12:42,405 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 05:12:58,991 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1181, simple_loss=0.2047, pruned_loss=0.01572, over 914524.00 frames.
+2022-05-04 05:13:41,063 INFO [train.py:715] (3/8) Epoch 2, batch 9050, loss[loss=0.1543, simple_loss=0.2291, pruned_loss=0.0397, over 4831.00 frames.], tot_loss[loss=0.1729, simple_loss=0.239, pruned_loss=0.05344, over 971628.80 frames.], batch size: 15, lr: 7.15e-04
+2022-05-04 05:14:21,245 INFO [train.py:715] (3/8) Epoch 2, batch 9100, loss[loss=0.1545, simple_loss=0.2324, pruned_loss=0.03827, over 4802.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2402, pruned_loss=0.05384, over 972062.38 frames.], batch size: 21, lr: 7.14e-04
+2022-05-04 05:15:02,337 INFO [train.py:715] (3/8) Epoch 2, batch 9150, loss[loss=0.2036, simple_loss=0.2524, pruned_loss=0.07738, over 4845.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2404, pruned_loss=0.05431, over 972228.86 frames.], batch size: 30, lr: 7.14e-04
+2022-05-04 05:15:43,582 INFO [train.py:715] (3/8) Epoch 2, batch 9200, loss[loss=0.164, simple_loss=0.2374, pruned_loss=0.04527, over 4993.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2389, pruned_loss=0.05329, over 972529.60 frames.], batch size: 16, lr: 7.14e-04
+2022-05-04 05:16:25,087 INFO [train.py:715] (3/8) Epoch 2, batch 9250, loss[loss=0.1622, simple_loss=0.2303, pruned_loss=0.04705, over 4847.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2393, pruned_loss=0.05357, over 971429.54 frames.], batch size: 15, lr: 7.14e-04
+2022-05-04 05:17:05,071 INFO [train.py:715] (3/8) Epoch 2, batch 9300, loss[loss=0.1436, simple_loss=0.2211, pruned_loss=0.03307, over 4829.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2393, pruned_loss=0.05358, over 970893.86 frames.], batch size: 27, lr: 7.13e-04
+2022-05-04 05:17:46,766 INFO [train.py:715] (3/8) Epoch 2, batch 9350, loss[loss=0.1872, simple_loss=0.2555, pruned_loss=0.05945, over 4926.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2381, pruned_loss=0.05263, over 971028.68 frames.], batch size: 29, lr: 7.13e-04
+2022-05-04 05:18:28,873 INFO [train.py:715] (3/8) Epoch 2, batch 9400, loss[loss=0.1632, simple_loss=0.2315, pruned_loss=0.04742, over 4855.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2381, pruned_loss=0.05254, over 971418.68 frames.], batch size: 20, lr: 7.13e-04
+2022-05-04 05:19:08,502 INFO [train.py:715] (3/8) Epoch 2, batch 9450, loss[loss=0.1903, simple_loss=0.2522, pruned_loss=0.06422, over 4944.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2384, pruned_loss=0.05255, over 971979.33 frames.], batch size: 39, lr: 7.13e-04
+2022-05-04 05:19:48,356 INFO [train.py:715] (3/8) Epoch 2, batch 9500, loss[loss=0.1896, simple_loss=0.2519, pruned_loss=0.06364, over 4645.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2383, pruned_loss=0.05278, over 972701.40 frames.], batch size: 13, lr: 7.13e-04
+2022-05-04 05:20:28,629 INFO [train.py:715] (3/8) Epoch 2, batch 9550, loss[loss=0.1522, simple_loss=0.2159, pruned_loss=0.04428, over 4762.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2394, pruned_loss=0.05319, over 972603.08 frames.], batch size: 16, lr: 7.12e-04
+2022-05-04 05:21:08,635 INFO [train.py:715] (3/8) Epoch 2, batch 9600, loss[loss=0.1351, simple_loss=0.2067, pruned_loss=0.0318, over 4785.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2388, pruned_loss=0.05311, over 971846.25 frames.], batch size: 19, lr: 7.12e-04
+2022-05-04 05:21:47,534 INFO [train.py:715] (3/8) Epoch 2, batch 9650, loss[loss=0.1864, simple_loss=0.2505, pruned_loss=0.0612, over 4941.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2394, pruned_loss=0.05421, over 970876.49 frames.], batch size: 29, lr: 7.12e-04
+2022-05-04 05:22:27,792 INFO [train.py:715] (3/8) Epoch 2, batch 9700, loss[loss=0.1971, simple_loss=0.2813, pruned_loss=0.05642, over 4938.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2398, pruned_loss=0.05386, over 971474.77 frames.], batch size: 21, lr: 7.12e-04
+2022-05-04 05:23:08,422 INFO [train.py:715] (3/8) Epoch 2, batch 9750, loss[loss=0.177, simple_loss=0.2485, pruned_loss=0.05281, over 4918.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2398, pruned_loss=0.0537, over 972138.07 frames.], batch size: 18, lr: 7.11e-04
+2022-05-04 05:23:47,697 INFO [train.py:715] (3/8) Epoch 2, batch 9800, loss[loss=0.1718, simple_loss=0.242, pruned_loss=0.0508, over 4836.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2399, pruned_loss=0.05397, over 971741.25 frames.], batch size: 26, lr: 7.11e-04
+2022-05-04 05:24:26,794 INFO [train.py:715] (3/8) Epoch 2, batch 9850, loss[loss=0.1855, simple_loss=0.2535, pruned_loss=0.05873, over 4887.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2402, pruned_loss=0.05436, over 972354.35 frames.], batch size: 16, lr: 7.11e-04
+2022-05-04 05:25:06,815 INFO [train.py:715] (3/8) Epoch 2, batch 9900, loss[loss=0.1625, simple_loss=0.2295, pruned_loss=0.04776, over 4763.00 frames.], tot_loss[loss=0.1743, simple_loss=0.24, pruned_loss=0.05431, over 972398.45 frames.], batch size: 19, lr: 7.11e-04
+2022-05-04 05:25:46,405 INFO [train.py:715] (3/8) Epoch 2, batch 9950, loss[loss=0.1332, simple_loss=0.1944, pruned_loss=0.03599, over 4743.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2399, pruned_loss=0.05383, over 973216.52 frames.], batch size: 12, lr: 7.11e-04
+2022-05-04 05:26:25,427 INFO [train.py:715] (3/8) Epoch 2, batch 10000, loss[loss=0.1316, simple_loss=0.2089, pruned_loss=0.02718, over 4856.00 frames.], tot_loss[loss=0.173, simple_loss=0.239, pruned_loss=0.05351, over 972568.41 frames.], batch size: 20, lr: 7.10e-04
+2022-05-04 05:27:06,103 INFO [train.py:715] (3/8) Epoch 2, batch 10050, loss[loss=0.2067, simple_loss=0.2584, pruned_loss=0.07751, over 4970.00 frames.], tot_loss[loss=0.1732, simple_loss=0.239, pruned_loss=0.05368, over 972340.38 frames.], batch size: 35, lr: 7.10e-04
+2022-05-04 05:27:45,912 INFO [train.py:715] (3/8) Epoch 2, batch 10100, loss[loss=0.1677, simple_loss=0.2354, pruned_loss=0.04998, over 4797.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2393, pruned_loss=0.05353, over 973141.69 frames.], batch size: 18, lr: 7.10e-04
+2022-05-04 05:28:25,916 INFO [train.py:715] (3/8) Epoch 2, batch 10150, loss[loss=0.2265, simple_loss=0.2855, pruned_loss=0.08375, over 4860.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2398, pruned_loss=0.05357, over 972457.12 frames.], batch size: 32, lr: 7.10e-04
+2022-05-04 05:29:06,172 INFO [train.py:715] (3/8) Epoch 2, batch 10200, loss[loss=0.1658, simple_loss=0.245, pruned_loss=0.04332, over 4927.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2405, pruned_loss=0.05357, over 972596.79 frames.], batch size: 23, lr: 7.09e-04
+2022-05-04 05:29:47,602 INFO [train.py:715] (3/8) Epoch 2, batch 10250, loss[loss=0.1617, simple_loss=0.2277, pruned_loss=0.04784, over 4964.00 frames.], tot_loss[loss=0.175, simple_loss=0.2412, pruned_loss=0.05437, over 973276.13 frames.], batch size: 14, lr: 7.09e-04
+2022-05-04 05:30:27,419 INFO [train.py:715] (3/8) Epoch 2, batch 10300, loss[loss=0.2145, simple_loss=0.2657, pruned_loss=0.08159, over 4809.00 frames.], tot_loss[loss=0.1747, simple_loss=0.241, pruned_loss=0.05426, over 973200.88 frames.], batch size: 21, lr: 7.09e-04
+2022-05-04 05:31:07,035 INFO [train.py:715] (3/8) Epoch 2, batch 10350, loss[loss=0.169, simple_loss=0.2308, pruned_loss=0.05365, over 4696.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2418, pruned_loss=0.05497, over 972813.10 frames.], batch size: 15, lr: 7.09e-04
+2022-05-04 05:31:49,850 INFO [train.py:715] (3/8) Epoch 2, batch 10400, loss[loss=0.1875, simple_loss=0.2528, pruned_loss=0.06111, over 4885.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2415, pruned_loss=0.05506, over 972804.57 frames.], batch size: 32, lr: 7.09e-04
+2022-05-04 05:32:31,017 INFO [train.py:715] (3/8) Epoch 2, batch 10450, loss[loss=0.1585, simple_loss=0.2241, pruned_loss=0.04646, over 4900.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2414, pruned_loss=0.05502, over 972697.72 frames.], batch size: 17, lr: 7.08e-04
+2022-05-04 05:33:11,275 INFO [train.py:715] (3/8) Epoch 2, batch 10500, loss[loss=0.1662, simple_loss=0.235, pruned_loss=0.04865, over 4841.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2405, pruned_loss=0.05436, over 972868.62 frames.], batch size: 30, lr: 7.08e-04
+2022-05-04 05:33:50,620 INFO [train.py:715] (3/8) Epoch 2, batch 10550, loss[loss=0.15, simple_loss=0.2261, pruned_loss=0.037, over 4932.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2398, pruned_loss=0.05392, over 972291.85 frames.], batch size: 24, lr: 7.08e-04
+2022-05-04 05:34:31,844 INFO [train.py:715] (3/8) Epoch 2, batch 10600, loss[loss=0.1492, simple_loss=0.2068, pruned_loss=0.04583, over 4648.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2399, pruned_loss=0.05341, over 971679.63 frames.], batch size: 13, lr: 7.08e-04
+2022-05-04 05:35:12,036 INFO [train.py:715] (3/8) Epoch 2, batch 10650, loss[loss=0.1664, simple_loss=0.2384, pruned_loss=0.04727, over 4813.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2395, pruned_loss=0.05382, over 971025.46 frames.], batch size: 27, lr: 7.07e-04
+2022-05-04 05:35:51,939 INFO [train.py:715] (3/8) Epoch 2, batch 10700, loss[loss=0.1795, simple_loss=0.2471, pruned_loss=0.056, over 4854.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2395, pruned_loss=0.05391, over 971839.31 frames.], batch size: 30, lr: 7.07e-04
+2022-05-04 05:36:32,501 INFO [train.py:715] (3/8) Epoch 2, batch 10750, loss[loss=0.1521, simple_loss=0.2205, pruned_loss=0.04184, over 4759.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2396, pruned_loss=0.05336, over 971702.54 frames.], batch size: 19, lr: 7.07e-04
+2022-05-04 05:37:13,630 INFO [train.py:715] (3/8) Epoch 2, batch 10800, loss[loss=0.184, simple_loss=0.2532, pruned_loss=0.05739, over 4895.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2388, pruned_loss=0.05292, over 971635.83 frames.], batch size: 19, lr: 7.07e-04
+2022-05-04 05:37:53,806 INFO [train.py:715] (3/8) Epoch 2, batch 10850, loss[loss=0.2074, simple_loss=0.2633, pruned_loss=0.0758, over 4831.00 frames.], tot_loss[loss=0.173, simple_loss=0.2392, pruned_loss=0.05334, over 972058.45 frames.], batch size: 30, lr: 7.07e-04
+2022-05-04 05:38:33,324 INFO [train.py:715] (3/8) Epoch 2, batch 10900, loss[loss=0.1517, simple_loss=0.2232, pruned_loss=0.04014, over 4988.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2391, pruned_loss=0.05335, over 972911.32 frames.], batch size: 25, lr: 7.06e-04
+2022-05-04 05:39:14,356 INFO [train.py:715] (3/8) Epoch 2, batch 10950, loss[loss=0.1897, simple_loss=0.2492, pruned_loss=0.06505, over 4799.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2404, pruned_loss=0.05426, over 972707.59 frames.], batch size: 21, lr: 7.06e-04
+2022-05-04 05:39:54,157 INFO [train.py:715] (3/8) Epoch 2, batch 11000, loss[loss=0.1523, simple_loss=0.2294, pruned_loss=0.03766, over 4760.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2388, pruned_loss=0.05339, over 972418.99 frames.], batch size: 16, lr: 7.06e-04
+2022-05-04 05:40:33,757 INFO [train.py:715] (3/8) Epoch 2, batch 11050, loss[loss=0.1412, simple_loss=0.2088, pruned_loss=0.03675, over 4882.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2388, pruned_loss=0.05308, over 971711.48 frames.], batch size: 22, lr: 7.06e-04
+2022-05-04 05:41:14,433 INFO [train.py:715] (3/8) Epoch 2, batch 11100, loss[loss=0.1449, simple_loss=0.2184, pruned_loss=0.03577, over 4951.00 frames.], tot_loss[loss=0.172, simple_loss=0.2384, pruned_loss=0.05278, over 971834.74 frames.], batch size: 24, lr: 7.05e-04
+2022-05-04 05:41:54,865 INFO [train.py:715] (3/8) Epoch 2, batch 11150, loss[loss=0.1828, simple_loss=0.2637, pruned_loss=0.05091, over 4834.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2387, pruned_loss=0.05299, over 972473.83 frames.], batch size: 25, lr: 7.05e-04
+2022-05-04 05:42:35,624 INFO [train.py:715] (3/8) Epoch 2, batch 11200, loss[loss=0.1753, simple_loss=0.2523, pruned_loss=0.04919, over 4909.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2396, pruned_loss=0.05353, over 973276.70 frames.], batch size: 38, lr: 7.05e-04
+2022-05-04 05:43:15,653 INFO [train.py:715] (3/8) Epoch 2, batch 11250, loss[loss=0.114, simple_loss=0.1881, pruned_loss=0.01998, over 4805.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2389, pruned_loss=0.05299, over 972494.39 frames.], batch size: 12, lr: 7.05e-04
+2022-05-04 05:43:56,716 INFO [train.py:715] (3/8) Epoch 2, batch 11300, loss[loss=0.1652, simple_loss=0.245, pruned_loss=0.04273, over 4812.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2385, pruned_loss=0.05235, over 971930.65 frames.], batch size: 25, lr: 7.05e-04
+2022-05-04 05:44:37,057 INFO [train.py:715] (3/8) Epoch 2, batch 11350, loss[loss=0.1975, simple_loss=0.257, pruned_loss=0.06903, over 4884.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2392, pruned_loss=0.05311, over 973153.97 frames.], batch size: 22, lr: 7.04e-04
+2022-05-04 05:45:16,682 INFO [train.py:715] (3/8) Epoch 2, batch 11400, loss[loss=0.197, simple_loss=0.2632, pruned_loss=0.06542, over 4951.00 frames.], tot_loss[loss=0.174, simple_loss=0.2396, pruned_loss=0.05414, over 972824.00 frames.], batch size: 21, lr: 7.04e-04
+2022-05-04 05:45:56,734 INFO [train.py:715] (3/8) Epoch 2, batch 11450, loss[loss=0.1662, simple_loss=0.2352, pruned_loss=0.0486, over 4763.00 frames.], tot_loss[loss=0.1734, simple_loss=0.239, pruned_loss=0.05387, over 973348.99 frames.], batch size: 19, lr: 7.04e-04
+2022-05-04 05:46:37,326 INFO [train.py:715] (3/8) Epoch 2, batch 11500, loss[loss=0.1762, simple_loss=0.2422, pruned_loss=0.05511, over 4969.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2383, pruned_loss=0.05314, over 974001.55 frames.], batch size: 24, lr: 7.04e-04
+2022-05-04 05:47:18,052 INFO [train.py:715] (3/8) Epoch 2, batch 11550, loss[loss=0.144, simple_loss=0.2134, pruned_loss=0.03727, over 4828.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2374, pruned_loss=0.0528, over 973413.83 frames.], batch size: 15, lr: 7.04e-04
+2022-05-04 05:47:58,021 INFO [train.py:715] (3/8) Epoch 2, batch 11600, loss[loss=0.1554, simple_loss=0.2272, pruned_loss=0.04175, over 4769.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2366, pruned_loss=0.05176, over 973228.29 frames.], batch size: 19, lr: 7.03e-04
+2022-05-04 05:48:39,175 INFO [train.py:715] (3/8) Epoch 2, batch 11650, loss[loss=0.1946, simple_loss=0.2562, pruned_loss=0.06647, over 4866.00 frames.], tot_loss[loss=0.17, simple_loss=0.2364, pruned_loss=0.05177, over 973516.09 frames.], batch size: 16, lr: 7.03e-04
+2022-05-04 05:49:19,421 INFO [train.py:715] (3/8) Epoch 2, batch 11700, loss[loss=0.1963, simple_loss=0.2535, pruned_loss=0.06957, over 4871.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2368, pruned_loss=0.05209, over 973784.69 frames.], batch size: 32, lr: 7.03e-04
+2022-05-04 05:49:59,621 INFO [train.py:715] (3/8) Epoch 2, batch 11750, loss[loss=0.1874, simple_loss=0.2566, pruned_loss=0.05912, over 4888.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2368, pruned_loss=0.05268, over 973424.71 frames.], batch size: 22, lr: 7.03e-04
+2022-05-04 05:50:40,404 INFO [train.py:715] (3/8) Epoch 2, batch 11800, loss[loss=0.161, simple_loss=0.2322, pruned_loss=0.04485, over 4813.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2363, pruned_loss=0.05215, over 973468.50 frames.], batch size: 25, lr: 7.02e-04
+2022-05-04 05:51:20,985 INFO [train.py:715] (3/8) Epoch 2, batch 11850, loss[loss=0.1581, simple_loss=0.2405, pruned_loss=0.03785, over 4981.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2378, pruned_loss=0.05247, over 973806.62 frames.], batch size: 25, lr: 7.02e-04
+2022-05-04 05:52:00,403 INFO [train.py:715] (3/8) Epoch 2, batch 11900, loss[loss=0.1521, simple_loss=0.2117, pruned_loss=0.04624, over 4693.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2381, pruned_loss=0.05253, over 973515.12 frames.], batch size: 15, lr: 7.02e-04
+2022-05-04 05:52:40,332 INFO [train.py:715] (3/8) Epoch 2, batch 11950, loss[loss=0.1611, simple_loss=0.234, pruned_loss=0.04412, over 4940.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2373, pruned_loss=0.05188, over 972821.01 frames.], batch size: 23, lr: 7.02e-04
+2022-05-04 05:53:21,657 INFO [train.py:715] (3/8) Epoch 2, batch 12000, loss[loss=0.1521, simple_loss=0.223, pruned_loss=0.04067, over 4755.00 frames.], tot_loss[loss=0.172, simple_loss=0.2389, pruned_loss=0.05261, over 973330.98 frames.], batch size: 17, lr: 7.02e-04
+2022-05-04 05:53:21,657 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 05:53:45,623 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1181, simple_loss=0.2049, pruned_loss=0.01568, over 914524.00 frames.
+2022-05-04 05:54:27,022 INFO [train.py:715] (3/8) Epoch 2, batch 12050, loss[loss=0.1828, simple_loss=0.2519, pruned_loss=0.05691, over 4931.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2387, pruned_loss=0.05247, over 973941.94 frames.], batch size: 29, lr: 7.01e-04
+2022-05-04 05:55:07,113 INFO [train.py:715] (3/8) Epoch 2, batch 12100, loss[loss=0.1611, simple_loss=0.2335, pruned_loss=0.04432, over 4935.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2392, pruned_loss=0.05286, over 973081.32 frames.], batch size: 29, lr: 7.01e-04
+2022-05-04 05:55:47,109 INFO [train.py:715] (3/8) Epoch 2, batch 12150, loss[loss=0.1485, simple_loss=0.2168, pruned_loss=0.04012, over 4894.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2382, pruned_loss=0.05251, over 972672.20 frames.], batch size: 32, lr: 7.01e-04
+2022-05-04 05:56:27,807 INFO [train.py:715] (3/8) Epoch 2, batch 12200, loss[loss=0.1272, simple_loss=0.1958, pruned_loss=0.0293, over 4833.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2379, pruned_loss=0.05234, over 972749.20 frames.], batch size: 12, lr: 7.01e-04
+2022-05-04 05:57:07,982 INFO [train.py:715] (3/8) Epoch 2, batch 12250, loss[loss=0.1859, simple_loss=0.2518, pruned_loss=0.06002, over 4796.00 frames.], tot_loss[loss=0.171, simple_loss=0.2372, pruned_loss=0.0524, over 972295.61 frames.], batch size: 12, lr: 7.01e-04
+2022-05-04 05:57:48,410 INFO [train.py:715] (3/8) Epoch 2, batch 12300, loss[loss=0.18, simple_loss=0.247, pruned_loss=0.05646, over 4769.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2384, pruned_loss=0.05321, over 972162.91 frames.], batch size: 18, lr: 7.00e-04
+2022-05-04 05:58:28,537 INFO [train.py:715] (3/8) Epoch 2, batch 12350, loss[loss=0.1644, simple_loss=0.2279, pruned_loss=0.0505, over 4987.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2385, pruned_loss=0.05307, over 972407.97 frames.], batch size: 25, lr: 7.00e-04
+2022-05-04 05:59:09,753 INFO [train.py:715] (3/8) Epoch 2, batch 12400, loss[loss=0.1798, simple_loss=0.2401, pruned_loss=0.0598, over 4961.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2386, pruned_loss=0.05322, over 972359.36 frames.], batch size: 15, lr: 7.00e-04
+2022-05-04 05:59:50,011 INFO [train.py:715] (3/8) Epoch 2, batch 12450, loss[loss=0.1739, simple_loss=0.2388, pruned_loss=0.05446, over 4696.00 frames.], tot_loss[loss=0.1733, simple_loss=0.239, pruned_loss=0.05376, over 971400.92 frames.], batch size: 15, lr: 7.00e-04
+2022-05-04 06:00:29,870 INFO [train.py:715] (3/8) Epoch 2, batch 12500, loss[loss=0.1549, simple_loss=0.2232, pruned_loss=0.04331, over 4928.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2387, pruned_loss=0.05371, over 971669.01 frames.], batch size: 18, lr: 6.99e-04
+2022-05-04 06:01:10,537 INFO [train.py:715] (3/8) Epoch 2, batch 12550, loss[loss=0.1476, simple_loss=0.2084, pruned_loss=0.04336, over 4801.00 frames.], tot_loss[loss=0.1721, simple_loss=0.238, pruned_loss=0.0531, over 971685.29 frames.], batch size: 14, lr: 6.99e-04
+2022-05-04 06:01:50,871 INFO [train.py:715] (3/8) Epoch 2, batch 12600, loss[loss=0.1833, simple_loss=0.2594, pruned_loss=0.05357, over 4777.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2381, pruned_loss=0.05308, over 971308.59 frames.], batch size: 17, lr: 6.99e-04
+2022-05-04 06:02:30,888 INFO [train.py:715] (3/8) Epoch 2, batch 12650, loss[loss=0.1621, simple_loss=0.2346, pruned_loss=0.04481, over 4940.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2377, pruned_loss=0.05284, over 971338.18 frames.], batch size: 39, lr: 6.99e-04
+2022-05-04 06:03:11,021 INFO [train.py:715] (3/8) Epoch 2, batch 12700, loss[loss=0.2025, simple_loss=0.2556, pruned_loss=0.07466, over 4785.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2382, pruned_loss=0.0531, over 972341.70 frames.], batch size: 17, lr: 6.99e-04
+2022-05-04 06:03:51,754 INFO [train.py:715] (3/8) Epoch 2, batch 12750, loss[loss=0.1238, simple_loss=0.1952, pruned_loss=0.02625, over 4816.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2379, pruned_loss=0.0526, over 972561.43 frames.], batch size: 13, lr: 6.98e-04
+2022-05-04 06:04:31,917 INFO [train.py:715] (3/8) Epoch 2, batch 12800, loss[loss=0.2127, simple_loss=0.2406, pruned_loss=0.09237, over 4819.00 frames.], tot_loss[loss=0.1719, simple_loss=0.238, pruned_loss=0.05288, over 972625.96 frames.], batch size: 12, lr: 6.98e-04
+2022-05-04 06:05:11,602 INFO [train.py:715] (3/8) Epoch 2, batch 12850, loss[loss=0.1706, simple_loss=0.234, pruned_loss=0.05358, over 4959.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2383, pruned_loss=0.0531, over 972688.60 frames.], batch size: 15, lr: 6.98e-04
+2022-05-04 06:05:52,432 INFO [train.py:715] (3/8) Epoch 2, batch 12900, loss[loss=0.1959, simple_loss=0.25, pruned_loss=0.07085, over 4807.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2388, pruned_loss=0.0538, over 972355.59 frames.], batch size: 21, lr: 6.98e-04
+2022-05-04 06:06:32,852 INFO [train.py:715] (3/8) Epoch 2, batch 12950, loss[loss=0.1631, simple_loss=0.217, pruned_loss=0.05455, over 4941.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2394, pruned_loss=0.05425, over 972226.93 frames.], batch size: 35, lr: 6.98e-04
+2022-05-04 06:07:12,806 INFO [train.py:715] (3/8) Epoch 2, batch 13000, loss[loss=0.1593, simple_loss=0.228, pruned_loss=0.04527, over 4816.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2396, pruned_loss=0.05468, over 971847.91 frames.], batch size: 15, lr: 6.97e-04
+2022-05-04 06:07:53,249 INFO [train.py:715] (3/8) Epoch 2, batch 13050, loss[loss=0.1984, simple_loss=0.2674, pruned_loss=0.06474, over 4752.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2398, pruned_loss=0.05447, over 971484.62 frames.], batch size: 16, lr: 6.97e-04
+2022-05-04 06:08:34,487 INFO [train.py:715] (3/8) Epoch 2, batch 13100, loss[loss=0.1542, simple_loss=0.2297, pruned_loss=0.03932, over 4790.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2391, pruned_loss=0.05375, over 970438.26 frames.], batch size: 24, lr: 6.97e-04
+2022-05-04 06:09:14,676 INFO [train.py:715] (3/8) Epoch 2, batch 13150, loss[loss=0.179, simple_loss=0.2603, pruned_loss=0.04885, over 4819.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2395, pruned_loss=0.05333, over 970931.49 frames.], batch size: 25, lr: 6.97e-04
+2022-05-04 06:09:54,433 INFO [train.py:715] (3/8) Epoch 2, batch 13200, loss[loss=0.2217, simple_loss=0.2807, pruned_loss=0.0813, over 4911.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2393, pruned_loss=0.05327, over 971522.98 frames.], batch size: 23, lr: 6.96e-04
+2022-05-04 06:10:35,328 INFO [train.py:715] (3/8) Epoch 2, batch 13250, loss[loss=0.189, simple_loss=0.2652, pruned_loss=0.05642, over 4955.00 frames.], tot_loss[loss=0.172, simple_loss=0.2387, pruned_loss=0.05265, over 972065.67 frames.], batch size: 24, lr: 6.96e-04
+2022-05-04 06:11:15,860 INFO [train.py:715] (3/8) Epoch 2, batch 13300, loss[loss=0.1687, simple_loss=0.2354, pruned_loss=0.05101, over 4955.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2393, pruned_loss=0.05325, over 972376.47 frames.], batch size: 35, lr: 6.96e-04
+2022-05-04 06:11:55,895 INFO [train.py:715] (3/8) Epoch 2, batch 13350, loss[loss=0.1944, simple_loss=0.264, pruned_loss=0.06238, over 4980.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2385, pruned_loss=0.053, over 973142.71 frames.], batch size: 25, lr: 6.96e-04
+2022-05-04 06:12:36,493 INFO [train.py:715] (3/8) Epoch 2, batch 13400, loss[loss=0.1607, simple_loss=0.2324, pruned_loss=0.04455, over 4782.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2395, pruned_loss=0.05334, over 972846.67 frames.], batch size: 14, lr: 6.96e-04
+2022-05-04 06:13:17,575 INFO [train.py:715] (3/8) Epoch 2, batch 13450, loss[loss=0.1649, simple_loss=0.2463, pruned_loss=0.04179, over 4784.00 frames.], tot_loss[loss=0.173, simple_loss=0.2396, pruned_loss=0.0532, over 972920.78 frames.], batch size: 14, lr: 6.95e-04
+2022-05-04 06:13:57,529 INFO [train.py:715] (3/8) Epoch 2, batch 13500, loss[loss=0.2146, simple_loss=0.2763, pruned_loss=0.07644, over 4779.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2397, pruned_loss=0.05333, over 972192.69 frames.], batch size: 18, lr: 6.95e-04
+2022-05-04 06:14:37,537 INFO [train.py:715] (3/8) Epoch 2, batch 13550, loss[loss=0.1695, simple_loss=0.2365, pruned_loss=0.05127, over 4862.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2402, pruned_loss=0.05353, over 972888.93 frames.], batch size: 32, lr: 6.95e-04
+2022-05-04 06:15:18,679 INFO [train.py:715] (3/8) Epoch 2, batch 13600, loss[loss=0.2016, simple_loss=0.2544, pruned_loss=0.07436, over 4895.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2385, pruned_loss=0.05267, over 972394.59 frames.], batch size: 19, lr: 6.95e-04
+2022-05-04 06:15:59,125 INFO [train.py:715] (3/8) Epoch 2, batch 13650, loss[loss=0.1981, simple_loss=0.2453, pruned_loss=0.07548, over 4757.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2378, pruned_loss=0.05234, over 971601.38 frames.], batch size: 16, lr: 6.95e-04
+2022-05-04 06:16:38,691 INFO [train.py:715] (3/8) Epoch 2, batch 13700, loss[loss=0.1535, simple_loss=0.2374, pruned_loss=0.03481, over 4908.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2383, pruned_loss=0.05261, over 971814.16 frames.], batch size: 17, lr: 6.94e-04
+2022-05-04 06:17:19,956 INFO [train.py:715] (3/8) Epoch 2, batch 13750, loss[loss=0.1385, simple_loss=0.2089, pruned_loss=0.03405, over 4816.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2392, pruned_loss=0.05291, over 972076.19 frames.], batch size: 25, lr: 6.94e-04
+2022-05-04 06:18:00,035 INFO [train.py:715] (3/8) Epoch 2, batch 13800, loss[loss=0.1501, simple_loss=0.2128, pruned_loss=0.04371, over 4634.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2387, pruned_loss=0.05304, over 971280.43 frames.], batch size: 13, lr: 6.94e-04
+2022-05-04 06:18:39,727 INFO [train.py:715] (3/8) Epoch 2, batch 13850, loss[loss=0.1449, simple_loss=0.2188, pruned_loss=0.03547, over 4990.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2388, pruned_loss=0.05289, over 971902.23 frames.], batch size: 15, lr: 6.94e-04
+2022-05-04 06:19:19,318 INFO [train.py:715] (3/8) Epoch 2, batch 13900, loss[loss=0.1318, simple_loss=0.1951, pruned_loss=0.0342, over 4779.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2388, pruned_loss=0.05275, over 972364.18 frames.], batch size: 12, lr: 6.94e-04
+2022-05-04 06:20:00,085 INFO [train.py:715] (3/8) Epoch 2, batch 13950, loss[loss=0.1798, simple_loss=0.2516, pruned_loss=0.054, over 4961.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2387, pruned_loss=0.05277, over 970968.74 frames.], batch size: 29, lr: 6.93e-04
+2022-05-04 06:20:40,293 INFO [train.py:715] (3/8) Epoch 2, batch 14000, loss[loss=0.156, simple_loss=0.2371, pruned_loss=0.03744, over 4984.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2387, pruned_loss=0.05285, over 971400.91 frames.], batch size: 26, lr: 6.93e-04
+2022-05-04 06:21:19,542 INFO [train.py:715] (3/8) Epoch 2, batch 14050, loss[loss=0.1598, simple_loss=0.2242, pruned_loss=0.04771, over 4904.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2383, pruned_loss=0.0528, over 972123.96 frames.], batch size: 17, lr: 6.93e-04
+2022-05-04 06:22:01,049 INFO [train.py:715] (3/8) Epoch 2, batch 14100, loss[loss=0.163, simple_loss=0.243, pruned_loss=0.04152, over 4700.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2386, pruned_loss=0.05286, over 972357.63 frames.], batch size: 15, lr: 6.93e-04
+2022-05-04 06:22:41,689 INFO [train.py:715] (3/8) Epoch 2, batch 14150, loss[loss=0.1681, simple_loss=0.2407, pruned_loss=0.04771, over 4967.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2381, pruned_loss=0.05261, over 972618.85 frames.], batch size: 24, lr: 6.93e-04
+2022-05-04 06:23:21,639 INFO [train.py:715] (3/8) Epoch 2, batch 14200, loss[loss=0.1749, simple_loss=0.2435, pruned_loss=0.05314, over 4926.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2385, pruned_loss=0.05291, over 972911.43 frames.], batch size: 18, lr: 6.92e-04
+2022-05-04 06:24:01,479 INFO [train.py:715] (3/8) Epoch 2, batch 14250, loss[loss=0.1531, simple_loss=0.2236, pruned_loss=0.0413, over 4884.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2396, pruned_loss=0.0534, over 973121.03 frames.], batch size: 22, lr: 6.92e-04
+2022-05-04 06:24:42,097 INFO [train.py:715] (3/8) Epoch 2, batch 14300, loss[loss=0.1679, simple_loss=0.2484, pruned_loss=0.04366, over 4799.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2405, pruned_loss=0.05397, over 973368.78 frames.], batch size: 17, lr: 6.92e-04
+2022-05-04 06:25:21,660 INFO [train.py:715] (3/8) Epoch 2, batch 14350, loss[loss=0.2044, simple_loss=0.2659, pruned_loss=0.07142, over 4835.00 frames.], tot_loss[loss=0.173, simple_loss=0.2397, pruned_loss=0.05314, over 973084.44 frames.], batch size: 15, lr: 6.92e-04
+2022-05-04 06:26:01,519 INFO [train.py:715] (3/8) Epoch 2, batch 14400, loss[loss=0.1356, simple_loss=0.2064, pruned_loss=0.0324, over 4834.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2383, pruned_loss=0.0522, over 972984.49 frames.], batch size: 15, lr: 6.92e-04
+2022-05-04 06:26:41,858 INFO [train.py:715] (3/8) Epoch 2, batch 14450, loss[loss=0.1572, simple_loss=0.2286, pruned_loss=0.04289, over 4930.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2387, pruned_loss=0.05229, over 973260.95 frames.], batch size: 23, lr: 6.91e-04
+2022-05-04 06:27:22,094 INFO [train.py:715] (3/8) Epoch 2, batch 14500, loss[loss=0.169, simple_loss=0.2363, pruned_loss=0.05084, over 4796.00 frames.], tot_loss[loss=0.172, simple_loss=0.2391, pruned_loss=0.05242, over 972290.06 frames.], batch size: 24, lr: 6.91e-04
+2022-05-04 06:28:01,692 INFO [train.py:715] (3/8) Epoch 2, batch 14550, loss[loss=0.2094, simple_loss=0.2593, pruned_loss=0.0798, over 4921.00 frames.], tot_loss[loss=0.1721, simple_loss=0.239, pruned_loss=0.05261, over 972845.74 frames.], batch size: 17, lr: 6.91e-04
+2022-05-04 06:28:42,166 INFO [train.py:715] (3/8) Epoch 2, batch 14600, loss[loss=0.1493, simple_loss=0.2211, pruned_loss=0.03872, over 4920.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2391, pruned_loss=0.05309, over 972832.19 frames.], batch size: 29, lr: 6.91e-04
+2022-05-04 06:29:22,662 INFO [train.py:715] (3/8) Epoch 2, batch 14650, loss[loss=0.1899, simple_loss=0.2478, pruned_loss=0.06602, over 4908.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2404, pruned_loss=0.0537, over 973149.25 frames.], batch size: 19, lr: 6.90e-04
+2022-05-04 06:30:01,955 INFO [train.py:715] (3/8) Epoch 2, batch 14700, loss[loss=0.1691, simple_loss=0.2376, pruned_loss=0.05034, over 4826.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2392, pruned_loss=0.05309, over 972843.63 frames.], batch size: 27, lr: 6.90e-04
+2022-05-04 06:30:41,281 INFO [train.py:715] (3/8) Epoch 2, batch 14750, loss[loss=0.1617, simple_loss=0.2317, pruned_loss=0.04582, over 4979.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2384, pruned_loss=0.05266, over 973139.66 frames.], batch size: 25, lr: 6.90e-04
+2022-05-04 06:31:21,767 INFO [train.py:715] (3/8) Epoch 2, batch 14800, loss[loss=0.1692, simple_loss=0.2262, pruned_loss=0.05613, over 4749.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2382, pruned_loss=0.05295, over 971868.12 frames.], batch size: 16, lr: 6.90e-04
+2022-05-04 06:32:01,268 INFO [train.py:715] (3/8) Epoch 2, batch 14850, loss[loss=0.1467, simple_loss=0.2192, pruned_loss=0.03706, over 4972.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2371, pruned_loss=0.05253, over 971707.36 frames.], batch size: 25, lr: 6.90e-04
+2022-05-04 06:32:40,952 INFO [train.py:715] (3/8) Epoch 2, batch 14900, loss[loss=0.1778, simple_loss=0.2478, pruned_loss=0.05392, over 4856.00 frames.], tot_loss[loss=0.171, simple_loss=0.2377, pruned_loss=0.05221, over 971468.21 frames.], batch size: 32, lr: 6.89e-04
+2022-05-04 06:33:21,117 INFO [train.py:715] (3/8) Epoch 2, batch 14950, loss[loss=0.225, simple_loss=0.2942, pruned_loss=0.07792, over 4985.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2384, pruned_loss=0.05249, over 971907.76 frames.], batch size: 25, lr: 6.89e-04
+2022-05-04 06:34:01,756 INFO [train.py:715] (3/8) Epoch 2, batch 15000, loss[loss=0.2057, simple_loss=0.2655, pruned_loss=0.07294, over 4809.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2379, pruned_loss=0.05239, over 972609.48 frames.], batch size: 25, lr: 6.89e-04
+2022-05-04 06:34:01,756 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 06:34:11,141 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1176, simple_loss=0.2043, pruned_loss=0.01548, over 914524.00 frames.
+2022-05-04 06:34:52,063 INFO [train.py:715] (3/8) Epoch 2, batch 15050, loss[loss=0.1494, simple_loss=0.2248, pruned_loss=0.03695, over 4972.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2379, pruned_loss=0.0524, over 971885.30 frames.], batch size: 24, lr: 6.89e-04
+2022-05-04 06:35:31,186 INFO [train.py:715] (3/8) Epoch 2, batch 15100, loss[loss=0.1712, simple_loss=0.2493, pruned_loss=0.0465, over 4837.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2385, pruned_loss=0.0524, over 972488.53 frames.], batch size: 15, lr: 6.89e-04
+2022-05-04 06:36:11,669 INFO [train.py:715] (3/8) Epoch 2, batch 15150, loss[loss=0.1676, simple_loss=0.2405, pruned_loss=0.04735, over 4867.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2387, pruned_loss=0.05289, over 972921.52 frames.], batch size: 16, lr: 6.88e-04
+2022-05-04 06:36:52,156 INFO [train.py:715] (3/8) Epoch 2, batch 15200, loss[loss=0.1777, simple_loss=0.247, pruned_loss=0.0542, over 4756.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2387, pruned_loss=0.05277, over 972204.67 frames.], batch size: 16, lr: 6.88e-04
+2022-05-04 06:37:31,885 INFO [train.py:715] (3/8) Epoch 2, batch 15250, loss[loss=0.163, simple_loss=0.2267, pruned_loss=0.04968, over 4889.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2391, pruned_loss=0.0532, over 972137.50 frames.], batch size: 16, lr: 6.88e-04
+2022-05-04 06:38:11,343 INFO [train.py:715] (3/8) Epoch 2, batch 15300, loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03235, over 4903.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2384, pruned_loss=0.05303, over 972500.04 frames.], batch size: 17, lr: 6.88e-04
+2022-05-04 06:38:51,801 INFO [train.py:715] (3/8) Epoch 2, batch 15350, loss[loss=0.2092, simple_loss=0.268, pruned_loss=0.07517, over 4876.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2377, pruned_loss=0.05238, over 971823.44 frames.], batch size: 22, lr: 6.88e-04
+2022-05-04 06:39:32,692 INFO [train.py:715] (3/8) Epoch 2, batch 15400, loss[loss=0.1984, simple_loss=0.258, pruned_loss=0.06933, over 4945.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2396, pruned_loss=0.05359, over 972760.62 frames.], batch size: 39, lr: 6.87e-04
+2022-05-04 06:40:11,869 INFO [train.py:715] (3/8) Epoch 2, batch 15450, loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03247, over 4863.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2389, pruned_loss=0.05369, over 972446.37 frames.], batch size: 20, lr: 6.87e-04
+2022-05-04 06:40:52,373 INFO [train.py:715] (3/8) Epoch 2, batch 15500, loss[loss=0.18, simple_loss=0.2565, pruned_loss=0.05178, over 4901.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2391, pruned_loss=0.05336, over 972568.71 frames.], batch size: 19, lr: 6.87e-04
+2022-05-04 06:41:32,621 INFO [train.py:715] (3/8) Epoch 2, batch 15550, loss[loss=0.2281, simple_loss=0.2851, pruned_loss=0.08556, over 4774.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2381, pruned_loss=0.05244, over 972657.26 frames.], batch size: 18, lr: 6.87e-04
+2022-05-04 06:42:12,563 INFO [train.py:715] (3/8) Epoch 2, batch 15600, loss[loss=0.1682, simple_loss=0.2369, pruned_loss=0.04976, over 4911.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2383, pruned_loss=0.05216, over 972790.59 frames.], batch size: 23, lr: 6.87e-04
+2022-05-04 06:42:52,372 INFO [train.py:715] (3/8) Epoch 2, batch 15650, loss[loss=0.1857, simple_loss=0.2553, pruned_loss=0.05799, over 4929.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2381, pruned_loss=0.05234, over 972699.85 frames.], batch size: 40, lr: 6.86e-04
+2022-05-04 06:43:33,096 INFO [train.py:715] (3/8) Epoch 2, batch 15700, loss[loss=0.1671, simple_loss=0.2395, pruned_loss=0.04739, over 4893.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2384, pruned_loss=0.05222, over 973297.55 frames.], batch size: 22, lr: 6.86e-04
+2022-05-04 06:44:13,627 INFO [train.py:715] (3/8) Epoch 2, batch 15750, loss[loss=0.1844, simple_loss=0.2398, pruned_loss=0.06453, over 4842.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2381, pruned_loss=0.05148, over 973600.11 frames.], batch size: 30, lr: 6.86e-04
+2022-05-04 06:44:52,969 INFO [train.py:715] (3/8) Epoch 2, batch 15800, loss[loss=0.1813, simple_loss=0.2455, pruned_loss=0.0585, over 4875.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2373, pruned_loss=0.0511, over 972800.36 frames.], batch size: 32, lr: 6.86e-04
+2022-05-04 06:45:33,630 INFO [train.py:715] (3/8) Epoch 2, batch 15850, loss[loss=0.1666, simple_loss=0.2447, pruned_loss=0.04426, over 4812.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2375, pruned_loss=0.05107, over 973810.22 frames.], batch size: 27, lr: 6.86e-04
+2022-05-04 06:46:14,110 INFO [train.py:715] (3/8) Epoch 2, batch 15900, loss[loss=0.1867, simple_loss=0.2493, pruned_loss=0.06202, over 4798.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2377, pruned_loss=0.0514, over 973210.59 frames.], batch size: 21, lr: 6.85e-04
+2022-05-04 06:46:53,876 INFO [train.py:715] (3/8) Epoch 2, batch 15950, loss[loss=0.165, simple_loss=0.2343, pruned_loss=0.04782, over 4869.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2369, pruned_loss=0.05112, over 973076.00 frames.], batch size: 22, lr: 6.85e-04
+2022-05-04 06:47:34,107 INFO [train.py:715] (3/8) Epoch 2, batch 16000, loss[loss=0.1791, simple_loss=0.2417, pruned_loss=0.0583, over 4788.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2372, pruned_loss=0.05147, over 972980.34 frames.], batch size: 17, lr: 6.85e-04
+2022-05-04 06:48:14,440 INFO [train.py:715] (3/8) Epoch 2, batch 16050, loss[loss=0.1153, simple_loss=0.1838, pruned_loss=0.02341, over 4981.00 frames.], tot_loss[loss=0.1713, simple_loss=0.238, pruned_loss=0.05232, over 971921.25 frames.], batch size: 14, lr: 6.85e-04
+2022-05-04 06:48:54,891 INFO [train.py:715] (3/8) Epoch 2, batch 16100, loss[loss=0.1546, simple_loss=0.2278, pruned_loss=0.04075, over 4916.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2378, pruned_loss=0.05202, over 972579.45 frames.], batch size: 23, lr: 6.85e-04
+2022-05-04 06:49:34,155 INFO [train.py:715] (3/8) Epoch 2, batch 16150, loss[loss=0.1803, simple_loss=0.2417, pruned_loss=0.05942, over 4946.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2376, pruned_loss=0.05201, over 972535.75 frames.], batch size: 21, lr: 6.84e-04
+2022-05-04 06:50:14,543 INFO [train.py:715] (3/8) Epoch 2, batch 16200, loss[loss=0.1645, simple_loss=0.2317, pruned_loss=0.04868, over 4940.00 frames.], tot_loss[loss=0.17, simple_loss=0.2369, pruned_loss=0.05155, over 972498.00 frames.], batch size: 21, lr: 6.84e-04
+2022-05-04 06:50:54,950 INFO [train.py:715] (3/8) Epoch 2, batch 16250, loss[loss=0.2021, simple_loss=0.2603, pruned_loss=0.07199, over 4882.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2377, pruned_loss=0.05152, over 972304.08 frames.], batch size: 19, lr: 6.84e-04
+2022-05-04 06:51:34,791 INFO [train.py:715] (3/8) Epoch 2, batch 16300, loss[loss=0.1518, simple_loss=0.2292, pruned_loss=0.03718, over 4952.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2372, pruned_loss=0.05147, over 972166.23 frames.], batch size: 21, lr: 6.84e-04
+2022-05-04 06:52:14,669 INFO [train.py:715] (3/8) Epoch 2, batch 16350, loss[loss=0.2246, simple_loss=0.2736, pruned_loss=0.08778, over 4860.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2367, pruned_loss=0.05119, over 972174.85 frames.], batch size: 32, lr: 6.84e-04
+2022-05-04 06:52:55,172 INFO [train.py:715] (3/8) Epoch 2, batch 16400, loss[loss=0.1643, simple_loss=0.236, pruned_loss=0.04625, over 4828.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2369, pruned_loss=0.05139, over 972335.33 frames.], batch size: 15, lr: 6.83e-04
+2022-05-04 06:53:35,562 INFO [train.py:715] (3/8) Epoch 2, batch 16450, loss[loss=0.1591, simple_loss=0.228, pruned_loss=0.04508, over 4881.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2371, pruned_loss=0.05179, over 972355.32 frames.], batch size: 20, lr: 6.83e-04
+2022-05-04 06:54:15,144 INFO [train.py:715] (3/8) Epoch 2, batch 16500, loss[loss=0.1622, simple_loss=0.2281, pruned_loss=0.04816, over 4949.00 frames.], tot_loss[loss=0.1705, simple_loss=0.237, pruned_loss=0.05205, over 973067.79 frames.], batch size: 29, lr: 6.83e-04
+2022-05-04 06:54:56,121 INFO [train.py:715] (3/8) Epoch 2, batch 16550, loss[loss=0.1483, simple_loss=0.2151, pruned_loss=0.04074, over 4868.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2392, pruned_loss=0.053, over 973093.09 frames.], batch size: 22, lr: 6.83e-04
+2022-05-04 06:55:36,862 INFO [train.py:715] (3/8) Epoch 2, batch 16600, loss[loss=0.1916, simple_loss=0.2445, pruned_loss=0.06937, over 4992.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2385, pruned_loss=0.05293, over 972574.59 frames.], batch size: 14, lr: 6.83e-04
+2022-05-04 06:56:16,712 INFO [train.py:715] (3/8) Epoch 2, batch 16650, loss[loss=0.1674, simple_loss=0.2382, pruned_loss=0.04832, over 4882.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2379, pruned_loss=0.05273, over 972297.09 frames.], batch size: 22, lr: 6.82e-04
+2022-05-04 06:56:57,159 INFO [train.py:715] (3/8) Epoch 2, batch 16700, loss[loss=0.1473, simple_loss=0.2228, pruned_loss=0.03584, over 4981.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2385, pruned_loss=0.05284, over 973044.15 frames.], batch size: 25, lr: 6.82e-04
+2022-05-04 06:57:37,914 INFO [train.py:715] (3/8) Epoch 2, batch 16750, loss[loss=0.2022, simple_loss=0.2679, pruned_loss=0.06826, over 4913.00 frames.], tot_loss[loss=0.172, simple_loss=0.2381, pruned_loss=0.05291, over 973163.59 frames.], batch size: 40, lr: 6.82e-04
+2022-05-04 06:58:18,617 INFO [train.py:715] (3/8) Epoch 2, batch 16800, loss[loss=0.1543, simple_loss=0.2297, pruned_loss=0.03948, over 4978.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2377, pruned_loss=0.05226, over 972574.34 frames.], batch size: 14, lr: 6.82e-04
+2022-05-04 06:58:58,044 INFO [train.py:715] (3/8) Epoch 2, batch 16850, loss[loss=0.1473, simple_loss=0.2174, pruned_loss=0.03854, over 4989.00 frames.], tot_loss[loss=0.1703, simple_loss=0.237, pruned_loss=0.05175, over 972795.34 frames.], batch size: 14, lr: 6.82e-04
+2022-05-04 06:59:39,313 INFO [train.py:715] (3/8) Epoch 2, batch 16900, loss[loss=0.1977, simple_loss=0.2567, pruned_loss=0.06933, over 4988.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2373, pruned_loss=0.05207, over 973146.51 frames.], batch size: 31, lr: 6.81e-04
+2022-05-04 07:00:20,133 INFO [train.py:715] (3/8) Epoch 2, batch 16950, loss[loss=0.1902, simple_loss=0.2553, pruned_loss=0.06258, over 4921.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2378, pruned_loss=0.05253, over 972491.45 frames.], batch size: 23, lr: 6.81e-04
+2022-05-04 07:00:59,942 INFO [train.py:715] (3/8) Epoch 2, batch 17000, loss[loss=0.1933, simple_loss=0.2494, pruned_loss=0.06857, over 4923.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2396, pruned_loss=0.05337, over 971994.11 frames.], batch size: 17, lr: 6.81e-04
+2022-05-04 07:01:40,371 INFO [train.py:715] (3/8) Epoch 2, batch 17050, loss[loss=0.2035, simple_loss=0.2773, pruned_loss=0.06486, over 4793.00 frames.], tot_loss[loss=0.173, simple_loss=0.2393, pruned_loss=0.05338, over 972425.89 frames.], batch size: 21, lr: 6.81e-04
+2022-05-04 07:02:20,962 INFO [train.py:715] (3/8) Epoch 2, batch 17100, loss[loss=0.146, simple_loss=0.2177, pruned_loss=0.03712, over 4988.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2391, pruned_loss=0.05319, over 972413.38 frames.], batch size: 25, lr: 6.81e-04
+2022-05-04 07:03:01,189 INFO [train.py:715] (3/8) Epoch 2, batch 17150, loss[loss=0.1953, simple_loss=0.2498, pruned_loss=0.07042, over 4926.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2379, pruned_loss=0.05254, over 972663.84 frames.], batch size: 39, lr: 6.81e-04
+2022-05-04 07:03:40,481 INFO [train.py:715] (3/8) Epoch 2, batch 17200, loss[loss=0.1569, simple_loss=0.224, pruned_loss=0.04491, over 4915.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2373, pruned_loss=0.05207, over 973277.61 frames.], batch size: 29, lr: 6.80e-04
+2022-05-04 07:04:20,885 INFO [train.py:715] (3/8) Epoch 2, batch 17250, loss[loss=0.1672, simple_loss=0.2333, pruned_loss=0.05055, over 4975.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2378, pruned_loss=0.0522, over 972560.67 frames.], batch size: 15, lr: 6.80e-04
+2022-05-04 07:05:01,344 INFO [train.py:715] (3/8) Epoch 2, batch 17300, loss[loss=0.199, simple_loss=0.2582, pruned_loss=0.06993, over 4887.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2374, pruned_loss=0.0519, over 972441.56 frames.], batch size: 22, lr: 6.80e-04
+2022-05-04 07:05:40,925 INFO [train.py:715] (3/8) Epoch 2, batch 17350, loss[loss=0.1527, simple_loss=0.2304, pruned_loss=0.03752, over 4956.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2371, pruned_loss=0.05161, over 972588.49 frames.], batch size: 21, lr: 6.80e-04
+2022-05-04 07:06:20,384 INFO [train.py:715] (3/8) Epoch 2, batch 17400, loss[loss=0.1475, simple_loss=0.2103, pruned_loss=0.04237, over 4929.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2372, pruned_loss=0.05155, over 972699.75 frames.], batch size: 18, lr: 6.80e-04
+2022-05-04 07:07:00,339 INFO [train.py:715] (3/8) Epoch 2, batch 17450, loss[loss=0.1398, simple_loss=0.2176, pruned_loss=0.03094, over 4768.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2372, pruned_loss=0.05161, over 972132.87 frames.], batch size: 19, lr: 6.79e-04
+2022-05-04 07:07:40,090 INFO [train.py:715] (3/8) Epoch 2, batch 17500, loss[loss=0.1165, simple_loss=0.1814, pruned_loss=0.02586, over 4842.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2359, pruned_loss=0.05116, over 971880.87 frames.], batch size: 12, lr: 6.79e-04
+2022-05-04 07:08:18,850 INFO [train.py:715] (3/8) Epoch 2, batch 17550, loss[loss=0.1356, simple_loss=0.2078, pruned_loss=0.03167, over 4805.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2363, pruned_loss=0.05142, over 971821.99 frames.], batch size: 21, lr: 6.79e-04
+2022-05-04 07:08:58,969 INFO [train.py:715] (3/8) Epoch 2, batch 17600, loss[loss=0.1612, simple_loss=0.2353, pruned_loss=0.04354, over 4856.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2365, pruned_loss=0.05221, over 971738.33 frames.], batch size: 30, lr: 6.79e-04
+2022-05-04 07:09:38,385 INFO [train.py:715] (3/8) Epoch 2, batch 17650, loss[loss=0.1857, simple_loss=0.266, pruned_loss=0.05268, over 4922.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2361, pruned_loss=0.05183, over 971538.85 frames.], batch size: 29, lr: 6.79e-04
+2022-05-04 07:10:17,890 INFO [train.py:715] (3/8) Epoch 2, batch 17700, loss[loss=0.1847, simple_loss=0.2492, pruned_loss=0.0601, over 4820.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2362, pruned_loss=0.0521, over 972407.57 frames.], batch size: 26, lr: 6.78e-04
+2022-05-04 07:10:57,825 INFO [train.py:715] (3/8) Epoch 2, batch 17750, loss[loss=0.1737, simple_loss=0.2361, pruned_loss=0.05568, over 4864.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2355, pruned_loss=0.05195, over 971506.40 frames.], batch size: 38, lr: 6.78e-04
+2022-05-04 07:11:37,688 INFO [train.py:715] (3/8) Epoch 2, batch 17800, loss[loss=0.1822, simple_loss=0.2496, pruned_loss=0.05736, over 4907.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2352, pruned_loss=0.05154, over 972156.79 frames.], batch size: 19, lr: 6.78e-04
+2022-05-04 07:12:17,992 INFO [train.py:715] (3/8) Epoch 2, batch 17850, loss[loss=0.1539, simple_loss=0.2154, pruned_loss=0.04618, over 4804.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2343, pruned_loss=0.05076, over 972394.43 frames.], batch size: 13, lr: 6.78e-04
+2022-05-04 07:12:56,814 INFO [train.py:715] (3/8) Epoch 2, batch 17900, loss[loss=0.1722, simple_loss=0.2494, pruned_loss=0.04756, over 4965.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2346, pruned_loss=0.05062, over 972538.14 frames.], batch size: 24, lr: 6.78e-04
+2022-05-04 07:13:36,734 INFO [train.py:715] (3/8) Epoch 2, batch 17950, loss[loss=0.1542, simple_loss=0.2191, pruned_loss=0.0447, over 4754.00 frames.], tot_loss[loss=0.1684, simple_loss=0.235, pruned_loss=0.05087, over 972258.13 frames.], batch size: 16, lr: 6.77e-04
+2022-05-04 07:14:16,911 INFO [train.py:715] (3/8) Epoch 2, batch 18000, loss[loss=0.1716, simple_loss=0.2396, pruned_loss=0.05184, over 4812.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2357, pruned_loss=0.05099, over 971859.64 frames.], batch size: 25, lr: 6.77e-04
+2022-05-04 07:14:16,912 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 07:14:26,627 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1173, simple_loss=0.2039, pruned_loss=0.01538, over 914524.00 frames.
+2022-05-04 07:15:07,354 INFO [train.py:715] (3/8) Epoch 2, batch 18050, loss[loss=0.1614, simple_loss=0.2245, pruned_loss=0.04915, over 4930.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2366, pruned_loss=0.05166, over 971869.22 frames.], batch size: 29, lr: 6.77e-04
+2022-05-04 07:15:46,535 INFO [train.py:715] (3/8) Epoch 2, batch 18100, loss[loss=0.1813, simple_loss=0.2378, pruned_loss=0.06242, over 4965.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2373, pruned_loss=0.05192, over 972489.70 frames.], batch size: 35, lr: 6.77e-04
+2022-05-04 07:16:27,423 INFO [train.py:715] (3/8) Epoch 2, batch 18150, loss[loss=0.1785, simple_loss=0.2525, pruned_loss=0.05225, over 4930.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2378, pruned_loss=0.05234, over 972026.26 frames.], batch size: 29, lr: 6.77e-04
+2022-05-04 07:17:08,375 INFO [train.py:715] (3/8) Epoch 2, batch 18200, loss[loss=0.1514, simple_loss=0.2282, pruned_loss=0.03728, over 4992.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2371, pruned_loss=0.0517, over 972545.75 frames.], batch size: 14, lr: 6.76e-04
+2022-05-04 07:17:49,832 INFO [train.py:715] (3/8) Epoch 2, batch 18250, loss[loss=0.1675, simple_loss=0.2406, pruned_loss=0.04719, over 4885.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2381, pruned_loss=0.05164, over 972891.60 frames.], batch size: 22, lr: 6.76e-04
+2022-05-04 07:18:30,274 INFO [train.py:715] (3/8) Epoch 2, batch 18300, loss[loss=0.1696, simple_loss=0.2288, pruned_loss=0.05517, over 4845.00 frames.], tot_loss[loss=0.171, simple_loss=0.2382, pruned_loss=0.05189, over 972047.67 frames.], batch size: 34, lr: 6.76e-04
+2022-05-04 07:19:12,137 INFO [train.py:715] (3/8) Epoch 2, batch 18350, loss[loss=0.1551, simple_loss=0.2224, pruned_loss=0.04391, over 4939.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2377, pruned_loss=0.0518, over 972474.72 frames.], batch size: 29, lr: 6.76e-04
+2022-05-04 07:19:56,502 INFO [train.py:715] (3/8) Epoch 2, batch 18400, loss[loss=0.1412, simple_loss=0.2121, pruned_loss=0.03515, over 4759.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2375, pruned_loss=0.05171, over 971976.05 frames.], batch size: 19, lr: 6.76e-04
+2022-05-04 07:20:36,619 INFO [train.py:715] (3/8) Epoch 2, batch 18450, loss[loss=0.1578, simple_loss=0.2266, pruned_loss=0.04453, over 4811.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2387, pruned_loss=0.05229, over 971181.66 frames.], batch size: 25, lr: 6.75e-04
+2022-05-04 07:21:18,110 INFO [train.py:715] (3/8) Epoch 2, batch 18500, loss[loss=0.2107, simple_loss=0.2698, pruned_loss=0.07582, over 4961.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2389, pruned_loss=0.052, over 970763.00 frames.], batch size: 15, lr: 6.75e-04
+2022-05-04 07:21:59,812 INFO [train.py:715] (3/8) Epoch 2, batch 18550, loss[loss=0.1748, simple_loss=0.2431, pruned_loss=0.0533, over 4964.00 frames.], tot_loss[loss=0.17, simple_loss=0.2375, pruned_loss=0.05129, over 971159.84 frames.], batch size: 28, lr: 6.75e-04
+2022-05-04 07:22:41,512 INFO [train.py:715] (3/8) Epoch 2, batch 18600, loss[loss=0.1613, simple_loss=0.2294, pruned_loss=0.04661, over 4813.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2368, pruned_loss=0.05113, over 972235.43 frames.], batch size: 26, lr: 6.75e-04
+2022-05-04 07:23:21,832 INFO [train.py:715] (3/8) Epoch 2, batch 18650, loss[loss=0.1709, simple_loss=0.2378, pruned_loss=0.05201, over 4708.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2356, pruned_loss=0.05065, over 971857.32 frames.], batch size: 15, lr: 6.75e-04
+2022-05-04 07:24:03,484 INFO [train.py:715] (3/8) Epoch 2, batch 18700, loss[loss=0.1807, simple_loss=0.2423, pruned_loss=0.05952, over 4931.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2363, pruned_loss=0.0509, over 971422.73 frames.], batch size: 23, lr: 6.75e-04
+2022-05-04 07:24:45,168 INFO [train.py:715] (3/8) Epoch 2, batch 18750, loss[loss=0.2008, simple_loss=0.2567, pruned_loss=0.07244, over 4962.00 frames.], tot_loss[loss=0.1691, simple_loss=0.236, pruned_loss=0.05115, over 971590.89 frames.], batch size: 14, lr: 6.74e-04
+2022-05-04 07:25:25,719 INFO [train.py:715] (3/8) Epoch 2, batch 18800, loss[loss=0.136, simple_loss=0.2087, pruned_loss=0.03162, over 4916.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2354, pruned_loss=0.05111, over 971493.43 frames.], batch size: 18, lr: 6.74e-04
+2022-05-04 07:26:06,670 INFO [train.py:715] (3/8) Epoch 2, batch 18850, loss[loss=0.1672, simple_loss=0.2408, pruned_loss=0.0468, over 4918.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2362, pruned_loss=0.05124, over 971997.01 frames.], batch size: 17, lr: 6.74e-04
+2022-05-04 07:26:48,081 INFO [train.py:715] (3/8) Epoch 2, batch 18900, loss[loss=0.1472, simple_loss=0.2173, pruned_loss=0.03853, over 4827.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2371, pruned_loss=0.05237, over 972461.41 frames.], batch size: 15, lr: 6.74e-04
+2022-05-04 07:27:29,072 INFO [train.py:715] (3/8) Epoch 2, batch 18950, loss[loss=0.1943, simple_loss=0.2585, pruned_loss=0.06503, over 4931.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2373, pruned_loss=0.05254, over 972812.16 frames.], batch size: 39, lr: 6.74e-04
+2022-05-04 07:28:09,468 INFO [train.py:715] (3/8) Epoch 2, batch 19000, loss[loss=0.175, simple_loss=0.2302, pruned_loss=0.05988, over 4803.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2371, pruned_loss=0.05266, over 971675.86 frames.], batch size: 21, lr: 6.73e-04
+2022-05-04 07:28:50,997 INFO [train.py:715] (3/8) Epoch 2, batch 19050, loss[loss=0.1498, simple_loss=0.2185, pruned_loss=0.04052, over 4851.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2366, pruned_loss=0.05185, over 971598.96 frames.], batch size: 20, lr: 6.73e-04
+2022-05-04 07:29:32,579 INFO [train.py:715] (3/8) Epoch 2, batch 19100, loss[loss=0.1683, simple_loss=0.241, pruned_loss=0.04778, over 4859.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2368, pruned_loss=0.05208, over 971945.75 frames.], batch size: 20, lr: 6.73e-04
+2022-05-04 07:30:13,197 INFO [train.py:715] (3/8) Epoch 2, batch 19150, loss[loss=0.1328, simple_loss=0.2119, pruned_loss=0.02684, over 4805.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2355, pruned_loss=0.05117, over 971651.71 frames.], batch size: 13, lr: 6.73e-04
+2022-05-04 07:30:53,906 INFO [train.py:715] (3/8) Epoch 2, batch 19200, loss[loss=0.1639, simple_loss=0.2347, pruned_loss=0.04657, over 4969.00 frames.], tot_loss[loss=0.169, simple_loss=0.236, pruned_loss=0.05099, over 972162.34 frames.], batch size: 15, lr: 6.73e-04
+2022-05-04 07:31:35,014 INFO [train.py:715] (3/8) Epoch 2, batch 19250, loss[loss=0.1478, simple_loss=0.2123, pruned_loss=0.04164, over 4838.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2352, pruned_loss=0.05066, over 972961.24 frames.], batch size: 15, lr: 6.72e-04
+2022-05-04 07:32:15,457 INFO [train.py:715] (3/8) Epoch 2, batch 19300, loss[loss=0.192, simple_loss=0.251, pruned_loss=0.06647, over 4974.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2359, pruned_loss=0.05155, over 972533.61 frames.], batch size: 39, lr: 6.72e-04
+2022-05-04 07:32:55,611 INFO [train.py:715] (3/8) Epoch 2, batch 19350, loss[loss=0.2059, simple_loss=0.2669, pruned_loss=0.07244, over 4947.00 frames.], tot_loss[loss=0.17, simple_loss=0.2364, pruned_loss=0.05177, over 972650.43 frames.], batch size: 39, lr: 6.72e-04
+2022-05-04 07:33:36,558 INFO [train.py:715] (3/8) Epoch 2, batch 19400, loss[loss=0.2362, simple_loss=0.2909, pruned_loss=0.09075, over 4849.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2362, pruned_loss=0.05178, over 973325.26 frames.], batch size: 20, lr: 6.72e-04
+2022-05-04 07:34:18,481 INFO [train.py:715] (3/8) Epoch 2, batch 19450, loss[loss=0.1965, simple_loss=0.2628, pruned_loss=0.0651, over 4791.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2369, pruned_loss=0.05225, over 973179.39 frames.], batch size: 18, lr: 6.72e-04
+2022-05-04 07:34:58,699 INFO [train.py:715] (3/8) Epoch 2, batch 19500, loss[loss=0.162, simple_loss=0.2373, pruned_loss=0.04331, over 4815.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2374, pruned_loss=0.05202, over 973814.52 frames.], batch size: 13, lr: 6.72e-04
+2022-05-04 07:35:38,981 INFO [train.py:715] (3/8) Epoch 2, batch 19550, loss[loss=0.1752, simple_loss=0.2323, pruned_loss=0.05906, over 4738.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2365, pruned_loss=0.05137, over 973016.15 frames.], batch size: 16, lr: 6.71e-04
+2022-05-04 07:36:20,456 INFO [train.py:715] (3/8) Epoch 2, batch 19600, loss[loss=0.1529, simple_loss=0.2374, pruned_loss=0.03418, over 4810.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2372, pruned_loss=0.05189, over 973002.38 frames.], batch size: 26, lr: 6.71e-04
+2022-05-04 07:37:01,111 INFO [train.py:715] (3/8) Epoch 2, batch 19650, loss[loss=0.1601, simple_loss=0.2386, pruned_loss=0.04081, over 4825.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2374, pruned_loss=0.05175, over 973280.33 frames.], batch size: 25, lr: 6.71e-04
+2022-05-04 07:37:40,950 INFO [train.py:715] (3/8) Epoch 2, batch 19700, loss[loss=0.1556, simple_loss=0.2192, pruned_loss=0.04599, over 4934.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2353, pruned_loss=0.05064, over 973344.52 frames.], batch size: 18, lr: 6.71e-04
+2022-05-04 07:38:21,841 INFO [train.py:715] (3/8) Epoch 2, batch 19750, loss[loss=0.2276, simple_loss=0.2769, pruned_loss=0.08915, over 4821.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2358, pruned_loss=0.05113, over 972413.77 frames.], batch size: 15, lr: 6.71e-04
+2022-05-04 07:39:02,974 INFO [train.py:715] (3/8) Epoch 2, batch 19800, loss[loss=0.1918, simple_loss=0.2578, pruned_loss=0.06293, over 4875.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2364, pruned_loss=0.0513, over 972728.34 frames.], batch size: 20, lr: 6.70e-04
+2022-05-04 07:39:42,769 INFO [train.py:715] (3/8) Epoch 2, batch 19850, loss[loss=0.1553, simple_loss=0.2274, pruned_loss=0.04161, over 4770.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2364, pruned_loss=0.05127, over 972463.98 frames.], batch size: 17, lr: 6.70e-04
+2022-05-04 07:40:23,483 INFO [train.py:715] (3/8) Epoch 2, batch 19900, loss[loss=0.1543, simple_loss=0.2271, pruned_loss=0.04076, over 4811.00 frames.], tot_loss[loss=0.1703, simple_loss=0.237, pruned_loss=0.05175, over 972823.95 frames.], batch size: 25, lr: 6.70e-04
+2022-05-04 07:41:04,462 INFO [train.py:715] (3/8) Epoch 2, batch 19950, loss[loss=0.1691, simple_loss=0.2354, pruned_loss=0.05141, over 4807.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2371, pruned_loss=0.05232, over 972921.05 frames.], batch size: 25, lr: 6.70e-04
+2022-05-04 07:41:44,810 INFO [train.py:715] (3/8) Epoch 2, batch 20000, loss[loss=0.1636, simple_loss=0.2164, pruned_loss=0.05545, over 4649.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2369, pruned_loss=0.05169, over 973118.81 frames.], batch size: 13, lr: 6.70e-04
+2022-05-04 07:42:25,545 INFO [train.py:715] (3/8) Epoch 2, batch 20050, loss[loss=0.1659, simple_loss=0.2404, pruned_loss=0.04566, over 4933.00 frames.], tot_loss[loss=0.1695, simple_loss=0.236, pruned_loss=0.05146, over 973317.76 frames.], batch size: 29, lr: 6.69e-04
+2022-05-04 07:43:06,876 INFO [train.py:715] (3/8) Epoch 2, batch 20100, loss[loss=0.1672, simple_loss=0.2459, pruned_loss=0.04427, over 4871.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2363, pruned_loss=0.05164, over 973116.30 frames.], batch size: 22, lr: 6.69e-04
+2022-05-04 07:43:48,582 INFO [train.py:715] (3/8) Epoch 2, batch 20150, loss[loss=0.1373, simple_loss=0.218, pruned_loss=0.02826, over 4964.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2368, pruned_loss=0.05173, over 972684.07 frames.], batch size: 24, lr: 6.69e-04
+2022-05-04 07:44:28,875 INFO [train.py:715] (3/8) Epoch 2, batch 20200, loss[loss=0.1508, simple_loss=0.2119, pruned_loss=0.04485, over 4752.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2365, pruned_loss=0.05155, over 972098.53 frames.], batch size: 16, lr: 6.69e-04
+2022-05-04 07:45:10,317 INFO [train.py:715] (3/8) Epoch 2, batch 20250, loss[loss=0.1529, simple_loss=0.2215, pruned_loss=0.04217, over 4755.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2363, pruned_loss=0.05116, over 972191.51 frames.], batch size: 19, lr: 6.69e-04
+2022-05-04 07:45:52,274 INFO [train.py:715] (3/8) Epoch 2, batch 20300, loss[loss=0.1686, simple_loss=0.2323, pruned_loss=0.0525, over 4847.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2381, pruned_loss=0.05249, over 972840.65 frames.], batch size: 34, lr: 6.69e-04
+2022-05-04 07:46:33,091 INFO [train.py:715] (3/8) Epoch 2, batch 20350, loss[loss=0.1291, simple_loss=0.2084, pruned_loss=0.0249, over 4803.00 frames.], tot_loss[loss=0.1704, simple_loss=0.237, pruned_loss=0.05196, over 972316.05 frames.], batch size: 25, lr: 6.68e-04
+2022-05-04 07:47:14,062 INFO [train.py:715] (3/8) Epoch 2, batch 20400, loss[loss=0.1933, simple_loss=0.2532, pruned_loss=0.06676, over 4811.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2378, pruned_loss=0.0527, over 971792.89 frames.], batch size: 25, lr: 6.68e-04
+2022-05-04 07:47:56,153 INFO [train.py:715] (3/8) Epoch 2, batch 20450, loss[loss=0.1516, simple_loss=0.2179, pruned_loss=0.04264, over 4850.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2376, pruned_loss=0.05294, over 971542.49 frames.], batch size: 32, lr: 6.68e-04
+2022-05-04 07:48:37,714 INFO [train.py:715] (3/8) Epoch 2, batch 20500, loss[loss=0.1762, simple_loss=0.2459, pruned_loss=0.0532, over 4821.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2376, pruned_loss=0.05265, over 971671.00 frames.], batch size: 21, lr: 6.68e-04
+2022-05-04 07:49:18,508 INFO [train.py:715] (3/8) Epoch 2, batch 20550, loss[loss=0.1735, simple_loss=0.2396, pruned_loss=0.05363, over 4939.00 frames.], tot_loss[loss=0.1715, simple_loss=0.238, pruned_loss=0.05247, over 971478.08 frames.], batch size: 21, lr: 6.68e-04
+2022-05-04 07:49:59,711 INFO [train.py:715] (3/8) Epoch 2, batch 20600, loss[loss=0.1954, simple_loss=0.2545, pruned_loss=0.06812, over 4797.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2386, pruned_loss=0.05292, over 972369.69 frames.], batch size: 24, lr: 6.67e-04
+2022-05-04 07:50:41,269 INFO [train.py:715] (3/8) Epoch 2, batch 20650, loss[loss=0.1408, simple_loss=0.2102, pruned_loss=0.03566, over 4792.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2378, pruned_loss=0.05232, over 971760.31 frames.], batch size: 12, lr: 6.67e-04
+2022-05-04 07:51:22,509 INFO [train.py:715] (3/8) Epoch 2, batch 20700, loss[loss=0.1626, simple_loss=0.2242, pruned_loss=0.05051, over 4850.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2374, pruned_loss=0.0525, over 971828.30 frames.], batch size: 30, lr: 6.67e-04
+2022-05-04 07:52:03,038 INFO [train.py:715] (3/8) Epoch 2, batch 20750, loss[loss=0.1661, simple_loss=0.2415, pruned_loss=0.04532, over 4967.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2367, pruned_loss=0.05186, over 972336.82 frames.], batch size: 24, lr: 6.67e-04
+2022-05-04 07:52:44,282 INFO [train.py:715] (3/8) Epoch 2, batch 20800, loss[loss=0.1408, simple_loss=0.2157, pruned_loss=0.03302, over 4830.00 frames.], tot_loss[loss=0.17, simple_loss=0.2366, pruned_loss=0.05168, over 972610.26 frames.], batch size: 12, lr: 6.67e-04
+2022-05-04 07:53:25,484 INFO [train.py:715] (3/8) Epoch 2, batch 20850, loss[loss=0.1868, simple_loss=0.2593, pruned_loss=0.05717, over 4933.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2382, pruned_loss=0.05256, over 972799.63 frames.], batch size: 35, lr: 6.66e-04
+2022-05-04 07:54:06,140 INFO [train.py:715] (3/8) Epoch 2, batch 20900, loss[loss=0.158, simple_loss=0.2413, pruned_loss=0.03733, over 4766.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2384, pruned_loss=0.0523, over 973432.50 frames.], batch size: 19, lr: 6.66e-04
+2022-05-04 07:54:47,192 INFO [train.py:715] (3/8) Epoch 2, batch 20950, loss[loss=0.1634, simple_loss=0.2291, pruned_loss=0.04884, over 4889.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2376, pruned_loss=0.05209, over 973381.52 frames.], batch size: 16, lr: 6.66e-04
+2022-05-04 07:55:28,390 INFO [train.py:715] (3/8) Epoch 2, batch 21000, loss[loss=0.1704, simple_loss=0.2357, pruned_loss=0.05252, over 4779.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2374, pruned_loss=0.05188, over 973690.63 frames.], batch size: 18, lr: 6.66e-04
+2022-05-04 07:55:28,391 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 07:55:39,043 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1174, simple_loss=0.2036, pruned_loss=0.01562, over 914524.00 frames.
+2022-05-04 07:56:20,520 INFO [train.py:715] (3/8) Epoch 2, batch 21050, loss[loss=0.1581, simple_loss=0.2119, pruned_loss=0.0521, over 4884.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2383, pruned_loss=0.05257, over 974145.01 frames.], batch size: 13, lr: 6.66e-04
+2022-05-04 07:57:00,992 INFO [train.py:715] (3/8) Epoch 2, batch 21100, loss[loss=0.1461, simple_loss=0.213, pruned_loss=0.03955, over 4685.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2377, pruned_loss=0.05241, over 974138.76 frames.], batch size: 15, lr: 6.66e-04
+2022-05-04 07:57:41,497 INFO [train.py:715] (3/8) Epoch 2, batch 21150, loss[loss=0.1752, simple_loss=0.248, pruned_loss=0.05117, over 4919.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2372, pruned_loss=0.05186, over 974331.96 frames.], batch size: 23, lr: 6.65e-04
+2022-05-04 07:58:22,039 INFO [train.py:715] (3/8) Epoch 2, batch 21200, loss[loss=0.1513, simple_loss=0.2151, pruned_loss=0.0437, over 4906.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2363, pruned_loss=0.05109, over 973810.34 frames.], batch size: 19, lr: 6.65e-04
+2022-05-04 07:59:02,135 INFO [train.py:715] (3/8) Epoch 2, batch 21250, loss[loss=0.1618, simple_loss=0.2288, pruned_loss=0.04737, over 4905.00 frames.], tot_loss[loss=0.169, simple_loss=0.2358, pruned_loss=0.05104, over 973604.47 frames.], batch size: 22, lr: 6.65e-04
+2022-05-04 07:59:42,849 INFO [train.py:715] (3/8) Epoch 2, batch 21300, loss[loss=0.1939, simple_loss=0.2618, pruned_loss=0.063, over 4756.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2362, pruned_loss=0.05124, over 972677.26 frames.], batch size: 16, lr: 6.65e-04
+2022-05-04 08:00:23,557 INFO [train.py:715] (3/8) Epoch 2, batch 21350, loss[loss=0.1553, simple_loss=0.216, pruned_loss=0.0473, over 4684.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2362, pruned_loss=0.05099, over 973047.35 frames.], batch size: 15, lr: 6.65e-04
+2022-05-04 08:01:04,862 INFO [train.py:715] (3/8) Epoch 2, batch 21400, loss[loss=0.1933, simple_loss=0.2528, pruned_loss=0.06691, over 4767.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2359, pruned_loss=0.05111, over 973251.52 frames.], batch size: 18, lr: 6.64e-04
+2022-05-04 08:01:45,135 INFO [train.py:715] (3/8) Epoch 2, batch 21450, loss[loss=0.1876, simple_loss=0.2478, pruned_loss=0.06369, over 4931.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2365, pruned_loss=0.05136, over 972431.93 frames.], batch size: 39, lr: 6.64e-04
+2022-05-04 08:02:26,066 INFO [train.py:715] (3/8) Epoch 2, batch 21500, loss[loss=0.1482, simple_loss=0.2184, pruned_loss=0.03897, over 4820.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2363, pruned_loss=0.05124, over 972324.05 frames.], batch size: 26, lr: 6.64e-04
+2022-05-04 08:03:07,356 INFO [train.py:715] (3/8) Epoch 2, batch 21550, loss[loss=0.1792, simple_loss=0.242, pruned_loss=0.05821, over 4789.00 frames.], tot_loss[loss=0.1712, simple_loss=0.237, pruned_loss=0.05268, over 971884.89 frames.], batch size: 17, lr: 6.64e-04
+2022-05-04 08:03:47,339 INFO [train.py:715] (3/8) Epoch 2, batch 21600, loss[loss=0.199, simple_loss=0.257, pruned_loss=0.07054, over 4959.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2366, pruned_loss=0.05232, over 971778.95 frames.], batch size: 35, lr: 6.64e-04
+2022-05-04 08:04:28,569 INFO [train.py:715] (3/8) Epoch 2, batch 21650, loss[loss=0.2207, simple_loss=0.2709, pruned_loss=0.08528, over 4905.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2377, pruned_loss=0.05246, over 972457.05 frames.], batch size: 17, lr: 6.64e-04
+2022-05-04 08:05:10,114 INFO [train.py:715] (3/8) Epoch 2, batch 21700, loss[loss=0.1375, simple_loss=0.2117, pruned_loss=0.03158, over 4773.00 frames.], tot_loss[loss=0.172, simple_loss=0.2384, pruned_loss=0.05284, over 972742.41 frames.], batch size: 18, lr: 6.63e-04
+2022-05-04 08:05:50,691 INFO [train.py:715] (3/8) Epoch 2, batch 21750, loss[loss=0.1672, simple_loss=0.2402, pruned_loss=0.04708, over 4800.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2371, pruned_loss=0.05234, over 972835.79 frames.], batch size: 17, lr: 6.63e-04
+2022-05-04 08:06:31,758 INFO [train.py:715] (3/8) Epoch 2, batch 21800, loss[loss=0.1758, simple_loss=0.2463, pruned_loss=0.05265, over 4926.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2372, pruned_loss=0.05286, over 973357.38 frames.], batch size: 23, lr: 6.63e-04
+2022-05-04 08:07:12,178 INFO [train.py:715] (3/8) Epoch 2, batch 21850, loss[loss=0.1775, simple_loss=0.2355, pruned_loss=0.0597, over 4876.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2378, pruned_loss=0.05323, over 972499.60 frames.], batch size: 20, lr: 6.63e-04
+2022-05-04 08:07:53,264 INFO [train.py:715] (3/8) Epoch 2, batch 21900, loss[loss=0.1374, simple_loss=0.202, pruned_loss=0.03638, over 4934.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2369, pruned_loss=0.05233, over 972787.47 frames.], batch size: 29, lr: 6.63e-04
+2022-05-04 08:08:33,958 INFO [train.py:715] (3/8) Epoch 2, batch 21950, loss[loss=0.1322, simple_loss=0.199, pruned_loss=0.03276, over 4779.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2362, pruned_loss=0.05163, over 972281.02 frames.], batch size: 14, lr: 6.62e-04
+2022-05-04 08:09:15,720 INFO [train.py:715] (3/8) Epoch 2, batch 22000, loss[loss=0.1709, simple_loss=0.2433, pruned_loss=0.04924, over 4937.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2369, pruned_loss=0.05208, over 972524.70 frames.], batch size: 21, lr: 6.62e-04
+2022-05-04 08:09:57,813 INFO [train.py:715] (3/8) Epoch 2, batch 22050, loss[loss=0.149, simple_loss=0.2238, pruned_loss=0.03705, over 4929.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2373, pruned_loss=0.05248, over 972532.85 frames.], batch size: 23, lr: 6.62e-04
+2022-05-04 08:10:38,624 INFO [train.py:715] (3/8) Epoch 2, batch 22100, loss[loss=0.1724, simple_loss=0.2438, pruned_loss=0.05054, over 4756.00 frames.], tot_loss[loss=0.1706, simple_loss=0.237, pruned_loss=0.05214, over 972247.44 frames.], batch size: 16, lr: 6.62e-04
+2022-05-04 08:11:20,102 INFO [train.py:715] (3/8) Epoch 2, batch 22150, loss[loss=0.1608, simple_loss=0.2193, pruned_loss=0.05114, over 4954.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2366, pruned_loss=0.05155, over 971399.39 frames.], batch size: 21, lr: 6.62e-04
+2022-05-04 08:12:01,865 INFO [train.py:715] (3/8) Epoch 2, batch 22200, loss[loss=0.1381, simple_loss=0.2153, pruned_loss=0.0304, over 4751.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2361, pruned_loss=0.05129, over 970634.81 frames.], batch size: 19, lr: 6.62e-04
+2022-05-04 08:12:43,328 INFO [train.py:715] (3/8) Epoch 2, batch 22250, loss[loss=0.1752, simple_loss=0.2487, pruned_loss=0.05084, over 4782.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2364, pruned_loss=0.05122, over 971104.75 frames.], batch size: 17, lr: 6.61e-04
+2022-05-04 08:13:24,125 INFO [train.py:715] (3/8) Epoch 2, batch 22300, loss[loss=0.1676, simple_loss=0.2446, pruned_loss=0.04528, over 4872.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2375, pruned_loss=0.05158, over 971623.72 frames.], batch size: 22, lr: 6.61e-04
+2022-05-04 08:14:05,210 INFO [train.py:715] (3/8) Epoch 2, batch 22350, loss[loss=0.1525, simple_loss=0.2285, pruned_loss=0.03826, over 4888.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2377, pruned_loss=0.05198, over 971503.47 frames.], batch size: 19, lr: 6.61e-04
+2022-05-04 08:14:46,092 INFO [train.py:715] (3/8) Epoch 2, batch 22400, loss[loss=0.1659, simple_loss=0.2239, pruned_loss=0.05391, over 4965.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2371, pruned_loss=0.05177, over 971580.76 frames.], batch size: 24, lr: 6.61e-04
+2022-05-04 08:15:26,446 INFO [train.py:715] (3/8) Epoch 2, batch 22450, loss[loss=0.1616, simple_loss=0.2165, pruned_loss=0.05337, over 4896.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2372, pruned_loss=0.05188, over 971784.60 frames.], batch size: 19, lr: 6.61e-04
+2022-05-04 08:16:07,664 INFO [train.py:715] (3/8) Epoch 2, batch 22500, loss[loss=0.1587, simple_loss=0.2217, pruned_loss=0.04784, over 4865.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2373, pruned_loss=0.05193, over 971826.53 frames.], batch size: 16, lr: 6.61e-04
+2022-05-04 08:16:48,519 INFO [train.py:715] (3/8) Epoch 2, batch 22550, loss[loss=0.1918, simple_loss=0.2614, pruned_loss=0.06106, over 4739.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2372, pruned_loss=0.05164, over 972295.78 frames.], batch size: 16, lr: 6.60e-04
+2022-05-04 08:17:29,224 INFO [train.py:715] (3/8) Epoch 2, batch 22600, loss[loss=0.149, simple_loss=0.2133, pruned_loss=0.04236, over 4799.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2362, pruned_loss=0.05139, over 971929.46 frames.], batch size: 12, lr: 6.60e-04
+2022-05-04 08:18:09,992 INFO [train.py:715] (3/8) Epoch 2, batch 22650, loss[loss=0.1837, simple_loss=0.2457, pruned_loss=0.06088, over 4821.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2365, pruned_loss=0.05136, over 971351.84 frames.], batch size: 15, lr: 6.60e-04
+2022-05-04 08:18:50,670 INFO [train.py:715] (3/8) Epoch 2, batch 22700, loss[loss=0.1912, simple_loss=0.2604, pruned_loss=0.06095, over 4884.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2373, pruned_loss=0.05163, over 972579.74 frames.], batch size: 39, lr: 6.60e-04
+2022-05-04 08:19:31,400 INFO [train.py:715] (3/8) Epoch 2, batch 22750, loss[loss=0.1879, simple_loss=0.2686, pruned_loss=0.05357, over 4931.00 frames.], tot_loss[loss=0.171, simple_loss=0.2375, pruned_loss=0.05224, over 971764.39 frames.], batch size: 23, lr: 6.60e-04
+2022-05-04 08:20:12,247 INFO [train.py:715] (3/8) Epoch 2, batch 22800, loss[loss=0.1778, simple_loss=0.2437, pruned_loss=0.05597, over 4865.00 frames.], tot_loss[loss=0.17, simple_loss=0.2372, pruned_loss=0.05138, over 971277.57 frames.], batch size: 20, lr: 6.59e-04
+2022-05-04 08:20:53,299 INFO [train.py:715] (3/8) Epoch 2, batch 22850, loss[loss=0.1495, simple_loss=0.2215, pruned_loss=0.0387, over 4831.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2369, pruned_loss=0.05139, over 972381.54 frames.], batch size: 15, lr: 6.59e-04
+2022-05-04 08:21:34,654 INFO [train.py:715] (3/8) Epoch 2, batch 22900, loss[loss=0.166, simple_loss=0.2296, pruned_loss=0.05123, over 4864.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2382, pruned_loss=0.05213, over 973166.82 frames.], batch size: 16, lr: 6.59e-04
+2022-05-04 08:22:15,451 INFO [train.py:715] (3/8) Epoch 2, batch 22950, loss[loss=0.1741, simple_loss=0.2413, pruned_loss=0.0535, over 4834.00 frames.], tot_loss[loss=0.1713, simple_loss=0.238, pruned_loss=0.05229, over 972934.90 frames.], batch size: 13, lr: 6.59e-04
+2022-05-04 08:22:56,049 INFO [train.py:715] (3/8) Epoch 2, batch 23000, loss[loss=0.1732, simple_loss=0.2488, pruned_loss=0.0488, over 4917.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2366, pruned_loss=0.05133, over 972473.42 frames.], batch size: 29, lr: 6.59e-04
+2022-05-04 08:23:37,065 INFO [train.py:715] (3/8) Epoch 2, batch 23050, loss[loss=0.1283, simple_loss=0.1894, pruned_loss=0.03355, over 4777.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2364, pruned_loss=0.05146, over 971870.18 frames.], batch size: 14, lr: 6.59e-04
+2022-05-04 08:24:17,896 INFO [train.py:715] (3/8) Epoch 2, batch 23100, loss[loss=0.1758, simple_loss=0.2463, pruned_loss=0.05265, over 4798.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2373, pruned_loss=0.0518, over 971895.80 frames.], batch size: 21, lr: 6.58e-04
+2022-05-04 08:24:58,401 INFO [train.py:715] (3/8) Epoch 2, batch 23150, loss[loss=0.1772, simple_loss=0.2427, pruned_loss=0.05579, over 4845.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2377, pruned_loss=0.05183, over 972195.15 frames.], batch size: 15, lr: 6.58e-04
+2022-05-04 08:25:39,720 INFO [train.py:715] (3/8) Epoch 2, batch 23200, loss[loss=0.1516, simple_loss=0.2294, pruned_loss=0.03692, over 4969.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2378, pruned_loss=0.05181, over 972083.25 frames.], batch size: 35, lr: 6.58e-04
+2022-05-04 08:26:20,395 INFO [train.py:715] (3/8) Epoch 2, batch 23250, loss[loss=0.1603, simple_loss=0.2257, pruned_loss=0.04749, over 4947.00 frames.], tot_loss[loss=0.17, simple_loss=0.2367, pruned_loss=0.05161, over 972092.35 frames.], batch size: 21, lr: 6.58e-04
+2022-05-04 08:27:00,749 INFO [train.py:715] (3/8) Epoch 2, batch 23300, loss[loss=0.1687, simple_loss=0.2373, pruned_loss=0.05011, over 4860.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2368, pruned_loss=0.05125, over 972074.38 frames.], batch size: 20, lr: 6.58e-04
+2022-05-04 08:27:41,446 INFO [train.py:715] (3/8) Epoch 2, batch 23350, loss[loss=0.1548, simple_loss=0.2215, pruned_loss=0.04398, over 4896.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2367, pruned_loss=0.05134, over 972235.17 frames.], batch size: 22, lr: 6.57e-04
+2022-05-04 08:28:22,395 INFO [train.py:715] (3/8) Epoch 2, batch 23400, loss[loss=0.1939, simple_loss=0.2595, pruned_loss=0.06413, over 4922.00 frames.], tot_loss[loss=0.169, simple_loss=0.2361, pruned_loss=0.05099, over 972759.57 frames.], batch size: 29, lr: 6.57e-04
+2022-05-04 08:29:03,326 INFO [train.py:715] (3/8) Epoch 2, batch 23450, loss[loss=0.1679, simple_loss=0.2336, pruned_loss=0.05105, over 4983.00 frames.], tot_loss[loss=0.169, simple_loss=0.2359, pruned_loss=0.051, over 973286.20 frames.], batch size: 25, lr: 6.57e-04
+2022-05-04 08:29:43,618 INFO [train.py:715] (3/8) Epoch 2, batch 23500, loss[loss=0.1365, simple_loss=0.1901, pruned_loss=0.04148, over 4759.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2351, pruned_loss=0.05034, over 973114.65 frames.], batch size: 12, lr: 6.57e-04
+2022-05-04 08:30:24,810 INFO [train.py:715] (3/8) Epoch 2, batch 23550, loss[loss=0.1613, simple_loss=0.2281, pruned_loss=0.04728, over 4966.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2357, pruned_loss=0.05056, over 973075.01 frames.], batch size: 39, lr: 6.57e-04
+2022-05-04 08:31:05,703 INFO [train.py:715] (3/8) Epoch 2, batch 23600, loss[loss=0.1819, simple_loss=0.2571, pruned_loss=0.05336, over 4808.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2366, pruned_loss=0.05087, over 973040.02 frames.], batch size: 21, lr: 6.57e-04
+2022-05-04 08:31:45,439 INFO [train.py:715] (3/8) Epoch 2, batch 23650, loss[loss=0.1846, simple_loss=0.2393, pruned_loss=0.06498, over 4749.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2363, pruned_loss=0.051, over 972722.07 frames.], batch size: 16, lr: 6.56e-04
+2022-05-04 08:32:27,506 INFO [train.py:715] (3/8) Epoch 2, batch 23700, loss[loss=0.1511, simple_loss=0.2247, pruned_loss=0.03875, over 4932.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2358, pruned_loss=0.05076, over 972635.25 frames.], batch size: 23, lr: 6.56e-04
+2022-05-04 08:33:07,930 INFO [train.py:715] (3/8) Epoch 2, batch 23750, loss[loss=0.1824, simple_loss=0.2436, pruned_loss=0.06062, over 4911.00 frames.], tot_loss[loss=0.169, simple_loss=0.236, pruned_loss=0.05103, over 973502.56 frames.], batch size: 38, lr: 6.56e-04
+2022-05-04 08:33:48,795 INFO [train.py:715] (3/8) Epoch 2, batch 23800, loss[loss=0.1501, simple_loss=0.2019, pruned_loss=0.04914, over 4831.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2364, pruned_loss=0.05159, over 973936.46 frames.], batch size: 12, lr: 6.56e-04
+2022-05-04 08:34:29,262 INFO [train.py:715] (3/8) Epoch 2, batch 23850, loss[loss=0.1579, simple_loss=0.2251, pruned_loss=0.04536, over 4760.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2379, pruned_loss=0.05282, over 973946.18 frames.], batch size: 19, lr: 6.56e-04
+2022-05-04 08:35:10,697 INFO [train.py:715] (3/8) Epoch 2, batch 23900, loss[loss=0.1807, simple_loss=0.2474, pruned_loss=0.057, over 4870.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2367, pruned_loss=0.05226, over 973211.41 frames.], batch size: 20, lr: 6.56e-04
+2022-05-04 08:35:51,714 INFO [train.py:715] (3/8) Epoch 2, batch 23950, loss[loss=0.1571, simple_loss=0.2227, pruned_loss=0.04574, over 4703.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2367, pruned_loss=0.05196, over 972642.88 frames.], batch size: 15, lr: 6.55e-04
+2022-05-04 08:36:31,650 INFO [train.py:715] (3/8) Epoch 2, batch 24000, loss[loss=0.1386, simple_loss=0.2059, pruned_loss=0.03561, over 4747.00 frames.], tot_loss[loss=0.1708, simple_loss=0.237, pruned_loss=0.05227, over 972339.20 frames.], batch size: 16, lr: 6.55e-04
+2022-05-04 08:36:31,651 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 08:36:40,333 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1168, simple_loss=0.2032, pruned_loss=0.01518, over 914524.00 frames.
+2022-05-04 08:37:20,458 INFO [train.py:715] (3/8) Epoch 2, batch 24050, loss[loss=0.1773, simple_loss=0.2448, pruned_loss=0.05497, over 4944.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2365, pruned_loss=0.05186, over 972795.80 frames.], batch size: 39, lr: 6.55e-04
+2022-05-04 08:38:01,993 INFO [train.py:715] (3/8) Epoch 2, batch 24100, loss[loss=0.1369, simple_loss=0.2155, pruned_loss=0.02917, over 4804.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2368, pruned_loss=0.05172, over 972049.86 frames.], batch size: 21, lr: 6.55e-04
+2022-05-04 08:38:42,993 INFO [train.py:715] (3/8) Epoch 2, batch 24150, loss[loss=0.1751, simple_loss=0.2532, pruned_loss=0.04844, over 4950.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2354, pruned_loss=0.05071, over 972535.95 frames.], batch size: 21, lr: 6.55e-04
+2022-05-04 08:39:24,313 INFO [train.py:715] (3/8) Epoch 2, batch 24200, loss[loss=0.1715, simple_loss=0.2439, pruned_loss=0.04954, over 4749.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2354, pruned_loss=0.05061, over 973192.56 frames.], batch size: 16, lr: 6.55e-04
+2022-05-04 08:40:05,194 INFO [train.py:715] (3/8) Epoch 2, batch 24250, loss[loss=0.2039, simple_loss=0.2581, pruned_loss=0.07484, over 4872.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2355, pruned_loss=0.05074, over 973100.06 frames.], batch size: 16, lr: 6.54e-04
+2022-05-04 08:40:46,096 INFO [train.py:715] (3/8) Epoch 2, batch 24300, loss[loss=0.1811, simple_loss=0.2487, pruned_loss=0.05673, over 4810.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2356, pruned_loss=0.05073, over 972594.52 frames.], batch size: 21, lr: 6.54e-04
+2022-05-04 08:41:26,661 INFO [train.py:715] (3/8) Epoch 2, batch 24350, loss[loss=0.1774, simple_loss=0.2367, pruned_loss=0.05909, over 4972.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2351, pruned_loss=0.05062, over 972775.83 frames.], batch size: 15, lr: 6.54e-04
+2022-05-04 08:42:06,526 INFO [train.py:715] (3/8) Epoch 2, batch 24400, loss[loss=0.1982, simple_loss=0.259, pruned_loss=0.06871, over 4899.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2344, pruned_loss=0.05021, over 972903.79 frames.], batch size: 19, lr: 6.54e-04
+2022-05-04 08:42:47,544 INFO [train.py:715] (3/8) Epoch 2, batch 24450, loss[loss=0.1549, simple_loss=0.2165, pruned_loss=0.04668, over 4807.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2343, pruned_loss=0.05065, over 972426.12 frames.], batch size: 25, lr: 6.54e-04
+2022-05-04 08:43:27,490 INFO [train.py:715] (3/8) Epoch 2, batch 24500, loss[loss=0.1553, simple_loss=0.2162, pruned_loss=0.04717, over 4919.00 frames.], tot_loss[loss=0.168, simple_loss=0.2344, pruned_loss=0.05077, over 972324.43 frames.], batch size: 17, lr: 6.53e-04
+2022-05-04 08:44:07,366 INFO [train.py:715] (3/8) Epoch 2, batch 24550, loss[loss=0.1805, simple_loss=0.2545, pruned_loss=0.05329, over 4862.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2354, pruned_loss=0.0508, over 972096.74 frames.], batch size: 32, lr: 6.53e-04
+2022-05-04 08:44:46,875 INFO [train.py:715] (3/8) Epoch 2, batch 24600, loss[loss=0.1931, simple_loss=0.2587, pruned_loss=0.06373, over 4788.00 frames.], tot_loss[loss=0.169, simple_loss=0.2359, pruned_loss=0.05107, over 971446.36 frames.], batch size: 18, lr: 6.53e-04
+2022-05-04 08:45:27,055 INFO [train.py:715] (3/8) Epoch 2, batch 24650, loss[loss=0.1278, simple_loss=0.1991, pruned_loss=0.02825, over 4743.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2358, pruned_loss=0.05078, over 972036.04 frames.], batch size: 12, lr: 6.53e-04
+2022-05-04 08:46:06,408 INFO [train.py:715] (3/8) Epoch 2, batch 24700, loss[loss=0.1499, simple_loss=0.2127, pruned_loss=0.0435, over 4840.00 frames.], tot_loss[loss=0.17, simple_loss=0.237, pruned_loss=0.05149, over 972096.61 frames.], batch size: 13, lr: 6.53e-04
+2022-05-04 08:46:45,152 INFO [train.py:715] (3/8) Epoch 2, batch 24750, loss[loss=0.1581, simple_loss=0.2431, pruned_loss=0.03657, over 4937.00 frames.], tot_loss[loss=0.1697, simple_loss=0.237, pruned_loss=0.05121, over 972045.06 frames.], batch size: 39, lr: 6.53e-04
+2022-05-04 08:47:24,977 INFO [train.py:715] (3/8) Epoch 2, batch 24800, loss[loss=0.1645, simple_loss=0.2333, pruned_loss=0.04782, over 4844.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2369, pruned_loss=0.05165, over 972599.85 frames.], batch size: 30, lr: 6.52e-04
+2022-05-04 08:48:04,570 INFO [train.py:715] (3/8) Epoch 2, batch 24850, loss[loss=0.1757, simple_loss=0.2354, pruned_loss=0.05801, over 4892.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2368, pruned_loss=0.05168, over 972274.67 frames.], batch size: 17, lr: 6.52e-04
+2022-05-04 08:48:43,454 INFO [train.py:715] (3/8) Epoch 2, batch 24900, loss[loss=0.1326, simple_loss=0.1896, pruned_loss=0.0378, over 4805.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2359, pruned_loss=0.0512, over 971970.74 frames.], batch size: 12, lr: 6.52e-04
+2022-05-04 08:49:22,923 INFO [train.py:715] (3/8) Epoch 2, batch 24950, loss[loss=0.1691, simple_loss=0.2272, pruned_loss=0.05552, over 4780.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2363, pruned_loss=0.05166, over 971977.51 frames.], batch size: 12, lr: 6.52e-04
+2022-05-04 08:50:02,456 INFO [train.py:715] (3/8) Epoch 2, batch 25000, loss[loss=0.2037, simple_loss=0.2537, pruned_loss=0.07685, over 4869.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2361, pruned_loss=0.05152, over 972480.32 frames.], batch size: 38, lr: 6.52e-04
+2022-05-04 08:50:41,254 INFO [train.py:715] (3/8) Epoch 2, batch 25050, loss[loss=0.166, simple_loss=0.2282, pruned_loss=0.0519, over 4648.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2368, pruned_loss=0.05221, over 972078.20 frames.], batch size: 13, lr: 6.52e-04
+2022-05-04 08:51:19,781 INFO [train.py:715] (3/8) Epoch 2, batch 25100, loss[loss=0.1743, simple_loss=0.2397, pruned_loss=0.05443, over 4818.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2365, pruned_loss=0.05194, over 972165.23 frames.], batch size: 12, lr: 6.51e-04
+2022-05-04 08:51:59,031 INFO [train.py:715] (3/8) Epoch 2, batch 25150, loss[loss=0.179, simple_loss=0.2605, pruned_loss=0.04874, over 4974.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2372, pruned_loss=0.05231, over 972001.19 frames.], batch size: 24, lr: 6.51e-04
+2022-05-04 08:52:37,844 INFO [train.py:715] (3/8) Epoch 2, batch 25200, loss[loss=0.1843, simple_loss=0.258, pruned_loss=0.05533, over 4808.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2376, pruned_loss=0.05252, over 971322.42 frames.], batch size: 21, lr: 6.51e-04
+2022-05-04 08:53:16,878 INFO [train.py:715] (3/8) Epoch 2, batch 25250, loss[loss=0.1729, simple_loss=0.2373, pruned_loss=0.0542, over 4702.00 frames.], tot_loss[loss=0.172, simple_loss=0.2385, pruned_loss=0.05279, over 972142.19 frames.], batch size: 15, lr: 6.51e-04
+2022-05-04 08:53:55,852 INFO [train.py:715] (3/8) Epoch 2, batch 25300, loss[loss=0.1609, simple_loss=0.2294, pruned_loss=0.04623, over 4779.00 frames.], tot_loss[loss=0.1717, simple_loss=0.238, pruned_loss=0.05266, over 972968.92 frames.], batch size: 14, lr: 6.51e-04
+2022-05-04 08:54:35,073 INFO [train.py:715] (3/8) Epoch 2, batch 25350, loss[loss=0.179, simple_loss=0.2409, pruned_loss=0.05853, over 4879.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2387, pruned_loss=0.05334, over 973760.80 frames.], batch size: 16, lr: 6.51e-04
+2022-05-04 08:55:14,149 INFO [train.py:715] (3/8) Epoch 2, batch 25400, loss[loss=0.1646, simple_loss=0.2291, pruned_loss=0.05006, over 4947.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2373, pruned_loss=0.0525, over 972609.10 frames.], batch size: 35, lr: 6.50e-04
+2022-05-04 08:55:52,993 INFO [train.py:715] (3/8) Epoch 2, batch 25450, loss[loss=0.1641, simple_loss=0.2332, pruned_loss=0.04756, over 4971.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2369, pruned_loss=0.05196, over 973147.86 frames.], batch size: 24, lr: 6.50e-04
+2022-05-04 08:56:32,020 INFO [train.py:715] (3/8) Epoch 2, batch 25500, loss[loss=0.1696, simple_loss=0.2323, pruned_loss=0.05341, over 4871.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2374, pruned_loss=0.0517, over 972465.52 frames.], batch size: 16, lr: 6.50e-04
+2022-05-04 08:57:11,299 INFO [train.py:715] (3/8) Epoch 2, batch 25550, loss[loss=0.1729, simple_loss=0.2214, pruned_loss=0.06226, over 4776.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2376, pruned_loss=0.05164, over 971829.46 frames.], batch size: 12, lr: 6.50e-04
+2022-05-04 08:57:50,301 INFO [train.py:715] (3/8) Epoch 2, batch 25600, loss[loss=0.1739, simple_loss=0.2382, pruned_loss=0.05481, over 4880.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2374, pruned_loss=0.05179, over 972007.54 frames.], batch size: 22, lr: 6.50e-04
+2022-05-04 08:58:29,642 INFO [train.py:715] (3/8) Epoch 2, batch 25650, loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.03652, over 4950.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2373, pruned_loss=0.05194, over 973318.06 frames.], batch size: 21, lr: 6.50e-04
+2022-05-04 08:59:09,550 INFO [train.py:715] (3/8) Epoch 2, batch 25700, loss[loss=0.1615, simple_loss=0.2257, pruned_loss=0.04865, over 4945.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2365, pruned_loss=0.05069, over 973269.66 frames.], batch size: 21, lr: 6.49e-04
+2022-05-04 08:59:48,686 INFO [train.py:715] (3/8) Epoch 2, batch 25750, loss[loss=0.1502, simple_loss=0.2204, pruned_loss=0.03996, over 4804.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2357, pruned_loss=0.05022, over 972954.60 frames.], batch size: 21, lr: 6.49e-04
+2022-05-04 09:00:27,440 INFO [train.py:715] (3/8) Epoch 2, batch 25800, loss[loss=0.1493, simple_loss=0.2153, pruned_loss=0.04161, over 4841.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2364, pruned_loss=0.05055, over 972612.77 frames.], batch size: 12, lr: 6.49e-04
+2022-05-04 09:01:06,417 INFO [train.py:715] (3/8) Epoch 2, batch 25850, loss[loss=0.169, simple_loss=0.2423, pruned_loss=0.04785, over 4954.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2361, pruned_loss=0.05024, over 972021.79 frames.], batch size: 21, lr: 6.49e-04
+2022-05-04 09:01:46,183 INFO [train.py:715] (3/8) Epoch 2, batch 25900, loss[loss=0.1699, simple_loss=0.2426, pruned_loss=0.04859, over 4886.00 frames.], tot_loss[loss=0.1674, simple_loss=0.235, pruned_loss=0.04987, over 971790.38 frames.], batch size: 17, lr: 6.49e-04
+2022-05-04 09:02:25,987 INFO [train.py:715] (3/8) Epoch 2, batch 25950, loss[loss=0.1745, simple_loss=0.2344, pruned_loss=0.05733, over 4873.00 frames.], tot_loss[loss=0.1679, simple_loss=0.235, pruned_loss=0.05038, over 971995.37 frames.], batch size: 22, lr: 6.49e-04
+2022-05-04 09:03:05,064 INFO [train.py:715] (3/8) Epoch 2, batch 26000, loss[loss=0.1617, simple_loss=0.2251, pruned_loss=0.0492, over 4986.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2356, pruned_loss=0.05066, over 972326.20 frames.], batch size: 31, lr: 6.48e-04
+2022-05-04 09:03:44,734 INFO [train.py:715] (3/8) Epoch 2, batch 26050, loss[loss=0.1509, simple_loss=0.225, pruned_loss=0.03844, over 4808.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2358, pruned_loss=0.05077, over 972064.28 frames.], batch size: 21, lr: 6.48e-04
+2022-05-04 09:04:24,304 INFO [train.py:715] (3/8) Epoch 2, batch 26100, loss[loss=0.1738, simple_loss=0.2383, pruned_loss=0.05467, over 4823.00 frames.], tot_loss[loss=0.1687, simple_loss=0.236, pruned_loss=0.05076, over 972627.11 frames.], batch size: 26, lr: 6.48e-04
+2022-05-04 09:05:03,478 INFO [train.py:715] (3/8) Epoch 2, batch 26150, loss[loss=0.1451, simple_loss=0.2146, pruned_loss=0.03782, over 4956.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2355, pruned_loss=0.05076, over 972710.17 frames.], batch size: 15, lr: 6.48e-04
+2022-05-04 09:05:42,983 INFO [train.py:715] (3/8) Epoch 2, batch 26200, loss[loss=0.1899, simple_loss=0.2482, pruned_loss=0.06581, over 4823.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2357, pruned_loss=0.05082, over 971460.18 frames.], batch size: 13, lr: 6.48e-04
+2022-05-04 09:06:22,732 INFO [train.py:715] (3/8) Epoch 2, batch 26250, loss[loss=0.1601, simple_loss=0.2255, pruned_loss=0.04731, over 4907.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2357, pruned_loss=0.0506, over 971931.37 frames.], batch size: 19, lr: 6.48e-04
+2022-05-04 09:07:02,319 INFO [train.py:715] (3/8) Epoch 2, batch 26300, loss[loss=0.1307, simple_loss=0.2012, pruned_loss=0.03016, over 4778.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2352, pruned_loss=0.05014, over 971516.20 frames.], batch size: 14, lr: 6.47e-04
+2022-05-04 09:07:40,826 INFO [train.py:715] (3/8) Epoch 2, batch 26350, loss[loss=0.1664, simple_loss=0.2331, pruned_loss=0.04984, over 4984.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2354, pruned_loss=0.05016, over 971482.75 frames.], batch size: 27, lr: 6.47e-04
+2022-05-04 09:08:23,928 INFO [train.py:715] (3/8) Epoch 2, batch 26400, loss[loss=0.1892, simple_loss=0.2668, pruned_loss=0.05585, over 4874.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2361, pruned_loss=0.05013, over 971120.31 frames.], batch size: 22, lr: 6.47e-04
+2022-05-04 09:09:03,683 INFO [train.py:715] (3/8) Epoch 2, batch 26450, loss[loss=0.1769, simple_loss=0.253, pruned_loss=0.05035, over 4897.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2362, pruned_loss=0.05003, over 971156.44 frames.], batch size: 19, lr: 6.47e-04
+2022-05-04 09:09:42,580 INFO [train.py:715] (3/8) Epoch 2, batch 26500, loss[loss=0.1241, simple_loss=0.1988, pruned_loss=0.0247, over 4812.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2355, pruned_loss=0.05016, over 971454.35 frames.], batch size: 27, lr: 6.47e-04
+2022-05-04 09:10:22,391 INFO [train.py:715] (3/8) Epoch 2, batch 26550, loss[loss=0.1759, simple_loss=0.2459, pruned_loss=0.05301, over 4895.00 frames.], tot_loss[loss=0.168, simple_loss=0.2353, pruned_loss=0.05032, over 971730.23 frames.], batch size: 22, lr: 6.46e-04
+2022-05-04 09:11:02,381 INFO [train.py:715] (3/8) Epoch 2, batch 26600, loss[loss=0.1566, simple_loss=0.2169, pruned_loss=0.04813, over 4924.00 frames.], tot_loss[loss=0.1676, simple_loss=0.235, pruned_loss=0.05016, over 971128.25 frames.], batch size: 29, lr: 6.46e-04
+2022-05-04 09:11:41,994 INFO [train.py:715] (3/8) Epoch 2, batch 26650, loss[loss=0.1879, simple_loss=0.2622, pruned_loss=0.05683, over 4739.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2348, pruned_loss=0.04998, over 971526.78 frames.], batch size: 16, lr: 6.46e-04
+2022-05-04 09:12:21,003 INFO [train.py:715] (3/8) Epoch 2, batch 26700, loss[loss=0.1674, simple_loss=0.2349, pruned_loss=0.04992, over 4944.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2351, pruned_loss=0.05037, over 971667.07 frames.], batch size: 21, lr: 6.46e-04
+2022-05-04 09:13:00,966 INFO [train.py:715] (3/8) Epoch 2, batch 26750, loss[loss=0.1799, simple_loss=0.2455, pruned_loss=0.0571, over 4980.00 frames.], tot_loss[loss=0.1702, simple_loss=0.237, pruned_loss=0.05173, over 970885.60 frames.], batch size: 26, lr: 6.46e-04
+2022-05-04 09:13:40,193 INFO [train.py:715] (3/8) Epoch 2, batch 26800, loss[loss=0.1525, simple_loss=0.2255, pruned_loss=0.03974, over 4769.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2374, pruned_loss=0.05241, over 972152.27 frames.], batch size: 19, lr: 6.46e-04
+2022-05-04 09:14:19,182 INFO [train.py:715] (3/8) Epoch 2, batch 26850, loss[loss=0.143, simple_loss=0.1994, pruned_loss=0.04331, over 4796.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2366, pruned_loss=0.05193, over 971347.83 frames.], batch size: 12, lr: 6.45e-04
+2022-05-04 09:14:58,117 INFO [train.py:715] (3/8) Epoch 2, batch 26900, loss[loss=0.2166, simple_loss=0.2694, pruned_loss=0.0819, over 4892.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2374, pruned_loss=0.05192, over 972400.79 frames.], batch size: 22, lr: 6.45e-04
+2022-05-04 09:15:37,580 INFO [train.py:715] (3/8) Epoch 2, batch 26950, loss[loss=0.1729, simple_loss=0.2449, pruned_loss=0.05043, over 4926.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2368, pruned_loss=0.05169, over 971872.88 frames.], batch size: 29, lr: 6.45e-04
+2022-05-04 09:16:16,468 INFO [train.py:715] (3/8) Epoch 2, batch 27000, loss[loss=0.1604, simple_loss=0.2276, pruned_loss=0.04661, over 4974.00 frames.], tot_loss[loss=0.17, simple_loss=0.2368, pruned_loss=0.05164, over 971846.30 frames.], batch size: 14, lr: 6.45e-04
+2022-05-04 09:16:16,469 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 09:16:25,254 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1164, simple_loss=0.2027, pruned_loss=0.01502, over 914524.00 frames.
+2022-05-04 09:17:03,618 INFO [train.py:715] (3/8) Epoch 2, batch 27050, loss[loss=0.1784, simple_loss=0.2421, pruned_loss=0.05739, over 4843.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2367, pruned_loss=0.05148, over 971391.05 frames.], batch size: 30, lr: 6.45e-04
+2022-05-04 09:17:42,882 INFO [train.py:715] (3/8) Epoch 2, batch 27100, loss[loss=0.179, simple_loss=0.2443, pruned_loss=0.05688, over 4825.00 frames.], tot_loss[loss=0.1712, simple_loss=0.238, pruned_loss=0.0522, over 971152.02 frames.], batch size: 27, lr: 6.45e-04
+2022-05-04 09:18:22,884 INFO [train.py:715] (3/8) Epoch 2, batch 27150, loss[loss=0.1661, simple_loss=0.2303, pruned_loss=0.05096, over 4790.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2378, pruned_loss=0.05203, over 970529.99 frames.], batch size: 24, lr: 6.44e-04
+2022-05-04 09:19:02,264 INFO [train.py:715] (3/8) Epoch 2, batch 27200, loss[loss=0.1532, simple_loss=0.2234, pruned_loss=0.04152, over 4909.00 frames.], tot_loss[loss=0.1703, simple_loss=0.237, pruned_loss=0.05183, over 970940.42 frames.], batch size: 18, lr: 6.44e-04
+2022-05-04 09:19:41,120 INFO [train.py:715] (3/8) Epoch 2, batch 27250, loss[loss=0.1611, simple_loss=0.23, pruned_loss=0.04608, over 4734.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2361, pruned_loss=0.05127, over 971329.34 frames.], batch size: 16, lr: 6.44e-04
+2022-05-04 09:20:20,689 INFO [train.py:715] (3/8) Epoch 2, batch 27300, loss[loss=0.1819, simple_loss=0.258, pruned_loss=0.05289, over 4747.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2354, pruned_loss=0.05067, over 971438.04 frames.], batch size: 19, lr: 6.44e-04
+2022-05-04 09:20:59,722 INFO [train.py:715] (3/8) Epoch 2, batch 27350, loss[loss=0.1821, simple_loss=0.2513, pruned_loss=0.05641, over 4968.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2366, pruned_loss=0.05121, over 971177.17 frames.], batch size: 24, lr: 6.44e-04
+2022-05-04 09:21:38,801 INFO [train.py:715] (3/8) Epoch 2, batch 27400, loss[loss=0.2021, simple_loss=0.2652, pruned_loss=0.06955, over 4896.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2369, pruned_loss=0.05113, over 971987.22 frames.], batch size: 16, lr: 6.44e-04
+2022-05-04 09:22:17,479 INFO [train.py:715] (3/8) Epoch 2, batch 27450, loss[loss=0.158, simple_loss=0.2205, pruned_loss=0.04774, over 4812.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2364, pruned_loss=0.05125, over 971461.89 frames.], batch size: 25, lr: 6.44e-04
+2022-05-04 09:22:57,212 INFO [train.py:715] (3/8) Epoch 2, batch 27500, loss[loss=0.1603, simple_loss=0.2251, pruned_loss=0.04771, over 4939.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2362, pruned_loss=0.05124, over 972360.67 frames.], batch size: 29, lr: 6.43e-04
+2022-05-04 09:23:37,092 INFO [train.py:715] (3/8) Epoch 2, batch 27550, loss[loss=0.2153, simple_loss=0.2853, pruned_loss=0.07266, over 4913.00 frames.], tot_loss[loss=0.1691, simple_loss=0.236, pruned_loss=0.05112, over 971719.85 frames.], batch size: 17, lr: 6.43e-04
+2022-05-04 09:24:16,420 INFO [train.py:715] (3/8) Epoch 2, batch 27600, loss[loss=0.1247, simple_loss=0.2037, pruned_loss=0.0229, over 4770.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2359, pruned_loss=0.05087, over 972010.08 frames.], batch size: 12, lr: 6.43e-04
+2022-05-04 09:24:55,996 INFO [train.py:715] (3/8) Epoch 2, batch 27650, loss[loss=0.1642, simple_loss=0.2364, pruned_loss=0.04602, over 4645.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2357, pruned_loss=0.05101, over 972340.23 frames.], batch size: 13, lr: 6.43e-04
+2022-05-04 09:25:36,591 INFO [train.py:715] (3/8) Epoch 2, batch 27700, loss[loss=0.1777, simple_loss=0.2314, pruned_loss=0.06207, over 4971.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2343, pruned_loss=0.05037, over 972762.84 frames.], batch size: 15, lr: 6.43e-04
+2022-05-04 09:26:16,919 INFO [train.py:715] (3/8) Epoch 2, batch 27750, loss[loss=0.1761, simple_loss=0.2458, pruned_loss=0.05318, over 4778.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2353, pruned_loss=0.05107, over 972510.53 frames.], batch size: 18, lr: 6.43e-04
+2022-05-04 09:26:56,303 INFO [train.py:715] (3/8) Epoch 2, batch 27800, loss[loss=0.2109, simple_loss=0.2686, pruned_loss=0.0766, over 4933.00 frames.], tot_loss[loss=0.1683, simple_loss=0.235, pruned_loss=0.05079, over 971579.88 frames.], batch size: 23, lr: 6.42e-04
+2022-05-04 09:27:36,594 INFO [train.py:715] (3/8) Epoch 2, batch 27850, loss[loss=0.1429, simple_loss=0.2084, pruned_loss=0.03872, over 4929.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2336, pruned_loss=0.05004, over 971809.18 frames.], batch size: 18, lr: 6.42e-04
+2022-05-04 09:28:15,904 INFO [train.py:715] (3/8) Epoch 2, batch 27900, loss[loss=0.1148, simple_loss=0.1882, pruned_loss=0.02067, over 4917.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2334, pruned_loss=0.04979, over 971370.46 frames.], batch size: 23, lr: 6.42e-04
+2022-05-04 09:28:55,088 INFO [train.py:715] (3/8) Epoch 2, batch 27950, loss[loss=0.1517, simple_loss=0.2156, pruned_loss=0.04391, over 4763.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2342, pruned_loss=0.05051, over 972112.94 frames.], batch size: 12, lr: 6.42e-04
+2022-05-04 09:29:34,670 INFO [train.py:715] (3/8) Epoch 2, batch 28000, loss[loss=0.1764, simple_loss=0.2346, pruned_loss=0.05909, over 4876.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2339, pruned_loss=0.05025, over 972706.99 frames.], batch size: 30, lr: 6.42e-04
+2022-05-04 09:30:15,043 INFO [train.py:715] (3/8) Epoch 2, batch 28050, loss[loss=0.1656, simple_loss=0.2336, pruned_loss=0.04882, over 4815.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2336, pruned_loss=0.04979, over 972215.41 frames.], batch size: 26, lr: 6.42e-04
+2022-05-04 09:30:54,019 INFO [train.py:715] (3/8) Epoch 2, batch 28100, loss[loss=0.1353, simple_loss=0.2106, pruned_loss=0.02994, over 4951.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2341, pruned_loss=0.05014, over 973105.26 frames.], batch size: 29, lr: 6.41e-04
+2022-05-04 09:31:33,557 INFO [train.py:715] (3/8) Epoch 2, batch 28150, loss[loss=0.1444, simple_loss=0.2135, pruned_loss=0.03772, over 4700.00 frames.], tot_loss[loss=0.168, simple_loss=0.2348, pruned_loss=0.0506, over 972953.48 frames.], batch size: 15, lr: 6.41e-04
+2022-05-04 09:32:13,296 INFO [train.py:715] (3/8) Epoch 2, batch 28200, loss[loss=0.1619, simple_loss=0.2302, pruned_loss=0.04677, over 4978.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2347, pruned_loss=0.05032, over 973562.02 frames.], batch size: 28, lr: 6.41e-04
+2022-05-04 09:32:52,899 INFO [train.py:715] (3/8) Epoch 2, batch 28250, loss[loss=0.133, simple_loss=0.1983, pruned_loss=0.03383, over 4803.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2344, pruned_loss=0.05018, over 973186.85 frames.], batch size: 14, lr: 6.41e-04
+2022-05-04 09:33:31,977 INFO [train.py:715] (3/8) Epoch 2, batch 28300, loss[loss=0.1596, simple_loss=0.2202, pruned_loss=0.04955, over 4846.00 frames.], tot_loss[loss=0.167, simple_loss=0.2343, pruned_loss=0.04988, over 972529.97 frames.], batch size: 13, lr: 6.41e-04
+2022-05-04 09:34:11,318 INFO [train.py:715] (3/8) Epoch 2, batch 28350, loss[loss=0.1639, simple_loss=0.236, pruned_loss=0.04583, over 4912.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2351, pruned_loss=0.05049, over 972506.15 frames.], batch size: 17, lr: 6.41e-04
+2022-05-04 09:34:51,511 INFO [train.py:715] (3/8) Epoch 2, batch 28400, loss[loss=0.1766, simple_loss=0.246, pruned_loss=0.05357, over 4975.00 frames.], tot_loss[loss=0.168, simple_loss=0.235, pruned_loss=0.05048, over 972181.42 frames.], batch size: 28, lr: 6.40e-04
+2022-05-04 09:35:30,759 INFO [train.py:715] (3/8) Epoch 2, batch 28450, loss[loss=0.1871, simple_loss=0.2483, pruned_loss=0.06298, over 4757.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2354, pruned_loss=0.05072, over 971875.64 frames.], batch size: 16, lr: 6.40e-04
+2022-05-04 09:36:10,160 INFO [train.py:715] (3/8) Epoch 2, batch 28500, loss[loss=0.1769, simple_loss=0.237, pruned_loss=0.05843, over 4862.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2346, pruned_loss=0.05017, over 972461.56 frames.], batch size: 20, lr: 6.40e-04
+2022-05-04 09:36:50,108 INFO [train.py:715] (3/8) Epoch 2, batch 28550, loss[loss=0.2152, simple_loss=0.2802, pruned_loss=0.07508, over 4838.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2357, pruned_loss=0.05064, over 972529.14 frames.], batch size: 30, lr: 6.40e-04
+2022-05-04 09:37:30,235 INFO [train.py:715] (3/8) Epoch 2, batch 28600, loss[loss=0.1779, simple_loss=0.2531, pruned_loss=0.05134, over 4777.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2362, pruned_loss=0.05108, over 972647.34 frames.], batch size: 17, lr: 6.40e-04
+2022-05-04 09:38:09,270 INFO [train.py:715] (3/8) Epoch 2, batch 28650, loss[loss=0.1375, simple_loss=0.2113, pruned_loss=0.03186, over 4896.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2346, pruned_loss=0.05017, over 972270.78 frames.], batch size: 19, lr: 6.40e-04
+2022-05-04 09:38:49,123 INFO [train.py:715] (3/8) Epoch 2, batch 28700, loss[loss=0.1487, simple_loss=0.227, pruned_loss=0.03521, over 4924.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2351, pruned_loss=0.05066, over 972507.10 frames.], batch size: 18, lr: 6.39e-04
+2022-05-04 09:39:29,582 INFO [train.py:715] (3/8) Epoch 2, batch 28750, loss[loss=0.1258, simple_loss=0.2045, pruned_loss=0.02355, over 4817.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2346, pruned_loss=0.05051, over 971940.00 frames.], batch size: 26, lr: 6.39e-04
+2022-05-04 09:40:08,509 INFO [train.py:715] (3/8) Epoch 2, batch 28800, loss[loss=0.189, simple_loss=0.2505, pruned_loss=0.06376, over 4865.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2352, pruned_loss=0.05115, over 970867.26 frames.], batch size: 20, lr: 6.39e-04
+2022-05-04 09:40:48,102 INFO [train.py:715] (3/8) Epoch 2, batch 28850, loss[loss=0.1753, simple_loss=0.2517, pruned_loss=0.04943, over 4829.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2352, pruned_loss=0.05062, over 971515.57 frames.], batch size: 15, lr: 6.39e-04
+2022-05-04 09:41:28,107 INFO [train.py:715] (3/8) Epoch 2, batch 28900, loss[loss=0.1832, simple_loss=0.259, pruned_loss=0.05367, over 4911.00 frames.], tot_loss[loss=0.167, simple_loss=0.2344, pruned_loss=0.04985, over 971532.42 frames.], batch size: 19, lr: 6.39e-04
+2022-05-04 09:42:07,484 INFO [train.py:715] (3/8) Epoch 2, batch 28950, loss[loss=0.1569, simple_loss=0.229, pruned_loss=0.04243, over 4794.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2352, pruned_loss=0.05048, over 971589.91 frames.], batch size: 21, lr: 6.39e-04
+2022-05-04 09:42:46,856 INFO [train.py:715] (3/8) Epoch 2, batch 29000, loss[loss=0.1337, simple_loss=0.2087, pruned_loss=0.0294, over 4916.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2362, pruned_loss=0.05097, over 972035.07 frames.], batch size: 18, lr: 6.38e-04
+2022-05-04 09:43:26,613 INFO [train.py:715] (3/8) Epoch 2, batch 29050, loss[loss=0.167, simple_loss=0.2442, pruned_loss=0.04486, over 4930.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2368, pruned_loss=0.05118, over 972558.97 frames.], batch size: 29, lr: 6.38e-04
+2022-05-04 09:44:06,287 INFO [train.py:715] (3/8) Epoch 2, batch 29100, loss[loss=0.162, simple_loss=0.2262, pruned_loss=0.04894, over 4811.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2369, pruned_loss=0.05147, over 972771.05 frames.], batch size: 27, lr: 6.38e-04
+2022-05-04 09:44:45,461 INFO [train.py:715] (3/8) Epoch 2, batch 29150, loss[loss=0.1693, simple_loss=0.2424, pruned_loss=0.04806, over 4800.00 frames.], tot_loss[loss=0.169, simple_loss=0.2358, pruned_loss=0.05114, over 972045.26 frames.], batch size: 17, lr: 6.38e-04
+2022-05-04 09:45:24,944 INFO [train.py:715] (3/8) Epoch 2, batch 29200, loss[loss=0.159, simple_loss=0.2183, pruned_loss=0.04986, over 4788.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2351, pruned_loss=0.05075, over 971851.67 frames.], batch size: 14, lr: 6.38e-04
+2022-05-04 09:46:05,374 INFO [train.py:715] (3/8) Epoch 2, batch 29250, loss[loss=0.1621, simple_loss=0.2352, pruned_loss=0.04456, over 4696.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2359, pruned_loss=0.05118, over 971263.44 frames.], batch size: 15, lr: 6.38e-04
+2022-05-04 09:46:44,477 INFO [train.py:715] (3/8) Epoch 2, batch 29300, loss[loss=0.1648, simple_loss=0.2446, pruned_loss=0.04255, over 4765.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2354, pruned_loss=0.05069, over 971378.75 frames.], batch size: 19, lr: 6.37e-04
+2022-05-04 09:47:23,247 INFO [train.py:715] (3/8) Epoch 2, batch 29350, loss[loss=0.1817, simple_loss=0.2388, pruned_loss=0.06233, over 4831.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2345, pruned_loss=0.0501, over 971590.32 frames.], batch size: 26, lr: 6.37e-04
+2022-05-04 09:48:02,465 INFO [train.py:715] (3/8) Epoch 2, batch 29400, loss[loss=0.1688, simple_loss=0.2337, pruned_loss=0.05197, over 4871.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2344, pruned_loss=0.04997, over 971064.82 frames.], batch size: 20, lr: 6.37e-04
+2022-05-04 09:48:41,885 INFO [train.py:715] (3/8) Epoch 2, batch 29450, loss[loss=0.1542, simple_loss=0.2159, pruned_loss=0.04627, over 4969.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2347, pruned_loss=0.05034, over 972569.43 frames.], batch size: 15, lr: 6.37e-04
+2022-05-04 09:49:20,754 INFO [train.py:715] (3/8) Epoch 2, batch 29500, loss[loss=0.1792, simple_loss=0.2369, pruned_loss=0.06071, over 4912.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2347, pruned_loss=0.05022, over 972395.12 frames.], batch size: 17, lr: 6.37e-04
+2022-05-04 09:49:59,766 INFO [train.py:715] (3/8) Epoch 2, batch 29550, loss[loss=0.2178, simple_loss=0.272, pruned_loss=0.08181, over 4930.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2355, pruned_loss=0.05106, over 973380.70 frames.], batch size: 21, lr: 6.37e-04
+2022-05-04 09:50:39,177 INFO [train.py:715] (3/8) Epoch 2, batch 29600, loss[loss=0.1585, simple_loss=0.2259, pruned_loss=0.0455, over 4788.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2346, pruned_loss=0.05013, over 973800.71 frames.], batch size: 17, lr: 6.37e-04
+2022-05-04 09:51:18,364 INFO [train.py:715] (3/8) Epoch 2, batch 29650, loss[loss=0.1557, simple_loss=0.2366, pruned_loss=0.0374, over 4763.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2352, pruned_loss=0.05035, over 973444.93 frames.], batch size: 12, lr: 6.36e-04
+2022-05-04 09:51:57,126 INFO [train.py:715] (3/8) Epoch 2, batch 29700, loss[loss=0.1312, simple_loss=0.2008, pruned_loss=0.03077, over 4880.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2354, pruned_loss=0.05012, over 973229.92 frames.], batch size: 22, lr: 6.36e-04
+2022-05-04 09:52:36,251 INFO [train.py:715] (3/8) Epoch 2, batch 29750, loss[loss=0.1746, simple_loss=0.2481, pruned_loss=0.05058, over 4848.00 frames.], tot_loss[loss=0.168, simple_loss=0.2358, pruned_loss=0.0501, over 972610.52 frames.], batch size: 32, lr: 6.36e-04
+2022-05-04 09:53:15,368 INFO [train.py:715] (3/8) Epoch 2, batch 29800, loss[loss=0.224, simple_loss=0.2834, pruned_loss=0.08236, over 4864.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2367, pruned_loss=0.0509, over 972691.20 frames.], batch size: 30, lr: 6.36e-04
+2022-05-04 09:53:53,998 INFO [train.py:715] (3/8) Epoch 2, batch 29850, loss[loss=0.1794, simple_loss=0.2437, pruned_loss=0.05758, over 4792.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2371, pruned_loss=0.05133, over 973400.14 frames.], batch size: 24, lr: 6.36e-04
+2022-05-04 09:54:33,008 INFO [train.py:715] (3/8) Epoch 2, batch 29900, loss[loss=0.1697, simple_loss=0.2333, pruned_loss=0.05305, over 4812.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2357, pruned_loss=0.0508, over 973110.33 frames.], batch size: 13, lr: 6.36e-04
+2022-05-04 09:55:12,828 INFO [train.py:715] (3/8) Epoch 2, batch 29950, loss[loss=0.148, simple_loss=0.2214, pruned_loss=0.03725, over 4956.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2349, pruned_loss=0.04981, over 972340.48 frames.], batch size: 24, lr: 6.35e-04
+2022-05-04 09:55:51,635 INFO [train.py:715] (3/8) Epoch 2, batch 30000, loss[loss=0.1685, simple_loss=0.2324, pruned_loss=0.05227, over 4895.00 frames.], tot_loss[loss=0.1673, simple_loss=0.235, pruned_loss=0.04976, over 973345.76 frames.], batch size: 39, lr: 6.35e-04
+2022-05-04 09:55:51,635 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 09:56:00,453 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1166, simple_loss=0.2028, pruned_loss=0.01515, over 914524.00 frames.
+2022-05-04 09:56:39,115 INFO [train.py:715] (3/8) Epoch 2, batch 30050, loss[loss=0.1852, simple_loss=0.2416, pruned_loss=0.06438, over 4913.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2348, pruned_loss=0.04998, over 973839.28 frames.], batch size: 17, lr: 6.35e-04
+2022-05-04 09:57:18,474 INFO [train.py:715] (3/8) Epoch 2, batch 30100, loss[loss=0.1712, simple_loss=0.2513, pruned_loss=0.04557, over 4938.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2363, pruned_loss=0.05048, over 973788.51 frames.], batch size: 21, lr: 6.35e-04
+2022-05-04 09:57:57,549 INFO [train.py:715] (3/8) Epoch 2, batch 30150, loss[loss=0.1506, simple_loss=0.2257, pruned_loss=0.03775, over 4980.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2349, pruned_loss=0.04951, over 973791.17 frames.], batch size: 15, lr: 6.35e-04
+2022-05-04 09:58:37,029 INFO [train.py:715] (3/8) Epoch 2, batch 30200, loss[loss=0.1548, simple_loss=0.2265, pruned_loss=0.04148, over 4817.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2355, pruned_loss=0.04967, over 972974.96 frames.], batch size: 26, lr: 6.35e-04
+2022-05-04 09:59:15,773 INFO [train.py:715] (3/8) Epoch 2, batch 30250, loss[loss=0.1585, simple_loss=0.2226, pruned_loss=0.04714, over 4837.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2355, pruned_loss=0.04974, over 973995.49 frames.], batch size: 13, lr: 6.34e-04
+2022-05-04 09:59:55,025 INFO [train.py:715] (3/8) Epoch 2, batch 30300, loss[loss=0.1699, simple_loss=0.2344, pruned_loss=0.05266, over 4847.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2354, pruned_loss=0.05001, over 974060.33 frames.], batch size: 32, lr: 6.34e-04
+2022-05-04 10:00:35,003 INFO [train.py:715] (3/8) Epoch 2, batch 30350, loss[loss=0.1435, simple_loss=0.2088, pruned_loss=0.03909, over 4960.00 frames.], tot_loss[loss=0.168, simple_loss=0.2353, pruned_loss=0.05029, over 974480.46 frames.], batch size: 35, lr: 6.34e-04
+2022-05-04 10:01:14,087 INFO [train.py:715] (3/8) Epoch 2, batch 30400, loss[loss=0.1736, simple_loss=0.2459, pruned_loss=0.05069, over 4901.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2357, pruned_loss=0.05056, over 974198.18 frames.], batch size: 19, lr: 6.34e-04
+2022-05-04 10:01:53,191 INFO [train.py:715] (3/8) Epoch 2, batch 30450, loss[loss=0.1846, simple_loss=0.2468, pruned_loss=0.06122, over 4982.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2354, pruned_loss=0.05048, over 974292.07 frames.], batch size: 15, lr: 6.34e-04
+2022-05-04 10:02:32,961 INFO [train.py:715] (3/8) Epoch 2, batch 30500, loss[loss=0.1597, simple_loss=0.2311, pruned_loss=0.04412, over 4830.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2358, pruned_loss=0.05081, over 973573.68 frames.], batch size: 25, lr: 6.34e-04
+2022-05-04 10:03:12,631 INFO [train.py:715] (3/8) Epoch 2, batch 30550, loss[loss=0.1885, simple_loss=0.2566, pruned_loss=0.06019, over 4758.00 frames.], tot_loss[loss=0.169, simple_loss=0.2358, pruned_loss=0.0511, over 973014.50 frames.], batch size: 19, lr: 6.33e-04
+2022-05-04 10:03:51,362 INFO [train.py:715] (3/8) Epoch 2, batch 30600, loss[loss=0.1437, simple_loss=0.2028, pruned_loss=0.0423, over 4864.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2349, pruned_loss=0.05048, over 973131.07 frames.], batch size: 32, lr: 6.33e-04
+2022-05-04 10:04:31,215 INFO [train.py:715] (3/8) Epoch 2, batch 30650, loss[loss=0.1747, simple_loss=0.2396, pruned_loss=0.05489, over 4814.00 frames.], tot_loss[loss=0.169, simple_loss=0.2358, pruned_loss=0.05107, over 973218.80 frames.], batch size: 14, lr: 6.33e-04
+2022-05-04 10:05:11,277 INFO [train.py:715] (3/8) Epoch 2, batch 30700, loss[loss=0.2395, simple_loss=0.2972, pruned_loss=0.09093, over 4808.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2359, pruned_loss=0.05082, over 972855.45 frames.], batch size: 21, lr: 6.33e-04
+2022-05-04 10:05:51,104 INFO [train.py:715] (3/8) Epoch 2, batch 30750, loss[loss=0.1603, simple_loss=0.2327, pruned_loss=0.04391, over 4917.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2353, pruned_loss=0.0506, over 973074.53 frames.], batch size: 18, lr: 6.33e-04
+2022-05-04 10:06:30,171 INFO [train.py:715] (3/8) Epoch 2, batch 30800, loss[loss=0.1529, simple_loss=0.2261, pruned_loss=0.0399, over 4688.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2351, pruned_loss=0.05027, over 972996.88 frames.], batch size: 15, lr: 6.33e-04
+2022-05-04 10:07:09,684 INFO [train.py:715] (3/8) Epoch 2, batch 30850, loss[loss=0.1641, simple_loss=0.2464, pruned_loss=0.04095, over 4965.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2363, pruned_loss=0.05109, over 973148.87 frames.], batch size: 15, lr: 6.33e-04
+2022-05-04 10:07:49,327 INFO [train.py:715] (3/8) Epoch 2, batch 30900, loss[loss=0.1729, simple_loss=0.2625, pruned_loss=0.04168, over 4793.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2364, pruned_loss=0.05107, over 973181.51 frames.], batch size: 17, lr: 6.32e-04
+2022-05-04 10:08:27,845 INFO [train.py:715] (3/8) Epoch 2, batch 30950, loss[loss=0.1493, simple_loss=0.2213, pruned_loss=0.03865, over 4860.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2361, pruned_loss=0.05029, over 973026.51 frames.], batch size: 13, lr: 6.32e-04
+2022-05-04 10:09:07,771 INFO [train.py:715] (3/8) Epoch 2, batch 31000, loss[loss=0.1374, simple_loss=0.2021, pruned_loss=0.0364, over 4901.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2358, pruned_loss=0.05029, over 973822.07 frames.], batch size: 18, lr: 6.32e-04
+2022-05-04 10:09:48,211 INFO [train.py:715] (3/8) Epoch 2, batch 31050, loss[loss=0.1672, simple_loss=0.2306, pruned_loss=0.05187, over 4772.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2357, pruned_loss=0.05007, over 973221.04 frames.], batch size: 14, lr: 6.32e-04
+2022-05-04 10:10:27,688 INFO [train.py:715] (3/8) Epoch 2, batch 31100, loss[loss=0.2004, simple_loss=0.2632, pruned_loss=0.06876, over 4942.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2364, pruned_loss=0.05101, over 974143.45 frames.], batch size: 21, lr: 6.32e-04
+2022-05-04 10:11:07,480 INFO [train.py:715] (3/8) Epoch 2, batch 31150, loss[loss=0.1418, simple_loss=0.2149, pruned_loss=0.03438, over 4772.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2365, pruned_loss=0.05111, over 973647.72 frames.], batch size: 18, lr: 6.32e-04
+2022-05-04 10:11:47,660 INFO [train.py:715] (3/8) Epoch 2, batch 31200, loss[loss=0.1502, simple_loss=0.2234, pruned_loss=0.03848, over 4942.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2355, pruned_loss=0.0509, over 972826.48 frames.], batch size: 21, lr: 6.31e-04
+2022-05-04 10:12:27,442 INFO [train.py:715] (3/8) Epoch 2, batch 31250, loss[loss=0.1524, simple_loss=0.2196, pruned_loss=0.04258, over 4869.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2348, pruned_loss=0.05071, over 972540.51 frames.], batch size: 32, lr: 6.31e-04
+2022-05-04 10:13:06,641 INFO [train.py:715] (3/8) Epoch 2, batch 31300, loss[loss=0.1841, simple_loss=0.2418, pruned_loss=0.06326, over 4991.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2346, pruned_loss=0.05053, over 972769.01 frames.], batch size: 14, lr: 6.31e-04
+2022-05-04 10:13:46,585 INFO [train.py:715] (3/8) Epoch 2, batch 31350, loss[loss=0.1845, simple_loss=0.2556, pruned_loss=0.05672, over 4957.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2352, pruned_loss=0.05056, over 973255.85 frames.], batch size: 15, lr: 6.31e-04
+2022-05-04 10:14:26,952 INFO [train.py:715] (3/8) Epoch 2, batch 31400, loss[loss=0.1606, simple_loss=0.2283, pruned_loss=0.04644, over 4814.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2341, pruned_loss=0.05018, over 972537.74 frames.], batch size: 27, lr: 6.31e-04
+2022-05-04 10:15:06,595 INFO [train.py:715] (3/8) Epoch 2, batch 31450, loss[loss=0.2141, simple_loss=0.2768, pruned_loss=0.07569, over 4846.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2344, pruned_loss=0.0503, over 972645.55 frames.], batch size: 20, lr: 6.31e-04
+2022-05-04 10:15:46,238 INFO [train.py:715] (3/8) Epoch 2, batch 31500, loss[loss=0.1325, simple_loss=0.2108, pruned_loss=0.02712, over 4916.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2346, pruned_loss=0.05014, over 972611.74 frames.], batch size: 17, lr: 6.31e-04
+2022-05-04 10:16:26,032 INFO [train.py:715] (3/8) Epoch 2, batch 31550, loss[loss=0.219, simple_loss=0.2762, pruned_loss=0.08096, over 4737.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2354, pruned_loss=0.05022, over 972512.91 frames.], batch size: 16, lr: 6.30e-04
+2022-05-04 10:17:05,439 INFO [train.py:715] (3/8) Epoch 2, batch 31600, loss[loss=0.1641, simple_loss=0.2334, pruned_loss=0.04741, over 4905.00 frames.], tot_loss[loss=0.1679, simple_loss=0.235, pruned_loss=0.05042, over 971838.36 frames.], batch size: 19, lr: 6.30e-04
+2022-05-04 10:17:44,222 INFO [train.py:715] (3/8) Epoch 2, batch 31650, loss[loss=0.1694, simple_loss=0.2478, pruned_loss=0.04551, over 4698.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2345, pruned_loss=0.04942, over 971452.72 frames.], batch size: 15, lr: 6.30e-04
+2022-05-04 10:18:24,066 INFO [train.py:715] (3/8) Epoch 2, batch 31700, loss[loss=0.1544, simple_loss=0.2216, pruned_loss=0.04364, over 4919.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2348, pruned_loss=0.04974, over 972536.94 frames.], batch size: 18, lr: 6.30e-04
+2022-05-04 10:19:04,303 INFO [train.py:715] (3/8) Epoch 2, batch 31750, loss[loss=0.1739, simple_loss=0.2288, pruned_loss=0.05946, over 4822.00 frames.], tot_loss[loss=0.1676, simple_loss=0.235, pruned_loss=0.05012, over 971757.94 frames.], batch size: 13, lr: 6.30e-04
+2022-05-04 10:19:44,142 INFO [train.py:715] (3/8) Epoch 2, batch 31800, loss[loss=0.1783, simple_loss=0.2581, pruned_loss=0.04927, over 4954.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2353, pruned_loss=0.05012, over 972128.69 frames.], batch size: 21, lr: 6.30e-04
+2022-05-04 10:20:23,462 INFO [train.py:715] (3/8) Epoch 2, batch 31850, loss[loss=0.1779, simple_loss=0.2476, pruned_loss=0.05412, over 4783.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2344, pruned_loss=0.04926, over 972416.34 frames.], batch size: 17, lr: 6.29e-04
+2022-05-04 10:21:02,954 INFO [train.py:715] (3/8) Epoch 2, batch 31900, loss[loss=0.164, simple_loss=0.2407, pruned_loss=0.04369, over 4899.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2339, pruned_loss=0.04933, over 972302.64 frames.], batch size: 19, lr: 6.29e-04
+2022-05-04 10:21:42,553 INFO [train.py:715] (3/8) Epoch 2, batch 31950, loss[loss=0.1694, simple_loss=0.2321, pruned_loss=0.05332, over 4704.00 frames.], tot_loss[loss=0.1665, simple_loss=0.234, pruned_loss=0.04946, over 972364.25 frames.], batch size: 15, lr: 6.29e-04
+2022-05-04 10:22:21,474 INFO [train.py:715] (3/8) Epoch 2, batch 32000, loss[loss=0.145, simple_loss=0.205, pruned_loss=0.04253, over 4781.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2349, pruned_loss=0.05, over 971525.52 frames.], batch size: 18, lr: 6.29e-04
+2022-05-04 10:23:01,106 INFO [train.py:715] (3/8) Epoch 2, batch 32050, loss[loss=0.1626, simple_loss=0.2237, pruned_loss=0.05074, over 4885.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2353, pruned_loss=0.04995, over 970832.12 frames.], batch size: 16, lr: 6.29e-04
+2022-05-04 10:23:41,014 INFO [train.py:715] (3/8) Epoch 2, batch 32100, loss[loss=0.1452, simple_loss=0.2192, pruned_loss=0.0356, over 4926.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2355, pruned_loss=0.04995, over 971655.34 frames.], batch size: 23, lr: 6.29e-04
+2022-05-04 10:24:20,305 INFO [train.py:715] (3/8) Epoch 2, batch 32150, loss[loss=0.1559, simple_loss=0.2202, pruned_loss=0.0458, over 4930.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2353, pruned_loss=0.0498, over 972366.08 frames.], batch size: 23, lr: 6.29e-04
+2022-05-04 10:24:59,277 INFO [train.py:715] (3/8) Epoch 2, batch 32200, loss[loss=0.1914, simple_loss=0.2475, pruned_loss=0.06766, over 4836.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2353, pruned_loss=0.05016, over 972504.74 frames.], batch size: 15, lr: 6.28e-04
+2022-05-04 10:25:39,137 INFO [train.py:715] (3/8) Epoch 2, batch 32250, loss[loss=0.1596, simple_loss=0.2218, pruned_loss=0.0487, over 4978.00 frames.], tot_loss[loss=0.168, simple_loss=0.2353, pruned_loss=0.05034, over 971397.66 frames.], batch size: 35, lr: 6.28e-04
+2022-05-04 10:26:18,493 INFO [train.py:715] (3/8) Epoch 2, batch 32300, loss[loss=0.1563, simple_loss=0.2316, pruned_loss=0.04047, over 4873.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2348, pruned_loss=0.04982, over 971674.43 frames.], batch size: 20, lr: 6.28e-04
+2022-05-04 10:26:57,488 INFO [train.py:715] (3/8) Epoch 2, batch 32350, loss[loss=0.1962, simple_loss=0.2445, pruned_loss=0.07389, over 4701.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2351, pruned_loss=0.05014, over 971027.11 frames.], batch size: 15, lr: 6.28e-04
+2022-05-04 10:27:37,323 INFO [train.py:715] (3/8) Epoch 2, batch 32400, loss[loss=0.1642, simple_loss=0.2271, pruned_loss=0.05064, over 4966.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2356, pruned_loss=0.05073, over 971229.68 frames.], batch size: 28, lr: 6.28e-04
+2022-05-04 10:28:17,091 INFO [train.py:715] (3/8) Epoch 2, batch 32450, loss[loss=0.1464, simple_loss=0.2186, pruned_loss=0.03713, over 4840.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2354, pruned_loss=0.05068, over 972071.23 frames.], batch size: 26, lr: 6.28e-04
+2022-05-04 10:28:56,077 INFO [train.py:715] (3/8) Epoch 2, batch 32500, loss[loss=0.1781, simple_loss=0.242, pruned_loss=0.05707, over 4970.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2343, pruned_loss=0.0501, over 972192.47 frames.], batch size: 31, lr: 6.27e-04
+2022-05-04 10:29:35,592 INFO [train.py:715] (3/8) Epoch 2, batch 32550, loss[loss=0.1626, simple_loss=0.2341, pruned_loss=0.04555, over 4961.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2346, pruned_loss=0.05036, over 973612.10 frames.], batch size: 24, lr: 6.27e-04
+2022-05-04 10:30:15,646 INFO [train.py:715] (3/8) Epoch 2, batch 32600, loss[loss=0.156, simple_loss=0.2307, pruned_loss=0.04061, over 4765.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2352, pruned_loss=0.05025, over 973051.69 frames.], batch size: 14, lr: 6.27e-04
+2022-05-04 10:30:54,904 INFO [train.py:715] (3/8) Epoch 2, batch 32650, loss[loss=0.1558, simple_loss=0.2291, pruned_loss=0.04123, over 4815.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2348, pruned_loss=0.04942, over 972578.38 frames.], batch size: 26, lr: 6.27e-04
+2022-05-04 10:31:33,746 INFO [train.py:715] (3/8) Epoch 2, batch 32700, loss[loss=0.1572, simple_loss=0.2188, pruned_loss=0.04781, over 4814.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2336, pruned_loss=0.04872, over 972464.15 frames.], batch size: 26, lr: 6.27e-04
+2022-05-04 10:32:13,540 INFO [train.py:715] (3/8) Epoch 2, batch 32750, loss[loss=0.1671, simple_loss=0.2271, pruned_loss=0.05353, over 4946.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2349, pruned_loss=0.04969, over 972182.36 frames.], batch size: 39, lr: 6.27e-04
+2022-05-04 10:32:53,521 INFO [train.py:715] (3/8) Epoch 2, batch 32800, loss[loss=0.1924, simple_loss=0.2604, pruned_loss=0.06225, over 4839.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2347, pruned_loss=0.04956, over 972407.10 frames.], batch size: 15, lr: 6.27e-04
+2022-05-04 10:33:32,249 INFO [train.py:715] (3/8) Epoch 2, batch 32850, loss[loss=0.1398, simple_loss=0.2074, pruned_loss=0.03608, over 4905.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2333, pruned_loss=0.04874, over 971932.06 frames.], batch size: 19, lr: 6.26e-04
+2022-05-04 10:34:11,593 INFO [train.py:715] (3/8) Epoch 2, batch 32900, loss[loss=0.1523, simple_loss=0.2341, pruned_loss=0.03519, over 4885.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2326, pruned_loss=0.04781, over 971944.62 frames.], batch size: 19, lr: 6.26e-04
+2022-05-04 10:34:51,513 INFO [train.py:715] (3/8) Epoch 2, batch 32950, loss[loss=0.1555, simple_loss=0.2305, pruned_loss=0.0402, over 4971.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2326, pruned_loss=0.04837, over 972513.12 frames.], batch size: 21, lr: 6.26e-04
+2022-05-04 10:35:30,093 INFO [train.py:715] (3/8) Epoch 2, batch 33000, loss[loss=0.1992, simple_loss=0.2602, pruned_loss=0.0691, over 4901.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2333, pruned_loss=0.04883, over 971869.85 frames.], batch size: 22, lr: 6.26e-04
+2022-05-04 10:35:30,094 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 10:35:38,852 INFO [train.py:742] (3/8) Epoch 2, validation: loss=0.1163, simple_loss=0.2025, pruned_loss=0.01504, over 914524.00 frames.
+2022-05-04 10:36:17,839 INFO [train.py:715] (3/8) Epoch 2, batch 33050, loss[loss=0.1506, simple_loss=0.2389, pruned_loss=0.03114, over 4840.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2343, pruned_loss=0.04916, over 972483.08 frames.], batch size: 26, lr: 6.26e-04
+2022-05-04 10:36:57,380 INFO [train.py:715] (3/8) Epoch 2, batch 33100, loss[loss=0.1577, simple_loss=0.2249, pruned_loss=0.04526, over 4926.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2338, pruned_loss=0.04931, over 972520.29 frames.], batch size: 29, lr: 6.26e-04
+2022-05-04 10:37:37,175 INFO [train.py:715] (3/8) Epoch 2, batch 33150, loss[loss=0.1615, simple_loss=0.2262, pruned_loss=0.04842, over 4815.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2337, pruned_loss=0.04963, over 971313.78 frames.], batch size: 21, lr: 6.25e-04
+2022-05-04 10:38:16,781 INFO [train.py:715] (3/8) Epoch 2, batch 33200, loss[loss=0.1807, simple_loss=0.2447, pruned_loss=0.05829, over 4709.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2332, pruned_loss=0.04958, over 971515.83 frames.], batch size: 15, lr: 6.25e-04
+2022-05-04 10:38:56,316 INFO [train.py:715] (3/8) Epoch 2, batch 33250, loss[loss=0.1635, simple_loss=0.2297, pruned_loss=0.04862, over 4835.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2327, pruned_loss=0.04948, over 971553.31 frames.], batch size: 15, lr: 6.25e-04
+2022-05-04 10:39:35,521 INFO [train.py:715] (3/8) Epoch 2, batch 33300, loss[loss=0.1612, simple_loss=0.2314, pruned_loss=0.04551, over 4935.00 frames.], tot_loss[loss=0.1671, simple_loss=0.234, pruned_loss=0.05015, over 972322.26 frames.], batch size: 29, lr: 6.25e-04
+2022-05-04 10:40:14,693 INFO [train.py:715] (3/8) Epoch 2, batch 33350, loss[loss=0.1745, simple_loss=0.2388, pruned_loss=0.05507, over 4815.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2347, pruned_loss=0.05053, over 972304.82 frames.], batch size: 25, lr: 6.25e-04
+2022-05-04 10:40:53,959 INFO [train.py:715] (3/8) Epoch 2, batch 33400, loss[loss=0.1652, simple_loss=0.2323, pruned_loss=0.049, over 4934.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2347, pruned_loss=0.05047, over 972456.47 frames.], batch size: 23, lr: 6.25e-04
+2022-05-04 10:41:33,180 INFO [train.py:715] (3/8) Epoch 2, batch 33450, loss[loss=0.1295, simple_loss=0.1958, pruned_loss=0.03161, over 4776.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2348, pruned_loss=0.05064, over 972853.51 frames.], batch size: 17, lr: 6.25e-04
+2022-05-04 10:42:13,246 INFO [train.py:715] (3/8) Epoch 2, batch 33500, loss[loss=0.1679, simple_loss=0.2248, pruned_loss=0.05543, over 4799.00 frames.], tot_loss[loss=0.168, simple_loss=0.2348, pruned_loss=0.05064, over 972131.43 frames.], batch size: 14, lr: 6.24e-04
+2022-05-04 10:42:52,005 INFO [train.py:715] (3/8) Epoch 2, batch 33550, loss[loss=0.162, simple_loss=0.2339, pruned_loss=0.045, over 4928.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2345, pruned_loss=0.05002, over 972052.80 frames.], batch size: 18, lr: 6.24e-04
+2022-05-04 10:43:31,503 INFO [train.py:715] (3/8) Epoch 2, batch 33600, loss[loss=0.1556, simple_loss=0.2315, pruned_loss=0.0399, over 4862.00 frames.], tot_loss[loss=0.1665, simple_loss=0.234, pruned_loss=0.04949, over 972412.93 frames.], batch size: 15, lr: 6.24e-04
+2022-05-04 10:44:11,050 INFO [train.py:715] (3/8) Epoch 2, batch 33650, loss[loss=0.23, simple_loss=0.2844, pruned_loss=0.08783, over 4735.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2347, pruned_loss=0.04983, over 972778.88 frames.], batch size: 16, lr: 6.24e-04
+2022-05-04 10:44:50,488 INFO [train.py:715] (3/8) Epoch 2, batch 33700, loss[loss=0.1579, simple_loss=0.2342, pruned_loss=0.04076, over 4837.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2347, pruned_loss=0.04975, over 972573.49 frames.], batch size: 13, lr: 6.24e-04
+2022-05-04 10:45:29,903 INFO [train.py:715] (3/8) Epoch 2, batch 33750, loss[loss=0.1262, simple_loss=0.1892, pruned_loss=0.03157, over 4765.00 frames.], tot_loss[loss=0.166, simple_loss=0.2335, pruned_loss=0.04929, over 971410.71 frames.], batch size: 19, lr: 6.24e-04
+2022-05-04 10:46:09,309 INFO [train.py:715] (3/8) Epoch 2, batch 33800, loss[loss=0.1689, simple_loss=0.2324, pruned_loss=0.05266, over 4851.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2341, pruned_loss=0.04955, over 971701.06 frames.], batch size: 30, lr: 6.23e-04
+2022-05-04 10:46:49,490 INFO [train.py:715] (3/8) Epoch 2, batch 33850, loss[loss=0.2144, simple_loss=0.2722, pruned_loss=0.07825, over 4928.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2342, pruned_loss=0.04927, over 972179.51 frames.], batch size: 39, lr: 6.23e-04
+2022-05-04 10:47:28,885 INFO [train.py:715] (3/8) Epoch 2, batch 33900, loss[loss=0.1618, simple_loss=0.2346, pruned_loss=0.04449, over 4923.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2338, pruned_loss=0.04876, over 971987.71 frames.], batch size: 29, lr: 6.23e-04
+2022-05-04 10:48:08,027 INFO [train.py:715] (3/8) Epoch 2, batch 33950, loss[loss=0.1701, simple_loss=0.2322, pruned_loss=0.05396, over 4807.00 frames.], tot_loss[loss=0.1655, simple_loss=0.234, pruned_loss=0.04845, over 971661.14 frames.], batch size: 21, lr: 6.23e-04
+2022-05-04 10:48:47,951 INFO [train.py:715] (3/8) Epoch 2, batch 34000, loss[loss=0.1831, simple_loss=0.2503, pruned_loss=0.05799, over 4939.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2353, pruned_loss=0.04969, over 971810.74 frames.], batch size: 18, lr: 6.23e-04
+2022-05-04 10:49:27,580 INFO [train.py:715] (3/8) Epoch 2, batch 34050, loss[loss=0.1765, simple_loss=0.246, pruned_loss=0.05345, over 4975.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2358, pruned_loss=0.04992, over 971810.60 frames.], batch size: 15, lr: 6.23e-04
+2022-05-04 10:50:07,046 INFO [train.py:715] (3/8) Epoch 2, batch 34100, loss[loss=0.1644, simple_loss=0.2422, pruned_loss=0.04334, over 4932.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2355, pruned_loss=0.04966, over 971859.90 frames.], batch size: 23, lr: 6.23e-04
+2022-05-04 10:50:46,459 INFO [train.py:715] (3/8) Epoch 2, batch 34150, loss[loss=0.172, simple_loss=0.2336, pruned_loss=0.0552, over 4885.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2353, pruned_loss=0.04952, over 972271.48 frames.], batch size: 19, lr: 6.22e-04
+2022-05-04 10:51:26,748 INFO [train.py:715] (3/8) Epoch 2, batch 34200, loss[loss=0.1636, simple_loss=0.2187, pruned_loss=0.05428, over 4988.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2352, pruned_loss=0.04979, over 973466.56 frames.], batch size: 35, lr: 6.22e-04
+2022-05-04 10:52:06,318 INFO [train.py:715] (3/8) Epoch 2, batch 34250, loss[loss=0.1831, simple_loss=0.2554, pruned_loss=0.05543, over 4704.00 frames.], tot_loss[loss=0.169, simple_loss=0.2365, pruned_loss=0.05079, over 973201.89 frames.], batch size: 15, lr: 6.22e-04
+2022-05-04 10:52:45,480 INFO [train.py:715] (3/8) Epoch 2, batch 34300, loss[loss=0.1606, simple_loss=0.2276, pruned_loss=0.04677, over 4828.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2355, pruned_loss=0.05062, over 972629.98 frames.], batch size: 15, lr: 6.22e-04
+2022-05-04 10:53:25,366 INFO [train.py:715] (3/8) Epoch 2, batch 34350, loss[loss=0.1876, simple_loss=0.2416, pruned_loss=0.06678, over 4918.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2341, pruned_loss=0.05009, over 973769.19 frames.], batch size: 17, lr: 6.22e-04
+2022-05-04 10:54:07,391 INFO [train.py:715] (3/8) Epoch 2, batch 34400, loss[loss=0.1707, simple_loss=0.2399, pruned_loss=0.05075, over 4855.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2342, pruned_loss=0.04977, over 973023.50 frames.], batch size: 30, lr: 6.22e-04
+2022-05-04 10:54:46,513 INFO [train.py:715] (3/8) Epoch 2, batch 34450, loss[loss=0.1339, simple_loss=0.205, pruned_loss=0.0314, over 4735.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2346, pruned_loss=0.04986, over 972785.68 frames.], batch size: 16, lr: 6.22e-04
+2022-05-04 10:55:25,438 INFO [train.py:715] (3/8) Epoch 2, batch 34500, loss[loss=0.1802, simple_loss=0.257, pruned_loss=0.05167, over 4847.00 frames.], tot_loss[loss=0.1685, simple_loss=0.236, pruned_loss=0.0505, over 973376.63 frames.], batch size: 30, lr: 6.21e-04
+2022-05-04 10:56:05,354 INFO [train.py:715] (3/8) Epoch 2, batch 34550, loss[loss=0.1491, simple_loss=0.2257, pruned_loss=0.03628, over 4861.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2359, pruned_loss=0.05089, over 973816.70 frames.], batch size: 20, lr: 6.21e-04
+2022-05-04 10:56:44,139 INFO [train.py:715] (3/8) Epoch 2, batch 34600, loss[loss=0.1835, simple_loss=0.2452, pruned_loss=0.06087, over 4926.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2352, pruned_loss=0.05057, over 974253.26 frames.], batch size: 17, lr: 6.21e-04
+2022-05-04 10:57:23,174 INFO [train.py:715] (3/8) Epoch 2, batch 34650, loss[loss=0.1717, simple_loss=0.2342, pruned_loss=0.05456, over 4880.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2344, pruned_loss=0.05048, over 973891.18 frames.], batch size: 22, lr: 6.21e-04
+2022-05-04 10:58:02,537 INFO [train.py:715] (3/8) Epoch 2, batch 34700, loss[loss=0.1595, simple_loss=0.2311, pruned_loss=0.04396, over 4833.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2338, pruned_loss=0.05005, over 973848.39 frames.], batch size: 27, lr: 6.21e-04
+2022-05-04 10:58:40,565 INFO [train.py:715] (3/8) Epoch 2, batch 34750, loss[loss=0.1717, simple_loss=0.2414, pruned_loss=0.05097, over 4771.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2332, pruned_loss=0.04953, over 973224.15 frames.], batch size: 14, lr: 6.21e-04
+2022-05-04 10:59:17,104 INFO [train.py:715] (3/8) Epoch 2, batch 34800, loss[loss=0.207, simple_loss=0.2722, pruned_loss=0.07095, over 4886.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2333, pruned_loss=0.04968, over 972314.03 frames.], batch size: 22, lr: 6.20e-04
+2022-05-04 11:00:07,064 INFO [train.py:715] (3/8) Epoch 3, batch 0, loss[loss=0.1853, simple_loss=0.2488, pruned_loss=0.0609, over 4926.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2488, pruned_loss=0.0609, over 4926.00 frames.], batch size: 29, lr: 5.87e-04
+2022-05-04 11:00:45,739 INFO [train.py:715] (3/8) Epoch 3, batch 50, loss[loss=0.1846, simple_loss=0.2402, pruned_loss=0.06454, over 4962.00 frames.], tot_loss[loss=0.1663, simple_loss=0.233, pruned_loss=0.04981, over 221249.49 frames.], batch size: 35, lr: 5.87e-04
+2022-05-04 11:01:25,678 INFO [train.py:715] (3/8) Epoch 3, batch 100, loss[loss=0.1674, simple_loss=0.243, pruned_loss=0.04592, over 4762.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2317, pruned_loss=0.04932, over 387921.21 frames.], batch size: 19, lr: 5.87e-04
+2022-05-04 11:02:05,237 INFO [train.py:715] (3/8) Epoch 3, batch 150, loss[loss=0.165, simple_loss=0.2324, pruned_loss=0.0488, over 4793.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2325, pruned_loss=0.04929, over 516970.90 frames.], batch size: 17, lr: 5.86e-04
+2022-05-04 11:02:44,386 INFO [train.py:715] (3/8) Epoch 3, batch 200, loss[loss=0.1605, simple_loss=0.2256, pruned_loss=0.04765, over 4980.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2331, pruned_loss=0.04894, over 617173.81 frames.], batch size: 15, lr: 5.86e-04
+2022-05-04 11:03:23,625 INFO [train.py:715] (3/8) Epoch 3, batch 250, loss[loss=0.2022, simple_loss=0.2602, pruned_loss=0.07213, over 4953.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2341, pruned_loss=0.04948, over 695386.69 frames.], batch size: 39, lr: 5.86e-04
+2022-05-04 11:04:03,633 INFO [train.py:715] (3/8) Epoch 3, batch 300, loss[loss=0.1882, simple_loss=0.2433, pruned_loss=0.06655, over 4847.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2333, pruned_loss=0.04875, over 756971.84 frames.], batch size: 15, lr: 5.86e-04
+2022-05-04 11:04:42,643 INFO [train.py:715] (3/8) Epoch 3, batch 350, loss[loss=0.2006, simple_loss=0.2616, pruned_loss=0.0698, over 4809.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2354, pruned_loss=0.04945, over 805227.57 frames.], batch size: 21, lr: 5.86e-04
+2022-05-04 11:05:21,844 INFO [train.py:715] (3/8) Epoch 3, batch 400, loss[loss=0.1638, simple_loss=0.223, pruned_loss=0.05223, over 4829.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2343, pruned_loss=0.04902, over 842721.51 frames.], batch size: 12, lr: 5.86e-04
+2022-05-04 11:06:01,613 INFO [train.py:715] (3/8) Epoch 3, batch 450, loss[loss=0.1877, simple_loss=0.2454, pruned_loss=0.06504, over 4859.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2337, pruned_loss=0.04894, over 871258.65 frames.], batch size: 32, lr: 5.86e-04
+2022-05-04 11:06:41,121 INFO [train.py:715] (3/8) Epoch 3, batch 500, loss[loss=0.1542, simple_loss=0.2176, pruned_loss=0.04543, over 4777.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2337, pruned_loss=0.04878, over 893599.51 frames.], batch size: 17, lr: 5.85e-04
+2022-05-04 11:07:20,466 INFO [train.py:715] (3/8) Epoch 3, batch 550, loss[loss=0.1684, simple_loss=0.2194, pruned_loss=0.05871, over 4825.00 frames.], tot_loss[loss=0.165, simple_loss=0.2332, pruned_loss=0.04841, over 910980.33 frames.], batch size: 13, lr: 5.85e-04
+2022-05-04 11:07:59,338 INFO [train.py:715] (3/8) Epoch 3, batch 600, loss[loss=0.1346, simple_loss=0.2041, pruned_loss=0.03257, over 4744.00 frames.], tot_loss[loss=0.165, simple_loss=0.2328, pruned_loss=0.04862, over 924623.38 frames.], batch size: 12, lr: 5.85e-04
+2022-05-04 11:08:39,296 INFO [train.py:715] (3/8) Epoch 3, batch 650, loss[loss=0.1612, simple_loss=0.2263, pruned_loss=0.04804, over 4937.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2326, pruned_loss=0.04856, over 934922.38 frames.], batch size: 29, lr: 5.85e-04
+2022-05-04 11:09:18,636 INFO [train.py:715] (3/8) Epoch 3, batch 700, loss[loss=0.1847, simple_loss=0.2568, pruned_loss=0.05625, over 4970.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2329, pruned_loss=0.04871, over 943488.30 frames.], batch size: 14, lr: 5.85e-04
+2022-05-04 11:09:57,738 INFO [train.py:715] (3/8) Epoch 3, batch 750, loss[loss=0.1608, simple_loss=0.2406, pruned_loss=0.04051, over 4803.00 frames.], tot_loss[loss=0.165, simple_loss=0.2332, pruned_loss=0.04842, over 949512.23 frames.], batch size: 25, lr: 5.85e-04
+2022-05-04 11:10:37,306 INFO [train.py:715] (3/8) Epoch 3, batch 800, loss[loss=0.1333, simple_loss=0.2106, pruned_loss=0.02801, over 4971.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2335, pruned_loss=0.04846, over 955332.58 frames.], batch size: 15, lr: 5.85e-04
+2022-05-04 11:11:17,440 INFO [train.py:715] (3/8) Epoch 3, batch 850, loss[loss=0.1566, simple_loss=0.222, pruned_loss=0.04565, over 4767.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2334, pruned_loss=0.04851, over 958915.75 frames.], batch size: 18, lr: 5.84e-04
+2022-05-04 11:11:56,828 INFO [train.py:715] (3/8) Epoch 3, batch 900, loss[loss=0.1475, simple_loss=0.2159, pruned_loss=0.03954, over 4835.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2333, pruned_loss=0.04861, over 962019.96 frames.], batch size: 15, lr: 5.84e-04
+2022-05-04 11:12:35,441 INFO [train.py:715] (3/8) Epoch 3, batch 950, loss[loss=0.1612, simple_loss=0.2189, pruned_loss=0.05177, over 4873.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2326, pruned_loss=0.04827, over 964237.11 frames.], batch size: 32, lr: 5.84e-04
+2022-05-04 11:13:15,423 INFO [train.py:715] (3/8) Epoch 3, batch 1000, loss[loss=0.1405, simple_loss=0.2081, pruned_loss=0.03648, over 4802.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2327, pruned_loss=0.04854, over 966255.87 frames.], batch size: 25, lr: 5.84e-04
+2022-05-04 11:13:55,092 INFO [train.py:715] (3/8) Epoch 3, batch 1050, loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02992, over 4806.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2329, pruned_loss=0.04902, over 966988.77 frames.], batch size: 25, lr: 5.84e-04
+2022-05-04 11:14:34,003 INFO [train.py:715] (3/8) Epoch 3, batch 1100, loss[loss=0.1613, simple_loss=0.2263, pruned_loss=0.04815, over 4914.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2317, pruned_loss=0.04862, over 967898.17 frames.], batch size: 23, lr: 5.84e-04
+2022-05-04 11:15:12,875 INFO [train.py:715] (3/8) Epoch 3, batch 1150, loss[loss=0.1596, simple_loss=0.2255, pruned_loss=0.04685, over 4804.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2321, pruned_loss=0.04907, over 968470.86 frames.], batch size: 13, lr: 5.84e-04
+2022-05-04 11:15:52,683 INFO [train.py:715] (3/8) Epoch 3, batch 1200, loss[loss=0.1636, simple_loss=0.2261, pruned_loss=0.05059, over 4892.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2325, pruned_loss=0.049, over 969343.22 frames.], batch size: 39, lr: 5.83e-04
+2022-05-04 11:16:31,656 INFO [train.py:715] (3/8) Epoch 3, batch 1250, loss[loss=0.1649, simple_loss=0.2328, pruned_loss=0.04851, over 4937.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2325, pruned_loss=0.04911, over 969622.29 frames.], batch size: 21, lr: 5.83e-04
+2022-05-04 11:17:10,164 INFO [train.py:715] (3/8) Epoch 3, batch 1300, loss[loss=0.1407, simple_loss=0.2152, pruned_loss=0.03305, over 4829.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2316, pruned_loss=0.04801, over 970346.32 frames.], batch size: 15, lr: 5.83e-04
+2022-05-04 11:17:49,722 INFO [train.py:715] (3/8) Epoch 3, batch 1350, loss[loss=0.1419, simple_loss=0.2112, pruned_loss=0.03634, over 4844.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2315, pruned_loss=0.04752, over 970361.54 frames.], batch size: 13, lr: 5.83e-04
+2022-05-04 11:18:28,998 INFO [train.py:715] (3/8) Epoch 3, batch 1400, loss[loss=0.1821, simple_loss=0.2555, pruned_loss=0.05441, over 4889.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2324, pruned_loss=0.04835, over 971253.27 frames.], batch size: 22, lr: 5.83e-04
+2022-05-04 11:19:07,864 INFO [train.py:715] (3/8) Epoch 3, batch 1450, loss[loss=0.1606, simple_loss=0.2289, pruned_loss=0.04614, over 4834.00 frames.], tot_loss[loss=0.165, simple_loss=0.2328, pruned_loss=0.04863, over 970987.42 frames.], batch size: 26, lr: 5.83e-04
+2022-05-04 11:19:46,421 INFO [train.py:715] (3/8) Epoch 3, batch 1500, loss[loss=0.1601, simple_loss=0.2301, pruned_loss=0.04508, over 4778.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2325, pruned_loss=0.04825, over 971028.14 frames.], batch size: 14, lr: 5.83e-04
+2022-05-04 11:20:26,148 INFO [train.py:715] (3/8) Epoch 3, batch 1550, loss[loss=0.1829, simple_loss=0.2489, pruned_loss=0.05846, over 4941.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2336, pruned_loss=0.0493, over 970894.50 frames.], batch size: 29, lr: 5.83e-04
+2022-05-04 11:21:05,414 INFO [train.py:715] (3/8) Epoch 3, batch 1600, loss[loss=0.1427, simple_loss=0.218, pruned_loss=0.03372, over 4810.00 frames.], tot_loss[loss=0.1659, simple_loss=0.233, pruned_loss=0.04941, over 970907.66 frames.], batch size: 21, lr: 5.82e-04
+2022-05-04 11:21:43,530 INFO [train.py:715] (3/8) Epoch 3, batch 1650, loss[loss=0.1717, simple_loss=0.2424, pruned_loss=0.05048, over 4978.00 frames.], tot_loss[loss=0.165, simple_loss=0.2324, pruned_loss=0.04883, over 972081.15 frames.], batch size: 39, lr: 5.82e-04
+2022-05-04 11:22:22,780 INFO [train.py:715] (3/8) Epoch 3, batch 1700, loss[loss=0.1715, simple_loss=0.2504, pruned_loss=0.0463, over 4772.00 frames.], tot_loss[loss=0.1662, simple_loss=0.234, pruned_loss=0.04918, over 971960.81 frames.], batch size: 18, lr: 5.82e-04
+2022-05-04 11:23:02,318 INFO [train.py:715] (3/8) Epoch 3, batch 1750, loss[loss=0.1881, simple_loss=0.2364, pruned_loss=0.06986, over 4690.00 frames.], tot_loss[loss=0.167, simple_loss=0.2344, pruned_loss=0.04982, over 972491.23 frames.], batch size: 15, lr: 5.82e-04
+2022-05-04 11:23:41,622 INFO [train.py:715] (3/8) Epoch 3, batch 1800, loss[loss=0.1584, simple_loss=0.2238, pruned_loss=0.04646, over 4966.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2343, pruned_loss=0.04968, over 972747.90 frames.], batch size: 35, lr: 5.82e-04
+2022-05-04 11:24:20,321 INFO [train.py:715] (3/8) Epoch 3, batch 1850, loss[loss=0.1305, simple_loss=0.1954, pruned_loss=0.03283, over 4741.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2335, pruned_loss=0.04891, over 972015.70 frames.], batch size: 19, lr: 5.82e-04
+2022-05-04 11:25:00,294 INFO [train.py:715] (3/8) Epoch 3, batch 1900, loss[loss=0.1367, simple_loss=0.2087, pruned_loss=0.03234, over 4882.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2335, pruned_loss=0.04893, over 972227.53 frames.], batch size: 16, lr: 5.82e-04
+2022-05-04 11:25:39,886 INFO [train.py:715] (3/8) Epoch 3, batch 1950, loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03003, over 4779.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2337, pruned_loss=0.04895, over 972206.41 frames.], batch size: 19, lr: 5.81e-04
+2022-05-04 11:26:18,805 INFO [train.py:715] (3/8) Epoch 3, batch 2000, loss[loss=0.1763, simple_loss=0.2511, pruned_loss=0.05078, over 4805.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2331, pruned_loss=0.0485, over 972077.17 frames.], batch size: 25, lr: 5.81e-04
+2022-05-04 11:26:58,012 INFO [train.py:715] (3/8) Epoch 3, batch 2050, loss[loss=0.1968, simple_loss=0.2622, pruned_loss=0.06566, over 4880.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2335, pruned_loss=0.04885, over 972562.98 frames.], batch size: 39, lr: 5.81e-04
+2022-05-04 11:27:37,795 INFO [train.py:715] (3/8) Epoch 3, batch 2100, loss[loss=0.1915, simple_loss=0.2576, pruned_loss=0.06272, over 4837.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2331, pruned_loss=0.04859, over 972494.16 frames.], batch size: 30, lr: 5.81e-04
+2022-05-04 11:28:17,049 INFO [train.py:715] (3/8) Epoch 3, batch 2150, loss[loss=0.15, simple_loss=0.2178, pruned_loss=0.04109, over 4977.00 frames.], tot_loss[loss=0.1653, simple_loss=0.233, pruned_loss=0.04881, over 972732.27 frames.], batch size: 39, lr: 5.81e-04
+2022-05-04 11:28:55,720 INFO [train.py:715] (3/8) Epoch 3, batch 2200, loss[loss=0.1485, simple_loss=0.2035, pruned_loss=0.04676, over 4915.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2335, pruned_loss=0.04943, over 972315.95 frames.], batch size: 18, lr: 5.81e-04
+2022-05-04 11:29:35,102 INFO [train.py:715] (3/8) Epoch 3, batch 2250, loss[loss=0.1601, simple_loss=0.2282, pruned_loss=0.04601, over 4858.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2333, pruned_loss=0.04917, over 972298.35 frames.], batch size: 32, lr: 5.81e-04
+2022-05-04 11:30:14,521 INFO [train.py:715] (3/8) Epoch 3, batch 2300, loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03232, over 4708.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2326, pruned_loss=0.04844, over 972393.96 frames.], batch size: 12, lr: 5.80e-04
+2022-05-04 11:30:53,579 INFO [train.py:715] (3/8) Epoch 3, batch 2350, loss[loss=0.1697, simple_loss=0.2314, pruned_loss=0.05397, over 4742.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2322, pruned_loss=0.04821, over 971583.73 frames.], batch size: 12, lr: 5.80e-04
+2022-05-04 11:31:32,373 INFO [train.py:715] (3/8) Epoch 3, batch 2400, loss[loss=0.177, simple_loss=0.2436, pruned_loss=0.05521, over 4881.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2315, pruned_loss=0.04795, over 972126.03 frames.], batch size: 19, lr: 5.80e-04
+2022-05-04 11:32:12,610 INFO [train.py:715] (3/8) Epoch 3, batch 2450, loss[loss=0.2071, simple_loss=0.2632, pruned_loss=0.07546, over 4973.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2326, pruned_loss=0.04879, over 971948.83 frames.], batch size: 35, lr: 5.80e-04
+2022-05-04 11:32:51,964 INFO [train.py:715] (3/8) Epoch 3, batch 2500, loss[loss=0.1771, simple_loss=0.2338, pruned_loss=0.06018, over 4870.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2328, pruned_loss=0.0489, over 972953.95 frames.], batch size: 20, lr: 5.80e-04
+2022-05-04 11:33:30,787 INFO [train.py:715] (3/8) Epoch 3, batch 2550, loss[loss=0.1285, simple_loss=0.2057, pruned_loss=0.0257, over 4976.00 frames.], tot_loss[loss=0.166, simple_loss=0.2336, pruned_loss=0.04922, over 972765.16 frames.], batch size: 24, lr: 5.80e-04
+2022-05-04 11:34:11,445 INFO [train.py:715] (3/8) Epoch 3, batch 2600, loss[loss=0.1588, simple_loss=0.2288, pruned_loss=0.04439, over 4763.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2329, pruned_loss=0.0488, over 972218.33 frames.], batch size: 18, lr: 5.80e-04
+2022-05-04 11:34:51,561 INFO [train.py:715] (3/8) Epoch 3, batch 2650, loss[loss=0.1652, simple_loss=0.2305, pruned_loss=0.04991, over 4859.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2338, pruned_loss=0.04933, over 972385.71 frames.], batch size: 30, lr: 5.80e-04
+2022-05-04 11:35:30,756 INFO [train.py:715] (3/8) Epoch 3, batch 2700, loss[loss=0.186, simple_loss=0.2612, pruned_loss=0.05539, over 4816.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2336, pruned_loss=0.04912, over 972709.09 frames.], batch size: 24, lr: 5.79e-04
+2022-05-04 11:36:10,257 INFO [train.py:715] (3/8) Epoch 3, batch 2750, loss[loss=0.1517, simple_loss=0.2236, pruned_loss=0.03986, over 4807.00 frames.], tot_loss[loss=0.167, simple_loss=0.2346, pruned_loss=0.04967, over 972331.91 frames.], batch size: 21, lr: 5.79e-04
+2022-05-04 11:36:50,511 INFO [train.py:715] (3/8) Epoch 3, batch 2800, loss[loss=0.1569, simple_loss=0.2291, pruned_loss=0.04236, over 4916.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2352, pruned_loss=0.05003, over 973844.08 frames.], batch size: 29, lr: 5.79e-04
+2022-05-04 11:37:29,792 INFO [train.py:715] (3/8) Epoch 3, batch 2850, loss[loss=0.1746, simple_loss=0.2452, pruned_loss=0.05196, over 4965.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2348, pruned_loss=0.04975, over 973081.62 frames.], batch size: 21, lr: 5.79e-04
+2022-05-04 11:38:08,470 INFO [train.py:715] (3/8) Epoch 3, batch 2900, loss[loss=0.1525, simple_loss=0.222, pruned_loss=0.04152, over 4886.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2338, pruned_loss=0.04933, over 973371.34 frames.], batch size: 22, lr: 5.79e-04
+2022-05-04 11:38:48,423 INFO [train.py:715] (3/8) Epoch 3, batch 2950, loss[loss=0.1382, simple_loss=0.205, pruned_loss=0.03564, over 4822.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2332, pruned_loss=0.04915, over 973082.00 frames.], batch size: 27, lr: 5.79e-04
+2022-05-04 11:39:28,055 INFO [train.py:715] (3/8) Epoch 3, batch 3000, loss[loss=0.1797, simple_loss=0.2442, pruned_loss=0.05753, over 4731.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2336, pruned_loss=0.04951, over 972129.42 frames.], batch size: 16, lr: 5.79e-04
+2022-05-04 11:39:28,055 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 11:39:36,789 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1153, simple_loss=0.2015, pruned_loss=0.0146, over 914524.00 frames.
+2022-05-04 11:40:16,884 INFO [train.py:715] (3/8) Epoch 3, batch 3050, loss[loss=0.1985, simple_loss=0.262, pruned_loss=0.06752, over 4694.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2333, pruned_loss=0.0491, over 971095.55 frames.], batch size: 15, lr: 5.78e-04
+2022-05-04 11:40:55,668 INFO [train.py:715] (3/8) Epoch 3, batch 3100, loss[loss=0.1516, simple_loss=0.2111, pruned_loss=0.04608, over 4794.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2336, pruned_loss=0.04911, over 971020.48 frames.], batch size: 12, lr: 5.78e-04
+2022-05-04 11:41:35,054 INFO [train.py:715] (3/8) Epoch 3, batch 3150, loss[loss=0.1936, simple_loss=0.2634, pruned_loss=0.06191, over 4965.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2335, pruned_loss=0.0487, over 971450.73 frames.], batch size: 24, lr: 5.78e-04
+2022-05-04 11:42:14,855 INFO [train.py:715] (3/8) Epoch 3, batch 3200, loss[loss=0.1948, simple_loss=0.2685, pruned_loss=0.06055, over 4800.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2335, pruned_loss=0.04853, over 971108.80 frames.], batch size: 24, lr: 5.78e-04
+2022-05-04 11:42:54,655 INFO [train.py:715] (3/8) Epoch 3, batch 3250, loss[loss=0.171, simple_loss=0.2509, pruned_loss=0.04556, over 4908.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2342, pruned_loss=0.04919, over 971593.41 frames.], batch size: 23, lr: 5.78e-04
+2022-05-04 11:43:33,194 INFO [train.py:715] (3/8) Epoch 3, batch 3300, loss[loss=0.1851, simple_loss=0.2521, pruned_loss=0.05904, over 4971.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2345, pruned_loss=0.04954, over 971318.61 frames.], batch size: 14, lr: 5.78e-04
+2022-05-04 11:44:13,008 INFO [train.py:715] (3/8) Epoch 3, batch 3350, loss[loss=0.1964, simple_loss=0.2579, pruned_loss=0.06747, over 4819.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2337, pruned_loss=0.04909, over 971388.20 frames.], batch size: 26, lr: 5.78e-04
+2022-05-04 11:44:52,483 INFO [train.py:715] (3/8) Epoch 3, batch 3400, loss[loss=0.1898, simple_loss=0.2555, pruned_loss=0.06206, over 4756.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2339, pruned_loss=0.04919, over 971350.01 frames.], batch size: 19, lr: 5.77e-04
+2022-05-04 11:45:31,170 INFO [train.py:715] (3/8) Epoch 3, batch 3450, loss[loss=0.1579, simple_loss=0.2295, pruned_loss=0.04312, over 4879.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2348, pruned_loss=0.04949, over 970841.93 frames.], batch size: 22, lr: 5.77e-04
+2022-05-04 11:46:10,502 INFO [train.py:715] (3/8) Epoch 3, batch 3500, loss[loss=0.1607, simple_loss=0.2263, pruned_loss=0.04752, over 4932.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2343, pruned_loss=0.04905, over 970761.36 frames.], batch size: 18, lr: 5.77e-04
+2022-05-04 11:46:50,808 INFO [train.py:715] (3/8) Epoch 3, batch 3550, loss[loss=0.2332, simple_loss=0.2937, pruned_loss=0.08634, over 4877.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2342, pruned_loss=0.04854, over 971516.22 frames.], batch size: 39, lr: 5.77e-04
+2022-05-04 11:47:30,666 INFO [train.py:715] (3/8) Epoch 3, batch 3600, loss[loss=0.1378, simple_loss=0.2128, pruned_loss=0.03144, over 4881.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2344, pruned_loss=0.04858, over 972083.54 frames.], batch size: 22, lr: 5.77e-04
+2022-05-04 11:48:09,899 INFO [train.py:715] (3/8) Epoch 3, batch 3650, loss[loss=0.1901, simple_loss=0.2485, pruned_loss=0.06591, over 4948.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2342, pruned_loss=0.04847, over 971667.14 frames.], batch size: 21, lr: 5.77e-04
+2022-05-04 11:48:49,626 INFO [train.py:715] (3/8) Epoch 3, batch 3700, loss[loss=0.195, simple_loss=0.2564, pruned_loss=0.06682, over 4845.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2341, pruned_loss=0.04876, over 971224.05 frames.], batch size: 30, lr: 5.77e-04
+2022-05-04 11:49:29,643 INFO [train.py:715] (3/8) Epoch 3, batch 3750, loss[loss=0.1427, simple_loss=0.212, pruned_loss=0.03669, over 4936.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2337, pruned_loss=0.04868, over 971345.31 frames.], batch size: 21, lr: 5.77e-04
+2022-05-04 11:50:09,330 INFO [train.py:715] (3/8) Epoch 3, batch 3800, loss[loss=0.161, simple_loss=0.2153, pruned_loss=0.05329, over 4927.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2327, pruned_loss=0.04849, over 971140.31 frames.], batch size: 18, lr: 5.76e-04
+2022-05-04 11:50:48,719 INFO [train.py:715] (3/8) Epoch 3, batch 3850, loss[loss=0.1858, simple_loss=0.2628, pruned_loss=0.05437, over 4858.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2327, pruned_loss=0.04833, over 972198.83 frames.], batch size: 20, lr: 5.76e-04
+2022-05-04 11:51:28,561 INFO [train.py:715] (3/8) Epoch 3, batch 3900, loss[loss=0.1496, simple_loss=0.2231, pruned_loss=0.03805, over 4920.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2333, pruned_loss=0.04872, over 972218.39 frames.], batch size: 29, lr: 5.76e-04
+2022-05-04 11:52:08,060 INFO [train.py:715] (3/8) Epoch 3, batch 3950, loss[loss=0.1836, simple_loss=0.2457, pruned_loss=0.06078, over 4887.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2347, pruned_loss=0.04921, over 971487.04 frames.], batch size: 19, lr: 5.76e-04
+2022-05-04 11:52:47,080 INFO [train.py:715] (3/8) Epoch 3, batch 4000, loss[loss=0.1629, simple_loss=0.2438, pruned_loss=0.04101, over 4805.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2338, pruned_loss=0.04892, over 971777.51 frames.], batch size: 12, lr: 5.76e-04
+2022-05-04 11:53:26,526 INFO [train.py:715] (3/8) Epoch 3, batch 4050, loss[loss=0.1555, simple_loss=0.2277, pruned_loss=0.04166, over 4927.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2338, pruned_loss=0.04878, over 972423.94 frames.], batch size: 23, lr: 5.76e-04
+2022-05-04 11:54:06,702 INFO [train.py:715] (3/8) Epoch 3, batch 4100, loss[loss=0.2087, simple_loss=0.2731, pruned_loss=0.07213, over 4871.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2334, pruned_loss=0.04853, over 971659.39 frames.], batch size: 16, lr: 5.76e-04
+2022-05-04 11:54:45,655 INFO [train.py:715] (3/8) Epoch 3, batch 4150, loss[loss=0.1485, simple_loss=0.2274, pruned_loss=0.03476, over 4798.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2329, pruned_loss=0.04806, over 970847.31 frames.], batch size: 17, lr: 5.76e-04
+2022-05-04 11:55:24,492 INFO [train.py:715] (3/8) Epoch 3, batch 4200, loss[loss=0.2048, simple_loss=0.2606, pruned_loss=0.07448, over 4640.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2328, pruned_loss=0.04814, over 970460.20 frames.], batch size: 13, lr: 5.75e-04
+2022-05-04 11:56:04,947 INFO [train.py:715] (3/8) Epoch 3, batch 4250, loss[loss=0.1486, simple_loss=0.214, pruned_loss=0.04159, over 4983.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2327, pruned_loss=0.04839, over 970990.13 frames.], batch size: 14, lr: 5.75e-04
+2022-05-04 11:56:44,322 INFO [train.py:715] (3/8) Epoch 3, batch 4300, loss[loss=0.1469, simple_loss=0.2211, pruned_loss=0.03632, over 4866.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2323, pruned_loss=0.04829, over 971679.97 frames.], batch size: 20, lr: 5.75e-04
+2022-05-04 11:57:23,800 INFO [train.py:715] (3/8) Epoch 3, batch 4350, loss[loss=0.1518, simple_loss=0.2276, pruned_loss=0.038, over 4880.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2333, pruned_loss=0.04912, over 971732.23 frames.], batch size: 16, lr: 5.75e-04
+2022-05-04 11:58:03,480 INFO [train.py:715] (3/8) Epoch 3, batch 4400, loss[loss=0.1551, simple_loss=0.2329, pruned_loss=0.03864, over 4782.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2333, pruned_loss=0.04902, over 972072.02 frames.], batch size: 17, lr: 5.75e-04
+2022-05-04 11:58:43,521 INFO [train.py:715] (3/8) Epoch 3, batch 4450, loss[loss=0.1794, simple_loss=0.2401, pruned_loss=0.0593, over 4754.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2333, pruned_loss=0.04891, over 971996.42 frames.], batch size: 16, lr: 5.75e-04
+2022-05-04 11:59:22,566 INFO [train.py:715] (3/8) Epoch 3, batch 4500, loss[loss=0.2202, simple_loss=0.2816, pruned_loss=0.07936, over 4894.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2337, pruned_loss=0.04882, over 971079.31 frames.], batch size: 17, lr: 5.75e-04
+2022-05-04 12:00:01,992 INFO [train.py:715] (3/8) Epoch 3, batch 4550, loss[loss=0.1685, simple_loss=0.2364, pruned_loss=0.05026, over 4826.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2328, pruned_loss=0.04853, over 971197.88 frames.], batch size: 15, lr: 5.74e-04
+2022-05-04 12:00:41,745 INFO [train.py:715] (3/8) Epoch 3, batch 4600, loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03065, over 4901.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2327, pruned_loss=0.04859, over 971113.58 frames.], batch size: 22, lr: 5.74e-04
+2022-05-04 12:01:21,001 INFO [train.py:715] (3/8) Epoch 3, batch 4650, loss[loss=0.1586, simple_loss=0.232, pruned_loss=0.04257, over 4765.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2319, pruned_loss=0.0482, over 970966.96 frames.], batch size: 19, lr: 5.74e-04
+2022-05-04 12:01:59,932 INFO [train.py:715] (3/8) Epoch 3, batch 4700, loss[loss=0.1674, simple_loss=0.2212, pruned_loss=0.05682, over 4982.00 frames.], tot_loss[loss=0.1644, simple_loss=0.232, pruned_loss=0.04838, over 971170.74 frames.], batch size: 31, lr: 5.74e-04
+2022-05-04 12:02:39,135 INFO [train.py:715] (3/8) Epoch 3, batch 4750, loss[loss=0.1749, simple_loss=0.2404, pruned_loss=0.05465, over 4827.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2317, pruned_loss=0.04807, over 971324.22 frames.], batch size: 26, lr: 5.74e-04
+2022-05-04 12:03:18,739 INFO [train.py:715] (3/8) Epoch 3, batch 4800, loss[loss=0.1913, simple_loss=0.2533, pruned_loss=0.06459, over 4946.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2322, pruned_loss=0.04823, over 973040.94 frames.], batch size: 39, lr: 5.74e-04
+2022-05-04 12:03:58,124 INFO [train.py:715] (3/8) Epoch 3, batch 4850, loss[loss=0.1832, simple_loss=0.2451, pruned_loss=0.0606, over 4815.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2321, pruned_loss=0.04809, over 973193.12 frames.], batch size: 13, lr: 5.74e-04
+2022-05-04 12:04:36,950 INFO [train.py:715] (3/8) Epoch 3, batch 4900, loss[loss=0.1559, simple_loss=0.2318, pruned_loss=0.04003, over 4934.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2323, pruned_loss=0.04854, over 973005.03 frames.], batch size: 29, lr: 5.74e-04
+2022-05-04 12:05:16,866 INFO [train.py:715] (3/8) Epoch 3, batch 4950, loss[loss=0.1743, simple_loss=0.2413, pruned_loss=0.05365, over 4889.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2323, pruned_loss=0.04839, over 972681.51 frames.], batch size: 16, lr: 5.73e-04
+2022-05-04 12:05:56,321 INFO [train.py:715] (3/8) Epoch 3, batch 5000, loss[loss=0.1439, simple_loss=0.2141, pruned_loss=0.03681, over 4817.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2322, pruned_loss=0.04825, over 972476.95 frames.], batch size: 25, lr: 5.73e-04
+2022-05-04 12:06:35,119 INFO [train.py:715] (3/8) Epoch 3, batch 5050, loss[loss=0.1564, simple_loss=0.2196, pruned_loss=0.04654, over 4930.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2333, pruned_loss=0.04886, over 974020.36 frames.], batch size: 35, lr: 5.73e-04
+2022-05-04 12:07:14,487 INFO [train.py:715] (3/8) Epoch 3, batch 5100, loss[loss=0.1822, simple_loss=0.2368, pruned_loss=0.06384, over 4776.00 frames.], tot_loss[loss=0.165, simple_loss=0.233, pruned_loss=0.04852, over 973246.41 frames.], batch size: 18, lr: 5.73e-04
+2022-05-04 12:07:54,245 INFO [train.py:715] (3/8) Epoch 3, batch 5150, loss[loss=0.1571, simple_loss=0.2314, pruned_loss=0.04143, over 4777.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2334, pruned_loss=0.04857, over 973248.62 frames.], batch size: 18, lr: 5.73e-04
+2022-05-04 12:08:32,990 INFO [train.py:715] (3/8) Epoch 3, batch 5200, loss[loss=0.1437, simple_loss=0.2145, pruned_loss=0.03646, over 4937.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2328, pruned_loss=0.04808, over 972956.92 frames.], batch size: 23, lr: 5.73e-04
+2022-05-04 12:09:12,110 INFO [train.py:715] (3/8) Epoch 3, batch 5250, loss[loss=0.1828, simple_loss=0.2452, pruned_loss=0.0602, over 4799.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2321, pruned_loss=0.04767, over 972398.69 frames.], batch size: 14, lr: 5.73e-04
+2022-05-04 12:09:52,196 INFO [train.py:715] (3/8) Epoch 3, batch 5300, loss[loss=0.155, simple_loss=0.2255, pruned_loss=0.04225, over 4760.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2312, pruned_loss=0.04716, over 973118.42 frames.], batch size: 16, lr: 5.72e-04
+2022-05-04 12:10:31,371 INFO [train.py:715] (3/8) Epoch 3, batch 5350, loss[loss=0.1683, simple_loss=0.2343, pruned_loss=0.05112, over 4925.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04757, over 973556.24 frames.], batch size: 23, lr: 5.72e-04
+2022-05-04 12:11:10,303 INFO [train.py:715] (3/8) Epoch 3, batch 5400, loss[loss=0.1471, simple_loss=0.2271, pruned_loss=0.03351, over 4779.00 frames.], tot_loss[loss=0.163, simple_loss=0.2317, pruned_loss=0.04718, over 973628.61 frames.], batch size: 14, lr: 5.72e-04
+2022-05-04 12:11:49,950 INFO [train.py:715] (3/8) Epoch 3, batch 5450, loss[loss=0.2242, simple_loss=0.2735, pruned_loss=0.08747, over 4846.00 frames.], tot_loss[loss=0.1649, simple_loss=0.233, pruned_loss=0.0484, over 973379.08 frames.], batch size: 32, lr: 5.72e-04
+2022-05-04 12:12:30,205 INFO [train.py:715] (3/8) Epoch 3, batch 5500, loss[loss=0.1724, simple_loss=0.2414, pruned_loss=0.05165, over 4828.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2335, pruned_loss=0.04932, over 972857.14 frames.], batch size: 26, lr: 5.72e-04
+2022-05-04 12:13:09,479 INFO [train.py:715] (3/8) Epoch 3, batch 5550, loss[loss=0.1784, simple_loss=0.2369, pruned_loss=0.05994, over 4984.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2335, pruned_loss=0.04942, over 973077.88 frames.], batch size: 35, lr: 5.72e-04
+2022-05-04 12:13:49,877 INFO [train.py:715] (3/8) Epoch 3, batch 5600, loss[loss=0.1848, simple_loss=0.2509, pruned_loss=0.05933, over 4988.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2331, pruned_loss=0.04929, over 972648.28 frames.], batch size: 14, lr: 5.72e-04
+2022-05-04 12:14:29,646 INFO [train.py:715] (3/8) Epoch 3, batch 5650, loss[loss=0.1446, simple_loss=0.2186, pruned_loss=0.03527, over 4785.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2321, pruned_loss=0.04859, over 972162.36 frames.], batch size: 17, lr: 5.72e-04
+2022-05-04 12:15:08,734 INFO [train.py:715] (3/8) Epoch 3, batch 5700, loss[loss=0.1519, simple_loss=0.2256, pruned_loss=0.03906, over 4937.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2322, pruned_loss=0.04851, over 972664.53 frames.], batch size: 29, lr: 5.71e-04
+2022-05-04 12:15:48,070 INFO [train.py:715] (3/8) Epoch 3, batch 5750, loss[loss=0.191, simple_loss=0.2626, pruned_loss=0.05964, over 4881.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2333, pruned_loss=0.04892, over 972033.11 frames.], batch size: 16, lr: 5.71e-04
+2022-05-04 12:16:27,887 INFO [train.py:715] (3/8) Epoch 3, batch 5800, loss[loss=0.1422, simple_loss=0.2172, pruned_loss=0.03356, over 4806.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2327, pruned_loss=0.04843, over 973029.05 frames.], batch size: 21, lr: 5.71e-04
+2022-05-04 12:17:07,628 INFO [train.py:715] (3/8) Epoch 3, batch 5850, loss[loss=0.1759, simple_loss=0.2462, pruned_loss=0.05273, over 4935.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2323, pruned_loss=0.04824, over 973068.06 frames.], batch size: 23, lr: 5.71e-04
+2022-05-04 12:17:46,987 INFO [train.py:715] (3/8) Epoch 3, batch 5900, loss[loss=0.1516, simple_loss=0.2256, pruned_loss=0.03885, over 4774.00 frames.], tot_loss[loss=0.164, simple_loss=0.2321, pruned_loss=0.048, over 972606.00 frames.], batch size: 17, lr: 5.71e-04
+2022-05-04 12:18:26,960 INFO [train.py:715] (3/8) Epoch 3, batch 5950, loss[loss=0.1698, simple_loss=0.2491, pruned_loss=0.04529, over 4941.00 frames.], tot_loss[loss=0.165, simple_loss=0.2329, pruned_loss=0.04855, over 973060.02 frames.], batch size: 29, lr: 5.71e-04
+2022-05-04 12:19:06,645 INFO [train.py:715] (3/8) Epoch 3, batch 6000, loss[loss=0.1692, simple_loss=0.2384, pruned_loss=0.04998, over 4944.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2328, pruned_loss=0.0484, over 972238.58 frames.], batch size: 21, lr: 5.71e-04
+2022-05-04 12:19:06,645 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 12:19:15,397 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1149, simple_loss=0.2013, pruned_loss=0.01424, over 914524.00 frames.
+2022-05-04 12:19:55,208 INFO [train.py:715] (3/8) Epoch 3, batch 6050, loss[loss=0.1652, simple_loss=0.2356, pruned_loss=0.04744, over 4743.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2335, pruned_loss=0.04842, over 971917.13 frames.], batch size: 16, lr: 5.71e-04
+2022-05-04 12:20:34,637 INFO [train.py:715] (3/8) Epoch 3, batch 6100, loss[loss=0.1547, simple_loss=0.2327, pruned_loss=0.0384, over 4775.00 frames.], tot_loss[loss=0.165, simple_loss=0.2334, pruned_loss=0.04837, over 971760.87 frames.], batch size: 19, lr: 5.70e-04
+2022-05-04 12:21:13,560 INFO [train.py:715] (3/8) Epoch 3, batch 6150, loss[loss=0.1779, simple_loss=0.2477, pruned_loss=0.05409, over 4814.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2335, pruned_loss=0.0486, over 972686.33 frames.], batch size: 25, lr: 5.70e-04
+2022-05-04 12:21:53,158 INFO [train.py:715] (3/8) Epoch 3, batch 6200, loss[loss=0.1639, simple_loss=0.2228, pruned_loss=0.05248, over 4992.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2339, pruned_loss=0.04886, over 972361.63 frames.], batch size: 16, lr: 5.70e-04
+2022-05-04 12:22:33,152 INFO [train.py:715] (3/8) Epoch 3, batch 6250, loss[loss=0.1483, simple_loss=0.2106, pruned_loss=0.04298, over 4701.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2323, pruned_loss=0.04809, over 972154.70 frames.], batch size: 15, lr: 5.70e-04
+2022-05-04 12:23:12,504 INFO [train.py:715] (3/8) Epoch 3, batch 6300, loss[loss=0.16, simple_loss=0.2291, pruned_loss=0.04541, over 4813.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2329, pruned_loss=0.04834, over 971914.29 frames.], batch size: 26, lr: 5.70e-04
+2022-05-04 12:23:51,738 INFO [train.py:715] (3/8) Epoch 3, batch 6350, loss[loss=0.167, simple_loss=0.2382, pruned_loss=0.04787, over 4796.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2337, pruned_loss=0.04888, over 972198.63 frames.], batch size: 24, lr: 5.70e-04
+2022-05-04 12:24:31,949 INFO [train.py:715] (3/8) Epoch 3, batch 6400, loss[loss=0.1416, simple_loss=0.2112, pruned_loss=0.03602, over 4928.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2329, pruned_loss=0.04844, over 972301.66 frames.], batch size: 29, lr: 5.70e-04
+2022-05-04 12:25:11,500 INFO [train.py:715] (3/8) Epoch 3, batch 6450, loss[loss=0.1844, simple_loss=0.2598, pruned_loss=0.05455, over 4758.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2324, pruned_loss=0.04799, over 971675.10 frames.], batch size: 19, lr: 5.70e-04
+2022-05-04 12:25:50,481 INFO [train.py:715] (3/8) Epoch 3, batch 6500, loss[loss=0.1532, simple_loss=0.2275, pruned_loss=0.03948, over 4786.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2331, pruned_loss=0.0483, over 971929.61 frames.], batch size: 17, lr: 5.69e-04
+2022-05-04 12:26:30,133 INFO [train.py:715] (3/8) Epoch 3, batch 6550, loss[loss=0.1345, simple_loss=0.2053, pruned_loss=0.03188, over 4896.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2321, pruned_loss=0.04771, over 972399.45 frames.], batch size: 22, lr: 5.69e-04
+2022-05-04 12:27:09,928 INFO [train.py:715] (3/8) Epoch 3, batch 6600, loss[loss=0.175, simple_loss=0.2407, pruned_loss=0.05467, over 4957.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2324, pruned_loss=0.04785, over 971899.54 frames.], batch size: 29, lr: 5.69e-04
+2022-05-04 12:27:49,182 INFO [train.py:715] (3/8) Epoch 3, batch 6650, loss[loss=0.1753, simple_loss=0.2535, pruned_loss=0.04854, over 4940.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04759, over 971990.02 frames.], batch size: 29, lr: 5.69e-04
+2022-05-04 12:28:28,360 INFO [train.py:715] (3/8) Epoch 3, batch 6700, loss[loss=0.1405, simple_loss=0.2141, pruned_loss=0.0334, over 4774.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2318, pruned_loss=0.04782, over 971970.23 frames.], batch size: 14, lr: 5.69e-04
+2022-05-04 12:29:08,702 INFO [train.py:715] (3/8) Epoch 3, batch 6750, loss[loss=0.1533, simple_loss=0.2245, pruned_loss=0.04107, over 4980.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2325, pruned_loss=0.04846, over 971951.71 frames.], batch size: 15, lr: 5.69e-04
+2022-05-04 12:29:47,741 INFO [train.py:715] (3/8) Epoch 3, batch 6800, loss[loss=0.1702, simple_loss=0.2285, pruned_loss=0.05599, over 4887.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2321, pruned_loss=0.04858, over 972438.14 frames.], batch size: 12, lr: 5.69e-04
+2022-05-04 12:30:27,117 INFO [train.py:715] (3/8) Epoch 3, batch 6850, loss[loss=0.1857, simple_loss=0.2374, pruned_loss=0.06698, over 4751.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2317, pruned_loss=0.04805, over 972978.48 frames.], batch size: 16, lr: 5.68e-04
+2022-05-04 12:31:06,818 INFO [train.py:715] (3/8) Epoch 3, batch 6900, loss[loss=0.1561, simple_loss=0.2201, pruned_loss=0.04606, over 4815.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2308, pruned_loss=0.04776, over 972678.32 frames.], batch size: 25, lr: 5.68e-04
+2022-05-04 12:31:46,650 INFO [train.py:715] (3/8) Epoch 3, batch 6950, loss[loss=0.1708, simple_loss=0.2379, pruned_loss=0.0518, over 4700.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2316, pruned_loss=0.04756, over 972753.26 frames.], batch size: 15, lr: 5.68e-04
+2022-05-04 12:32:25,806 INFO [train.py:715] (3/8) Epoch 3, batch 7000, loss[loss=0.1859, simple_loss=0.2481, pruned_loss=0.06186, over 4810.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2326, pruned_loss=0.04793, over 972627.95 frames.], batch size: 25, lr: 5.68e-04
+2022-05-04 12:33:05,828 INFO [train.py:715] (3/8) Epoch 3, batch 7050, loss[loss=0.1763, simple_loss=0.2449, pruned_loss=0.05384, over 4859.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2333, pruned_loss=0.04823, over 971720.45 frames.], batch size: 16, lr: 5.68e-04
+2022-05-04 12:33:45,719 INFO [train.py:715] (3/8) Epoch 3, batch 7100, loss[loss=0.1527, simple_loss=0.2277, pruned_loss=0.03886, over 4814.00 frames.], tot_loss[loss=0.1658, simple_loss=0.234, pruned_loss=0.04882, over 971247.88 frames.], batch size: 12, lr: 5.68e-04
+2022-05-04 12:34:24,806 INFO [train.py:715] (3/8) Epoch 3, batch 7150, loss[loss=0.1543, simple_loss=0.2242, pruned_loss=0.04221, over 4983.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2336, pruned_loss=0.04868, over 970649.41 frames.], batch size: 28, lr: 5.68e-04
+2022-05-04 12:35:04,376 INFO [train.py:715] (3/8) Epoch 3, batch 7200, loss[loss=0.1543, simple_loss=0.2244, pruned_loss=0.04209, over 4921.00 frames.], tot_loss[loss=0.1656, simple_loss=0.234, pruned_loss=0.04864, over 971158.27 frames.], batch size: 39, lr: 5.68e-04
+2022-05-04 12:35:44,148 INFO [train.py:715] (3/8) Epoch 3, batch 7250, loss[loss=0.1844, simple_loss=0.2568, pruned_loss=0.05602, over 4787.00 frames.], tot_loss[loss=0.164, simple_loss=0.2325, pruned_loss=0.04777, over 971670.07 frames.], batch size: 18, lr: 5.67e-04
+2022-05-04 12:36:23,545 INFO [train.py:715] (3/8) Epoch 3, batch 7300, loss[loss=0.1495, simple_loss=0.2118, pruned_loss=0.0436, over 4753.00 frames.], tot_loss[loss=0.1643, simple_loss=0.233, pruned_loss=0.04776, over 972058.67 frames.], batch size: 12, lr: 5.67e-04
+2022-05-04 12:37:03,013 INFO [train.py:715] (3/8) Epoch 3, batch 7350, loss[loss=0.1762, simple_loss=0.2396, pruned_loss=0.05641, over 4886.00 frames.], tot_loss[loss=0.1644, simple_loss=0.233, pruned_loss=0.04785, over 972141.17 frames.], batch size: 22, lr: 5.67e-04
+2022-05-04 12:37:42,374 INFO [train.py:715] (3/8) Epoch 3, batch 7400, loss[loss=0.17, simple_loss=0.2351, pruned_loss=0.0525, over 4949.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2326, pruned_loss=0.04788, over 971728.15 frames.], batch size: 21, lr: 5.67e-04
+2022-05-04 12:38:22,631 INFO [train.py:715] (3/8) Epoch 3, batch 7450, loss[loss=0.1307, simple_loss=0.1989, pruned_loss=0.03121, over 4873.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2334, pruned_loss=0.04835, over 972647.15 frames.], batch size: 22, lr: 5.67e-04
+2022-05-04 12:39:01,777 INFO [train.py:715] (3/8) Epoch 3, batch 7500, loss[loss=0.1938, simple_loss=0.2439, pruned_loss=0.07186, over 4887.00 frames.], tot_loss[loss=0.165, simple_loss=0.2334, pruned_loss=0.04827, over 971452.07 frames.], batch size: 16, lr: 5.67e-04
+2022-05-04 12:39:41,041 INFO [train.py:715] (3/8) Epoch 3, batch 7550, loss[loss=0.1586, simple_loss=0.2322, pruned_loss=0.04251, over 4884.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2334, pruned_loss=0.04837, over 972272.86 frames.], batch size: 32, lr: 5.67e-04
+2022-05-04 12:40:22,795 INFO [train.py:715] (3/8) Epoch 3, batch 7600, loss[loss=0.1519, simple_loss=0.234, pruned_loss=0.03491, over 4863.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2327, pruned_loss=0.04784, over 972550.11 frames.], batch size: 20, lr: 5.67e-04
+2022-05-04 12:41:02,149 INFO [train.py:715] (3/8) Epoch 3, batch 7650, loss[loss=0.1681, simple_loss=0.2347, pruned_loss=0.05073, over 4841.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2327, pruned_loss=0.04784, over 972326.54 frames.], batch size: 13, lr: 5.66e-04
+2022-05-04 12:41:41,414 INFO [train.py:715] (3/8) Epoch 3, batch 7700, loss[loss=0.1732, simple_loss=0.2441, pruned_loss=0.05114, over 4686.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2343, pruned_loss=0.04862, over 971351.66 frames.], batch size: 15, lr: 5.66e-04
+2022-05-04 12:42:20,883 INFO [train.py:715] (3/8) Epoch 3, batch 7750, loss[loss=0.1406, simple_loss=0.196, pruned_loss=0.0426, over 4988.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2341, pruned_loss=0.04877, over 972944.04 frames.], batch size: 14, lr: 5.66e-04
+2022-05-04 12:43:00,214 INFO [train.py:715] (3/8) Epoch 3, batch 7800, loss[loss=0.1583, simple_loss=0.2235, pruned_loss=0.04652, over 4797.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2341, pruned_loss=0.04843, over 973505.12 frames.], batch size: 21, lr: 5.66e-04
+2022-05-04 12:43:38,786 INFO [train.py:715] (3/8) Epoch 3, batch 7850, loss[loss=0.2024, simple_loss=0.2647, pruned_loss=0.07011, over 4895.00 frames.], tot_loss[loss=0.1653, simple_loss=0.234, pruned_loss=0.04832, over 973518.75 frames.], batch size: 39, lr: 5.66e-04
+2022-05-04 12:44:18,373 INFO [train.py:715] (3/8) Epoch 3, batch 7900, loss[loss=0.1888, simple_loss=0.2469, pruned_loss=0.06533, over 4848.00 frames.], tot_loss[loss=0.165, simple_loss=0.2335, pruned_loss=0.04823, over 972482.73 frames.], batch size: 32, lr: 5.66e-04
+2022-05-04 12:44:58,146 INFO [train.py:715] (3/8) Epoch 3, batch 7950, loss[loss=0.1598, simple_loss=0.2179, pruned_loss=0.05085, over 4768.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2331, pruned_loss=0.04838, over 972137.12 frames.], batch size: 18, lr: 5.66e-04
+2022-05-04 12:45:36,729 INFO [train.py:715] (3/8) Epoch 3, batch 8000, loss[loss=0.1543, simple_loss=0.2054, pruned_loss=0.05163, over 4839.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2337, pruned_loss=0.0485, over 971398.58 frames.], batch size: 30, lr: 5.66e-04
+2022-05-04 12:46:14,906 INFO [train.py:715] (3/8) Epoch 3, batch 8050, loss[loss=0.1316, simple_loss=0.1996, pruned_loss=0.03179, over 4989.00 frames.], tot_loss[loss=0.1652, simple_loss=0.233, pruned_loss=0.04866, over 971474.61 frames.], batch size: 25, lr: 5.65e-04
+2022-05-04 12:46:53,638 INFO [train.py:715] (3/8) Epoch 3, batch 8100, loss[loss=0.1516, simple_loss=0.2205, pruned_loss=0.04139, over 4768.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2326, pruned_loss=0.04887, over 970706.34 frames.], batch size: 18, lr: 5.65e-04
+2022-05-04 12:47:31,945 INFO [train.py:715] (3/8) Epoch 3, batch 8150, loss[loss=0.1238, simple_loss=0.2062, pruned_loss=0.02071, over 4802.00 frames.], tot_loss[loss=0.165, simple_loss=0.2324, pruned_loss=0.04881, over 970840.37 frames.], batch size: 14, lr: 5.65e-04
+2022-05-04 12:48:10,088 INFO [train.py:715] (3/8) Epoch 3, batch 8200, loss[loss=0.1546, simple_loss=0.234, pruned_loss=0.0376, over 4811.00 frames.], tot_loss[loss=0.165, simple_loss=0.2323, pruned_loss=0.04885, over 970767.79 frames.], batch size: 27, lr: 5.65e-04
+2022-05-04 12:48:49,889 INFO [train.py:715] (3/8) Epoch 3, batch 8250, loss[loss=0.1532, simple_loss=0.2237, pruned_loss=0.04138, over 4835.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2323, pruned_loss=0.04873, over 970546.25 frames.], batch size: 30, lr: 5.65e-04
+2022-05-04 12:49:30,616 INFO [train.py:715] (3/8) Epoch 3, batch 8300, loss[loss=0.1756, simple_loss=0.2466, pruned_loss=0.05229, over 4872.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2332, pruned_loss=0.04914, over 972066.03 frames.], batch size: 22, lr: 5.65e-04
+2022-05-04 12:50:10,666 INFO [train.py:715] (3/8) Epoch 3, batch 8350, loss[loss=0.1433, simple_loss=0.2208, pruned_loss=0.03289, over 4878.00 frames.], tot_loss[loss=0.165, simple_loss=0.2322, pruned_loss=0.0489, over 972322.30 frames.], batch size: 22, lr: 5.65e-04
+2022-05-04 12:50:50,666 INFO [train.py:715] (3/8) Epoch 3, batch 8400, loss[loss=0.1637, simple_loss=0.2427, pruned_loss=0.04236, over 4947.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2325, pruned_loss=0.04898, over 972078.84 frames.], batch size: 24, lr: 5.65e-04
+2022-05-04 12:51:30,649 INFO [train.py:715] (3/8) Epoch 3, batch 8450, loss[loss=0.1776, simple_loss=0.2449, pruned_loss=0.05517, over 4902.00 frames.], tot_loss[loss=0.166, simple_loss=0.2333, pruned_loss=0.04938, over 972535.25 frames.], batch size: 19, lr: 5.64e-04
+2022-05-04 12:52:10,871 INFO [train.py:715] (3/8) Epoch 3, batch 8500, loss[loss=0.1758, simple_loss=0.2448, pruned_loss=0.05338, over 4812.00 frames.], tot_loss[loss=0.165, simple_loss=0.2325, pruned_loss=0.04876, over 972304.91 frames.], batch size: 24, lr: 5.64e-04
+2022-05-04 12:52:49,928 INFO [train.py:715] (3/8) Epoch 3, batch 8550, loss[loss=0.1433, simple_loss=0.2125, pruned_loss=0.03702, over 4871.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2329, pruned_loss=0.04889, over 973015.01 frames.], batch size: 20, lr: 5.64e-04
+2022-05-04 12:53:31,546 INFO [train.py:715] (3/8) Epoch 3, batch 8600, loss[loss=0.1334, simple_loss=0.1922, pruned_loss=0.03733, over 4957.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2322, pruned_loss=0.04881, over 973880.89 frames.], batch size: 14, lr: 5.64e-04
+2022-05-04 12:54:13,122 INFO [train.py:715] (3/8) Epoch 3, batch 8650, loss[loss=0.1366, simple_loss=0.2092, pruned_loss=0.03203, over 4990.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2314, pruned_loss=0.04802, over 974131.57 frames.], batch size: 26, lr: 5.64e-04
+2022-05-04 12:54:53,242 INFO [train.py:715] (3/8) Epoch 3, batch 8700, loss[loss=0.1419, simple_loss=0.2158, pruned_loss=0.03398, over 4859.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2318, pruned_loss=0.04832, over 974272.83 frames.], batch size: 20, lr: 5.64e-04
+2022-05-04 12:55:34,483 INFO [train.py:715] (3/8) Epoch 3, batch 8750, loss[loss=0.1827, simple_loss=0.2336, pruned_loss=0.06593, over 4992.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2325, pruned_loss=0.04896, over 974306.02 frames.], batch size: 14, lr: 5.64e-04
+2022-05-04 12:56:14,899 INFO [train.py:715] (3/8) Epoch 3, batch 8800, loss[loss=0.1646, simple_loss=0.2359, pruned_loss=0.04665, over 4838.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2329, pruned_loss=0.04893, over 974275.69 frames.], batch size: 15, lr: 5.64e-04
+2022-05-04 12:56:55,633 INFO [train.py:715] (3/8) Epoch 3, batch 8850, loss[loss=0.2068, simple_loss=0.2578, pruned_loss=0.07783, over 4793.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2327, pruned_loss=0.04921, over 972672.60 frames.], batch size: 12, lr: 5.63e-04
+2022-05-04 12:57:35,612 INFO [train.py:715] (3/8) Epoch 3, batch 8900, loss[loss=0.1367, simple_loss=0.2097, pruned_loss=0.03188, over 4905.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2319, pruned_loss=0.04864, over 971501.34 frames.], batch size: 23, lr: 5.63e-04
+2022-05-04 12:58:17,381 INFO [train.py:715] (3/8) Epoch 3, batch 8950, loss[loss=0.1756, simple_loss=0.2423, pruned_loss=0.05447, over 4810.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2326, pruned_loss=0.04865, over 971136.97 frames.], batch size: 25, lr: 5.63e-04
+2022-05-04 12:58:59,319 INFO [train.py:715] (3/8) Epoch 3, batch 9000, loss[loss=0.1506, simple_loss=0.2204, pruned_loss=0.04044, over 4696.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2319, pruned_loss=0.04845, over 971329.98 frames.], batch size: 15, lr: 5.63e-04
+2022-05-04 12:58:59,320 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 12:59:08,108 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1147, simple_loss=0.2006, pruned_loss=0.01442, over 914524.00 frames.
+2022-05-04 12:59:49,672 INFO [train.py:715] (3/8) Epoch 3, batch 9050, loss[loss=0.164, simple_loss=0.2326, pruned_loss=0.04772, over 4760.00 frames.], tot_loss[loss=0.165, simple_loss=0.2325, pruned_loss=0.04874, over 971452.15 frames.], batch size: 19, lr: 5.63e-04
+2022-05-04 13:00:30,635 INFO [train.py:715] (3/8) Epoch 3, batch 9100, loss[loss=0.1677, simple_loss=0.2433, pruned_loss=0.04609, over 4812.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2332, pruned_loss=0.0489, over 971105.45 frames.], batch size: 21, lr: 5.63e-04
+2022-05-04 13:01:11,923 INFO [train.py:715] (3/8) Epoch 3, batch 9150, loss[loss=0.1517, simple_loss=0.2223, pruned_loss=0.04058, over 4749.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2331, pruned_loss=0.04886, over 972024.43 frames.], batch size: 19, lr: 5.63e-04
+2022-05-04 13:01:53,286 INFO [train.py:715] (3/8) Epoch 3, batch 9200, loss[loss=0.1722, simple_loss=0.2409, pruned_loss=0.05177, over 4780.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2331, pruned_loss=0.04868, over 971632.86 frames.], batch size: 17, lr: 5.63e-04
+2022-05-04 13:02:34,661 INFO [train.py:715] (3/8) Epoch 3, batch 9250, loss[loss=0.1543, simple_loss=0.2177, pruned_loss=0.04541, over 4776.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2333, pruned_loss=0.04865, over 971720.01 frames.], batch size: 14, lr: 5.62e-04
+2022-05-04 13:03:15,390 INFO [train.py:715] (3/8) Epoch 3, batch 9300, loss[loss=0.1677, simple_loss=0.2371, pruned_loss=0.04913, over 4700.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2334, pruned_loss=0.04867, over 971990.45 frames.], batch size: 15, lr: 5.62e-04
+2022-05-04 13:03:56,632 INFO [train.py:715] (3/8) Epoch 3, batch 9350, loss[loss=0.1822, simple_loss=0.2528, pruned_loss=0.05576, over 4950.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2334, pruned_loss=0.04838, over 971724.87 frames.], batch size: 39, lr: 5.62e-04
+2022-05-04 13:04:38,909 INFO [train.py:715] (3/8) Epoch 3, batch 9400, loss[loss=0.1581, simple_loss=0.2308, pruned_loss=0.04276, over 4911.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2328, pruned_loss=0.04848, over 971611.69 frames.], batch size: 18, lr: 5.62e-04
+2022-05-04 13:05:19,293 INFO [train.py:715] (3/8) Epoch 3, batch 9450, loss[loss=0.1598, simple_loss=0.2211, pruned_loss=0.04923, over 4831.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2329, pruned_loss=0.04831, over 972130.67 frames.], batch size: 13, lr: 5.62e-04
+2022-05-04 13:06:00,823 INFO [train.py:715] (3/8) Epoch 3, batch 9500, loss[loss=0.198, simple_loss=0.2599, pruned_loss=0.06808, over 4822.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2335, pruned_loss=0.04872, over 972202.40 frames.], batch size: 15, lr: 5.62e-04
+2022-05-04 13:06:42,688 INFO [train.py:715] (3/8) Epoch 3, batch 9550, loss[loss=0.1405, simple_loss=0.213, pruned_loss=0.03396, over 4791.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2328, pruned_loss=0.04827, over 970407.49 frames.], batch size: 12, lr: 5.62e-04
+2022-05-04 13:07:24,284 INFO [train.py:715] (3/8) Epoch 3, batch 9600, loss[loss=0.1361, simple_loss=0.2113, pruned_loss=0.03047, over 4855.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2323, pruned_loss=0.0479, over 970392.59 frames.], batch size: 20, lr: 5.62e-04
+2022-05-04 13:08:05,434 INFO [train.py:715] (3/8) Epoch 3, batch 9650, loss[loss=0.1523, simple_loss=0.2261, pruned_loss=0.0393, over 4788.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2315, pruned_loss=0.04749, over 970509.32 frames.], batch size: 14, lr: 5.61e-04
+2022-05-04 13:08:46,944 INFO [train.py:715] (3/8) Epoch 3, batch 9700, loss[loss=0.1568, simple_loss=0.2247, pruned_loss=0.04446, over 4830.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2324, pruned_loss=0.04769, over 970783.39 frames.], batch size: 26, lr: 5.61e-04
+2022-05-04 13:09:27,936 INFO [train.py:715] (3/8) Epoch 3, batch 9750, loss[loss=0.1542, simple_loss=0.2268, pruned_loss=0.04077, over 4944.00 frames.], tot_loss[loss=0.164, simple_loss=0.2323, pruned_loss=0.04789, over 970958.78 frames.], batch size: 29, lr: 5.61e-04
+2022-05-04 13:10:08,809 INFO [train.py:715] (3/8) Epoch 3, batch 9800, loss[loss=0.158, simple_loss=0.2282, pruned_loss=0.04393, over 4793.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2319, pruned_loss=0.04737, over 971686.11 frames.], batch size: 24, lr: 5.61e-04
+2022-05-04 13:10:50,543 INFO [train.py:715] (3/8) Epoch 3, batch 9850, loss[loss=0.1848, simple_loss=0.2422, pruned_loss=0.06377, over 4886.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2323, pruned_loss=0.04761, over 972250.19 frames.], batch size: 16, lr: 5.61e-04
+2022-05-04 13:11:32,497 INFO [train.py:715] (3/8) Epoch 3, batch 9900, loss[loss=0.1234, simple_loss=0.191, pruned_loss=0.02795, over 4975.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2312, pruned_loss=0.04708, over 972624.16 frames.], batch size: 25, lr: 5.61e-04
+2022-05-04 13:12:12,998 INFO [train.py:715] (3/8) Epoch 3, batch 9950, loss[loss=0.1297, simple_loss=0.2002, pruned_loss=0.02962, over 4957.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2317, pruned_loss=0.04761, over 972679.04 frames.], batch size: 15, lr: 5.61e-04
+2022-05-04 13:12:54,728 INFO [train.py:715] (3/8) Epoch 3, batch 10000, loss[loss=0.1536, simple_loss=0.2216, pruned_loss=0.04284, over 4756.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2316, pruned_loss=0.04793, over 972495.33 frames.], batch size: 19, lr: 5.61e-04
+2022-05-04 13:13:36,178 INFO [train.py:715] (3/8) Epoch 3, batch 10050, loss[loss=0.1774, simple_loss=0.2431, pruned_loss=0.05588, over 4922.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2317, pruned_loss=0.04766, over 972873.53 frames.], batch size: 23, lr: 5.61e-04
+2022-05-04 13:14:17,628 INFO [train.py:715] (3/8) Epoch 3, batch 10100, loss[loss=0.137, simple_loss=0.2056, pruned_loss=0.03415, over 4793.00 frames.], tot_loss[loss=0.1629, simple_loss=0.231, pruned_loss=0.04734, over 972231.99 frames.], batch size: 12, lr: 5.60e-04
+2022-05-04 13:14:58,627 INFO [train.py:715] (3/8) Epoch 3, batch 10150, loss[loss=0.1266, simple_loss=0.1895, pruned_loss=0.03182, over 4830.00 frames.], tot_loss[loss=0.1637, simple_loss=0.232, pruned_loss=0.04768, over 972659.62 frames.], batch size: 12, lr: 5.60e-04
+2022-05-04 13:15:40,199 INFO [train.py:715] (3/8) Epoch 3, batch 10200, loss[loss=0.1744, simple_loss=0.2412, pruned_loss=0.05385, over 4797.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04761, over 972558.41 frames.], batch size: 24, lr: 5.60e-04
+2022-05-04 13:16:21,937 INFO [train.py:715] (3/8) Epoch 3, batch 10250, loss[loss=0.1355, simple_loss=0.2107, pruned_loss=0.03021, over 4923.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2319, pruned_loss=0.04773, over 972381.90 frames.], batch size: 18, lr: 5.60e-04
+2022-05-04 13:17:01,803 INFO [train.py:715] (3/8) Epoch 3, batch 10300, loss[loss=0.1578, simple_loss=0.2301, pruned_loss=0.04277, over 4798.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2319, pruned_loss=0.04769, over 972291.58 frames.], batch size: 21, lr: 5.60e-04
+2022-05-04 13:17:42,039 INFO [train.py:715] (3/8) Epoch 3, batch 10350, loss[loss=0.1585, simple_loss=0.2169, pruned_loss=0.05001, over 4854.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2325, pruned_loss=0.04798, over 972273.23 frames.], batch size: 32, lr: 5.60e-04
+2022-05-04 13:18:22,569 INFO [train.py:715] (3/8) Epoch 3, batch 10400, loss[loss=0.1513, simple_loss=0.2227, pruned_loss=0.0399, over 4803.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2324, pruned_loss=0.04765, over 972561.15 frames.], batch size: 21, lr: 5.60e-04
+2022-05-04 13:19:03,200 INFO [train.py:715] (3/8) Epoch 3, batch 10450, loss[loss=0.1495, simple_loss=0.2067, pruned_loss=0.04612, over 4952.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2321, pruned_loss=0.04771, over 972052.91 frames.], batch size: 29, lr: 5.60e-04
+2022-05-04 13:19:43,606 INFO [train.py:715] (3/8) Epoch 3, batch 10500, loss[loss=0.1685, simple_loss=0.2453, pruned_loss=0.04583, over 4860.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2319, pruned_loss=0.04762, over 972342.48 frames.], batch size: 20, lr: 5.59e-04
+2022-05-04 13:20:24,623 INFO [train.py:715] (3/8) Epoch 3, batch 10550, loss[loss=0.2012, simple_loss=0.2619, pruned_loss=0.07024, over 4921.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2318, pruned_loss=0.04786, over 971902.19 frames.], batch size: 39, lr: 5.59e-04
+2022-05-04 13:21:07,131 INFO [train.py:715] (3/8) Epoch 3, batch 10600, loss[loss=0.1687, simple_loss=0.2352, pruned_loss=0.05113, over 4934.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2325, pruned_loss=0.04806, over 972531.94 frames.], batch size: 23, lr: 5.59e-04
+2022-05-04 13:21:48,619 INFO [train.py:715] (3/8) Epoch 3, batch 10650, loss[loss=0.1772, simple_loss=0.2473, pruned_loss=0.05352, over 4855.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2323, pruned_loss=0.04774, over 972162.06 frames.], batch size: 30, lr: 5.59e-04
+2022-05-04 13:22:30,743 INFO [train.py:715] (3/8) Epoch 3, batch 10700, loss[loss=0.1737, simple_loss=0.249, pruned_loss=0.04916, over 4990.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2322, pruned_loss=0.04779, over 972734.01 frames.], batch size: 26, lr: 5.59e-04
+2022-05-04 13:23:13,521 INFO [train.py:715] (3/8) Epoch 3, batch 10750, loss[loss=0.1332, simple_loss=0.2009, pruned_loss=0.03273, over 4778.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2313, pruned_loss=0.04708, over 972599.68 frames.], batch size: 18, lr: 5.59e-04
+2022-05-04 13:23:56,756 INFO [train.py:715] (3/8) Epoch 3, batch 10800, loss[loss=0.1585, simple_loss=0.2211, pruned_loss=0.048, over 4763.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2306, pruned_loss=0.04686, over 972034.47 frames.], batch size: 16, lr: 5.59e-04
+2022-05-04 13:24:38,551 INFO [train.py:715] (3/8) Epoch 3, batch 10850, loss[loss=0.1733, simple_loss=0.2354, pruned_loss=0.05563, over 4895.00 frames.], tot_loss[loss=0.1625, simple_loss=0.231, pruned_loss=0.04701, over 972342.36 frames.], batch size: 39, lr: 5.59e-04
+2022-05-04 13:25:21,318 INFO [train.py:715] (3/8) Epoch 3, batch 10900, loss[loss=0.1636, simple_loss=0.23, pruned_loss=0.04858, over 4959.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2295, pruned_loss=0.04668, over 971995.72 frames.], batch size: 24, lr: 5.58e-04
+2022-05-04 13:26:04,560 INFO [train.py:715] (3/8) Epoch 3, batch 10950, loss[loss=0.1751, simple_loss=0.2393, pruned_loss=0.05545, over 4654.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2294, pruned_loss=0.04708, over 972317.20 frames.], batch size: 13, lr: 5.58e-04
+2022-05-04 13:26:46,515 INFO [train.py:715] (3/8) Epoch 3, batch 11000, loss[loss=0.1626, simple_loss=0.224, pruned_loss=0.05058, over 4954.00 frames.], tot_loss[loss=0.1623, simple_loss=0.23, pruned_loss=0.04728, over 973615.10 frames.], batch size: 35, lr: 5.58e-04
+2022-05-04 13:27:28,081 INFO [train.py:715] (3/8) Epoch 3, batch 11050, loss[loss=0.1814, simple_loss=0.2399, pruned_loss=0.06143, over 4873.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2305, pruned_loss=0.04815, over 973273.11 frames.], batch size: 22, lr: 5.58e-04
+2022-05-04 13:28:11,597 INFO [train.py:715] (3/8) Epoch 3, batch 11100, loss[loss=0.1527, simple_loss=0.2306, pruned_loss=0.03735, over 4780.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2301, pruned_loss=0.04747, over 972990.79 frames.], batch size: 18, lr: 5.58e-04
+2022-05-04 13:28:53,675 INFO [train.py:715] (3/8) Epoch 3, batch 11150, loss[loss=0.1439, simple_loss=0.2082, pruned_loss=0.03978, over 4893.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2303, pruned_loss=0.04718, over 972133.11 frames.], batch size: 19, lr: 5.58e-04
+2022-05-04 13:29:35,735 INFO [train.py:715] (3/8) Epoch 3, batch 11200, loss[loss=0.1927, simple_loss=0.2602, pruned_loss=0.06261, over 4930.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2312, pruned_loss=0.0478, over 972808.21 frames.], batch size: 29, lr: 5.58e-04
+2022-05-04 13:30:18,276 INFO [train.py:715] (3/8) Epoch 3, batch 11250, loss[loss=0.2138, simple_loss=0.2757, pruned_loss=0.07597, over 4989.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2316, pruned_loss=0.04776, over 972598.63 frames.], batch size: 28, lr: 5.58e-04
+2022-05-04 13:31:01,498 INFO [train.py:715] (3/8) Epoch 3, batch 11300, loss[loss=0.1584, simple_loss=0.2366, pruned_loss=0.0401, over 4924.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2312, pruned_loss=0.04747, over 972459.71 frames.], batch size: 18, lr: 5.57e-04
+2022-05-04 13:31:42,775 INFO [train.py:715] (3/8) Epoch 3, batch 11350, loss[loss=0.1839, simple_loss=0.2389, pruned_loss=0.0644, over 4885.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2323, pruned_loss=0.04801, over 972894.39 frames.], batch size: 32, lr: 5.57e-04
+2022-05-04 13:32:25,111 INFO [train.py:715] (3/8) Epoch 3, batch 11400, loss[loss=0.1494, simple_loss=0.2242, pruned_loss=0.03729, over 4985.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2322, pruned_loss=0.04777, over 972089.03 frames.], batch size: 28, lr: 5.57e-04
+2022-05-04 13:33:08,053 INFO [train.py:715] (3/8) Epoch 3, batch 11450, loss[loss=0.177, simple_loss=0.2485, pruned_loss=0.05279, over 4896.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2326, pruned_loss=0.04792, over 972118.14 frames.], batch size: 17, lr: 5.57e-04
+2022-05-04 13:33:50,184 INFO [train.py:715] (3/8) Epoch 3, batch 11500, loss[loss=0.1874, simple_loss=0.2566, pruned_loss=0.05911, over 4947.00 frames.], tot_loss[loss=0.164, simple_loss=0.2326, pruned_loss=0.04768, over 972815.39 frames.], batch size: 21, lr: 5.57e-04
+2022-05-04 13:34:32,229 INFO [train.py:715] (3/8) Epoch 3, batch 11550, loss[loss=0.1677, simple_loss=0.2249, pruned_loss=0.0552, over 4852.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2321, pruned_loss=0.04778, over 972036.24 frames.], batch size: 32, lr: 5.57e-04
+2022-05-04 13:35:14,413 INFO [train.py:715] (3/8) Epoch 3, batch 11600, loss[loss=0.2227, simple_loss=0.2774, pruned_loss=0.08403, over 4777.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2316, pruned_loss=0.04768, over 972279.35 frames.], batch size: 17, lr: 5.57e-04
+2022-05-04 13:35:57,173 INFO [train.py:715] (3/8) Epoch 3, batch 11650, loss[loss=0.1605, simple_loss=0.2319, pruned_loss=0.04458, over 4984.00 frames.], tot_loss[loss=0.163, simple_loss=0.2313, pruned_loss=0.04735, over 972396.14 frames.], batch size: 15, lr: 5.57e-04
+2022-05-04 13:36:39,259 INFO [train.py:715] (3/8) Epoch 3, batch 11700, loss[loss=0.1363, simple_loss=0.2175, pruned_loss=0.02755, over 4901.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2317, pruned_loss=0.04729, over 973093.84 frames.], batch size: 19, lr: 5.57e-04
+2022-05-04 13:37:21,481 INFO [train.py:715] (3/8) Epoch 3, batch 11750, loss[loss=0.1252, simple_loss=0.1954, pruned_loss=0.02752, over 4979.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2312, pruned_loss=0.04756, over 972327.27 frames.], batch size: 14, lr: 5.56e-04
+2022-05-04 13:38:05,288 INFO [train.py:715] (3/8) Epoch 3, batch 11800, loss[loss=0.1747, simple_loss=0.241, pruned_loss=0.05422, over 4841.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2304, pruned_loss=0.04737, over 972792.55 frames.], batch size: 13, lr: 5.56e-04
+2022-05-04 13:38:47,460 INFO [train.py:715] (3/8) Epoch 3, batch 11850, loss[loss=0.1757, simple_loss=0.2458, pruned_loss=0.05282, over 4897.00 frames.], tot_loss[loss=0.163, simple_loss=0.2307, pruned_loss=0.04767, over 972859.78 frames.], batch size: 22, lr: 5.56e-04
+2022-05-04 13:39:29,605 INFO [train.py:715] (3/8) Epoch 3, batch 11900, loss[loss=0.1746, simple_loss=0.2284, pruned_loss=0.0604, over 4785.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2296, pruned_loss=0.04685, over 971849.79 frames.], batch size: 18, lr: 5.56e-04
+2022-05-04 13:40:11,703 INFO [train.py:715] (3/8) Epoch 3, batch 11950, loss[loss=0.1688, simple_loss=0.2311, pruned_loss=0.05326, over 4913.00 frames.], tot_loss[loss=0.162, simple_loss=0.2299, pruned_loss=0.04699, over 972470.00 frames.], batch size: 18, lr: 5.56e-04
+2022-05-04 13:40:54,203 INFO [train.py:715] (3/8) Epoch 3, batch 12000, loss[loss=0.1644, simple_loss=0.2276, pruned_loss=0.05058, over 4885.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2297, pruned_loss=0.04662, over 972878.06 frames.], batch size: 19, lr: 5.56e-04
+2022-05-04 13:40:54,204 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 13:41:02,571 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1142, simple_loss=0.2003, pruned_loss=0.01401, over 914524.00 frames.
+2022-05-04 13:41:44,684 INFO [train.py:715] (3/8) Epoch 3, batch 12050, loss[loss=0.1514, simple_loss=0.2146, pruned_loss=0.04414, over 4852.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2302, pruned_loss=0.04694, over 972703.73 frames.], batch size: 30, lr: 5.56e-04
+2022-05-04 13:42:26,373 INFO [train.py:715] (3/8) Epoch 3, batch 12100, loss[loss=0.1444, simple_loss=0.2065, pruned_loss=0.0411, over 4686.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2305, pruned_loss=0.04712, over 972178.09 frames.], batch size: 15, lr: 5.56e-04
+2022-05-04 13:43:08,779 INFO [train.py:715] (3/8) Epoch 3, batch 12150, loss[loss=0.1406, simple_loss=0.2072, pruned_loss=0.03699, over 4963.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2298, pruned_loss=0.04691, over 971692.59 frames.], batch size: 35, lr: 5.55e-04
+2022-05-04 13:43:52,020 INFO [train.py:715] (3/8) Epoch 3, batch 12200, loss[loss=0.1802, simple_loss=0.2427, pruned_loss=0.05889, over 4821.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2294, pruned_loss=0.04685, over 972262.00 frames.], batch size: 25, lr: 5.55e-04
+2022-05-04 13:44:33,690 INFO [train.py:715] (3/8) Epoch 3, batch 12250, loss[loss=0.1369, simple_loss=0.2122, pruned_loss=0.03081, over 4950.00 frames.], tot_loss[loss=0.1621, simple_loss=0.23, pruned_loss=0.04712, over 971927.24 frames.], batch size: 21, lr: 5.55e-04
+2022-05-04 13:45:15,595 INFO [train.py:715] (3/8) Epoch 3, batch 12300, loss[loss=0.1918, simple_loss=0.2665, pruned_loss=0.05856, over 4937.00 frames.], tot_loss[loss=0.162, simple_loss=0.2299, pruned_loss=0.04704, over 972390.07 frames.], batch size: 21, lr: 5.55e-04
+2022-05-04 13:45:58,050 INFO [train.py:715] (3/8) Epoch 3, batch 12350, loss[loss=0.1556, simple_loss=0.2238, pruned_loss=0.04371, over 4903.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2306, pruned_loss=0.04683, over 971386.28 frames.], batch size: 18, lr: 5.55e-04
+2022-05-04 13:46:41,401 INFO [train.py:715] (3/8) Epoch 3, batch 12400, loss[loss=0.1931, simple_loss=0.2475, pruned_loss=0.0694, over 4811.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2305, pruned_loss=0.04667, over 971157.93 frames.], batch size: 25, lr: 5.55e-04
+2022-05-04 13:47:23,070 INFO [train.py:715] (3/8) Epoch 3, batch 12450, loss[loss=0.2162, simple_loss=0.2896, pruned_loss=0.07141, over 4940.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2315, pruned_loss=0.0475, over 971895.50 frames.], batch size: 29, lr: 5.55e-04
+2022-05-04 13:48:04,574 INFO [train.py:715] (3/8) Epoch 3, batch 12500, loss[loss=0.1345, simple_loss=0.2124, pruned_loss=0.02833, over 4943.00 frames.], tot_loss[loss=0.1625, simple_loss=0.231, pruned_loss=0.04702, over 971581.72 frames.], batch size: 29, lr: 5.55e-04
+2022-05-04 13:48:47,317 INFO [train.py:715] (3/8) Epoch 3, batch 12550, loss[loss=0.171, simple_loss=0.2422, pruned_loss=0.04987, over 4843.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2325, pruned_loss=0.04834, over 971818.76 frames.], batch size: 34, lr: 5.54e-04
+2022-05-04 13:49:29,596 INFO [train.py:715] (3/8) Epoch 3, batch 12600, loss[loss=0.1446, simple_loss=0.2188, pruned_loss=0.0352, over 4822.00 frames.], tot_loss[loss=0.165, simple_loss=0.233, pruned_loss=0.04851, over 971363.72 frames.], batch size: 26, lr: 5.54e-04
+2022-05-04 13:50:11,359 INFO [train.py:715] (3/8) Epoch 3, batch 12650, loss[loss=0.1418, simple_loss=0.2068, pruned_loss=0.03839, over 4781.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2324, pruned_loss=0.04825, over 971761.81 frames.], batch size: 14, lr: 5.54e-04
+2022-05-04 13:50:53,060 INFO [train.py:715] (3/8) Epoch 3, batch 12700, loss[loss=0.1582, simple_loss=0.2262, pruned_loss=0.0451, over 4785.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2319, pruned_loss=0.04786, over 972032.04 frames.], batch size: 17, lr: 5.54e-04
+2022-05-04 13:51:35,155 INFO [train.py:715] (3/8) Epoch 3, batch 12750, loss[loss=0.1864, simple_loss=0.2578, pruned_loss=0.05755, over 4934.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2311, pruned_loss=0.04765, over 971475.88 frames.], batch size: 23, lr: 5.54e-04
+2022-05-04 13:52:17,427 INFO [train.py:715] (3/8) Epoch 3, batch 12800, loss[loss=0.1986, simple_loss=0.2666, pruned_loss=0.06533, over 4969.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2307, pruned_loss=0.04793, over 971526.51 frames.], batch size: 15, lr: 5.54e-04
+2022-05-04 13:52:58,259 INFO [train.py:715] (3/8) Epoch 3, batch 12850, loss[loss=0.1571, simple_loss=0.2157, pruned_loss=0.04928, over 4841.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2307, pruned_loss=0.04723, over 971876.99 frames.], batch size: 13, lr: 5.54e-04
+2022-05-04 13:53:40,955 INFO [train.py:715] (3/8) Epoch 3, batch 12900, loss[loss=0.2198, simple_loss=0.2816, pruned_loss=0.07896, over 4704.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2322, pruned_loss=0.04845, over 971579.47 frames.], batch size: 15, lr: 5.54e-04
+2022-05-04 13:54:23,559 INFO [train.py:715] (3/8) Epoch 3, batch 12950, loss[loss=0.1867, simple_loss=0.2484, pruned_loss=0.06251, over 4976.00 frames.], tot_loss[loss=0.165, simple_loss=0.2327, pruned_loss=0.04865, over 972063.34 frames.], batch size: 24, lr: 5.54e-04
+2022-05-04 13:55:04,929 INFO [train.py:715] (3/8) Epoch 3, batch 13000, loss[loss=0.1785, simple_loss=0.2561, pruned_loss=0.05049, over 4748.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2337, pruned_loss=0.04861, over 971606.91 frames.], batch size: 19, lr: 5.53e-04
+2022-05-04 13:55:46,798 INFO [train.py:715] (3/8) Epoch 3, batch 13050, loss[loss=0.1792, simple_loss=0.2405, pruned_loss=0.05897, over 4958.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2332, pruned_loss=0.04864, over 971280.17 frames.], batch size: 24, lr: 5.53e-04
+2022-05-04 13:56:28,788 INFO [train.py:715] (3/8) Epoch 3, batch 13100, loss[loss=0.1555, simple_loss=0.2151, pruned_loss=0.04799, over 4946.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2322, pruned_loss=0.04825, over 971868.84 frames.], batch size: 35, lr: 5.53e-04
+2022-05-04 13:57:10,554 INFO [train.py:715] (3/8) Epoch 3, batch 13150, loss[loss=0.1702, simple_loss=0.2359, pruned_loss=0.05227, over 4948.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2326, pruned_loss=0.04829, over 971907.15 frames.], batch size: 35, lr: 5.53e-04
+2022-05-04 13:57:52,117 INFO [train.py:715] (3/8) Epoch 3, batch 13200, loss[loss=0.1962, simple_loss=0.2515, pruned_loss=0.07039, over 4950.00 frames.], tot_loss[loss=0.1643, simple_loss=0.232, pruned_loss=0.04834, over 972064.67 frames.], batch size: 35, lr: 5.53e-04
+2022-05-04 13:58:34,746 INFO [train.py:715] (3/8) Epoch 3, batch 13250, loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03162, over 4867.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2314, pruned_loss=0.04826, over 972694.81 frames.], batch size: 20, lr: 5.53e-04
+2022-05-04 13:59:17,144 INFO [train.py:715] (3/8) Epoch 3, batch 13300, loss[loss=0.1492, simple_loss=0.2194, pruned_loss=0.0395, over 4705.00 frames.], tot_loss[loss=0.163, simple_loss=0.2308, pruned_loss=0.04764, over 972472.21 frames.], batch size: 15, lr: 5.53e-04
+2022-05-04 13:59:58,633 INFO [train.py:715] (3/8) Epoch 3, batch 13350, loss[loss=0.1887, simple_loss=0.2602, pruned_loss=0.05864, over 4844.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2296, pruned_loss=0.04674, over 972611.16 frames.], batch size: 32, lr: 5.53e-04
+2022-05-04 14:00:40,467 INFO [train.py:715] (3/8) Epoch 3, batch 13400, loss[loss=0.14, simple_loss=0.2147, pruned_loss=0.0327, over 4917.00 frames.], tot_loss[loss=0.162, simple_loss=0.23, pruned_loss=0.04705, over 972844.91 frames.], batch size: 18, lr: 5.52e-04
+2022-05-04 14:01:23,052 INFO [train.py:715] (3/8) Epoch 3, batch 13450, loss[loss=0.155, simple_loss=0.2267, pruned_loss=0.04162, over 4795.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2312, pruned_loss=0.0479, over 972961.48 frames.], batch size: 14, lr: 5.52e-04
+2022-05-04 14:02:04,524 INFO [train.py:715] (3/8) Epoch 3, batch 13500, loss[loss=0.1742, simple_loss=0.248, pruned_loss=0.05023, over 4939.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2311, pruned_loss=0.0479, over 973693.48 frames.], batch size: 21, lr: 5.52e-04
+2022-05-04 14:02:46,050 INFO [train.py:715] (3/8) Epoch 3, batch 13550, loss[loss=0.1509, simple_loss=0.2206, pruned_loss=0.04057, over 4873.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2303, pruned_loss=0.0475, over 973409.67 frames.], batch size: 22, lr: 5.52e-04
+2022-05-04 14:03:28,377 INFO [train.py:715] (3/8) Epoch 3, batch 13600, loss[loss=0.1953, simple_loss=0.2517, pruned_loss=0.06943, over 4822.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2295, pruned_loss=0.04666, over 972482.29 frames.], batch size: 15, lr: 5.52e-04
+2022-05-04 14:04:10,279 INFO [train.py:715] (3/8) Epoch 3, batch 13650, loss[loss=0.1671, simple_loss=0.234, pruned_loss=0.05008, over 4767.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2309, pruned_loss=0.0469, over 972645.74 frames.], batch size: 17, lr: 5.52e-04
+2022-05-04 14:04:51,708 INFO [train.py:715] (3/8) Epoch 3, batch 13700, loss[loss=0.2033, simple_loss=0.2629, pruned_loss=0.07189, over 4962.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2307, pruned_loss=0.04706, over 972966.20 frames.], batch size: 29, lr: 5.52e-04
+2022-05-04 14:05:34,464 INFO [train.py:715] (3/8) Epoch 3, batch 13750, loss[loss=0.1653, simple_loss=0.2484, pruned_loss=0.04105, over 4756.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2306, pruned_loss=0.04717, over 973128.75 frames.], batch size: 19, lr: 5.52e-04
+2022-05-04 14:06:16,547 INFO [train.py:715] (3/8) Epoch 3, batch 13800, loss[loss=0.1504, simple_loss=0.2218, pruned_loss=0.03945, over 4852.00 frames.], tot_loss[loss=0.1629, simple_loss=0.231, pruned_loss=0.04739, over 973279.57 frames.], batch size: 20, lr: 5.52e-04
+2022-05-04 14:06:58,025 INFO [train.py:715] (3/8) Epoch 3, batch 13850, loss[loss=0.1702, simple_loss=0.2457, pruned_loss=0.04735, over 4923.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2314, pruned_loss=0.0474, over 973005.63 frames.], batch size: 29, lr: 5.51e-04
+2022-05-04 14:07:39,262 INFO [train.py:715] (3/8) Epoch 3, batch 13900, loss[loss=0.1602, simple_loss=0.2259, pruned_loss=0.04727, over 4791.00 frames.], tot_loss[loss=0.1634, simple_loss=0.232, pruned_loss=0.04742, over 973569.66 frames.], batch size: 24, lr: 5.51e-04
+2022-05-04 14:08:21,702 INFO [train.py:715] (3/8) Epoch 3, batch 13950, loss[loss=0.143, simple_loss=0.211, pruned_loss=0.03748, over 4814.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2318, pruned_loss=0.04772, over 973303.34 frames.], batch size: 27, lr: 5.51e-04
+2022-05-04 14:09:04,161 INFO [train.py:715] (3/8) Epoch 3, batch 14000, loss[loss=0.1492, simple_loss=0.2166, pruned_loss=0.04091, over 4762.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2326, pruned_loss=0.04794, over 973595.56 frames.], batch size: 19, lr: 5.51e-04
+2022-05-04 14:09:45,590 INFO [train.py:715] (3/8) Epoch 3, batch 14050, loss[loss=0.164, simple_loss=0.2343, pruned_loss=0.04687, over 4937.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2327, pruned_loss=0.04828, over 973892.02 frames.], batch size: 29, lr: 5.51e-04
+2022-05-04 14:10:28,391 INFO [train.py:715] (3/8) Epoch 3, batch 14100, loss[loss=0.177, simple_loss=0.2452, pruned_loss=0.0544, over 4769.00 frames.], tot_loss[loss=0.165, simple_loss=0.233, pruned_loss=0.04853, over 973391.08 frames.], batch size: 17, lr: 5.51e-04
+2022-05-04 14:11:10,224 INFO [train.py:715] (3/8) Epoch 3, batch 14150, loss[loss=0.1699, simple_loss=0.2267, pruned_loss=0.05661, over 4862.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2317, pruned_loss=0.04803, over 973182.12 frames.], batch size: 32, lr: 5.51e-04
+2022-05-04 14:11:51,368 INFO [train.py:715] (3/8) Epoch 3, batch 14200, loss[loss=0.1424, simple_loss=0.214, pruned_loss=0.03541, over 4770.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2308, pruned_loss=0.04742, over 973260.28 frames.], batch size: 14, lr: 5.51e-04
+2022-05-04 14:12:33,502 INFO [train.py:715] (3/8) Epoch 3, batch 14250, loss[loss=0.1747, simple_loss=0.2451, pruned_loss=0.05217, over 4969.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2319, pruned_loss=0.04784, over 973015.88 frames.], batch size: 14, lr: 5.51e-04
+2022-05-04 14:13:15,873 INFO [train.py:715] (3/8) Epoch 3, batch 14300, loss[loss=0.1666, simple_loss=0.2253, pruned_loss=0.05395, over 4897.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2314, pruned_loss=0.04752, over 972873.73 frames.], batch size: 17, lr: 5.50e-04
+2022-05-04 14:13:58,172 INFO [train.py:715] (3/8) Epoch 3, batch 14350, loss[loss=0.1762, simple_loss=0.2433, pruned_loss=0.05449, over 4829.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2309, pruned_loss=0.04723, over 972783.78 frames.], batch size: 15, lr: 5.50e-04
+2022-05-04 14:14:38,948 INFO [train.py:715] (3/8) Epoch 3, batch 14400, loss[loss=0.1665, simple_loss=0.2445, pruned_loss=0.04431, over 4934.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2312, pruned_loss=0.04734, over 972342.68 frames.], batch size: 21, lr: 5.50e-04
+2022-05-04 14:15:21,406 INFO [train.py:715] (3/8) Epoch 3, batch 14450, loss[loss=0.1726, simple_loss=0.2345, pruned_loss=0.05534, over 4750.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2313, pruned_loss=0.04752, over 972265.60 frames.], batch size: 16, lr: 5.50e-04
+2022-05-04 14:16:03,343 INFO [train.py:715] (3/8) Epoch 3, batch 14500, loss[loss=0.167, simple_loss=0.242, pruned_loss=0.04603, over 4935.00 frames.], tot_loss[loss=0.1629, simple_loss=0.231, pruned_loss=0.04734, over 972153.26 frames.], batch size: 23, lr: 5.50e-04
+2022-05-04 14:16:44,524 INFO [train.py:715] (3/8) Epoch 3, batch 14550, loss[loss=0.1849, simple_loss=0.2485, pruned_loss=0.06066, over 4796.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2315, pruned_loss=0.04794, over 972441.00 frames.], batch size: 21, lr: 5.50e-04
+2022-05-04 14:17:26,977 INFO [train.py:715] (3/8) Epoch 3, batch 14600, loss[loss=0.1502, simple_loss=0.228, pruned_loss=0.03624, over 4819.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2308, pruned_loss=0.04731, over 972598.35 frames.], batch size: 25, lr: 5.50e-04
+2022-05-04 14:18:08,860 INFO [train.py:715] (3/8) Epoch 3, batch 14650, loss[loss=0.1358, simple_loss=0.2045, pruned_loss=0.03352, over 4872.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2319, pruned_loss=0.04751, over 971873.55 frames.], batch size: 16, lr: 5.50e-04
+2022-05-04 14:18:50,910 INFO [train.py:715] (3/8) Epoch 3, batch 14700, loss[loss=0.1562, simple_loss=0.213, pruned_loss=0.04972, over 4926.00 frames.], tot_loss[loss=0.162, simple_loss=0.2305, pruned_loss=0.04675, over 971699.40 frames.], batch size: 23, lr: 5.49e-04
+2022-05-04 14:19:32,219 INFO [train.py:715] (3/8) Epoch 3, batch 14750, loss[loss=0.1735, simple_loss=0.2453, pruned_loss=0.05083, over 4831.00 frames.], tot_loss[loss=0.163, simple_loss=0.2317, pruned_loss=0.04709, over 972225.16 frames.], batch size: 15, lr: 5.49e-04
+2022-05-04 14:20:14,631 INFO [train.py:715] (3/8) Epoch 3, batch 14800, loss[loss=0.2014, simple_loss=0.2648, pruned_loss=0.06899, over 4973.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2315, pruned_loss=0.04735, over 972629.61 frames.], batch size: 35, lr: 5.49e-04
+2022-05-04 14:20:56,941 INFO [train.py:715] (3/8) Epoch 3, batch 14850, loss[loss=0.1369, simple_loss=0.1982, pruned_loss=0.03783, over 4859.00 frames.], tot_loss[loss=0.163, simple_loss=0.2315, pruned_loss=0.04727, over 972724.40 frames.], batch size: 32, lr: 5.49e-04
+2022-05-04 14:21:37,852 INFO [train.py:715] (3/8) Epoch 3, batch 14900, loss[loss=0.1761, simple_loss=0.2348, pruned_loss=0.05868, over 4843.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2316, pruned_loss=0.04772, over 972075.51 frames.], batch size: 30, lr: 5.49e-04
+2022-05-04 14:22:20,813 INFO [train.py:715] (3/8) Epoch 3, batch 14950, loss[loss=0.1701, simple_loss=0.2436, pruned_loss=0.04835, over 4766.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2307, pruned_loss=0.04707, over 971285.80 frames.], batch size: 18, lr: 5.49e-04
+2022-05-04 14:23:02,210 INFO [train.py:715] (3/8) Epoch 3, batch 15000, loss[loss=0.1577, simple_loss=0.2306, pruned_loss=0.04235, over 4983.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2309, pruned_loss=0.04687, over 971751.67 frames.], batch size: 25, lr: 5.49e-04
+2022-05-04 14:23:02,211 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 14:23:10,875 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1142, simple_loss=0.2003, pruned_loss=0.01402, over 914524.00 frames.
+2022-05-04 14:23:52,705 INFO [train.py:715] (3/8) Epoch 3, batch 15050, loss[loss=0.2046, simple_loss=0.2722, pruned_loss=0.06849, over 4980.00 frames.], tot_loss[loss=0.165, simple_loss=0.233, pruned_loss=0.0485, over 971218.80 frames.], batch size: 39, lr: 5.49e-04
+2022-05-04 14:24:34,028 INFO [train.py:715] (3/8) Epoch 3, batch 15100, loss[loss=0.1485, simple_loss=0.2232, pruned_loss=0.03696, over 4927.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2324, pruned_loss=0.04827, over 971293.26 frames.], batch size: 23, lr: 5.49e-04
+2022-05-04 14:25:16,180 INFO [train.py:715] (3/8) Epoch 3, batch 15150, loss[loss=0.1434, simple_loss=0.2089, pruned_loss=0.03893, over 4932.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2324, pruned_loss=0.04807, over 970466.86 frames.], batch size: 18, lr: 5.48e-04
+2022-05-04 14:25:57,812 INFO [train.py:715] (3/8) Epoch 3, batch 15200, loss[loss=0.1817, simple_loss=0.2617, pruned_loss=0.05082, over 4796.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2326, pruned_loss=0.04795, over 970372.35 frames.], batch size: 17, lr: 5.48e-04
+2022-05-04 14:26:39,371 INFO [train.py:715] (3/8) Epoch 3, batch 15250, loss[loss=0.1824, simple_loss=0.2465, pruned_loss=0.05919, over 4931.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2328, pruned_loss=0.04788, over 970884.40 frames.], batch size: 39, lr: 5.48e-04
+2022-05-04 14:27:20,704 INFO [train.py:715] (3/8) Epoch 3, batch 15300, loss[loss=0.1585, simple_loss=0.2279, pruned_loss=0.04452, over 4921.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2324, pruned_loss=0.04732, over 972215.29 frames.], batch size: 18, lr: 5.48e-04
+2022-05-04 14:28:02,525 INFO [train.py:715] (3/8) Epoch 3, batch 15350, loss[loss=0.1599, simple_loss=0.2324, pruned_loss=0.04367, over 4957.00 frames.], tot_loss[loss=0.1626, simple_loss=0.231, pruned_loss=0.04712, over 971668.00 frames.], batch size: 15, lr: 5.48e-04
+2022-05-04 14:28:44,643 INFO [train.py:715] (3/8) Epoch 3, batch 15400, loss[loss=0.1729, simple_loss=0.2457, pruned_loss=0.05003, over 4951.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2314, pruned_loss=0.04752, over 971843.04 frames.], batch size: 35, lr: 5.48e-04
+2022-05-04 14:29:25,741 INFO [train.py:715] (3/8) Epoch 3, batch 15450, loss[loss=0.1573, simple_loss=0.2327, pruned_loss=0.04093, over 4856.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2307, pruned_loss=0.0469, over 972375.19 frames.], batch size: 20, lr: 5.48e-04
+2022-05-04 14:30:08,680 INFO [train.py:715] (3/8) Epoch 3, batch 15500, loss[loss=0.1526, simple_loss=0.2365, pruned_loss=0.03432, over 4986.00 frames.], tot_loss[loss=0.164, simple_loss=0.2321, pruned_loss=0.04799, over 972282.98 frames.], batch size: 24, lr: 5.48e-04
+2022-05-04 14:30:50,506 INFO [train.py:715] (3/8) Epoch 3, batch 15550, loss[loss=0.1495, simple_loss=0.2323, pruned_loss=0.03336, over 4952.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2313, pruned_loss=0.04711, over 971781.49 frames.], batch size: 15, lr: 5.48e-04
+2022-05-04 14:31:35,085 INFO [train.py:715] (3/8) Epoch 3, batch 15600, loss[loss=0.1408, simple_loss=0.2097, pruned_loss=0.03594, over 4941.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2327, pruned_loss=0.04772, over 970984.66 frames.], batch size: 29, lr: 5.47e-04
+2022-05-04 14:32:16,097 INFO [train.py:715] (3/8) Epoch 3, batch 15650, loss[loss=0.1573, simple_loss=0.2337, pruned_loss=0.04048, over 4860.00 frames.], tot_loss[loss=0.1642, simple_loss=0.233, pruned_loss=0.04774, over 971158.52 frames.], batch size: 32, lr: 5.47e-04
+2022-05-04 14:32:57,688 INFO [train.py:715] (3/8) Epoch 3, batch 15700, loss[loss=0.1593, simple_loss=0.2231, pruned_loss=0.04778, over 4902.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2323, pruned_loss=0.04745, over 971799.50 frames.], batch size: 19, lr: 5.47e-04
+2022-05-04 14:33:40,522 INFO [train.py:715] (3/8) Epoch 3, batch 15750, loss[loss=0.1658, simple_loss=0.2425, pruned_loss=0.0445, over 4958.00 frames.], tot_loss[loss=0.163, simple_loss=0.232, pruned_loss=0.04707, over 971618.86 frames.], batch size: 24, lr: 5.47e-04
+2022-05-04 14:34:22,328 INFO [train.py:715] (3/8) Epoch 3, batch 15800, loss[loss=0.1842, simple_loss=0.2436, pruned_loss=0.06242, over 4978.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2316, pruned_loss=0.04729, over 973035.22 frames.], batch size: 33, lr: 5.47e-04
+2022-05-04 14:35:03,581 INFO [train.py:715] (3/8) Epoch 3, batch 15850, loss[loss=0.1676, simple_loss=0.2331, pruned_loss=0.05104, over 4870.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2323, pruned_loss=0.04778, over 973474.62 frames.], batch size: 16, lr: 5.47e-04
+2022-05-04 14:35:45,953 INFO [train.py:715] (3/8) Epoch 3, batch 15900, loss[loss=0.1938, simple_loss=0.2549, pruned_loss=0.06634, over 4867.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04755, over 973428.25 frames.], batch size: 32, lr: 5.47e-04
+2022-05-04 14:36:28,593 INFO [train.py:715] (3/8) Epoch 3, batch 15950, loss[loss=0.1743, simple_loss=0.2401, pruned_loss=0.05428, over 4829.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2316, pruned_loss=0.0476, over 973236.72 frames.], batch size: 26, lr: 5.47e-04
+2022-05-04 14:37:09,197 INFO [train.py:715] (3/8) Epoch 3, batch 16000, loss[loss=0.1591, simple_loss=0.2185, pruned_loss=0.04988, over 4846.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2312, pruned_loss=0.04698, over 973968.88 frames.], batch size: 32, lr: 5.47e-04
+2022-05-04 14:37:50,848 INFO [train.py:715] (3/8) Epoch 3, batch 16050, loss[loss=0.1452, simple_loss=0.2292, pruned_loss=0.03061, over 4891.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2314, pruned_loss=0.04699, over 974145.06 frames.], batch size: 22, lr: 5.46e-04
+2022-05-04 14:38:33,475 INFO [train.py:715] (3/8) Epoch 3, batch 16100, loss[loss=0.1563, simple_loss=0.2303, pruned_loss=0.04116, over 4939.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2312, pruned_loss=0.04698, over 974089.73 frames.], batch size: 24, lr: 5.46e-04
+2022-05-04 14:39:15,448 INFO [train.py:715] (3/8) Epoch 3, batch 16150, loss[loss=0.129, simple_loss=0.2065, pruned_loss=0.02574, over 4823.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2303, pruned_loss=0.04631, over 972892.97 frames.], batch size: 26, lr: 5.46e-04
+2022-05-04 14:39:56,183 INFO [train.py:715] (3/8) Epoch 3, batch 16200, loss[loss=0.1633, simple_loss=0.223, pruned_loss=0.05176, over 4711.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2306, pruned_loss=0.0463, over 972029.68 frames.], batch size: 15, lr: 5.46e-04
+2022-05-04 14:40:38,486 INFO [train.py:715] (3/8) Epoch 3, batch 16250, loss[loss=0.1523, simple_loss=0.2337, pruned_loss=0.03544, over 4892.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2307, pruned_loss=0.04623, over 971772.92 frames.], batch size: 22, lr: 5.46e-04
+2022-05-04 14:41:20,553 INFO [train.py:715] (3/8) Epoch 3, batch 16300, loss[loss=0.1361, simple_loss=0.2076, pruned_loss=0.03228, over 4989.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2305, pruned_loss=0.04596, over 970944.17 frames.], batch size: 14, lr: 5.46e-04
+2022-05-04 14:42:01,217 INFO [train.py:715] (3/8) Epoch 3, batch 16350, loss[loss=0.1708, simple_loss=0.2325, pruned_loss=0.05454, over 4894.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2304, pruned_loss=0.04637, over 971047.12 frames.], batch size: 39, lr: 5.46e-04
+2022-05-04 14:42:43,180 INFO [train.py:715] (3/8) Epoch 3, batch 16400, loss[loss=0.1629, simple_loss=0.2398, pruned_loss=0.04293, over 4933.00 frames.], tot_loss[loss=0.1621, simple_loss=0.231, pruned_loss=0.0466, over 972108.62 frames.], batch size: 23, lr: 5.46e-04
+2022-05-04 14:43:25,720 INFO [train.py:715] (3/8) Epoch 3, batch 16450, loss[loss=0.1802, simple_loss=0.2461, pruned_loss=0.05719, over 4886.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2306, pruned_loss=0.04723, over 971499.70 frames.], batch size: 17, lr: 5.45e-04
+2022-05-04 14:44:08,339 INFO [train.py:715] (3/8) Epoch 3, batch 16500, loss[loss=0.1577, simple_loss=0.2212, pruned_loss=0.04707, over 4857.00 frames.], tot_loss[loss=0.162, simple_loss=0.2302, pruned_loss=0.04685, over 971252.64 frames.], batch size: 20, lr: 5.45e-04
+2022-05-04 14:44:49,040 INFO [train.py:715] (3/8) Epoch 3, batch 16550, loss[loss=0.1885, simple_loss=0.2631, pruned_loss=0.05701, over 4915.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2302, pruned_loss=0.04707, over 971453.18 frames.], batch size: 39, lr: 5.45e-04
+2022-05-04 14:45:31,915 INFO [train.py:715] (3/8) Epoch 3, batch 16600, loss[loss=0.1682, simple_loss=0.2354, pruned_loss=0.05049, over 4965.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2302, pruned_loss=0.047, over 972765.90 frames.], batch size: 15, lr: 5.45e-04
+2022-05-04 14:46:14,681 INFO [train.py:715] (3/8) Epoch 3, batch 16650, loss[loss=0.1317, simple_loss=0.2045, pruned_loss=0.02944, over 4860.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2298, pruned_loss=0.04702, over 973307.36 frames.], batch size: 32, lr: 5.45e-04
+2022-05-04 14:46:55,377 INFO [train.py:715] (3/8) Epoch 3, batch 16700, loss[loss=0.1653, simple_loss=0.2414, pruned_loss=0.0446, over 4832.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2308, pruned_loss=0.04753, over 973142.42 frames.], batch size: 13, lr: 5.45e-04
+2022-05-04 14:47:37,406 INFO [train.py:715] (3/8) Epoch 3, batch 16750, loss[loss=0.1572, simple_loss=0.2248, pruned_loss=0.04478, over 4978.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2308, pruned_loss=0.04752, over 972859.89 frames.], batch size: 35, lr: 5.45e-04
+2022-05-04 14:48:19,855 INFO [train.py:715] (3/8) Epoch 3, batch 16800, loss[loss=0.1409, simple_loss=0.2098, pruned_loss=0.03602, over 4818.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2305, pruned_loss=0.04737, over 972760.76 frames.], batch size: 25, lr: 5.45e-04
+2022-05-04 14:49:01,331 INFO [train.py:715] (3/8) Epoch 3, batch 16850, loss[loss=0.1605, simple_loss=0.2334, pruned_loss=0.04375, over 4913.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2304, pruned_loss=0.04718, over 972964.86 frames.], batch size: 29, lr: 5.45e-04
+2022-05-04 14:49:42,744 INFO [train.py:715] (3/8) Epoch 3, batch 16900, loss[loss=0.1876, simple_loss=0.2506, pruned_loss=0.06232, over 4994.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2303, pruned_loss=0.04711, over 972805.20 frames.], batch size: 14, lr: 5.44e-04
+2022-05-04 14:50:24,685 INFO [train.py:715] (3/8) Epoch 3, batch 16950, loss[loss=0.1665, simple_loss=0.2356, pruned_loss=0.04868, over 4815.00 frames.], tot_loss[loss=0.163, simple_loss=0.2309, pruned_loss=0.04756, over 973219.25 frames.], batch size: 25, lr: 5.44e-04
+2022-05-04 14:51:07,235 INFO [train.py:715] (3/8) Epoch 3, batch 17000, loss[loss=0.1466, simple_loss=0.2224, pruned_loss=0.03542, over 4789.00 frames.], tot_loss[loss=0.163, simple_loss=0.2311, pruned_loss=0.04751, over 972863.92 frames.], batch size: 17, lr: 5.44e-04
+2022-05-04 14:51:47,564 INFO [train.py:715] (3/8) Epoch 3, batch 17050, loss[loss=0.1621, simple_loss=0.2384, pruned_loss=0.04285, over 4976.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2316, pruned_loss=0.0473, over 972597.65 frames.], batch size: 24, lr: 5.44e-04
+2022-05-04 14:52:29,479 INFO [train.py:715] (3/8) Epoch 3, batch 17100, loss[loss=0.1649, simple_loss=0.2259, pruned_loss=0.05191, over 4921.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2311, pruned_loss=0.04725, over 972608.72 frames.], batch size: 23, lr: 5.44e-04
+2022-05-04 14:53:11,179 INFO [train.py:715] (3/8) Epoch 3, batch 17150, loss[loss=0.14, simple_loss=0.2069, pruned_loss=0.03651, over 4834.00 frames.], tot_loss[loss=0.163, simple_loss=0.2313, pruned_loss=0.04739, over 971875.05 frames.], batch size: 13, lr: 5.44e-04
+2022-05-04 14:53:52,355 INFO [train.py:715] (3/8) Epoch 3, batch 17200, loss[loss=0.1689, simple_loss=0.2374, pruned_loss=0.05025, over 4965.00 frames.], tot_loss[loss=0.162, simple_loss=0.2304, pruned_loss=0.04683, over 971177.29 frames.], batch size: 15, lr: 5.44e-04
+2022-05-04 14:54:33,050 INFO [train.py:715] (3/8) Epoch 3, batch 17250, loss[loss=0.168, simple_loss=0.2364, pruned_loss=0.04977, over 4891.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2298, pruned_loss=0.04671, over 970794.38 frames.], batch size: 19, lr: 5.44e-04
+2022-05-04 14:55:14,506 INFO [train.py:715] (3/8) Epoch 3, batch 17300, loss[loss=0.1672, simple_loss=0.2283, pruned_loss=0.05304, over 4861.00 frames.], tot_loss[loss=0.162, simple_loss=0.2298, pruned_loss=0.04708, over 971459.67 frames.], batch size: 32, lr: 5.44e-04
+2022-05-04 14:55:56,122 INFO [train.py:715] (3/8) Epoch 3, batch 17350, loss[loss=0.1698, simple_loss=0.2371, pruned_loss=0.05126, over 4932.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2302, pruned_loss=0.04733, over 972436.74 frames.], batch size: 39, lr: 5.43e-04
+2022-05-04 14:56:36,186 INFO [train.py:715] (3/8) Epoch 3, batch 17400, loss[loss=0.1272, simple_loss=0.1967, pruned_loss=0.02882, over 4768.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2307, pruned_loss=0.04758, over 972520.17 frames.], batch size: 12, lr: 5.43e-04
+2022-05-04 14:57:18,253 INFO [train.py:715] (3/8) Epoch 3, batch 17450, loss[loss=0.1892, simple_loss=0.267, pruned_loss=0.05576, over 4817.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2293, pruned_loss=0.04641, over 972917.09 frames.], batch size: 27, lr: 5.43e-04
+2022-05-04 14:58:00,474 INFO [train.py:715] (3/8) Epoch 3, batch 17500, loss[loss=0.1491, simple_loss=0.2169, pruned_loss=0.04071, over 4773.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2303, pruned_loss=0.04661, over 973234.36 frames.], batch size: 18, lr: 5.43e-04
+2022-05-04 14:58:41,509 INFO [train.py:715] (3/8) Epoch 3, batch 17550, loss[loss=0.1446, simple_loss=0.207, pruned_loss=0.04114, over 4776.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2291, pruned_loss=0.046, over 973529.89 frames.], batch size: 18, lr: 5.43e-04
+2022-05-04 14:59:22,856 INFO [train.py:715] (3/8) Epoch 3, batch 17600, loss[loss=0.1636, simple_loss=0.2326, pruned_loss=0.04723, over 4814.00 frames.], tot_loss[loss=0.161, simple_loss=0.2292, pruned_loss=0.04636, over 973850.25 frames.], batch size: 27, lr: 5.43e-04
+2022-05-04 15:00:04,534 INFO [train.py:715] (3/8) Epoch 3, batch 17650, loss[loss=0.1809, simple_loss=0.2498, pruned_loss=0.056, over 4796.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2289, pruned_loss=0.04631, over 972691.85 frames.], batch size: 21, lr: 5.43e-04
+2022-05-04 15:00:46,085 INFO [train.py:715] (3/8) Epoch 3, batch 17700, loss[loss=0.1738, simple_loss=0.2315, pruned_loss=0.05807, over 4812.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2289, pruned_loss=0.04668, over 972541.40 frames.], batch size: 25, lr: 5.43e-04
+2022-05-04 15:01:26,895 INFO [train.py:715] (3/8) Epoch 3, batch 17750, loss[loss=0.1609, simple_loss=0.243, pruned_loss=0.03935, over 4942.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2295, pruned_loss=0.04694, over 972889.77 frames.], batch size: 29, lr: 5.43e-04
+2022-05-04 15:02:08,926 INFO [train.py:715] (3/8) Epoch 3, batch 17800, loss[loss=0.1624, simple_loss=0.2292, pruned_loss=0.04779, over 4908.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2298, pruned_loss=0.04685, over 972100.92 frames.], batch size: 17, lr: 5.42e-04
+2022-05-04 15:02:50,347 INFO [train.py:715] (3/8) Epoch 3, batch 17850, loss[loss=0.144, simple_loss=0.2165, pruned_loss=0.03571, over 4748.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2296, pruned_loss=0.04631, over 971765.66 frames.], batch size: 19, lr: 5.42e-04
+2022-05-04 15:03:30,306 INFO [train.py:715] (3/8) Epoch 3, batch 17900, loss[loss=0.1747, simple_loss=0.2436, pruned_loss=0.0529, over 4918.00 frames.], tot_loss[loss=0.1613, simple_loss=0.23, pruned_loss=0.04633, over 971398.97 frames.], batch size: 39, lr: 5.42e-04
+2022-05-04 15:04:12,146 INFO [train.py:715] (3/8) Epoch 3, batch 17950, loss[loss=0.185, simple_loss=0.2499, pruned_loss=0.06011, over 4818.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2297, pruned_loss=0.04643, over 970943.32 frames.], batch size: 26, lr: 5.42e-04
+2022-05-04 15:04:53,407 INFO [train.py:715] (3/8) Epoch 3, batch 18000, loss[loss=0.182, simple_loss=0.2628, pruned_loss=0.05055, over 4761.00 frames.], tot_loss[loss=0.1618, simple_loss=0.23, pruned_loss=0.0468, over 971469.50 frames.], batch size: 18, lr: 5.42e-04
+2022-05-04 15:04:53,408 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 15:05:02,069 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1143, simple_loss=0.2002, pruned_loss=0.01414, over 914524.00 frames.
+2022-05-04 15:05:43,867 INFO [train.py:715] (3/8) Epoch 3, batch 18050, loss[loss=0.1517, simple_loss=0.2142, pruned_loss=0.04459, over 4766.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2294, pruned_loss=0.04665, over 972202.76 frames.], batch size: 17, lr: 5.42e-04
+2022-05-04 15:06:25,511 INFO [train.py:715] (3/8) Epoch 3, batch 18100, loss[loss=0.1403, simple_loss=0.2091, pruned_loss=0.03578, over 4937.00 frames.], tot_loss[loss=0.1617, simple_loss=0.23, pruned_loss=0.04666, over 972322.68 frames.], batch size: 29, lr: 5.42e-04
+2022-05-04 15:07:06,175 INFO [train.py:715] (3/8) Epoch 3, batch 18150, loss[loss=0.1619, simple_loss=0.2204, pruned_loss=0.05175, over 4940.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2303, pruned_loss=0.04724, over 972934.38 frames.], batch size: 35, lr: 5.42e-04
+2022-05-04 15:07:47,679 INFO [train.py:715] (3/8) Epoch 3, batch 18200, loss[loss=0.154, simple_loss=0.2253, pruned_loss=0.04132, over 4826.00 frames.], tot_loss[loss=0.1634, simple_loss=0.231, pruned_loss=0.04787, over 972146.69 frames.], batch size: 13, lr: 5.42e-04
+2022-05-04 15:08:29,475 INFO [train.py:715] (3/8) Epoch 3, batch 18250, loss[loss=0.1514, simple_loss=0.2075, pruned_loss=0.04764, over 4863.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2303, pruned_loss=0.04754, over 972165.56 frames.], batch size: 13, lr: 5.41e-04
+2022-05-04 15:09:10,292 INFO [train.py:715] (3/8) Epoch 3, batch 18300, loss[loss=0.1858, simple_loss=0.2547, pruned_loss=0.05849, over 4892.00 frames.], tot_loss[loss=0.162, simple_loss=0.2301, pruned_loss=0.04695, over 971737.66 frames.], batch size: 19, lr: 5.41e-04
+2022-05-04 15:09:51,601 INFO [train.py:715] (3/8) Epoch 3, batch 18350, loss[loss=0.1347, simple_loss=0.2094, pruned_loss=0.03004, over 4749.00 frames.], tot_loss[loss=0.161, simple_loss=0.2295, pruned_loss=0.04623, over 971479.53 frames.], batch size: 19, lr: 5.41e-04
+2022-05-04 15:10:33,029 INFO [train.py:715] (3/8) Epoch 3, batch 18400, loss[loss=0.1767, simple_loss=0.2287, pruned_loss=0.06232, over 4920.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2295, pruned_loss=0.04637, over 971896.87 frames.], batch size: 18, lr: 5.41e-04
+2022-05-04 15:11:13,985 INFO [train.py:715] (3/8) Epoch 3, batch 18450, loss[loss=0.141, simple_loss=0.2103, pruned_loss=0.03582, over 4930.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2313, pruned_loss=0.04707, over 971235.85 frames.], batch size: 29, lr: 5.41e-04
+2022-05-04 15:11:55,020 INFO [train.py:715] (3/8) Epoch 3, batch 18500, loss[loss=0.1594, simple_loss=0.2126, pruned_loss=0.05314, over 4906.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2321, pruned_loss=0.04754, over 970928.64 frames.], batch size: 19, lr: 5.41e-04
+2022-05-04 15:12:36,398 INFO [train.py:715] (3/8) Epoch 3, batch 18550, loss[loss=0.1173, simple_loss=0.1942, pruned_loss=0.02021, over 4968.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.0476, over 971185.18 frames.], batch size: 14, lr: 5.41e-04
+2022-05-04 15:13:18,629 INFO [train.py:715] (3/8) Epoch 3, batch 18600, loss[loss=0.1773, simple_loss=0.2531, pruned_loss=0.05077, over 4902.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2321, pruned_loss=0.04758, over 972170.95 frames.], batch size: 17, lr: 5.41e-04
+2022-05-04 15:13:58,619 INFO [train.py:715] (3/8) Epoch 3, batch 18650, loss[loss=0.1671, simple_loss=0.2342, pruned_loss=0.04997, over 4764.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2317, pruned_loss=0.04764, over 971672.24 frames.], batch size: 19, lr: 5.41e-04
+2022-05-04 15:14:39,320 INFO [train.py:715] (3/8) Epoch 3, batch 18700, loss[loss=0.1513, simple_loss=0.2138, pruned_loss=0.04446, over 4866.00 frames.], tot_loss[loss=0.1628, simple_loss=0.231, pruned_loss=0.04726, over 971902.45 frames.], batch size: 13, lr: 5.40e-04
+2022-05-04 15:15:20,416 INFO [train.py:715] (3/8) Epoch 3, batch 18750, loss[loss=0.127, simple_loss=0.1911, pruned_loss=0.03146, over 4837.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2295, pruned_loss=0.04609, over 971753.26 frames.], batch size: 26, lr: 5.40e-04
+2022-05-04 15:16:00,281 INFO [train.py:715] (3/8) Epoch 3, batch 18800, loss[loss=0.1426, simple_loss=0.2161, pruned_loss=0.03453, over 4821.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2298, pruned_loss=0.04627, over 970851.98 frames.], batch size: 26, lr: 5.40e-04
+2022-05-04 15:16:41,100 INFO [train.py:715] (3/8) Epoch 3, batch 18850, loss[loss=0.1622, simple_loss=0.2325, pruned_loss=0.046, over 4863.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2312, pruned_loss=0.04695, over 970384.87 frames.], batch size: 30, lr: 5.40e-04
+2022-05-04 15:17:21,056 INFO [train.py:715] (3/8) Epoch 3, batch 18900, loss[loss=0.1722, simple_loss=0.2378, pruned_loss=0.05328, over 4987.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2306, pruned_loss=0.04699, over 971701.91 frames.], batch size: 25, lr: 5.40e-04
+2022-05-04 15:18:01,539 INFO [train.py:715] (3/8) Epoch 3, batch 18950, loss[loss=0.1428, simple_loss=0.2148, pruned_loss=0.03547, over 4958.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2306, pruned_loss=0.04698, over 971806.44 frames.], batch size: 15, lr: 5.40e-04
+2022-05-04 15:18:40,942 INFO [train.py:715] (3/8) Epoch 3, batch 19000, loss[loss=0.1921, simple_loss=0.2432, pruned_loss=0.07053, over 4864.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2313, pruned_loss=0.04694, over 971857.71 frames.], batch size: 32, lr: 5.40e-04
+2022-05-04 15:19:20,768 INFO [train.py:715] (3/8) Epoch 3, batch 19050, loss[loss=0.1274, simple_loss=0.195, pruned_loss=0.02992, over 4791.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2306, pruned_loss=0.04659, over 971870.56 frames.], batch size: 14, lr: 5.40e-04
+2022-05-04 15:20:01,074 INFO [train.py:715] (3/8) Epoch 3, batch 19100, loss[loss=0.1896, simple_loss=0.2507, pruned_loss=0.06422, over 4839.00 frames.], tot_loss[loss=0.161, simple_loss=0.23, pruned_loss=0.04599, over 972127.55 frames.], batch size: 30, lr: 5.40e-04
+2022-05-04 15:20:40,496 INFO [train.py:715] (3/8) Epoch 3, batch 19150, loss[loss=0.1454, simple_loss=0.2186, pruned_loss=0.03612, over 4862.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2301, pruned_loss=0.04581, over 972424.22 frames.], batch size: 13, lr: 5.40e-04
+2022-05-04 15:21:20,179 INFO [train.py:715] (3/8) Epoch 3, batch 19200, loss[loss=0.1503, simple_loss=0.2237, pruned_loss=0.03844, over 4950.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2303, pruned_loss=0.04636, over 972981.72 frames.], batch size: 15, lr: 5.39e-04
+2022-05-04 15:21:59,826 INFO [train.py:715] (3/8) Epoch 3, batch 19250, loss[loss=0.1921, simple_loss=0.2592, pruned_loss=0.06245, over 4806.00 frames.], tot_loss[loss=0.1622, simple_loss=0.231, pruned_loss=0.04674, over 973183.35 frames.], batch size: 24, lr: 5.39e-04
+2022-05-04 15:22:40,129 INFO [train.py:715] (3/8) Epoch 3, batch 19300, loss[loss=0.1695, simple_loss=0.2235, pruned_loss=0.05771, over 4897.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2308, pruned_loss=0.04699, over 973235.44 frames.], batch size: 18, lr: 5.39e-04
+2022-05-04 15:23:19,473 INFO [train.py:715] (3/8) Epoch 3, batch 19350, loss[loss=0.2466, simple_loss=0.3076, pruned_loss=0.0928, over 4757.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2312, pruned_loss=0.04692, over 972795.11 frames.], batch size: 19, lr: 5.39e-04
+2022-05-04 15:23:59,203 INFO [train.py:715] (3/8) Epoch 3, batch 19400, loss[loss=0.2093, simple_loss=0.2717, pruned_loss=0.07344, over 4904.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2314, pruned_loss=0.04702, over 973033.48 frames.], batch size: 18, lr: 5.39e-04
+2022-05-04 15:24:39,296 INFO [train.py:715] (3/8) Epoch 3, batch 19450, loss[loss=0.189, simple_loss=0.2481, pruned_loss=0.06497, over 4812.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2333, pruned_loss=0.04826, over 972755.43 frames.], batch size: 21, lr: 5.39e-04
+2022-05-04 15:25:18,371 INFO [train.py:715] (3/8) Epoch 3, batch 19500, loss[loss=0.178, simple_loss=0.2249, pruned_loss=0.06555, over 4825.00 frames.], tot_loss[loss=0.1647, simple_loss=0.233, pruned_loss=0.04816, over 973785.72 frames.], batch size: 13, lr: 5.39e-04
+2022-05-04 15:25:58,125 INFO [train.py:715] (3/8) Epoch 3, batch 19550, loss[loss=0.1347, simple_loss=0.2098, pruned_loss=0.02982, over 4695.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2329, pruned_loss=0.04817, over 973199.52 frames.], batch size: 15, lr: 5.39e-04
+2022-05-04 15:26:37,669 INFO [train.py:715] (3/8) Epoch 3, batch 19600, loss[loss=0.1611, simple_loss=0.2302, pruned_loss=0.04599, over 4953.00 frames.], tot_loss[loss=0.1645, simple_loss=0.233, pruned_loss=0.04797, over 972260.31 frames.], batch size: 39, lr: 5.39e-04
+2022-05-04 15:27:17,574 INFO [train.py:715] (3/8) Epoch 3, batch 19650, loss[loss=0.1668, simple_loss=0.2258, pruned_loss=0.05385, over 4932.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2316, pruned_loss=0.04738, over 972415.13 frames.], batch size: 18, lr: 5.38e-04
+2022-05-04 15:27:56,472 INFO [train.py:715] (3/8) Epoch 3, batch 19700, loss[loss=0.1848, simple_loss=0.2604, pruned_loss=0.05464, over 4919.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2316, pruned_loss=0.04769, over 972745.34 frames.], batch size: 29, lr: 5.38e-04
+2022-05-04 15:28:36,070 INFO [train.py:715] (3/8) Epoch 3, batch 19750, loss[loss=0.1674, simple_loss=0.2334, pruned_loss=0.05068, over 4940.00 frames.], tot_loss[loss=0.1625, simple_loss=0.231, pruned_loss=0.04703, over 973014.19 frames.], batch size: 18, lr: 5.38e-04
+2022-05-04 15:29:15,541 INFO [train.py:715] (3/8) Epoch 3, batch 19800, loss[loss=0.1569, simple_loss=0.2213, pruned_loss=0.04622, over 4905.00 frames.], tot_loss[loss=0.1638, simple_loss=0.232, pruned_loss=0.04783, over 973928.43 frames.], batch size: 22, lr: 5.38e-04
+2022-05-04 15:29:55,117 INFO [train.py:715] (3/8) Epoch 3, batch 19850, loss[loss=0.1465, simple_loss=0.211, pruned_loss=0.04101, over 4930.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2311, pruned_loss=0.04722, over 972843.32 frames.], batch size: 23, lr: 5.38e-04
+2022-05-04 15:30:34,816 INFO [train.py:715] (3/8) Epoch 3, batch 19900, loss[loss=0.2109, simple_loss=0.2648, pruned_loss=0.07845, over 4699.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2306, pruned_loss=0.04703, over 972814.16 frames.], batch size: 15, lr: 5.38e-04
+2022-05-04 15:31:15,109 INFO [train.py:715] (3/8) Epoch 3, batch 19950, loss[loss=0.1957, simple_loss=0.2651, pruned_loss=0.06318, over 4837.00 frames.], tot_loss[loss=0.162, simple_loss=0.2306, pruned_loss=0.04668, over 971991.34 frames.], batch size: 32, lr: 5.38e-04
+2022-05-04 15:31:54,892 INFO [train.py:715] (3/8) Epoch 3, batch 20000, loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03842, over 4985.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2289, pruned_loss=0.04601, over 972568.98 frames.], batch size: 24, lr: 5.38e-04
+2022-05-04 15:32:34,163 INFO [train.py:715] (3/8) Epoch 3, batch 20050, loss[loss=0.1625, simple_loss=0.2255, pruned_loss=0.04977, over 4776.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2287, pruned_loss=0.04638, over 972306.15 frames.], batch size: 17, lr: 5.38e-04
+2022-05-04 15:33:14,400 INFO [train.py:715] (3/8) Epoch 3, batch 20100, loss[loss=0.1399, simple_loss=0.2071, pruned_loss=0.03636, over 4896.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2288, pruned_loss=0.04612, over 972318.99 frames.], batch size: 19, lr: 5.37e-04
+2022-05-04 15:33:54,295 INFO [train.py:715] (3/8) Epoch 3, batch 20150, loss[loss=0.1757, simple_loss=0.2373, pruned_loss=0.05706, over 4765.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2296, pruned_loss=0.04661, over 971781.01 frames.], batch size: 18, lr: 5.37e-04
+2022-05-04 15:34:33,627 INFO [train.py:715] (3/8) Epoch 3, batch 20200, loss[loss=0.1427, simple_loss=0.2106, pruned_loss=0.03738, over 4936.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2297, pruned_loss=0.04662, over 972370.30 frames.], batch size: 35, lr: 5.37e-04
+2022-05-04 15:35:13,294 INFO [train.py:715] (3/8) Epoch 3, batch 20250, loss[loss=0.1666, simple_loss=0.226, pruned_loss=0.05359, over 4867.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2298, pruned_loss=0.04635, over 972115.20 frames.], batch size: 20, lr: 5.37e-04
+2022-05-04 15:35:53,125 INFO [train.py:715] (3/8) Epoch 3, batch 20300, loss[loss=0.1806, simple_loss=0.248, pruned_loss=0.05656, over 4801.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2303, pruned_loss=0.04669, over 972633.44 frames.], batch size: 21, lr: 5.37e-04
+2022-05-04 15:36:33,508 INFO [train.py:715] (3/8) Epoch 3, batch 20350, loss[loss=0.1658, simple_loss=0.2353, pruned_loss=0.04815, over 4914.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2298, pruned_loss=0.04657, over 972403.18 frames.], batch size: 18, lr: 5.37e-04
+2022-05-04 15:37:12,087 INFO [train.py:715] (3/8) Epoch 3, batch 20400, loss[loss=0.1828, simple_loss=0.2553, pruned_loss=0.05512, over 4904.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2298, pruned_loss=0.04661, over 972446.45 frames.], batch size: 17, lr: 5.37e-04
+2022-05-04 15:37:51,790 INFO [train.py:715] (3/8) Epoch 3, batch 20450, loss[loss=0.1488, simple_loss=0.2301, pruned_loss=0.03379, over 4816.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2304, pruned_loss=0.04724, over 972214.85 frames.], batch size: 13, lr: 5.37e-04
+2022-05-04 15:38:31,862 INFO [train.py:715] (3/8) Epoch 3, batch 20500, loss[loss=0.1688, simple_loss=0.2366, pruned_loss=0.0505, over 4914.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2301, pruned_loss=0.04726, over 971281.78 frames.], batch size: 17, lr: 5.37e-04
+2022-05-04 15:39:10,982 INFO [train.py:715] (3/8) Epoch 3, batch 20550, loss[loss=0.1967, simple_loss=0.2747, pruned_loss=0.05937, over 4804.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2315, pruned_loss=0.04815, over 970365.77 frames.], batch size: 24, lr: 5.36e-04
+2022-05-04 15:39:50,435 INFO [train.py:715] (3/8) Epoch 3, batch 20600, loss[loss=0.1738, simple_loss=0.2434, pruned_loss=0.05204, over 4789.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2313, pruned_loss=0.04752, over 970193.30 frames.], batch size: 14, lr: 5.36e-04
+2022-05-04 15:40:30,882 INFO [train.py:715] (3/8) Epoch 3, batch 20650, loss[loss=0.1452, simple_loss=0.2144, pruned_loss=0.03802, over 4984.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2311, pruned_loss=0.04759, over 971116.81 frames.], batch size: 27, lr: 5.36e-04
+2022-05-04 15:41:10,736 INFO [train.py:715] (3/8) Epoch 3, batch 20700, loss[loss=0.1464, simple_loss=0.2122, pruned_loss=0.04034, over 4804.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2302, pruned_loss=0.04704, over 971589.36 frames.], batch size: 14, lr: 5.36e-04
+2022-05-04 15:41:50,204 INFO [train.py:715] (3/8) Epoch 3, batch 20750, loss[loss=0.142, simple_loss=0.2113, pruned_loss=0.03637, over 4938.00 frames.], tot_loss[loss=0.1617, simple_loss=0.23, pruned_loss=0.04675, over 971816.23 frames.], batch size: 35, lr: 5.36e-04
+2022-05-04 15:42:30,290 INFO [train.py:715] (3/8) Epoch 3, batch 20800, loss[loss=0.1542, simple_loss=0.2203, pruned_loss=0.04404, over 4983.00 frames.], tot_loss[loss=0.1615, simple_loss=0.23, pruned_loss=0.04655, over 972309.12 frames.], batch size: 15, lr: 5.36e-04
+2022-05-04 15:43:11,033 INFO [train.py:715] (3/8) Epoch 3, batch 20850, loss[loss=0.1785, simple_loss=0.2424, pruned_loss=0.05726, over 4908.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2304, pruned_loss=0.04654, over 972806.87 frames.], batch size: 18, lr: 5.36e-04
+2022-05-04 15:43:50,801 INFO [train.py:715] (3/8) Epoch 3, batch 20900, loss[loss=0.139, simple_loss=0.2099, pruned_loss=0.03404, over 4767.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2314, pruned_loss=0.04697, over 972719.33 frames.], batch size: 19, lr: 5.36e-04
+2022-05-04 15:44:31,207 INFO [train.py:715] (3/8) Epoch 3, batch 20950, loss[loss=0.1672, simple_loss=0.2348, pruned_loss=0.0498, over 4784.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2317, pruned_loss=0.0473, over 973093.64 frames.], batch size: 18, lr: 5.36e-04
+2022-05-04 15:45:11,742 INFO [train.py:715] (3/8) Epoch 3, batch 21000, loss[loss=0.1703, simple_loss=0.2296, pruned_loss=0.05548, over 4764.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2317, pruned_loss=0.04725, over 973386.66 frames.], batch size: 19, lr: 5.36e-04
+2022-05-04 15:45:11,742 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 15:45:24,192 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1137, simple_loss=0.1999, pruned_loss=0.01377, over 914524.00 frames.
+2022-05-04 15:46:04,597 INFO [train.py:715] (3/8) Epoch 3, batch 21050, loss[loss=0.1303, simple_loss=0.2033, pruned_loss=0.02862, over 4983.00 frames.], tot_loss[loss=0.1637, simple_loss=0.232, pruned_loss=0.04772, over 973467.47 frames.], batch size: 14, lr: 5.35e-04
+2022-05-04 15:46:45,382 INFO [train.py:715] (3/8) Epoch 3, batch 21100, loss[loss=0.1317, simple_loss=0.2072, pruned_loss=0.02808, over 4814.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2311, pruned_loss=0.04737, over 973858.89 frames.], batch size: 26, lr: 5.35e-04
+2022-05-04 15:47:25,767 INFO [train.py:715] (3/8) Epoch 3, batch 21150, loss[loss=0.1986, simple_loss=0.2776, pruned_loss=0.05979, over 4962.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2307, pruned_loss=0.04739, over 973307.98 frames.], batch size: 24, lr: 5.35e-04
+2022-05-04 15:48:08,588 INFO [train.py:715] (3/8) Epoch 3, batch 21200, loss[loss=0.1546, simple_loss=0.2274, pruned_loss=0.04095, over 4703.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2302, pruned_loss=0.0466, over 973068.88 frames.], batch size: 15, lr: 5.35e-04
+2022-05-04 15:48:49,621 INFO [train.py:715] (3/8) Epoch 3, batch 21250, loss[loss=0.1406, simple_loss=0.2146, pruned_loss=0.03337, over 4740.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2311, pruned_loss=0.04704, over 973601.10 frames.], batch size: 16, lr: 5.35e-04
+2022-05-04 15:49:28,345 INFO [train.py:715] (3/8) Epoch 3, batch 21300, loss[loss=0.1585, simple_loss=0.2296, pruned_loss=0.04371, over 4973.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2304, pruned_loss=0.04698, over 972835.06 frames.], batch size: 24, lr: 5.35e-04
+2022-05-04 15:50:10,544 INFO [train.py:715] (3/8) Epoch 3, batch 21350, loss[loss=0.162, simple_loss=0.2293, pruned_loss=0.04729, over 4917.00 frames.], tot_loss[loss=0.162, simple_loss=0.2308, pruned_loss=0.0466, over 971996.65 frames.], batch size: 19, lr: 5.35e-04
+2022-05-04 15:50:51,359 INFO [train.py:715] (3/8) Epoch 3, batch 21400, loss[loss=0.1757, simple_loss=0.2445, pruned_loss=0.05344, over 4974.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2314, pruned_loss=0.04718, over 972774.80 frames.], batch size: 25, lr: 5.35e-04
+2022-05-04 15:51:30,339 INFO [train.py:715] (3/8) Epoch 3, batch 21450, loss[loss=0.1683, simple_loss=0.228, pruned_loss=0.0543, over 4988.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2304, pruned_loss=0.04652, over 973694.63 frames.], batch size: 25, lr: 5.35e-04
+2022-05-04 15:52:08,621 INFO [train.py:715] (3/8) Epoch 3, batch 21500, loss[loss=0.1541, simple_loss=0.2271, pruned_loss=0.04058, over 4861.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2306, pruned_loss=0.04626, over 973616.81 frames.], batch size: 16, lr: 5.34e-04
+2022-05-04 15:52:47,664 INFO [train.py:715] (3/8) Epoch 3, batch 21550, loss[loss=0.1352, simple_loss=0.2069, pruned_loss=0.03177, over 4788.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2308, pruned_loss=0.04646, over 973038.17 frames.], batch size: 24, lr: 5.34e-04
+2022-05-04 15:53:27,201 INFO [train.py:715] (3/8) Epoch 3, batch 21600, loss[loss=0.1456, simple_loss=0.2237, pruned_loss=0.0338, over 4827.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2314, pruned_loss=0.04684, over 972750.36 frames.], batch size: 25, lr: 5.34e-04
+2022-05-04 15:54:06,107 INFO [train.py:715] (3/8) Epoch 3, batch 21650, loss[loss=0.1545, simple_loss=0.227, pruned_loss=0.04099, over 4933.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2322, pruned_loss=0.0478, over 973217.31 frames.], batch size: 21, lr: 5.34e-04
+2022-05-04 15:54:46,392 INFO [train.py:715] (3/8) Epoch 3, batch 21700, loss[loss=0.1738, simple_loss=0.2394, pruned_loss=0.05408, over 4928.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2323, pruned_loss=0.04808, over 973563.74 frames.], batch size: 18, lr: 5.34e-04
+2022-05-04 15:55:26,905 INFO [train.py:715] (3/8) Epoch 3, batch 21750, loss[loss=0.1718, simple_loss=0.2441, pruned_loss=0.04971, over 4885.00 frames.], tot_loss[loss=0.164, simple_loss=0.2317, pruned_loss=0.0481, over 973614.20 frames.], batch size: 22, lr: 5.34e-04
+2022-05-04 15:56:06,026 INFO [train.py:715] (3/8) Epoch 3, batch 21800, loss[loss=0.1883, simple_loss=0.2394, pruned_loss=0.06862, over 4872.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2316, pruned_loss=0.04857, over 973336.42 frames.], batch size: 32, lr: 5.34e-04
+2022-05-04 15:56:44,181 INFO [train.py:715] (3/8) Epoch 3, batch 21850, loss[loss=0.1536, simple_loss=0.2174, pruned_loss=0.04491, over 4886.00 frames.], tot_loss[loss=0.1645, simple_loss=0.232, pruned_loss=0.04851, over 972699.61 frames.], batch size: 22, lr: 5.34e-04
+2022-05-04 15:57:22,930 INFO [train.py:715] (3/8) Epoch 3, batch 21900, loss[loss=0.1355, simple_loss=0.2031, pruned_loss=0.03398, over 4962.00 frames.], tot_loss[loss=0.1632, simple_loss=0.231, pruned_loss=0.04766, over 973118.95 frames.], batch size: 35, lr: 5.34e-04
+2022-05-04 15:58:03,623 INFO [train.py:715] (3/8) Epoch 3, batch 21950, loss[loss=0.1458, simple_loss=0.2148, pruned_loss=0.03841, over 4903.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2306, pruned_loss=0.04737, over 972248.46 frames.], batch size: 19, lr: 5.34e-04
+2022-05-04 15:58:43,250 INFO [train.py:715] (3/8) Epoch 3, batch 22000, loss[loss=0.1682, simple_loss=0.2385, pruned_loss=0.04901, over 4760.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2297, pruned_loss=0.04675, over 972192.72 frames.], batch size: 19, lr: 5.33e-04
+2022-05-04 15:59:23,573 INFO [train.py:715] (3/8) Epoch 3, batch 22050, loss[loss=0.1464, simple_loss=0.2248, pruned_loss=0.03399, over 4985.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2298, pruned_loss=0.04669, over 972040.32 frames.], batch size: 24, lr: 5.33e-04
+2022-05-04 16:00:04,306 INFO [train.py:715] (3/8) Epoch 3, batch 22100, loss[loss=0.1517, simple_loss=0.2316, pruned_loss=0.0359, over 4771.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2297, pruned_loss=0.04651, over 971438.00 frames.], batch size: 17, lr: 5.33e-04
+2022-05-04 16:00:44,824 INFO [train.py:715] (3/8) Epoch 3, batch 22150, loss[loss=0.1369, simple_loss=0.212, pruned_loss=0.03087, over 4976.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2297, pruned_loss=0.04599, over 971928.39 frames.], batch size: 25, lr: 5.33e-04
+2022-05-04 16:01:24,065 INFO [train.py:715] (3/8) Epoch 3, batch 22200, loss[loss=0.1725, simple_loss=0.2515, pruned_loss=0.04678, over 4944.00 frames.], tot_loss[loss=0.16, simple_loss=0.2288, pruned_loss=0.04564, over 972082.02 frames.], batch size: 21, lr: 5.33e-04
+2022-05-04 16:02:04,292 INFO [train.py:715] (3/8) Epoch 3, batch 22250, loss[loss=0.1741, simple_loss=0.2431, pruned_loss=0.0526, over 4988.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2287, pruned_loss=0.04549, over 972204.94 frames.], batch size: 15, lr: 5.33e-04
+2022-05-04 16:02:45,552 INFO [train.py:715] (3/8) Epoch 3, batch 22300, loss[loss=0.1683, simple_loss=0.2319, pruned_loss=0.05239, over 4888.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2303, pruned_loss=0.04626, over 972433.63 frames.], batch size: 19, lr: 5.33e-04
+2022-05-04 16:03:24,535 INFO [train.py:715] (3/8) Epoch 3, batch 22350, loss[loss=0.1538, simple_loss=0.2257, pruned_loss=0.04098, over 4880.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2302, pruned_loss=0.04636, over 971321.04 frames.], batch size: 22, lr: 5.33e-04
+2022-05-04 16:04:04,612 INFO [train.py:715] (3/8) Epoch 3, batch 22400, loss[loss=0.1851, simple_loss=0.2522, pruned_loss=0.05898, over 4979.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2312, pruned_loss=0.04705, over 970914.01 frames.], batch size: 15, lr: 5.33e-04
+2022-05-04 16:04:45,519 INFO [train.py:715] (3/8) Epoch 3, batch 22450, loss[loss=0.1545, simple_loss=0.2324, pruned_loss=0.03827, over 4757.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2305, pruned_loss=0.04652, over 971387.94 frames.], batch size: 16, lr: 5.32e-04
+2022-05-04 16:05:25,969 INFO [train.py:715] (3/8) Epoch 3, batch 22500, loss[loss=0.1794, simple_loss=0.2474, pruned_loss=0.05571, over 4812.00 frames.], tot_loss[loss=0.163, simple_loss=0.2314, pruned_loss=0.04734, over 971745.64 frames.], batch size: 25, lr: 5.32e-04
+2022-05-04 16:06:05,381 INFO [train.py:715] (3/8) Epoch 3, batch 22550, loss[loss=0.1788, simple_loss=0.2368, pruned_loss=0.06041, over 4926.00 frames.], tot_loss[loss=0.1635, simple_loss=0.232, pruned_loss=0.04754, over 972120.07 frames.], batch size: 18, lr: 5.32e-04
+2022-05-04 16:06:45,641 INFO [train.py:715] (3/8) Epoch 3, batch 22600, loss[loss=0.1833, simple_loss=0.2492, pruned_loss=0.0587, over 4969.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2314, pruned_loss=0.04743, over 971992.91 frames.], batch size: 35, lr: 5.32e-04
+2022-05-04 16:07:26,481 INFO [train.py:715] (3/8) Epoch 3, batch 22650, loss[loss=0.1632, simple_loss=0.224, pruned_loss=0.05118, over 4754.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2305, pruned_loss=0.04688, over 972212.56 frames.], batch size: 19, lr: 5.32e-04
+2022-05-04 16:08:06,300 INFO [train.py:715] (3/8) Epoch 3, batch 22700, loss[loss=0.1438, simple_loss=0.2107, pruned_loss=0.0385, over 4788.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2313, pruned_loss=0.04721, over 972850.06 frames.], batch size: 14, lr: 5.32e-04
+2022-05-04 16:08:46,705 INFO [train.py:715] (3/8) Epoch 3, batch 22750, loss[loss=0.1777, simple_loss=0.2433, pruned_loss=0.05608, over 4858.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2325, pruned_loss=0.0475, over 973781.22 frames.], batch size: 32, lr: 5.32e-04
+2022-05-04 16:09:27,106 INFO [train.py:715] (3/8) Epoch 3, batch 22800, loss[loss=0.175, simple_loss=0.2494, pruned_loss=0.05026, over 4797.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2321, pruned_loss=0.04727, over 973547.98 frames.], batch size: 21, lr: 5.32e-04
+2022-05-04 16:10:07,178 INFO [train.py:715] (3/8) Epoch 3, batch 22850, loss[loss=0.1913, simple_loss=0.2374, pruned_loss=0.07262, over 4986.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2315, pruned_loss=0.0469, over 973099.35 frames.], batch size: 14, lr: 5.32e-04
+2022-05-04 16:10:46,896 INFO [train.py:715] (3/8) Epoch 3, batch 22900, loss[loss=0.1421, simple_loss=0.2203, pruned_loss=0.03191, over 4989.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2313, pruned_loss=0.04708, over 972513.01 frames.], batch size: 14, lr: 5.32e-04
+2022-05-04 16:11:27,326 INFO [train.py:715] (3/8) Epoch 3, batch 22950, loss[loss=0.1613, simple_loss=0.2281, pruned_loss=0.04728, over 4748.00 frames.], tot_loss[loss=0.163, simple_loss=0.2313, pruned_loss=0.04729, over 972833.20 frames.], batch size: 16, lr: 5.31e-04
+2022-05-04 16:12:08,441 INFO [train.py:715] (3/8) Epoch 3, batch 23000, loss[loss=0.1611, simple_loss=0.2253, pruned_loss=0.0484, over 4761.00 frames.], tot_loss[loss=0.1626, simple_loss=0.231, pruned_loss=0.0471, over 972221.07 frames.], batch size: 16, lr: 5.31e-04
+2022-05-04 16:12:48,300 INFO [train.py:715] (3/8) Epoch 3, batch 23050, loss[loss=0.1441, simple_loss=0.2102, pruned_loss=0.03906, over 4880.00 frames.], tot_loss[loss=0.1623, simple_loss=0.231, pruned_loss=0.04681, over 972248.34 frames.], batch size: 32, lr: 5.31e-04
+2022-05-04 16:13:28,632 INFO [train.py:715] (3/8) Epoch 3, batch 23100, loss[loss=0.1666, simple_loss=0.2269, pruned_loss=0.05316, over 4785.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2308, pruned_loss=0.0471, over 971352.39 frames.], batch size: 14, lr: 5.31e-04
+2022-05-04 16:14:09,397 INFO [train.py:715] (3/8) Epoch 3, batch 23150, loss[loss=0.125, simple_loss=0.1995, pruned_loss=0.02522, over 4827.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2297, pruned_loss=0.04659, over 971669.47 frames.], batch size: 27, lr: 5.31e-04
+2022-05-04 16:14:49,966 INFO [train.py:715] (3/8) Epoch 3, batch 23200, loss[loss=0.1713, simple_loss=0.2401, pruned_loss=0.05128, over 4932.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2303, pruned_loss=0.04698, over 972226.70 frames.], batch size: 29, lr: 5.31e-04
+2022-05-04 16:15:29,490 INFO [train.py:715] (3/8) Epoch 3, batch 23250, loss[loss=0.1671, simple_loss=0.2385, pruned_loss=0.04786, over 4798.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2308, pruned_loss=0.04736, over 972103.13 frames.], batch size: 25, lr: 5.31e-04
+2022-05-04 16:16:10,263 INFO [train.py:715] (3/8) Epoch 3, batch 23300, loss[loss=0.2208, simple_loss=0.2866, pruned_loss=0.07751, over 4746.00 frames.], tot_loss[loss=0.164, simple_loss=0.2316, pruned_loss=0.04819, over 972001.66 frames.], batch size: 16, lr: 5.31e-04
+2022-05-04 16:16:49,871 INFO [train.py:715] (3/8) Epoch 3, batch 23350, loss[loss=0.1732, simple_loss=0.2291, pruned_loss=0.05866, over 4864.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2323, pruned_loss=0.04839, over 972815.44 frames.], batch size: 32, lr: 5.31e-04
+2022-05-04 16:17:27,677 INFO [train.py:715] (3/8) Epoch 3, batch 23400, loss[loss=0.1688, simple_loss=0.2411, pruned_loss=0.0482, over 4986.00 frames.], tot_loss[loss=0.165, simple_loss=0.2332, pruned_loss=0.04838, over 973871.26 frames.], batch size: 28, lr: 5.30e-04
+2022-05-04 16:18:06,223 INFO [train.py:715] (3/8) Epoch 3, batch 23450, loss[loss=0.1496, simple_loss=0.2256, pruned_loss=0.03675, over 4774.00 frames.], tot_loss[loss=0.1635, simple_loss=0.232, pruned_loss=0.04749, over 972175.79 frames.], batch size: 14, lr: 5.30e-04
+2022-05-04 16:18:44,911 INFO [train.py:715] (3/8) Epoch 3, batch 23500, loss[loss=0.1719, simple_loss=0.2427, pruned_loss=0.05055, over 4858.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2319, pruned_loss=0.04736, over 971857.58 frames.], batch size: 38, lr: 5.30e-04
+2022-05-04 16:19:24,105 INFO [train.py:715] (3/8) Epoch 3, batch 23550, loss[loss=0.1734, simple_loss=0.2383, pruned_loss=0.05418, over 4817.00 frames.], tot_loss[loss=0.1626, simple_loss=0.231, pruned_loss=0.04711, over 972218.24 frames.], batch size: 15, lr: 5.30e-04
+2022-05-04 16:20:05,338 INFO [train.py:715] (3/8) Epoch 3, batch 23600, loss[loss=0.1547, simple_loss=0.2212, pruned_loss=0.0441, over 4832.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2304, pruned_loss=0.04687, over 971586.97 frames.], batch size: 15, lr: 5.30e-04
+2022-05-04 16:20:44,861 INFO [train.py:715] (3/8) Epoch 3, batch 23650, loss[loss=0.1276, simple_loss=0.1991, pruned_loss=0.02808, over 4805.00 frames.], tot_loss[loss=0.1616, simple_loss=0.23, pruned_loss=0.04661, over 971499.68 frames.], batch size: 13, lr: 5.30e-04
+2022-05-04 16:21:24,817 INFO [train.py:715] (3/8) Epoch 3, batch 23700, loss[loss=0.1515, simple_loss=0.2276, pruned_loss=0.03766, over 4859.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2312, pruned_loss=0.04697, over 971175.85 frames.], batch size: 20, lr: 5.30e-04
+2022-05-04 16:22:03,568 INFO [train.py:715] (3/8) Epoch 3, batch 23750, loss[loss=0.1899, simple_loss=0.2553, pruned_loss=0.06223, over 4948.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2309, pruned_loss=0.04671, over 971631.17 frames.], batch size: 21, lr: 5.30e-04
+2022-05-04 16:22:43,185 INFO [train.py:715] (3/8) Epoch 3, batch 23800, loss[loss=0.1516, simple_loss=0.2163, pruned_loss=0.04347, over 4886.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2301, pruned_loss=0.04607, over 972213.29 frames.], batch size: 19, lr: 5.30e-04
+2022-05-04 16:23:22,781 INFO [train.py:715] (3/8) Epoch 3, batch 23850, loss[loss=0.2179, simple_loss=0.2636, pruned_loss=0.08606, over 4907.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2307, pruned_loss=0.04633, over 972388.16 frames.], batch size: 17, lr: 5.30e-04
+2022-05-04 16:24:02,496 INFO [train.py:715] (3/8) Epoch 3, batch 23900, loss[loss=0.1647, simple_loss=0.23, pruned_loss=0.04976, over 4922.00 frames.], tot_loss[loss=0.1624, simple_loss=0.231, pruned_loss=0.04692, over 972185.18 frames.], batch size: 18, lr: 5.29e-04
+2022-05-04 16:24:41,550 INFO [train.py:715] (3/8) Epoch 3, batch 23950, loss[loss=0.1658, simple_loss=0.2353, pruned_loss=0.04816, over 4834.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2303, pruned_loss=0.04668, over 971656.66 frames.], batch size: 25, lr: 5.29e-04
+2022-05-04 16:25:20,399 INFO [train.py:715] (3/8) Epoch 3, batch 24000, loss[loss=0.1811, simple_loss=0.2339, pruned_loss=0.06413, over 4965.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2299, pruned_loss=0.04647, over 971854.29 frames.], batch size: 15, lr: 5.29e-04
+2022-05-04 16:25:20,399 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 16:25:32,861 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1132, simple_loss=0.1992, pruned_loss=0.0136, over 914524.00 frames.
+2022-05-04 16:26:12,212 INFO [train.py:715] (3/8) Epoch 3, batch 24050, loss[loss=0.1758, simple_loss=0.2405, pruned_loss=0.0555, over 4775.00 frames.], tot_loss[loss=0.161, simple_loss=0.2295, pruned_loss=0.04628, over 972028.11 frames.], batch size: 14, lr: 5.29e-04
+2022-05-04 16:26:52,061 INFO [train.py:715] (3/8) Epoch 3, batch 24100, loss[loss=0.1254, simple_loss=0.2044, pruned_loss=0.02315, over 4788.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2291, pruned_loss=0.04612, over 972796.04 frames.], batch size: 18, lr: 5.29e-04
+2022-05-04 16:27:30,860 INFO [train.py:715] (3/8) Epoch 3, batch 24150, loss[loss=0.1444, simple_loss=0.2124, pruned_loss=0.03822, over 4866.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2294, pruned_loss=0.04647, over 973139.25 frames.], batch size: 32, lr: 5.29e-04
+2022-05-04 16:28:10,106 INFO [train.py:715] (3/8) Epoch 3, batch 24200, loss[loss=0.1477, simple_loss=0.2161, pruned_loss=0.03967, over 4916.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2297, pruned_loss=0.04655, over 973056.72 frames.], batch size: 18, lr: 5.29e-04
+2022-05-04 16:28:50,508 INFO [train.py:715] (3/8) Epoch 3, batch 24250, loss[loss=0.203, simple_loss=0.2517, pruned_loss=0.07718, over 4921.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2298, pruned_loss=0.04692, over 972750.39 frames.], batch size: 39, lr: 5.29e-04
+2022-05-04 16:29:30,768 INFO [train.py:715] (3/8) Epoch 3, batch 24300, loss[loss=0.1539, simple_loss=0.236, pruned_loss=0.03592, over 4931.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2304, pruned_loss=0.04725, over 972480.75 frames.], batch size: 23, lr: 5.29e-04
+2022-05-04 16:30:10,089 INFO [train.py:715] (3/8) Epoch 3, batch 24350, loss[loss=0.1509, simple_loss=0.2207, pruned_loss=0.04052, over 4822.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2307, pruned_loss=0.04725, over 972306.66 frames.], batch size: 25, lr: 5.29e-04
+2022-05-04 16:30:49,733 INFO [train.py:715] (3/8) Epoch 3, batch 24400, loss[loss=0.1241, simple_loss=0.1954, pruned_loss=0.02642, over 4980.00 frames.], tot_loss[loss=0.162, simple_loss=0.2306, pruned_loss=0.04673, over 972707.12 frames.], batch size: 14, lr: 5.28e-04
+2022-05-04 16:31:29,802 INFO [train.py:715] (3/8) Epoch 3, batch 24450, loss[loss=0.1626, simple_loss=0.2355, pruned_loss=0.04482, over 4889.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2304, pruned_loss=0.04656, over 971910.86 frames.], batch size: 22, lr: 5.28e-04
+2022-05-04 16:32:09,117 INFO [train.py:715] (3/8) Epoch 3, batch 24500, loss[loss=0.1511, simple_loss=0.2274, pruned_loss=0.03743, over 4917.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2298, pruned_loss=0.04652, over 972598.08 frames.], batch size: 39, lr: 5.28e-04
+2022-05-04 16:32:48,514 INFO [train.py:715] (3/8) Epoch 3, batch 24550, loss[loss=0.2217, simple_loss=0.2723, pruned_loss=0.08552, over 4821.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2297, pruned_loss=0.0461, over 973880.82 frames.], batch size: 15, lr: 5.28e-04
+2022-05-04 16:33:28,760 INFO [train.py:715] (3/8) Epoch 3, batch 24600, loss[loss=0.1438, simple_loss=0.2163, pruned_loss=0.03561, over 4961.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2291, pruned_loss=0.04599, over 973935.82 frames.], batch size: 24, lr: 5.28e-04
+2022-05-04 16:34:08,288 INFO [train.py:715] (3/8) Epoch 3, batch 24650, loss[loss=0.1412, simple_loss=0.2091, pruned_loss=0.03665, over 4776.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2287, pruned_loss=0.04585, over 973624.28 frames.], batch size: 14, lr: 5.28e-04
+2022-05-04 16:34:47,792 INFO [train.py:715] (3/8) Epoch 3, batch 24700, loss[loss=0.175, simple_loss=0.2514, pruned_loss=0.04929, over 4749.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2289, pruned_loss=0.04611, over 973353.19 frames.], batch size: 16, lr: 5.28e-04
+2022-05-04 16:35:26,411 INFO [train.py:715] (3/8) Epoch 3, batch 24750, loss[loss=0.1826, simple_loss=0.257, pruned_loss=0.05413, over 4758.00 frames.], tot_loss[loss=0.1615, simple_loss=0.23, pruned_loss=0.04648, over 973175.64 frames.], batch size: 19, lr: 5.28e-04
+2022-05-04 16:36:07,062 INFO [train.py:715] (3/8) Epoch 3, batch 24800, loss[loss=0.1882, simple_loss=0.2405, pruned_loss=0.06792, over 4777.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2302, pruned_loss=0.04679, over 973707.47 frames.], batch size: 18, lr: 5.28e-04
+2022-05-04 16:36:46,785 INFO [train.py:715] (3/8) Epoch 3, batch 24850, loss[loss=0.1642, simple_loss=0.238, pruned_loss=0.04526, over 4863.00 frames.], tot_loss[loss=0.161, simple_loss=0.2297, pruned_loss=0.04613, over 972703.63 frames.], batch size: 20, lr: 5.28e-04
+2022-05-04 16:37:25,565 INFO [train.py:715] (3/8) Epoch 3, batch 24900, loss[loss=0.181, simple_loss=0.2422, pruned_loss=0.05988, over 4903.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2299, pruned_loss=0.04626, over 972608.06 frames.], batch size: 19, lr: 5.27e-04
+2022-05-04 16:38:05,477 INFO [train.py:715] (3/8) Epoch 3, batch 24950, loss[loss=0.1634, simple_loss=0.2279, pruned_loss=0.04949, over 4940.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2299, pruned_loss=0.04627, over 971972.54 frames.], batch size: 21, lr: 5.27e-04
+2022-05-04 16:38:45,653 INFO [train.py:715] (3/8) Epoch 3, batch 25000, loss[loss=0.1366, simple_loss=0.2013, pruned_loss=0.03593, over 4791.00 frames.], tot_loss[loss=0.1612, simple_loss=0.23, pruned_loss=0.04618, over 972390.35 frames.], batch size: 13, lr: 5.27e-04
+2022-05-04 16:39:25,200 INFO [train.py:715] (3/8) Epoch 3, batch 25050, loss[loss=0.1516, simple_loss=0.2262, pruned_loss=0.03856, over 4955.00 frames.], tot_loss[loss=0.1612, simple_loss=0.23, pruned_loss=0.04623, over 972903.05 frames.], batch size: 21, lr: 5.27e-04
+2022-05-04 16:40:04,367 INFO [train.py:715] (3/8) Epoch 3, batch 25100, loss[loss=0.1531, simple_loss=0.2406, pruned_loss=0.03283, over 4940.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2304, pruned_loss=0.0464, over 972668.73 frames.], batch size: 18, lr: 5.27e-04
+2022-05-04 16:40:44,395 INFO [train.py:715] (3/8) Epoch 3, batch 25150, loss[loss=0.143, simple_loss=0.2188, pruned_loss=0.03357, over 4954.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2305, pruned_loss=0.04645, over 972940.15 frames.], batch size: 14, lr: 5.27e-04
+2022-05-04 16:41:23,891 INFO [train.py:715] (3/8) Epoch 3, batch 25200, loss[loss=0.1601, simple_loss=0.2234, pruned_loss=0.04844, over 4761.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2308, pruned_loss=0.04703, over 972162.09 frames.], batch size: 16, lr: 5.27e-04
+2022-05-04 16:42:03,023 INFO [train.py:715] (3/8) Epoch 3, batch 25250, loss[loss=0.1477, simple_loss=0.2217, pruned_loss=0.03685, over 4887.00 frames.], tot_loss[loss=0.1627, simple_loss=0.231, pruned_loss=0.04721, over 973006.68 frames.], batch size: 22, lr: 5.27e-04
+2022-05-04 16:42:43,126 INFO [train.py:715] (3/8) Epoch 3, batch 25300, loss[loss=0.1501, simple_loss=0.2151, pruned_loss=0.04252, over 4820.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2315, pruned_loss=0.04753, over 972023.20 frames.], batch size: 26, lr: 5.27e-04
+2022-05-04 16:43:22,958 INFO [train.py:715] (3/8) Epoch 3, batch 25350, loss[loss=0.2013, simple_loss=0.2587, pruned_loss=0.07192, over 4867.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2327, pruned_loss=0.0482, over 972364.12 frames.], batch size: 13, lr: 5.26e-04
+2022-05-04 16:44:02,967 INFO [train.py:715] (3/8) Epoch 3, batch 25400, loss[loss=0.1567, simple_loss=0.2216, pruned_loss=0.04594, over 4804.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2319, pruned_loss=0.04753, over 971951.05 frames.], batch size: 21, lr: 5.26e-04
+2022-05-04 16:44:42,162 INFO [train.py:715] (3/8) Epoch 3, batch 25450, loss[loss=0.1571, simple_loss=0.2422, pruned_loss=0.03602, over 4874.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2327, pruned_loss=0.04785, over 973153.65 frames.], batch size: 22, lr: 5.26e-04
+2022-05-04 16:45:22,339 INFO [train.py:715] (3/8) Epoch 3, batch 25500, loss[loss=0.1656, simple_loss=0.2394, pruned_loss=0.04586, over 4864.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2313, pruned_loss=0.04711, over 973194.67 frames.], batch size: 30, lr: 5.26e-04
+2022-05-04 16:46:02,169 INFO [train.py:715] (3/8) Epoch 3, batch 25550, loss[loss=0.199, simple_loss=0.2595, pruned_loss=0.06925, over 4977.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2315, pruned_loss=0.04753, over 973500.18 frames.], batch size: 35, lr: 5.26e-04
+2022-05-04 16:46:41,627 INFO [train.py:715] (3/8) Epoch 3, batch 25600, loss[loss=0.1777, simple_loss=0.2563, pruned_loss=0.04954, over 4766.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2314, pruned_loss=0.04722, over 973626.04 frames.], batch size: 19, lr: 5.26e-04
+2022-05-04 16:47:22,009 INFO [train.py:715] (3/8) Epoch 3, batch 25650, loss[loss=0.1465, simple_loss=0.212, pruned_loss=0.04045, over 4770.00 frames.], tot_loss[loss=0.1623, simple_loss=0.231, pruned_loss=0.04683, over 973241.95 frames.], batch size: 18, lr: 5.26e-04
+2022-05-04 16:48:02,206 INFO [train.py:715] (3/8) Epoch 3, batch 25700, loss[loss=0.1752, simple_loss=0.2427, pruned_loss=0.05381, over 4920.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2309, pruned_loss=0.04674, over 973620.50 frames.], batch size: 18, lr: 5.26e-04
+2022-05-04 16:48:41,539 INFO [train.py:715] (3/8) Epoch 3, batch 25750, loss[loss=0.1521, simple_loss=0.214, pruned_loss=0.04516, over 4826.00 frames.], tot_loss[loss=0.1623, simple_loss=0.231, pruned_loss=0.04678, over 972521.18 frames.], batch size: 30, lr: 5.26e-04
+2022-05-04 16:49:21,104 INFO [train.py:715] (3/8) Epoch 3, batch 25800, loss[loss=0.1573, simple_loss=0.2194, pruned_loss=0.04756, over 4765.00 frames.], tot_loss[loss=0.163, simple_loss=0.2314, pruned_loss=0.04733, over 973138.52 frames.], batch size: 14, lr: 5.26e-04
+2022-05-04 16:50:01,082 INFO [train.py:715] (3/8) Epoch 3, batch 25850, loss[loss=0.1728, simple_loss=0.2481, pruned_loss=0.04875, over 4764.00 frames.], tot_loss[loss=0.1614, simple_loss=0.23, pruned_loss=0.04636, over 972660.10 frames.], batch size: 19, lr: 5.25e-04
+2022-05-04 16:50:39,397 INFO [train.py:715] (3/8) Epoch 3, batch 25900, loss[loss=0.166, simple_loss=0.2379, pruned_loss=0.04704, over 4852.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2295, pruned_loss=0.04616, over 972631.15 frames.], batch size: 20, lr: 5.25e-04
+2022-05-04 16:51:18,328 INFO [train.py:715] (3/8) Epoch 3, batch 25950, loss[loss=0.1701, simple_loss=0.2333, pruned_loss=0.05347, over 4873.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2301, pruned_loss=0.04657, over 972036.11 frames.], batch size: 30, lr: 5.25e-04
+2022-05-04 16:51:58,433 INFO [train.py:715] (3/8) Epoch 3, batch 26000, loss[loss=0.1405, simple_loss=0.2083, pruned_loss=0.0364, over 4985.00 frames.], tot_loss[loss=0.162, simple_loss=0.2303, pruned_loss=0.04681, over 972208.46 frames.], batch size: 25, lr: 5.25e-04
+2022-05-04 16:52:37,677 INFO [train.py:715] (3/8) Epoch 3, batch 26050, loss[loss=0.1538, simple_loss=0.2305, pruned_loss=0.03858, over 4747.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2305, pruned_loss=0.04668, over 972234.87 frames.], batch size: 16, lr: 5.25e-04
+2022-05-04 16:53:16,012 INFO [train.py:715] (3/8) Epoch 3, batch 26100, loss[loss=0.1658, simple_loss=0.2311, pruned_loss=0.0502, over 4983.00 frames.], tot_loss[loss=0.162, simple_loss=0.2304, pruned_loss=0.04676, over 971681.02 frames.], batch size: 25, lr: 5.25e-04
+2022-05-04 16:53:55,502 INFO [train.py:715] (3/8) Epoch 3, batch 26150, loss[loss=0.1718, simple_loss=0.2225, pruned_loss=0.06052, over 4802.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2304, pruned_loss=0.04713, over 971260.52 frames.], batch size: 12, lr: 5.25e-04
+2022-05-04 16:54:35,542 INFO [train.py:715] (3/8) Epoch 3, batch 26200, loss[loss=0.1559, simple_loss=0.2314, pruned_loss=0.04025, over 4875.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2297, pruned_loss=0.04622, over 971209.12 frames.], batch size: 16, lr: 5.25e-04
+2022-05-04 16:55:13,647 INFO [train.py:715] (3/8) Epoch 3, batch 26250, loss[loss=0.1977, simple_loss=0.2565, pruned_loss=0.0695, over 4849.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2298, pruned_loss=0.0462, over 970605.27 frames.], batch size: 15, lr: 5.25e-04
+2022-05-04 16:55:52,855 INFO [train.py:715] (3/8) Epoch 3, batch 26300, loss[loss=0.1447, simple_loss=0.208, pruned_loss=0.04067, over 4982.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2295, pruned_loss=0.04602, over 971427.38 frames.], batch size: 14, lr: 5.25e-04
+2022-05-04 16:56:32,818 INFO [train.py:715] (3/8) Epoch 3, batch 26350, loss[loss=0.1448, simple_loss=0.218, pruned_loss=0.03576, over 4903.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2299, pruned_loss=0.04647, over 971022.32 frames.], batch size: 22, lr: 5.24e-04
+2022-05-04 16:57:12,182 INFO [train.py:715] (3/8) Epoch 3, batch 26400, loss[loss=0.1667, simple_loss=0.2387, pruned_loss=0.04732, over 4921.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2307, pruned_loss=0.04683, over 970987.72 frames.], batch size: 23, lr: 5.24e-04
+2022-05-04 16:57:51,174 INFO [train.py:715] (3/8) Epoch 3, batch 26450, loss[loss=0.1649, simple_loss=0.2261, pruned_loss=0.05182, over 4984.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2301, pruned_loss=0.04651, over 971031.43 frames.], batch size: 25, lr: 5.24e-04
+2022-05-04 16:58:30,426 INFO [train.py:715] (3/8) Epoch 3, batch 26500, loss[loss=0.1426, simple_loss=0.2193, pruned_loss=0.03295, over 4930.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2301, pruned_loss=0.04609, over 971351.62 frames.], batch size: 21, lr: 5.24e-04
+2022-05-04 16:59:09,908 INFO [train.py:715] (3/8) Epoch 3, batch 26550, loss[loss=0.1906, simple_loss=0.2515, pruned_loss=0.06482, over 4860.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2305, pruned_loss=0.04665, over 971335.66 frames.], batch size: 30, lr: 5.24e-04
+2022-05-04 16:59:48,113 INFO [train.py:715] (3/8) Epoch 3, batch 26600, loss[loss=0.1613, simple_loss=0.2395, pruned_loss=0.04152, over 4926.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2313, pruned_loss=0.04686, over 970946.72 frames.], batch size: 29, lr: 5.24e-04
+2022-05-04 17:00:27,330 INFO [train.py:715] (3/8) Epoch 3, batch 26650, loss[loss=0.1386, simple_loss=0.2016, pruned_loss=0.0378, over 4767.00 frames.], tot_loss[loss=0.163, simple_loss=0.2315, pruned_loss=0.04728, over 970565.25 frames.], batch size: 17, lr: 5.24e-04
+2022-05-04 17:01:07,872 INFO [train.py:715] (3/8) Epoch 3, batch 26700, loss[loss=0.1766, simple_loss=0.2322, pruned_loss=0.06051, over 4870.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2313, pruned_loss=0.04767, over 971452.91 frames.], batch size: 30, lr: 5.24e-04
+2022-05-04 17:01:47,351 INFO [train.py:715] (3/8) Epoch 3, batch 26750, loss[loss=0.1704, simple_loss=0.2411, pruned_loss=0.04987, over 4988.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2319, pruned_loss=0.04774, over 971494.87 frames.], batch size: 25, lr: 5.24e-04
+2022-05-04 17:02:26,599 INFO [train.py:715] (3/8) Epoch 3, batch 26800, loss[loss=0.2005, simple_loss=0.2668, pruned_loss=0.06714, over 4896.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2318, pruned_loss=0.04776, over 971110.23 frames.], batch size: 39, lr: 5.24e-04
+2022-05-04 17:03:06,720 INFO [train.py:715] (3/8) Epoch 3, batch 26850, loss[loss=0.1378, simple_loss=0.2102, pruned_loss=0.03274, over 4808.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2309, pruned_loss=0.0474, over 971926.42 frames.], batch size: 26, lr: 5.23e-04
+2022-05-04 17:03:47,105 INFO [train.py:715] (3/8) Epoch 3, batch 26900, loss[loss=0.1477, simple_loss=0.2142, pruned_loss=0.04063, over 4797.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2302, pruned_loss=0.04735, over 972594.67 frames.], batch size: 12, lr: 5.23e-04
+2022-05-04 17:04:26,664 INFO [train.py:715] (3/8) Epoch 3, batch 26950, loss[loss=0.2036, simple_loss=0.2618, pruned_loss=0.07267, over 4971.00 frames.], tot_loss[loss=0.163, simple_loss=0.231, pruned_loss=0.04753, over 971716.58 frames.], batch size: 35, lr: 5.23e-04
+2022-05-04 17:05:05,427 INFO [train.py:715] (3/8) Epoch 3, batch 27000, loss[loss=0.1456, simple_loss=0.225, pruned_loss=0.03316, over 4973.00 frames.], tot_loss[loss=0.1627, simple_loss=0.231, pruned_loss=0.04719, over 972875.25 frames.], batch size: 24, lr: 5.23e-04
+2022-05-04 17:05:05,428 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 17:05:14,908 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1134, simple_loss=0.1995, pruned_loss=0.01366, over 914524.00 frames.
+2022-05-04 17:05:54,548 INFO [train.py:715] (3/8) Epoch 3, batch 27050, loss[loss=0.1833, simple_loss=0.2619, pruned_loss=0.05232, over 4927.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2309, pruned_loss=0.04675, over 972888.06 frames.], batch size: 18, lr: 5.23e-04
+2022-05-04 17:06:34,873 INFO [train.py:715] (3/8) Epoch 3, batch 27100, loss[loss=0.1401, simple_loss=0.2031, pruned_loss=0.03855, over 4878.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2307, pruned_loss=0.04686, over 972405.73 frames.], batch size: 22, lr: 5.23e-04
+2022-05-04 17:07:14,170 INFO [train.py:715] (3/8) Epoch 3, batch 27150, loss[loss=0.1456, simple_loss=0.2207, pruned_loss=0.03529, over 4821.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2302, pruned_loss=0.04654, over 972498.78 frames.], batch size: 25, lr: 5.23e-04
+2022-05-04 17:07:52,930 INFO [train.py:715] (3/8) Epoch 3, batch 27200, loss[loss=0.1569, simple_loss=0.2221, pruned_loss=0.04583, over 4781.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2302, pruned_loss=0.04664, over 973151.16 frames.], batch size: 17, lr: 5.23e-04
+2022-05-04 17:08:32,667 INFO [train.py:715] (3/8) Epoch 3, batch 27250, loss[loss=0.1569, simple_loss=0.2274, pruned_loss=0.04319, over 4964.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2294, pruned_loss=0.04599, over 973574.38 frames.], batch size: 15, lr: 5.23e-04
+2022-05-04 17:09:12,364 INFO [train.py:715] (3/8) Epoch 3, batch 27300, loss[loss=0.1464, simple_loss=0.218, pruned_loss=0.03742, over 4777.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2293, pruned_loss=0.04597, over 972827.84 frames.], batch size: 18, lr: 5.23e-04
+2022-05-04 17:09:51,022 INFO [train.py:715] (3/8) Epoch 3, batch 27350, loss[loss=0.1502, simple_loss=0.205, pruned_loss=0.04772, over 4862.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2295, pruned_loss=0.04614, over 972757.85 frames.], batch size: 32, lr: 5.22e-04
+2022-05-04 17:10:30,269 INFO [train.py:715] (3/8) Epoch 3, batch 27400, loss[loss=0.1601, simple_loss=0.2216, pruned_loss=0.0493, over 4966.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2304, pruned_loss=0.04659, over 973261.13 frames.], batch size: 35, lr: 5.22e-04
+2022-05-04 17:11:10,416 INFO [train.py:715] (3/8) Epoch 3, batch 27450, loss[loss=0.1835, simple_loss=0.2521, pruned_loss=0.05745, over 4829.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2295, pruned_loss=0.0461, over 973729.12 frames.], batch size: 13, lr: 5.22e-04
+2022-05-04 17:11:49,743 INFO [train.py:715] (3/8) Epoch 3, batch 27500, loss[loss=0.1557, simple_loss=0.225, pruned_loss=0.04317, over 4893.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2298, pruned_loss=0.0469, over 973009.71 frames.], batch size: 19, lr: 5.22e-04
+2022-05-04 17:12:28,640 INFO [train.py:715] (3/8) Epoch 3, batch 27550, loss[loss=0.1737, simple_loss=0.2443, pruned_loss=0.05158, over 4881.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2305, pruned_loss=0.04704, over 972792.22 frames.], batch size: 22, lr: 5.22e-04
+2022-05-04 17:13:08,353 INFO [train.py:715] (3/8) Epoch 3, batch 27600, loss[loss=0.1836, simple_loss=0.2492, pruned_loss=0.05896, over 4651.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2304, pruned_loss=0.04694, over 971566.96 frames.], batch size: 13, lr: 5.22e-04
+2022-05-04 17:13:48,000 INFO [train.py:715] (3/8) Epoch 3, batch 27650, loss[loss=0.1598, simple_loss=0.2321, pruned_loss=0.04374, over 4944.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2303, pruned_loss=0.04697, over 972003.57 frames.], batch size: 29, lr: 5.22e-04
+2022-05-04 17:14:26,623 INFO [train.py:715] (3/8) Epoch 3, batch 27700, loss[loss=0.159, simple_loss=0.2247, pruned_loss=0.04668, over 4813.00 frames.], tot_loss[loss=0.164, simple_loss=0.2322, pruned_loss=0.04791, over 972257.70 frames.], batch size: 25, lr: 5.22e-04
+2022-05-04 17:15:06,397 INFO [train.py:715] (3/8) Epoch 3, batch 27750, loss[loss=0.1663, simple_loss=0.235, pruned_loss=0.04882, over 4818.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2312, pruned_loss=0.04734, over 972067.75 frames.], batch size: 26, lr: 5.22e-04
+2022-05-04 17:15:46,350 INFO [train.py:715] (3/8) Epoch 3, batch 27800, loss[loss=0.1692, simple_loss=0.2423, pruned_loss=0.04806, over 4904.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2296, pruned_loss=0.04672, over 971679.85 frames.], batch size: 19, lr: 5.22e-04
+2022-05-04 17:16:25,743 INFO [train.py:715] (3/8) Epoch 3, batch 27850, loss[loss=0.1484, simple_loss=0.2205, pruned_loss=0.03816, over 4990.00 frames.], tot_loss[loss=0.161, simple_loss=0.2294, pruned_loss=0.04628, over 971693.76 frames.], batch size: 25, lr: 5.21e-04
+2022-05-04 17:17:04,210 INFO [train.py:715] (3/8) Epoch 3, batch 27900, loss[loss=0.1855, simple_loss=0.2545, pruned_loss=0.05831, over 4701.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2299, pruned_loss=0.04641, over 971286.98 frames.], batch size: 15, lr: 5.21e-04
+2022-05-04 17:17:43,815 INFO [train.py:715] (3/8) Epoch 3, batch 27950, loss[loss=0.1473, simple_loss=0.2216, pruned_loss=0.03644, over 4916.00 frames.], tot_loss[loss=0.162, simple_loss=0.2306, pruned_loss=0.04671, over 971171.72 frames.], batch size: 29, lr: 5.21e-04
+2022-05-04 17:18:23,715 INFO [train.py:715] (3/8) Epoch 3, batch 28000, loss[loss=0.1362, simple_loss=0.1958, pruned_loss=0.03828, over 4814.00 frames.], tot_loss[loss=0.163, simple_loss=0.2314, pruned_loss=0.04727, over 971712.56 frames.], batch size: 12, lr: 5.21e-04
+2022-05-04 17:19:02,276 INFO [train.py:715] (3/8) Epoch 3, batch 28050, loss[loss=0.1635, simple_loss=0.2415, pruned_loss=0.04276, over 4841.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2307, pruned_loss=0.04672, over 972610.08 frames.], batch size: 15, lr: 5.21e-04
+2022-05-04 17:19:41,710 INFO [train.py:715] (3/8) Epoch 3, batch 28100, loss[loss=0.1822, simple_loss=0.244, pruned_loss=0.06021, over 4973.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2304, pruned_loss=0.04663, over 972395.56 frames.], batch size: 24, lr: 5.21e-04
+2022-05-04 17:20:21,588 INFO [train.py:715] (3/8) Epoch 3, batch 28150, loss[loss=0.1795, simple_loss=0.2345, pruned_loss=0.06225, over 4914.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2305, pruned_loss=0.04699, over 972570.40 frames.], batch size: 23, lr: 5.21e-04
+2022-05-04 17:21:00,809 INFO [train.py:715] (3/8) Epoch 3, batch 28200, loss[loss=0.1825, simple_loss=0.25, pruned_loss=0.05751, over 4797.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2307, pruned_loss=0.04755, over 972273.67 frames.], batch size: 21, lr: 5.21e-04
+2022-05-04 17:21:39,658 INFO [train.py:715] (3/8) Epoch 3, batch 28250, loss[loss=0.1457, simple_loss=0.2183, pruned_loss=0.03653, over 4761.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2303, pruned_loss=0.04734, over 971886.59 frames.], batch size: 14, lr: 5.21e-04
+2022-05-04 17:22:18,998 INFO [train.py:715] (3/8) Epoch 3, batch 28300, loss[loss=0.1463, simple_loss=0.227, pruned_loss=0.03279, over 4970.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2307, pruned_loss=0.04731, over 971415.47 frames.], batch size: 28, lr: 5.21e-04
+2022-05-04 17:22:58,002 INFO [train.py:715] (3/8) Epoch 3, batch 28350, loss[loss=0.1625, simple_loss=0.2296, pruned_loss=0.0477, over 4886.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2296, pruned_loss=0.04644, over 970652.02 frames.], batch size: 22, lr: 5.21e-04
+2022-05-04 17:23:37,192 INFO [train.py:715] (3/8) Epoch 3, batch 28400, loss[loss=0.1745, simple_loss=0.2353, pruned_loss=0.05686, over 4975.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2303, pruned_loss=0.04657, over 971639.79 frames.], batch size: 25, lr: 5.20e-04
+2022-05-04 17:24:15,826 INFO [train.py:715] (3/8) Epoch 3, batch 28450, loss[loss=0.1288, simple_loss=0.2026, pruned_loss=0.02753, over 4794.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2306, pruned_loss=0.0468, over 972116.61 frames.], batch size: 24, lr: 5.20e-04
+2022-05-04 17:24:55,564 INFO [train.py:715] (3/8) Epoch 3, batch 28500, loss[loss=0.1418, simple_loss=0.2127, pruned_loss=0.03549, over 4991.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2303, pruned_loss=0.04629, over 972431.45 frames.], batch size: 28, lr: 5.20e-04
+2022-05-04 17:25:34,507 INFO [train.py:715] (3/8) Epoch 3, batch 28550, loss[loss=0.1845, simple_loss=0.2491, pruned_loss=0.05997, over 4910.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2307, pruned_loss=0.04612, over 972633.16 frames.], batch size: 17, lr: 5.20e-04
+2022-05-04 17:26:13,421 INFO [train.py:715] (3/8) Epoch 3, batch 28600, loss[loss=0.181, simple_loss=0.2488, pruned_loss=0.05663, over 4918.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2304, pruned_loss=0.04596, over 972735.26 frames.], batch size: 19, lr: 5.20e-04
+2022-05-04 17:26:53,129 INFO [train.py:715] (3/8) Epoch 3, batch 28650, loss[loss=0.1417, simple_loss=0.2161, pruned_loss=0.03367, over 4918.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2309, pruned_loss=0.04619, over 972569.81 frames.], batch size: 23, lr: 5.20e-04
+2022-05-04 17:27:33,006 INFO [train.py:715] (3/8) Epoch 3, batch 28700, loss[loss=0.1556, simple_loss=0.2385, pruned_loss=0.03641, over 4956.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2316, pruned_loss=0.04676, over 972958.17 frames.], batch size: 15, lr: 5.20e-04
+2022-05-04 17:28:12,159 INFO [train.py:715] (3/8) Epoch 3, batch 28750, loss[loss=0.1568, simple_loss=0.2287, pruned_loss=0.04245, over 4710.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2321, pruned_loss=0.04713, over 972576.43 frames.], batch size: 15, lr: 5.20e-04
+2022-05-04 17:28:52,001 INFO [train.py:715] (3/8) Epoch 3, batch 28800, loss[loss=0.1581, simple_loss=0.235, pruned_loss=0.04063, over 4928.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2328, pruned_loss=0.04737, over 973160.68 frames.], batch size: 18, lr: 5.20e-04
+2022-05-04 17:29:32,018 INFO [train.py:715] (3/8) Epoch 3, batch 28850, loss[loss=0.1466, simple_loss=0.2117, pruned_loss=0.04078, over 4972.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2326, pruned_loss=0.04713, over 974160.19 frames.], batch size: 35, lr: 5.20e-04
+2022-05-04 17:30:11,198 INFO [train.py:715] (3/8) Epoch 3, batch 28900, loss[loss=0.1326, simple_loss=0.1945, pruned_loss=0.0354, over 4822.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2312, pruned_loss=0.04672, over 974612.16 frames.], batch size: 15, lr: 5.19e-04
+2022-05-04 17:30:50,079 INFO [train.py:715] (3/8) Epoch 3, batch 28950, loss[loss=0.1533, simple_loss=0.2321, pruned_loss=0.03723, over 4900.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2309, pruned_loss=0.04674, over 974407.97 frames.], batch size: 22, lr: 5.19e-04
+2022-05-04 17:31:29,815 INFO [train.py:715] (3/8) Epoch 3, batch 29000, loss[loss=0.1595, simple_loss=0.2296, pruned_loss=0.04467, over 4887.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2297, pruned_loss=0.04601, over 974718.12 frames.], batch size: 17, lr: 5.19e-04
+2022-05-04 17:32:10,056 INFO [train.py:715] (3/8) Epoch 3, batch 29050, loss[loss=0.1375, simple_loss=0.2194, pruned_loss=0.02781, over 4837.00 frames.], tot_loss[loss=0.1609, simple_loss=0.23, pruned_loss=0.04596, over 973879.10 frames.], batch size: 15, lr: 5.19e-04
+2022-05-04 17:32:48,615 INFO [train.py:715] (3/8) Epoch 3, batch 29100, loss[loss=0.1787, simple_loss=0.243, pruned_loss=0.05714, over 4866.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2305, pruned_loss=0.04616, over 973812.18 frames.], batch size: 20, lr: 5.19e-04
+2022-05-04 17:33:28,199 INFO [train.py:715] (3/8) Epoch 3, batch 29150, loss[loss=0.1498, simple_loss=0.2203, pruned_loss=0.03968, over 4913.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2292, pruned_loss=0.04553, over 973931.95 frames.], batch size: 18, lr: 5.19e-04
+2022-05-04 17:34:08,090 INFO [train.py:715] (3/8) Epoch 3, batch 29200, loss[loss=0.1556, simple_loss=0.2328, pruned_loss=0.03915, over 4935.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2283, pruned_loss=0.04538, over 973900.70 frames.], batch size: 23, lr: 5.19e-04
+2022-05-04 17:34:47,189 INFO [train.py:715] (3/8) Epoch 3, batch 29250, loss[loss=0.1607, simple_loss=0.2335, pruned_loss=0.04395, over 4827.00 frames.], tot_loss[loss=0.159, simple_loss=0.228, pruned_loss=0.04505, over 972098.40 frames.], batch size: 27, lr: 5.19e-04
+2022-05-04 17:35:26,068 INFO [train.py:715] (3/8) Epoch 3, batch 29300, loss[loss=0.1495, simple_loss=0.2179, pruned_loss=0.04055, over 4743.00 frames.], tot_loss[loss=0.157, simple_loss=0.2261, pruned_loss=0.0439, over 971835.13 frames.], batch size: 16, lr: 5.19e-04
+2022-05-04 17:36:06,260 INFO [train.py:715] (3/8) Epoch 3, batch 29350, loss[loss=0.1424, simple_loss=0.2162, pruned_loss=0.03427, over 4968.00 frames.], tot_loss[loss=0.1568, simple_loss=0.226, pruned_loss=0.04384, over 972136.15 frames.], batch size: 24, lr: 5.19e-04
+2022-05-04 17:36:45,935 INFO [train.py:715] (3/8) Epoch 3, batch 29400, loss[loss=0.153, simple_loss=0.2224, pruned_loss=0.04181, over 4782.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2263, pruned_loss=0.04394, over 972109.95 frames.], batch size: 18, lr: 5.18e-04
+2022-05-04 17:37:24,689 INFO [train.py:715] (3/8) Epoch 3, batch 29450, loss[loss=0.1364, simple_loss=0.1963, pruned_loss=0.03823, over 4904.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2282, pruned_loss=0.0451, over 972079.00 frames.], batch size: 22, lr: 5.18e-04
+2022-05-04 17:38:03,870 INFO [train.py:715] (3/8) Epoch 3, batch 29500, loss[loss=0.1758, simple_loss=0.2435, pruned_loss=0.05408, over 4759.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2285, pruned_loss=0.04539, over 971878.13 frames.], batch size: 14, lr: 5.18e-04
+2022-05-04 17:38:43,451 INFO [train.py:715] (3/8) Epoch 3, batch 29550, loss[loss=0.1434, simple_loss=0.2175, pruned_loss=0.03468, over 4838.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2283, pruned_loss=0.04538, over 971194.07 frames.], batch size: 26, lr: 5.18e-04
+2022-05-04 17:39:22,773 INFO [train.py:715] (3/8) Epoch 3, batch 29600, loss[loss=0.151, simple_loss=0.2082, pruned_loss=0.0469, over 4733.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2291, pruned_loss=0.04582, over 970757.17 frames.], batch size: 12, lr: 5.18e-04
+2022-05-04 17:40:01,837 INFO [train.py:715] (3/8) Epoch 3, batch 29650, loss[loss=0.1472, simple_loss=0.2094, pruned_loss=0.04244, over 4784.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2297, pruned_loss=0.04593, over 971235.68 frames.], batch size: 18, lr: 5.18e-04
+2022-05-04 17:40:41,989 INFO [train.py:715] (3/8) Epoch 3, batch 29700, loss[loss=0.1316, simple_loss=0.2144, pruned_loss=0.02442, over 4811.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2298, pruned_loss=0.04604, over 971623.25 frames.], batch size: 27, lr: 5.18e-04
+2022-05-04 17:41:22,015 INFO [train.py:715] (3/8) Epoch 3, batch 29750, loss[loss=0.1784, simple_loss=0.2349, pruned_loss=0.061, over 4985.00 frames.], tot_loss[loss=0.161, simple_loss=0.2297, pruned_loss=0.04614, over 972086.21 frames.], batch size: 33, lr: 5.18e-04
+2022-05-04 17:42:00,530 INFO [train.py:715] (3/8) Epoch 3, batch 29800, loss[loss=0.1459, simple_loss=0.2251, pruned_loss=0.03335, over 4847.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2303, pruned_loss=0.04625, over 972402.86 frames.], batch size: 20, lr: 5.18e-04
+2022-05-04 17:42:40,516 INFO [train.py:715] (3/8) Epoch 3, batch 29850, loss[loss=0.1729, simple_loss=0.2295, pruned_loss=0.05817, over 4828.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2301, pruned_loss=0.0462, over 972963.51 frames.], batch size: 13, lr: 5.18e-04
+2022-05-04 17:43:20,047 INFO [train.py:715] (3/8) Epoch 3, batch 29900, loss[loss=0.1745, simple_loss=0.2439, pruned_loss=0.05258, over 4980.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2303, pruned_loss=0.04623, over 973243.16 frames.], batch size: 26, lr: 5.18e-04
+2022-05-04 17:43:58,724 INFO [train.py:715] (3/8) Epoch 3, batch 29950, loss[loss=0.1714, simple_loss=0.2322, pruned_loss=0.05524, over 4759.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2296, pruned_loss=0.04577, over 972406.45 frames.], batch size: 19, lr: 5.17e-04
+2022-05-04 17:44:37,451 INFO [train.py:715] (3/8) Epoch 3, batch 30000, loss[loss=0.1678, simple_loss=0.238, pruned_loss=0.0488, over 4965.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2298, pruned_loss=0.0457, over 972352.18 frames.], batch size: 39, lr: 5.17e-04
+2022-05-04 17:44:37,451 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 17:44:47,856 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1135, simple_loss=0.1993, pruned_loss=0.01381, over 914524.00 frames.
+2022-05-04 17:45:26,668 INFO [train.py:715] (3/8) Epoch 3, batch 30050, loss[loss=0.2551, simple_loss=0.3113, pruned_loss=0.09947, over 4928.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2299, pruned_loss=0.04587, over 971820.75 frames.], batch size: 39, lr: 5.17e-04
+2022-05-04 17:46:06,304 INFO [train.py:715] (3/8) Epoch 3, batch 30100, loss[loss=0.1699, simple_loss=0.2361, pruned_loss=0.05191, over 4924.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2296, pruned_loss=0.04587, over 971766.19 frames.], batch size: 23, lr: 5.17e-04
+2022-05-04 17:46:46,370 INFO [train.py:715] (3/8) Epoch 3, batch 30150, loss[loss=0.1922, simple_loss=0.2535, pruned_loss=0.06546, over 4863.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2299, pruned_loss=0.0464, over 971435.82 frames.], batch size: 20, lr: 5.17e-04
+2022-05-04 17:47:24,501 INFO [train.py:715] (3/8) Epoch 3, batch 30200, loss[loss=0.1765, simple_loss=0.2496, pruned_loss=0.05173, over 4774.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2301, pruned_loss=0.04647, over 971647.92 frames.], batch size: 18, lr: 5.17e-04
+2022-05-04 17:48:04,129 INFO [train.py:715] (3/8) Epoch 3, batch 30250, loss[loss=0.1438, simple_loss=0.2177, pruned_loss=0.03497, over 4864.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2289, pruned_loss=0.04578, over 973457.07 frames.], batch size: 20, lr: 5.17e-04
+2022-05-04 17:48:44,310 INFO [train.py:715] (3/8) Epoch 3, batch 30300, loss[loss=0.1896, simple_loss=0.2498, pruned_loss=0.06473, over 4929.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2302, pruned_loss=0.04629, over 972932.02 frames.], batch size: 35, lr: 5.17e-04
+2022-05-04 17:49:23,079 INFO [train.py:715] (3/8) Epoch 3, batch 30350, loss[loss=0.1456, simple_loss=0.2117, pruned_loss=0.03977, over 4790.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2292, pruned_loss=0.04592, over 973030.94 frames.], batch size: 17, lr: 5.17e-04
+2022-05-04 17:50:02,735 INFO [train.py:715] (3/8) Epoch 3, batch 30400, loss[loss=0.2056, simple_loss=0.2607, pruned_loss=0.0752, over 4917.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2294, pruned_loss=0.04636, over 972958.60 frames.], batch size: 18, lr: 5.17e-04
+2022-05-04 17:50:42,522 INFO [train.py:715] (3/8) Epoch 3, batch 30450, loss[loss=0.1332, simple_loss=0.2134, pruned_loss=0.02648, over 4774.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2298, pruned_loss=0.04675, over 973080.89 frames.], batch size: 18, lr: 5.16e-04
+2022-05-04 17:51:22,932 INFO [train.py:715] (3/8) Epoch 3, batch 30500, loss[loss=0.1491, simple_loss=0.2172, pruned_loss=0.04052, over 4645.00 frames.], tot_loss[loss=0.162, simple_loss=0.2302, pruned_loss=0.04692, over 972342.42 frames.], batch size: 13, lr: 5.16e-04
+2022-05-04 17:52:02,155 INFO [train.py:715] (3/8) Epoch 3, batch 30550, loss[loss=0.1754, simple_loss=0.2584, pruned_loss=0.04619, over 4973.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2291, pruned_loss=0.04605, over 972937.45 frames.], batch size: 24, lr: 5.16e-04
+2022-05-04 17:52:41,686 INFO [train.py:715] (3/8) Epoch 3, batch 30600, loss[loss=0.1873, simple_loss=0.243, pruned_loss=0.06575, over 4951.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2293, pruned_loss=0.04625, over 972651.64 frames.], batch size: 21, lr: 5.16e-04
+2022-05-04 17:53:21,641 INFO [train.py:715] (3/8) Epoch 3, batch 30650, loss[loss=0.1589, simple_loss=0.2333, pruned_loss=0.04226, over 4763.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2292, pruned_loss=0.04586, over 972918.19 frames.], batch size: 19, lr: 5.16e-04
+2022-05-04 17:54:00,308 INFO [train.py:715] (3/8) Epoch 3, batch 30700, loss[loss=0.1491, simple_loss=0.2193, pruned_loss=0.03941, over 4756.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2292, pruned_loss=0.04559, over 972451.50 frames.], batch size: 19, lr: 5.16e-04
+2022-05-04 17:54:39,863 INFO [train.py:715] (3/8) Epoch 3, batch 30750, loss[loss=0.1493, simple_loss=0.2263, pruned_loss=0.03619, over 4889.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2292, pruned_loss=0.04568, over 971810.55 frames.], batch size: 22, lr: 5.16e-04
+2022-05-04 17:55:19,269 INFO [train.py:715] (3/8) Epoch 3, batch 30800, loss[loss=0.1622, simple_loss=0.2444, pruned_loss=0.03997, over 4932.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2295, pruned_loss=0.04599, over 971725.03 frames.], batch size: 23, lr: 5.16e-04
+2022-05-04 17:55:59,092 INFO [train.py:715] (3/8) Epoch 3, batch 30850, loss[loss=0.1173, simple_loss=0.1912, pruned_loss=0.02167, over 4785.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2297, pruned_loss=0.04595, over 971031.49 frames.], batch size: 18, lr: 5.16e-04
+2022-05-04 17:56:37,364 INFO [train.py:715] (3/8) Epoch 3, batch 30900, loss[loss=0.1753, simple_loss=0.2406, pruned_loss=0.055, over 4931.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2292, pruned_loss=0.04552, over 971809.88 frames.], batch size: 39, lr: 5.16e-04
+2022-05-04 17:57:16,438 INFO [train.py:715] (3/8) Epoch 3, batch 30950, loss[loss=0.179, simple_loss=0.2357, pruned_loss=0.06113, over 4757.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2286, pruned_loss=0.04502, over 971271.14 frames.], batch size: 12, lr: 5.15e-04
+2022-05-04 17:57:55,759 INFO [train.py:715] (3/8) Epoch 3, batch 31000, loss[loss=0.1492, simple_loss=0.222, pruned_loss=0.03821, over 4741.00 frames.], tot_loss[loss=0.1585, simple_loss=0.228, pruned_loss=0.04444, over 970900.76 frames.], batch size: 16, lr: 5.15e-04
+2022-05-04 17:58:35,033 INFO [train.py:715] (3/8) Epoch 3, batch 31050, loss[loss=0.1517, simple_loss=0.2217, pruned_loss=0.04086, over 4800.00 frames.], tot_loss[loss=0.158, simple_loss=0.2272, pruned_loss=0.0444, over 971772.78 frames.], batch size: 25, lr: 5.15e-04
+2022-05-04 17:59:13,607 INFO [train.py:715] (3/8) Epoch 3, batch 31100, loss[loss=0.1517, simple_loss=0.2255, pruned_loss=0.03896, over 4807.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2278, pruned_loss=0.04451, over 971918.44 frames.], batch size: 21, lr: 5.15e-04
+2022-05-04 17:59:53,183 INFO [train.py:715] (3/8) Epoch 3, batch 31150, loss[loss=0.1621, simple_loss=0.2366, pruned_loss=0.04378, over 4884.00 frames.], tot_loss[loss=0.159, simple_loss=0.2285, pruned_loss=0.04474, over 972715.71 frames.], batch size: 22, lr: 5.15e-04
+2022-05-04 18:00:32,418 INFO [train.py:715] (3/8) Epoch 3, batch 31200, loss[loss=0.1483, simple_loss=0.2072, pruned_loss=0.04475, over 4826.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2283, pruned_loss=0.04492, over 972413.39 frames.], batch size: 26, lr: 5.15e-04
+2022-05-04 18:01:11,062 INFO [train.py:715] (3/8) Epoch 3, batch 31250, loss[loss=0.1841, simple_loss=0.2516, pruned_loss=0.05832, over 4984.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2288, pruned_loss=0.04528, over 973307.16 frames.], batch size: 28, lr: 5.15e-04
+2022-05-04 18:01:50,133 INFO [train.py:715] (3/8) Epoch 3, batch 31300, loss[loss=0.147, simple_loss=0.2309, pruned_loss=0.03158, over 4987.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2296, pruned_loss=0.04532, over 973044.86 frames.], batch size: 28, lr: 5.15e-04
+2022-05-04 18:02:29,482 INFO [train.py:715] (3/8) Epoch 3, batch 31350, loss[loss=0.1558, simple_loss=0.2349, pruned_loss=0.03838, over 4808.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2299, pruned_loss=0.04549, over 973382.32 frames.], batch size: 26, lr: 5.15e-04
+2022-05-04 18:03:08,646 INFO [train.py:715] (3/8) Epoch 3, batch 31400, loss[loss=0.2064, simple_loss=0.2681, pruned_loss=0.07231, over 4910.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2298, pruned_loss=0.0457, over 973095.51 frames.], batch size: 19, lr: 5.15e-04
+2022-05-04 18:03:47,230 INFO [train.py:715] (3/8) Epoch 3, batch 31450, loss[loss=0.1443, simple_loss=0.2061, pruned_loss=0.04131, over 4902.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2283, pruned_loss=0.04523, over 972575.67 frames.], batch size: 17, lr: 5.15e-04
+2022-05-04 18:04:26,975 INFO [train.py:715] (3/8) Epoch 3, batch 31500, loss[loss=0.1421, simple_loss=0.2079, pruned_loss=0.03818, over 4844.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2293, pruned_loss=0.04571, over 972745.52 frames.], batch size: 30, lr: 5.14e-04
+2022-05-04 18:05:06,852 INFO [train.py:715] (3/8) Epoch 3, batch 31550, loss[loss=0.1601, simple_loss=0.2127, pruned_loss=0.05376, over 4872.00 frames.], tot_loss[loss=0.1604, simple_loss=0.229, pruned_loss=0.04595, over 972749.34 frames.], batch size: 32, lr: 5.14e-04
+2022-05-04 18:05:47,989 INFO [train.py:715] (3/8) Epoch 3, batch 31600, loss[loss=0.1294, simple_loss=0.2008, pruned_loss=0.02902, over 4868.00 frames.], tot_loss[loss=0.1605, simple_loss=0.229, pruned_loss=0.04607, over 972153.03 frames.], batch size: 16, lr: 5.14e-04
+2022-05-04 18:06:26,994 INFO [train.py:715] (3/8) Epoch 3, batch 31650, loss[loss=0.1505, simple_loss=0.2231, pruned_loss=0.039, over 4916.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2287, pruned_loss=0.04607, over 971909.81 frames.], batch size: 19, lr: 5.14e-04
+2022-05-04 18:07:07,177 INFO [train.py:715] (3/8) Epoch 3, batch 31700, loss[loss=0.1973, simple_loss=0.2608, pruned_loss=0.06687, over 4770.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2292, pruned_loss=0.04613, over 972272.11 frames.], batch size: 17, lr: 5.14e-04
+2022-05-04 18:07:46,357 INFO [train.py:715] (3/8) Epoch 3, batch 31750, loss[loss=0.2035, simple_loss=0.2625, pruned_loss=0.07222, over 4887.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2294, pruned_loss=0.04615, over 971844.16 frames.], batch size: 16, lr: 5.14e-04
+2022-05-04 18:08:24,501 INFO [train.py:715] (3/8) Epoch 3, batch 31800, loss[loss=0.1764, simple_loss=0.2431, pruned_loss=0.05483, over 4692.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2292, pruned_loss=0.04608, over 971431.34 frames.], batch size: 15, lr: 5.14e-04
+2022-05-04 18:09:04,271 INFO [train.py:715] (3/8) Epoch 3, batch 31850, loss[loss=0.1572, simple_loss=0.2156, pruned_loss=0.04935, over 4641.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2276, pruned_loss=0.04544, over 970949.76 frames.], batch size: 13, lr: 5.14e-04
+2022-05-04 18:09:43,773 INFO [train.py:715] (3/8) Epoch 3, batch 31900, loss[loss=0.1573, simple_loss=0.2269, pruned_loss=0.04382, over 4924.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2272, pruned_loss=0.04511, over 970945.06 frames.], batch size: 18, lr: 5.14e-04
+2022-05-04 18:10:22,480 INFO [train.py:715] (3/8) Epoch 3, batch 31950, loss[loss=0.1786, simple_loss=0.2474, pruned_loss=0.05493, over 4899.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2286, pruned_loss=0.04594, over 971611.79 frames.], batch size: 18, lr: 5.14e-04
+2022-05-04 18:11:01,412 INFO [train.py:715] (3/8) Epoch 3, batch 32000, loss[loss=0.1756, simple_loss=0.2275, pruned_loss=0.06189, over 4924.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2286, pruned_loss=0.04597, over 971947.03 frames.], batch size: 18, lr: 5.14e-04
+2022-05-04 18:11:41,008 INFO [train.py:715] (3/8) Epoch 3, batch 32050, loss[loss=0.1425, simple_loss=0.2213, pruned_loss=0.03189, over 4758.00 frames.], tot_loss[loss=0.159, simple_loss=0.2281, pruned_loss=0.045, over 972342.64 frames.], batch size: 16, lr: 5.13e-04
+2022-05-04 18:12:19,207 INFO [train.py:715] (3/8) Epoch 3, batch 32100, loss[loss=0.1636, simple_loss=0.2281, pruned_loss=0.04957, over 4868.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2288, pruned_loss=0.04552, over 972537.37 frames.], batch size: 13, lr: 5.13e-04
+2022-05-04 18:12:58,311 INFO [train.py:715] (3/8) Epoch 3, batch 32150, loss[loss=0.1365, simple_loss=0.2073, pruned_loss=0.0329, over 4862.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2279, pruned_loss=0.04517, over 971157.39 frames.], batch size: 20, lr: 5.13e-04
+2022-05-04 18:13:37,852 INFO [train.py:715] (3/8) Epoch 3, batch 32200, loss[loss=0.1373, simple_loss=0.2049, pruned_loss=0.03491, over 4833.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2279, pruned_loss=0.04543, over 971239.79 frames.], batch size: 13, lr: 5.13e-04
+2022-05-04 18:14:16,673 INFO [train.py:715] (3/8) Epoch 3, batch 32250, loss[loss=0.1519, simple_loss=0.2293, pruned_loss=0.03724, over 4985.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2283, pruned_loss=0.04549, over 971466.99 frames.], batch size: 28, lr: 5.13e-04
+2022-05-04 18:14:55,236 INFO [train.py:715] (3/8) Epoch 3, batch 32300, loss[loss=0.1547, simple_loss=0.2279, pruned_loss=0.0407, over 4824.00 frames.], tot_loss[loss=0.1601, simple_loss=0.229, pruned_loss=0.04561, over 972031.75 frames.], batch size: 15, lr: 5.13e-04
+2022-05-04 18:15:34,899 INFO [train.py:715] (3/8) Epoch 3, batch 32350, loss[loss=0.1612, simple_loss=0.2343, pruned_loss=0.04406, over 4785.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2292, pruned_loss=0.04565, over 972244.90 frames.], batch size: 18, lr: 5.13e-04
+2022-05-04 18:16:14,618 INFO [train.py:715] (3/8) Epoch 3, batch 32400, loss[loss=0.1559, simple_loss=0.2325, pruned_loss=0.03969, over 4784.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2293, pruned_loss=0.04603, over 972630.32 frames.], batch size: 18, lr: 5.13e-04
+2022-05-04 18:16:52,600 INFO [train.py:715] (3/8) Epoch 3, batch 32450, loss[loss=0.1351, simple_loss=0.2167, pruned_loss=0.02678, over 4894.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2303, pruned_loss=0.04666, over 972512.33 frames.], batch size: 22, lr: 5.13e-04
+2022-05-04 18:17:32,078 INFO [train.py:715] (3/8) Epoch 3, batch 32500, loss[loss=0.1901, simple_loss=0.2571, pruned_loss=0.06156, over 4689.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2292, pruned_loss=0.04588, over 971772.70 frames.], batch size: 15, lr: 5.13e-04
+2022-05-04 18:18:11,715 INFO [train.py:715] (3/8) Epoch 3, batch 32550, loss[loss=0.167, simple_loss=0.2351, pruned_loss=0.0495, over 4815.00 frames.], tot_loss[loss=0.1603, simple_loss=0.229, pruned_loss=0.04583, over 972105.61 frames.], batch size: 26, lr: 5.12e-04
+2022-05-04 18:18:50,230 INFO [train.py:715] (3/8) Epoch 3, batch 32600, loss[loss=0.1826, simple_loss=0.252, pruned_loss=0.05665, over 4809.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2291, pruned_loss=0.04588, over 972131.96 frames.], batch size: 21, lr: 5.12e-04
+2022-05-04 18:19:29,061 INFO [train.py:715] (3/8) Epoch 3, batch 32650, loss[loss=0.1622, simple_loss=0.237, pruned_loss=0.04373, over 4927.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2293, pruned_loss=0.04587, over 972022.55 frames.], batch size: 39, lr: 5.12e-04
+2022-05-04 18:20:08,687 INFO [train.py:715] (3/8) Epoch 3, batch 32700, loss[loss=0.1452, simple_loss=0.2164, pruned_loss=0.03703, over 4762.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2294, pruned_loss=0.0456, over 972619.27 frames.], batch size: 18, lr: 5.12e-04
+2022-05-04 18:20:47,703 INFO [train.py:715] (3/8) Epoch 3, batch 32750, loss[loss=0.1554, simple_loss=0.2277, pruned_loss=0.04148, over 4800.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2288, pruned_loss=0.04532, over 973138.31 frames.], batch size: 17, lr: 5.12e-04
+2022-05-04 18:21:26,288 INFO [train.py:715] (3/8) Epoch 3, batch 32800, loss[loss=0.1767, simple_loss=0.2422, pruned_loss=0.05557, over 4871.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2286, pruned_loss=0.04518, over 973325.65 frames.], batch size: 22, lr: 5.12e-04
+2022-05-04 18:22:05,409 INFO [train.py:715] (3/8) Epoch 3, batch 32850, loss[loss=0.1506, simple_loss=0.2207, pruned_loss=0.04026, over 4755.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2294, pruned_loss=0.04577, over 972527.54 frames.], batch size: 19, lr: 5.12e-04
+2022-05-04 18:22:44,589 INFO [train.py:715] (3/8) Epoch 3, batch 32900, loss[loss=0.1275, simple_loss=0.1991, pruned_loss=0.02797, over 4683.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2288, pruned_loss=0.04556, over 972232.17 frames.], batch size: 15, lr: 5.12e-04
+2022-05-04 18:23:23,655 INFO [train.py:715] (3/8) Epoch 3, batch 32950, loss[loss=0.1651, simple_loss=0.2397, pruned_loss=0.0453, over 4828.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2283, pruned_loss=0.04501, over 971532.09 frames.], batch size: 15, lr: 5.12e-04
+2022-05-04 18:24:02,388 INFO [train.py:715] (3/8) Epoch 3, batch 33000, loss[loss=0.1633, simple_loss=0.2441, pruned_loss=0.04125, over 4840.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2284, pruned_loss=0.04521, over 971720.33 frames.], batch size: 15, lr: 5.12e-04
+2022-05-04 18:24:02,389 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 18:24:11,704 INFO [train.py:742] (3/8) Epoch 3, validation: loss=0.1131, simple_loss=0.199, pruned_loss=0.01363, over 914524.00 frames.
+2022-05-04 18:24:50,800 INFO [train.py:715] (3/8) Epoch 3, batch 33050, loss[loss=0.1502, simple_loss=0.2279, pruned_loss=0.03622, over 4945.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2282, pruned_loss=0.04525, over 971700.85 frames.], batch size: 21, lr: 5.12e-04
+2022-05-04 18:25:30,711 INFO [train.py:715] (3/8) Epoch 3, batch 33100, loss[loss=0.193, simple_loss=0.2611, pruned_loss=0.06244, over 4866.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2279, pruned_loss=0.04489, over 971915.21 frames.], batch size: 16, lr: 5.11e-04
+2022-05-04 18:26:09,587 INFO [train.py:715] (3/8) Epoch 3, batch 33150, loss[loss=0.1743, simple_loss=0.2471, pruned_loss=0.05079, over 4975.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2289, pruned_loss=0.04522, over 972735.05 frames.], batch size: 15, lr: 5.11e-04
+2022-05-04 18:26:48,262 INFO [train.py:715] (3/8) Epoch 3, batch 33200, loss[loss=0.1549, simple_loss=0.2297, pruned_loss=0.04007, over 4972.00 frames.], tot_loss[loss=0.1598, simple_loss=0.229, pruned_loss=0.04532, over 973179.43 frames.], batch size: 15, lr: 5.11e-04
+2022-05-04 18:27:28,161 INFO [train.py:715] (3/8) Epoch 3, batch 33250, loss[loss=0.133, simple_loss=0.202, pruned_loss=0.03195, over 4911.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2293, pruned_loss=0.04526, over 974002.83 frames.], batch size: 17, lr: 5.11e-04
+2022-05-04 18:28:07,720 INFO [train.py:715] (3/8) Epoch 3, batch 33300, loss[loss=0.1533, simple_loss=0.2251, pruned_loss=0.04076, over 4980.00 frames.], tot_loss[loss=0.1598, simple_loss=0.229, pruned_loss=0.04529, over 973339.15 frames.], batch size: 27, lr: 5.11e-04
+2022-05-04 18:28:46,234 INFO [train.py:715] (3/8) Epoch 3, batch 33350, loss[loss=0.1682, simple_loss=0.2421, pruned_loss=0.04716, over 4866.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2298, pruned_loss=0.0456, over 973512.69 frames.], batch size: 22, lr: 5.11e-04
+2022-05-04 18:29:25,535 INFO [train.py:715] (3/8) Epoch 3, batch 33400, loss[loss=0.1723, simple_loss=0.2354, pruned_loss=0.05458, over 4868.00 frames.], tot_loss[loss=0.1605, simple_loss=0.23, pruned_loss=0.04549, over 973235.15 frames.], batch size: 32, lr: 5.11e-04
+2022-05-04 18:30:05,188 INFO [train.py:715] (3/8) Epoch 3, batch 33450, loss[loss=0.1819, simple_loss=0.2563, pruned_loss=0.05371, over 4774.00 frames.], tot_loss[loss=0.161, simple_loss=0.2304, pruned_loss=0.04583, over 972583.78 frames.], batch size: 18, lr: 5.11e-04
+2022-05-04 18:30:44,206 INFO [train.py:715] (3/8) Epoch 3, batch 33500, loss[loss=0.1778, simple_loss=0.2492, pruned_loss=0.05322, over 4915.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2303, pruned_loss=0.04569, over 972327.73 frames.], batch size: 19, lr: 5.11e-04
+2022-05-04 18:31:23,295 INFO [train.py:715] (3/8) Epoch 3, batch 33550, loss[loss=0.2065, simple_loss=0.2642, pruned_loss=0.07437, over 4769.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2306, pruned_loss=0.04593, over 972717.58 frames.], batch size: 14, lr: 5.11e-04
+2022-05-04 18:32:03,653 INFO [train.py:715] (3/8) Epoch 3, batch 33600, loss[loss=0.1638, simple_loss=0.2412, pruned_loss=0.04323, over 4759.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2293, pruned_loss=0.04508, over 972688.55 frames.], batch size: 19, lr: 5.11e-04
+2022-05-04 18:32:43,011 INFO [train.py:715] (3/8) Epoch 3, batch 33650, loss[loss=0.1186, simple_loss=0.1896, pruned_loss=0.02382, over 4837.00 frames.], tot_loss[loss=0.1605, simple_loss=0.23, pruned_loss=0.04549, over 972321.86 frames.], batch size: 26, lr: 5.10e-04
+2022-05-04 18:33:21,657 INFO [train.py:715] (3/8) Epoch 3, batch 33700, loss[loss=0.1776, simple_loss=0.2384, pruned_loss=0.05838, over 4739.00 frames.], tot_loss[loss=0.16, simple_loss=0.2295, pruned_loss=0.04528, over 972604.57 frames.], batch size: 16, lr: 5.10e-04
+2022-05-04 18:34:01,449 INFO [train.py:715] (3/8) Epoch 3, batch 33750, loss[loss=0.1738, simple_loss=0.2426, pruned_loss=0.05245, over 4972.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2295, pruned_loss=0.04535, over 971566.20 frames.], batch size: 24, lr: 5.10e-04
+2022-05-04 18:34:40,932 INFO [train.py:715] (3/8) Epoch 3, batch 33800, loss[loss=0.1963, simple_loss=0.2579, pruned_loss=0.06739, over 4896.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2301, pruned_loss=0.04575, over 972420.35 frames.], batch size: 39, lr: 5.10e-04
+2022-05-04 18:35:19,311 INFO [train.py:715] (3/8) Epoch 3, batch 33850, loss[loss=0.1844, simple_loss=0.2546, pruned_loss=0.05706, over 4909.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2306, pruned_loss=0.04598, over 972614.85 frames.], batch size: 17, lr: 5.10e-04
+2022-05-04 18:35:58,140 INFO [train.py:715] (3/8) Epoch 3, batch 33900, loss[loss=0.1408, simple_loss=0.2099, pruned_loss=0.03579, over 4892.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2305, pruned_loss=0.04604, over 972877.66 frames.], batch size: 22, lr: 5.10e-04
+2022-05-04 18:36:38,299 INFO [train.py:715] (3/8) Epoch 3, batch 33950, loss[loss=0.1279, simple_loss=0.2033, pruned_loss=0.0262, over 4795.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2303, pruned_loss=0.0461, over 972758.83 frames.], batch size: 12, lr: 5.10e-04
+2022-05-04 18:37:17,238 INFO [train.py:715] (3/8) Epoch 3, batch 34000, loss[loss=0.1545, simple_loss=0.223, pruned_loss=0.04306, over 4735.00 frames.], tot_loss[loss=0.1609, simple_loss=0.23, pruned_loss=0.04592, over 971372.29 frames.], batch size: 16, lr: 5.10e-04
+2022-05-04 18:37:55,980 INFO [train.py:715] (3/8) Epoch 3, batch 34050, loss[loss=0.1905, simple_loss=0.251, pruned_loss=0.065, over 4869.00 frames.], tot_loss[loss=0.161, simple_loss=0.2301, pruned_loss=0.04596, over 971919.58 frames.], batch size: 22, lr: 5.10e-04
+2022-05-04 18:38:35,310 INFO [train.py:715] (3/8) Epoch 3, batch 34100, loss[loss=0.1402, simple_loss=0.2089, pruned_loss=0.03571, over 4752.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2295, pruned_loss=0.04565, over 971550.42 frames.], batch size: 19, lr: 5.10e-04
+2022-05-04 18:39:15,278 INFO [train.py:715] (3/8) Epoch 3, batch 34150, loss[loss=0.1905, simple_loss=0.2539, pruned_loss=0.06354, over 4974.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2297, pruned_loss=0.04595, over 971082.55 frames.], batch size: 24, lr: 5.10e-04
+2022-05-04 18:39:53,556 INFO [train.py:715] (3/8) Epoch 3, batch 34200, loss[loss=0.1596, simple_loss=0.2259, pruned_loss=0.04668, over 4951.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2285, pruned_loss=0.04512, over 971070.78 frames.], batch size: 29, lr: 5.09e-04
+2022-05-04 18:40:33,002 INFO [train.py:715] (3/8) Epoch 3, batch 34250, loss[loss=0.1785, simple_loss=0.2489, pruned_loss=0.05411, over 4909.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2296, pruned_loss=0.04552, over 971864.94 frames.], batch size: 17, lr: 5.09e-04
+2022-05-04 18:41:13,063 INFO [train.py:715] (3/8) Epoch 3, batch 34300, loss[loss=0.161, simple_loss=0.2177, pruned_loss=0.05218, over 4774.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2284, pruned_loss=0.04536, over 971695.61 frames.], batch size: 14, lr: 5.09e-04
+2022-05-04 18:41:52,489 INFO [train.py:715] (3/8) Epoch 3, batch 34350, loss[loss=0.1579, simple_loss=0.2334, pruned_loss=0.0412, over 4966.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2284, pruned_loss=0.04554, over 971901.76 frames.], batch size: 15, lr: 5.09e-04
+2022-05-04 18:42:31,602 INFO [train.py:715] (3/8) Epoch 3, batch 34400, loss[loss=0.1802, simple_loss=0.2595, pruned_loss=0.05047, over 4948.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2293, pruned_loss=0.04598, over 972503.80 frames.], batch size: 29, lr: 5.09e-04
+2022-05-04 18:43:11,182 INFO [train.py:715] (3/8) Epoch 3, batch 34450, loss[loss=0.1819, simple_loss=0.2386, pruned_loss=0.06259, over 4897.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2302, pruned_loss=0.04648, over 972639.98 frames.], batch size: 39, lr: 5.09e-04
+2022-05-04 18:43:51,338 INFO [train.py:715] (3/8) Epoch 3, batch 34500, loss[loss=0.1569, simple_loss=0.2244, pruned_loss=0.04475, over 4824.00 frames.], tot_loss[loss=0.1626, simple_loss=0.231, pruned_loss=0.04711, over 972896.97 frames.], batch size: 15, lr: 5.09e-04
+2022-05-04 18:44:29,764 INFO [train.py:715] (3/8) Epoch 3, batch 34550, loss[loss=0.169, simple_loss=0.2467, pruned_loss=0.04563, over 4933.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2312, pruned_loss=0.04701, over 972768.82 frames.], batch size: 23, lr: 5.09e-04
+2022-05-04 18:45:08,815 INFO [train.py:715] (3/8) Epoch 3, batch 34600, loss[loss=0.1382, simple_loss=0.2166, pruned_loss=0.02985, over 4792.00 frames.], tot_loss[loss=0.163, simple_loss=0.2318, pruned_loss=0.04709, over 972675.40 frames.], batch size: 21, lr: 5.09e-04
+2022-05-04 18:45:49,189 INFO [train.py:715] (3/8) Epoch 3, batch 34650, loss[loss=0.1746, simple_loss=0.2307, pruned_loss=0.05928, over 4977.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2315, pruned_loss=0.04746, over 972335.50 frames.], batch size: 14, lr: 5.09e-04
+2022-05-04 18:46:28,775 INFO [train.py:715] (3/8) Epoch 3, batch 34700, loss[loss=0.1691, simple_loss=0.2323, pruned_loss=0.05289, over 4873.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2317, pruned_loss=0.04763, over 972316.61 frames.], batch size: 16, lr: 5.09e-04
+2022-05-04 18:47:07,060 INFO [train.py:715] (3/8) Epoch 3, batch 34750, loss[loss=0.1421, simple_loss=0.2124, pruned_loss=0.03593, over 4929.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2312, pruned_loss=0.047, over 972649.25 frames.], batch size: 23, lr: 5.08e-04
+2022-05-04 18:47:44,746 INFO [train.py:715] (3/8) Epoch 3, batch 34800, loss[loss=0.1556, simple_loss=0.219, pruned_loss=0.04608, over 4734.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2279, pruned_loss=0.0458, over 971573.23 frames.], batch size: 12, lr: 5.08e-04
+2022-05-04 18:48:35,139 INFO [train.py:715] (3/8) Epoch 4, batch 0, loss[loss=0.1903, simple_loss=0.2584, pruned_loss=0.06111, over 4693.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2584, pruned_loss=0.06111, over 4693.00 frames.], batch size: 15, lr: 4.78e-04
+2022-05-04 18:49:16,505 INFO [train.py:715] (3/8) Epoch 4, batch 50, loss[loss=0.1275, simple_loss=0.1965, pruned_loss=0.02927, over 4746.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2287, pruned_loss=0.0474, over 218628.75 frames.], batch size: 12, lr: 4.78e-04
+2022-05-04 18:49:57,160 INFO [train.py:715] (3/8) Epoch 4, batch 100, loss[loss=0.1824, simple_loss=0.2529, pruned_loss=0.05598, over 4941.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2293, pruned_loss=0.04644, over 385687.65 frames.], batch size: 23, lr: 4.78e-04
+2022-05-04 18:50:37,983 INFO [train.py:715] (3/8) Epoch 4, batch 150, loss[loss=0.1846, simple_loss=0.2598, pruned_loss=0.05472, over 4793.00 frames.], tot_loss[loss=0.1615, simple_loss=0.23, pruned_loss=0.04649, over 516212.14 frames.], batch size: 17, lr: 4.78e-04
+2022-05-04 18:51:19,049 INFO [train.py:715] (3/8) Epoch 4, batch 200, loss[loss=0.1539, simple_loss=0.2215, pruned_loss=0.04317, over 4934.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2311, pruned_loss=0.04621, over 617571.57 frames.], batch size: 18, lr: 4.78e-04
+2022-05-04 18:52:00,239 INFO [train.py:715] (3/8) Epoch 4, batch 250, loss[loss=0.1257, simple_loss=0.2033, pruned_loss=0.02407, over 4776.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2303, pruned_loss=0.04558, over 697378.76 frames.], batch size: 18, lr: 4.77e-04
+2022-05-04 18:52:41,177 INFO [train.py:715] (3/8) Epoch 4, batch 300, loss[loss=0.1671, simple_loss=0.2251, pruned_loss=0.05459, over 4785.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2288, pruned_loss=0.0444, over 758822.75 frames.], batch size: 17, lr: 4.77e-04
+2022-05-04 18:53:22,426 INFO [train.py:715] (3/8) Epoch 4, batch 350, loss[loss=0.1674, simple_loss=0.2439, pruned_loss=0.04549, over 4821.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2284, pruned_loss=0.04406, over 805795.69 frames.], batch size: 25, lr: 4.77e-04
+2022-05-04 18:54:04,557 INFO [train.py:715] (3/8) Epoch 4, batch 400, loss[loss=0.1295, simple_loss=0.2014, pruned_loss=0.02878, over 4826.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2283, pruned_loss=0.04439, over 843317.41 frames.], batch size: 13, lr: 4.77e-04
+2022-05-04 18:54:45,179 INFO [train.py:715] (3/8) Epoch 4, batch 450, loss[loss=0.1872, simple_loss=0.261, pruned_loss=0.05666, over 4855.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2282, pruned_loss=0.04452, over 871422.00 frames.], batch size: 38, lr: 4.77e-04
+2022-05-04 18:55:26,265 INFO [train.py:715] (3/8) Epoch 4, batch 500, loss[loss=0.1288, simple_loss=0.2068, pruned_loss=0.02541, over 4805.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2285, pruned_loss=0.04489, over 893690.78 frames.], batch size: 26, lr: 4.77e-04
+2022-05-04 18:56:07,507 INFO [train.py:715] (3/8) Epoch 4, batch 550, loss[loss=0.1563, simple_loss=0.2336, pruned_loss=0.03953, over 4932.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2285, pruned_loss=0.04441, over 910450.31 frames.], batch size: 29, lr: 4.77e-04
+2022-05-04 18:56:48,416 INFO [train.py:715] (3/8) Epoch 4, batch 600, loss[loss=0.1376, simple_loss=0.2077, pruned_loss=0.03381, over 4875.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2283, pruned_loss=0.04433, over 924546.91 frames.], batch size: 16, lr: 4.77e-04
+2022-05-04 18:57:28,919 INFO [train.py:715] (3/8) Epoch 4, batch 650, loss[loss=0.1255, simple_loss=0.2093, pruned_loss=0.02085, over 4964.00 frames.], tot_loss[loss=0.159, simple_loss=0.2288, pruned_loss=0.04458, over 935768.86 frames.], batch size: 24, lr: 4.77e-04
+2022-05-04 18:58:10,000 INFO [train.py:715] (3/8) Epoch 4, batch 700, loss[loss=0.1613, simple_loss=0.2283, pruned_loss=0.04714, over 4758.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2291, pruned_loss=0.04485, over 944081.87 frames.], batch size: 16, lr: 4.77e-04
+2022-05-04 18:58:51,943 INFO [train.py:715] (3/8) Epoch 4, batch 750, loss[loss=0.1579, simple_loss=0.22, pruned_loss=0.04785, over 4783.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2286, pruned_loss=0.04447, over 950063.13 frames.], batch size: 17, lr: 4.77e-04
+2022-05-04 18:59:33,007 INFO [train.py:715] (3/8) Epoch 4, batch 800, loss[loss=0.2208, simple_loss=0.2921, pruned_loss=0.07471, over 4977.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2288, pruned_loss=0.04476, over 955588.25 frames.], batch size: 40, lr: 4.77e-04
+2022-05-04 19:00:13,433 INFO [train.py:715] (3/8) Epoch 4, batch 850, loss[loss=0.1371, simple_loss=0.2153, pruned_loss=0.02948, over 4866.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2285, pruned_loss=0.04472, over 958512.42 frames.], batch size: 16, lr: 4.76e-04
+2022-05-04 19:00:54,507 INFO [train.py:715] (3/8) Epoch 4, batch 900, loss[loss=0.1415, simple_loss=0.2161, pruned_loss=0.03342, over 4907.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2293, pruned_loss=0.04495, over 961863.80 frames.], batch size: 18, lr: 4.76e-04
+2022-05-04 19:01:35,347 INFO [train.py:715] (3/8) Epoch 4, batch 950, loss[loss=0.1593, simple_loss=0.2245, pruned_loss=0.04705, over 4788.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2288, pruned_loss=0.045, over 964122.01 frames.], batch size: 17, lr: 4.76e-04
+2022-05-04 19:02:16,229 INFO [train.py:715] (3/8) Epoch 4, batch 1000, loss[loss=0.1373, simple_loss=0.2056, pruned_loss=0.0345, over 4790.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2272, pruned_loss=0.04446, over 965462.39 frames.], batch size: 12, lr: 4.76e-04
+2022-05-04 19:02:56,938 INFO [train.py:715] (3/8) Epoch 4, batch 1050, loss[loss=0.1803, simple_loss=0.2552, pruned_loss=0.05264, over 4844.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2278, pruned_loss=0.04507, over 966293.57 frames.], batch size: 15, lr: 4.76e-04
+2022-05-04 19:03:38,130 INFO [train.py:715] (3/8) Epoch 4, batch 1100, loss[loss=0.131, simple_loss=0.1997, pruned_loss=0.03116, over 4978.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2283, pruned_loss=0.04536, over 966973.44 frames.], batch size: 14, lr: 4.76e-04
+2022-05-04 19:04:18,531 INFO [train.py:715] (3/8) Epoch 4, batch 1150, loss[loss=0.1858, simple_loss=0.2372, pruned_loss=0.06718, over 4816.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2287, pruned_loss=0.04573, over 967491.97 frames.], batch size: 26, lr: 4.76e-04
+2022-05-04 19:04:58,028 INFO [train.py:715] (3/8) Epoch 4, batch 1200, loss[loss=0.1784, simple_loss=0.2482, pruned_loss=0.05431, over 4884.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2279, pruned_loss=0.04529, over 969230.24 frames.], batch size: 16, lr: 4.76e-04
+2022-05-04 19:05:38,585 INFO [train.py:715] (3/8) Epoch 4, batch 1250, loss[loss=0.1627, simple_loss=0.2459, pruned_loss=0.0397, over 4713.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2279, pruned_loss=0.04521, over 970062.39 frames.], batch size: 15, lr: 4.76e-04
+2022-05-04 19:06:19,649 INFO [train.py:715] (3/8) Epoch 4, batch 1300, loss[loss=0.1714, simple_loss=0.25, pruned_loss=0.04641, over 4932.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2278, pruned_loss=0.04528, over 970308.83 frames.], batch size: 35, lr: 4.76e-04
+2022-05-04 19:06:59,662 INFO [train.py:715] (3/8) Epoch 4, batch 1350, loss[loss=0.2119, simple_loss=0.2828, pruned_loss=0.07047, over 4915.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2281, pruned_loss=0.04523, over 971129.82 frames.], batch size: 39, lr: 4.76e-04
+2022-05-04 19:07:40,377 INFO [train.py:715] (3/8) Epoch 4, batch 1400, loss[loss=0.1477, simple_loss=0.2181, pruned_loss=0.03868, over 4986.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2281, pruned_loss=0.04525, over 971516.90 frames.], batch size: 15, lr: 4.76e-04
+2022-05-04 19:08:21,352 INFO [train.py:715] (3/8) Epoch 4, batch 1450, loss[loss=0.1601, simple_loss=0.2169, pruned_loss=0.05165, over 4961.00 frames.], tot_loss[loss=0.159, simple_loss=0.2279, pruned_loss=0.04504, over 972679.31 frames.], batch size: 21, lr: 4.75e-04
+2022-05-04 19:09:02,419 INFO [train.py:715] (3/8) Epoch 4, batch 1500, loss[loss=0.1647, simple_loss=0.2378, pruned_loss=0.04582, over 4881.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04402, over 973287.22 frames.], batch size: 16, lr: 4.75e-04
+2022-05-04 19:09:42,047 INFO [train.py:715] (3/8) Epoch 4, batch 1550, loss[loss=0.1488, simple_loss=0.2107, pruned_loss=0.04351, over 4821.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2282, pruned_loss=0.04461, over 973008.67 frames.], batch size: 15, lr: 4.75e-04
+2022-05-04 19:10:23,010 INFO [train.py:715] (3/8) Epoch 4, batch 1600, loss[loss=0.1603, simple_loss=0.2364, pruned_loss=0.04214, over 4764.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2274, pruned_loss=0.04446, over 972501.65 frames.], batch size: 16, lr: 4.75e-04
+2022-05-04 19:11:04,739 INFO [train.py:715] (3/8) Epoch 4, batch 1650, loss[loss=0.2, simple_loss=0.2464, pruned_loss=0.07682, over 4929.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2277, pruned_loss=0.0447, over 973170.43 frames.], batch size: 18, lr: 4.75e-04
+2022-05-04 19:11:45,100 INFO [train.py:715] (3/8) Epoch 4, batch 1700, loss[loss=0.1663, simple_loss=0.2332, pruned_loss=0.04971, over 4834.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2288, pruned_loss=0.04547, over 971955.16 frames.], batch size: 30, lr: 4.75e-04
+2022-05-04 19:12:25,114 INFO [train.py:715] (3/8) Epoch 4, batch 1750, loss[loss=0.1467, simple_loss=0.2123, pruned_loss=0.04053, over 4986.00 frames.], tot_loss[loss=0.1589, simple_loss=0.228, pruned_loss=0.04488, over 972378.65 frames.], batch size: 26, lr: 4.75e-04
+2022-05-04 19:13:06,318 INFO [train.py:715] (3/8) Epoch 4, batch 1800, loss[loss=0.1326, simple_loss=0.2031, pruned_loss=0.03108, over 4866.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2276, pruned_loss=0.04463, over 973053.94 frames.], batch size: 20, lr: 4.75e-04
+2022-05-04 19:13:47,663 INFO [train.py:715] (3/8) Epoch 4, batch 1850, loss[loss=0.1556, simple_loss=0.231, pruned_loss=0.04012, over 4840.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2274, pruned_loss=0.04487, over 972394.44 frames.], batch size: 15, lr: 4.75e-04
+2022-05-04 19:14:27,700 INFO [train.py:715] (3/8) Epoch 4, batch 1900, loss[loss=0.1534, simple_loss=0.2104, pruned_loss=0.04815, over 4776.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2269, pruned_loss=0.04473, over 972359.39 frames.], batch size: 14, lr: 4.75e-04
+2022-05-04 19:15:08,453 INFO [train.py:715] (3/8) Epoch 4, batch 1950, loss[loss=0.159, simple_loss=0.2311, pruned_loss=0.04347, over 4897.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2268, pruned_loss=0.04476, over 972720.01 frames.], batch size: 19, lr: 4.75e-04
+2022-05-04 19:15:48,966 INFO [train.py:715] (3/8) Epoch 4, batch 2000, loss[loss=0.1585, simple_loss=0.2212, pruned_loss=0.04788, over 4946.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2276, pruned_loss=0.04497, over 972524.31 frames.], batch size: 21, lr: 4.74e-04
+2022-05-04 19:16:28,965 INFO [train.py:715] (3/8) Epoch 4, batch 2050, loss[loss=0.1407, simple_loss=0.2003, pruned_loss=0.04058, over 4805.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2275, pruned_loss=0.04489, over 972711.42 frames.], batch size: 13, lr: 4.74e-04
+2022-05-04 19:17:08,513 INFO [train.py:715] (3/8) Epoch 4, batch 2100, loss[loss=0.2175, simple_loss=0.275, pruned_loss=0.08, over 4832.00 frames.], tot_loss[loss=0.158, simple_loss=0.2269, pruned_loss=0.04462, over 972631.80 frames.], batch size: 30, lr: 4.74e-04
+2022-05-04 19:17:48,265 INFO [train.py:715] (3/8) Epoch 4, batch 2150, loss[loss=0.1492, simple_loss=0.2193, pruned_loss=0.03951, over 4853.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2272, pruned_loss=0.04465, over 972158.53 frames.], batch size: 20, lr: 4.74e-04
+2022-05-04 19:18:29,061 INFO [train.py:715] (3/8) Epoch 4, batch 2200, loss[loss=0.1657, simple_loss=0.2205, pruned_loss=0.05548, over 4894.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2276, pruned_loss=0.04479, over 971796.94 frames.], batch size: 17, lr: 4.74e-04
+2022-05-04 19:19:09,439 INFO [train.py:715] (3/8) Epoch 4, batch 2250, loss[loss=0.1632, simple_loss=0.2313, pruned_loss=0.0475, over 4961.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2286, pruned_loss=0.04508, over 972425.19 frames.], batch size: 35, lr: 4.74e-04
+2022-05-04 19:19:48,815 INFO [train.py:715] (3/8) Epoch 4, batch 2300, loss[loss=0.1534, simple_loss=0.2235, pruned_loss=0.04162, over 4738.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2281, pruned_loss=0.04481, over 972770.56 frames.], batch size: 16, lr: 4.74e-04
+2022-05-04 19:20:28,744 INFO [train.py:715] (3/8) Epoch 4, batch 2350, loss[loss=0.1465, simple_loss=0.2256, pruned_loss=0.03375, over 4939.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2281, pruned_loss=0.0447, over 972862.79 frames.], batch size: 21, lr: 4.74e-04
+2022-05-04 19:21:08,832 INFO [train.py:715] (3/8) Epoch 4, batch 2400, loss[loss=0.1484, simple_loss=0.2228, pruned_loss=0.03696, over 4822.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2265, pruned_loss=0.04348, over 972968.39 frames.], batch size: 25, lr: 4.74e-04
+2022-05-04 19:21:48,323 INFO [train.py:715] (3/8) Epoch 4, batch 2450, loss[loss=0.1716, simple_loss=0.2364, pruned_loss=0.05344, over 4804.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2266, pruned_loss=0.04343, over 972448.50 frames.], batch size: 21, lr: 4.74e-04
+2022-05-04 19:22:28,658 INFO [train.py:715] (3/8) Epoch 4, batch 2500, loss[loss=0.1913, simple_loss=0.2521, pruned_loss=0.06521, over 4842.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2266, pruned_loss=0.04337, over 973396.07 frames.], batch size: 15, lr: 4.74e-04
+2022-05-04 19:23:09,573 INFO [train.py:715] (3/8) Epoch 4, batch 2550, loss[loss=0.1818, simple_loss=0.2483, pruned_loss=0.05762, over 4932.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2269, pruned_loss=0.0433, over 973020.49 frames.], batch size: 35, lr: 4.74e-04
+2022-05-04 19:23:49,881 INFO [train.py:715] (3/8) Epoch 4, batch 2600, loss[loss=0.1595, simple_loss=0.2175, pruned_loss=0.05076, over 4956.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2273, pruned_loss=0.04383, over 972471.81 frames.], batch size: 24, lr: 4.73e-04
+2022-05-04 19:24:29,133 INFO [train.py:715] (3/8) Epoch 4, batch 2650, loss[loss=0.1603, simple_loss=0.2338, pruned_loss=0.0434, over 4916.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2275, pruned_loss=0.04418, over 972359.03 frames.], batch size: 22, lr: 4.73e-04
+2022-05-04 19:25:09,500 INFO [train.py:715] (3/8) Epoch 4, batch 2700, loss[loss=0.1436, simple_loss=0.2107, pruned_loss=0.0383, over 4754.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2266, pruned_loss=0.04377, over 973271.62 frames.], batch size: 16, lr: 4.73e-04
+2022-05-04 19:25:49,762 INFO [train.py:715] (3/8) Epoch 4, batch 2750, loss[loss=0.1522, simple_loss=0.2153, pruned_loss=0.04457, over 4931.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04388, over 972786.77 frames.], batch size: 18, lr: 4.73e-04
+2022-05-04 19:26:29,539 INFO [train.py:715] (3/8) Epoch 4, batch 2800, loss[loss=0.1679, simple_loss=0.2447, pruned_loss=0.04559, over 4849.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2274, pruned_loss=0.04394, over 972252.22 frames.], batch size: 32, lr: 4.73e-04
+2022-05-04 19:27:08,933 INFO [train.py:715] (3/8) Epoch 4, batch 2850, loss[loss=0.1497, simple_loss=0.2159, pruned_loss=0.0417, over 4794.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2271, pruned_loss=0.04398, over 972368.71 frames.], batch size: 24, lr: 4.73e-04
+2022-05-04 19:27:49,244 INFO [train.py:715] (3/8) Epoch 4, batch 2900, loss[loss=0.1667, simple_loss=0.2327, pruned_loss=0.05036, over 4749.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2269, pruned_loss=0.04382, over 971475.67 frames.], batch size: 16, lr: 4.73e-04
+2022-05-04 19:28:29,131 INFO [train.py:715] (3/8) Epoch 4, batch 2950, loss[loss=0.1601, simple_loss=0.2278, pruned_loss=0.04626, over 4780.00 frames.], tot_loss[loss=0.157, simple_loss=0.2264, pruned_loss=0.04375, over 972452.23 frames.], batch size: 18, lr: 4.73e-04
+2022-05-04 19:29:08,447 INFO [train.py:715] (3/8) Epoch 4, batch 3000, loss[loss=0.152, simple_loss=0.2315, pruned_loss=0.03623, over 4955.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2265, pruned_loss=0.04354, over 973175.48 frames.], batch size: 15, lr: 4.73e-04
+2022-05-04 19:29:08,448 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 19:29:17,943 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1127, simple_loss=0.1984, pruned_loss=0.01346, over 914524.00 frames.
+2022-05-04 19:29:57,095 INFO [train.py:715] (3/8) Epoch 4, batch 3050, loss[loss=0.132, simple_loss=0.2, pruned_loss=0.03201, over 4638.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2263, pruned_loss=0.04355, over 972697.70 frames.], batch size: 13, lr: 4.73e-04
+2022-05-04 19:30:37,135 INFO [train.py:715] (3/8) Epoch 4, batch 3100, loss[loss=0.1205, simple_loss=0.2013, pruned_loss=0.01982, over 4838.00 frames.], tot_loss[loss=0.158, simple_loss=0.2275, pruned_loss=0.04425, over 972502.25 frames.], batch size: 15, lr: 4.73e-04
+2022-05-04 19:31:17,410 INFO [train.py:715] (3/8) Epoch 4, batch 3150, loss[loss=0.1556, simple_loss=0.223, pruned_loss=0.04414, over 4780.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2289, pruned_loss=0.04491, over 972326.10 frames.], batch size: 18, lr: 4.73e-04
+2022-05-04 19:31:57,022 INFO [train.py:715] (3/8) Epoch 4, batch 3200, loss[loss=0.1524, simple_loss=0.2254, pruned_loss=0.03975, over 4784.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2287, pruned_loss=0.04483, over 971916.50 frames.], batch size: 17, lr: 4.72e-04
+2022-05-04 19:32:36,973 INFO [train.py:715] (3/8) Epoch 4, batch 3250, loss[loss=0.1491, simple_loss=0.2154, pruned_loss=0.04134, over 4834.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2294, pruned_loss=0.04581, over 971641.39 frames.], batch size: 15, lr: 4.72e-04
+2022-05-04 19:33:16,911 INFO [train.py:715] (3/8) Epoch 4, batch 3300, loss[loss=0.1439, simple_loss=0.2131, pruned_loss=0.03737, over 4757.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2289, pruned_loss=0.04527, over 971997.41 frames.], batch size: 19, lr: 4.72e-04
+2022-05-04 19:33:56,288 INFO [train.py:715] (3/8) Epoch 4, batch 3350, loss[loss=0.1467, simple_loss=0.2247, pruned_loss=0.03435, over 4723.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2282, pruned_loss=0.04457, over 971640.37 frames.], batch size: 15, lr: 4.72e-04
+2022-05-04 19:34:35,328 INFO [train.py:715] (3/8) Epoch 4, batch 3400, loss[loss=0.1916, simple_loss=0.266, pruned_loss=0.05859, over 4869.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2298, pruned_loss=0.04586, over 972051.89 frames.], batch size: 16, lr: 4.72e-04
+2022-05-04 19:35:15,775 INFO [train.py:715] (3/8) Epoch 4, batch 3450, loss[loss=0.1802, simple_loss=0.2525, pruned_loss=0.05398, over 4946.00 frames.], tot_loss[loss=0.16, simple_loss=0.2294, pruned_loss=0.04534, over 972334.14 frames.], batch size: 35, lr: 4.72e-04
+2022-05-04 19:35:55,189 INFO [train.py:715] (3/8) Epoch 4, batch 3500, loss[loss=0.1356, simple_loss=0.2066, pruned_loss=0.03235, over 4907.00 frames.], tot_loss[loss=0.1598, simple_loss=0.229, pruned_loss=0.04527, over 972321.87 frames.], batch size: 17, lr: 4.72e-04
+2022-05-04 19:36:34,857 INFO [train.py:715] (3/8) Epoch 4, batch 3550, loss[loss=0.1604, simple_loss=0.2353, pruned_loss=0.04277, over 4946.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2288, pruned_loss=0.04508, over 971634.17 frames.], batch size: 35, lr: 4.72e-04
+2022-05-04 19:37:14,696 INFO [train.py:715] (3/8) Epoch 4, batch 3600, loss[loss=0.1502, simple_loss=0.2281, pruned_loss=0.03619, over 4933.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2287, pruned_loss=0.0452, over 972562.95 frames.], batch size: 23, lr: 4.72e-04
+2022-05-04 19:37:54,697 INFO [train.py:715] (3/8) Epoch 4, batch 3650, loss[loss=0.1353, simple_loss=0.2068, pruned_loss=0.03188, over 4924.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2283, pruned_loss=0.0451, over 972711.79 frames.], batch size: 39, lr: 4.72e-04
+2022-05-04 19:38:34,067 INFO [train.py:715] (3/8) Epoch 4, batch 3700, loss[loss=0.1558, simple_loss=0.2206, pruned_loss=0.04555, over 4841.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2286, pruned_loss=0.04492, over 972534.55 frames.], batch size: 12, lr: 4.72e-04
+2022-05-04 19:39:13,348 INFO [train.py:715] (3/8) Epoch 4, batch 3750, loss[loss=0.1517, simple_loss=0.2287, pruned_loss=0.03733, over 4928.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2279, pruned_loss=0.04473, over 972284.14 frames.], batch size: 29, lr: 4.72e-04
+2022-05-04 19:39:53,216 INFO [train.py:715] (3/8) Epoch 4, batch 3800, loss[loss=0.1439, simple_loss=0.2119, pruned_loss=0.03799, over 4971.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2275, pruned_loss=0.04482, over 972472.68 frames.], batch size: 15, lr: 4.72e-04
+2022-05-04 19:40:32,932 INFO [train.py:715] (3/8) Epoch 4, batch 3850, loss[loss=0.1562, simple_loss=0.2285, pruned_loss=0.04196, over 4776.00 frames.], tot_loss[loss=0.159, simple_loss=0.2279, pruned_loss=0.04504, over 971859.73 frames.], batch size: 18, lr: 4.71e-04
+2022-05-04 19:41:13,118 INFO [train.py:715] (3/8) Epoch 4, batch 3900, loss[loss=0.1687, simple_loss=0.2449, pruned_loss=0.04626, over 4846.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2289, pruned_loss=0.04545, over 971634.30 frames.], batch size: 32, lr: 4.71e-04
+2022-05-04 19:41:53,256 INFO [train.py:715] (3/8) Epoch 4, batch 3950, loss[loss=0.1524, simple_loss=0.2118, pruned_loss=0.04652, over 4933.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2291, pruned_loss=0.04562, over 971155.58 frames.], batch size: 23, lr: 4.71e-04
+2022-05-04 19:42:33,630 INFO [train.py:715] (3/8) Epoch 4, batch 4000, loss[loss=0.1919, simple_loss=0.2732, pruned_loss=0.05531, over 4779.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2292, pruned_loss=0.04555, over 970997.67 frames.], batch size: 18, lr: 4.71e-04
+2022-05-04 19:43:13,663 INFO [train.py:715] (3/8) Epoch 4, batch 4050, loss[loss=0.1651, simple_loss=0.2298, pruned_loss=0.05024, over 4986.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2289, pruned_loss=0.04544, over 970960.85 frames.], batch size: 14, lr: 4.71e-04
+2022-05-04 19:43:53,239 INFO [train.py:715] (3/8) Epoch 4, batch 4100, loss[loss=0.1741, simple_loss=0.2398, pruned_loss=0.05422, over 4783.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2294, pruned_loss=0.04555, over 970555.74 frames.], batch size: 14, lr: 4.71e-04
+2022-05-04 19:44:33,947 INFO [train.py:715] (3/8) Epoch 4, batch 4150, loss[loss=0.1459, simple_loss=0.2164, pruned_loss=0.03773, over 4983.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2298, pruned_loss=0.04586, over 970436.94 frames.], batch size: 28, lr: 4.71e-04
+2022-05-04 19:45:13,437 INFO [train.py:715] (3/8) Epoch 4, batch 4200, loss[loss=0.1547, simple_loss=0.2253, pruned_loss=0.04203, over 4978.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2299, pruned_loss=0.04592, over 971104.95 frames.], batch size: 25, lr: 4.71e-04
+2022-05-04 19:45:52,910 INFO [train.py:715] (3/8) Epoch 4, batch 4250, loss[loss=0.1679, simple_loss=0.2288, pruned_loss=0.05357, over 4990.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2302, pruned_loss=0.04638, over 972676.88 frames.], batch size: 28, lr: 4.71e-04
+2022-05-04 19:46:33,011 INFO [train.py:715] (3/8) Epoch 4, batch 4300, loss[loss=0.1718, simple_loss=0.2453, pruned_loss=0.04914, over 4700.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2294, pruned_loss=0.04551, over 973982.90 frames.], batch size: 15, lr: 4.71e-04
+2022-05-04 19:47:13,033 INFO [train.py:715] (3/8) Epoch 4, batch 4350, loss[loss=0.1757, simple_loss=0.2453, pruned_loss=0.05308, over 4902.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2288, pruned_loss=0.04535, over 973595.86 frames.], batch size: 19, lr: 4.71e-04
+2022-05-04 19:47:52,119 INFO [train.py:715] (3/8) Epoch 4, batch 4400, loss[loss=0.1495, simple_loss=0.2369, pruned_loss=0.03104, over 4971.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2287, pruned_loss=0.04494, over 973862.64 frames.], batch size: 24, lr: 4.71e-04
+2022-05-04 19:48:31,826 INFO [train.py:715] (3/8) Epoch 4, batch 4450, loss[loss=0.159, simple_loss=0.221, pruned_loss=0.04851, over 4924.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2274, pruned_loss=0.04383, over 972923.26 frames.], batch size: 23, lr: 4.70e-04
+2022-05-04 19:49:12,000 INFO [train.py:715] (3/8) Epoch 4, batch 4500, loss[loss=0.1776, simple_loss=0.2475, pruned_loss=0.05386, over 4916.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2279, pruned_loss=0.04445, over 972640.60 frames.], batch size: 18, lr: 4.70e-04
+2022-05-04 19:49:51,278 INFO [train.py:715] (3/8) Epoch 4, batch 4550, loss[loss=0.1764, simple_loss=0.242, pruned_loss=0.05537, over 4980.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2264, pruned_loss=0.04349, over 971969.11 frames.], batch size: 39, lr: 4.70e-04
+2022-05-04 19:50:30,673 INFO [train.py:715] (3/8) Epoch 4, batch 4600, loss[loss=0.1775, simple_loss=0.2477, pruned_loss=0.05369, over 4946.00 frames.], tot_loss[loss=0.1574, simple_loss=0.227, pruned_loss=0.04389, over 971428.54 frames.], batch size: 23, lr: 4.70e-04
+2022-05-04 19:51:10,987 INFO [train.py:715] (3/8) Epoch 4, batch 4650, loss[loss=0.1804, simple_loss=0.2322, pruned_loss=0.06428, over 4774.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2274, pruned_loss=0.04445, over 971904.26 frames.], batch size: 14, lr: 4.70e-04
+2022-05-04 19:51:51,340 INFO [train.py:715] (3/8) Epoch 4, batch 4700, loss[loss=0.1609, simple_loss=0.2342, pruned_loss=0.04377, over 4816.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2267, pruned_loss=0.04409, over 971982.67 frames.], batch size: 25, lr: 4.70e-04
+2022-05-04 19:52:31,248 INFO [train.py:715] (3/8) Epoch 4, batch 4750, loss[loss=0.1879, simple_loss=0.2494, pruned_loss=0.06318, over 4753.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2261, pruned_loss=0.04387, over 971335.27 frames.], batch size: 16, lr: 4.70e-04
+2022-05-04 19:53:13,034 INFO [train.py:715] (3/8) Epoch 4, batch 4800, loss[loss=0.1275, simple_loss=0.203, pruned_loss=0.02602, over 4975.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2261, pruned_loss=0.04385, over 972430.05 frames.], batch size: 28, lr: 4.70e-04
+2022-05-04 19:53:53,555 INFO [train.py:715] (3/8) Epoch 4, batch 4850, loss[loss=0.1634, simple_loss=0.228, pruned_loss=0.04937, over 4776.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2264, pruned_loss=0.04415, over 972726.02 frames.], batch size: 19, lr: 4.70e-04
+2022-05-04 19:54:32,958 INFO [train.py:715] (3/8) Epoch 4, batch 4900, loss[loss=0.185, simple_loss=0.2629, pruned_loss=0.05358, over 4805.00 frames.], tot_loss[loss=0.1571, simple_loss=0.226, pruned_loss=0.04414, over 972344.88 frames.], batch size: 25, lr: 4.70e-04
+2022-05-04 19:55:12,347 INFO [train.py:715] (3/8) Epoch 4, batch 4950, loss[loss=0.1295, simple_loss=0.214, pruned_loss=0.0225, over 4917.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2269, pruned_loss=0.04413, over 972756.55 frames.], batch size: 23, lr: 4.70e-04
+2022-05-04 19:55:52,409 INFO [train.py:715] (3/8) Epoch 4, batch 5000, loss[loss=0.1692, simple_loss=0.2298, pruned_loss=0.05433, over 4795.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2277, pruned_loss=0.04486, over 972774.38 frames.], batch size: 14, lr: 4.70e-04
+2022-05-04 19:56:32,439 INFO [train.py:715] (3/8) Epoch 4, batch 5050, loss[loss=0.1786, simple_loss=0.2432, pruned_loss=0.05694, over 4954.00 frames.], tot_loss[loss=0.1591, simple_loss=0.228, pruned_loss=0.04509, over 972278.93 frames.], batch size: 39, lr: 4.69e-04
+2022-05-04 19:57:12,347 INFO [train.py:715] (3/8) Epoch 4, batch 5100, loss[loss=0.1693, simple_loss=0.2346, pruned_loss=0.05195, over 4978.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2278, pruned_loss=0.04491, over 972237.99 frames.], batch size: 26, lr: 4.69e-04
+2022-05-04 19:57:51,517 INFO [train.py:715] (3/8) Epoch 4, batch 5150, loss[loss=0.1424, simple_loss=0.2129, pruned_loss=0.03591, over 4915.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2281, pruned_loss=0.04498, over 972473.02 frames.], batch size: 17, lr: 4.69e-04
+2022-05-04 19:58:31,724 INFO [train.py:715] (3/8) Epoch 4, batch 5200, loss[loss=0.1634, simple_loss=0.2378, pruned_loss=0.0445, over 4800.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2279, pruned_loss=0.04528, over 972811.15 frames.], batch size: 21, lr: 4.69e-04
+2022-05-04 19:59:11,084 INFO [train.py:715] (3/8) Epoch 4, batch 5250, loss[loss=0.1798, simple_loss=0.2306, pruned_loss=0.06454, over 4764.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2284, pruned_loss=0.04529, over 971730.59 frames.], batch size: 19, lr: 4.69e-04
+2022-05-04 19:59:50,709 INFO [train.py:715] (3/8) Epoch 4, batch 5300, loss[loss=0.1364, simple_loss=0.2128, pruned_loss=0.02994, over 4988.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2274, pruned_loss=0.04452, over 971865.34 frames.], batch size: 26, lr: 4.69e-04
+2022-05-04 20:00:30,977 INFO [train.py:715] (3/8) Epoch 4, batch 5350, loss[loss=0.1327, simple_loss=0.1985, pruned_loss=0.03344, over 4809.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2274, pruned_loss=0.04465, over 971786.63 frames.], batch size: 12, lr: 4.69e-04
+2022-05-04 20:01:11,128 INFO [train.py:715] (3/8) Epoch 4, batch 5400, loss[loss=0.175, simple_loss=0.2376, pruned_loss=0.05623, over 4974.00 frames.], tot_loss[loss=0.1588, simple_loss=0.228, pruned_loss=0.04481, over 972190.90 frames.], batch size: 31, lr: 4.69e-04
+2022-05-04 20:01:51,433 INFO [train.py:715] (3/8) Epoch 4, batch 5450, loss[loss=0.1259, simple_loss=0.1885, pruned_loss=0.03166, over 4965.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2274, pruned_loss=0.04441, over 972617.06 frames.], batch size: 14, lr: 4.69e-04
+2022-05-04 20:02:30,839 INFO [train.py:715] (3/8) Epoch 4, batch 5500, loss[loss=0.1436, simple_loss=0.2259, pruned_loss=0.03071, over 4945.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2273, pruned_loss=0.04424, over 972494.63 frames.], batch size: 21, lr: 4.69e-04
+2022-05-04 20:03:11,383 INFO [train.py:715] (3/8) Epoch 4, batch 5550, loss[loss=0.1252, simple_loss=0.2047, pruned_loss=0.02288, over 4989.00 frames.], tot_loss[loss=0.1576, simple_loss=0.227, pruned_loss=0.04414, over 973470.49 frames.], batch size: 28, lr: 4.69e-04
+2022-05-04 20:03:51,126 INFO [train.py:715] (3/8) Epoch 4, batch 5600, loss[loss=0.1307, simple_loss=0.2086, pruned_loss=0.02645, over 4982.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2265, pruned_loss=0.04365, over 973982.94 frames.], batch size: 25, lr: 4.69e-04
+2022-05-04 20:04:31,006 INFO [train.py:715] (3/8) Epoch 4, batch 5650, loss[loss=0.1392, simple_loss=0.2068, pruned_loss=0.03579, over 4781.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2262, pruned_loss=0.0436, over 973177.99 frames.], batch size: 17, lr: 4.68e-04
+2022-05-04 20:05:10,989 INFO [train.py:715] (3/8) Epoch 4, batch 5700, loss[loss=0.1639, simple_loss=0.2288, pruned_loss=0.04951, over 4977.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2276, pruned_loss=0.04448, over 972729.22 frames.], batch size: 28, lr: 4.68e-04
+2022-05-04 20:05:51,205 INFO [train.py:715] (3/8) Epoch 4, batch 5750, loss[loss=0.1866, simple_loss=0.2488, pruned_loss=0.06223, over 4758.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2278, pruned_loss=0.0447, over 972519.34 frames.], batch size: 19, lr: 4.68e-04
+2022-05-04 20:06:31,308 INFO [train.py:715] (3/8) Epoch 4, batch 5800, loss[loss=0.1256, simple_loss=0.1937, pruned_loss=0.02873, over 4784.00 frames.], tot_loss[loss=0.158, simple_loss=0.2275, pruned_loss=0.04425, over 973644.35 frames.], batch size: 12, lr: 4.68e-04
+2022-05-04 20:07:10,959 INFO [train.py:715] (3/8) Epoch 4, batch 5850, loss[loss=0.1606, simple_loss=0.2325, pruned_loss=0.04438, over 4787.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2271, pruned_loss=0.04432, over 972353.95 frames.], batch size: 17, lr: 4.68e-04
+2022-05-04 20:07:51,257 INFO [train.py:715] (3/8) Epoch 4, batch 5900, loss[loss=0.1591, simple_loss=0.2336, pruned_loss=0.04229, over 4924.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2276, pruned_loss=0.0446, over 971740.17 frames.], batch size: 29, lr: 4.68e-04
+2022-05-04 20:08:30,936 INFO [train.py:715] (3/8) Epoch 4, batch 5950, loss[loss=0.1499, simple_loss=0.2241, pruned_loss=0.03782, over 4799.00 frames.], tot_loss[loss=0.159, simple_loss=0.2282, pruned_loss=0.04493, over 972004.17 frames.], batch size: 25, lr: 4.68e-04
+2022-05-04 20:09:10,570 INFO [train.py:715] (3/8) Epoch 4, batch 6000, loss[loss=0.1677, simple_loss=0.2298, pruned_loss=0.05282, over 4787.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2274, pruned_loss=0.04488, over 973070.41 frames.], batch size: 14, lr: 4.68e-04
+2022-05-04 20:09:10,571 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 20:09:20,451 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1124, simple_loss=0.1981, pruned_loss=0.01337, over 914524.00 frames.
+2022-05-04 20:10:00,571 INFO [train.py:715] (3/8) Epoch 4, batch 6050, loss[loss=0.1661, simple_loss=0.2453, pruned_loss=0.04349, over 4892.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2278, pruned_loss=0.04473, over 973227.80 frames.], batch size: 22, lr: 4.68e-04
+2022-05-04 20:10:40,767 INFO [train.py:715] (3/8) Epoch 4, batch 6100, loss[loss=0.2186, simple_loss=0.28, pruned_loss=0.07857, over 4920.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2276, pruned_loss=0.0446, over 973285.72 frames.], batch size: 18, lr: 4.68e-04
+2022-05-04 20:11:21,158 INFO [train.py:715] (3/8) Epoch 4, batch 6150, loss[loss=0.1548, simple_loss=0.2257, pruned_loss=0.04193, over 4881.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2272, pruned_loss=0.04474, over 973113.66 frames.], batch size: 22, lr: 4.68e-04
+2022-05-04 20:12:01,192 INFO [train.py:715] (3/8) Epoch 4, batch 6200, loss[loss=0.1866, simple_loss=0.2687, pruned_loss=0.05219, over 4802.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2267, pruned_loss=0.04451, over 973257.78 frames.], batch size: 25, lr: 4.68e-04
+2022-05-04 20:12:40,823 INFO [train.py:715] (3/8) Epoch 4, batch 6250, loss[loss=0.1503, simple_loss=0.2223, pruned_loss=0.03913, over 4811.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2256, pruned_loss=0.044, over 972785.20 frames.], batch size: 25, lr: 4.68e-04
+2022-05-04 20:13:21,465 INFO [train.py:715] (3/8) Epoch 4, batch 6300, loss[loss=0.1184, simple_loss=0.1907, pruned_loss=0.0231, over 4973.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2265, pruned_loss=0.04397, over 973193.76 frames.], batch size: 14, lr: 4.67e-04
+2022-05-04 20:14:00,897 INFO [train.py:715] (3/8) Epoch 4, batch 6350, loss[loss=0.1571, simple_loss=0.2239, pruned_loss=0.04513, over 4705.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2262, pruned_loss=0.04381, over 972867.16 frames.], batch size: 15, lr: 4.67e-04
+2022-05-04 20:14:41,820 INFO [train.py:715] (3/8) Epoch 4, batch 6400, loss[loss=0.1255, simple_loss=0.1988, pruned_loss=0.02604, over 4978.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2267, pruned_loss=0.04415, over 972204.77 frames.], batch size: 25, lr: 4.67e-04
+2022-05-04 20:15:21,558 INFO [train.py:715] (3/8) Epoch 4, batch 6450, loss[loss=0.1555, simple_loss=0.2171, pruned_loss=0.04696, over 4959.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2269, pruned_loss=0.04403, over 972110.88 frames.], batch size: 14, lr: 4.67e-04
+2022-05-04 20:16:01,662 INFO [train.py:715] (3/8) Epoch 4, batch 6500, loss[loss=0.181, simple_loss=0.252, pruned_loss=0.05496, over 4934.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2266, pruned_loss=0.04377, over 972069.67 frames.], batch size: 29, lr: 4.67e-04
+2022-05-04 20:16:41,332 INFO [train.py:715] (3/8) Epoch 4, batch 6550, loss[loss=0.1757, simple_loss=0.2477, pruned_loss=0.05185, over 4923.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2262, pruned_loss=0.04345, over 971713.42 frames.], batch size: 18, lr: 4.67e-04
+2022-05-04 20:17:20,644 INFO [train.py:715] (3/8) Epoch 4, batch 6600, loss[loss=0.1623, simple_loss=0.2315, pruned_loss=0.04652, over 4761.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2264, pruned_loss=0.04292, over 971528.01 frames.], batch size: 18, lr: 4.67e-04
+2022-05-04 20:18:01,337 INFO [train.py:715] (3/8) Epoch 4, batch 6650, loss[loss=0.1448, simple_loss=0.2137, pruned_loss=0.03796, over 4942.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2265, pruned_loss=0.04331, over 971819.60 frames.], batch size: 29, lr: 4.67e-04
+2022-05-04 20:18:40,886 INFO [train.py:715] (3/8) Epoch 4, batch 6700, loss[loss=0.1667, simple_loss=0.2411, pruned_loss=0.04616, over 4748.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2273, pruned_loss=0.04424, over 973245.81 frames.], batch size: 19, lr: 4.67e-04
+2022-05-04 20:19:21,004 INFO [train.py:715] (3/8) Epoch 4, batch 6750, loss[loss=0.1557, simple_loss=0.2211, pruned_loss=0.04518, over 4832.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2268, pruned_loss=0.0441, over 973094.33 frames.], batch size: 30, lr: 4.67e-04
+2022-05-04 20:20:00,764 INFO [train.py:715] (3/8) Epoch 4, batch 6800, loss[loss=0.1714, simple_loss=0.2322, pruned_loss=0.05533, over 4977.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2281, pruned_loss=0.04476, over 973566.76 frames.], batch size: 15, lr: 4.67e-04
+2022-05-04 20:20:40,795 INFO [train.py:715] (3/8) Epoch 4, batch 6850, loss[loss=0.1539, simple_loss=0.224, pruned_loss=0.04189, over 4947.00 frames.], tot_loss[loss=0.158, simple_loss=0.2275, pruned_loss=0.04421, over 973069.22 frames.], batch size: 21, lr: 4.67e-04
+2022-05-04 20:21:20,096 INFO [train.py:715] (3/8) Epoch 4, batch 6900, loss[loss=0.1961, simple_loss=0.2577, pruned_loss=0.06721, over 4944.00 frames.], tot_loss[loss=0.158, simple_loss=0.2276, pruned_loss=0.04421, over 973670.50 frames.], batch size: 35, lr: 4.66e-04
+2022-05-04 20:21:59,578 INFO [train.py:715] (3/8) Epoch 4, batch 6950, loss[loss=0.1444, simple_loss=0.2124, pruned_loss=0.03818, over 4796.00 frames.], tot_loss[loss=0.157, simple_loss=0.2269, pruned_loss=0.04354, over 974128.58 frames.], batch size: 12, lr: 4.66e-04
+2022-05-04 20:22:39,323 INFO [train.py:715] (3/8) Epoch 4, batch 7000, loss[loss=0.1683, simple_loss=0.2366, pruned_loss=0.04996, over 4773.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2278, pruned_loss=0.04418, over 973933.58 frames.], batch size: 17, lr: 4.66e-04
+2022-05-04 20:23:19,195 INFO [train.py:715] (3/8) Epoch 4, batch 7050, loss[loss=0.178, simple_loss=0.2366, pruned_loss=0.05973, over 4820.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2281, pruned_loss=0.04431, over 974381.24 frames.], batch size: 15, lr: 4.66e-04
+2022-05-04 20:23:58,923 INFO [train.py:715] (3/8) Epoch 4, batch 7100, loss[loss=0.1989, simple_loss=0.2706, pruned_loss=0.06359, over 4938.00 frames.], tot_loss[loss=0.1594, simple_loss=0.229, pruned_loss=0.04494, over 973867.07 frames.], batch size: 35, lr: 4.66e-04
+2022-05-04 20:24:39,015 INFO [train.py:715] (3/8) Epoch 4, batch 7150, loss[loss=0.1487, simple_loss=0.2194, pruned_loss=0.03902, over 4919.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2285, pruned_loss=0.04452, over 972973.33 frames.], batch size: 23, lr: 4.66e-04
+2022-05-04 20:25:18,946 INFO [train.py:715] (3/8) Epoch 4, batch 7200, loss[loss=0.1598, simple_loss=0.2305, pruned_loss=0.04455, over 4965.00 frames.], tot_loss[loss=0.1584, simple_loss=0.228, pruned_loss=0.04438, over 972104.34 frames.], batch size: 15, lr: 4.66e-04
+2022-05-04 20:25:59,097 INFO [train.py:715] (3/8) Epoch 4, batch 7250, loss[loss=0.217, simple_loss=0.2755, pruned_loss=0.07924, over 4910.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2278, pruned_loss=0.04493, over 971696.50 frames.], batch size: 18, lr: 4.66e-04
+2022-05-04 20:26:38,419 INFO [train.py:715] (3/8) Epoch 4, batch 7300, loss[loss=0.158, simple_loss=0.2247, pruned_loss=0.04565, over 4976.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2287, pruned_loss=0.04528, over 972237.45 frames.], batch size: 14, lr: 4.66e-04
+2022-05-04 20:27:18,104 INFO [train.py:715] (3/8) Epoch 4, batch 7350, loss[loss=0.17, simple_loss=0.2434, pruned_loss=0.04828, over 4962.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2284, pruned_loss=0.04512, over 972244.77 frames.], batch size: 15, lr: 4.66e-04
+2022-05-04 20:27:58,074 INFO [train.py:715] (3/8) Epoch 4, batch 7400, loss[loss=0.1391, simple_loss=0.2116, pruned_loss=0.03329, over 4910.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2277, pruned_loss=0.04442, over 971660.36 frames.], batch size: 19, lr: 4.66e-04
+2022-05-04 20:28:38,812 INFO [train.py:715] (3/8) Epoch 4, batch 7450, loss[loss=0.1708, simple_loss=0.2465, pruned_loss=0.04753, over 4969.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2278, pruned_loss=0.04404, over 971771.04 frames.], batch size: 24, lr: 4.66e-04
+2022-05-04 20:29:18,220 INFO [train.py:715] (3/8) Epoch 4, batch 7500, loss[loss=0.1354, simple_loss=0.2119, pruned_loss=0.02946, over 4812.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2274, pruned_loss=0.04381, over 971267.17 frames.], batch size: 21, lr: 4.66e-04
+2022-05-04 20:29:58,239 INFO [train.py:715] (3/8) Epoch 4, batch 7550, loss[loss=0.1278, simple_loss=0.1959, pruned_loss=0.02985, over 4692.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2266, pruned_loss=0.0435, over 970661.66 frames.], batch size: 15, lr: 4.65e-04
+2022-05-04 20:30:38,893 INFO [train.py:715] (3/8) Epoch 4, batch 7600, loss[loss=0.1728, simple_loss=0.2346, pruned_loss=0.05555, over 4815.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2261, pruned_loss=0.04338, over 970692.12 frames.], batch size: 14, lr: 4.65e-04
+2022-05-04 20:31:18,408 INFO [train.py:715] (3/8) Epoch 4, batch 7650, loss[loss=0.1506, simple_loss=0.2274, pruned_loss=0.0369, over 4933.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2271, pruned_loss=0.04406, over 971409.35 frames.], batch size: 29, lr: 4.65e-04
+2022-05-04 20:31:58,071 INFO [train.py:715] (3/8) Epoch 4, batch 7700, loss[loss=0.1311, simple_loss=0.2003, pruned_loss=0.03101, over 4855.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2264, pruned_loss=0.04366, over 971723.54 frames.], batch size: 13, lr: 4.65e-04
+2022-05-04 20:32:38,167 INFO [train.py:715] (3/8) Epoch 4, batch 7750, loss[loss=0.1459, simple_loss=0.2202, pruned_loss=0.03581, over 4684.00 frames.], tot_loss[loss=0.1574, simple_loss=0.227, pruned_loss=0.04392, over 972047.54 frames.], batch size: 15, lr: 4.65e-04
+2022-05-04 20:33:18,306 INFO [train.py:715] (3/8) Epoch 4, batch 7800, loss[loss=0.1561, simple_loss=0.2353, pruned_loss=0.0384, over 4881.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2266, pruned_loss=0.0432, over 971846.68 frames.], batch size: 22, lr: 4.65e-04
+2022-05-04 20:33:57,307 INFO [train.py:715] (3/8) Epoch 4, batch 7850, loss[loss=0.169, simple_loss=0.2233, pruned_loss=0.05737, over 4963.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2265, pruned_loss=0.04334, over 972931.74 frames.], batch size: 24, lr: 4.65e-04
+2022-05-04 20:34:36,904 INFO [train.py:715] (3/8) Epoch 4, batch 7900, loss[loss=0.1564, simple_loss=0.2278, pruned_loss=0.04252, over 4926.00 frames.], tot_loss[loss=0.1561, simple_loss=0.226, pruned_loss=0.0431, over 973108.31 frames.], batch size: 18, lr: 4.65e-04
+2022-05-04 20:35:16,766 INFO [train.py:715] (3/8) Epoch 4, batch 7950, loss[loss=0.1598, simple_loss=0.2261, pruned_loss=0.0468, over 4758.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2276, pruned_loss=0.04361, over 972555.20 frames.], batch size: 19, lr: 4.65e-04
+2022-05-04 20:35:56,346 INFO [train.py:715] (3/8) Epoch 4, batch 8000, loss[loss=0.1951, simple_loss=0.252, pruned_loss=0.06912, over 4774.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2283, pruned_loss=0.04459, over 971736.03 frames.], batch size: 17, lr: 4.65e-04
+2022-05-04 20:36:36,311 INFO [train.py:715] (3/8) Epoch 4, batch 8050, loss[loss=0.154, simple_loss=0.22, pruned_loss=0.04402, over 4879.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2294, pruned_loss=0.04501, over 971556.38 frames.], batch size: 16, lr: 4.65e-04
+2022-05-04 20:37:16,267 INFO [train.py:715] (3/8) Epoch 4, batch 8100, loss[loss=0.1923, simple_loss=0.2492, pruned_loss=0.06775, over 4964.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2286, pruned_loss=0.04497, over 972235.59 frames.], batch size: 35, lr: 4.65e-04
+2022-05-04 20:37:56,506 INFO [train.py:715] (3/8) Epoch 4, batch 8150, loss[loss=0.1846, simple_loss=0.2519, pruned_loss=0.05866, over 4822.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2293, pruned_loss=0.04516, over 972153.74 frames.], batch size: 25, lr: 4.65e-04
+2022-05-04 20:38:35,991 INFO [train.py:715] (3/8) Epoch 4, batch 8200, loss[loss=0.1543, simple_loss=0.2345, pruned_loss=0.03706, over 4990.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2295, pruned_loss=0.04487, over 971820.41 frames.], batch size: 25, lr: 4.64e-04
+2022-05-04 20:39:15,725 INFO [train.py:715] (3/8) Epoch 4, batch 8250, loss[loss=0.13, simple_loss=0.202, pruned_loss=0.02902, over 4805.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2283, pruned_loss=0.04426, over 972103.99 frames.], batch size: 25, lr: 4.64e-04
+2022-05-04 20:39:55,876 INFO [train.py:715] (3/8) Epoch 4, batch 8300, loss[loss=0.1779, simple_loss=0.2441, pruned_loss=0.0559, over 4777.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2283, pruned_loss=0.04438, over 972875.32 frames.], batch size: 18, lr: 4.64e-04
+2022-05-04 20:40:35,313 INFO [train.py:715] (3/8) Epoch 4, batch 8350, loss[loss=0.1469, simple_loss=0.2177, pruned_loss=0.03799, over 4835.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2281, pruned_loss=0.04402, over 972365.32 frames.], batch size: 13, lr: 4.64e-04
+2022-05-04 20:41:15,401 INFO [train.py:715] (3/8) Epoch 4, batch 8400, loss[loss=0.1806, simple_loss=0.2482, pruned_loss=0.05653, over 4887.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2275, pruned_loss=0.04393, over 972344.14 frames.], batch size: 16, lr: 4.64e-04
+2022-05-04 20:41:55,743 INFO [train.py:715] (3/8) Epoch 4, batch 8450, loss[loss=0.1755, simple_loss=0.2388, pruned_loss=0.05609, over 4916.00 frames.], tot_loss[loss=0.157, simple_loss=0.2266, pruned_loss=0.04373, over 971936.73 frames.], batch size: 17, lr: 4.64e-04
+2022-05-04 20:42:35,853 INFO [train.py:715] (3/8) Epoch 4, batch 8500, loss[loss=0.1866, simple_loss=0.2465, pruned_loss=0.0634, over 4858.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2264, pruned_loss=0.04412, over 971770.80 frames.], batch size: 20, lr: 4.64e-04
+2022-05-04 20:43:15,261 INFO [train.py:715] (3/8) Epoch 4, batch 8550, loss[loss=0.1777, simple_loss=0.2379, pruned_loss=0.05874, over 4836.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2265, pruned_loss=0.0445, over 972373.13 frames.], batch size: 30, lr: 4.64e-04
+2022-05-04 20:43:55,081 INFO [train.py:715] (3/8) Epoch 4, batch 8600, loss[loss=0.1369, simple_loss=0.2027, pruned_loss=0.03554, over 4756.00 frames.], tot_loss[loss=0.1583, simple_loss=0.227, pruned_loss=0.04474, over 972703.09 frames.], batch size: 12, lr: 4.64e-04
+2022-05-04 20:44:35,239 INFO [train.py:715] (3/8) Epoch 4, batch 8650, loss[loss=0.1974, simple_loss=0.2613, pruned_loss=0.06677, over 4964.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2274, pruned_loss=0.04481, over 972482.83 frames.], batch size: 15, lr: 4.64e-04
+2022-05-04 20:45:14,869 INFO [train.py:715] (3/8) Epoch 4, batch 8700, loss[loss=0.1261, simple_loss=0.2028, pruned_loss=0.02468, over 4816.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2262, pruned_loss=0.04401, over 972055.03 frames.], batch size: 27, lr: 4.64e-04
+2022-05-04 20:45:55,167 INFO [train.py:715] (3/8) Epoch 4, batch 8750, loss[loss=0.1459, simple_loss=0.2266, pruned_loss=0.03258, over 4799.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2252, pruned_loss=0.04365, over 972169.80 frames.], batch size: 24, lr: 4.64e-04
+2022-05-04 20:46:35,396 INFO [train.py:715] (3/8) Epoch 4, batch 8800, loss[loss=0.1354, simple_loss=0.2018, pruned_loss=0.03453, over 4902.00 frames.], tot_loss[loss=0.1558, simple_loss=0.225, pruned_loss=0.04325, over 972945.54 frames.], batch size: 19, lr: 4.63e-04
+2022-05-04 20:47:15,432 INFO [train.py:715] (3/8) Epoch 4, batch 8850, loss[loss=0.1684, simple_loss=0.2321, pruned_loss=0.05233, over 4734.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2255, pruned_loss=0.04301, over 972078.73 frames.], batch size: 16, lr: 4.63e-04
+2022-05-04 20:47:55,126 INFO [train.py:715] (3/8) Epoch 4, batch 8900, loss[loss=0.1335, simple_loss=0.205, pruned_loss=0.03098, over 4906.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2251, pruned_loss=0.04284, over 971193.88 frames.], batch size: 19, lr: 4.63e-04
+2022-05-04 20:48:34,759 INFO [train.py:715] (3/8) Epoch 4, batch 8950, loss[loss=0.1734, simple_loss=0.2401, pruned_loss=0.0534, over 4899.00 frames.], tot_loss[loss=0.1554, simple_loss=0.225, pruned_loss=0.04293, over 970740.98 frames.], batch size: 19, lr: 4.63e-04
+2022-05-04 20:49:15,024 INFO [train.py:715] (3/8) Epoch 4, batch 9000, loss[loss=0.204, simple_loss=0.2684, pruned_loss=0.06978, over 4937.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2267, pruned_loss=0.0442, over 971945.32 frames.], batch size: 39, lr: 4.63e-04
+2022-05-04 20:49:15,024 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 20:49:24,976 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1123, simple_loss=0.1979, pruned_loss=0.01336, over 914524.00 frames.
+2022-05-04 20:50:05,303 INFO [train.py:715] (3/8) Epoch 4, batch 9050, loss[loss=0.1166, simple_loss=0.1887, pruned_loss=0.02223, over 4932.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04385, over 971626.47 frames.], batch size: 23, lr: 4.63e-04
+2022-05-04 20:50:45,311 INFO [train.py:715] (3/8) Epoch 4, batch 9100, loss[loss=0.1721, simple_loss=0.2314, pruned_loss=0.05644, over 4851.00 frames.], tot_loss[loss=0.1567, simple_loss=0.226, pruned_loss=0.04367, over 971783.20 frames.], batch size: 32, lr: 4.63e-04
+2022-05-04 20:51:24,708 INFO [train.py:715] (3/8) Epoch 4, batch 9150, loss[loss=0.1739, simple_loss=0.2374, pruned_loss=0.05524, over 4859.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2253, pruned_loss=0.04353, over 971995.80 frames.], batch size: 39, lr: 4.63e-04
+2022-05-04 20:52:04,886 INFO [train.py:715] (3/8) Epoch 4, batch 9200, loss[loss=0.1535, simple_loss=0.2069, pruned_loss=0.05009, over 4909.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2254, pruned_loss=0.04353, over 972150.55 frames.], batch size: 18, lr: 4.63e-04
+2022-05-04 20:52:45,293 INFO [train.py:715] (3/8) Epoch 4, batch 9250, loss[loss=0.1333, simple_loss=0.2014, pruned_loss=0.03257, over 4731.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2262, pruned_loss=0.04404, over 972742.27 frames.], batch size: 12, lr: 4.63e-04
+2022-05-04 20:53:24,536 INFO [train.py:715] (3/8) Epoch 4, batch 9300, loss[loss=0.1168, simple_loss=0.1875, pruned_loss=0.02309, over 4835.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2265, pruned_loss=0.04404, over 972098.66 frames.], batch size: 26, lr: 4.63e-04
+2022-05-04 20:54:04,527 INFO [train.py:715] (3/8) Epoch 4, batch 9350, loss[loss=0.173, simple_loss=0.2437, pruned_loss=0.05117, over 4937.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2267, pruned_loss=0.04439, over 971683.31 frames.], batch size: 23, lr: 4.63e-04
+2022-05-04 20:54:44,470 INFO [train.py:715] (3/8) Epoch 4, batch 9400, loss[loss=0.1913, simple_loss=0.2596, pruned_loss=0.06151, over 4897.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2274, pruned_loss=0.04451, over 971701.53 frames.], batch size: 19, lr: 4.63e-04
+2022-05-04 20:55:24,002 INFO [train.py:715] (3/8) Epoch 4, batch 9450, loss[loss=0.1469, simple_loss=0.2238, pruned_loss=0.03503, over 4763.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2275, pruned_loss=0.04451, over 971735.96 frames.], batch size: 19, lr: 4.62e-04
+2022-05-04 20:56:04,093 INFO [train.py:715] (3/8) Epoch 4, batch 9500, loss[loss=0.1457, simple_loss=0.2137, pruned_loss=0.03884, over 4928.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2274, pruned_loss=0.04469, over 971573.25 frames.], batch size: 29, lr: 4.62e-04
+2022-05-04 20:56:44,148 INFO [train.py:715] (3/8) Epoch 4, batch 9550, loss[loss=0.1239, simple_loss=0.1906, pruned_loss=0.02862, over 4813.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2276, pruned_loss=0.04469, over 971241.34 frames.], batch size: 25, lr: 4.62e-04
+2022-05-04 20:57:24,668 INFO [train.py:715] (3/8) Epoch 4, batch 9600, loss[loss=0.1626, simple_loss=0.2353, pruned_loss=0.04498, over 4868.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2266, pruned_loss=0.0444, over 971483.63 frames.], batch size: 20, lr: 4.62e-04
+2022-05-04 20:58:04,092 INFO [train.py:715] (3/8) Epoch 4, batch 9650, loss[loss=0.1373, simple_loss=0.2047, pruned_loss=0.03502, over 4956.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2267, pruned_loss=0.04422, over 972724.49 frames.], batch size: 14, lr: 4.62e-04
+2022-05-04 20:58:44,655 INFO [train.py:715] (3/8) Epoch 4, batch 9700, loss[loss=0.1502, simple_loss=0.2167, pruned_loss=0.04187, over 4781.00 frames.], tot_loss[loss=0.1576, simple_loss=0.227, pruned_loss=0.04414, over 972619.06 frames.], batch size: 17, lr: 4.62e-04
+2022-05-04 20:59:25,196 INFO [train.py:715] (3/8) Epoch 4, batch 9750, loss[loss=0.1286, simple_loss=0.1956, pruned_loss=0.03083, over 4685.00 frames.], tot_loss[loss=0.158, simple_loss=0.2273, pruned_loss=0.0443, over 972630.58 frames.], batch size: 15, lr: 4.62e-04
+2022-05-04 21:00:04,726 INFO [train.py:715] (3/8) Epoch 4, batch 9800, loss[loss=0.1482, simple_loss=0.2094, pruned_loss=0.04351, over 4980.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2279, pruned_loss=0.04457, over 973382.41 frames.], batch size: 14, lr: 4.62e-04
+2022-05-04 21:00:43,861 INFO [train.py:715] (3/8) Epoch 4, batch 9850, loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02856, over 4925.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2276, pruned_loss=0.04444, over 972851.22 frames.], batch size: 18, lr: 4.62e-04
+2022-05-04 21:01:23,904 INFO [train.py:715] (3/8) Epoch 4, batch 9900, loss[loss=0.1528, simple_loss=0.2215, pruned_loss=0.0421, over 4946.00 frames.], tot_loss[loss=0.157, simple_loss=0.2265, pruned_loss=0.04369, over 973258.81 frames.], batch size: 24, lr: 4.62e-04
+2022-05-04 21:02:03,377 INFO [train.py:715] (3/8) Epoch 4, batch 9950, loss[loss=0.1658, simple_loss=0.246, pruned_loss=0.04286, over 4809.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2267, pruned_loss=0.04333, over 973160.58 frames.], batch size: 21, lr: 4.62e-04
+2022-05-04 21:02:42,751 INFO [train.py:715] (3/8) Epoch 4, batch 10000, loss[loss=0.1779, simple_loss=0.2337, pruned_loss=0.061, over 4784.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2263, pruned_loss=0.04338, over 974037.96 frames.], batch size: 14, lr: 4.62e-04
+2022-05-04 21:03:22,513 INFO [train.py:715] (3/8) Epoch 4, batch 10050, loss[loss=0.2355, simple_loss=0.3089, pruned_loss=0.08108, over 4895.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2273, pruned_loss=0.04367, over 973645.57 frames.], batch size: 22, lr: 4.62e-04
+2022-05-04 21:04:02,313 INFO [train.py:715] (3/8) Epoch 4, batch 10100, loss[loss=0.173, simple_loss=0.2381, pruned_loss=0.05393, over 4800.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2278, pruned_loss=0.04369, over 974261.61 frames.], batch size: 25, lr: 4.61e-04
+2022-05-04 21:04:41,556 INFO [train.py:715] (3/8) Epoch 4, batch 10150, loss[loss=0.1749, simple_loss=0.2473, pruned_loss=0.05128, over 4980.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2271, pruned_loss=0.04401, over 974228.41 frames.], batch size: 14, lr: 4.61e-04
+2022-05-04 21:05:21,478 INFO [train.py:715] (3/8) Epoch 4, batch 10200, loss[loss=0.1833, simple_loss=0.258, pruned_loss=0.0543, over 4817.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2279, pruned_loss=0.04455, over 974143.12 frames.], batch size: 25, lr: 4.61e-04
+2022-05-04 21:06:02,062 INFO [train.py:715] (3/8) Epoch 4, batch 10250, loss[loss=0.1258, simple_loss=0.2046, pruned_loss=0.02352, over 4806.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2275, pruned_loss=0.04408, over 973299.04 frames.], batch size: 21, lr: 4.61e-04
+2022-05-04 21:06:41,846 INFO [train.py:715] (3/8) Epoch 4, batch 10300, loss[loss=0.1723, simple_loss=0.248, pruned_loss=0.04827, over 4967.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2283, pruned_loss=0.04478, over 973536.25 frames.], batch size: 24, lr: 4.61e-04
+2022-05-04 21:07:21,505 INFO [train.py:715] (3/8) Epoch 4, batch 10350, loss[loss=0.1486, simple_loss=0.2277, pruned_loss=0.03476, over 4955.00 frames.], tot_loss[loss=0.158, simple_loss=0.2275, pruned_loss=0.04428, over 973065.60 frames.], batch size: 24, lr: 4.61e-04
+2022-05-04 21:08:01,703 INFO [train.py:715] (3/8) Epoch 4, batch 10400, loss[loss=0.1678, simple_loss=0.2357, pruned_loss=0.04996, over 4871.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2264, pruned_loss=0.04389, over 972083.03 frames.], batch size: 30, lr: 4.61e-04
+2022-05-04 21:08:42,279 INFO [train.py:715] (3/8) Epoch 4, batch 10450, loss[loss=0.1146, simple_loss=0.1737, pruned_loss=0.02777, over 4773.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2257, pruned_loss=0.04376, over 972052.19 frames.], batch size: 12, lr: 4.61e-04
+2022-05-04 21:09:21,890 INFO [train.py:715] (3/8) Epoch 4, batch 10500, loss[loss=0.135, simple_loss=0.215, pruned_loss=0.02753, over 4958.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2258, pruned_loss=0.04351, over 972432.01 frames.], batch size: 21, lr: 4.61e-04
+2022-05-04 21:10:02,146 INFO [train.py:715] (3/8) Epoch 4, batch 10550, loss[loss=0.1294, simple_loss=0.2064, pruned_loss=0.02622, over 4752.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2264, pruned_loss=0.04356, over 972259.99 frames.], batch size: 16, lr: 4.61e-04
+2022-05-04 21:10:42,491 INFO [train.py:715] (3/8) Epoch 4, batch 10600, loss[loss=0.1629, simple_loss=0.2418, pruned_loss=0.04203, over 4758.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04315, over 972696.27 frames.], batch size: 16, lr: 4.61e-04
+2022-05-04 21:11:22,294 INFO [train.py:715] (3/8) Epoch 4, batch 10650, loss[loss=0.1637, simple_loss=0.2401, pruned_loss=0.04363, over 4948.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2262, pruned_loss=0.04332, over 973279.85 frames.], batch size: 29, lr: 4.61e-04
+2022-05-04 21:12:02,339 INFO [train.py:715] (3/8) Epoch 4, batch 10700, loss[loss=0.2021, simple_loss=0.2689, pruned_loss=0.06767, over 4824.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2263, pruned_loss=0.0433, over 972911.81 frames.], batch size: 15, lr: 4.61e-04
+2022-05-04 21:12:42,038 INFO [train.py:715] (3/8) Epoch 4, batch 10750, loss[loss=0.1963, simple_loss=0.2612, pruned_loss=0.06572, over 4889.00 frames.], tot_loss[loss=0.1573, simple_loss=0.227, pruned_loss=0.04376, over 972218.13 frames.], batch size: 16, lr: 4.60e-04
+2022-05-04 21:13:22,454 INFO [train.py:715] (3/8) Epoch 4, batch 10800, loss[loss=0.1484, simple_loss=0.2055, pruned_loss=0.04566, over 4893.00 frames.], tot_loss[loss=0.157, simple_loss=0.2266, pruned_loss=0.04369, over 973172.86 frames.], batch size: 32, lr: 4.60e-04
+2022-05-04 21:14:01,774 INFO [train.py:715] (3/8) Epoch 4, batch 10850, loss[loss=0.1379, simple_loss=0.2135, pruned_loss=0.0311, over 4779.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2259, pruned_loss=0.04294, over 973175.63 frames.], batch size: 17, lr: 4.60e-04
+2022-05-04 21:14:41,705 INFO [train.py:715] (3/8) Epoch 4, batch 10900, loss[loss=0.1568, simple_loss=0.2236, pruned_loss=0.04501, over 4949.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2261, pruned_loss=0.04323, over 973371.64 frames.], batch size: 21, lr: 4.60e-04
+2022-05-04 21:15:22,019 INFO [train.py:715] (3/8) Epoch 4, batch 10950, loss[loss=0.1584, simple_loss=0.2262, pruned_loss=0.04537, over 4943.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2263, pruned_loss=0.04321, over 973143.97 frames.], batch size: 39, lr: 4.60e-04
+2022-05-04 21:16:01,655 INFO [train.py:715] (3/8) Epoch 4, batch 11000, loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.02849, over 4778.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2257, pruned_loss=0.04323, over 974014.02 frames.], batch size: 17, lr: 4.60e-04
+2022-05-04 21:16:44,081 INFO [train.py:715] (3/8) Epoch 4, batch 11050, loss[loss=0.1666, simple_loss=0.2465, pruned_loss=0.04339, over 4936.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2259, pruned_loss=0.0435, over 973396.72 frames.], batch size: 29, lr: 4.60e-04
+2022-05-04 21:17:24,568 INFO [train.py:715] (3/8) Epoch 4, batch 11100, loss[loss=0.1284, simple_loss=0.1959, pruned_loss=0.03046, over 4920.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2255, pruned_loss=0.0431, over 973079.76 frames.], batch size: 17, lr: 4.60e-04
+2022-05-04 21:18:07,382 INFO [train.py:715] (3/8) Epoch 4, batch 11150, loss[loss=0.1814, simple_loss=0.2445, pruned_loss=0.05913, over 4883.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2264, pruned_loss=0.04339, over 972816.06 frames.], batch size: 16, lr: 4.60e-04
+2022-05-04 21:18:49,597 INFO [train.py:715] (3/8) Epoch 4, batch 11200, loss[loss=0.144, simple_loss=0.2171, pruned_loss=0.03542, over 4810.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2261, pruned_loss=0.04319, over 972337.29 frames.], batch size: 26, lr: 4.60e-04
+2022-05-04 21:19:29,999 INFO [train.py:715] (3/8) Epoch 4, batch 11250, loss[loss=0.1749, simple_loss=0.2419, pruned_loss=0.05392, over 4780.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2264, pruned_loss=0.04343, over 972303.83 frames.], batch size: 17, lr: 4.60e-04
+2022-05-04 21:20:12,913 INFO [train.py:715] (3/8) Epoch 4, batch 11300, loss[loss=0.1206, simple_loss=0.1899, pruned_loss=0.02565, over 4935.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2265, pruned_loss=0.04367, over 972143.59 frames.], batch size: 29, lr: 4.60e-04
+2022-05-04 21:20:52,369 INFO [train.py:715] (3/8) Epoch 4, batch 11350, loss[loss=0.1576, simple_loss=0.2281, pruned_loss=0.04353, over 4868.00 frames.], tot_loss[loss=0.1576, simple_loss=0.227, pruned_loss=0.04411, over 973017.72 frames.], batch size: 13, lr: 4.60e-04
+2022-05-04 21:21:31,879 INFO [train.py:715] (3/8) Epoch 4, batch 11400, loss[loss=0.1469, simple_loss=0.2148, pruned_loss=0.03949, over 4917.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04399, over 972653.62 frames.], batch size: 17, lr: 4.59e-04
+2022-05-04 21:22:11,706 INFO [train.py:715] (3/8) Epoch 4, batch 11450, loss[loss=0.1466, simple_loss=0.2255, pruned_loss=0.03383, over 4770.00 frames.], tot_loss[loss=0.1568, simple_loss=0.226, pruned_loss=0.04376, over 972060.47 frames.], batch size: 14, lr: 4.59e-04
+2022-05-04 21:22:51,369 INFO [train.py:715] (3/8) Epoch 4, batch 11500, loss[loss=0.1347, simple_loss=0.2101, pruned_loss=0.02964, over 4773.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2269, pruned_loss=0.04395, over 971475.66 frames.], batch size: 17, lr: 4.59e-04
+2022-05-04 21:23:30,621 INFO [train.py:715] (3/8) Epoch 4, batch 11550, loss[loss=0.1525, simple_loss=0.2254, pruned_loss=0.03985, over 4953.00 frames.], tot_loss[loss=0.156, simple_loss=0.2255, pruned_loss=0.04323, over 972581.74 frames.], batch size: 14, lr: 4.59e-04
+2022-05-04 21:24:09,876 INFO [train.py:715] (3/8) Epoch 4, batch 11600, loss[loss=0.1632, simple_loss=0.239, pruned_loss=0.04364, over 4923.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2256, pruned_loss=0.04362, over 973118.98 frames.], batch size: 23, lr: 4.59e-04
+2022-05-04 21:24:50,390 INFO [train.py:715] (3/8) Epoch 4, batch 11650, loss[loss=0.1773, simple_loss=0.2446, pruned_loss=0.05494, over 4866.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2256, pruned_loss=0.04366, over 972249.21 frames.], batch size: 20, lr: 4.59e-04
+2022-05-04 21:25:30,290 INFO [train.py:715] (3/8) Epoch 4, batch 11700, loss[loss=0.1496, simple_loss=0.2149, pruned_loss=0.04213, over 4841.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2261, pruned_loss=0.04409, over 972137.20 frames.], batch size: 26, lr: 4.59e-04
+2022-05-04 21:26:10,261 INFO [train.py:715] (3/8) Epoch 4, batch 11750, loss[loss=0.1355, simple_loss=0.2204, pruned_loss=0.0253, over 4902.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2264, pruned_loss=0.0435, over 971593.26 frames.], batch size: 17, lr: 4.59e-04
+2022-05-04 21:26:50,010 INFO [train.py:715] (3/8) Epoch 4, batch 11800, loss[loss=0.1665, simple_loss=0.2228, pruned_loss=0.05512, over 4834.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2265, pruned_loss=0.04389, over 971114.99 frames.], batch size: 15, lr: 4.59e-04
+2022-05-04 21:27:30,277 INFO [train.py:715] (3/8) Epoch 4, batch 11850, loss[loss=0.136, simple_loss=0.2102, pruned_loss=0.0309, over 4833.00 frames.], tot_loss[loss=0.157, simple_loss=0.2264, pruned_loss=0.04382, over 971717.91 frames.], batch size: 15, lr: 4.59e-04
+2022-05-04 21:28:09,539 INFO [train.py:715] (3/8) Epoch 4, batch 11900, loss[loss=0.1821, simple_loss=0.2464, pruned_loss=0.05888, over 4916.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04392, over 972013.94 frames.], batch size: 17, lr: 4.59e-04
+2022-05-04 21:28:49,311 INFO [train.py:715] (3/8) Epoch 4, batch 11950, loss[loss=0.1594, simple_loss=0.221, pruned_loss=0.04893, over 4806.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2261, pruned_loss=0.04367, over 972513.17 frames.], batch size: 13, lr: 4.59e-04
+2022-05-04 21:29:29,768 INFO [train.py:715] (3/8) Epoch 4, batch 12000, loss[loss=0.1444, simple_loss=0.2153, pruned_loss=0.03678, over 4861.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2278, pruned_loss=0.04428, over 972722.67 frames.], batch size: 20, lr: 4.59e-04
+2022-05-04 21:29:29,769 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 21:29:49,525 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1122, simple_loss=0.198, pruned_loss=0.01324, over 914524.00 frames.
+2022-05-04 21:30:30,070 INFO [train.py:715] (3/8) Epoch 4, batch 12050, loss[loss=0.1419, simple_loss=0.2242, pruned_loss=0.02981, over 4795.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2272, pruned_loss=0.04376, over 972602.30 frames.], batch size: 21, lr: 4.58e-04
+2022-05-04 21:31:09,883 INFO [train.py:715] (3/8) Epoch 4, batch 12100, loss[loss=0.1741, simple_loss=0.2482, pruned_loss=0.05002, over 4879.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2278, pruned_loss=0.0439, over 972478.79 frames.], batch size: 32, lr: 4.58e-04
+2022-05-04 21:31:50,061 INFO [train.py:715] (3/8) Epoch 4, batch 12150, loss[loss=0.131, simple_loss=0.2017, pruned_loss=0.03017, over 4752.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2268, pruned_loss=0.04372, over 972774.09 frames.], batch size: 16, lr: 4.58e-04
+2022-05-04 21:32:30,107 INFO [train.py:715] (3/8) Epoch 4, batch 12200, loss[loss=0.1516, simple_loss=0.2174, pruned_loss=0.04286, over 4927.00 frames.], tot_loss[loss=0.1565, simple_loss=0.226, pruned_loss=0.0435, over 973463.92 frames.], batch size: 39, lr: 4.58e-04
+2022-05-04 21:33:10,437 INFO [train.py:715] (3/8) Epoch 4, batch 12250, loss[loss=0.135, simple_loss=0.2127, pruned_loss=0.02872, over 4780.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2258, pruned_loss=0.04357, over 972509.68 frames.], batch size: 18, lr: 4.58e-04
+2022-05-04 21:33:49,420 INFO [train.py:715] (3/8) Epoch 4, batch 12300, loss[loss=0.1786, simple_loss=0.2354, pruned_loss=0.06092, over 4824.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2268, pruned_loss=0.04387, over 972337.48 frames.], batch size: 15, lr: 4.58e-04
+2022-05-04 21:34:29,438 INFO [train.py:715] (3/8) Epoch 4, batch 12350, loss[loss=0.175, simple_loss=0.2366, pruned_loss=0.05674, over 4931.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2281, pruned_loss=0.04441, over 972802.81 frames.], batch size: 35, lr: 4.58e-04
+2022-05-04 21:35:10,027 INFO [train.py:715] (3/8) Epoch 4, batch 12400, loss[loss=0.1517, simple_loss=0.2299, pruned_loss=0.0367, over 4812.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2282, pruned_loss=0.04442, over 972842.82 frames.], batch size: 27, lr: 4.58e-04
+2022-05-04 21:35:49,239 INFO [train.py:715] (3/8) Epoch 4, batch 12450, loss[loss=0.149, simple_loss=0.2186, pruned_loss=0.03969, over 4887.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2278, pruned_loss=0.04433, over 973042.45 frames.], batch size: 19, lr: 4.58e-04
+2022-05-04 21:36:29,203 INFO [train.py:715] (3/8) Epoch 4, batch 12500, loss[loss=0.1196, simple_loss=0.1861, pruned_loss=0.0265, over 4815.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2263, pruned_loss=0.04365, over 973493.67 frames.], batch size: 26, lr: 4.58e-04
+2022-05-04 21:37:08,760 INFO [train.py:715] (3/8) Epoch 4, batch 12550, loss[loss=0.1639, simple_loss=0.2387, pruned_loss=0.04455, over 4812.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2263, pruned_loss=0.04393, over 972729.27 frames.], batch size: 26, lr: 4.58e-04
+2022-05-04 21:37:48,547 INFO [train.py:715] (3/8) Epoch 4, batch 12600, loss[loss=0.1184, simple_loss=0.1915, pruned_loss=0.02267, over 4788.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2266, pruned_loss=0.04421, over 971500.62 frames.], batch size: 14, lr: 4.58e-04
+2022-05-04 21:38:27,436 INFO [train.py:715] (3/8) Epoch 4, batch 12650, loss[loss=0.154, simple_loss=0.2198, pruned_loss=0.04408, over 4800.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2259, pruned_loss=0.0439, over 971871.58 frames.], batch size: 21, lr: 4.58e-04
+2022-05-04 21:39:07,279 INFO [train.py:715] (3/8) Epoch 4, batch 12700, loss[loss=0.1957, simple_loss=0.2708, pruned_loss=0.06032, over 4891.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2265, pruned_loss=0.04388, over 972023.74 frames.], batch size: 22, lr: 4.58e-04
+2022-05-04 21:39:47,348 INFO [train.py:715] (3/8) Epoch 4, batch 12750, loss[loss=0.1451, simple_loss=0.2076, pruned_loss=0.04133, over 4848.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2272, pruned_loss=0.04433, over 972783.23 frames.], batch size: 30, lr: 4.57e-04
+2022-05-04 21:40:29,601 INFO [train.py:715] (3/8) Epoch 4, batch 12800, loss[loss=0.1662, simple_loss=0.2219, pruned_loss=0.05527, over 4909.00 frames.], tot_loss[loss=0.158, simple_loss=0.2273, pruned_loss=0.04439, over 971817.01 frames.], batch size: 18, lr: 4.57e-04
+2022-05-04 21:41:09,000 INFO [train.py:715] (3/8) Epoch 4, batch 12850, loss[loss=0.136, simple_loss=0.213, pruned_loss=0.02945, over 4820.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2272, pruned_loss=0.04418, over 971481.59 frames.], batch size: 26, lr: 4.57e-04
+2022-05-04 21:41:49,126 INFO [train.py:715] (3/8) Epoch 4, batch 12900, loss[loss=0.1952, simple_loss=0.2433, pruned_loss=0.07358, over 4757.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2275, pruned_loss=0.04382, over 971906.97 frames.], batch size: 16, lr: 4.57e-04
+2022-05-04 21:42:29,051 INFO [train.py:715] (3/8) Epoch 4, batch 12950, loss[loss=0.1442, simple_loss=0.2232, pruned_loss=0.03263, over 4783.00 frames.], tot_loss[loss=0.157, simple_loss=0.2267, pruned_loss=0.04363, over 972739.20 frames.], batch size: 14, lr: 4.57e-04
+2022-05-04 21:43:07,919 INFO [train.py:715] (3/8) Epoch 4, batch 13000, loss[loss=0.1776, simple_loss=0.2377, pruned_loss=0.05876, over 4782.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2272, pruned_loss=0.04377, over 972883.46 frames.], batch size: 18, lr: 4.57e-04
+2022-05-04 21:43:47,506 INFO [train.py:715] (3/8) Epoch 4, batch 13050, loss[loss=0.1472, simple_loss=0.2182, pruned_loss=0.03805, over 4777.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2273, pruned_loss=0.0436, over 972773.11 frames.], batch size: 17, lr: 4.57e-04
+2022-05-04 21:44:27,470 INFO [train.py:715] (3/8) Epoch 4, batch 13100, loss[loss=0.1341, simple_loss=0.1944, pruned_loss=0.03687, over 4963.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2253, pruned_loss=0.04287, over 972418.21 frames.], batch size: 15, lr: 4.57e-04
+2022-05-04 21:45:06,508 INFO [train.py:715] (3/8) Epoch 4, batch 13150, loss[loss=0.1393, simple_loss=0.2059, pruned_loss=0.03635, over 4975.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2259, pruned_loss=0.04367, over 972539.01 frames.], batch size: 28, lr: 4.57e-04
+2022-05-04 21:45:46,249 INFO [train.py:715] (3/8) Epoch 4, batch 13200, loss[loss=0.1504, simple_loss=0.2304, pruned_loss=0.03524, over 4802.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2255, pruned_loss=0.04314, over 972992.81 frames.], batch size: 21, lr: 4.57e-04
+2022-05-04 21:46:26,567 INFO [train.py:715] (3/8) Epoch 4, batch 13250, loss[loss=0.1635, simple_loss=0.2344, pruned_loss=0.0463, over 4982.00 frames.], tot_loss[loss=0.1564, simple_loss=0.226, pruned_loss=0.04339, over 972358.23 frames.], batch size: 28, lr: 4.57e-04
+2022-05-04 21:47:06,174 INFO [train.py:715] (3/8) Epoch 4, batch 13300, loss[loss=0.1523, simple_loss=0.2139, pruned_loss=0.04532, over 4986.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2265, pruned_loss=0.04358, over 972761.23 frames.], batch size: 28, lr: 4.57e-04
+2022-05-04 21:47:45,761 INFO [train.py:715] (3/8) Epoch 4, batch 13350, loss[loss=0.1417, simple_loss=0.2107, pruned_loss=0.03629, over 4989.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2261, pruned_loss=0.0436, over 973374.56 frames.], batch size: 20, lr: 4.57e-04
+2022-05-04 21:48:25,403 INFO [train.py:715] (3/8) Epoch 4, batch 13400, loss[loss=0.185, simple_loss=0.2464, pruned_loss=0.06181, over 4879.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2255, pruned_loss=0.04353, over 973286.86 frames.], batch size: 16, lr: 4.56e-04
+2022-05-04 21:49:05,432 INFO [train.py:715] (3/8) Epoch 4, batch 13450, loss[loss=0.1767, simple_loss=0.2488, pruned_loss=0.0523, over 4823.00 frames.], tot_loss[loss=0.156, simple_loss=0.2249, pruned_loss=0.04356, over 972842.50 frames.], batch size: 15, lr: 4.56e-04
+2022-05-04 21:49:45,241 INFO [train.py:715] (3/8) Epoch 4, batch 13500, loss[loss=0.1215, simple_loss=0.2017, pruned_loss=0.02065, over 4939.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2248, pruned_loss=0.04315, over 973646.15 frames.], batch size: 23, lr: 4.56e-04
+2022-05-04 21:50:27,087 INFO [train.py:715] (3/8) Epoch 4, batch 13550, loss[loss=0.1568, simple_loss=0.217, pruned_loss=0.04826, over 4973.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2246, pruned_loss=0.04254, over 973622.79 frames.], batch size: 35, lr: 4.56e-04
+2022-05-04 21:51:07,662 INFO [train.py:715] (3/8) Epoch 4, batch 13600, loss[loss=0.1393, simple_loss=0.215, pruned_loss=0.03179, over 4962.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2257, pruned_loss=0.04334, over 972665.86 frames.], batch size: 25, lr: 4.56e-04
+2022-05-04 21:51:47,216 INFO [train.py:715] (3/8) Epoch 4, batch 13650, loss[loss=0.1461, simple_loss=0.2221, pruned_loss=0.03507, over 4875.00 frames.], tot_loss[loss=0.157, simple_loss=0.2262, pruned_loss=0.04386, over 973814.50 frames.], batch size: 16, lr: 4.56e-04
+2022-05-04 21:52:26,532 INFO [train.py:715] (3/8) Epoch 4, batch 13700, loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03093, over 4799.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2254, pruned_loss=0.04315, over 972931.70 frames.], batch size: 24, lr: 4.56e-04
+2022-05-04 21:53:06,456 INFO [train.py:715] (3/8) Epoch 4, batch 13750, loss[loss=0.1622, simple_loss=0.2209, pruned_loss=0.05172, over 4840.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2247, pruned_loss=0.0424, over 972134.75 frames.], batch size: 32, lr: 4.56e-04
+2022-05-04 21:53:48,116 INFO [train.py:715] (3/8) Epoch 4, batch 13800, loss[loss=0.2265, simple_loss=0.2807, pruned_loss=0.08616, over 4974.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2263, pruned_loss=0.04344, over 972575.52 frames.], batch size: 15, lr: 4.56e-04
+2022-05-04 21:54:29,028 INFO [train.py:715] (3/8) Epoch 4, batch 13850, loss[loss=0.1201, simple_loss=0.1985, pruned_loss=0.02085, over 4863.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2258, pruned_loss=0.04347, over 972468.05 frames.], batch size: 12, lr: 4.56e-04
+2022-05-04 21:55:10,921 INFO [train.py:715] (3/8) Epoch 4, batch 13900, loss[loss=0.1522, simple_loss=0.2271, pruned_loss=0.03866, over 4835.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2257, pruned_loss=0.04363, over 973063.45 frames.], batch size: 13, lr: 4.56e-04
+2022-05-04 21:55:52,333 INFO [train.py:715] (3/8) Epoch 4, batch 13950, loss[loss=0.1773, simple_loss=0.2565, pruned_loss=0.04907, over 4905.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2263, pruned_loss=0.04423, over 973436.34 frames.], batch size: 19, lr: 4.56e-04
+2022-05-04 21:56:31,849 INFO [train.py:715] (3/8) Epoch 4, batch 14000, loss[loss=0.1647, simple_loss=0.2315, pruned_loss=0.04899, over 4845.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2266, pruned_loss=0.04401, over 972854.54 frames.], batch size: 30, lr: 4.56e-04
+2022-05-04 21:57:12,907 INFO [train.py:715] (3/8) Epoch 4, batch 14050, loss[loss=0.1648, simple_loss=0.2068, pruned_loss=0.06139, over 4786.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2259, pruned_loss=0.04373, over 973061.44 frames.], batch size: 12, lr: 4.55e-04
+2022-05-04 21:57:52,568 INFO [train.py:715] (3/8) Epoch 4, batch 14100, loss[loss=0.1253, simple_loss=0.2005, pruned_loss=0.02504, over 4979.00 frames.], tot_loss[loss=0.157, simple_loss=0.2261, pruned_loss=0.04397, over 971978.99 frames.], batch size: 24, lr: 4.55e-04
+2022-05-04 21:58:32,931 INFO [train.py:715] (3/8) Epoch 4, batch 14150, loss[loss=0.1727, simple_loss=0.2508, pruned_loss=0.0473, over 4781.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2268, pruned_loss=0.0444, over 972179.77 frames.], batch size: 18, lr: 4.55e-04
+2022-05-04 21:59:12,289 INFO [train.py:715] (3/8) Epoch 4, batch 14200, loss[loss=0.1518, simple_loss=0.2236, pruned_loss=0.04002, over 4872.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2268, pruned_loss=0.04439, over 972439.59 frames.], batch size: 16, lr: 4.55e-04
+2022-05-04 21:59:51,983 INFO [train.py:715] (3/8) Epoch 4, batch 14250, loss[loss=0.1601, simple_loss=0.226, pruned_loss=0.0471, over 4766.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2255, pruned_loss=0.04357, over 972224.25 frames.], batch size: 17, lr: 4.55e-04
+2022-05-04 22:00:32,134 INFO [train.py:715] (3/8) Epoch 4, batch 14300, loss[loss=0.1665, simple_loss=0.2257, pruned_loss=0.0536, over 4882.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2246, pruned_loss=0.04293, over 972452.61 frames.], batch size: 32, lr: 4.55e-04
+2022-05-04 22:01:10,606 INFO [train.py:715] (3/8) Epoch 4, batch 14350, loss[loss=0.1535, simple_loss=0.2133, pruned_loss=0.04688, over 4684.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2251, pruned_loss=0.04278, over 972522.93 frames.], batch size: 15, lr: 4.55e-04
+2022-05-04 22:01:50,875 INFO [train.py:715] (3/8) Epoch 4, batch 14400, loss[loss=0.1406, simple_loss=0.2055, pruned_loss=0.03784, over 4850.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2248, pruned_loss=0.0428, over 972330.40 frames.], batch size: 32, lr: 4.55e-04
+2022-05-04 22:02:30,301 INFO [train.py:715] (3/8) Epoch 4, batch 14450, loss[loss=0.1775, simple_loss=0.2484, pruned_loss=0.05329, over 4776.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2255, pruned_loss=0.04332, over 973251.67 frames.], batch size: 18, lr: 4.55e-04
+2022-05-04 22:03:09,288 INFO [train.py:715] (3/8) Epoch 4, batch 14500, loss[loss=0.1336, simple_loss=0.205, pruned_loss=0.03108, over 4924.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2253, pruned_loss=0.043, over 973729.40 frames.], batch size: 21, lr: 4.55e-04
+2022-05-04 22:03:48,142 INFO [train.py:715] (3/8) Epoch 4, batch 14550, loss[loss=0.173, simple_loss=0.2397, pruned_loss=0.05315, over 4981.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2271, pruned_loss=0.04365, over 973668.34 frames.], batch size: 15, lr: 4.55e-04
+2022-05-04 22:04:27,645 INFO [train.py:715] (3/8) Epoch 4, batch 14600, loss[loss=0.119, simple_loss=0.1785, pruned_loss=0.0298, over 4789.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2262, pruned_loss=0.04348, over 973509.65 frames.], batch size: 12, lr: 4.55e-04
+2022-05-04 22:05:07,546 INFO [train.py:715] (3/8) Epoch 4, batch 14650, loss[loss=0.1593, simple_loss=0.2276, pruned_loss=0.04549, over 4815.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2272, pruned_loss=0.04404, over 973395.80 frames.], batch size: 26, lr: 4.55e-04
+2022-05-04 22:05:46,292 INFO [train.py:715] (3/8) Epoch 4, batch 14700, loss[loss=0.147, simple_loss=0.2133, pruned_loss=0.04035, over 4730.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2269, pruned_loss=0.04416, over 973539.85 frames.], batch size: 16, lr: 4.55e-04
+2022-05-04 22:06:26,142 INFO [train.py:715] (3/8) Epoch 4, batch 14750, loss[loss=0.1295, simple_loss=0.2022, pruned_loss=0.02843, over 4934.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2265, pruned_loss=0.04388, over 972918.37 frames.], batch size: 21, lr: 4.54e-04
+2022-05-04 22:07:06,149 INFO [train.py:715] (3/8) Epoch 4, batch 14800, loss[loss=0.1504, simple_loss=0.2249, pruned_loss=0.03794, over 4978.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2269, pruned_loss=0.04363, over 973136.55 frames.], batch size: 15, lr: 4.54e-04
+2022-05-04 22:07:51,026 INFO [train.py:715] (3/8) Epoch 4, batch 14850, loss[loss=0.1748, simple_loss=0.2381, pruned_loss=0.05572, over 4904.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2262, pruned_loss=0.04333, over 972793.56 frames.], batch size: 19, lr: 4.54e-04
+2022-05-04 22:08:31,251 INFO [train.py:715] (3/8) Epoch 4, batch 14900, loss[loss=0.1343, simple_loss=0.2105, pruned_loss=0.02905, over 4896.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2261, pruned_loss=0.0433, over 972536.42 frames.], batch size: 19, lr: 4.54e-04
+2022-05-04 22:09:11,335 INFO [train.py:715] (3/8) Epoch 4, batch 14950, loss[loss=0.1827, simple_loss=0.2517, pruned_loss=0.05687, over 4748.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2255, pruned_loss=0.04317, over 971638.40 frames.], batch size: 19, lr: 4.54e-04
+2022-05-04 22:09:51,667 INFO [train.py:715] (3/8) Epoch 4, batch 15000, loss[loss=0.1391, simple_loss=0.2183, pruned_loss=0.02989, over 4955.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2257, pruned_loss=0.04295, over 972062.95 frames.], batch size: 24, lr: 4.54e-04
+2022-05-04 22:09:51,668 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 22:10:32,003 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1122, simple_loss=0.1978, pruned_loss=0.01336, over 914524.00 frames.
+2022-05-04 22:11:12,734 INFO [train.py:715] (3/8) Epoch 4, batch 15050, loss[loss=0.1414, simple_loss=0.1989, pruned_loss=0.04194, over 4685.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2253, pruned_loss=0.04264, over 971426.58 frames.], batch size: 15, lr: 4.54e-04
+2022-05-04 22:11:52,176 INFO [train.py:715] (3/8) Epoch 4, batch 15100, loss[loss=0.1374, simple_loss=0.2122, pruned_loss=0.0313, over 4895.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2251, pruned_loss=0.04274, over 971575.96 frames.], batch size: 29, lr: 4.54e-04
+2022-05-04 22:12:32,072 INFO [train.py:715] (3/8) Epoch 4, batch 15150, loss[loss=0.1155, simple_loss=0.1894, pruned_loss=0.02075, over 4815.00 frames.], tot_loss[loss=0.1554, simple_loss=0.225, pruned_loss=0.04289, over 972110.23 frames.], batch size: 27, lr: 4.54e-04
+2022-05-04 22:13:12,027 INFO [train.py:715] (3/8) Epoch 4, batch 15200, loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02903, over 4806.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2248, pruned_loss=0.04312, over 972044.96 frames.], batch size: 26, lr: 4.54e-04
+2022-05-04 22:13:51,745 INFO [train.py:715] (3/8) Epoch 4, batch 15250, loss[loss=0.1469, simple_loss=0.2174, pruned_loss=0.03822, over 4943.00 frames.], tot_loss[loss=0.156, simple_loss=0.2255, pruned_loss=0.04325, over 972005.07 frames.], batch size: 29, lr: 4.54e-04
+2022-05-04 22:14:31,959 INFO [train.py:715] (3/8) Epoch 4, batch 15300, loss[loss=0.1573, simple_loss=0.2392, pruned_loss=0.03768, over 4891.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2263, pruned_loss=0.04353, over 972868.37 frames.], batch size: 19, lr: 4.54e-04
+2022-05-04 22:15:12,421 INFO [train.py:715] (3/8) Epoch 4, batch 15350, loss[loss=0.1501, simple_loss=0.217, pruned_loss=0.04162, over 4972.00 frames.], tot_loss[loss=0.1565, simple_loss=0.226, pruned_loss=0.04352, over 972958.44 frames.], batch size: 31, lr: 4.54e-04
+2022-05-04 22:15:52,257 INFO [train.py:715] (3/8) Epoch 4, batch 15400, loss[loss=0.1313, simple_loss=0.2161, pruned_loss=0.02324, over 4956.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2259, pruned_loss=0.0438, over 971561.42 frames.], batch size: 24, lr: 4.53e-04
+2022-05-04 22:16:32,479 INFO [train.py:715] (3/8) Epoch 4, batch 15450, loss[loss=0.1653, simple_loss=0.2253, pruned_loss=0.05263, over 4688.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2257, pruned_loss=0.04368, over 971033.07 frames.], batch size: 15, lr: 4.53e-04
+2022-05-04 22:17:12,932 INFO [train.py:715] (3/8) Epoch 4, batch 15500, loss[loss=0.1671, simple_loss=0.2412, pruned_loss=0.04647, over 4915.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2256, pruned_loss=0.04334, over 970689.40 frames.], batch size: 18, lr: 4.53e-04
+2022-05-04 22:17:53,285 INFO [train.py:715] (3/8) Epoch 4, batch 15550, loss[loss=0.1535, simple_loss=0.2166, pruned_loss=0.04518, over 4849.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2257, pruned_loss=0.04368, over 971339.55 frames.], batch size: 13, lr: 4.53e-04
+2022-05-04 22:18:32,667 INFO [train.py:715] (3/8) Epoch 4, batch 15600, loss[loss=0.1882, simple_loss=0.2522, pruned_loss=0.06207, over 4821.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2254, pruned_loss=0.04368, over 971282.55 frames.], batch size: 26, lr: 4.53e-04
+2022-05-04 22:19:13,497 INFO [train.py:715] (3/8) Epoch 4, batch 15650, loss[loss=0.133, simple_loss=0.2081, pruned_loss=0.02895, over 4929.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2254, pruned_loss=0.04354, over 971846.21 frames.], batch size: 23, lr: 4.53e-04
+2022-05-04 22:19:53,087 INFO [train.py:715] (3/8) Epoch 4, batch 15700, loss[loss=0.1588, simple_loss=0.2311, pruned_loss=0.04325, over 4842.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2256, pruned_loss=0.04351, over 972174.73 frames.], batch size: 15, lr: 4.53e-04
+2022-05-04 22:20:33,263 INFO [train.py:715] (3/8) Epoch 4, batch 15750, loss[loss=0.1617, simple_loss=0.2287, pruned_loss=0.04741, over 4941.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2257, pruned_loss=0.04365, over 971402.44 frames.], batch size: 23, lr: 4.53e-04
+2022-05-04 22:21:12,810 INFO [train.py:715] (3/8) Epoch 4, batch 15800, loss[loss=0.1422, simple_loss=0.2191, pruned_loss=0.03271, over 4962.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2255, pruned_loss=0.04352, over 971777.30 frames.], batch size: 21, lr: 4.53e-04
+2022-05-04 22:21:53,778 INFO [train.py:715] (3/8) Epoch 4, batch 15850, loss[loss=0.1416, simple_loss=0.2134, pruned_loss=0.03483, over 4829.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2257, pruned_loss=0.04337, over 971827.97 frames.], batch size: 13, lr: 4.53e-04
+2022-05-04 22:22:34,972 INFO [train.py:715] (3/8) Epoch 4, batch 15900, loss[loss=0.1356, simple_loss=0.208, pruned_loss=0.03154, over 4969.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2258, pruned_loss=0.04336, over 971632.14 frames.], batch size: 15, lr: 4.53e-04
+2022-05-04 22:23:14,297 INFO [train.py:715] (3/8) Epoch 4, batch 15950, loss[loss=0.1419, simple_loss=0.2176, pruned_loss=0.0331, over 4815.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2259, pruned_loss=0.04354, over 971636.42 frames.], batch size: 26, lr: 4.53e-04
+2022-05-04 22:23:54,445 INFO [train.py:715] (3/8) Epoch 4, batch 16000, loss[loss=0.1612, simple_loss=0.2343, pruned_loss=0.04408, over 4797.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2261, pruned_loss=0.04341, over 971777.17 frames.], batch size: 18, lr: 4.53e-04
+2022-05-04 22:24:34,930 INFO [train.py:715] (3/8) Epoch 4, batch 16050, loss[loss=0.1541, simple_loss=0.2319, pruned_loss=0.03816, over 4874.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2263, pruned_loss=0.04347, over 972305.44 frames.], batch size: 32, lr: 4.53e-04
+2022-05-04 22:25:14,771 INFO [train.py:715] (3/8) Epoch 4, batch 16100, loss[loss=0.1399, simple_loss=0.207, pruned_loss=0.03635, over 4937.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2261, pruned_loss=0.04356, over 972594.32 frames.], batch size: 18, lr: 4.52e-04
+2022-05-04 22:25:54,144 INFO [train.py:715] (3/8) Epoch 4, batch 16150, loss[loss=0.1612, simple_loss=0.224, pruned_loss=0.04921, over 4885.00 frames.], tot_loss[loss=0.156, simple_loss=0.2254, pruned_loss=0.04328, over 972536.61 frames.], batch size: 39, lr: 4.52e-04
+2022-05-04 22:26:34,757 INFO [train.py:715] (3/8) Epoch 4, batch 16200, loss[loss=0.1388, simple_loss=0.2151, pruned_loss=0.03128, over 4881.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2263, pruned_loss=0.04362, over 971375.39 frames.], batch size: 22, lr: 4.52e-04
+2022-05-04 22:27:15,075 INFO [train.py:715] (3/8) Epoch 4, batch 16250, loss[loss=0.1825, simple_loss=0.246, pruned_loss=0.05948, over 4899.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2269, pruned_loss=0.04372, over 971851.09 frames.], batch size: 19, lr: 4.52e-04
+2022-05-04 22:27:54,411 INFO [train.py:715] (3/8) Epoch 4, batch 16300, loss[loss=0.1218, simple_loss=0.197, pruned_loss=0.02332, over 4841.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2273, pruned_loss=0.04417, over 972221.82 frames.], batch size: 12, lr: 4.52e-04
+2022-05-04 22:28:34,989 INFO [train.py:715] (3/8) Epoch 4, batch 16350, loss[loss=0.1209, simple_loss=0.1901, pruned_loss=0.02589, over 4814.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2276, pruned_loss=0.04408, over 971938.39 frames.], batch size: 13, lr: 4.52e-04
+2022-05-04 22:29:15,664 INFO [train.py:715] (3/8) Epoch 4, batch 16400, loss[loss=0.1536, simple_loss=0.2259, pruned_loss=0.04063, over 4917.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2286, pruned_loss=0.04451, over 972647.63 frames.], batch size: 19, lr: 4.52e-04
+2022-05-04 22:29:56,020 INFO [train.py:715] (3/8) Epoch 4, batch 16450, loss[loss=0.1502, simple_loss=0.2282, pruned_loss=0.03612, over 4757.00 frames.], tot_loss[loss=0.159, simple_loss=0.2285, pruned_loss=0.04477, over 972689.28 frames.], batch size: 19, lr: 4.52e-04
+2022-05-04 22:30:35,457 INFO [train.py:715] (3/8) Epoch 4, batch 16500, loss[loss=0.1308, simple_loss=0.2038, pruned_loss=0.02885, over 4803.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2271, pruned_loss=0.0439, over 972126.05 frames.], batch size: 25, lr: 4.52e-04
+2022-05-04 22:31:15,348 INFO [train.py:715] (3/8) Epoch 4, batch 16550, loss[loss=0.1776, simple_loss=0.2403, pruned_loss=0.05751, over 4965.00 frames.], tot_loss[loss=0.157, simple_loss=0.2268, pruned_loss=0.04357, over 971657.54 frames.], batch size: 14, lr: 4.52e-04
+2022-05-04 22:31:55,173 INFO [train.py:715] (3/8) Epoch 4, batch 16600, loss[loss=0.149, simple_loss=0.2161, pruned_loss=0.04098, over 4807.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2258, pruned_loss=0.04325, over 971932.38 frames.], batch size: 25, lr: 4.52e-04
+2022-05-04 22:32:33,992 INFO [train.py:715] (3/8) Epoch 4, batch 16650, loss[loss=0.1194, simple_loss=0.1856, pruned_loss=0.02658, over 4991.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2241, pruned_loss=0.04218, over 972714.04 frames.], batch size: 16, lr: 4.52e-04
+2022-05-04 22:33:12,849 INFO [train.py:715] (3/8) Epoch 4, batch 16700, loss[loss=0.1643, simple_loss=0.2452, pruned_loss=0.04173, over 4844.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2249, pruned_loss=0.04271, over 972427.75 frames.], batch size: 30, lr: 4.52e-04
+2022-05-04 22:33:52,193 INFO [train.py:715] (3/8) Epoch 4, batch 16750, loss[loss=0.1793, simple_loss=0.249, pruned_loss=0.05481, over 4879.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2256, pruned_loss=0.04342, over 972287.29 frames.], batch size: 22, lr: 4.52e-04
+2022-05-04 22:34:31,639 INFO [train.py:715] (3/8) Epoch 4, batch 16800, loss[loss=0.161, simple_loss=0.2282, pruned_loss=0.04692, over 4982.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2261, pruned_loss=0.0434, over 972335.70 frames.], batch size: 15, lr: 4.51e-04
+2022-05-04 22:35:10,402 INFO [train.py:715] (3/8) Epoch 4, batch 16850, loss[loss=0.1747, simple_loss=0.2426, pruned_loss=0.05336, over 4972.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.04382, over 971757.56 frames.], batch size: 15, lr: 4.51e-04
+2022-05-04 22:35:50,737 INFO [train.py:715] (3/8) Epoch 4, batch 16900, loss[loss=0.1609, simple_loss=0.2254, pruned_loss=0.04813, over 4894.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2282, pruned_loss=0.04479, over 972254.54 frames.], batch size: 17, lr: 4.51e-04
+2022-05-04 22:36:31,088 INFO [train.py:715] (3/8) Epoch 4, batch 16950, loss[loss=0.1655, simple_loss=0.232, pruned_loss=0.04945, over 4850.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2279, pruned_loss=0.04443, over 972311.06 frames.], batch size: 32, lr: 4.51e-04
+2022-05-04 22:37:10,626 INFO [train.py:715] (3/8) Epoch 4, batch 17000, loss[loss=0.1737, simple_loss=0.2248, pruned_loss=0.06127, over 4988.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2276, pruned_loss=0.0445, over 971974.87 frames.], batch size: 14, lr: 4.51e-04
+2022-05-04 22:37:50,455 INFO [train.py:715] (3/8) Epoch 4, batch 17050, loss[loss=0.1317, simple_loss=0.2046, pruned_loss=0.02947, over 4968.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2274, pruned_loss=0.04446, over 971789.31 frames.], batch size: 24, lr: 4.51e-04
+2022-05-04 22:38:30,859 INFO [train.py:715] (3/8) Epoch 4, batch 17100, loss[loss=0.1408, simple_loss=0.2153, pruned_loss=0.0331, over 4758.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2272, pruned_loss=0.04428, over 972330.28 frames.], batch size: 19, lr: 4.51e-04
+2022-05-04 22:39:10,963 INFO [train.py:715] (3/8) Epoch 4, batch 17150, loss[loss=0.1496, simple_loss=0.2146, pruned_loss=0.04233, over 4768.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2264, pruned_loss=0.04393, over 972124.21 frames.], batch size: 12, lr: 4.51e-04
+2022-05-04 22:39:50,101 INFO [train.py:715] (3/8) Epoch 4, batch 17200, loss[loss=0.1551, simple_loss=0.2239, pruned_loss=0.04317, over 4949.00 frames.], tot_loss[loss=0.157, simple_loss=0.2266, pruned_loss=0.04365, over 972186.55 frames.], batch size: 35, lr: 4.51e-04
+2022-05-04 22:40:30,247 INFO [train.py:715] (3/8) Epoch 4, batch 17250, loss[loss=0.1367, simple_loss=0.2043, pruned_loss=0.03452, over 4783.00 frames.], tot_loss[loss=0.1565, simple_loss=0.226, pruned_loss=0.04351, over 972346.87 frames.], batch size: 12, lr: 4.51e-04
+2022-05-04 22:41:10,197 INFO [train.py:715] (3/8) Epoch 4, batch 17300, loss[loss=0.1916, simple_loss=0.2462, pruned_loss=0.06855, over 4752.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2255, pruned_loss=0.0428, over 972002.89 frames.], batch size: 19, lr: 4.51e-04
+2022-05-04 22:41:49,927 INFO [train.py:715] (3/8) Epoch 4, batch 17350, loss[loss=0.1602, simple_loss=0.2365, pruned_loss=0.04198, over 4813.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2253, pruned_loss=0.04283, over 972312.07 frames.], batch size: 26, lr: 4.51e-04
+2022-05-04 22:42:29,447 INFO [train.py:715] (3/8) Epoch 4, batch 17400, loss[loss=0.1516, simple_loss=0.2232, pruned_loss=0.04003, over 4969.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2253, pruned_loss=0.04224, over 972688.12 frames.], batch size: 24, lr: 4.51e-04
+2022-05-04 22:43:09,756 INFO [train.py:715] (3/8) Epoch 4, batch 17450, loss[loss=0.1416, simple_loss=0.2126, pruned_loss=0.03529, over 4884.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2248, pruned_loss=0.04213, over 972260.79 frames.], batch size: 22, lr: 4.51e-04
+2022-05-04 22:43:50,029 INFO [train.py:715] (3/8) Epoch 4, batch 17500, loss[loss=0.1348, simple_loss=0.2046, pruned_loss=0.03257, over 4789.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2249, pruned_loss=0.0422, over 972059.81 frames.], batch size: 24, lr: 4.50e-04
+2022-05-04 22:44:29,246 INFO [train.py:715] (3/8) Epoch 4, batch 17550, loss[loss=0.1477, simple_loss=0.2197, pruned_loss=0.03786, over 4928.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2259, pruned_loss=0.04288, over 972881.53 frames.], batch size: 21, lr: 4.50e-04
+2022-05-04 22:45:09,114 INFO [train.py:715] (3/8) Epoch 4, batch 17600, loss[loss=0.1514, simple_loss=0.2134, pruned_loss=0.04471, over 4908.00 frames.], tot_loss[loss=0.156, simple_loss=0.2257, pruned_loss=0.04311, over 972674.16 frames.], batch size: 23, lr: 4.50e-04
+2022-05-04 22:45:49,513 INFO [train.py:715] (3/8) Epoch 4, batch 17650, loss[loss=0.1308, simple_loss=0.1974, pruned_loss=0.03211, over 4982.00 frames.], tot_loss[loss=0.157, simple_loss=0.2261, pruned_loss=0.0439, over 972735.79 frames.], batch size: 15, lr: 4.50e-04
+2022-05-04 22:46:29,574 INFO [train.py:715] (3/8) Epoch 4, batch 17700, loss[loss=0.1474, simple_loss=0.206, pruned_loss=0.04437, over 4921.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2264, pruned_loss=0.04415, over 973360.06 frames.], batch size: 18, lr: 4.50e-04
+2022-05-04 22:47:09,164 INFO [train.py:715] (3/8) Epoch 4, batch 17750, loss[loss=0.1685, simple_loss=0.2318, pruned_loss=0.05256, over 4903.00 frames.], tot_loss[loss=0.157, simple_loss=0.2262, pruned_loss=0.04389, over 973397.70 frames.], batch size: 22, lr: 4.50e-04
+2022-05-04 22:47:49,260 INFO [train.py:715] (3/8) Epoch 4, batch 17800, loss[loss=0.1522, simple_loss=0.2284, pruned_loss=0.038, over 4822.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2263, pruned_loss=0.04364, over 973276.31 frames.], batch size: 15, lr: 4.50e-04
+2022-05-04 22:48:29,930 INFO [train.py:715] (3/8) Epoch 4, batch 17850, loss[loss=0.1761, simple_loss=0.2486, pruned_loss=0.05183, over 4917.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2264, pruned_loss=0.04347, over 972911.45 frames.], batch size: 17, lr: 4.50e-04
+2022-05-04 22:49:09,027 INFO [train.py:715] (3/8) Epoch 4, batch 17900, loss[loss=0.1658, simple_loss=0.2172, pruned_loss=0.05716, over 4730.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2272, pruned_loss=0.04383, over 972969.37 frames.], batch size: 12, lr: 4.50e-04
+2022-05-04 22:49:49,027 INFO [train.py:715] (3/8) Epoch 4, batch 17950, loss[loss=0.1447, simple_loss=0.1991, pruned_loss=0.04518, over 4840.00 frames.], tot_loss[loss=0.1576, simple_loss=0.227, pruned_loss=0.04411, over 972822.94 frames.], batch size: 12, lr: 4.50e-04
+2022-05-04 22:50:29,186 INFO [train.py:715] (3/8) Epoch 4, batch 18000, loss[loss=0.1457, simple_loss=0.2222, pruned_loss=0.03456, over 4967.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2276, pruned_loss=0.04395, over 973084.04 frames.], batch size: 15, lr: 4.50e-04
+2022-05-04 22:50:29,187 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 22:50:38,823 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1119, simple_loss=0.1976, pruned_loss=0.01313, over 914524.00 frames.
+2022-05-04 22:51:19,285 INFO [train.py:715] (3/8) Epoch 4, batch 18050, loss[loss=0.1392, simple_loss=0.2075, pruned_loss=0.03546, over 4967.00 frames.], tot_loss[loss=0.1572, simple_loss=0.227, pruned_loss=0.04369, over 972176.24 frames.], batch size: 35, lr: 4.50e-04
+2022-05-04 22:51:59,526 INFO [train.py:715] (3/8) Epoch 4, batch 18100, loss[loss=0.161, simple_loss=0.226, pruned_loss=0.04796, over 4969.00 frames.], tot_loss[loss=0.158, simple_loss=0.2278, pruned_loss=0.0441, over 972156.21 frames.], batch size: 35, lr: 4.50e-04
+2022-05-04 22:52:39,097 INFO [train.py:715] (3/8) Epoch 4, batch 18150, loss[loss=0.1338, simple_loss=0.206, pruned_loss=0.03085, over 4949.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2279, pruned_loss=0.04424, over 971768.38 frames.], batch size: 21, lr: 4.50e-04
+2022-05-04 22:53:19,406 INFO [train.py:715] (3/8) Epoch 4, batch 18200, loss[loss=0.1802, simple_loss=0.244, pruned_loss=0.0582, over 4855.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2278, pruned_loss=0.0446, over 972033.58 frames.], batch size: 15, lr: 4.49e-04
+2022-05-04 22:53:59,871 INFO [train.py:715] (3/8) Epoch 4, batch 18250, loss[loss=0.1819, simple_loss=0.2428, pruned_loss=0.06046, over 4985.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2276, pruned_loss=0.04445, over 971908.60 frames.], batch size: 31, lr: 4.49e-04
+2022-05-04 22:54:39,571 INFO [train.py:715] (3/8) Epoch 4, batch 18300, loss[loss=0.1715, simple_loss=0.2257, pruned_loss=0.0587, over 4973.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2276, pruned_loss=0.04443, over 971758.90 frames.], batch size: 24, lr: 4.49e-04
+2022-05-04 22:55:19,283 INFO [train.py:715] (3/8) Epoch 4, batch 18350, loss[loss=0.174, simple_loss=0.2389, pruned_loss=0.05452, over 4716.00 frames.], tot_loss[loss=0.159, simple_loss=0.2281, pruned_loss=0.04494, over 971974.18 frames.], batch size: 15, lr: 4.49e-04
+2022-05-04 22:56:00,396 INFO [train.py:715] (3/8) Epoch 4, batch 18400, loss[loss=0.1272, simple_loss=0.2036, pruned_loss=0.02541, over 4864.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2264, pruned_loss=0.04412, over 971700.64 frames.], batch size: 22, lr: 4.49e-04
+2022-05-04 22:56:40,807 INFO [train.py:715] (3/8) Epoch 4, batch 18450, loss[loss=0.1583, simple_loss=0.2253, pruned_loss=0.04564, over 4766.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2264, pruned_loss=0.04437, over 970806.86 frames.], batch size: 14, lr: 4.49e-04
+2022-05-04 22:57:20,899 INFO [train.py:715] (3/8) Epoch 4, batch 18500, loss[loss=0.1358, simple_loss=0.1987, pruned_loss=0.03643, over 4896.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2262, pruned_loss=0.04412, over 970474.21 frames.], batch size: 19, lr: 4.49e-04
+2022-05-04 22:58:01,187 INFO [train.py:715] (3/8) Epoch 4, batch 18550, loss[loss=0.1496, simple_loss=0.2136, pruned_loss=0.04275, over 4793.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2275, pruned_loss=0.04488, over 969940.32 frames.], batch size: 12, lr: 4.49e-04
+2022-05-04 22:58:41,893 INFO [train.py:715] (3/8) Epoch 4, batch 18600, loss[loss=0.1372, simple_loss=0.2145, pruned_loss=0.02998, over 4705.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2276, pruned_loss=0.04547, over 969754.80 frames.], batch size: 15, lr: 4.49e-04
+2022-05-04 22:59:21,460 INFO [train.py:715] (3/8) Epoch 4, batch 18650, loss[loss=0.1718, simple_loss=0.2349, pruned_loss=0.05429, over 4775.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2275, pruned_loss=0.04511, over 970899.19 frames.], batch size: 17, lr: 4.49e-04
+2022-05-04 23:00:01,609 INFO [train.py:715] (3/8) Epoch 4, batch 18700, loss[loss=0.15, simple_loss=0.2202, pruned_loss=0.03991, over 4981.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2277, pruned_loss=0.04505, over 971231.51 frames.], batch size: 25, lr: 4.49e-04
+2022-05-04 23:00:42,466 INFO [train.py:715] (3/8) Epoch 4, batch 18750, loss[loss=0.1494, simple_loss=0.2228, pruned_loss=0.03804, over 4819.00 frames.], tot_loss[loss=0.1572, simple_loss=0.226, pruned_loss=0.04416, over 971114.81 frames.], batch size: 27, lr: 4.49e-04
+2022-05-04 23:01:21,944 INFO [train.py:715] (3/8) Epoch 4, batch 18800, loss[loss=0.121, simple_loss=0.1895, pruned_loss=0.02631, over 4800.00 frames.], tot_loss[loss=0.1571, simple_loss=0.226, pruned_loss=0.04406, over 971236.22 frames.], batch size: 12, lr: 4.49e-04
+2022-05-04 23:02:02,025 INFO [train.py:715] (3/8) Epoch 4, batch 18850, loss[loss=0.203, simple_loss=0.2614, pruned_loss=0.0723, over 4961.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2265, pruned_loss=0.04456, over 971996.76 frames.], batch size: 39, lr: 4.49e-04
+2022-05-04 23:02:42,435 INFO [train.py:715] (3/8) Epoch 4, batch 18900, loss[loss=0.1319, simple_loss=0.2162, pruned_loss=0.02385, over 4732.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2267, pruned_loss=0.04431, over 972843.96 frames.], batch size: 16, lr: 4.48e-04
+2022-05-04 23:03:22,747 INFO [train.py:715] (3/8) Epoch 4, batch 18950, loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.0286, over 4763.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2258, pruned_loss=0.04351, over 972217.68 frames.], batch size: 12, lr: 4.48e-04
+2022-05-04 23:04:01,995 INFO [train.py:715] (3/8) Epoch 4, batch 19000, loss[loss=0.1528, simple_loss=0.2272, pruned_loss=0.03919, over 4954.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2259, pruned_loss=0.04343, over 972050.72 frames.], batch size: 39, lr: 4.48e-04
+2022-05-04 23:04:42,501 INFO [train.py:715] (3/8) Epoch 4, batch 19050, loss[loss=0.1506, simple_loss=0.2144, pruned_loss=0.04335, over 4966.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04315, over 972342.29 frames.], batch size: 35, lr: 4.48e-04
+2022-05-04 23:05:23,219 INFO [train.py:715] (3/8) Epoch 4, batch 19100, loss[loss=0.1483, simple_loss=0.2161, pruned_loss=0.04025, over 4888.00 frames.], tot_loss[loss=0.155, simple_loss=0.2249, pruned_loss=0.04261, over 971425.91 frames.], batch size: 19, lr: 4.48e-04
+2022-05-04 23:06:03,173 INFO [train.py:715] (3/8) Epoch 4, batch 19150, loss[loss=0.1672, simple_loss=0.2256, pruned_loss=0.05441, over 4864.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2253, pruned_loss=0.04301, over 971470.85 frames.], batch size: 13, lr: 4.48e-04
+2022-05-04 23:06:43,533 INFO [train.py:715] (3/8) Epoch 4, batch 19200, loss[loss=0.1616, simple_loss=0.2347, pruned_loss=0.04421, over 4939.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2257, pruned_loss=0.0432, over 971566.68 frames.], batch size: 21, lr: 4.48e-04
+2022-05-04 23:07:24,308 INFO [train.py:715] (3/8) Epoch 4, batch 19250, loss[loss=0.1511, simple_loss=0.2286, pruned_loss=0.03679, over 4896.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2259, pruned_loss=0.04319, over 971589.35 frames.], batch size: 19, lr: 4.48e-04
+2022-05-04 23:08:04,910 INFO [train.py:715] (3/8) Epoch 4, batch 19300, loss[loss=0.1388, simple_loss=0.2092, pruned_loss=0.03418, over 4837.00 frames.], tot_loss[loss=0.1552, simple_loss=0.225, pruned_loss=0.04268, over 970974.34 frames.], batch size: 30, lr: 4.48e-04
+2022-05-04 23:08:44,084 INFO [train.py:715] (3/8) Epoch 4, batch 19350, loss[loss=0.1422, simple_loss=0.2122, pruned_loss=0.03605, over 4900.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2262, pruned_loss=0.04325, over 970791.94 frames.], batch size: 22, lr: 4.48e-04
+2022-05-04 23:09:24,774 INFO [train.py:715] (3/8) Epoch 4, batch 19400, loss[loss=0.1536, simple_loss=0.227, pruned_loss=0.04006, over 4878.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2266, pruned_loss=0.04324, over 971088.31 frames.], batch size: 22, lr: 4.48e-04
+2022-05-04 23:10:06,276 INFO [train.py:715] (3/8) Epoch 4, batch 19450, loss[loss=0.1789, simple_loss=0.2446, pruned_loss=0.05657, over 4834.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2272, pruned_loss=0.04361, over 971089.82 frames.], batch size: 30, lr: 4.48e-04
+2022-05-04 23:10:47,440 INFO [train.py:715] (3/8) Epoch 4, batch 19500, loss[loss=0.155, simple_loss=0.2274, pruned_loss=0.04132, over 4915.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2272, pruned_loss=0.04359, over 971667.28 frames.], batch size: 17, lr: 4.48e-04
+2022-05-04 23:11:27,085 INFO [train.py:715] (3/8) Epoch 4, batch 19550, loss[loss=0.1724, simple_loss=0.2333, pruned_loss=0.05573, over 4968.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2276, pruned_loss=0.04402, over 972526.09 frames.], batch size: 35, lr: 4.48e-04
+2022-05-04 23:12:07,480 INFO [train.py:715] (3/8) Epoch 4, batch 19600, loss[loss=0.1546, simple_loss=0.2195, pruned_loss=0.04487, over 4942.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2268, pruned_loss=0.04369, over 971984.00 frames.], batch size: 35, lr: 4.47e-04
+2022-05-04 23:12:47,699 INFO [train.py:715] (3/8) Epoch 4, batch 19650, loss[loss=0.1714, simple_loss=0.2448, pruned_loss=0.04895, over 4983.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2274, pruned_loss=0.04413, over 972492.48 frames.], batch size: 20, lr: 4.47e-04
+2022-05-04 23:13:26,467 INFO [train.py:715] (3/8) Epoch 4, batch 19700, loss[loss=0.1308, simple_loss=0.197, pruned_loss=0.03233, over 4807.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.0439, over 972020.65 frames.], batch size: 21, lr: 4.47e-04
+2022-05-04 23:14:07,146 INFO [train.py:715] (3/8) Epoch 4, batch 19750, loss[loss=0.1581, simple_loss=0.2314, pruned_loss=0.04245, over 4912.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2261, pruned_loss=0.04351, over 971575.92 frames.], batch size: 19, lr: 4.47e-04
+2022-05-04 23:14:47,971 INFO [train.py:715] (3/8) Epoch 4, batch 19800, loss[loss=0.1561, simple_loss=0.2299, pruned_loss=0.04112, over 4748.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2251, pruned_loss=0.04284, over 972343.57 frames.], batch size: 16, lr: 4.47e-04
+2022-05-04 23:15:27,714 INFO [train.py:715] (3/8) Epoch 4, batch 19850, loss[loss=0.1526, simple_loss=0.2198, pruned_loss=0.04272, over 4948.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2248, pruned_loss=0.04287, over 972635.25 frames.], batch size: 35, lr: 4.47e-04
+2022-05-04 23:16:07,786 INFO [train.py:715] (3/8) Epoch 4, batch 19900, loss[loss=0.1544, simple_loss=0.2184, pruned_loss=0.04517, over 4840.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2247, pruned_loss=0.04279, over 971731.93 frames.], batch size: 30, lr: 4.47e-04
+2022-05-04 23:16:47,903 INFO [train.py:715] (3/8) Epoch 4, batch 19950, loss[loss=0.1651, simple_loss=0.2367, pruned_loss=0.04677, over 4877.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2249, pruned_loss=0.04268, over 971865.86 frames.], batch size: 39, lr: 4.47e-04
+2022-05-04 23:17:28,071 INFO [train.py:715] (3/8) Epoch 4, batch 20000, loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02945, over 4926.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2242, pruned_loss=0.0423, over 971511.25 frames.], batch size: 23, lr: 4.47e-04
+2022-05-04 23:18:06,771 INFO [train.py:715] (3/8) Epoch 4, batch 20050, loss[loss=0.163, simple_loss=0.2381, pruned_loss=0.04391, over 4895.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2232, pruned_loss=0.04188, over 972108.76 frames.], batch size: 19, lr: 4.47e-04
+2022-05-04 23:18:46,563 INFO [train.py:715] (3/8) Epoch 4, batch 20100, loss[loss=0.2014, simple_loss=0.2718, pruned_loss=0.06553, over 4791.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2251, pruned_loss=0.04291, over 971668.14 frames.], batch size: 14, lr: 4.47e-04
+2022-05-04 23:19:26,629 INFO [train.py:715] (3/8) Epoch 4, batch 20150, loss[loss=0.1369, simple_loss=0.2083, pruned_loss=0.03277, over 4839.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2249, pruned_loss=0.04269, over 971473.83 frames.], batch size: 20, lr: 4.47e-04
+2022-05-04 23:20:06,051 INFO [train.py:715] (3/8) Epoch 4, batch 20200, loss[loss=0.1717, simple_loss=0.2336, pruned_loss=0.05485, over 4972.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2256, pruned_loss=0.04311, over 972023.37 frames.], batch size: 39, lr: 4.47e-04
+2022-05-04 23:20:45,796 INFO [train.py:715] (3/8) Epoch 4, batch 20250, loss[loss=0.1387, simple_loss=0.2021, pruned_loss=0.03769, over 4942.00 frames.], tot_loss[loss=0.156, simple_loss=0.2258, pruned_loss=0.04306, over 971793.79 frames.], batch size: 21, lr: 4.47e-04
+2022-05-04 23:21:26,115 INFO [train.py:715] (3/8) Epoch 4, batch 20300, loss[loss=0.2016, simple_loss=0.2561, pruned_loss=0.07356, over 4848.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2252, pruned_loss=0.04265, over 972178.36 frames.], batch size: 15, lr: 4.46e-04
+2022-05-04 23:22:06,212 INFO [train.py:715] (3/8) Epoch 4, batch 20350, loss[loss=0.1691, simple_loss=0.2331, pruned_loss=0.05259, over 4839.00 frames.], tot_loss[loss=0.155, simple_loss=0.225, pruned_loss=0.04253, over 972210.74 frames.], batch size: 30, lr: 4.46e-04
+2022-05-04 23:22:45,052 INFO [train.py:715] (3/8) Epoch 4, batch 20400, loss[loss=0.1856, simple_loss=0.2545, pruned_loss=0.05832, over 4851.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2261, pruned_loss=0.04334, over 972857.54 frames.], batch size: 32, lr: 4.46e-04
+2022-05-04 23:23:25,037 INFO [train.py:715] (3/8) Epoch 4, batch 20450, loss[loss=0.1499, simple_loss=0.2159, pruned_loss=0.04193, over 4702.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04309, over 972725.26 frames.], batch size: 15, lr: 4.46e-04
+2022-05-04 23:24:04,961 INFO [train.py:715] (3/8) Epoch 4, batch 20500, loss[loss=0.1504, simple_loss=0.2256, pruned_loss=0.03761, over 4953.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2251, pruned_loss=0.04262, over 973158.80 frames.], batch size: 29, lr: 4.46e-04
+2022-05-04 23:24:44,754 INFO [train.py:715] (3/8) Epoch 4, batch 20550, loss[loss=0.1356, simple_loss=0.2007, pruned_loss=0.03527, over 4818.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2249, pruned_loss=0.04217, over 973473.12 frames.], batch size: 15, lr: 4.46e-04
+2022-05-04 23:25:23,723 INFO [train.py:715] (3/8) Epoch 4, batch 20600, loss[loss=0.1662, simple_loss=0.2229, pruned_loss=0.05472, over 4782.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2259, pruned_loss=0.04284, over 972832.51 frames.], batch size: 14, lr: 4.46e-04
+2022-05-04 23:26:03,659 INFO [train.py:715] (3/8) Epoch 4, batch 20650, loss[loss=0.1433, simple_loss=0.2179, pruned_loss=0.03433, over 4931.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2269, pruned_loss=0.04343, over 973155.63 frames.], batch size: 23, lr: 4.46e-04
+2022-05-04 23:26:44,157 INFO [train.py:715] (3/8) Epoch 4, batch 20700, loss[loss=0.1355, simple_loss=0.1934, pruned_loss=0.03881, over 4904.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2265, pruned_loss=0.04353, over 973268.26 frames.], batch size: 17, lr: 4.46e-04
+2022-05-04 23:27:22,805 INFO [train.py:715] (3/8) Epoch 4, batch 20750, loss[loss=0.1421, simple_loss=0.2122, pruned_loss=0.03603, over 4985.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2264, pruned_loss=0.04304, over 973339.95 frames.], batch size: 25, lr: 4.46e-04
+2022-05-04 23:28:04,818 INFO [train.py:715] (3/8) Epoch 4, batch 20800, loss[loss=0.1413, simple_loss=0.2198, pruned_loss=0.03139, over 4761.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2274, pruned_loss=0.04345, over 972715.31 frames.], batch size: 16, lr: 4.46e-04
+2022-05-04 23:28:44,605 INFO [train.py:715] (3/8) Epoch 4, batch 20850, loss[loss=0.1606, simple_loss=0.2322, pruned_loss=0.04445, over 4868.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2261, pruned_loss=0.04261, over 972703.58 frames.], batch size: 39, lr: 4.46e-04
+2022-05-04 23:29:24,438 INFO [train.py:715] (3/8) Epoch 4, batch 20900, loss[loss=0.1374, simple_loss=0.2036, pruned_loss=0.03564, over 4941.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2267, pruned_loss=0.04283, over 971496.91 frames.], batch size: 29, lr: 4.46e-04
+2022-05-04 23:30:03,474 INFO [train.py:715] (3/8) Epoch 4, batch 20950, loss[loss=0.1303, simple_loss=0.209, pruned_loss=0.02578, over 4819.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2264, pruned_loss=0.04271, over 972029.99 frames.], batch size: 15, lr: 4.46e-04
+2022-05-04 23:30:43,449 INFO [train.py:715] (3/8) Epoch 4, batch 21000, loss[loss=0.1473, simple_loss=0.2175, pruned_loss=0.03855, over 4854.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2265, pruned_loss=0.04298, over 972492.19 frames.], batch size: 20, lr: 4.46e-04
+2022-05-04 23:30:43,449 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-04 23:30:52,894 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1116, simple_loss=0.1973, pruned_loss=0.01293, over 914524.00 frames.
+2022-05-04 23:31:33,190 INFO [train.py:715] (3/8) Epoch 4, batch 21050, loss[loss=0.1651, simple_loss=0.2425, pruned_loss=0.04392, over 4972.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2277, pruned_loss=0.04354, over 972394.92 frames.], batch size: 35, lr: 4.45e-04
+2022-05-04 23:32:12,981 INFO [train.py:715] (3/8) Epoch 4, batch 21100, loss[loss=0.1492, simple_loss=0.2129, pruned_loss=0.04273, over 4862.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2278, pruned_loss=0.04322, over 971759.06 frames.], batch size: 20, lr: 4.45e-04
+2022-05-04 23:32:52,576 INFO [train.py:715] (3/8) Epoch 4, batch 21150, loss[loss=0.1524, simple_loss=0.2202, pruned_loss=0.0423, over 4761.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2273, pruned_loss=0.04303, over 971233.10 frames.], batch size: 14, lr: 4.45e-04
+2022-05-04 23:33:32,161 INFO [train.py:715] (3/8) Epoch 4, batch 21200, loss[loss=0.175, simple_loss=0.2278, pruned_loss=0.0611, over 4751.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2263, pruned_loss=0.04264, over 971714.31 frames.], batch size: 16, lr: 4.45e-04
+2022-05-04 23:34:12,366 INFO [train.py:715] (3/8) Epoch 4, batch 21250, loss[loss=0.1713, simple_loss=0.228, pruned_loss=0.0573, over 4977.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2258, pruned_loss=0.04262, over 971999.67 frames.], batch size: 35, lr: 4.45e-04
+2022-05-04 23:34:51,186 INFO [train.py:715] (3/8) Epoch 4, batch 21300, loss[loss=0.1755, simple_loss=0.2428, pruned_loss=0.05407, over 4911.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2266, pruned_loss=0.04317, over 971873.71 frames.], batch size: 29, lr: 4.45e-04
+2022-05-04 23:35:30,242 INFO [train.py:715] (3/8) Epoch 4, batch 21350, loss[loss=0.1359, simple_loss=0.2059, pruned_loss=0.03293, over 4751.00 frames.], tot_loss[loss=0.1559, simple_loss=0.226, pruned_loss=0.04292, over 972132.62 frames.], batch size: 12, lr: 4.45e-04
+2022-05-04 23:36:09,892 INFO [train.py:715] (3/8) Epoch 4, batch 21400, loss[loss=0.1714, simple_loss=0.2461, pruned_loss=0.0483, over 4982.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2255, pruned_loss=0.04244, over 971642.48 frames.], batch size: 25, lr: 4.45e-04
+2022-05-04 23:36:49,456 INFO [train.py:715] (3/8) Epoch 4, batch 21450, loss[loss=0.1485, simple_loss=0.2234, pruned_loss=0.03683, over 4959.00 frames.], tot_loss[loss=0.156, simple_loss=0.2261, pruned_loss=0.04298, over 970775.29 frames.], batch size: 35, lr: 4.45e-04
+2022-05-04 23:37:28,646 INFO [train.py:715] (3/8) Epoch 4, batch 21500, loss[loss=0.1694, simple_loss=0.2339, pruned_loss=0.05246, over 4794.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2271, pruned_loss=0.04399, over 970257.45 frames.], batch size: 24, lr: 4.45e-04
+2022-05-04 23:38:08,475 INFO [train.py:715] (3/8) Epoch 4, batch 21550, loss[loss=0.1386, simple_loss=0.2132, pruned_loss=0.03195, over 4784.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2266, pruned_loss=0.04381, over 970260.05 frames.], batch size: 14, lr: 4.45e-04
+2022-05-04 23:38:48,859 INFO [train.py:715] (3/8) Epoch 4, batch 21600, loss[loss=0.1997, simple_loss=0.2625, pruned_loss=0.06843, over 4880.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2269, pruned_loss=0.04417, over 971000.62 frames.], batch size: 22, lr: 4.45e-04
+2022-05-04 23:39:28,099 INFO [train.py:715] (3/8) Epoch 4, batch 21650, loss[loss=0.1581, simple_loss=0.2326, pruned_loss=0.04182, over 4820.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2267, pruned_loss=0.04392, over 971673.42 frames.], batch size: 24, lr: 4.45e-04
+2022-05-04 23:40:08,351 INFO [train.py:715] (3/8) Epoch 4, batch 21700, loss[loss=0.1531, simple_loss=0.2229, pruned_loss=0.04161, over 4979.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2252, pruned_loss=0.04292, over 972272.75 frames.], batch size: 25, lr: 4.45e-04
+2022-05-04 23:40:49,363 INFO [train.py:715] (3/8) Epoch 4, batch 21750, loss[loss=0.1904, simple_loss=0.2579, pruned_loss=0.06143, over 4902.00 frames.], tot_loss[loss=0.1552, simple_loss=0.225, pruned_loss=0.04272, over 972581.97 frames.], batch size: 39, lr: 4.44e-04
+2022-05-04 23:41:29,016 INFO [train.py:715] (3/8) Epoch 4, batch 21800, loss[loss=0.1511, simple_loss=0.2184, pruned_loss=0.0419, over 4868.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2244, pruned_loss=0.04242, over 973141.41 frames.], batch size: 20, lr: 4.44e-04
+2022-05-04 23:42:08,603 INFO [train.py:715] (3/8) Epoch 4, batch 21850, loss[loss=0.1521, simple_loss=0.2171, pruned_loss=0.04361, over 4797.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2239, pruned_loss=0.04261, over 972617.67 frames.], batch size: 21, lr: 4.44e-04
+2022-05-04 23:42:48,651 INFO [train.py:715] (3/8) Epoch 4, batch 21900, loss[loss=0.1807, simple_loss=0.2426, pruned_loss=0.05936, over 4961.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2248, pruned_loss=0.04315, over 973340.92 frames.], batch size: 14, lr: 4.44e-04
+2022-05-04 23:43:29,092 INFO [train.py:715] (3/8) Epoch 4, batch 21950, loss[loss=0.1534, simple_loss=0.2248, pruned_loss=0.04097, over 4895.00 frames.], tot_loss[loss=0.155, simple_loss=0.2244, pruned_loss=0.04278, over 973690.45 frames.], batch size: 22, lr: 4.44e-04
+2022-05-04 23:44:08,294 INFO [train.py:715] (3/8) Epoch 4, batch 22000, loss[loss=0.1434, simple_loss=0.2175, pruned_loss=0.03466, over 4808.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2239, pruned_loss=0.04234, over 973177.75 frames.], batch size: 21, lr: 4.44e-04
+2022-05-04 23:44:48,081 INFO [train.py:715] (3/8) Epoch 4, batch 22050, loss[loss=0.1474, simple_loss=0.2194, pruned_loss=0.03772, over 4816.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2235, pruned_loss=0.04164, over 972017.93 frames.], batch size: 15, lr: 4.44e-04
+2022-05-04 23:45:28,543 INFO [train.py:715] (3/8) Epoch 4, batch 22100, loss[loss=0.176, simple_loss=0.2426, pruned_loss=0.05466, over 4972.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2255, pruned_loss=0.04296, over 971343.90 frames.], batch size: 15, lr: 4.44e-04
+2022-05-04 23:46:08,389 INFO [train.py:715] (3/8) Epoch 4, batch 22150, loss[loss=0.1495, simple_loss=0.218, pruned_loss=0.04049, over 4830.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2258, pruned_loss=0.04301, over 971235.23 frames.], batch size: 13, lr: 4.44e-04
+2022-05-04 23:46:47,296 INFO [train.py:715] (3/8) Epoch 4, batch 22200, loss[loss=0.149, simple_loss=0.2141, pruned_loss=0.04193, over 4934.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2264, pruned_loss=0.04287, over 971989.74 frames.], batch size: 29, lr: 4.44e-04
+2022-05-04 23:47:27,365 INFO [train.py:715] (3/8) Epoch 4, batch 22250, loss[loss=0.1764, simple_loss=0.2418, pruned_loss=0.05547, over 4766.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2264, pruned_loss=0.04293, over 971451.58 frames.], batch size: 19, lr: 4.44e-04
+2022-05-04 23:48:07,761 INFO [train.py:715] (3/8) Epoch 4, batch 22300, loss[loss=0.134, simple_loss=0.2051, pruned_loss=0.03151, over 4989.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2257, pruned_loss=0.04244, over 972426.97 frames.], batch size: 25, lr: 4.44e-04
+2022-05-04 23:48:46,517 INFO [train.py:715] (3/8) Epoch 4, batch 22350, loss[loss=0.1485, simple_loss=0.2256, pruned_loss=0.03568, over 4814.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2251, pruned_loss=0.04181, over 972189.04 frames.], batch size: 25, lr: 4.44e-04
+2022-05-04 23:49:25,542 INFO [train.py:715] (3/8) Epoch 4, batch 22400, loss[loss=0.1509, simple_loss=0.2192, pruned_loss=0.04126, over 4763.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2259, pruned_loss=0.04236, over 971251.23 frames.], batch size: 19, lr: 4.44e-04
+2022-05-04 23:50:06,129 INFO [train.py:715] (3/8) Epoch 4, batch 22450, loss[loss=0.1553, simple_loss=0.2331, pruned_loss=0.03882, over 4908.00 frames.], tot_loss[loss=0.155, simple_loss=0.2256, pruned_loss=0.0422, over 971560.53 frames.], batch size: 19, lr: 4.44e-04
+2022-05-04 23:50:45,317 INFO [train.py:715] (3/8) Epoch 4, batch 22500, loss[loss=0.1621, simple_loss=0.2332, pruned_loss=0.04547, over 4805.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2251, pruned_loss=0.04226, over 971460.41 frames.], batch size: 25, lr: 4.43e-04
+2022-05-04 23:51:24,260 INFO [train.py:715] (3/8) Epoch 4, batch 22550, loss[loss=0.1535, simple_loss=0.2283, pruned_loss=0.03936, over 4884.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2252, pruned_loss=0.04249, over 971788.91 frames.], batch size: 22, lr: 4.43e-04
+2022-05-04 23:52:04,196 INFO [train.py:715] (3/8) Epoch 4, batch 22600, loss[loss=0.1677, simple_loss=0.2232, pruned_loss=0.05605, over 4872.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2255, pruned_loss=0.04252, over 971783.29 frames.], batch size: 32, lr: 4.43e-04
+2022-05-04 23:52:44,025 INFO [train.py:715] (3/8) Epoch 4, batch 22650, loss[loss=0.1947, simple_loss=0.275, pruned_loss=0.05722, over 4822.00 frames.], tot_loss[loss=0.156, simple_loss=0.2263, pruned_loss=0.0429, over 973175.23 frames.], batch size: 26, lr: 4.43e-04
+2022-05-04 23:53:22,947 INFO [train.py:715] (3/8) Epoch 4, batch 22700, loss[loss=0.1649, simple_loss=0.2309, pruned_loss=0.04948, over 4954.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2254, pruned_loss=0.04291, over 973348.49 frames.], batch size: 35, lr: 4.43e-04
+2022-05-04 23:54:02,347 INFO [train.py:715] (3/8) Epoch 4, batch 22750, loss[loss=0.1651, simple_loss=0.234, pruned_loss=0.04811, over 4964.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2261, pruned_loss=0.04321, over 972933.01 frames.], batch size: 15, lr: 4.43e-04
+2022-05-04 23:54:42,047 INFO [train.py:715] (3/8) Epoch 4, batch 22800, loss[loss=0.1726, simple_loss=0.2558, pruned_loss=0.04474, over 4967.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2258, pruned_loss=0.0429, over 972209.96 frames.], batch size: 24, lr: 4.43e-04
+2022-05-04 23:55:21,169 INFO [train.py:715] (3/8) Epoch 4, batch 22850, loss[loss=0.1658, simple_loss=0.2258, pruned_loss=0.05293, over 4986.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2261, pruned_loss=0.04345, over 972968.89 frames.], batch size: 15, lr: 4.43e-04
+2022-05-04 23:55:59,903 INFO [train.py:715] (3/8) Epoch 4, batch 22900, loss[loss=0.1518, simple_loss=0.2302, pruned_loss=0.0367, over 4862.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2269, pruned_loss=0.0439, over 972629.98 frames.], batch size: 32, lr: 4.43e-04
+2022-05-04 23:56:39,567 INFO [train.py:715] (3/8) Epoch 4, batch 22950, loss[loss=0.1427, simple_loss=0.211, pruned_loss=0.03723, over 4908.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04405, over 971530.91 frames.], batch size: 19, lr: 4.43e-04
+2022-05-04 23:57:19,678 INFO [train.py:715] (3/8) Epoch 4, batch 23000, loss[loss=0.1422, simple_loss=0.2105, pruned_loss=0.037, over 4852.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2257, pruned_loss=0.0434, over 972085.44 frames.], batch size: 20, lr: 4.43e-04
+2022-05-04 23:57:58,016 INFO [train.py:715] (3/8) Epoch 4, batch 23050, loss[loss=0.1571, simple_loss=0.2154, pruned_loss=0.04944, over 4798.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2262, pruned_loss=0.04365, over 971779.83 frames.], batch size: 24, lr: 4.43e-04
+2022-05-04 23:58:37,638 INFO [train.py:715] (3/8) Epoch 4, batch 23100, loss[loss=0.1651, simple_loss=0.2319, pruned_loss=0.04912, over 4952.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04402, over 972159.56 frames.], batch size: 21, lr: 4.43e-04
+2022-05-04 23:59:18,005 INFO [train.py:715] (3/8) Epoch 4, batch 23150, loss[loss=0.1291, simple_loss=0.2004, pruned_loss=0.0289, over 4794.00 frames.], tot_loss[loss=0.1578, simple_loss=0.227, pruned_loss=0.04434, over 971894.12 frames.], batch size: 12, lr: 4.43e-04
+2022-05-04 23:59:57,817 INFO [train.py:715] (3/8) Epoch 4, batch 23200, loss[loss=0.1627, simple_loss=0.2255, pruned_loss=0.04991, over 4816.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2267, pruned_loss=0.04396, over 972320.07 frames.], batch size: 13, lr: 4.42e-04
+2022-05-05 00:00:36,520 INFO [train.py:715] (3/8) Epoch 4, batch 23250, loss[loss=0.1288, simple_loss=0.2016, pruned_loss=0.02797, over 4838.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2277, pruned_loss=0.04427, over 972391.50 frames.], batch size: 12, lr: 4.42e-04
+2022-05-05 00:01:16,402 INFO [train.py:715] (3/8) Epoch 4, batch 23300, loss[loss=0.1793, simple_loss=0.2426, pruned_loss=0.05802, over 4693.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2272, pruned_loss=0.04404, over 972038.60 frames.], batch size: 15, lr: 4.42e-04
+2022-05-05 00:01:56,704 INFO [train.py:715] (3/8) Epoch 4, batch 23350, loss[loss=0.1322, simple_loss=0.2028, pruned_loss=0.03082, over 4772.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2272, pruned_loss=0.04413, over 971352.72 frames.], batch size: 19, lr: 4.42e-04
+2022-05-05 00:02:35,079 INFO [train.py:715] (3/8) Epoch 4, batch 23400, loss[loss=0.1464, simple_loss=0.2037, pruned_loss=0.04455, over 4981.00 frames.], tot_loss[loss=0.1579, simple_loss=0.227, pruned_loss=0.04435, over 970841.60 frames.], batch size: 35, lr: 4.42e-04
+2022-05-05 00:03:14,413 INFO [train.py:715] (3/8) Epoch 4, batch 23450, loss[loss=0.1786, simple_loss=0.2468, pruned_loss=0.0552, over 4959.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2266, pruned_loss=0.04433, over 972311.04 frames.], batch size: 15, lr: 4.42e-04
+2022-05-05 00:03:55,001 INFO [train.py:715] (3/8) Epoch 4, batch 23500, loss[loss=0.1546, simple_loss=0.2295, pruned_loss=0.03984, over 4919.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2264, pruned_loss=0.04388, over 973319.88 frames.], batch size: 19, lr: 4.42e-04
+2022-05-05 00:04:33,373 INFO [train.py:715] (3/8) Epoch 4, batch 23550, loss[loss=0.1315, simple_loss=0.1955, pruned_loss=0.03377, over 4827.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04396, over 972317.93 frames.], batch size: 12, lr: 4.42e-04
+2022-05-05 00:05:12,659 INFO [train.py:715] (3/8) Epoch 4, batch 23600, loss[loss=0.1641, simple_loss=0.2297, pruned_loss=0.04927, over 4841.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2267, pruned_loss=0.04426, over 971609.59 frames.], batch size: 26, lr: 4.42e-04
+2022-05-05 00:05:53,469 INFO [train.py:715] (3/8) Epoch 4, batch 23650, loss[loss=0.1617, simple_loss=0.2234, pruned_loss=0.04999, over 4842.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2267, pruned_loss=0.04431, over 972036.95 frames.], batch size: 13, lr: 4.42e-04
+2022-05-05 00:06:34,864 INFO [train.py:715] (3/8) Epoch 4, batch 23700, loss[loss=0.1701, simple_loss=0.2273, pruned_loss=0.05647, over 4789.00 frames.], tot_loss[loss=0.157, simple_loss=0.226, pruned_loss=0.04405, over 972526.59 frames.], batch size: 12, lr: 4.42e-04
+2022-05-05 00:07:14,372 INFO [train.py:715] (3/8) Epoch 4, batch 23750, loss[loss=0.1553, simple_loss=0.2268, pruned_loss=0.04193, over 4933.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2259, pruned_loss=0.04381, over 973177.89 frames.], batch size: 35, lr: 4.42e-04
+2022-05-05 00:07:53,777 INFO [train.py:715] (3/8) Epoch 4, batch 23800, loss[loss=0.1796, simple_loss=0.2442, pruned_loss=0.05752, over 4885.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2266, pruned_loss=0.04416, over 973293.38 frames.], batch size: 16, lr: 4.42e-04
+2022-05-05 00:08:34,378 INFO [train.py:715] (3/8) Epoch 4, batch 23850, loss[loss=0.1472, simple_loss=0.2238, pruned_loss=0.03532, over 4780.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.044, over 973367.61 frames.], batch size: 18, lr: 4.42e-04
+2022-05-05 00:09:13,929 INFO [train.py:715] (3/8) Epoch 4, batch 23900, loss[loss=0.1305, simple_loss=0.1961, pruned_loss=0.0324, over 4881.00 frames.], tot_loss[loss=0.1563, simple_loss=0.226, pruned_loss=0.04334, over 972860.23 frames.], batch size: 16, lr: 4.42e-04
+2022-05-05 00:09:53,727 INFO [train.py:715] (3/8) Epoch 4, batch 23950, loss[loss=0.1545, simple_loss=0.2431, pruned_loss=0.03292, over 4936.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2258, pruned_loss=0.04319, over 972821.45 frames.], batch size: 29, lr: 4.41e-04
+2022-05-05 00:10:34,506 INFO [train.py:715] (3/8) Epoch 4, batch 24000, loss[loss=0.1594, simple_loss=0.2225, pruned_loss=0.04817, over 4759.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2258, pruned_loss=0.04322, over 973586.04 frames.], batch size: 17, lr: 4.41e-04
+2022-05-05 00:10:34,507 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 00:10:44,331 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1115, simple_loss=0.1974, pruned_loss=0.01276, over 914524.00 frames.
+2022-05-05 00:11:25,477 INFO [train.py:715] (3/8) Epoch 4, batch 24050, loss[loss=0.2076, simple_loss=0.2774, pruned_loss=0.06893, over 4890.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2266, pruned_loss=0.04377, over 973234.64 frames.], batch size: 19, lr: 4.41e-04
+2022-05-05 00:12:06,060 INFO [train.py:715] (3/8) Epoch 4, batch 24100, loss[loss=0.1516, simple_loss=0.2253, pruned_loss=0.03893, over 4842.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2266, pruned_loss=0.04385, over 974116.76 frames.], batch size: 30, lr: 4.41e-04
+2022-05-05 00:12:45,928 INFO [train.py:715] (3/8) Epoch 4, batch 24150, loss[loss=0.1556, simple_loss=0.2208, pruned_loss=0.04526, over 4959.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2267, pruned_loss=0.04353, over 973795.66 frames.], batch size: 35, lr: 4.41e-04
+2022-05-05 00:13:25,912 INFO [train.py:715] (3/8) Epoch 4, batch 24200, loss[loss=0.1372, simple_loss=0.2125, pruned_loss=0.03096, over 4842.00 frames.], tot_loss[loss=0.1573, simple_loss=0.227, pruned_loss=0.04382, over 973172.24 frames.], batch size: 13, lr: 4.41e-04
+2022-05-05 00:14:07,342 INFO [train.py:715] (3/8) Epoch 4, batch 24250, loss[loss=0.1391, simple_loss=0.2213, pruned_loss=0.02845, over 4743.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2275, pruned_loss=0.04402, over 972611.99 frames.], batch size: 16, lr: 4.41e-04
+2022-05-05 00:14:46,255 INFO [train.py:715] (3/8) Epoch 4, batch 24300, loss[loss=0.146, simple_loss=0.2238, pruned_loss=0.03414, over 4823.00 frames.], tot_loss[loss=0.1588, simple_loss=0.228, pruned_loss=0.04482, over 973726.77 frames.], batch size: 27, lr: 4.41e-04
+2022-05-05 00:15:26,724 INFO [train.py:715] (3/8) Epoch 4, batch 24350, loss[loss=0.2011, simple_loss=0.2598, pruned_loss=0.07116, over 4983.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2276, pruned_loss=0.0444, over 973332.84 frames.], batch size: 31, lr: 4.41e-04
+2022-05-05 00:16:07,661 INFO [train.py:715] (3/8) Epoch 4, batch 24400, loss[loss=0.1327, simple_loss=0.2108, pruned_loss=0.02734, over 4988.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2279, pruned_loss=0.04432, over 972716.35 frames.], batch size: 28, lr: 4.41e-04
+2022-05-05 00:16:47,250 INFO [train.py:715] (3/8) Epoch 4, batch 24450, loss[loss=0.1339, simple_loss=0.2113, pruned_loss=0.02829, over 4776.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2268, pruned_loss=0.04392, over 972011.81 frames.], batch size: 17, lr: 4.41e-04
+2022-05-05 00:17:27,008 INFO [train.py:715] (3/8) Epoch 4, batch 24500, loss[loss=0.1619, simple_loss=0.2294, pruned_loss=0.04714, over 4768.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2259, pruned_loss=0.04357, over 972831.48 frames.], batch size: 18, lr: 4.41e-04
+2022-05-05 00:18:06,875 INFO [train.py:715] (3/8) Epoch 4, batch 24550, loss[loss=0.171, simple_loss=0.2378, pruned_loss=0.05208, over 4787.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2259, pruned_loss=0.04371, over 972640.25 frames.], batch size: 14, lr: 4.41e-04
+2022-05-05 00:18:48,107 INFO [train.py:715] (3/8) Epoch 4, batch 24600, loss[loss=0.1551, simple_loss=0.2231, pruned_loss=0.04354, over 4866.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2261, pruned_loss=0.04343, over 972327.54 frames.], batch size: 32, lr: 4.41e-04
+2022-05-05 00:19:27,467 INFO [train.py:715] (3/8) Epoch 4, batch 24650, loss[loss=0.1343, simple_loss=0.207, pruned_loss=0.0308, over 4978.00 frames.], tot_loss[loss=0.157, simple_loss=0.2261, pruned_loss=0.04391, over 972863.96 frames.], batch size: 15, lr: 4.41e-04
+2022-05-05 00:20:08,195 INFO [train.py:715] (3/8) Epoch 4, batch 24700, loss[loss=0.1656, simple_loss=0.233, pruned_loss=0.04912, over 4808.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2262, pruned_loss=0.0442, over 972425.69 frames.], batch size: 14, lr: 4.40e-04
+2022-05-05 00:20:49,278 INFO [train.py:715] (3/8) Epoch 4, batch 24750, loss[loss=0.1457, simple_loss=0.2195, pruned_loss=0.03595, over 4900.00 frames.], tot_loss[loss=0.157, simple_loss=0.2264, pruned_loss=0.04378, over 973196.75 frames.], batch size: 22, lr: 4.40e-04
+2022-05-05 00:21:28,791 INFO [train.py:715] (3/8) Epoch 4, batch 24800, loss[loss=0.1526, simple_loss=0.2262, pruned_loss=0.0395, over 4909.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2273, pruned_loss=0.04479, over 973955.23 frames.], batch size: 19, lr: 4.40e-04
+2022-05-05 00:22:08,800 INFO [train.py:715] (3/8) Epoch 4, batch 24850, loss[loss=0.1384, simple_loss=0.2178, pruned_loss=0.02953, over 4961.00 frames.], tot_loss[loss=0.157, simple_loss=0.2261, pruned_loss=0.04391, over 973642.93 frames.], batch size: 24, lr: 4.40e-04
+2022-05-05 00:22:49,040 INFO [train.py:715] (3/8) Epoch 4, batch 24900, loss[loss=0.1674, simple_loss=0.2274, pruned_loss=0.0537, over 4984.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2253, pruned_loss=0.04365, over 973441.35 frames.], batch size: 15, lr: 4.40e-04
+2022-05-05 00:23:30,189 INFO [train.py:715] (3/8) Epoch 4, batch 24950, loss[loss=0.1604, simple_loss=0.2329, pruned_loss=0.04398, over 4836.00 frames.], tot_loss[loss=0.157, simple_loss=0.2261, pruned_loss=0.04391, over 974289.90 frames.], batch size: 13, lr: 4.40e-04
+2022-05-05 00:24:09,091 INFO [train.py:715] (3/8) Epoch 4, batch 25000, loss[loss=0.1472, simple_loss=0.2237, pruned_loss=0.03539, over 4862.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2261, pruned_loss=0.04361, over 973978.42 frames.], batch size: 38, lr: 4.40e-04
+2022-05-05 00:24:49,332 INFO [train.py:715] (3/8) Epoch 4, batch 25050, loss[loss=0.1426, simple_loss=0.2295, pruned_loss=0.02784, over 4690.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2263, pruned_loss=0.04344, over 973246.96 frames.], batch size: 15, lr: 4.40e-04
+2022-05-05 00:25:30,454 INFO [train.py:715] (3/8) Epoch 4, batch 25100, loss[loss=0.1559, simple_loss=0.2143, pruned_loss=0.04872, over 4963.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2267, pruned_loss=0.04395, over 973126.13 frames.], batch size: 14, lr: 4.40e-04
+2022-05-05 00:26:10,375 INFO [train.py:715] (3/8) Epoch 4, batch 25150, loss[loss=0.1612, simple_loss=0.2301, pruned_loss=0.04614, over 4957.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2259, pruned_loss=0.04337, over 973086.31 frames.], batch size: 35, lr: 4.40e-04
+2022-05-05 00:26:49,794 INFO [train.py:715] (3/8) Epoch 4, batch 25200, loss[loss=0.1623, simple_loss=0.2307, pruned_loss=0.04691, over 4837.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2259, pruned_loss=0.04324, over 972510.47 frames.], batch size: 26, lr: 4.40e-04
+2022-05-05 00:27:30,067 INFO [train.py:715] (3/8) Epoch 4, batch 25250, loss[loss=0.1758, simple_loss=0.238, pruned_loss=0.05679, over 4815.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2261, pruned_loss=0.04318, over 972665.79 frames.], batch size: 13, lr: 4.40e-04
+2022-05-05 00:28:10,080 INFO [train.py:715] (3/8) Epoch 4, batch 25300, loss[loss=0.1673, simple_loss=0.2383, pruned_loss=0.04813, over 4922.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2252, pruned_loss=0.04284, over 971905.30 frames.], batch size: 29, lr: 4.40e-04
+2022-05-05 00:28:47,883 INFO [train.py:715] (3/8) Epoch 4, batch 25350, loss[loss=0.1523, simple_loss=0.2282, pruned_loss=0.03818, over 4970.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2254, pruned_loss=0.04281, over 972105.15 frames.], batch size: 28, lr: 4.40e-04
+2022-05-05 00:29:26,732 INFO [train.py:715] (3/8) Epoch 4, batch 25400, loss[loss=0.1436, simple_loss=0.219, pruned_loss=0.03407, over 4652.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2261, pruned_loss=0.04331, over 971783.75 frames.], batch size: 13, lr: 4.40e-04
+2022-05-05 00:30:06,396 INFO [train.py:715] (3/8) Epoch 4, batch 25450, loss[loss=0.1555, simple_loss=0.2261, pruned_loss=0.0425, over 4792.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2252, pruned_loss=0.0428, over 971356.53 frames.], batch size: 14, lr: 4.39e-04
+2022-05-05 00:30:45,455 INFO [train.py:715] (3/8) Epoch 4, batch 25500, loss[loss=0.175, simple_loss=0.2395, pruned_loss=0.05528, over 4871.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2258, pruned_loss=0.04324, over 972531.86 frames.], batch size: 34, lr: 4.39e-04
+2022-05-05 00:31:25,317 INFO [train.py:715] (3/8) Epoch 4, batch 25550, loss[loss=0.1841, simple_loss=0.2525, pruned_loss=0.0578, over 4919.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2255, pruned_loss=0.04291, over 972699.41 frames.], batch size: 39, lr: 4.39e-04
+2022-05-05 00:32:05,294 INFO [train.py:715] (3/8) Epoch 4, batch 25600, loss[loss=0.203, simple_loss=0.2658, pruned_loss=0.0701, over 4712.00 frames.], tot_loss[loss=0.157, simple_loss=0.2266, pruned_loss=0.04374, over 972656.69 frames.], batch size: 15, lr: 4.39e-04
+2022-05-05 00:32:45,566 INFO [train.py:715] (3/8) Epoch 4, batch 25650, loss[loss=0.1566, simple_loss=0.2238, pruned_loss=0.04471, over 4994.00 frames.], tot_loss[loss=0.1562, simple_loss=0.226, pruned_loss=0.0432, over 973184.62 frames.], batch size: 16, lr: 4.39e-04
+2022-05-05 00:33:24,673 INFO [train.py:715] (3/8) Epoch 4, batch 25700, loss[loss=0.1432, simple_loss=0.2078, pruned_loss=0.03928, over 4748.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2255, pruned_loss=0.04288, over 972428.29 frames.], batch size: 12, lr: 4.39e-04
+2022-05-05 00:34:04,656 INFO [train.py:715] (3/8) Epoch 4, batch 25750, loss[loss=0.1715, simple_loss=0.2392, pruned_loss=0.05194, over 4775.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2259, pruned_loss=0.04324, over 971820.02 frames.], batch size: 18, lr: 4.39e-04
+2022-05-05 00:34:45,101 INFO [train.py:715] (3/8) Epoch 4, batch 25800, loss[loss=0.1586, simple_loss=0.2222, pruned_loss=0.04752, over 4856.00 frames.], tot_loss[loss=0.156, simple_loss=0.2262, pruned_loss=0.04289, over 972003.32 frames.], batch size: 30, lr: 4.39e-04
+2022-05-05 00:35:24,460 INFO [train.py:715] (3/8) Epoch 4, batch 25850, loss[loss=0.1609, simple_loss=0.2363, pruned_loss=0.04274, over 4763.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2262, pruned_loss=0.04282, over 971924.46 frames.], batch size: 18, lr: 4.39e-04
+2022-05-05 00:36:03,600 INFO [train.py:715] (3/8) Epoch 4, batch 25900, loss[loss=0.1275, simple_loss=0.2016, pruned_loss=0.02673, over 4709.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2267, pruned_loss=0.0433, over 971482.29 frames.], batch size: 15, lr: 4.39e-04
+2022-05-05 00:36:43,850 INFO [train.py:715] (3/8) Epoch 4, batch 25950, loss[loss=0.198, simple_loss=0.2671, pruned_loss=0.06448, over 4903.00 frames.], tot_loss[loss=0.157, simple_loss=0.2268, pruned_loss=0.04356, over 972068.59 frames.], batch size: 19, lr: 4.39e-04
+2022-05-05 00:37:24,111 INFO [train.py:715] (3/8) Epoch 4, batch 26000, loss[loss=0.1655, simple_loss=0.2285, pruned_loss=0.05124, over 4882.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2271, pruned_loss=0.04381, over 972551.67 frames.], batch size: 22, lr: 4.39e-04
+2022-05-05 00:38:02,817 INFO [train.py:715] (3/8) Epoch 4, batch 26050, loss[loss=0.1571, simple_loss=0.2337, pruned_loss=0.04019, over 4942.00 frames.], tot_loss[loss=0.1563, simple_loss=0.226, pruned_loss=0.0433, over 972934.88 frames.], batch size: 23, lr: 4.39e-04
+2022-05-05 00:38:42,225 INFO [train.py:715] (3/8) Epoch 4, batch 26100, loss[loss=0.1286, simple_loss=0.2037, pruned_loss=0.02679, over 4661.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04323, over 972516.36 frames.], batch size: 13, lr: 4.39e-04
+2022-05-05 00:39:22,684 INFO [train.py:715] (3/8) Epoch 4, batch 26150, loss[loss=0.176, simple_loss=0.2409, pruned_loss=0.05554, over 4916.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2253, pruned_loss=0.04327, over 971959.97 frames.], batch size: 39, lr: 4.39e-04
+2022-05-05 00:40:01,756 INFO [train.py:715] (3/8) Epoch 4, batch 26200, loss[loss=0.1231, simple_loss=0.1954, pruned_loss=0.02541, over 4838.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2239, pruned_loss=0.04229, over 971058.58 frames.], batch size: 26, lr: 4.38e-04
+2022-05-05 00:40:41,527 INFO [train.py:715] (3/8) Epoch 4, batch 26250, loss[loss=0.1659, simple_loss=0.2297, pruned_loss=0.05109, over 4857.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2236, pruned_loss=0.04207, over 970970.01 frames.], batch size: 30, lr: 4.38e-04
+2022-05-05 00:41:21,392 INFO [train.py:715] (3/8) Epoch 4, batch 26300, loss[loss=0.1466, simple_loss=0.2224, pruned_loss=0.03536, over 4966.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2238, pruned_loss=0.04217, over 971290.99 frames.], batch size: 25, lr: 4.38e-04
+2022-05-05 00:42:01,535 INFO [train.py:715] (3/8) Epoch 4, batch 26350, loss[loss=0.1408, simple_loss=0.2121, pruned_loss=0.0348, over 4769.00 frames.], tot_loss[loss=0.155, simple_loss=0.2247, pruned_loss=0.04269, over 970933.00 frames.], batch size: 17, lr: 4.38e-04
+2022-05-05 00:42:40,876 INFO [train.py:715] (3/8) Epoch 4, batch 26400, loss[loss=0.1772, simple_loss=0.2467, pruned_loss=0.05388, over 4816.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2252, pruned_loss=0.04275, over 972009.16 frames.], batch size: 27, lr: 4.38e-04
+2022-05-05 00:43:20,963 INFO [train.py:715] (3/8) Epoch 4, batch 26450, loss[loss=0.1455, simple_loss=0.2174, pruned_loss=0.03678, over 4845.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2251, pruned_loss=0.04262, over 971966.93 frames.], batch size: 32, lr: 4.38e-04
+2022-05-05 00:44:01,485 INFO [train.py:715] (3/8) Epoch 4, batch 26500, loss[loss=0.1545, simple_loss=0.2225, pruned_loss=0.04321, over 4917.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2246, pruned_loss=0.04206, over 972768.06 frames.], batch size: 19, lr: 4.38e-04
+2022-05-05 00:44:40,387 INFO [train.py:715] (3/8) Epoch 4, batch 26550, loss[loss=0.17, simple_loss=0.2318, pruned_loss=0.05405, over 4888.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2249, pruned_loss=0.04233, over 971934.38 frames.], batch size: 16, lr: 4.38e-04
+2022-05-05 00:45:20,038 INFO [train.py:715] (3/8) Epoch 4, batch 26600, loss[loss=0.1544, simple_loss=0.2355, pruned_loss=0.03665, over 4975.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2253, pruned_loss=0.04221, over 972699.23 frames.], batch size: 24, lr: 4.38e-04
+2022-05-05 00:46:00,423 INFO [train.py:715] (3/8) Epoch 4, batch 26650, loss[loss=0.1455, simple_loss=0.2155, pruned_loss=0.03776, over 4969.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2245, pruned_loss=0.04235, over 973281.92 frames.], batch size: 28, lr: 4.38e-04
+2022-05-05 00:46:41,230 INFO [train.py:715] (3/8) Epoch 4, batch 26700, loss[loss=0.1574, simple_loss=0.2289, pruned_loss=0.0429, over 4937.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2253, pruned_loss=0.04285, over 974191.30 frames.], batch size: 21, lr: 4.38e-04
+2022-05-05 00:47:20,021 INFO [train.py:715] (3/8) Epoch 4, batch 26750, loss[loss=0.1562, simple_loss=0.2272, pruned_loss=0.04257, over 4969.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04306, over 973426.01 frames.], batch size: 15, lr: 4.38e-04
+2022-05-05 00:47:59,597 INFO [train.py:715] (3/8) Epoch 4, batch 26800, loss[loss=0.1166, simple_loss=0.1869, pruned_loss=0.02317, over 4854.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2244, pruned_loss=0.04261, over 973617.23 frames.], batch size: 20, lr: 4.38e-04
+2022-05-05 00:48:39,808 INFO [train.py:715] (3/8) Epoch 4, batch 26850, loss[loss=0.1494, simple_loss=0.226, pruned_loss=0.03643, over 4804.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2251, pruned_loss=0.04282, over 973507.65 frames.], batch size: 25, lr: 4.38e-04
+2022-05-05 00:49:18,745 INFO [train.py:715] (3/8) Epoch 4, batch 26900, loss[loss=0.1485, simple_loss=0.2148, pruned_loss=0.04104, over 4793.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2257, pruned_loss=0.04305, over 972394.11 frames.], batch size: 24, lr: 4.38e-04
+2022-05-05 00:49:58,559 INFO [train.py:715] (3/8) Epoch 4, batch 26950, loss[loss=0.1459, simple_loss=0.2141, pruned_loss=0.03892, over 4784.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2257, pruned_loss=0.04322, over 972542.08 frames.], batch size: 14, lr: 4.37e-04
+2022-05-05 00:50:38,533 INFO [train.py:715] (3/8) Epoch 4, batch 27000, loss[loss=0.1439, simple_loss=0.2175, pruned_loss=0.03514, over 4835.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2258, pruned_loss=0.04335, over 972434.71 frames.], batch size: 15, lr: 4.37e-04
+2022-05-05 00:50:38,533 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 00:50:48,690 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1114, simple_loss=0.197, pruned_loss=0.01284, over 914524.00 frames.
+2022-05-05 00:51:28,850 INFO [train.py:715] (3/8) Epoch 4, batch 27050, loss[loss=0.151, simple_loss=0.2122, pruned_loss=0.04485, over 4707.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2258, pruned_loss=0.04325, over 973405.38 frames.], batch size: 15, lr: 4.37e-04
+2022-05-05 00:52:08,420 INFO [train.py:715] (3/8) Epoch 4, batch 27100, loss[loss=0.1393, simple_loss=0.215, pruned_loss=0.03181, over 4837.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2258, pruned_loss=0.0429, over 973640.70 frames.], batch size: 15, lr: 4.37e-04
+2022-05-05 00:52:47,729 INFO [train.py:715] (3/8) Epoch 4, batch 27150, loss[loss=0.1342, simple_loss=0.2075, pruned_loss=0.03046, over 4819.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2251, pruned_loss=0.04262, over 974084.45 frames.], batch size: 26, lr: 4.37e-04
+2022-05-05 00:53:27,409 INFO [train.py:715] (3/8) Epoch 4, batch 27200, loss[loss=0.1464, simple_loss=0.2198, pruned_loss=0.03653, over 4818.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2254, pruned_loss=0.04271, over 974121.33 frames.], batch size: 27, lr: 4.37e-04
+2022-05-05 00:54:07,876 INFO [train.py:715] (3/8) Epoch 4, batch 27250, loss[loss=0.1615, simple_loss=0.2261, pruned_loss=0.0484, over 4938.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2252, pruned_loss=0.04278, over 974124.67 frames.], batch size: 21, lr: 4.37e-04
+2022-05-05 00:54:46,637 INFO [train.py:715] (3/8) Epoch 4, batch 27300, loss[loss=0.124, simple_loss=0.189, pruned_loss=0.02951, over 4870.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2244, pruned_loss=0.04254, over 974198.56 frames.], batch size: 20, lr: 4.37e-04
+2022-05-05 00:55:26,631 INFO [train.py:715] (3/8) Epoch 4, batch 27350, loss[loss=0.1468, simple_loss=0.2142, pruned_loss=0.03972, over 4780.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2243, pruned_loss=0.0422, over 974095.56 frames.], batch size: 14, lr: 4.37e-04
+2022-05-05 00:56:06,584 INFO [train.py:715] (3/8) Epoch 4, batch 27400, loss[loss=0.1436, simple_loss=0.2132, pruned_loss=0.03696, over 4908.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2239, pruned_loss=0.04173, over 973426.38 frames.], batch size: 18, lr: 4.37e-04
+2022-05-05 00:56:45,009 INFO [train.py:715] (3/8) Epoch 4, batch 27450, loss[loss=0.1378, simple_loss=0.2067, pruned_loss=0.03442, over 4950.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2235, pruned_loss=0.04192, over 974075.06 frames.], batch size: 15, lr: 4.37e-04
+2022-05-05 00:57:24,955 INFO [train.py:715] (3/8) Epoch 4, batch 27500, loss[loss=0.1795, simple_loss=0.2544, pruned_loss=0.05232, over 4848.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2239, pruned_loss=0.04166, over 972748.69 frames.], batch size: 30, lr: 4.37e-04
+2022-05-05 00:58:03,977 INFO [train.py:715] (3/8) Epoch 4, batch 27550, loss[loss=0.124, simple_loss=0.1854, pruned_loss=0.03127, over 4846.00 frames.], tot_loss[loss=0.155, simple_loss=0.2254, pruned_loss=0.04237, over 972227.17 frames.], batch size: 13, lr: 4.37e-04
+2022-05-05 00:58:43,891 INFO [train.py:715] (3/8) Epoch 4, batch 27600, loss[loss=0.1936, simple_loss=0.2563, pruned_loss=0.06549, over 4788.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2257, pruned_loss=0.0425, over 972398.60 frames.], batch size: 14, lr: 4.37e-04
+2022-05-05 00:59:22,456 INFO [train.py:715] (3/8) Epoch 4, batch 27650, loss[loss=0.1488, simple_loss=0.2216, pruned_loss=0.038, over 4795.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2264, pruned_loss=0.0431, over 972342.41 frames.], batch size: 14, lr: 4.37e-04
+2022-05-05 01:00:01,781 INFO [train.py:715] (3/8) Epoch 4, batch 27700, loss[loss=0.1013, simple_loss=0.1601, pruned_loss=0.02123, over 4739.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2252, pruned_loss=0.04261, over 972380.98 frames.], batch size: 12, lr: 4.36e-04
+2022-05-05 01:00:41,406 INFO [train.py:715] (3/8) Epoch 4, batch 27750, loss[loss=0.1568, simple_loss=0.2251, pruned_loss=0.04421, over 4867.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2253, pruned_loss=0.04301, over 972580.29 frames.], batch size: 16, lr: 4.36e-04
+2022-05-05 01:01:20,723 INFO [train.py:715] (3/8) Epoch 4, batch 27800, loss[loss=0.148, simple_loss=0.2135, pruned_loss=0.04123, over 4877.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2258, pruned_loss=0.04332, over 973060.18 frames.], batch size: 32, lr: 4.36e-04
+2022-05-05 01:01:59,778 INFO [train.py:715] (3/8) Epoch 4, batch 27850, loss[loss=0.1672, simple_loss=0.239, pruned_loss=0.04773, over 4944.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2269, pruned_loss=0.04385, over 972406.56 frames.], batch size: 14, lr: 4.36e-04
+2022-05-05 01:02:38,864 INFO [train.py:715] (3/8) Epoch 4, batch 27900, loss[loss=0.1693, simple_loss=0.2314, pruned_loss=0.05366, over 4814.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2265, pruned_loss=0.04401, over 972014.09 frames.], batch size: 24, lr: 4.36e-04
+2022-05-05 01:03:18,312 INFO [train.py:715] (3/8) Epoch 4, batch 27950, loss[loss=0.1962, simple_loss=0.2609, pruned_loss=0.06574, over 4879.00 frames.], tot_loss[loss=0.157, simple_loss=0.2265, pruned_loss=0.04375, over 972262.65 frames.], batch size: 16, lr: 4.36e-04
+2022-05-05 01:03:57,877 INFO [train.py:715] (3/8) Epoch 4, batch 28000, loss[loss=0.1378, simple_loss=0.2062, pruned_loss=0.03466, over 4891.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2256, pruned_loss=0.04329, over 972613.48 frames.], batch size: 22, lr: 4.36e-04
+2022-05-05 01:04:37,837 INFO [train.py:715] (3/8) Epoch 4, batch 28050, loss[loss=0.2377, simple_loss=0.2957, pruned_loss=0.08988, over 4916.00 frames.], tot_loss[loss=0.1564, simple_loss=0.226, pruned_loss=0.04337, over 973109.45 frames.], batch size: 18, lr: 4.36e-04
+2022-05-05 01:05:17,719 INFO [train.py:715] (3/8) Epoch 4, batch 28100, loss[loss=0.1227, simple_loss=0.2054, pruned_loss=0.02001, over 4870.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2267, pruned_loss=0.04378, over 972988.77 frames.], batch size: 20, lr: 4.36e-04
+2022-05-05 01:05:57,314 INFO [train.py:715] (3/8) Epoch 4, batch 28150, loss[loss=0.1336, simple_loss=0.2027, pruned_loss=0.03224, over 4899.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2273, pruned_loss=0.04399, over 973678.28 frames.], batch size: 19, lr: 4.36e-04
+2022-05-05 01:06:36,803 INFO [train.py:715] (3/8) Epoch 4, batch 28200, loss[loss=0.1385, simple_loss=0.205, pruned_loss=0.03598, over 4821.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2269, pruned_loss=0.04367, over 972649.15 frames.], batch size: 12, lr: 4.36e-04
+2022-05-05 01:07:15,870 INFO [train.py:715] (3/8) Epoch 4, batch 28250, loss[loss=0.1365, simple_loss=0.2173, pruned_loss=0.02781, over 4828.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2272, pruned_loss=0.0441, over 972553.14 frames.], batch size: 15, lr: 4.36e-04
+2022-05-05 01:07:55,433 INFO [train.py:715] (3/8) Epoch 4, batch 28300, loss[loss=0.1441, simple_loss=0.2211, pruned_loss=0.03358, over 4916.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2268, pruned_loss=0.0438, over 972207.95 frames.], batch size: 29, lr: 4.36e-04
+2022-05-05 01:08:34,755 INFO [train.py:715] (3/8) Epoch 4, batch 28350, loss[loss=0.151, simple_loss=0.2229, pruned_loss=0.03957, over 4798.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2266, pruned_loss=0.04356, over 972617.36 frames.], batch size: 25, lr: 4.36e-04
+2022-05-05 01:09:14,655 INFO [train.py:715] (3/8) Epoch 4, batch 28400, loss[loss=0.127, simple_loss=0.2017, pruned_loss=0.02613, over 4786.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.0438, over 972494.81 frames.], batch size: 14, lr: 4.36e-04
+2022-05-05 01:09:53,870 INFO [train.py:715] (3/8) Epoch 4, batch 28450, loss[loss=0.1653, simple_loss=0.2419, pruned_loss=0.04436, over 4983.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2263, pruned_loss=0.04344, over 972456.31 frames.], batch size: 24, lr: 4.36e-04
+2022-05-05 01:10:32,528 INFO [train.py:715] (3/8) Epoch 4, batch 28500, loss[loss=0.1459, simple_loss=0.2125, pruned_loss=0.03971, over 4981.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2261, pruned_loss=0.04345, over 972460.41 frames.], batch size: 35, lr: 4.35e-04
+2022-05-05 01:11:12,039 INFO [train.py:715] (3/8) Epoch 4, batch 28550, loss[loss=0.1901, simple_loss=0.264, pruned_loss=0.05807, over 4737.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2257, pruned_loss=0.04294, over 971769.81 frames.], batch size: 16, lr: 4.35e-04
+2022-05-05 01:11:51,203 INFO [train.py:715] (3/8) Epoch 4, batch 28600, loss[loss=0.1507, simple_loss=0.2133, pruned_loss=0.04404, over 4994.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2255, pruned_loss=0.04269, over 973200.50 frames.], batch size: 15, lr: 4.35e-04
+2022-05-05 01:12:30,863 INFO [train.py:715] (3/8) Epoch 4, batch 28650, loss[loss=0.1576, simple_loss=0.2226, pruned_loss=0.0463, over 4985.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2265, pruned_loss=0.04292, over 973584.54 frames.], batch size: 14, lr: 4.35e-04
+2022-05-05 01:13:10,038 INFO [train.py:715] (3/8) Epoch 4, batch 28700, loss[loss=0.1538, simple_loss=0.2212, pruned_loss=0.04322, over 4977.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2261, pruned_loss=0.0426, over 974153.57 frames.], batch size: 35, lr: 4.35e-04
+2022-05-05 01:13:49,556 INFO [train.py:715] (3/8) Epoch 4, batch 28750, loss[loss=0.1908, simple_loss=0.2426, pruned_loss=0.06947, over 4840.00 frames.], tot_loss[loss=0.1546, simple_loss=0.225, pruned_loss=0.04214, over 973406.84 frames.], batch size: 27, lr: 4.35e-04
+2022-05-05 01:14:31,713 INFO [train.py:715] (3/8) Epoch 4, batch 28800, loss[loss=0.1547, simple_loss=0.2343, pruned_loss=0.03756, over 4924.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2267, pruned_loss=0.04327, over 973355.60 frames.], batch size: 18, lr: 4.35e-04
+2022-05-05 01:15:10,515 INFO [train.py:715] (3/8) Epoch 4, batch 28850, loss[loss=0.162, simple_loss=0.224, pruned_loss=0.04998, over 4944.00 frames.], tot_loss[loss=0.156, simple_loss=0.2259, pruned_loss=0.04309, over 973140.64 frames.], batch size: 35, lr: 4.35e-04
+2022-05-05 01:15:50,212 INFO [train.py:715] (3/8) Epoch 4, batch 28900, loss[loss=0.1932, simple_loss=0.2685, pruned_loss=0.05895, over 4935.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2254, pruned_loss=0.04218, over 972793.43 frames.], batch size: 39, lr: 4.35e-04
+2022-05-05 01:16:29,312 INFO [train.py:715] (3/8) Epoch 4, batch 28950, loss[loss=0.1531, simple_loss=0.2178, pruned_loss=0.04414, over 4852.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2252, pruned_loss=0.04274, over 973690.19 frames.], batch size: 20, lr: 4.35e-04
+2022-05-05 01:17:08,542 INFO [train.py:715] (3/8) Epoch 4, batch 29000, loss[loss=0.1589, simple_loss=0.2156, pruned_loss=0.05112, over 4913.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2242, pruned_loss=0.0422, over 973441.26 frames.], batch size: 18, lr: 4.35e-04
+2022-05-05 01:17:48,160 INFO [train.py:715] (3/8) Epoch 4, batch 29050, loss[loss=0.116, simple_loss=0.1969, pruned_loss=0.01753, over 4988.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2251, pruned_loss=0.04221, over 973616.74 frames.], batch size: 28, lr: 4.35e-04
+2022-05-05 01:18:28,178 INFO [train.py:715] (3/8) Epoch 4, batch 29100, loss[loss=0.1244, simple_loss=0.1938, pruned_loss=0.02748, over 4883.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2265, pruned_loss=0.04302, over 973644.76 frames.], batch size: 22, lr: 4.35e-04
+2022-05-05 01:19:07,856 INFO [train.py:715] (3/8) Epoch 4, batch 29150, loss[loss=0.153, simple_loss=0.2297, pruned_loss=0.03819, over 4963.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2248, pruned_loss=0.04219, over 973429.65 frames.], batch size: 24, lr: 4.35e-04
+2022-05-05 01:19:46,741 INFO [train.py:715] (3/8) Epoch 4, batch 29200, loss[loss=0.1616, simple_loss=0.2287, pruned_loss=0.04728, over 4824.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2252, pruned_loss=0.04259, over 973308.00 frames.], batch size: 15, lr: 4.35e-04
+2022-05-05 01:20:26,108 INFO [train.py:715] (3/8) Epoch 4, batch 29250, loss[loss=0.151, simple_loss=0.2184, pruned_loss=0.04176, over 4745.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2244, pruned_loss=0.0422, over 972377.15 frames.], batch size: 16, lr: 4.34e-04
+2022-05-05 01:21:05,005 INFO [train.py:715] (3/8) Epoch 4, batch 29300, loss[loss=0.143, simple_loss=0.2116, pruned_loss=0.03722, over 4895.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2237, pruned_loss=0.04191, over 972456.43 frames.], batch size: 19, lr: 4.34e-04
+2022-05-05 01:21:43,984 INFO [train.py:715] (3/8) Epoch 4, batch 29350, loss[loss=0.1546, simple_loss=0.2225, pruned_loss=0.04337, over 4974.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2242, pruned_loss=0.04234, over 973112.35 frames.], batch size: 15, lr: 4.34e-04
+2022-05-05 01:22:22,964 INFO [train.py:715] (3/8) Epoch 4, batch 29400, loss[loss=0.1571, simple_loss=0.2341, pruned_loss=0.04001, over 4942.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2249, pruned_loss=0.0426, over 972269.58 frames.], batch size: 21, lr: 4.34e-04
+2022-05-05 01:23:02,045 INFO [train.py:715] (3/8) Epoch 4, batch 29450, loss[loss=0.1468, simple_loss=0.2151, pruned_loss=0.0393, over 4819.00 frames.], tot_loss[loss=0.156, simple_loss=0.2255, pruned_loss=0.04329, over 971860.67 frames.], batch size: 12, lr: 4.34e-04
+2022-05-05 01:23:41,623 INFO [train.py:715] (3/8) Epoch 4, batch 29500, loss[loss=0.1481, simple_loss=0.2196, pruned_loss=0.03831, over 4848.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2244, pruned_loss=0.04311, over 972093.53 frames.], batch size: 30, lr: 4.34e-04
+2022-05-05 01:24:20,880 INFO [train.py:715] (3/8) Epoch 4, batch 29550, loss[loss=0.1366, simple_loss=0.2064, pruned_loss=0.03343, over 4979.00 frames.], tot_loss[loss=0.1564, simple_loss=0.225, pruned_loss=0.04389, over 972267.13 frames.], batch size: 24, lr: 4.34e-04
+2022-05-05 01:25:00,161 INFO [train.py:715] (3/8) Epoch 4, batch 29600, loss[loss=0.1217, simple_loss=0.1874, pruned_loss=0.028, over 4976.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2253, pruned_loss=0.0438, over 972895.82 frames.], batch size: 15, lr: 4.34e-04
+2022-05-05 01:25:39,284 INFO [train.py:715] (3/8) Epoch 4, batch 29650, loss[loss=0.1896, simple_loss=0.2558, pruned_loss=0.06168, over 4773.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2253, pruned_loss=0.04385, over 972480.62 frames.], batch size: 18, lr: 4.34e-04
+2022-05-05 01:26:18,055 INFO [train.py:715] (3/8) Epoch 4, batch 29700, loss[loss=0.1768, simple_loss=0.2359, pruned_loss=0.05887, over 4807.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2251, pruned_loss=0.04339, over 971994.67 frames.], batch size: 13, lr: 4.34e-04
+2022-05-05 01:26:57,623 INFO [train.py:715] (3/8) Epoch 4, batch 29750, loss[loss=0.1284, simple_loss=0.1974, pruned_loss=0.02964, over 4781.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04307, over 971849.34 frames.], batch size: 18, lr: 4.34e-04
+2022-05-05 01:27:36,802 INFO [train.py:715] (3/8) Epoch 4, batch 29800, loss[loss=0.139, simple_loss=0.2083, pruned_loss=0.03485, over 4907.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2253, pruned_loss=0.0428, over 971602.17 frames.], batch size: 17, lr: 4.34e-04
+2022-05-05 01:28:16,335 INFO [train.py:715] (3/8) Epoch 4, batch 29850, loss[loss=0.2009, simple_loss=0.2686, pruned_loss=0.06663, over 4962.00 frames.], tot_loss[loss=0.156, simple_loss=0.2258, pruned_loss=0.0431, over 971176.18 frames.], batch size: 15, lr: 4.34e-04
+2022-05-05 01:28:55,199 INFO [train.py:715] (3/8) Epoch 4, batch 29900, loss[loss=0.146, simple_loss=0.2128, pruned_loss=0.03967, over 4915.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2268, pruned_loss=0.0434, over 970970.15 frames.], batch size: 17, lr: 4.34e-04
+2022-05-05 01:29:34,841 INFO [train.py:715] (3/8) Epoch 4, batch 29950, loss[loss=0.166, simple_loss=0.2257, pruned_loss=0.05311, over 4906.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2264, pruned_loss=0.04325, over 972051.14 frames.], batch size: 23, lr: 4.34e-04
+2022-05-05 01:30:13,995 INFO [train.py:715] (3/8) Epoch 4, batch 30000, loss[loss=0.1452, simple_loss=0.2067, pruned_loss=0.04185, over 4732.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2256, pruned_loss=0.04293, over 971542.14 frames.], batch size: 12, lr: 4.34e-04
+2022-05-05 01:30:13,995 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 01:30:23,827 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1113, simple_loss=0.1968, pruned_loss=0.01286, over 914524.00 frames.
+2022-05-05 01:31:03,996 INFO [train.py:715] (3/8) Epoch 4, batch 30050, loss[loss=0.1736, simple_loss=0.2385, pruned_loss=0.05437, over 4758.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2243, pruned_loss=0.04223, over 972224.14 frames.], batch size: 12, lr: 4.33e-04
+2022-05-05 01:31:43,424 INFO [train.py:715] (3/8) Epoch 4, batch 30100, loss[loss=0.1458, simple_loss=0.2203, pruned_loss=0.03563, over 4796.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2242, pruned_loss=0.04182, over 971586.13 frames.], batch size: 17, lr: 4.33e-04
+2022-05-05 01:32:23,322 INFO [train.py:715] (3/8) Epoch 4, batch 30150, loss[loss=0.1649, simple_loss=0.2356, pruned_loss=0.04711, over 4945.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2241, pruned_loss=0.04171, over 971858.31 frames.], batch size: 35, lr: 4.33e-04
+2022-05-05 01:33:02,790 INFO [train.py:715] (3/8) Epoch 4, batch 30200, loss[loss=0.1505, simple_loss=0.2125, pruned_loss=0.0443, over 4854.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2247, pruned_loss=0.0421, over 972270.27 frames.], batch size: 32, lr: 4.33e-04
+2022-05-05 01:33:42,426 INFO [train.py:715] (3/8) Epoch 4, batch 30250, loss[loss=0.1762, simple_loss=0.2472, pruned_loss=0.05258, over 4961.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2257, pruned_loss=0.04259, over 972919.99 frames.], batch size: 28, lr: 4.33e-04
+2022-05-05 01:34:21,595 INFO [train.py:715] (3/8) Epoch 4, batch 30300, loss[loss=0.1641, simple_loss=0.2352, pruned_loss=0.04649, over 4964.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2258, pruned_loss=0.04293, over 973202.89 frames.], batch size: 15, lr: 4.33e-04
+2022-05-05 01:35:01,077 INFO [train.py:715] (3/8) Epoch 4, batch 30350, loss[loss=0.1321, simple_loss=0.2034, pruned_loss=0.03041, over 4912.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2247, pruned_loss=0.04253, over 972500.40 frames.], batch size: 19, lr: 4.33e-04
+2022-05-05 01:35:41,054 INFO [train.py:715] (3/8) Epoch 4, batch 30400, loss[loss=0.1391, simple_loss=0.2151, pruned_loss=0.03152, over 4812.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2249, pruned_loss=0.04265, over 972202.31 frames.], batch size: 24, lr: 4.33e-04
+2022-05-05 01:36:20,215 INFO [train.py:715] (3/8) Epoch 4, batch 30450, loss[loss=0.1361, simple_loss=0.2169, pruned_loss=0.02762, over 4984.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2244, pruned_loss=0.04229, over 972540.50 frames.], batch size: 25, lr: 4.33e-04
+2022-05-05 01:36:59,980 INFO [train.py:715] (3/8) Epoch 4, batch 30500, loss[loss=0.1461, simple_loss=0.2254, pruned_loss=0.03339, over 4900.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2231, pruned_loss=0.04166, over 972257.01 frames.], batch size: 17, lr: 4.33e-04
+2022-05-05 01:37:40,027 INFO [train.py:715] (3/8) Epoch 4, batch 30550, loss[loss=0.1328, simple_loss=0.2063, pruned_loss=0.02968, over 4909.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2233, pruned_loss=0.0416, over 972409.08 frames.], batch size: 18, lr: 4.33e-04
+2022-05-05 01:38:19,337 INFO [train.py:715] (3/8) Epoch 4, batch 30600, loss[loss=0.1334, simple_loss=0.213, pruned_loss=0.02687, over 4781.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2241, pruned_loss=0.04212, over 972683.30 frames.], batch size: 14, lr: 4.33e-04
+2022-05-05 01:38:58,941 INFO [train.py:715] (3/8) Epoch 4, batch 30650, loss[loss=0.1526, simple_loss=0.2298, pruned_loss=0.03773, over 4936.00 frames.], tot_loss[loss=0.155, simple_loss=0.225, pruned_loss=0.04255, over 972488.03 frames.], batch size: 18, lr: 4.33e-04
+2022-05-05 01:39:38,414 INFO [train.py:715] (3/8) Epoch 4, batch 30700, loss[loss=0.1436, simple_loss=0.212, pruned_loss=0.03761, over 4893.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2244, pruned_loss=0.04186, over 972371.22 frames.], batch size: 19, lr: 4.33e-04
+2022-05-05 01:40:18,147 INFO [train.py:715] (3/8) Epoch 4, batch 30750, loss[loss=0.1891, simple_loss=0.258, pruned_loss=0.06008, over 4787.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2244, pruned_loss=0.04169, over 973098.96 frames.], batch size: 18, lr: 4.33e-04
+2022-05-05 01:40:57,684 INFO [train.py:715] (3/8) Epoch 4, batch 30800, loss[loss=0.1765, simple_loss=0.2512, pruned_loss=0.05095, over 4974.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2245, pruned_loss=0.04203, over 972585.81 frames.], batch size: 28, lr: 4.32e-04
+2022-05-05 01:41:37,511 INFO [train.py:715] (3/8) Epoch 4, batch 30850, loss[loss=0.1418, simple_loss=0.2087, pruned_loss=0.03747, over 4907.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2245, pruned_loss=0.04182, over 973090.22 frames.], batch size: 23, lr: 4.32e-04
+2022-05-05 01:42:17,791 INFO [train.py:715] (3/8) Epoch 4, batch 30900, loss[loss=0.1645, simple_loss=0.2181, pruned_loss=0.05545, over 4965.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2243, pruned_loss=0.04194, over 972706.43 frames.], batch size: 14, lr: 4.32e-04
+2022-05-05 01:42:57,263 INFO [train.py:715] (3/8) Epoch 4, batch 30950, loss[loss=0.1762, simple_loss=0.2498, pruned_loss=0.05134, over 4804.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2243, pruned_loss=0.04198, over 972340.72 frames.], batch size: 26, lr: 4.32e-04
+2022-05-05 01:43:36,634 INFO [train.py:715] (3/8) Epoch 4, batch 31000, loss[loss=0.1469, simple_loss=0.215, pruned_loss=0.03944, over 4857.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2244, pruned_loss=0.04204, over 971319.21 frames.], batch size: 20, lr: 4.32e-04
+2022-05-05 01:44:16,109 INFO [train.py:715] (3/8) Epoch 4, batch 31050, loss[loss=0.1895, simple_loss=0.2619, pruned_loss=0.05854, over 4844.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2249, pruned_loss=0.04228, over 972147.54 frames.], batch size: 30, lr: 4.32e-04
+2022-05-05 01:44:55,519 INFO [train.py:715] (3/8) Epoch 4, batch 31100, loss[loss=0.1492, simple_loss=0.2245, pruned_loss=0.03693, over 4972.00 frames.], tot_loss[loss=0.155, simple_loss=0.2252, pruned_loss=0.04244, over 971317.79 frames.], batch size: 15, lr: 4.32e-04
+2022-05-05 01:45:35,034 INFO [train.py:715] (3/8) Epoch 4, batch 31150, loss[loss=0.1414, simple_loss=0.211, pruned_loss=0.03585, over 4862.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2257, pruned_loss=0.04299, over 971503.24 frames.], batch size: 20, lr: 4.32e-04
+2022-05-05 01:46:13,900 INFO [train.py:715] (3/8) Epoch 4, batch 31200, loss[loss=0.1672, simple_loss=0.2257, pruned_loss=0.05441, over 4770.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2247, pruned_loss=0.04292, over 971780.29 frames.], batch size: 18, lr: 4.32e-04
+2022-05-05 01:46:53,972 INFO [train.py:715] (3/8) Epoch 4, batch 31250, loss[loss=0.1777, simple_loss=0.2444, pruned_loss=0.05554, over 4928.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2249, pruned_loss=0.04278, over 973035.31 frames.], batch size: 35, lr: 4.32e-04
+2022-05-05 01:47:33,181 INFO [train.py:715] (3/8) Epoch 4, batch 31300, loss[loss=0.1677, simple_loss=0.2361, pruned_loss=0.04971, over 4783.00 frames.], tot_loss[loss=0.155, simple_loss=0.2249, pruned_loss=0.04259, over 972386.59 frames.], batch size: 14, lr: 4.32e-04
+2022-05-05 01:48:12,187 INFO [train.py:715] (3/8) Epoch 4, batch 31350, loss[loss=0.1686, simple_loss=0.2401, pruned_loss=0.04857, over 4964.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2244, pruned_loss=0.04225, over 972367.18 frames.], batch size: 35, lr: 4.32e-04
+2022-05-05 01:48:52,069 INFO [train.py:715] (3/8) Epoch 4, batch 31400, loss[loss=0.163, simple_loss=0.2387, pruned_loss=0.0436, over 4982.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2253, pruned_loss=0.04268, over 972463.38 frames.], batch size: 28, lr: 4.32e-04
+2022-05-05 01:49:31,804 INFO [train.py:715] (3/8) Epoch 4, batch 31450, loss[loss=0.1506, simple_loss=0.2201, pruned_loss=0.0405, over 4773.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2257, pruned_loss=0.04281, over 972222.90 frames.], batch size: 17, lr: 4.32e-04
+2022-05-05 01:50:11,367 INFO [train.py:715] (3/8) Epoch 4, batch 31500, loss[loss=0.138, simple_loss=0.2236, pruned_loss=0.02616, over 4864.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2254, pruned_loss=0.04297, over 971135.77 frames.], batch size: 20, lr: 4.32e-04
+2022-05-05 01:50:51,744 INFO [train.py:715] (3/8) Epoch 4, batch 31550, loss[loss=0.1622, simple_loss=0.2291, pruned_loss=0.04762, over 4869.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2265, pruned_loss=0.04345, over 972132.69 frames.], batch size: 16, lr: 4.32e-04
+2022-05-05 01:51:32,264 INFO [train.py:715] (3/8) Epoch 4, batch 31600, loss[loss=0.1556, simple_loss=0.2222, pruned_loss=0.04451, over 4862.00 frames.], tot_loss[loss=0.1575, simple_loss=0.227, pruned_loss=0.04398, over 972560.59 frames.], batch size: 30, lr: 4.31e-04
+2022-05-05 01:52:11,916 INFO [train.py:715] (3/8) Epoch 4, batch 31650, loss[loss=0.161, simple_loss=0.2203, pruned_loss=0.05086, over 4784.00 frames.], tot_loss[loss=0.156, simple_loss=0.2255, pruned_loss=0.04327, over 973241.61 frames.], batch size: 12, lr: 4.31e-04
+2022-05-05 01:52:51,497 INFO [train.py:715] (3/8) Epoch 4, batch 31700, loss[loss=0.223, simple_loss=0.2814, pruned_loss=0.0823, over 4835.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2256, pruned_loss=0.04294, over 972618.10 frames.], batch size: 15, lr: 4.31e-04
+2022-05-05 01:53:31,555 INFO [train.py:715] (3/8) Epoch 4, batch 31750, loss[loss=0.1465, simple_loss=0.2215, pruned_loss=0.03572, over 4804.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2254, pruned_loss=0.04288, over 973027.59 frames.], batch size: 21, lr: 4.31e-04
+2022-05-05 01:54:11,603 INFO [train.py:715] (3/8) Epoch 4, batch 31800, loss[loss=0.1251, simple_loss=0.1949, pruned_loss=0.02761, over 4989.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2255, pruned_loss=0.04305, over 973171.65 frames.], batch size: 14, lr: 4.31e-04
+2022-05-05 01:54:51,198 INFO [train.py:715] (3/8) Epoch 4, batch 31850, loss[loss=0.156, simple_loss=0.2241, pruned_loss=0.04401, over 4915.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2255, pruned_loss=0.04295, over 972530.72 frames.], batch size: 19, lr: 4.31e-04
+2022-05-05 01:55:30,806 INFO [train.py:715] (3/8) Epoch 4, batch 31900, loss[loss=0.1158, simple_loss=0.1817, pruned_loss=0.02495, over 4948.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2255, pruned_loss=0.04335, over 971925.98 frames.], batch size: 21, lr: 4.31e-04
+2022-05-05 01:56:11,027 INFO [train.py:715] (3/8) Epoch 4, batch 31950, loss[loss=0.1665, simple_loss=0.2412, pruned_loss=0.04588, over 4902.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2264, pruned_loss=0.04339, over 971009.23 frames.], batch size: 17, lr: 4.31e-04
+2022-05-05 01:56:50,986 INFO [train.py:715] (3/8) Epoch 4, batch 32000, loss[loss=0.1336, simple_loss=0.2083, pruned_loss=0.02948, over 4906.00 frames.], tot_loss[loss=0.1577, simple_loss=0.227, pruned_loss=0.04416, over 971395.34 frames.], batch size: 18, lr: 4.31e-04
+2022-05-05 01:57:30,377 INFO [train.py:715] (3/8) Epoch 4, batch 32050, loss[loss=0.1674, simple_loss=0.2328, pruned_loss=0.05096, over 4914.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04401, over 971698.84 frames.], batch size: 18, lr: 4.31e-04
+2022-05-05 01:58:10,944 INFO [train.py:715] (3/8) Epoch 4, batch 32100, loss[loss=0.1667, simple_loss=0.2309, pruned_loss=0.05129, over 4849.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2263, pruned_loss=0.04347, over 972135.44 frames.], batch size: 30, lr: 4.31e-04
+2022-05-05 01:58:50,867 INFO [train.py:715] (3/8) Epoch 4, batch 32150, loss[loss=0.1438, simple_loss=0.2222, pruned_loss=0.03272, over 4756.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2266, pruned_loss=0.0434, over 971554.69 frames.], batch size: 19, lr: 4.31e-04
+2022-05-05 01:59:30,405 INFO [train.py:715] (3/8) Epoch 4, batch 32200, loss[loss=0.1596, simple_loss=0.2262, pruned_loss=0.04647, over 4891.00 frames.], tot_loss[loss=0.157, simple_loss=0.2268, pruned_loss=0.04362, over 972009.88 frames.], batch size: 19, lr: 4.31e-04
+2022-05-05 02:00:10,362 INFO [train.py:715] (3/8) Epoch 4, batch 32250, loss[loss=0.148, simple_loss=0.213, pruned_loss=0.04153, over 4948.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2252, pruned_loss=0.04275, over 971508.55 frames.], batch size: 35, lr: 4.31e-04
+2022-05-05 02:00:51,157 INFO [train.py:715] (3/8) Epoch 4, batch 32300, loss[loss=0.1362, simple_loss=0.2038, pruned_loss=0.03426, over 4964.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2253, pruned_loss=0.04248, over 971485.71 frames.], batch size: 25, lr: 4.31e-04
+2022-05-05 02:01:31,941 INFO [train.py:715] (3/8) Epoch 4, batch 32350, loss[loss=0.1755, simple_loss=0.2547, pruned_loss=0.04818, over 4814.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2268, pruned_loss=0.04321, over 971344.18 frames.], batch size: 25, lr: 4.31e-04
+2022-05-05 02:02:12,274 INFO [train.py:715] (3/8) Epoch 4, batch 32400, loss[loss=0.1634, simple_loss=0.229, pruned_loss=0.04892, over 4981.00 frames.], tot_loss[loss=0.1559, simple_loss=0.226, pruned_loss=0.04293, over 971006.27 frames.], batch size: 25, lr: 4.30e-04
+2022-05-05 02:02:52,629 INFO [train.py:715] (3/8) Epoch 4, batch 32450, loss[loss=0.1336, simple_loss=0.2091, pruned_loss=0.02905, over 4934.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2262, pruned_loss=0.04316, over 971560.20 frames.], batch size: 18, lr: 4.30e-04
+2022-05-05 02:03:31,863 INFO [train.py:715] (3/8) Epoch 4, batch 32500, loss[loss=0.1232, simple_loss=0.2008, pruned_loss=0.02281, over 4984.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2256, pruned_loss=0.04294, over 971020.96 frames.], batch size: 28, lr: 4.30e-04
+2022-05-05 02:04:11,770 INFO [train.py:715] (3/8) Epoch 4, batch 32550, loss[loss=0.1369, simple_loss=0.2045, pruned_loss=0.03468, over 4955.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2249, pruned_loss=0.04264, over 970790.83 frames.], batch size: 24, lr: 4.30e-04
+2022-05-05 02:04:50,739 INFO [train.py:715] (3/8) Epoch 4, batch 32600, loss[loss=0.1422, simple_loss=0.2165, pruned_loss=0.03394, over 4940.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2254, pruned_loss=0.04253, over 970818.67 frames.], batch size: 21, lr: 4.30e-04
+2022-05-05 02:05:30,802 INFO [train.py:715] (3/8) Epoch 4, batch 32650, loss[loss=0.151, simple_loss=0.217, pruned_loss=0.04254, over 4864.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2253, pruned_loss=0.0426, over 970923.83 frames.], batch size: 32, lr: 4.30e-04
+2022-05-05 02:06:09,913 INFO [train.py:715] (3/8) Epoch 4, batch 32700, loss[loss=0.1599, simple_loss=0.2232, pruned_loss=0.04832, over 4937.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2258, pruned_loss=0.04279, over 971408.07 frames.], batch size: 21, lr: 4.30e-04
+2022-05-05 02:06:49,546 INFO [train.py:715] (3/8) Epoch 4, batch 32750, loss[loss=0.1599, simple_loss=0.2278, pruned_loss=0.04597, over 4963.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2265, pruned_loss=0.04308, over 972451.14 frames.], batch size: 24, lr: 4.30e-04
+2022-05-05 02:07:29,259 INFO [train.py:715] (3/8) Epoch 4, batch 32800, loss[loss=0.1574, simple_loss=0.2301, pruned_loss=0.04236, over 4976.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2267, pruned_loss=0.04298, over 972574.08 frames.], batch size: 14, lr: 4.30e-04
+2022-05-05 02:08:09,338 INFO [train.py:715] (3/8) Epoch 4, batch 32850, loss[loss=0.1726, simple_loss=0.2465, pruned_loss=0.0494, over 4691.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2266, pruned_loss=0.04247, over 971271.63 frames.], batch size: 15, lr: 4.30e-04
+2022-05-05 02:08:49,847 INFO [train.py:715] (3/8) Epoch 4, batch 32900, loss[loss=0.1442, simple_loss=0.2129, pruned_loss=0.03776, over 4939.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2266, pruned_loss=0.04287, over 971688.18 frames.], batch size: 23, lr: 4.30e-04
+2022-05-05 02:09:30,075 INFO [train.py:715] (3/8) Epoch 4, batch 32950, loss[loss=0.1537, simple_loss=0.2127, pruned_loss=0.04736, over 4656.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2265, pruned_loss=0.04332, over 970784.31 frames.], batch size: 13, lr: 4.30e-04
+2022-05-05 02:10:10,303 INFO [train.py:715] (3/8) Epoch 4, batch 33000, loss[loss=0.1473, simple_loss=0.2176, pruned_loss=0.03849, over 4925.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2263, pruned_loss=0.04309, over 970560.09 frames.], batch size: 21, lr: 4.30e-04
+2022-05-05 02:10:10,303 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 02:10:20,090 INFO [train.py:742] (3/8) Epoch 4, validation: loss=0.1115, simple_loss=0.197, pruned_loss=0.01298, over 914524.00 frames.
+2022-05-05 02:11:00,300 INFO [train.py:715] (3/8) Epoch 4, batch 33050, loss[loss=0.1526, simple_loss=0.2267, pruned_loss=0.03928, over 4884.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2264, pruned_loss=0.04316, over 970833.83 frames.], batch size: 16, lr: 4.30e-04
+2022-05-05 02:11:40,006 INFO [train.py:715] (3/8) Epoch 4, batch 33100, loss[loss=0.1516, simple_loss=0.2109, pruned_loss=0.04617, over 4981.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2257, pruned_loss=0.04266, over 971100.30 frames.], batch size: 15, lr: 4.30e-04
+2022-05-05 02:12:20,027 INFO [train.py:715] (3/8) Epoch 4, batch 33150, loss[loss=0.1737, simple_loss=0.2462, pruned_loss=0.05063, over 4912.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2255, pruned_loss=0.04249, over 970701.06 frames.], batch size: 17, lr: 4.30e-04
+2022-05-05 02:13:00,226 INFO [train.py:715] (3/8) Epoch 4, batch 33200, loss[loss=0.1451, simple_loss=0.2068, pruned_loss=0.04166, over 4825.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2254, pruned_loss=0.04259, over 970990.77 frames.], batch size: 15, lr: 4.29e-04
+2022-05-05 02:13:40,204 INFO [train.py:715] (3/8) Epoch 4, batch 33250, loss[loss=0.1445, simple_loss=0.211, pruned_loss=0.03894, over 4923.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2266, pruned_loss=0.04333, over 971455.79 frames.], batch size: 21, lr: 4.29e-04
+2022-05-05 02:14:20,215 INFO [train.py:715] (3/8) Epoch 4, batch 33300, loss[loss=0.1569, simple_loss=0.2226, pruned_loss=0.04563, over 4905.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2268, pruned_loss=0.04329, over 971651.01 frames.], batch size: 17, lr: 4.29e-04
+2022-05-05 02:14:59,209 INFO [train.py:715] (3/8) Epoch 4, batch 33350, loss[loss=0.1482, simple_loss=0.2163, pruned_loss=0.04008, over 4808.00 frames.], tot_loss[loss=0.156, simple_loss=0.2262, pruned_loss=0.04289, over 971755.28 frames.], batch size: 26, lr: 4.29e-04
+2022-05-05 02:15:38,982 INFO [train.py:715] (3/8) Epoch 4, batch 33400, loss[loss=0.1816, simple_loss=0.2534, pruned_loss=0.05487, over 4815.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2262, pruned_loss=0.04273, over 971377.16 frames.], batch size: 15, lr: 4.29e-04
+2022-05-05 02:16:18,843 INFO [train.py:715] (3/8) Epoch 4, batch 33450, loss[loss=0.1599, simple_loss=0.2263, pruned_loss=0.04675, over 4922.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2257, pruned_loss=0.04234, over 972193.20 frames.], batch size: 39, lr: 4.29e-04
+2022-05-05 02:16:58,403 INFO [train.py:715] (3/8) Epoch 4, batch 33500, loss[loss=0.1387, simple_loss=0.2214, pruned_loss=0.02802, over 4914.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2255, pruned_loss=0.04216, over 972440.41 frames.], batch size: 39, lr: 4.29e-04
+2022-05-05 02:17:38,200 INFO [train.py:715] (3/8) Epoch 4, batch 33550, loss[loss=0.1218, simple_loss=0.1896, pruned_loss=0.02696, over 4910.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2252, pruned_loss=0.04226, over 972278.17 frames.], batch size: 23, lr: 4.29e-04
+2022-05-05 02:18:17,698 INFO [train.py:715] (3/8) Epoch 4, batch 33600, loss[loss=0.1609, simple_loss=0.2385, pruned_loss=0.04159, over 4824.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2254, pruned_loss=0.04248, over 973363.36 frames.], batch size: 25, lr: 4.29e-04
+2022-05-05 02:18:57,442 INFO [train.py:715] (3/8) Epoch 4, batch 33650, loss[loss=0.1591, simple_loss=0.2245, pruned_loss=0.0468, over 4958.00 frames.], tot_loss[loss=0.1548, simple_loss=0.225, pruned_loss=0.04235, over 973690.89 frames.], batch size: 24, lr: 4.29e-04
+2022-05-05 02:19:36,829 INFO [train.py:715] (3/8) Epoch 4, batch 33700, loss[loss=0.127, simple_loss=0.1978, pruned_loss=0.02816, over 4823.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2247, pruned_loss=0.04207, over 974021.59 frames.], batch size: 12, lr: 4.29e-04
+2022-05-05 02:20:16,625 INFO [train.py:715] (3/8) Epoch 4, batch 33750, loss[loss=0.2105, simple_loss=0.2672, pruned_loss=0.07692, over 4934.00 frames.], tot_loss[loss=0.155, simple_loss=0.2253, pruned_loss=0.04236, over 973723.62 frames.], batch size: 39, lr: 4.29e-04
+2022-05-05 02:20:56,488 INFO [train.py:715] (3/8) Epoch 4, batch 33800, loss[loss=0.1408, simple_loss=0.2146, pruned_loss=0.03348, over 4834.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2256, pruned_loss=0.04306, over 973012.70 frames.], batch size: 26, lr: 4.29e-04
+2022-05-05 02:21:35,972 INFO [train.py:715] (3/8) Epoch 4, batch 33850, loss[loss=0.1747, simple_loss=0.2448, pruned_loss=0.05228, over 4962.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2253, pruned_loss=0.04271, over 973546.35 frames.], batch size: 35, lr: 4.29e-04
+2022-05-05 02:22:15,605 INFO [train.py:715] (3/8) Epoch 4, batch 33900, loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03341, over 4983.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2243, pruned_loss=0.04206, over 973717.31 frames.], batch size: 25, lr: 4.29e-04
+2022-05-05 02:22:55,357 INFO [train.py:715] (3/8) Epoch 4, batch 33950, loss[loss=0.1314, simple_loss=0.2076, pruned_loss=0.02762, over 4867.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2244, pruned_loss=0.04213, over 974321.52 frames.], batch size: 20, lr: 4.29e-04
+2022-05-05 02:23:35,326 INFO [train.py:715] (3/8) Epoch 4, batch 34000, loss[loss=0.1255, simple_loss=0.1915, pruned_loss=0.02973, over 4789.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2239, pruned_loss=0.04168, over 973956.30 frames.], batch size: 12, lr: 4.28e-04
+2022-05-05 02:24:14,850 INFO [train.py:715] (3/8) Epoch 4, batch 34050, loss[loss=0.1354, simple_loss=0.2026, pruned_loss=0.03415, over 4831.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2243, pruned_loss=0.04192, over 974283.40 frames.], batch size: 15, lr: 4.28e-04
+2022-05-05 02:24:54,569 INFO [train.py:715] (3/8) Epoch 4, batch 34100, loss[loss=0.1549, simple_loss=0.2171, pruned_loss=0.04635, over 4839.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2244, pruned_loss=0.04207, over 973077.78 frames.], batch size: 30, lr: 4.28e-04
+2022-05-05 02:25:34,631 INFO [train.py:715] (3/8) Epoch 4, batch 34150, loss[loss=0.1245, simple_loss=0.2124, pruned_loss=0.01832, over 4888.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2244, pruned_loss=0.04186, over 972884.80 frames.], batch size: 22, lr: 4.28e-04
+2022-05-05 02:26:13,485 INFO [train.py:715] (3/8) Epoch 4, batch 34200, loss[loss=0.1522, simple_loss=0.2258, pruned_loss=0.03927, over 4843.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2238, pruned_loss=0.04152, over 972377.10 frames.], batch size: 15, lr: 4.28e-04
+2022-05-05 02:26:54,315 INFO [train.py:715] (3/8) Epoch 4, batch 34250, loss[loss=0.1414, simple_loss=0.2061, pruned_loss=0.03839, over 4906.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2239, pruned_loss=0.04157, over 971550.50 frames.], batch size: 17, lr: 4.28e-04
+2022-05-05 02:27:34,190 INFO [train.py:715] (3/8) Epoch 4, batch 34300, loss[loss=0.1632, simple_loss=0.2419, pruned_loss=0.04222, over 4916.00 frames.], tot_loss[loss=0.1535, simple_loss=0.224, pruned_loss=0.04148, over 972374.14 frames.], batch size: 17, lr: 4.28e-04
+2022-05-05 02:28:13,945 INFO [train.py:715] (3/8) Epoch 4, batch 34350, loss[loss=0.1506, simple_loss=0.2239, pruned_loss=0.0386, over 4838.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2239, pruned_loss=0.04161, over 973510.09 frames.], batch size: 15, lr: 4.28e-04
+2022-05-05 02:28:53,974 INFO [train.py:715] (3/8) Epoch 4, batch 34400, loss[loss=0.1119, simple_loss=0.1932, pruned_loss=0.01534, over 4651.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2241, pruned_loss=0.04181, over 973240.03 frames.], batch size: 13, lr: 4.28e-04
+2022-05-05 02:29:33,807 INFO [train.py:715] (3/8) Epoch 4, batch 34450, loss[loss=0.1346, simple_loss=0.2061, pruned_loss=0.03155, over 4793.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2246, pruned_loss=0.04195, over 972632.07 frames.], batch size: 13, lr: 4.28e-04
+2022-05-05 02:30:14,469 INFO [train.py:715] (3/8) Epoch 4, batch 34500, loss[loss=0.1349, simple_loss=0.2106, pruned_loss=0.02965, over 4819.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2256, pruned_loss=0.04273, over 972385.26 frames.], batch size: 27, lr: 4.28e-04
+2022-05-05 02:30:53,313 INFO [train.py:715] (3/8) Epoch 4, batch 34550, loss[loss=0.1432, simple_loss=0.2124, pruned_loss=0.03699, over 4987.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2254, pruned_loss=0.04316, over 972559.53 frames.], batch size: 31, lr: 4.28e-04
+2022-05-05 02:31:33,260 INFO [train.py:715] (3/8) Epoch 4, batch 34600, loss[loss=0.1564, simple_loss=0.2275, pruned_loss=0.04263, over 4709.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2251, pruned_loss=0.04281, over 972253.90 frames.], batch size: 15, lr: 4.28e-04
+2022-05-05 02:32:13,236 INFO [train.py:715] (3/8) Epoch 4, batch 34650, loss[loss=0.1695, simple_loss=0.2462, pruned_loss=0.04642, over 4835.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2248, pruned_loss=0.04311, over 972168.58 frames.], batch size: 25, lr: 4.28e-04
+2022-05-05 02:32:52,589 INFO [train.py:715] (3/8) Epoch 4, batch 34700, loss[loss=0.1396, simple_loss=0.1996, pruned_loss=0.03979, over 4782.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2249, pruned_loss=0.04268, over 972283.13 frames.], batch size: 14, lr: 4.28e-04
+2022-05-05 02:33:30,871 INFO [train.py:715] (3/8) Epoch 4, batch 34750, loss[loss=0.1339, simple_loss=0.203, pruned_loss=0.03245, over 4785.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2246, pruned_loss=0.04213, over 971349.66 frames.], batch size: 18, lr: 4.28e-04
+2022-05-05 02:34:07,931 INFO [train.py:715] (3/8) Epoch 4, batch 34800, loss[loss=0.1653, simple_loss=0.2537, pruned_loss=0.03847, over 4909.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2254, pruned_loss=0.04255, over 972772.08 frames.], batch size: 19, lr: 4.27e-04
+2022-05-05 02:34:57,760 INFO [train.py:715] (3/8) Epoch 5, batch 0, loss[loss=0.1466, simple_loss=0.2191, pruned_loss=0.03701, over 4883.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2191, pruned_loss=0.03701, over 4883.00 frames.], batch size: 22, lr: 4.02e-04
+2022-05-05 02:35:38,097 INFO [train.py:715] (3/8) Epoch 5, batch 50, loss[loss=0.1479, simple_loss=0.2135, pruned_loss=0.0411, over 4983.00 frames.], tot_loss[loss=0.152, simple_loss=0.2225, pruned_loss=0.04079, over 219941.55 frames.], batch size: 14, lr: 4.02e-04
+2022-05-05 02:36:17,797 INFO [train.py:715] (3/8) Epoch 5, batch 100, loss[loss=0.105, simple_loss=0.1897, pruned_loss=0.01019, over 4988.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2225, pruned_loss=0.0412, over 386426.17 frames.], batch size: 28, lr: 4.02e-04
+2022-05-05 02:36:57,768 INFO [train.py:715] (3/8) Epoch 5, batch 150, loss[loss=0.176, simple_loss=0.2434, pruned_loss=0.05428, over 4810.00 frames.], tot_loss[loss=0.151, simple_loss=0.2215, pruned_loss=0.04025, over 516333.59 frames.], batch size: 21, lr: 4.02e-04
+2022-05-05 02:37:38,284 INFO [train.py:715] (3/8) Epoch 5, batch 200, loss[loss=0.1868, simple_loss=0.2575, pruned_loss=0.05803, over 4905.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2231, pruned_loss=0.04129, over 617304.86 frames.], batch size: 17, lr: 4.02e-04
+2022-05-05 02:38:17,737 INFO [train.py:715] (3/8) Epoch 5, batch 250, loss[loss=0.1481, simple_loss=0.2163, pruned_loss=0.03999, over 4809.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2234, pruned_loss=0.04176, over 697023.14 frames.], batch size: 15, lr: 4.02e-04
+2022-05-05 02:38:57,153 INFO [train.py:715] (3/8) Epoch 5, batch 300, loss[loss=0.1634, simple_loss=0.23, pruned_loss=0.04835, over 4983.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2239, pruned_loss=0.04254, over 758076.30 frames.], batch size: 28, lr: 4.01e-04
+2022-05-05 02:39:36,891 INFO [train.py:715] (3/8) Epoch 5, batch 350, loss[loss=0.177, simple_loss=0.2533, pruned_loss=0.05042, over 4950.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2238, pruned_loss=0.04199, over 805376.63 frames.], batch size: 21, lr: 4.01e-04
+2022-05-05 02:40:16,657 INFO [train.py:715] (3/8) Epoch 5, batch 400, loss[loss=0.1733, simple_loss=0.2451, pruned_loss=0.05074, over 4814.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2238, pruned_loss=0.04185, over 842300.13 frames.], batch size: 25, lr: 4.01e-04
+2022-05-05 02:40:56,048 INFO [train.py:715] (3/8) Epoch 5, batch 450, loss[loss=0.1626, simple_loss=0.2355, pruned_loss=0.04485, over 4818.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2238, pruned_loss=0.04173, over 870653.86 frames.], batch size: 27, lr: 4.01e-04
+2022-05-05 02:41:35,796 INFO [train.py:715] (3/8) Epoch 5, batch 500, loss[loss=0.1481, simple_loss=0.2224, pruned_loss=0.03684, over 4965.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2236, pruned_loss=0.04181, over 892788.87 frames.], batch size: 24, lr: 4.01e-04
+2022-05-05 02:42:15,655 INFO [train.py:715] (3/8) Epoch 5, batch 550, loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02943, over 4932.00 frames.], tot_loss[loss=0.1531, simple_loss=0.223, pruned_loss=0.04159, over 909874.92 frames.], batch size: 35, lr: 4.01e-04
+2022-05-05 02:42:54,757 INFO [train.py:715] (3/8) Epoch 5, batch 600, loss[loss=0.1475, simple_loss=0.2172, pruned_loss=0.03889, over 4886.00 frames.], tot_loss[loss=0.153, simple_loss=0.2229, pruned_loss=0.04152, over 924455.23 frames.], batch size: 16, lr: 4.01e-04
+2022-05-05 02:43:34,140 INFO [train.py:715] (3/8) Epoch 5, batch 650, loss[loss=0.1559, simple_loss=0.2194, pruned_loss=0.04621, over 4781.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2239, pruned_loss=0.04202, over 934893.96 frames.], batch size: 17, lr: 4.01e-04
+2022-05-05 02:44:13,847 INFO [train.py:715] (3/8) Epoch 5, batch 700, loss[loss=0.1515, simple_loss=0.2265, pruned_loss=0.03828, over 4802.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2229, pruned_loss=0.04134, over 943674.11 frames.], batch size: 25, lr: 4.01e-04
+2022-05-05 02:44:53,908 INFO [train.py:715] (3/8) Epoch 5, batch 750, loss[loss=0.1496, simple_loss=0.2232, pruned_loss=0.03797, over 4901.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2237, pruned_loss=0.04189, over 950002.62 frames.], batch size: 22, lr: 4.01e-04
+2022-05-05 02:45:33,280 INFO [train.py:715] (3/8) Epoch 5, batch 800, loss[loss=0.1696, simple_loss=0.2357, pruned_loss=0.05177, over 4689.00 frames.], tot_loss[loss=0.1528, simple_loss=0.223, pruned_loss=0.0413, over 955492.39 frames.], batch size: 15, lr: 4.01e-04
+2022-05-05 02:46:12,787 INFO [train.py:715] (3/8) Epoch 5, batch 850, loss[loss=0.2049, simple_loss=0.2589, pruned_loss=0.07542, over 4833.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2234, pruned_loss=0.04204, over 958675.03 frames.], batch size: 30, lr: 4.01e-04
+2022-05-05 02:46:52,362 INFO [train.py:715] (3/8) Epoch 5, batch 900, loss[loss=0.1446, simple_loss=0.2099, pruned_loss=0.03965, over 4907.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2229, pruned_loss=0.042, over 962087.51 frames.], batch size: 18, lr: 4.01e-04
+2022-05-05 02:47:31,842 INFO [train.py:715] (3/8) Epoch 5, batch 950, loss[loss=0.1743, simple_loss=0.2436, pruned_loss=0.0525, over 4742.00 frames.], tot_loss[loss=0.154, simple_loss=0.2233, pruned_loss=0.04236, over 963870.58 frames.], batch size: 16, lr: 4.01e-04
+2022-05-05 02:48:11,354 INFO [train.py:715] (3/8) Epoch 5, batch 1000, loss[loss=0.1596, simple_loss=0.2248, pruned_loss=0.04724, over 4986.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2243, pruned_loss=0.04256, over 965252.54 frames.], batch size: 35, lr: 4.01e-04
+2022-05-05 02:48:50,614 INFO [train.py:715] (3/8) Epoch 5, batch 1050, loss[loss=0.1504, simple_loss=0.2176, pruned_loss=0.04163, over 4830.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2235, pruned_loss=0.04243, over 966957.09 frames.], batch size: 30, lr: 4.01e-04
+2022-05-05 02:49:30,325 INFO [train.py:715] (3/8) Epoch 5, batch 1100, loss[loss=0.1298, simple_loss=0.2105, pruned_loss=0.02455, over 4789.00 frames.], tot_loss[loss=0.1538, simple_loss=0.223, pruned_loss=0.04229, over 967864.07 frames.], batch size: 21, lr: 4.01e-04
+2022-05-05 02:50:09,330 INFO [train.py:715] (3/8) Epoch 5, batch 1150, loss[loss=0.1537, simple_loss=0.2247, pruned_loss=0.04134, over 4753.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2222, pruned_loss=0.04126, over 968147.15 frames.], batch size: 16, lr: 4.00e-04
+2022-05-05 02:50:49,094 INFO [train.py:715] (3/8) Epoch 5, batch 1200, loss[loss=0.1371, simple_loss=0.206, pruned_loss=0.03413, over 4751.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2209, pruned_loss=0.04046, over 969030.10 frames.], batch size: 12, lr: 4.00e-04
+2022-05-05 02:51:29,238 INFO [train.py:715] (3/8) Epoch 5, batch 1250, loss[loss=0.1456, simple_loss=0.2189, pruned_loss=0.03611, over 4986.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2218, pruned_loss=0.04098, over 970283.84 frames.], batch size: 14, lr: 4.00e-04
+2022-05-05 02:52:08,409 INFO [train.py:715] (3/8) Epoch 5, batch 1300, loss[loss=0.1739, simple_loss=0.2441, pruned_loss=0.05184, over 4760.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2223, pruned_loss=0.04106, over 970143.79 frames.], batch size: 16, lr: 4.00e-04
+2022-05-05 02:52:48,192 INFO [train.py:715] (3/8) Epoch 5, batch 1350, loss[loss=0.1519, simple_loss=0.2273, pruned_loss=0.03827, over 4713.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2226, pruned_loss=0.04112, over 970185.41 frames.], batch size: 15, lr: 4.00e-04
+2022-05-05 02:53:27,483 INFO [train.py:715] (3/8) Epoch 5, batch 1400, loss[loss=0.1494, simple_loss=0.2043, pruned_loss=0.04724, over 4868.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2228, pruned_loss=0.04113, over 971353.12 frames.], batch size: 13, lr: 4.00e-04
+2022-05-05 02:54:07,305 INFO [train.py:715] (3/8) Epoch 5, batch 1450, loss[loss=0.146, simple_loss=0.2087, pruned_loss=0.04166, over 4851.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04043, over 971379.62 frames.], batch size: 32, lr: 4.00e-04
+2022-05-05 02:54:46,729 INFO [train.py:715] (3/8) Epoch 5, batch 1500, loss[loss=0.161, simple_loss=0.2307, pruned_loss=0.04565, over 4978.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2224, pruned_loss=0.0407, over 971588.99 frames.], batch size: 28, lr: 4.00e-04
+2022-05-05 02:55:25,724 INFO [train.py:715] (3/8) Epoch 5, batch 1550, loss[loss=0.1306, simple_loss=0.2026, pruned_loss=0.02928, over 4898.00 frames.], tot_loss[loss=0.1522, simple_loss=0.223, pruned_loss=0.04077, over 971874.97 frames.], batch size: 19, lr: 4.00e-04
+2022-05-05 02:56:05,366 INFO [train.py:715] (3/8) Epoch 5, batch 1600, loss[loss=0.1564, simple_loss=0.2332, pruned_loss=0.03978, over 4944.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2241, pruned_loss=0.04143, over 971788.37 frames.], batch size: 23, lr: 4.00e-04
+2022-05-05 02:56:45,701 INFO [train.py:715] (3/8) Epoch 5, batch 1650, loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.03499, over 4938.00 frames.], tot_loss[loss=0.1535, simple_loss=0.224, pruned_loss=0.04147, over 971253.22 frames.], batch size: 23, lr: 4.00e-04
+2022-05-05 02:57:24,646 INFO [train.py:715] (3/8) Epoch 5, batch 1700, loss[loss=0.1508, simple_loss=0.2199, pruned_loss=0.0409, over 4775.00 frames.], tot_loss[loss=0.153, simple_loss=0.2233, pruned_loss=0.04135, over 971240.20 frames.], batch size: 17, lr: 4.00e-04
+2022-05-05 02:58:05,303 INFO [train.py:715] (3/8) Epoch 5, batch 1750, loss[loss=0.1694, simple_loss=0.2394, pruned_loss=0.04974, over 4791.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2232, pruned_loss=0.04125, over 972008.88 frames.], batch size: 14, lr: 4.00e-04
+2022-05-05 02:58:45,447 INFO [train.py:715] (3/8) Epoch 5, batch 1800, loss[loss=0.1502, simple_loss=0.2186, pruned_loss=0.04091, over 4933.00 frames.], tot_loss[loss=0.153, simple_loss=0.223, pruned_loss=0.04147, over 972285.77 frames.], batch size: 21, lr: 4.00e-04
+2022-05-05 02:59:25,896 INFO [train.py:715] (3/8) Epoch 5, batch 1850, loss[loss=0.1325, simple_loss=0.2083, pruned_loss=0.02836, over 4898.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2235, pruned_loss=0.0415, over 971872.47 frames.], batch size: 22, lr: 4.00e-04
+2022-05-05 03:00:06,295 INFO [train.py:715] (3/8) Epoch 5, batch 1900, loss[loss=0.1634, simple_loss=0.2366, pruned_loss=0.04509, over 4970.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2244, pruned_loss=0.04229, over 972062.18 frames.], batch size: 39, lr: 4.00e-04
+2022-05-05 03:00:46,053 INFO [train.py:715] (3/8) Epoch 5, batch 1950, loss[loss=0.1399, simple_loss=0.2113, pruned_loss=0.03421, over 4931.00 frames.], tot_loss[loss=0.154, simple_loss=0.2237, pruned_loss=0.04212, over 972736.37 frames.], batch size: 29, lr: 4.00e-04
+2022-05-05 03:01:29,129 INFO [train.py:715] (3/8) Epoch 5, batch 2000, loss[loss=0.1591, simple_loss=0.2237, pruned_loss=0.0472, over 4967.00 frames.], tot_loss[loss=0.153, simple_loss=0.2229, pruned_loss=0.0416, over 973154.56 frames.], batch size: 35, lr: 4.00e-04
+2022-05-05 03:02:09,159 INFO [train.py:715] (3/8) Epoch 5, batch 2050, loss[loss=0.1413, simple_loss=0.2112, pruned_loss=0.03571, over 4778.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2233, pruned_loss=0.04156, over 973213.37 frames.], batch size: 19, lr: 3.99e-04
+2022-05-05 03:02:49,518 INFO [train.py:715] (3/8) Epoch 5, batch 2100, loss[loss=0.1705, simple_loss=0.2366, pruned_loss=0.05221, over 4827.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2231, pruned_loss=0.04162, over 973015.13 frames.], batch size: 27, lr: 3.99e-04
+2022-05-05 03:03:30,103 INFO [train.py:715] (3/8) Epoch 5, batch 2150, loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03327, over 4939.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2229, pruned_loss=0.04137, over 973043.61 frames.], batch size: 23, lr: 3.99e-04
+2022-05-05 03:04:09,668 INFO [train.py:715] (3/8) Epoch 5, batch 2200, loss[loss=0.1332, simple_loss=0.2002, pruned_loss=0.03308, over 4959.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2226, pruned_loss=0.04161, over 972779.85 frames.], batch size: 35, lr: 3.99e-04
+2022-05-05 03:04:50,064 INFO [train.py:715] (3/8) Epoch 5, batch 2250, loss[loss=0.1652, simple_loss=0.2429, pruned_loss=0.04377, over 4690.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2233, pruned_loss=0.04187, over 972968.65 frames.], batch size: 15, lr: 3.99e-04
+2022-05-05 03:05:30,780 INFO [train.py:715] (3/8) Epoch 5, batch 2300, loss[loss=0.1449, simple_loss=0.2104, pruned_loss=0.0397, over 4867.00 frames.], tot_loss[loss=0.1535, simple_loss=0.223, pruned_loss=0.04199, over 973582.99 frames.], batch size: 32, lr: 3.99e-04
+2022-05-05 03:06:10,990 INFO [train.py:715] (3/8) Epoch 5, batch 2350, loss[loss=0.1245, simple_loss=0.1971, pruned_loss=0.02596, over 4925.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2231, pruned_loss=0.04173, over 973483.23 frames.], batch size: 21, lr: 3.99e-04
+2022-05-05 03:06:51,192 INFO [train.py:715] (3/8) Epoch 5, batch 2400, loss[loss=0.1533, simple_loss=0.2272, pruned_loss=0.03963, over 4899.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2226, pruned_loss=0.04145, over 972975.54 frames.], batch size: 19, lr: 3.99e-04
+2022-05-05 03:07:31,710 INFO [train.py:715] (3/8) Epoch 5, batch 2450, loss[loss=0.1655, simple_loss=0.2333, pruned_loss=0.04886, over 4697.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2229, pruned_loss=0.04134, over 972490.19 frames.], batch size: 15, lr: 3.99e-04
+2022-05-05 03:08:12,417 INFO [train.py:715] (3/8) Epoch 5, batch 2500, loss[loss=0.128, simple_loss=0.2048, pruned_loss=0.02565, over 4940.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2226, pruned_loss=0.04125, over 971789.88 frames.], batch size: 23, lr: 3.99e-04
+2022-05-05 03:08:52,450 INFO [train.py:715] (3/8) Epoch 5, batch 2550, loss[loss=0.1974, simple_loss=0.2551, pruned_loss=0.06979, over 4957.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2242, pruned_loss=0.04216, over 971620.46 frames.], batch size: 15, lr: 3.99e-04
+2022-05-05 03:09:33,373 INFO [train.py:715] (3/8) Epoch 5, batch 2600, loss[loss=0.153, simple_loss=0.223, pruned_loss=0.04151, over 4839.00 frames.], tot_loss[loss=0.154, simple_loss=0.224, pruned_loss=0.04204, over 971421.67 frames.], batch size: 26, lr: 3.99e-04
+2022-05-05 03:10:13,555 INFO [train.py:715] (3/8) Epoch 5, batch 2650, loss[loss=0.1524, simple_loss=0.2249, pruned_loss=0.03993, over 4887.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2244, pruned_loss=0.04221, over 970922.29 frames.], batch size: 17, lr: 3.99e-04
+2022-05-05 03:10:54,123 INFO [train.py:715] (3/8) Epoch 5, batch 2700, loss[loss=0.1438, simple_loss=0.2101, pruned_loss=0.03878, over 4810.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2248, pruned_loss=0.04241, over 971022.44 frames.], batch size: 21, lr: 3.99e-04
+2022-05-05 03:11:34,318 INFO [train.py:715] (3/8) Epoch 5, batch 2750, loss[loss=0.1214, simple_loss=0.1983, pruned_loss=0.02223, over 4976.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2251, pruned_loss=0.0425, over 971366.68 frames.], batch size: 14, lr: 3.99e-04
+2022-05-05 03:12:14,290 INFO [train.py:715] (3/8) Epoch 5, batch 2800, loss[loss=0.1684, simple_loss=0.2398, pruned_loss=0.04852, over 4811.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2249, pruned_loss=0.04214, over 971734.08 frames.], batch size: 24, lr: 3.99e-04
+2022-05-05 03:12:54,885 INFO [train.py:715] (3/8) Epoch 5, batch 2850, loss[loss=0.1407, simple_loss=0.2197, pruned_loss=0.03082, over 4971.00 frames.], tot_loss[loss=0.1538, simple_loss=0.224, pruned_loss=0.04182, over 971597.59 frames.], batch size: 24, lr: 3.99e-04
+2022-05-05 03:13:35,010 INFO [train.py:715] (3/8) Epoch 5, batch 2900, loss[loss=0.1486, simple_loss=0.2308, pruned_loss=0.03317, over 4894.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2244, pruned_loss=0.04188, over 971815.08 frames.], batch size: 19, lr: 3.99e-04
+2022-05-05 03:14:15,399 INFO [train.py:715] (3/8) Epoch 5, batch 2950, loss[loss=0.1697, simple_loss=0.237, pruned_loss=0.05124, over 4916.00 frames.], tot_loss[loss=0.1534, simple_loss=0.224, pruned_loss=0.0414, over 972737.55 frames.], batch size: 17, lr: 3.98e-04
+2022-05-05 03:14:54,477 INFO [train.py:715] (3/8) Epoch 5, batch 3000, loss[loss=0.1537, simple_loss=0.2212, pruned_loss=0.0431, over 4913.00 frames.], tot_loss[loss=0.1528, simple_loss=0.223, pruned_loss=0.04126, over 972509.76 frames.], batch size: 39, lr: 3.98e-04
+2022-05-05 03:14:54,478 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 03:15:03,919 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.1108, simple_loss=0.1962, pruned_loss=0.01274, over 914524.00 frames.
+2022-05-05 03:15:42,396 INFO [train.py:715] (3/8) Epoch 5, batch 3050, loss[loss=0.1229, simple_loss=0.1935, pruned_loss=0.0262, over 4792.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2226, pruned_loss=0.04097, over 972119.33 frames.], batch size: 24, lr: 3.98e-04
+2022-05-05 03:16:21,555 INFO [train.py:715] (3/8) Epoch 5, batch 3100, loss[loss=0.1772, simple_loss=0.2352, pruned_loss=0.05961, over 4864.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2234, pruned_loss=0.04156, over 972818.44 frames.], batch size: 32, lr: 3.98e-04
+2022-05-05 03:17:00,520 INFO [train.py:715] (3/8) Epoch 5, batch 3150, loss[loss=0.1491, simple_loss=0.2288, pruned_loss=0.03464, over 4828.00 frames.], tot_loss[loss=0.153, simple_loss=0.2236, pruned_loss=0.04118, over 971737.05 frames.], batch size: 26, lr: 3.98e-04
+2022-05-05 03:17:40,035 INFO [train.py:715] (3/8) Epoch 5, batch 3200, loss[loss=0.1425, simple_loss=0.2071, pruned_loss=0.03895, over 4978.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2234, pruned_loss=0.04123, over 971603.91 frames.], batch size: 15, lr: 3.98e-04
+2022-05-05 03:18:19,743 INFO [train.py:715] (3/8) Epoch 5, batch 3250, loss[loss=0.1656, simple_loss=0.2293, pruned_loss=0.05098, over 4877.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.04081, over 971574.10 frames.], batch size: 32, lr: 3.98e-04
+2022-05-05 03:18:58,957 INFO [train.py:715] (3/8) Epoch 5, batch 3300, loss[loss=0.1506, simple_loss=0.223, pruned_loss=0.03913, over 4827.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2229, pruned_loss=0.0411, over 972549.08 frames.], batch size: 26, lr: 3.98e-04
+2022-05-05 03:19:38,239 INFO [train.py:715] (3/8) Epoch 5, batch 3350, loss[loss=0.1478, simple_loss=0.2174, pruned_loss=0.03912, over 4965.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2231, pruned_loss=0.04112, over 973108.78 frames.], batch size: 15, lr: 3.98e-04
+2022-05-05 03:20:17,970 INFO [train.py:715] (3/8) Epoch 5, batch 3400, loss[loss=0.1687, simple_loss=0.2296, pruned_loss=0.05389, over 4859.00 frames.], tot_loss[loss=0.152, simple_loss=0.2224, pruned_loss=0.04078, over 972581.10 frames.], batch size: 38, lr: 3.98e-04
+2022-05-05 03:20:57,513 INFO [train.py:715] (3/8) Epoch 5, batch 3450, loss[loss=0.1167, simple_loss=0.1954, pruned_loss=0.01895, over 4828.00 frames.], tot_loss[loss=0.152, simple_loss=0.2223, pruned_loss=0.04084, over 972611.54 frames.], batch size: 13, lr: 3.98e-04
+2022-05-05 03:21:36,806 INFO [train.py:715] (3/8) Epoch 5, batch 3500, loss[loss=0.127, simple_loss=0.2079, pruned_loss=0.0231, over 4951.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2221, pruned_loss=0.04119, over 971616.57 frames.], batch size: 29, lr: 3.98e-04
+2022-05-05 03:22:16,030 INFO [train.py:715] (3/8) Epoch 5, batch 3550, loss[loss=0.1413, simple_loss=0.234, pruned_loss=0.0243, over 4964.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2224, pruned_loss=0.04102, over 972370.38 frames.], batch size: 24, lr: 3.98e-04
+2022-05-05 03:22:55,528 INFO [train.py:715] (3/8) Epoch 5, batch 3600, loss[loss=0.1141, simple_loss=0.1915, pruned_loss=0.01835, over 4787.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2225, pruned_loss=0.04084, over 972522.31 frames.], batch size: 24, lr: 3.98e-04
+2022-05-05 03:23:34,520 INFO [train.py:715] (3/8) Epoch 5, batch 3650, loss[loss=0.1252, simple_loss=0.1902, pruned_loss=0.03017, over 4885.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2217, pruned_loss=0.04032, over 972589.70 frames.], batch size: 17, lr: 3.98e-04
+2022-05-05 03:24:13,762 INFO [train.py:715] (3/8) Epoch 5, batch 3700, loss[loss=0.1607, simple_loss=0.2277, pruned_loss=0.04688, over 4847.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2217, pruned_loss=0.04037, over 972538.52 frames.], batch size: 20, lr: 3.98e-04
+2022-05-05 03:24:53,921 INFO [train.py:715] (3/8) Epoch 5, batch 3750, loss[loss=0.1672, simple_loss=0.2357, pruned_loss=0.04938, over 4921.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2228, pruned_loss=0.04143, over 972933.90 frames.], batch size: 18, lr: 3.98e-04
+2022-05-05 03:25:33,698 INFO [train.py:715] (3/8) Epoch 5, batch 3800, loss[loss=0.1409, simple_loss=0.2118, pruned_loss=0.03496, over 4938.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2225, pruned_loss=0.04141, over 972415.04 frames.], batch size: 23, lr: 3.97e-04
+2022-05-05 03:26:13,091 INFO [train.py:715] (3/8) Epoch 5, batch 3850, loss[loss=0.1655, simple_loss=0.2426, pruned_loss=0.04417, over 4879.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2225, pruned_loss=0.04137, over 973113.64 frames.], batch size: 22, lr: 3.97e-04
+2022-05-05 03:26:52,958 INFO [train.py:715] (3/8) Epoch 5, batch 3900, loss[loss=0.1681, simple_loss=0.2328, pruned_loss=0.05165, over 4906.00 frames.], tot_loss[loss=0.1527, simple_loss=0.223, pruned_loss=0.04126, over 973042.95 frames.], batch size: 17, lr: 3.97e-04
+2022-05-05 03:27:32,998 INFO [train.py:715] (3/8) Epoch 5, batch 3950, loss[loss=0.1541, simple_loss=0.2238, pruned_loss=0.04219, over 4731.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.04108, over 972457.73 frames.], batch size: 12, lr: 3.97e-04
+2022-05-05 03:28:13,082 INFO [train.py:715] (3/8) Epoch 5, batch 4000, loss[loss=0.147, simple_loss=0.2155, pruned_loss=0.03926, over 4816.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2222, pruned_loss=0.04101, over 972771.13 frames.], batch size: 27, lr: 3.97e-04
+2022-05-05 03:28:53,736 INFO [train.py:715] (3/8) Epoch 5, batch 4050, loss[loss=0.2055, simple_loss=0.2709, pruned_loss=0.07011, over 4807.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2223, pruned_loss=0.04111, over 972314.84 frames.], batch size: 21, lr: 3.97e-04
+2022-05-05 03:29:33,846 INFO [train.py:715] (3/8) Epoch 5, batch 4100, loss[loss=0.1527, simple_loss=0.2242, pruned_loss=0.04061, over 4972.00 frames.], tot_loss[loss=0.1518, simple_loss=0.222, pruned_loss=0.04083, over 972607.87 frames.], batch size: 14, lr: 3.97e-04
+2022-05-05 03:30:14,067 INFO [train.py:715] (3/8) Epoch 5, batch 4150, loss[loss=0.1343, simple_loss=0.1959, pruned_loss=0.03633, over 4831.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.04099, over 973149.33 frames.], batch size: 15, lr: 3.97e-04
+2022-05-05 03:30:53,444 INFO [train.py:715] (3/8) Epoch 5, batch 4200, loss[loss=0.1613, simple_loss=0.2303, pruned_loss=0.04616, over 4809.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2239, pruned_loss=0.04154, over 973226.84 frames.], batch size: 13, lr: 3.97e-04
+2022-05-05 03:31:32,791 INFO [train.py:715] (3/8) Epoch 5, batch 4250, loss[loss=0.163, simple_loss=0.227, pruned_loss=0.04949, over 4857.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2235, pruned_loss=0.04121, over 973460.95 frames.], batch size: 13, lr: 3.97e-04
+2022-05-05 03:32:12,485 INFO [train.py:715] (3/8) Epoch 5, batch 4300, loss[loss=0.1662, simple_loss=0.229, pruned_loss=0.05172, over 4852.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2232, pruned_loss=0.04096, over 973809.71 frames.], batch size: 32, lr: 3.97e-04
+2022-05-05 03:32:52,102 INFO [train.py:715] (3/8) Epoch 5, batch 4350, loss[loss=0.1762, simple_loss=0.2422, pruned_loss=0.05506, over 4914.00 frames.], tot_loss[loss=0.1535, simple_loss=0.224, pruned_loss=0.04145, over 973323.48 frames.], batch size: 23, lr: 3.97e-04
+2022-05-05 03:33:32,068 INFO [train.py:715] (3/8) Epoch 5, batch 4400, loss[loss=0.179, simple_loss=0.2501, pruned_loss=0.05398, over 4854.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2241, pruned_loss=0.04167, over 972817.63 frames.], batch size: 20, lr: 3.97e-04
+2022-05-05 03:34:10,945 INFO [train.py:715] (3/8) Epoch 5, batch 4450, loss[loss=0.1525, simple_loss=0.2177, pruned_loss=0.0436, over 4966.00 frames.], tot_loss[loss=0.1527, simple_loss=0.223, pruned_loss=0.04118, over 973029.99 frames.], batch size: 15, lr: 3.97e-04
+2022-05-05 03:34:50,790 INFO [train.py:715] (3/8) Epoch 5, batch 4500, loss[loss=0.1235, simple_loss=0.1947, pruned_loss=0.0262, over 4916.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2237, pruned_loss=0.04155, over 973392.13 frames.], batch size: 17, lr: 3.97e-04
+2022-05-05 03:35:30,122 INFO [train.py:715] (3/8) Epoch 5, batch 4550, loss[loss=0.1667, simple_loss=0.2384, pruned_loss=0.04747, over 4981.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2227, pruned_loss=0.04079, over 973206.05 frames.], batch size: 28, lr: 3.97e-04
+2022-05-05 03:36:09,740 INFO [train.py:715] (3/8) Epoch 5, batch 4600, loss[loss=0.1597, simple_loss=0.2248, pruned_loss=0.0473, over 4821.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2223, pruned_loss=0.04056, over 972633.51 frames.], batch size: 26, lr: 3.97e-04
+2022-05-05 03:36:50,098 INFO [train.py:715] (3/8) Epoch 5, batch 4650, loss[loss=0.169, simple_loss=0.2496, pruned_loss=0.0442, over 4928.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2221, pruned_loss=0.04078, over 972133.76 frames.], batch size: 23, lr: 3.97e-04
+2022-05-05 03:37:30,431 INFO [train.py:715] (3/8) Epoch 5, batch 4700, loss[loss=0.1718, simple_loss=0.2184, pruned_loss=0.06256, over 4823.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2225, pruned_loss=0.04095, over 972459.91 frames.], batch size: 15, lr: 3.96e-04
+2022-05-05 03:38:10,931 INFO [train.py:715] (3/8) Epoch 5, batch 4750, loss[loss=0.1281, simple_loss=0.2079, pruned_loss=0.0242, over 4873.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2227, pruned_loss=0.04104, over 972366.95 frames.], batch size: 16, lr: 3.96e-04
+2022-05-05 03:38:50,697 INFO [train.py:715] (3/8) Epoch 5, batch 4800, loss[loss=0.2204, simple_loss=0.2712, pruned_loss=0.08482, over 4971.00 frames.], tot_loss[loss=0.1528, simple_loss=0.223, pruned_loss=0.04125, over 972612.88 frames.], batch size: 15, lr: 3.96e-04
+2022-05-05 03:39:31,182 INFO [train.py:715] (3/8) Epoch 5, batch 4850, loss[loss=0.1497, simple_loss=0.226, pruned_loss=0.03672, over 4811.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2235, pruned_loss=0.04147, over 972546.53 frames.], batch size: 13, lr: 3.96e-04
+2022-05-05 03:40:11,787 INFO [train.py:715] (3/8) Epoch 5, batch 4900, loss[loss=0.1739, simple_loss=0.2597, pruned_loss=0.04401, over 4938.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2227, pruned_loss=0.04141, over 972077.06 frames.], batch size: 21, lr: 3.96e-04
+2022-05-05 03:40:51,916 INFO [train.py:715] (3/8) Epoch 5, batch 4950, loss[loss=0.1789, simple_loss=0.2427, pruned_loss=0.05761, over 4787.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2235, pruned_loss=0.0419, over 971199.04 frames.], batch size: 18, lr: 3.96e-04
+2022-05-05 03:41:32,222 INFO [train.py:715] (3/8) Epoch 5, batch 5000, loss[loss=0.1412, simple_loss=0.2236, pruned_loss=0.02936, over 4803.00 frames.], tot_loss[loss=0.153, simple_loss=0.2231, pruned_loss=0.04142, over 971139.50 frames.], batch size: 21, lr: 3.96e-04
+2022-05-05 03:42:13,227 INFO [train.py:715] (3/8) Epoch 5, batch 5050, loss[loss=0.1075, simple_loss=0.1781, pruned_loss=0.01846, over 4759.00 frames.], tot_loss[loss=0.153, simple_loss=0.2235, pruned_loss=0.04123, over 971587.84 frames.], batch size: 12, lr: 3.96e-04
+2022-05-05 03:42:52,851 INFO [train.py:715] (3/8) Epoch 5, batch 5100, loss[loss=0.1725, simple_loss=0.2365, pruned_loss=0.05428, over 4925.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2251, pruned_loss=0.04222, over 972289.89 frames.], batch size: 18, lr: 3.96e-04
+2022-05-05 03:43:32,134 INFO [train.py:715] (3/8) Epoch 5, batch 5150, loss[loss=0.1164, simple_loss=0.1884, pruned_loss=0.02217, over 4786.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2252, pruned_loss=0.04227, over 971611.65 frames.], batch size: 18, lr: 3.96e-04
+2022-05-05 03:44:11,856 INFO [train.py:715] (3/8) Epoch 5, batch 5200, loss[loss=0.1517, simple_loss=0.2304, pruned_loss=0.03649, over 4907.00 frames.], tot_loss[loss=0.154, simple_loss=0.2247, pruned_loss=0.04167, over 971697.17 frames.], batch size: 18, lr: 3.96e-04
+2022-05-05 03:44:51,642 INFO [train.py:715] (3/8) Epoch 5, batch 5250, loss[loss=0.1382, simple_loss=0.2023, pruned_loss=0.03701, over 4932.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2247, pruned_loss=0.04189, over 972730.36 frames.], batch size: 21, lr: 3.96e-04
+2022-05-05 03:45:32,214 INFO [train.py:715] (3/8) Epoch 5, batch 5300, loss[loss=0.145, simple_loss=0.212, pruned_loss=0.03898, over 4811.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2238, pruned_loss=0.04141, over 972601.40 frames.], batch size: 24, lr: 3.96e-04
+2022-05-05 03:46:12,528 INFO [train.py:715] (3/8) Epoch 5, batch 5350, loss[loss=0.1508, simple_loss=0.2223, pruned_loss=0.03968, over 4906.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2248, pruned_loss=0.04214, over 972614.11 frames.], batch size: 39, lr: 3.96e-04
+2022-05-05 03:46:52,867 INFO [train.py:715] (3/8) Epoch 5, batch 5400, loss[loss=0.1449, simple_loss=0.2232, pruned_loss=0.03332, over 4982.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2245, pruned_loss=0.04214, over 971856.63 frames.], batch size: 24, lr: 3.96e-04
+2022-05-05 03:47:32,579 INFO [train.py:715] (3/8) Epoch 5, batch 5450, loss[loss=0.1474, simple_loss=0.2121, pruned_loss=0.0413, over 4976.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2247, pruned_loss=0.0425, over 971976.71 frames.], batch size: 14, lr: 3.96e-04
+2022-05-05 03:48:12,697 INFO [train.py:715] (3/8) Epoch 5, batch 5500, loss[loss=0.1822, simple_loss=0.2449, pruned_loss=0.05972, over 4794.00 frames.], tot_loss[loss=0.155, simple_loss=0.225, pruned_loss=0.04254, over 972863.16 frames.], batch size: 12, lr: 3.96e-04
+2022-05-05 03:48:53,028 INFO [train.py:715] (3/8) Epoch 5, batch 5550, loss[loss=0.1158, simple_loss=0.1838, pruned_loss=0.02394, over 4892.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2246, pruned_loss=0.04196, over 972899.64 frames.], batch size: 18, lr: 3.96e-04
+2022-05-05 03:49:33,408 INFO [train.py:715] (3/8) Epoch 5, batch 5600, loss[loss=0.1316, simple_loss=0.2198, pruned_loss=0.02166, over 4844.00 frames.], tot_loss[loss=0.154, simple_loss=0.2241, pruned_loss=0.04192, over 972835.39 frames.], batch size: 20, lr: 3.95e-04
+2022-05-05 03:50:13,545 INFO [train.py:715] (3/8) Epoch 5, batch 5650, loss[loss=0.1513, simple_loss=0.2311, pruned_loss=0.03572, over 4759.00 frames.], tot_loss[loss=0.154, simple_loss=0.2243, pruned_loss=0.0418, over 973209.72 frames.], batch size: 19, lr: 3.95e-04
+2022-05-05 03:50:52,898 INFO [train.py:715] (3/8) Epoch 5, batch 5700, loss[loss=0.1415, simple_loss=0.2098, pruned_loss=0.03658, over 4893.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2232, pruned_loss=0.04129, over 973125.10 frames.], batch size: 19, lr: 3.95e-04
+2022-05-05 03:51:33,318 INFO [train.py:715] (3/8) Epoch 5, batch 5750, loss[loss=0.1781, simple_loss=0.2496, pruned_loss=0.05333, over 4793.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2232, pruned_loss=0.04111, over 972669.54 frames.], batch size: 21, lr: 3.95e-04
+2022-05-05 03:52:13,226 INFO [train.py:715] (3/8) Epoch 5, batch 5800, loss[loss=0.1361, simple_loss=0.2083, pruned_loss=0.03192, over 4713.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2229, pruned_loss=0.04088, over 972453.53 frames.], batch size: 15, lr: 3.95e-04
+2022-05-05 03:52:53,761 INFO [train.py:715] (3/8) Epoch 5, batch 5850, loss[loss=0.1704, simple_loss=0.2489, pruned_loss=0.04597, over 4821.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2229, pruned_loss=0.04068, over 972422.76 frames.], batch size: 27, lr: 3.95e-04
+2022-05-05 03:53:33,395 INFO [train.py:715] (3/8) Epoch 5, batch 5900, loss[loss=0.1647, simple_loss=0.2314, pruned_loss=0.04902, over 4880.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2232, pruned_loss=0.04079, over 972021.15 frames.], batch size: 22, lr: 3.95e-04
+2022-05-05 03:54:13,784 INFO [train.py:715] (3/8) Epoch 5, batch 5950, loss[loss=0.1537, simple_loss=0.2261, pruned_loss=0.04068, over 4775.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2232, pruned_loss=0.04067, over 972689.62 frames.], batch size: 17, lr: 3.95e-04
+2022-05-05 03:54:53,620 INFO [train.py:715] (3/8) Epoch 5, batch 6000, loss[loss=0.1565, simple_loss=0.2183, pruned_loss=0.04736, over 4828.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2233, pruned_loss=0.04093, over 972194.83 frames.], batch size: 15, lr: 3.95e-04
+2022-05-05 03:54:53,621 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 03:55:03,070 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.1106, simple_loss=0.1959, pruned_loss=0.01263, over 914524.00 frames.
+2022-05-05 03:55:42,937 INFO [train.py:715] (3/8) Epoch 5, batch 6050, loss[loss=0.1392, simple_loss=0.2129, pruned_loss=0.03279, over 4693.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2238, pruned_loss=0.0412, over 972607.22 frames.], batch size: 15, lr: 3.95e-04
+2022-05-05 03:56:22,018 INFO [train.py:715] (3/8) Epoch 5, batch 6100, loss[loss=0.1512, simple_loss=0.2212, pruned_loss=0.04063, over 4845.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2239, pruned_loss=0.04132, over 972311.41 frames.], batch size: 30, lr: 3.95e-04
+2022-05-05 03:57:01,849 INFO [train.py:715] (3/8) Epoch 5, batch 6150, loss[loss=0.1708, simple_loss=0.2328, pruned_loss=0.05445, over 4821.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2237, pruned_loss=0.04149, over 972035.28 frames.], batch size: 15, lr: 3.95e-04
+2022-05-05 03:57:40,845 INFO [train.py:715] (3/8) Epoch 5, batch 6200, loss[loss=0.1246, simple_loss=0.196, pruned_loss=0.02661, over 4943.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2238, pruned_loss=0.04153, over 971602.43 frames.], batch size: 18, lr: 3.95e-04
+2022-05-05 03:58:21,088 INFO [train.py:715] (3/8) Epoch 5, batch 6250, loss[loss=0.1642, simple_loss=0.2219, pruned_loss=0.05324, over 4912.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2238, pruned_loss=0.0418, over 971902.17 frames.], batch size: 18, lr: 3.95e-04
+2022-05-05 03:58:59,730 INFO [train.py:715] (3/8) Epoch 5, batch 6300, loss[loss=0.1594, simple_loss=0.2198, pruned_loss=0.04947, over 4954.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2237, pruned_loss=0.04184, over 971052.76 frames.], batch size: 24, lr: 3.95e-04
+2022-05-05 03:59:39,537 INFO [train.py:715] (3/8) Epoch 5, batch 6350, loss[loss=0.1576, simple_loss=0.2349, pruned_loss=0.04017, over 4990.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2248, pruned_loss=0.04244, over 972097.05 frames.], batch size: 25, lr: 3.95e-04
+2022-05-05 04:00:18,904 INFO [train.py:715] (3/8) Epoch 5, batch 6400, loss[loss=0.1398, simple_loss=0.2139, pruned_loss=0.03281, over 4982.00 frames.], tot_loss[loss=0.155, simple_loss=0.2251, pruned_loss=0.04245, over 971651.50 frames.], batch size: 25, lr: 3.95e-04
+2022-05-05 04:00:57,767 INFO [train.py:715] (3/8) Epoch 5, batch 6450, loss[loss=0.1748, simple_loss=0.2488, pruned_loss=0.05041, over 4770.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2245, pruned_loss=0.04221, over 971736.40 frames.], batch size: 18, lr: 3.95e-04
+2022-05-05 04:01:37,236 INFO [train.py:715] (3/8) Epoch 5, batch 6500, loss[loss=0.1921, simple_loss=0.2578, pruned_loss=0.06322, over 4882.00 frames.], tot_loss[loss=0.155, simple_loss=0.2252, pruned_loss=0.04243, over 972257.60 frames.], batch size: 22, lr: 3.95e-04
+2022-05-05 04:02:16,586 INFO [train.py:715] (3/8) Epoch 5, batch 6550, loss[loss=0.1411, simple_loss=0.2094, pruned_loss=0.03641, over 4964.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2251, pruned_loss=0.04205, over 973090.04 frames.], batch size: 15, lr: 3.94e-04
+2022-05-05 04:02:55,730 INFO [train.py:715] (3/8) Epoch 5, batch 6600, loss[loss=0.181, simple_loss=0.2704, pruned_loss=0.04584, over 4955.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2241, pruned_loss=0.04126, over 972190.84 frames.], batch size: 39, lr: 3.94e-04
+2022-05-05 04:03:35,251 INFO [train.py:715] (3/8) Epoch 5, batch 6650, loss[loss=0.1313, simple_loss=0.2035, pruned_loss=0.02956, over 4949.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2237, pruned_loss=0.04104, over 971683.08 frames.], batch size: 21, lr: 3.94e-04
+2022-05-05 04:04:15,787 INFO [train.py:715] (3/8) Epoch 5, batch 6700, loss[loss=0.1398, simple_loss=0.2046, pruned_loss=0.03749, over 4869.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2232, pruned_loss=0.04133, over 971775.43 frames.], batch size: 16, lr: 3.94e-04
+2022-05-05 04:04:56,113 INFO [train.py:715] (3/8) Epoch 5, batch 6750, loss[loss=0.1517, simple_loss=0.2296, pruned_loss=0.03687, over 4858.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2242, pruned_loss=0.04173, over 972030.76 frames.], batch size: 20, lr: 3.94e-04
+2022-05-05 04:05:36,106 INFO [train.py:715] (3/8) Epoch 5, batch 6800, loss[loss=0.1724, simple_loss=0.2521, pruned_loss=0.04634, over 4832.00 frames.], tot_loss[loss=0.1547, simple_loss=0.225, pruned_loss=0.04215, over 971706.92 frames.], batch size: 15, lr: 3.94e-04
+2022-05-05 04:06:16,591 INFO [train.py:715] (3/8) Epoch 5, batch 6850, loss[loss=0.1848, simple_loss=0.2515, pruned_loss=0.05902, over 4779.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2249, pruned_loss=0.04198, over 972055.40 frames.], batch size: 17, lr: 3.94e-04
+2022-05-05 04:06:56,550 INFO [train.py:715] (3/8) Epoch 5, batch 6900, loss[loss=0.1269, simple_loss=0.1958, pruned_loss=0.02902, over 4798.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2255, pruned_loss=0.0423, over 972092.13 frames.], batch size: 21, lr: 3.94e-04
+2022-05-05 04:07:37,125 INFO [train.py:715] (3/8) Epoch 5, batch 6950, loss[loss=0.1526, simple_loss=0.2287, pruned_loss=0.03826, over 4836.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2251, pruned_loss=0.04205, over 971675.14 frames.], batch size: 30, lr: 3.94e-04
+2022-05-05 04:08:16,565 INFO [train.py:715] (3/8) Epoch 5, batch 7000, loss[loss=0.1679, simple_loss=0.2401, pruned_loss=0.04791, over 4900.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2253, pruned_loss=0.04243, over 971983.45 frames.], batch size: 17, lr: 3.94e-04
+2022-05-05 04:08:56,462 INFO [train.py:715] (3/8) Epoch 5, batch 7050, loss[loss=0.1351, simple_loss=0.2038, pruned_loss=0.03322, over 4920.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2244, pruned_loss=0.04216, over 973244.21 frames.], batch size: 18, lr: 3.94e-04
+2022-05-05 04:09:36,250 INFO [train.py:715] (3/8) Epoch 5, batch 7100, loss[loss=0.1411, simple_loss=0.2028, pruned_loss=0.03975, over 4649.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2237, pruned_loss=0.04163, over 972681.82 frames.], batch size: 13, lr: 3.94e-04
+2022-05-05 04:10:15,690 INFO [train.py:715] (3/8) Epoch 5, batch 7150, loss[loss=0.1657, simple_loss=0.237, pruned_loss=0.0472, over 4838.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2239, pruned_loss=0.04173, over 971266.19 frames.], batch size: 13, lr: 3.94e-04
+2022-05-05 04:10:55,647 INFO [train.py:715] (3/8) Epoch 5, batch 7200, loss[loss=0.169, simple_loss=0.2292, pruned_loss=0.05445, over 4870.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2235, pruned_loss=0.04155, over 971396.14 frames.], batch size: 20, lr: 3.94e-04
+2022-05-05 04:11:35,239 INFO [train.py:715] (3/8) Epoch 5, batch 7250, loss[loss=0.1286, simple_loss=0.2058, pruned_loss=0.02576, over 4822.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2226, pruned_loss=0.04113, over 972452.96 frames.], batch size: 26, lr: 3.94e-04
+2022-05-05 04:12:15,755 INFO [train.py:715] (3/8) Epoch 5, batch 7300, loss[loss=0.1404, simple_loss=0.2063, pruned_loss=0.03726, over 4959.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2235, pruned_loss=0.04214, over 972694.46 frames.], batch size: 21, lr: 3.94e-04
+2022-05-05 04:12:55,316 INFO [train.py:715] (3/8) Epoch 5, batch 7350, loss[loss=0.1598, simple_loss=0.2256, pruned_loss=0.04704, over 4855.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2238, pruned_loss=0.04223, over 972947.19 frames.], batch size: 32, lr: 3.94e-04
+2022-05-05 04:13:34,918 INFO [train.py:715] (3/8) Epoch 5, batch 7400, loss[loss=0.1425, simple_loss=0.2182, pruned_loss=0.03338, over 4832.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2234, pruned_loss=0.04194, over 973637.64 frames.], batch size: 15, lr: 3.94e-04
+2022-05-05 04:14:14,461 INFO [train.py:715] (3/8) Epoch 5, batch 7450, loss[loss=0.1628, simple_loss=0.2346, pruned_loss=0.04549, over 4948.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2243, pruned_loss=0.04254, over 973033.75 frames.], batch size: 35, lr: 3.93e-04
+2022-05-05 04:14:53,551 INFO [train.py:715] (3/8) Epoch 5, batch 7500, loss[loss=0.1396, simple_loss=0.202, pruned_loss=0.03856, over 4817.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2236, pruned_loss=0.04184, over 972328.81 frames.], batch size: 13, lr: 3.93e-04
+2022-05-05 04:15:33,685 INFO [train.py:715] (3/8) Epoch 5, batch 7550, loss[loss=0.1543, simple_loss=0.2257, pruned_loss=0.04144, over 4988.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2232, pruned_loss=0.04157, over 972217.68 frames.], batch size: 25, lr: 3.93e-04
+2022-05-05 04:16:13,351 INFO [train.py:715] (3/8) Epoch 5, batch 7600, loss[loss=0.1697, simple_loss=0.2387, pruned_loss=0.0504, over 4980.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2235, pruned_loss=0.04111, over 972821.64 frames.], batch size: 39, lr: 3.93e-04
+2022-05-05 04:16:53,609 INFO [train.py:715] (3/8) Epoch 5, batch 7650, loss[loss=0.1479, simple_loss=0.2229, pruned_loss=0.03643, over 4848.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2236, pruned_loss=0.04124, over 972223.34 frames.], batch size: 32, lr: 3.93e-04
+2022-05-05 04:17:33,267 INFO [train.py:715] (3/8) Epoch 5, batch 7700, loss[loss=0.1307, simple_loss=0.1935, pruned_loss=0.03394, over 4822.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2239, pruned_loss=0.04155, over 971979.60 frames.], batch size: 25, lr: 3.93e-04
+2022-05-05 04:18:12,777 INFO [train.py:715] (3/8) Epoch 5, batch 7750, loss[loss=0.1482, simple_loss=0.2125, pruned_loss=0.04193, over 4975.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2231, pruned_loss=0.04102, over 971974.26 frames.], batch size: 15, lr: 3.93e-04
+2022-05-05 04:18:52,925 INFO [train.py:715] (3/8) Epoch 5, batch 7800, loss[loss=0.1943, simple_loss=0.2503, pruned_loss=0.06918, over 4825.00 frames.], tot_loss[loss=0.1524, simple_loss=0.223, pruned_loss=0.04095, over 972627.82 frames.], batch size: 15, lr: 3.93e-04
+2022-05-05 04:19:32,129 INFO [train.py:715] (3/8) Epoch 5, batch 7850, loss[loss=0.1185, simple_loss=0.196, pruned_loss=0.02044, over 4873.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2234, pruned_loss=0.04098, over 972770.31 frames.], batch size: 13, lr: 3.93e-04
+2022-05-05 04:20:12,356 INFO [train.py:715] (3/8) Epoch 5, batch 7900, loss[loss=0.1316, simple_loss=0.1907, pruned_loss=0.03622, over 4756.00 frames.], tot_loss[loss=0.1526, simple_loss=0.223, pruned_loss=0.04104, over 972155.50 frames.], batch size: 12, lr: 3.93e-04
+2022-05-05 04:20:51,911 INFO [train.py:715] (3/8) Epoch 5, batch 7950, loss[loss=0.1715, simple_loss=0.2461, pruned_loss=0.04843, over 4810.00 frames.], tot_loss[loss=0.1519, simple_loss=0.223, pruned_loss=0.04038, over 971650.67 frames.], batch size: 21, lr: 3.93e-04
+2022-05-05 04:21:32,116 INFO [train.py:715] (3/8) Epoch 5, batch 8000, loss[loss=0.1154, simple_loss=0.1828, pruned_loss=0.02398, over 4755.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2232, pruned_loss=0.04053, over 971054.47 frames.], batch size: 12, lr: 3.93e-04
+2022-05-05 04:22:11,573 INFO [train.py:715] (3/8) Epoch 5, batch 8050, loss[loss=0.1829, simple_loss=0.2386, pruned_loss=0.06363, over 4774.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2244, pruned_loss=0.0414, over 971935.47 frames.], batch size: 14, lr: 3.93e-04
+2022-05-05 04:22:51,025 INFO [train.py:715] (3/8) Epoch 5, batch 8100, loss[loss=0.1579, simple_loss=0.2234, pruned_loss=0.04623, over 4961.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2233, pruned_loss=0.0411, over 972728.94 frames.], batch size: 35, lr: 3.93e-04
+2022-05-05 04:23:30,812 INFO [train.py:715] (3/8) Epoch 5, batch 8150, loss[loss=0.1628, simple_loss=0.2216, pruned_loss=0.05205, over 4866.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2237, pruned_loss=0.04123, over 972164.19 frames.], batch size: 30, lr: 3.93e-04
+2022-05-05 04:24:09,995 INFO [train.py:715] (3/8) Epoch 5, batch 8200, loss[loss=0.1596, simple_loss=0.2251, pruned_loss=0.04707, over 4939.00 frames.], tot_loss[loss=0.1521, simple_loss=0.223, pruned_loss=0.04062, over 971703.45 frames.], batch size: 23, lr: 3.93e-04
+2022-05-05 04:24:50,012 INFO [train.py:715] (3/8) Epoch 5, batch 8250, loss[loss=0.1687, simple_loss=0.2301, pruned_loss=0.05371, over 4869.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2218, pruned_loss=0.04044, over 971496.91 frames.], batch size: 32, lr: 3.93e-04
+2022-05-05 04:25:29,481 INFO [train.py:715] (3/8) Epoch 5, batch 8300, loss[loss=0.135, simple_loss=0.2068, pruned_loss=0.03156, over 4916.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.0406, over 972619.75 frames.], batch size: 19, lr: 3.93e-04
+2022-05-05 04:26:09,424 INFO [train.py:715] (3/8) Epoch 5, batch 8350, loss[loss=0.1288, simple_loss=0.1931, pruned_loss=0.03226, over 4821.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2214, pruned_loss=0.04006, over 972801.57 frames.], batch size: 13, lr: 3.93e-04
+2022-05-05 04:26:48,503 INFO [train.py:715] (3/8) Epoch 5, batch 8400, loss[loss=0.1681, simple_loss=0.2383, pruned_loss=0.04892, over 4830.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2228, pruned_loss=0.04043, over 971926.45 frames.], batch size: 30, lr: 3.92e-04
+2022-05-05 04:27:27,550 INFO [train.py:715] (3/8) Epoch 5, batch 8450, loss[loss=0.1705, simple_loss=0.233, pruned_loss=0.05406, over 4745.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04064, over 972325.45 frames.], batch size: 16, lr: 3.92e-04
+2022-05-05 04:28:06,815 INFO [train.py:715] (3/8) Epoch 5, batch 8500, loss[loss=0.1438, simple_loss=0.2293, pruned_loss=0.02912, over 4991.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2223, pruned_loss=0.0405, over 972744.50 frames.], batch size: 16, lr: 3.92e-04
+2022-05-05 04:28:45,804 INFO [train.py:715] (3/8) Epoch 5, batch 8550, loss[loss=0.1934, simple_loss=0.2576, pruned_loss=0.06461, over 4914.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2233, pruned_loss=0.04079, over 973449.95 frames.], batch size: 19, lr: 3.92e-04
+2022-05-05 04:29:25,248 INFO [train.py:715] (3/8) Epoch 5, batch 8600, loss[loss=0.1384, simple_loss=0.2105, pruned_loss=0.03318, over 4845.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2226, pruned_loss=0.04042, over 973644.24 frames.], batch size: 13, lr: 3.92e-04
+2022-05-05 04:30:04,414 INFO [train.py:715] (3/8) Epoch 5, batch 8650, loss[loss=0.1555, simple_loss=0.2215, pruned_loss=0.04475, over 4839.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2234, pruned_loss=0.04119, over 973506.50 frames.], batch size: 30, lr: 3.92e-04
+2022-05-05 04:30:43,885 INFO [train.py:715] (3/8) Epoch 5, batch 8700, loss[loss=0.1448, simple_loss=0.218, pruned_loss=0.03582, over 4857.00 frames.], tot_loss[loss=0.1538, simple_loss=0.224, pruned_loss=0.04182, over 973712.50 frames.], batch size: 20, lr: 3.92e-04
+2022-05-05 04:31:23,272 INFO [train.py:715] (3/8) Epoch 5, batch 8750, loss[loss=0.1459, simple_loss=0.2139, pruned_loss=0.03898, over 4803.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2234, pruned_loss=0.04162, over 973128.61 frames.], batch size: 13, lr: 3.92e-04
+2022-05-05 04:32:02,280 INFO [train.py:715] (3/8) Epoch 5, batch 8800, loss[loss=0.1283, simple_loss=0.1876, pruned_loss=0.03456, over 4779.00 frames.], tot_loss[loss=0.1537, simple_loss=0.224, pruned_loss=0.04173, over 973565.48 frames.], batch size: 17, lr: 3.92e-04
+2022-05-05 04:32:42,160 INFO [train.py:715] (3/8) Epoch 5, batch 8850, loss[loss=0.1667, simple_loss=0.2359, pruned_loss=0.04877, over 4892.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2246, pruned_loss=0.04228, over 973609.09 frames.], batch size: 39, lr: 3.92e-04
+2022-05-05 04:33:20,884 INFO [train.py:715] (3/8) Epoch 5, batch 8900, loss[loss=0.14, simple_loss=0.211, pruned_loss=0.03451, over 4838.00 frames.], tot_loss[loss=0.1539, simple_loss=0.224, pruned_loss=0.04194, over 973242.75 frames.], batch size: 13, lr: 3.92e-04
+2022-05-05 04:33:59,746 INFO [train.py:715] (3/8) Epoch 5, batch 8950, loss[loss=0.1497, simple_loss=0.228, pruned_loss=0.03576, over 4927.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2234, pruned_loss=0.04168, over 973381.61 frames.], batch size: 18, lr: 3.92e-04
+2022-05-05 04:34:39,032 INFO [train.py:715] (3/8) Epoch 5, batch 9000, loss[loss=0.1551, simple_loss=0.2225, pruned_loss=0.04383, over 4751.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2236, pruned_loss=0.04168, over 973100.08 frames.], batch size: 16, lr: 3.92e-04
+2022-05-05 04:34:39,032 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 04:34:48,552 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.1105, simple_loss=0.196, pruned_loss=0.01252, over 914524.00 frames.
+2022-05-05 04:35:28,195 INFO [train.py:715] (3/8) Epoch 5, batch 9050, loss[loss=0.1498, simple_loss=0.2246, pruned_loss=0.03748, over 4938.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2232, pruned_loss=0.04159, over 972847.43 frames.], batch size: 29, lr: 3.92e-04
+2022-05-05 04:36:07,672 INFO [train.py:715] (3/8) Epoch 5, batch 9100, loss[loss=0.1458, simple_loss=0.2145, pruned_loss=0.03858, over 4972.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2242, pruned_loss=0.04179, over 972595.89 frames.], batch size: 25, lr: 3.92e-04
+2022-05-05 04:36:46,713 INFO [train.py:715] (3/8) Epoch 5, batch 9150, loss[loss=0.1543, simple_loss=0.2274, pruned_loss=0.04062, over 4859.00 frames.], tot_loss[loss=0.153, simple_loss=0.2236, pruned_loss=0.04126, over 972017.81 frames.], batch size: 20, lr: 3.92e-04
+2022-05-05 04:37:26,203 INFO [train.py:715] (3/8) Epoch 5, batch 9200, loss[loss=0.136, simple_loss=0.2165, pruned_loss=0.02771, over 4787.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2238, pruned_loss=0.04132, over 971657.08 frames.], batch size: 18, lr: 3.92e-04
+2022-05-05 04:38:06,417 INFO [train.py:715] (3/8) Epoch 5, batch 9250, loss[loss=0.1629, simple_loss=0.2355, pruned_loss=0.04512, over 4764.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2241, pruned_loss=0.04154, over 971862.17 frames.], batch size: 16, lr: 3.92e-04
+2022-05-05 04:38:45,291 INFO [train.py:715] (3/8) Epoch 5, batch 9300, loss[loss=0.1583, simple_loss=0.2256, pruned_loss=0.04552, over 4903.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2239, pruned_loss=0.04157, over 972371.01 frames.], batch size: 17, lr: 3.91e-04
+2022-05-05 04:39:24,929 INFO [train.py:715] (3/8) Epoch 5, batch 9350, loss[loss=0.1484, simple_loss=0.2161, pruned_loss=0.04033, over 4786.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2233, pruned_loss=0.04144, over 972173.04 frames.], batch size: 18, lr: 3.91e-04
+2022-05-05 04:40:04,421 INFO [train.py:715] (3/8) Epoch 5, batch 9400, loss[loss=0.1491, simple_loss=0.2253, pruned_loss=0.03645, over 4798.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2219, pruned_loss=0.04049, over 972821.19 frames.], batch size: 21, lr: 3.91e-04
+2022-05-05 04:40:43,714 INFO [train.py:715] (3/8) Epoch 5, batch 9450, loss[loss=0.1438, simple_loss=0.2223, pruned_loss=0.0326, over 4867.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.04081, over 971674.48 frames.], batch size: 20, lr: 3.91e-04
+2022-05-05 04:41:22,596 INFO [train.py:715] (3/8) Epoch 5, batch 9500, loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03022, over 4914.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2227, pruned_loss=0.04081, over 971735.47 frames.], batch size: 19, lr: 3.91e-04
+2022-05-05 04:42:02,153 INFO [train.py:715] (3/8) Epoch 5, batch 9550, loss[loss=0.1358, simple_loss=0.2148, pruned_loss=0.0284, over 4977.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2231, pruned_loss=0.04095, over 971938.44 frames.], batch size: 28, lr: 3.91e-04
+2022-05-05 04:42:41,920 INFO [train.py:715] (3/8) Epoch 5, batch 9600, loss[loss=0.1622, simple_loss=0.233, pruned_loss=0.04569, over 4860.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.04104, over 972647.28 frames.], batch size: 20, lr: 3.91e-04
+2022-05-05 04:43:21,155 INFO [train.py:715] (3/8) Epoch 5, batch 9650, loss[loss=0.1757, simple_loss=0.242, pruned_loss=0.05472, over 4923.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2222, pruned_loss=0.04107, over 972602.51 frames.], batch size: 39, lr: 3.91e-04
+2022-05-05 04:44:00,815 INFO [train.py:715] (3/8) Epoch 5, batch 9700, loss[loss=0.1557, simple_loss=0.2155, pruned_loss=0.04798, over 4907.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2226, pruned_loss=0.04126, over 972907.52 frames.], batch size: 18, lr: 3.91e-04
+2022-05-05 04:44:40,237 INFO [train.py:715] (3/8) Epoch 5, batch 9750, loss[loss=0.1423, simple_loss=0.2217, pruned_loss=0.03139, over 4960.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2231, pruned_loss=0.04157, over 973060.39 frames.], batch size: 21, lr: 3.91e-04
+2022-05-05 04:45:19,135 INFO [train.py:715] (3/8) Epoch 5, batch 9800, loss[loss=0.149, simple_loss=0.2171, pruned_loss=0.04045, over 4844.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2231, pruned_loss=0.04122, over 972685.88 frames.], batch size: 20, lr: 3.91e-04
+2022-05-05 04:45:58,976 INFO [train.py:715] (3/8) Epoch 5, batch 9850, loss[loss=0.1495, simple_loss=0.2173, pruned_loss=0.04089, over 4962.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2234, pruned_loss=0.04099, over 972350.24 frames.], batch size: 15, lr: 3.91e-04
+2022-05-05 04:46:38,172 INFO [train.py:715] (3/8) Epoch 5, batch 9900, loss[loss=0.144, simple_loss=0.2033, pruned_loss=0.0423, over 4741.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2234, pruned_loss=0.04118, over 972513.62 frames.], batch size: 12, lr: 3.91e-04
+2022-05-05 04:47:17,938 INFO [train.py:715] (3/8) Epoch 5, batch 9950, loss[loss=0.1869, simple_loss=0.2576, pruned_loss=0.05811, over 4918.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2232, pruned_loss=0.04092, over 971253.88 frames.], batch size: 18, lr: 3.91e-04
+2022-05-05 04:47:59,850 INFO [train.py:715] (3/8) Epoch 5, batch 10000, loss[loss=0.1587, simple_loss=0.2298, pruned_loss=0.04383, over 4883.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2245, pruned_loss=0.04165, over 971371.91 frames.], batch size: 16, lr: 3.91e-04
+2022-05-05 04:48:39,807 INFO [train.py:715] (3/8) Epoch 5, batch 10050, loss[loss=0.1221, simple_loss=0.1951, pruned_loss=0.02456, over 4857.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2241, pruned_loss=0.04152, over 972490.52 frames.], batch size: 20, lr: 3.91e-04
+2022-05-05 04:49:19,416 INFO [train.py:715] (3/8) Epoch 5, batch 10100, loss[loss=0.1535, simple_loss=0.2252, pruned_loss=0.04087, over 4976.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2231, pruned_loss=0.04103, over 972749.96 frames.], batch size: 25, lr: 3.91e-04
+2022-05-05 04:49:58,584 INFO [train.py:715] (3/8) Epoch 5, batch 10150, loss[loss=0.15, simple_loss=0.2172, pruned_loss=0.04141, over 4916.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.04081, over 972175.31 frames.], batch size: 18, lr: 3.91e-04
+2022-05-05 04:50:38,452 INFO [train.py:715] (3/8) Epoch 5, batch 10200, loss[loss=0.1595, simple_loss=0.2299, pruned_loss=0.04449, over 4771.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2229, pruned_loss=0.04117, over 971526.41 frames.], batch size: 17, lr: 3.91e-04
+2022-05-05 04:51:17,795 INFO [train.py:715] (3/8) Epoch 5, batch 10250, loss[loss=0.1443, simple_loss=0.2156, pruned_loss=0.03645, over 4968.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2229, pruned_loss=0.04144, over 971046.55 frames.], batch size: 14, lr: 3.90e-04
+2022-05-05 04:51:56,801 INFO [train.py:715] (3/8) Epoch 5, batch 10300, loss[loss=0.1511, simple_loss=0.2157, pruned_loss=0.0433, over 4785.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2237, pruned_loss=0.04161, over 971996.05 frames.], batch size: 17, lr: 3.90e-04
+2022-05-05 04:52:36,625 INFO [train.py:715] (3/8) Epoch 5, batch 10350, loss[loss=0.1488, simple_loss=0.2157, pruned_loss=0.04093, over 4688.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2241, pruned_loss=0.04169, over 972355.43 frames.], batch size: 15, lr: 3.90e-04
+2022-05-05 04:53:15,667 INFO [train.py:715] (3/8) Epoch 5, batch 10400, loss[loss=0.1421, simple_loss=0.2149, pruned_loss=0.03464, over 4803.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2236, pruned_loss=0.04162, over 972434.74 frames.], batch size: 21, lr: 3.90e-04
+2022-05-05 04:53:55,619 INFO [train.py:715] (3/8) Epoch 5, batch 10450, loss[loss=0.147, simple_loss=0.21, pruned_loss=0.042, over 4837.00 frames.], tot_loss[loss=0.1538, simple_loss=0.224, pruned_loss=0.04182, over 973147.62 frames.], batch size: 13, lr: 3.90e-04
+2022-05-05 04:54:35,514 INFO [train.py:715] (3/8) Epoch 5, batch 10500, loss[loss=0.1934, simple_loss=0.2541, pruned_loss=0.06632, over 4921.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2243, pruned_loss=0.04248, over 972937.37 frames.], batch size: 39, lr: 3.90e-04
+2022-05-05 04:55:15,980 INFO [train.py:715] (3/8) Epoch 5, batch 10550, loss[loss=0.1416, simple_loss=0.2079, pruned_loss=0.03758, over 4842.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2242, pruned_loss=0.04216, over 971748.77 frames.], batch size: 34, lr: 3.90e-04
+2022-05-05 04:55:55,071 INFO [train.py:715] (3/8) Epoch 5, batch 10600, loss[loss=0.1575, simple_loss=0.24, pruned_loss=0.03747, over 4770.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2242, pruned_loss=0.04183, over 971756.09 frames.], batch size: 17, lr: 3.90e-04
+2022-05-05 04:56:34,539 INFO [train.py:715] (3/8) Epoch 5, batch 10650, loss[loss=0.1295, simple_loss=0.2154, pruned_loss=0.02179, over 4893.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2238, pruned_loss=0.04157, over 971887.86 frames.], batch size: 22, lr: 3.90e-04
+2022-05-05 04:57:14,071 INFO [train.py:715] (3/8) Epoch 5, batch 10700, loss[loss=0.1417, simple_loss=0.2083, pruned_loss=0.03753, over 4905.00 frames.], tot_loss[loss=0.154, simple_loss=0.224, pruned_loss=0.04197, over 972379.23 frames.], batch size: 18, lr: 3.90e-04
+2022-05-05 04:57:53,027 INFO [train.py:715] (3/8) Epoch 5, batch 10750, loss[loss=0.1622, simple_loss=0.2403, pruned_loss=0.042, over 4927.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2237, pruned_loss=0.04149, over 972270.95 frames.], batch size: 39, lr: 3.90e-04
+2022-05-05 04:58:32,275 INFO [train.py:715] (3/8) Epoch 5, batch 10800, loss[loss=0.1522, simple_loss=0.2149, pruned_loss=0.04472, over 4867.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2229, pruned_loss=0.0416, over 973492.65 frames.], batch size: 22, lr: 3.90e-04
+2022-05-05 04:59:11,503 INFO [train.py:715] (3/8) Epoch 5, batch 10850, loss[loss=0.1628, simple_loss=0.2297, pruned_loss=0.04793, over 4932.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2235, pruned_loss=0.04182, over 973885.70 frames.], batch size: 35, lr: 3.90e-04
+2022-05-05 04:59:51,498 INFO [train.py:715] (3/8) Epoch 5, batch 10900, loss[loss=0.1522, simple_loss=0.2434, pruned_loss=0.03054, over 4860.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2237, pruned_loss=0.04176, over 973529.49 frames.], batch size: 20, lr: 3.90e-04
+2022-05-05 05:00:30,697 INFO [train.py:715] (3/8) Epoch 5, batch 10950, loss[loss=0.1339, simple_loss=0.2014, pruned_loss=0.03315, over 4944.00 frames.], tot_loss[loss=0.154, simple_loss=0.2245, pruned_loss=0.04171, over 973563.58 frames.], batch size: 23, lr: 3.90e-04
+2022-05-05 05:01:10,471 INFO [train.py:715] (3/8) Epoch 5, batch 11000, loss[loss=0.1284, simple_loss=0.2047, pruned_loss=0.02599, over 4731.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2239, pruned_loss=0.04145, over 973787.06 frames.], batch size: 12, lr: 3.90e-04
+2022-05-05 05:01:49,965 INFO [train.py:715] (3/8) Epoch 5, batch 11050, loss[loss=0.1589, simple_loss=0.2287, pruned_loss=0.04458, over 4836.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2237, pruned_loss=0.04122, over 974564.12 frames.], batch size: 15, lr: 3.90e-04
+2022-05-05 05:02:29,389 INFO [train.py:715] (3/8) Epoch 5, batch 11100, loss[loss=0.1474, simple_loss=0.2216, pruned_loss=0.03661, over 4921.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04094, over 974590.20 frames.], batch size: 39, lr: 3.90e-04
+2022-05-05 05:03:08,929 INFO [train.py:715] (3/8) Epoch 5, batch 11150, loss[loss=0.1413, simple_loss=0.2098, pruned_loss=0.03639, over 4900.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2239, pruned_loss=0.04112, over 973787.67 frames.], batch size: 22, lr: 3.90e-04
+2022-05-05 05:03:48,023 INFO [train.py:715] (3/8) Epoch 5, batch 11200, loss[loss=0.1528, simple_loss=0.2303, pruned_loss=0.03767, over 4933.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2245, pruned_loss=0.04114, over 973676.74 frames.], batch size: 21, lr: 3.89e-04
+2022-05-05 05:04:27,936 INFO [train.py:715] (3/8) Epoch 5, batch 11250, loss[loss=0.1668, simple_loss=0.2315, pruned_loss=0.05108, over 4876.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2233, pruned_loss=0.04079, over 972832.67 frames.], batch size: 32, lr: 3.89e-04
+2022-05-05 05:05:07,258 INFO [train.py:715] (3/8) Epoch 5, batch 11300, loss[loss=0.137, simple_loss=0.2116, pruned_loss=0.03121, over 4831.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2233, pruned_loss=0.04057, over 972573.70 frames.], batch size: 25, lr: 3.89e-04
+2022-05-05 05:05:46,393 INFO [train.py:715] (3/8) Epoch 5, batch 11350, loss[loss=0.1554, simple_loss=0.2244, pruned_loss=0.04323, over 4929.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2233, pruned_loss=0.04069, over 971684.36 frames.], batch size: 18, lr: 3.89e-04
+2022-05-05 05:06:27,198 INFO [train.py:715] (3/8) Epoch 5, batch 11400, loss[loss=0.1292, simple_loss=0.2074, pruned_loss=0.02548, over 4784.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2236, pruned_loss=0.04098, over 971863.67 frames.], batch size: 18, lr: 3.89e-04
+2022-05-05 05:07:07,354 INFO [train.py:715] (3/8) Epoch 5, batch 11450, loss[loss=0.146, simple_loss=0.2084, pruned_loss=0.04174, over 4732.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2232, pruned_loss=0.04101, over 972544.16 frames.], batch size: 16, lr: 3.89e-04
+2022-05-05 05:07:47,394 INFO [train.py:715] (3/8) Epoch 5, batch 11500, loss[loss=0.1659, simple_loss=0.231, pruned_loss=0.05035, over 4865.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2235, pruned_loss=0.04141, over 972678.77 frames.], batch size: 32, lr: 3.89e-04
+2022-05-05 05:08:27,417 INFO [train.py:715] (3/8) Epoch 5, batch 11550, loss[loss=0.1449, simple_loss=0.2234, pruned_loss=0.0332, over 4983.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2231, pruned_loss=0.04104, over 972691.39 frames.], batch size: 28, lr: 3.89e-04
+2022-05-05 05:09:07,609 INFO [train.py:715] (3/8) Epoch 5, batch 11600, loss[loss=0.1654, simple_loss=0.2288, pruned_loss=0.05094, over 4694.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2234, pruned_loss=0.04091, over 972335.07 frames.], batch size: 15, lr: 3.89e-04
+2022-05-05 05:09:48,320 INFO [train.py:715] (3/8) Epoch 5, batch 11650, loss[loss=0.1586, simple_loss=0.2242, pruned_loss=0.04657, over 4902.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2232, pruned_loss=0.04058, over 972820.96 frames.], batch size: 19, lr: 3.89e-04
+2022-05-05 05:10:28,060 INFO [train.py:715] (3/8) Epoch 5, batch 11700, loss[loss=0.1681, simple_loss=0.2334, pruned_loss=0.05139, over 4871.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2219, pruned_loss=0.03999, over 972106.36 frames.], batch size: 32, lr: 3.89e-04
+2022-05-05 05:11:08,773 INFO [train.py:715] (3/8) Epoch 5, batch 11750, loss[loss=0.1701, simple_loss=0.2335, pruned_loss=0.0533, over 4866.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03987, over 971583.95 frames.], batch size: 38, lr: 3.89e-04
+2022-05-05 05:11:48,920 INFO [train.py:715] (3/8) Epoch 5, batch 11800, loss[loss=0.1361, simple_loss=0.2127, pruned_loss=0.02972, over 4821.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2215, pruned_loss=0.03986, over 971855.11 frames.], batch size: 27, lr: 3.89e-04
+2022-05-05 05:12:29,044 INFO [train.py:715] (3/8) Epoch 5, batch 11850, loss[loss=0.1539, simple_loss=0.2234, pruned_loss=0.04223, over 4884.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2216, pruned_loss=0.03976, over 972469.68 frames.], batch size: 22, lr: 3.89e-04
+2022-05-05 05:13:08,179 INFO [train.py:715] (3/8) Epoch 5, batch 11900, loss[loss=0.182, simple_loss=0.2535, pruned_loss=0.05526, over 4972.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2221, pruned_loss=0.04019, over 973136.38 frames.], batch size: 24, lr: 3.89e-04
+2022-05-05 05:13:47,504 INFO [train.py:715] (3/8) Epoch 5, batch 11950, loss[loss=0.1556, simple_loss=0.2328, pruned_loss=0.0392, over 4982.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2226, pruned_loss=0.0402, over 973556.54 frames.], batch size: 39, lr: 3.89e-04
+2022-05-05 05:14:27,513 INFO [train.py:715] (3/8) Epoch 5, batch 12000, loss[loss=0.1669, simple_loss=0.2215, pruned_loss=0.05614, over 4829.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2225, pruned_loss=0.04041, over 972964.76 frames.], batch size: 15, lr: 3.89e-04
+2022-05-05 05:14:27,513 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 05:14:37,326 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.1103, simple_loss=0.1957, pruned_loss=0.01243, over 914524.00 frames.
+2022-05-05 05:15:17,601 INFO [train.py:715] (3/8) Epoch 5, batch 12050, loss[loss=0.1544, simple_loss=0.2326, pruned_loss=0.03811, over 4757.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2231, pruned_loss=0.04069, over 972727.85 frames.], batch size: 19, lr: 3.89e-04
+2022-05-05 05:15:57,247 INFO [train.py:715] (3/8) Epoch 5, batch 12100, loss[loss=0.15, simple_loss=0.223, pruned_loss=0.03854, over 4747.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2231, pruned_loss=0.04059, over 972586.40 frames.], batch size: 16, lr: 3.89e-04
+2022-05-05 05:16:36,758 INFO [train.py:715] (3/8) Epoch 5, batch 12150, loss[loss=0.1322, simple_loss=0.2028, pruned_loss=0.0308, over 4970.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.03991, over 971745.39 frames.], batch size: 24, lr: 3.88e-04
+2022-05-05 05:17:16,021 INFO [train.py:715] (3/8) Epoch 5, batch 12200, loss[loss=0.1705, simple_loss=0.2276, pruned_loss=0.0567, over 4804.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2234, pruned_loss=0.04055, over 972476.32 frames.], batch size: 12, lr: 3.88e-04
+2022-05-05 05:17:56,098 INFO [train.py:715] (3/8) Epoch 5, batch 12250, loss[loss=0.1516, simple_loss=0.2274, pruned_loss=0.03794, over 4706.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2235, pruned_loss=0.04081, over 972246.83 frames.], batch size: 15, lr: 3.88e-04
+2022-05-05 05:18:35,378 INFO [train.py:715] (3/8) Epoch 5, batch 12300, loss[loss=0.1594, simple_loss=0.2242, pruned_loss=0.04733, over 4811.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2237, pruned_loss=0.04134, over 973481.34 frames.], batch size: 24, lr: 3.88e-04
+2022-05-05 05:19:14,278 INFO [train.py:715] (3/8) Epoch 5, batch 12350, loss[loss=0.1342, simple_loss=0.2099, pruned_loss=0.02927, over 4862.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2245, pruned_loss=0.04156, over 972704.01 frames.], batch size: 16, lr: 3.88e-04
+2022-05-05 05:19:53,846 INFO [train.py:715] (3/8) Epoch 5, batch 12400, loss[loss=0.1354, simple_loss=0.2082, pruned_loss=0.03131, over 4984.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2246, pruned_loss=0.04148, over 972555.09 frames.], batch size: 14, lr: 3.88e-04
+2022-05-05 05:20:33,433 INFO [train.py:715] (3/8) Epoch 5, batch 12450, loss[loss=0.1401, simple_loss=0.2116, pruned_loss=0.03432, over 4917.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2224, pruned_loss=0.04029, over 972391.92 frames.], batch size: 18, lr: 3.88e-04
+2022-05-05 05:21:12,665 INFO [train.py:715] (3/8) Epoch 5, batch 12500, loss[loss=0.1599, simple_loss=0.2265, pruned_loss=0.04664, over 4799.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2221, pruned_loss=0.04031, over 971101.07 frames.], batch size: 24, lr: 3.88e-04
+2022-05-05 05:21:51,878 INFO [train.py:715] (3/8) Epoch 5, batch 12550, loss[loss=0.1362, simple_loss=0.2154, pruned_loss=0.02853, over 4752.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2219, pruned_loss=0.04016, over 971394.56 frames.], batch size: 19, lr: 3.88e-04
+2022-05-05 05:22:30,628 INFO [train.py:715] (3/8) Epoch 5, batch 12600, loss[loss=0.137, simple_loss=0.211, pruned_loss=0.03152, over 4783.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2212, pruned_loss=0.03994, over 971247.35 frames.], batch size: 14, lr: 3.88e-04
+2022-05-05 05:23:08,928 INFO [train.py:715] (3/8) Epoch 5, batch 12650, loss[loss=0.1476, simple_loss=0.2181, pruned_loss=0.03861, over 4771.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2216, pruned_loss=0.03987, over 970934.90 frames.], batch size: 18, lr: 3.88e-04
+2022-05-05 05:23:47,149 INFO [train.py:715] (3/8) Epoch 5, batch 12700, loss[loss=0.1622, simple_loss=0.213, pruned_loss=0.0557, over 4818.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2218, pruned_loss=0.04038, over 970349.53 frames.], batch size: 13, lr: 3.88e-04
+2022-05-05 05:24:27,019 INFO [train.py:715] (3/8) Epoch 5, batch 12750, loss[loss=0.1493, simple_loss=0.2258, pruned_loss=0.03636, over 4811.00 frames.], tot_loss[loss=0.152, simple_loss=0.2223, pruned_loss=0.04083, over 971245.37 frames.], batch size: 25, lr: 3.88e-04
+2022-05-05 05:25:06,592 INFO [train.py:715] (3/8) Epoch 5, batch 12800, loss[loss=0.1412, simple_loss=0.2195, pruned_loss=0.03144, over 4865.00 frames.], tot_loss[loss=0.152, simple_loss=0.2224, pruned_loss=0.04081, over 971695.22 frames.], batch size: 20, lr: 3.88e-04
+2022-05-05 05:25:46,758 INFO [train.py:715] (3/8) Epoch 5, batch 12850, loss[loss=0.1642, simple_loss=0.2422, pruned_loss=0.04305, over 4968.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2238, pruned_loss=0.042, over 972290.68 frames.], batch size: 31, lr: 3.88e-04
+2022-05-05 05:26:26,310 INFO [train.py:715] (3/8) Epoch 5, batch 12900, loss[loss=0.1691, simple_loss=0.263, pruned_loss=0.03757, over 4684.00 frames.], tot_loss[loss=0.154, simple_loss=0.2241, pruned_loss=0.04201, over 971977.82 frames.], batch size: 15, lr: 3.88e-04
+2022-05-05 05:27:06,306 INFO [train.py:715] (3/8) Epoch 5, batch 12950, loss[loss=0.1529, simple_loss=0.2249, pruned_loss=0.04047, over 4707.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2233, pruned_loss=0.04155, over 971708.01 frames.], batch size: 15, lr: 3.88e-04
+2022-05-05 05:27:45,738 INFO [train.py:715] (3/8) Epoch 5, batch 13000, loss[loss=0.1421, simple_loss=0.2102, pruned_loss=0.03697, over 4704.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2237, pruned_loss=0.04172, over 971098.21 frames.], batch size: 15, lr: 3.88e-04
+2022-05-05 05:28:25,610 INFO [train.py:715] (3/8) Epoch 5, batch 13050, loss[loss=0.1279, simple_loss=0.1963, pruned_loss=0.02975, over 4967.00 frames.], tot_loss[loss=0.155, simple_loss=0.2248, pruned_loss=0.04262, over 970076.55 frames.], batch size: 24, lr: 3.88e-04
+2022-05-05 05:29:03,808 INFO [train.py:715] (3/8) Epoch 5, batch 13100, loss[loss=0.1344, simple_loss=0.2021, pruned_loss=0.03334, over 4960.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2244, pruned_loss=0.04226, over 970778.64 frames.], batch size: 35, lr: 3.87e-04
+2022-05-05 05:29:42,389 INFO [train.py:715] (3/8) Epoch 5, batch 13150, loss[loss=0.1848, simple_loss=0.2472, pruned_loss=0.06119, over 4798.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2255, pruned_loss=0.04294, over 970224.11 frames.], batch size: 25, lr: 3.87e-04
+2022-05-05 05:30:20,478 INFO [train.py:715] (3/8) Epoch 5, batch 13200, loss[loss=0.1663, simple_loss=0.2487, pruned_loss=0.04192, over 4969.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2247, pruned_loss=0.04235, over 970322.67 frames.], batch size: 35, lr: 3.87e-04
+2022-05-05 05:30:58,490 INFO [train.py:715] (3/8) Epoch 5, batch 13250, loss[loss=0.1413, simple_loss=0.2153, pruned_loss=0.03367, over 4892.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2243, pruned_loss=0.04257, over 970662.39 frames.], batch size: 22, lr: 3.87e-04
+2022-05-05 05:31:37,093 INFO [train.py:715] (3/8) Epoch 5, batch 13300, loss[loss=0.1429, simple_loss=0.2132, pruned_loss=0.03627, over 4948.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2247, pruned_loss=0.04281, over 971062.70 frames.], batch size: 21, lr: 3.87e-04
+2022-05-05 05:32:14,953 INFO [train.py:715] (3/8) Epoch 5, batch 13350, loss[loss=0.1923, simple_loss=0.2537, pruned_loss=0.06544, over 4825.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2246, pruned_loss=0.04276, over 971655.56 frames.], batch size: 25, lr: 3.87e-04
+2022-05-05 05:32:53,087 INFO [train.py:715] (3/8) Epoch 5, batch 13400, loss[loss=0.132, simple_loss=0.2073, pruned_loss=0.02841, over 4870.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2238, pruned_loss=0.042, over 971544.73 frames.], batch size: 16, lr: 3.87e-04
+2022-05-05 05:33:30,830 INFO [train.py:715] (3/8) Epoch 5, batch 13450, loss[loss=0.1513, simple_loss=0.2286, pruned_loss=0.03699, over 4941.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2248, pruned_loss=0.04277, over 971913.79 frames.], batch size: 29, lr: 3.87e-04
+2022-05-05 05:34:09,168 INFO [train.py:715] (3/8) Epoch 5, batch 13500, loss[loss=0.1672, simple_loss=0.2358, pruned_loss=0.04927, over 4793.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2252, pruned_loss=0.04266, over 971208.60 frames.], batch size: 14, lr: 3.87e-04
+2022-05-05 05:34:47,071 INFO [train.py:715] (3/8) Epoch 5, batch 13550, loss[loss=0.1517, simple_loss=0.2176, pruned_loss=0.04296, over 4980.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2249, pruned_loss=0.04231, over 971878.01 frames.], batch size: 14, lr: 3.87e-04
+2022-05-05 05:35:24,568 INFO [train.py:715] (3/8) Epoch 5, batch 13600, loss[loss=0.1481, simple_loss=0.2192, pruned_loss=0.03854, over 4889.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2241, pruned_loss=0.04209, over 972291.45 frames.], batch size: 22, lr: 3.87e-04
+2022-05-05 05:36:03,223 INFO [train.py:715] (3/8) Epoch 5, batch 13650, loss[loss=0.1542, simple_loss=0.2265, pruned_loss=0.04089, over 4966.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2235, pruned_loss=0.04173, over 972777.14 frames.], batch size: 14, lr: 3.87e-04
+2022-05-05 05:36:41,019 INFO [train.py:715] (3/8) Epoch 5, batch 13700, loss[loss=0.1542, simple_loss=0.2184, pruned_loss=0.04501, over 4834.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2228, pruned_loss=0.04142, over 972065.38 frames.], batch size: 15, lr: 3.87e-04
+2022-05-05 05:37:19,076 INFO [train.py:715] (3/8) Epoch 5, batch 13750, loss[loss=0.1469, simple_loss=0.2166, pruned_loss=0.0386, over 4790.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2224, pruned_loss=0.04088, over 972432.02 frames.], batch size: 18, lr: 3.87e-04
+2022-05-05 05:37:56,882 INFO [train.py:715] (3/8) Epoch 5, batch 13800, loss[loss=0.1254, simple_loss=0.1938, pruned_loss=0.02852, over 4900.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2226, pruned_loss=0.04087, over 972451.27 frames.], batch size: 17, lr: 3.87e-04
+2022-05-05 05:38:35,346 INFO [train.py:715] (3/8) Epoch 5, batch 13850, loss[loss=0.1413, simple_loss=0.2219, pruned_loss=0.03039, over 4788.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2217, pruned_loss=0.04036, over 972397.51 frames.], batch size: 17, lr: 3.87e-04
+2022-05-05 05:39:13,571 INFO [train.py:715] (3/8) Epoch 5, batch 13900, loss[loss=0.153, simple_loss=0.2253, pruned_loss=0.04039, over 4806.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2208, pruned_loss=0.03988, over 972868.49 frames.], batch size: 25, lr: 3.87e-04
+2022-05-05 05:39:51,058 INFO [train.py:715] (3/8) Epoch 5, batch 13950, loss[loss=0.1486, simple_loss=0.219, pruned_loss=0.03911, over 4964.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2212, pruned_loss=0.04011, over 973486.49 frames.], batch size: 15, lr: 3.87e-04
+2022-05-05 05:40:29,787 INFO [train.py:715] (3/8) Epoch 5, batch 14000, loss[loss=0.1466, simple_loss=0.2164, pruned_loss=0.0384, over 4941.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2212, pruned_loss=0.04035, over 974615.80 frames.], batch size: 18, lr: 3.87e-04
+2022-05-05 05:41:07,814 INFO [train.py:715] (3/8) Epoch 5, batch 14050, loss[loss=0.1295, simple_loss=0.1959, pruned_loss=0.03158, over 4788.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2211, pruned_loss=0.04034, over 973890.47 frames.], batch size: 18, lr: 3.87e-04
+2022-05-05 05:41:45,580 INFO [train.py:715] (3/8) Epoch 5, batch 14100, loss[loss=0.1484, simple_loss=0.2216, pruned_loss=0.0376, over 4764.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2225, pruned_loss=0.0409, over 974310.46 frames.], batch size: 16, lr: 3.86e-04
+2022-05-05 05:42:23,456 INFO [train.py:715] (3/8) Epoch 5, batch 14150, loss[loss=0.1679, simple_loss=0.243, pruned_loss=0.04643, over 4757.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2228, pruned_loss=0.0411, over 973252.74 frames.], batch size: 14, lr: 3.86e-04
+2022-05-05 05:43:01,800 INFO [train.py:715] (3/8) Epoch 5, batch 14200, loss[loss=0.1719, simple_loss=0.2344, pruned_loss=0.05472, over 4983.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2232, pruned_loss=0.04152, over 973700.59 frames.], batch size: 14, lr: 3.86e-04
+2022-05-05 05:43:40,050 INFO [train.py:715] (3/8) Epoch 5, batch 14250, loss[loss=0.1538, simple_loss=0.2383, pruned_loss=0.03463, over 4817.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2235, pruned_loss=0.04167, over 973597.45 frames.], batch size: 25, lr: 3.86e-04
+2022-05-05 05:44:18,051 INFO [train.py:715] (3/8) Epoch 5, batch 14300, loss[loss=0.1539, simple_loss=0.2137, pruned_loss=0.04705, over 4816.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2236, pruned_loss=0.04186, over 973512.76 frames.], batch size: 13, lr: 3.86e-04
+2022-05-05 05:44:56,435 INFO [train.py:715] (3/8) Epoch 5, batch 14350, loss[loss=0.1571, simple_loss=0.2318, pruned_loss=0.04116, over 4806.00 frames.], tot_loss[loss=0.1538, simple_loss=0.224, pruned_loss=0.04179, over 973633.26 frames.], batch size: 26, lr: 3.86e-04
+2022-05-05 05:45:34,231 INFO [train.py:715] (3/8) Epoch 5, batch 14400, loss[loss=0.15, simple_loss=0.2274, pruned_loss=0.03634, over 4814.00 frames.], tot_loss[loss=0.1536, simple_loss=0.224, pruned_loss=0.04165, over 973826.57 frames.], batch size: 27, lr: 3.86e-04
+2022-05-05 05:46:11,863 INFO [train.py:715] (3/8) Epoch 5, batch 14450, loss[loss=0.1359, simple_loss=0.2248, pruned_loss=0.02345, over 4969.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2234, pruned_loss=0.04151, over 972686.78 frames.], batch size: 24, lr: 3.86e-04
+2022-05-05 05:46:49,662 INFO [train.py:715] (3/8) Epoch 5, batch 14500, loss[loss=0.1588, simple_loss=0.2234, pruned_loss=0.04712, over 4793.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2234, pruned_loss=0.04146, over 972437.64 frames.], batch size: 24, lr: 3.86e-04
+2022-05-05 05:47:27,996 INFO [train.py:715] (3/8) Epoch 5, batch 14550, loss[loss=0.1784, simple_loss=0.2368, pruned_loss=0.06005, over 4782.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2232, pruned_loss=0.0415, over 972563.85 frames.], batch size: 14, lr: 3.86e-04
+2022-05-05 05:48:06,094 INFO [train.py:715] (3/8) Epoch 5, batch 14600, loss[loss=0.1545, simple_loss=0.2149, pruned_loss=0.047, over 4965.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2237, pruned_loss=0.04184, over 972150.60 frames.], batch size: 35, lr: 3.86e-04
+2022-05-05 05:48:44,026 INFO [train.py:715] (3/8) Epoch 5, batch 14650, loss[loss=0.2113, simple_loss=0.2672, pruned_loss=0.0777, over 4932.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2244, pruned_loss=0.04203, over 972085.63 frames.], batch size: 39, lr: 3.86e-04
+2022-05-05 05:49:22,273 INFO [train.py:715] (3/8) Epoch 5, batch 14700, loss[loss=0.133, simple_loss=0.1964, pruned_loss=0.03483, over 4952.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2236, pruned_loss=0.04154, over 972192.15 frames.], batch size: 35, lr: 3.86e-04
+2022-05-05 05:49:59,645 INFO [train.py:715] (3/8) Epoch 5, batch 14750, loss[loss=0.1239, simple_loss=0.2006, pruned_loss=0.02362, over 4861.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2233, pruned_loss=0.0415, over 971532.47 frames.], batch size: 20, lr: 3.86e-04
+2022-05-05 05:50:37,676 INFO [train.py:715] (3/8) Epoch 5, batch 14800, loss[loss=0.1662, simple_loss=0.2306, pruned_loss=0.05089, over 4907.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2228, pruned_loss=0.04117, over 971439.26 frames.], batch size: 17, lr: 3.86e-04
+2022-05-05 05:51:15,493 INFO [train.py:715] (3/8) Epoch 5, batch 14850, loss[loss=0.1352, simple_loss=0.2118, pruned_loss=0.02924, over 4900.00 frames.], tot_loss[loss=0.1526, simple_loss=0.223, pruned_loss=0.04113, over 971114.63 frames.], batch size: 18, lr: 3.86e-04
+2022-05-05 05:51:54,089 INFO [train.py:715] (3/8) Epoch 5, batch 14900, loss[loss=0.1568, simple_loss=0.2228, pruned_loss=0.04537, over 4745.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.0408, over 970998.32 frames.], batch size: 19, lr: 3.86e-04
+2022-05-05 05:52:32,750 INFO [train.py:715] (3/8) Epoch 5, batch 14950, loss[loss=0.1484, simple_loss=0.218, pruned_loss=0.03938, over 4928.00 frames.], tot_loss[loss=0.1524, simple_loss=0.223, pruned_loss=0.04086, over 971351.17 frames.], batch size: 23, lr: 3.86e-04
+2022-05-05 05:53:10,810 INFO [train.py:715] (3/8) Epoch 5, batch 15000, loss[loss=0.1462, simple_loss=0.22, pruned_loss=0.03615, over 4831.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2233, pruned_loss=0.04097, over 971296.57 frames.], batch size: 15, lr: 3.86e-04
+2022-05-05 05:53:10,810 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 05:53:21,082 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.1105, simple_loss=0.1958, pruned_loss=0.01261, over 914524.00 frames.
+2022-05-05 05:53:58,557 INFO [train.py:715] (3/8) Epoch 5, batch 15050, loss[loss=0.169, simple_loss=0.2271, pruned_loss=0.05539, over 4879.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2235, pruned_loss=0.04082, over 971058.37 frames.], batch size: 16, lr: 3.85e-04
+2022-05-05 05:54:37,215 INFO [train.py:715] (3/8) Epoch 5, batch 15100, loss[loss=0.1714, simple_loss=0.2283, pruned_loss=0.05719, over 4841.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04046, over 970106.75 frames.], batch size: 30, lr: 3.85e-04
+2022-05-05 05:55:15,136 INFO [train.py:715] (3/8) Epoch 5, batch 15150, loss[loss=0.1475, simple_loss=0.2107, pruned_loss=0.04217, over 4758.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2222, pruned_loss=0.04042, over 970795.02 frames.], batch size: 19, lr: 3.85e-04
+2022-05-05 05:55:53,272 INFO [train.py:715] (3/8) Epoch 5, batch 15200, loss[loss=0.1704, simple_loss=0.2356, pruned_loss=0.05257, over 4957.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04029, over 971834.18 frames.], batch size: 39, lr: 3.85e-04
+2022-05-05 05:56:32,188 INFO [train.py:715] (3/8) Epoch 5, batch 15250, loss[loss=0.1235, simple_loss=0.1999, pruned_loss=0.02353, over 4698.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2215, pruned_loss=0.03995, over 972218.16 frames.], batch size: 15, lr: 3.85e-04
+2022-05-05 05:57:10,899 INFO [train.py:715] (3/8) Epoch 5, batch 15300, loss[loss=0.1458, simple_loss=0.2194, pruned_loss=0.03612, over 4778.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04028, over 972345.70 frames.], batch size: 17, lr: 3.85e-04
+2022-05-05 05:57:50,139 INFO [train.py:715] (3/8) Epoch 5, batch 15350, loss[loss=0.1712, simple_loss=0.2414, pruned_loss=0.05046, over 4986.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2224, pruned_loss=0.04111, over 973297.58 frames.], batch size: 31, lr: 3.85e-04
+2022-05-05 05:58:28,475 INFO [train.py:715] (3/8) Epoch 5, batch 15400, loss[loss=0.1728, simple_loss=0.2329, pruned_loss=0.05635, over 4830.00 frames.], tot_loss[loss=0.152, simple_loss=0.2218, pruned_loss=0.04114, over 973449.10 frames.], batch size: 15, lr: 3.85e-04
+2022-05-05 05:59:07,519 INFO [train.py:715] (3/8) Epoch 5, batch 15450, loss[loss=0.1541, simple_loss=0.2161, pruned_loss=0.04605, over 4970.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2219, pruned_loss=0.04123, over 973554.47 frames.], batch size: 35, lr: 3.85e-04
+2022-05-05 05:59:46,050 INFO [train.py:715] (3/8) Epoch 5, batch 15500, loss[loss=0.1633, simple_loss=0.2264, pruned_loss=0.05011, over 4751.00 frames.], tot_loss[loss=0.152, simple_loss=0.2219, pruned_loss=0.04106, over 972732.69 frames.], batch size: 19, lr: 3.85e-04
+2022-05-05 06:00:25,318 INFO [train.py:715] (3/8) Epoch 5, batch 15550, loss[loss=0.1505, simple_loss=0.2249, pruned_loss=0.03806, over 4916.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2225, pruned_loss=0.04121, over 971889.37 frames.], batch size: 18, lr: 3.85e-04
+2022-05-05 06:01:03,326 INFO [train.py:715] (3/8) Epoch 5, batch 15600, loss[loss=0.1841, simple_loss=0.2582, pruned_loss=0.055, over 4769.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2236, pruned_loss=0.04179, over 971290.29 frames.], batch size: 14, lr: 3.85e-04
+2022-05-05 06:01:40,927 INFO [train.py:715] (3/8) Epoch 5, batch 15650, loss[loss=0.138, simple_loss=0.2087, pruned_loss=0.0336, over 4932.00 frames.], tot_loss[loss=0.152, simple_loss=0.2224, pruned_loss=0.04083, over 972183.56 frames.], batch size: 23, lr: 3.85e-04
+2022-05-05 06:02:18,447 INFO [train.py:715] (3/8) Epoch 5, batch 15700, loss[loss=0.1731, simple_loss=0.24, pruned_loss=0.05307, over 4947.00 frames.], tot_loss[loss=0.1526, simple_loss=0.223, pruned_loss=0.04116, over 972380.53 frames.], batch size: 23, lr: 3.85e-04
+2022-05-05 06:02:56,466 INFO [train.py:715] (3/8) Epoch 5, batch 15750, loss[loss=0.1373, simple_loss=0.2123, pruned_loss=0.03113, over 4820.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2231, pruned_loss=0.04136, over 973312.11 frames.], batch size: 12, lr: 3.85e-04
+2022-05-05 06:03:34,888 INFO [train.py:715] (3/8) Epoch 5, batch 15800, loss[loss=0.1563, simple_loss=0.2175, pruned_loss=0.04749, over 4990.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2226, pruned_loss=0.04124, over 972744.09 frames.], batch size: 33, lr: 3.85e-04
+2022-05-05 06:04:12,956 INFO [train.py:715] (3/8) Epoch 5, batch 15850, loss[loss=0.1364, simple_loss=0.2049, pruned_loss=0.03389, over 4794.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2214, pruned_loss=0.04091, over 972728.57 frames.], batch size: 13, lr: 3.85e-04
+2022-05-05 06:04:50,529 INFO [train.py:715] (3/8) Epoch 5, batch 15900, loss[loss=0.1782, simple_loss=0.2471, pruned_loss=0.05466, over 4883.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2217, pruned_loss=0.04088, over 972415.48 frames.], batch size: 39, lr: 3.85e-04
+2022-05-05 06:05:28,345 INFO [train.py:715] (3/8) Epoch 5, batch 15950, loss[loss=0.1417, simple_loss=0.2082, pruned_loss=0.03765, over 4926.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2219, pruned_loss=0.04077, over 972656.13 frames.], batch size: 23, lr: 3.85e-04
+2022-05-05 06:06:05,813 INFO [train.py:715] (3/8) Epoch 5, batch 16000, loss[loss=0.1549, simple_loss=0.2314, pruned_loss=0.03925, over 4991.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2218, pruned_loss=0.04078, over 972880.32 frames.], batch size: 20, lr: 3.85e-04
+2022-05-05 06:06:43,537 INFO [train.py:715] (3/8) Epoch 5, batch 16050, loss[loss=0.1346, simple_loss=0.2033, pruned_loss=0.03297, over 4956.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04039, over 972960.33 frames.], batch size: 15, lr: 3.84e-04
+2022-05-05 06:07:21,602 INFO [train.py:715] (3/8) Epoch 5, batch 16100, loss[loss=0.1365, simple_loss=0.2117, pruned_loss=0.03066, over 4994.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2225, pruned_loss=0.04096, over 972187.70 frames.], batch size: 20, lr: 3.84e-04
+2022-05-05 06:08:00,780 INFO [train.py:715] (3/8) Epoch 5, batch 16150, loss[loss=0.1391, simple_loss=0.2199, pruned_loss=0.02919, over 4927.00 frames.], tot_loss[loss=0.1526, simple_loss=0.223, pruned_loss=0.0411, over 972675.44 frames.], batch size: 29, lr: 3.84e-04
+2022-05-05 06:08:39,728 INFO [train.py:715] (3/8) Epoch 5, batch 16200, loss[loss=0.1375, simple_loss=0.2147, pruned_loss=0.0302, over 4940.00 frames.], tot_loss[loss=0.1516, simple_loss=0.222, pruned_loss=0.04062, over 971971.96 frames.], batch size: 21, lr: 3.84e-04
+2022-05-05 06:09:18,290 INFO [train.py:715] (3/8) Epoch 5, batch 16250, loss[loss=0.141, simple_loss=0.2112, pruned_loss=0.03538, over 4951.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2213, pruned_loss=0.04017, over 971817.64 frames.], batch size: 24, lr: 3.84e-04
+2022-05-05 06:09:56,099 INFO [train.py:715] (3/8) Epoch 5, batch 16300, loss[loss=0.163, simple_loss=0.2176, pruned_loss=0.05423, over 4855.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2217, pruned_loss=0.04059, over 971352.56 frames.], batch size: 32, lr: 3.84e-04
+2022-05-05 06:10:34,110 INFO [train.py:715] (3/8) Epoch 5, batch 16350, loss[loss=0.122, simple_loss=0.1928, pruned_loss=0.02561, over 4700.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04106, over 971530.31 frames.], batch size: 15, lr: 3.84e-04
+2022-05-05 06:11:12,494 INFO [train.py:715] (3/8) Epoch 5, batch 16400, loss[loss=0.1216, simple_loss=0.1939, pruned_loss=0.02469, over 4825.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2225, pruned_loss=0.04089, over 971829.97 frames.], batch size: 25, lr: 3.84e-04
+2022-05-05 06:11:50,952 INFO [train.py:715] (3/8) Epoch 5, batch 16450, loss[loss=0.143, simple_loss=0.2038, pruned_loss=0.04107, over 4782.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2222, pruned_loss=0.04052, over 972843.21 frames.], batch size: 14, lr: 3.84e-04
+2022-05-05 06:12:30,301 INFO [train.py:715] (3/8) Epoch 5, batch 16500, loss[loss=0.1645, simple_loss=0.2287, pruned_loss=0.05015, over 4866.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2216, pruned_loss=0.04029, over 971826.75 frames.], batch size: 34, lr: 3.84e-04
+2022-05-05 06:13:08,222 INFO [train.py:715] (3/8) Epoch 5, batch 16550, loss[loss=0.1508, simple_loss=0.2213, pruned_loss=0.04013, over 4776.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2215, pruned_loss=0.04073, over 971632.16 frames.], batch size: 18, lr: 3.84e-04
+2022-05-05 06:13:46,906 INFO [train.py:715] (3/8) Epoch 5, batch 16600, loss[loss=0.1693, simple_loss=0.2406, pruned_loss=0.04904, over 4845.00 frames.], tot_loss[loss=0.1518, simple_loss=0.222, pruned_loss=0.04087, over 971197.88 frames.], batch size: 30, lr: 3.84e-04
+2022-05-05 06:14:25,620 INFO [train.py:715] (3/8) Epoch 5, batch 16650, loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02876, over 4903.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2226, pruned_loss=0.04113, over 970921.92 frames.], batch size: 17, lr: 3.84e-04
+2022-05-05 06:15:04,295 INFO [train.py:715] (3/8) Epoch 5, batch 16700, loss[loss=0.1927, simple_loss=0.2479, pruned_loss=0.0688, over 4913.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2237, pruned_loss=0.0419, over 972231.62 frames.], batch size: 17, lr: 3.84e-04
+2022-05-05 06:15:42,484 INFO [train.py:715] (3/8) Epoch 5, batch 16750, loss[loss=0.1417, simple_loss=0.2055, pruned_loss=0.0389, over 4901.00 frames.], tot_loss[loss=0.153, simple_loss=0.2229, pruned_loss=0.04154, over 972413.17 frames.], batch size: 39, lr: 3.84e-04
+2022-05-05 06:16:20,936 INFO [train.py:715] (3/8) Epoch 5, batch 16800, loss[loss=0.1418, simple_loss=0.2165, pruned_loss=0.0336, over 4954.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.04101, over 972775.36 frames.], batch size: 24, lr: 3.84e-04
+2022-05-05 06:17:00,069 INFO [train.py:715] (3/8) Epoch 5, batch 16850, loss[loss=0.173, simple_loss=0.2379, pruned_loss=0.05409, over 4815.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2221, pruned_loss=0.04082, over 972052.26 frames.], batch size: 25, lr: 3.84e-04
+2022-05-05 06:17:37,930 INFO [train.py:715] (3/8) Epoch 5, batch 16900, loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03277, over 4810.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2227, pruned_loss=0.0413, over 973573.15 frames.], batch size: 25, lr: 3.84e-04
+2022-05-05 06:18:16,757 INFO [train.py:715] (3/8) Epoch 5, batch 16950, loss[loss=0.1676, simple_loss=0.2332, pruned_loss=0.05099, over 4856.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2227, pruned_loss=0.04103, over 973611.18 frames.], batch size: 16, lr: 3.84e-04
+2022-05-05 06:18:55,161 INFO [train.py:715] (3/8) Epoch 5, batch 17000, loss[loss=0.153, simple_loss=0.2354, pruned_loss=0.03537, over 4903.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2235, pruned_loss=0.0411, over 973487.82 frames.], batch size: 18, lr: 3.84e-04
+2022-05-05 06:19:33,551 INFO [train.py:715] (3/8) Epoch 5, batch 17050, loss[loss=0.1684, simple_loss=0.2368, pruned_loss=0.05005, over 4775.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2226, pruned_loss=0.04131, over 973490.67 frames.], batch size: 18, lr: 3.83e-04
+2022-05-05 06:20:11,942 INFO [train.py:715] (3/8) Epoch 5, batch 17100, loss[loss=0.1714, simple_loss=0.2482, pruned_loss=0.04731, over 4820.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2226, pruned_loss=0.04092, over 972576.56 frames.], batch size: 27, lr: 3.83e-04
+2022-05-05 06:20:49,751 INFO [train.py:715] (3/8) Epoch 5, batch 17150, loss[loss=0.1598, simple_loss=0.2135, pruned_loss=0.05305, over 4784.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2238, pruned_loss=0.04156, over 972291.29 frames.], batch size: 12, lr: 3.83e-04
+2022-05-05 06:21:27,630 INFO [train.py:715] (3/8) Epoch 5, batch 17200, loss[loss=0.1482, simple_loss=0.209, pruned_loss=0.0437, over 4775.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2231, pruned_loss=0.04122, over 973221.30 frames.], batch size: 17, lr: 3.83e-04
+2022-05-05 06:22:04,736 INFO [train.py:715] (3/8) Epoch 5, batch 17250, loss[loss=0.1686, simple_loss=0.2541, pruned_loss=0.04159, over 4804.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2227, pruned_loss=0.04104, over 974137.46 frames.], batch size: 21, lr: 3.83e-04
+2022-05-05 06:22:42,971 INFO [train.py:715] (3/8) Epoch 5, batch 17300, loss[loss=0.1245, simple_loss=0.1937, pruned_loss=0.02766, over 4821.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2223, pruned_loss=0.04095, over 973702.13 frames.], batch size: 26, lr: 3.83e-04
+2022-05-05 06:23:22,498 INFO [train.py:715] (3/8) Epoch 5, batch 17350, loss[loss=0.1683, simple_loss=0.2324, pruned_loss=0.05205, over 4932.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2231, pruned_loss=0.04162, over 973421.57 frames.], batch size: 39, lr: 3.83e-04
+2022-05-05 06:24:00,869 INFO [train.py:715] (3/8) Epoch 5, batch 17400, loss[loss=0.1375, simple_loss=0.2151, pruned_loss=0.02997, over 4923.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2218, pruned_loss=0.04066, over 974618.35 frames.], batch size: 29, lr: 3.83e-04
+2022-05-05 06:24:39,481 INFO [train.py:715] (3/8) Epoch 5, batch 17450, loss[loss=0.141, simple_loss=0.2042, pruned_loss=0.03886, over 4930.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2219, pruned_loss=0.04063, over 974562.58 frames.], batch size: 29, lr: 3.83e-04
+2022-05-05 06:25:17,955 INFO [train.py:715] (3/8) Epoch 5, batch 17500, loss[loss=0.1459, simple_loss=0.23, pruned_loss=0.03087, over 4743.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2221, pruned_loss=0.04067, over 973952.10 frames.], batch size: 16, lr: 3.83e-04
+2022-05-05 06:25:56,806 INFO [train.py:715] (3/8) Epoch 5, batch 17550, loss[loss=0.1819, simple_loss=0.2484, pruned_loss=0.0577, over 4971.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2212, pruned_loss=0.04017, over 974010.96 frames.], batch size: 35, lr: 3.83e-04
+2022-05-05 06:26:35,442 INFO [train.py:715] (3/8) Epoch 5, batch 17600, loss[loss=0.146, simple_loss=0.2088, pruned_loss=0.0416, over 4887.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2211, pruned_loss=0.04016, over 973591.38 frames.], batch size: 16, lr: 3.83e-04
+2022-05-05 06:27:14,152 INFO [train.py:715] (3/8) Epoch 5, batch 17650, loss[loss=0.1667, simple_loss=0.2345, pruned_loss=0.04948, over 4776.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.04015, over 973424.37 frames.], batch size: 18, lr: 3.83e-04
+2022-05-05 06:27:52,809 INFO [train.py:715] (3/8) Epoch 5, batch 17700, loss[loss=0.1579, simple_loss=0.2374, pruned_loss=0.03923, over 4902.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2216, pruned_loss=0.04001, over 974033.93 frames.], batch size: 17, lr: 3.83e-04
+2022-05-05 06:28:31,728 INFO [train.py:715] (3/8) Epoch 5, batch 17750, loss[loss=0.1799, simple_loss=0.2523, pruned_loss=0.05369, over 4891.00 frames.], tot_loss[loss=0.151, simple_loss=0.2216, pruned_loss=0.04019, over 972898.16 frames.], batch size: 39, lr: 3.83e-04
+2022-05-05 06:29:09,753 INFO [train.py:715] (3/8) Epoch 5, batch 17800, loss[loss=0.1488, simple_loss=0.224, pruned_loss=0.03683, over 4792.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2221, pruned_loss=0.04034, over 972803.84 frames.], batch size: 17, lr: 3.83e-04
+2022-05-05 06:29:48,584 INFO [train.py:715] (3/8) Epoch 5, batch 17850, loss[loss=0.1661, simple_loss=0.2376, pruned_loss=0.04736, over 4854.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2222, pruned_loss=0.04036, over 973729.66 frames.], batch size: 30, lr: 3.83e-04
+2022-05-05 06:30:27,678 INFO [train.py:715] (3/8) Epoch 5, batch 17900, loss[loss=0.1596, simple_loss=0.2392, pruned_loss=0.03999, over 4791.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2225, pruned_loss=0.04031, over 972860.85 frames.], batch size: 12, lr: 3.83e-04
+2022-05-05 06:31:06,330 INFO [train.py:715] (3/8) Epoch 5, batch 17950, loss[loss=0.1415, simple_loss=0.2111, pruned_loss=0.03597, over 4791.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2222, pruned_loss=0.0404, over 973686.15 frames.], batch size: 21, lr: 3.83e-04
+2022-05-05 06:31:47,054 INFO [train.py:715] (3/8) Epoch 5, batch 18000, loss[loss=0.2048, simple_loss=0.2643, pruned_loss=0.07262, over 4793.00 frames.], tot_loss[loss=0.152, simple_loss=0.2226, pruned_loss=0.04073, over 973511.37 frames.], batch size: 18, lr: 3.83e-04
+2022-05-05 06:31:47,054 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 06:31:59,753 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.1102, simple_loss=0.1955, pruned_loss=0.01245, over 914524.00 frames.
+2022-05-05 06:32:38,358 INFO [train.py:715] (3/8) Epoch 5, batch 18050, loss[loss=0.09822, simple_loss=0.1719, pruned_loss=0.01229, over 4956.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2228, pruned_loss=0.04082, over 973690.33 frames.], batch size: 24, lr: 3.82e-04
+2022-05-05 06:33:17,596 INFO [train.py:715] (3/8) Epoch 5, batch 18100, loss[loss=0.1411, simple_loss=0.2208, pruned_loss=0.03065, over 4692.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04099, over 972868.58 frames.], batch size: 15, lr: 3.82e-04
+2022-05-05 06:33:56,334 INFO [train.py:715] (3/8) Epoch 5, batch 18150, loss[loss=0.1302, simple_loss=0.2054, pruned_loss=0.02753, over 4987.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2229, pruned_loss=0.04092, over 972292.68 frames.], batch size: 25, lr: 3.82e-04
+2022-05-05 06:34:34,858 INFO [train.py:715] (3/8) Epoch 5, batch 18200, loss[loss=0.1718, simple_loss=0.2438, pruned_loss=0.04993, over 4767.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2233, pruned_loss=0.0412, over 972249.44 frames.], batch size: 18, lr: 3.82e-04
+2022-05-05 06:35:14,242 INFO [train.py:715] (3/8) Epoch 5, batch 18250, loss[loss=0.1674, simple_loss=0.228, pruned_loss=0.05337, over 4818.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2234, pruned_loss=0.04143, over 972483.73 frames.], batch size: 25, lr: 3.82e-04
+2022-05-05 06:35:53,137 INFO [train.py:715] (3/8) Epoch 5, batch 18300, loss[loss=0.117, simple_loss=0.1884, pruned_loss=0.02281, over 4833.00 frames.], tot_loss[loss=0.154, simple_loss=0.2242, pruned_loss=0.04195, over 972957.93 frames.], batch size: 13, lr: 3.82e-04
+2022-05-05 06:36:31,710 INFO [train.py:715] (3/8) Epoch 5, batch 18350, loss[loss=0.1572, simple_loss=0.2312, pruned_loss=0.04162, over 4872.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2234, pruned_loss=0.04105, over 973149.34 frames.], batch size: 22, lr: 3.82e-04
+2022-05-05 06:37:09,997 INFO [train.py:715] (3/8) Epoch 5, batch 18400, loss[loss=0.1467, simple_loss=0.2179, pruned_loss=0.0377, over 4784.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2232, pruned_loss=0.04061, over 973230.30 frames.], batch size: 14, lr: 3.82e-04
+2022-05-05 06:37:49,159 INFO [train.py:715] (3/8) Epoch 5, batch 18450, loss[loss=0.1249, simple_loss=0.1954, pruned_loss=0.02719, over 4985.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2222, pruned_loss=0.0405, over 972841.95 frames.], batch size: 15, lr: 3.82e-04
+2022-05-05 06:38:27,816 INFO [train.py:715] (3/8) Epoch 5, batch 18500, loss[loss=0.1402, simple_loss=0.2188, pruned_loss=0.03083, over 4975.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2216, pruned_loss=0.04, over 973164.37 frames.], batch size: 28, lr: 3.82e-04
+2022-05-05 06:39:06,126 INFO [train.py:715] (3/8) Epoch 5, batch 18550, loss[loss=0.1483, simple_loss=0.2182, pruned_loss=0.03919, over 4900.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2214, pruned_loss=0.03984, over 973003.82 frames.], batch size: 22, lr: 3.82e-04
+2022-05-05 06:39:45,170 INFO [train.py:715] (3/8) Epoch 5, batch 18600, loss[loss=0.1478, simple_loss=0.2106, pruned_loss=0.04246, over 4920.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03972, over 973505.82 frames.], batch size: 18, lr: 3.82e-04
+2022-05-05 06:40:23,780 INFO [train.py:715] (3/8) Epoch 5, batch 18650, loss[loss=0.153, simple_loss=0.2335, pruned_loss=0.03628, over 4749.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2213, pruned_loss=0.03966, over 972898.47 frames.], batch size: 16, lr: 3.82e-04
+2022-05-05 06:41:01,939 INFO [train.py:715] (3/8) Epoch 5, batch 18700, loss[loss=0.1402, simple_loss=0.2092, pruned_loss=0.0356, over 4905.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2216, pruned_loss=0.03989, over 973140.21 frames.], batch size: 19, lr: 3.82e-04
+2022-05-05 06:41:40,675 INFO [train.py:715] (3/8) Epoch 5, batch 18750, loss[loss=0.1785, simple_loss=0.2398, pruned_loss=0.05862, over 4966.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2234, pruned_loss=0.04097, over 971943.30 frames.], batch size: 24, lr: 3.82e-04
+2022-05-05 06:42:19,956 INFO [train.py:715] (3/8) Epoch 5, batch 18800, loss[loss=0.1288, simple_loss=0.2058, pruned_loss=0.0259, over 4966.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2223, pruned_loss=0.04041, over 972357.08 frames.], batch size: 24, lr: 3.82e-04
+2022-05-05 06:42:59,659 INFO [train.py:715] (3/8) Epoch 5, batch 18850, loss[loss=0.1284, simple_loss=0.1969, pruned_loss=0.02993, over 4932.00 frames.], tot_loss[loss=0.1511, simple_loss=0.222, pruned_loss=0.04011, over 972640.32 frames.], batch size: 29, lr: 3.82e-04
+2022-05-05 06:43:38,448 INFO [train.py:715] (3/8) Epoch 5, batch 18900, loss[loss=0.2078, simple_loss=0.2728, pruned_loss=0.07142, over 4837.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2225, pruned_loss=0.04018, over 972295.50 frames.], batch size: 26, lr: 3.82e-04
+2022-05-05 06:44:16,644 INFO [train.py:715] (3/8) Epoch 5, batch 18950, loss[loss=0.1594, simple_loss=0.2345, pruned_loss=0.04213, over 4987.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2229, pruned_loss=0.04039, over 972604.06 frames.], batch size: 25, lr: 3.82e-04
+2022-05-05 06:44:56,139 INFO [train.py:715] (3/8) Epoch 5, batch 19000, loss[loss=0.1384, simple_loss=0.206, pruned_loss=0.03543, over 4981.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2229, pruned_loss=0.04042, over 972590.38 frames.], batch size: 28, lr: 3.82e-04
+2022-05-05 06:45:34,090 INFO [train.py:715] (3/8) Epoch 5, batch 19050, loss[loss=0.2394, simple_loss=0.2665, pruned_loss=0.1061, over 4703.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2222, pruned_loss=0.04025, over 972576.98 frames.], batch size: 15, lr: 3.81e-04
+2022-05-05 06:46:13,038 INFO [train.py:715] (3/8) Epoch 5, batch 19100, loss[loss=0.162, simple_loss=0.2265, pruned_loss=0.04875, over 4847.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2218, pruned_loss=0.04034, over 972779.69 frames.], batch size: 32, lr: 3.81e-04
+2022-05-05 06:46:52,737 INFO [train.py:715] (3/8) Epoch 5, batch 19150, loss[loss=0.1492, simple_loss=0.2264, pruned_loss=0.03605, over 4881.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2222, pruned_loss=0.04035, over 972446.59 frames.], batch size: 22, lr: 3.81e-04
+2022-05-05 06:47:31,315 INFO [train.py:715] (3/8) Epoch 5, batch 19200, loss[loss=0.1651, simple_loss=0.2303, pruned_loss=0.04993, over 4766.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2226, pruned_loss=0.04015, over 971875.68 frames.], batch size: 18, lr: 3.81e-04
+2022-05-05 06:48:10,847 INFO [train.py:715] (3/8) Epoch 5, batch 19250, loss[loss=0.1424, simple_loss=0.2138, pruned_loss=0.03553, over 4834.00 frames.], tot_loss[loss=0.1522, simple_loss=0.223, pruned_loss=0.04071, over 972318.55 frames.], batch size: 30, lr: 3.81e-04
+2022-05-05 06:48:48,906 INFO [train.py:715] (3/8) Epoch 5, batch 19300, loss[loss=0.2034, simple_loss=0.2815, pruned_loss=0.06263, over 4948.00 frames.], tot_loss[loss=0.153, simple_loss=0.2235, pruned_loss=0.04127, over 972939.88 frames.], batch size: 29, lr: 3.81e-04
+2022-05-05 06:49:28,000 INFO [train.py:715] (3/8) Epoch 5, batch 19350, loss[loss=0.1314, simple_loss=0.2079, pruned_loss=0.02745, over 4826.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2233, pruned_loss=0.04083, over 972664.10 frames.], batch size: 25, lr: 3.81e-04
+2022-05-05 06:50:06,759 INFO [train.py:715] (3/8) Epoch 5, batch 19400, loss[loss=0.1643, simple_loss=0.2317, pruned_loss=0.04844, over 4876.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2234, pruned_loss=0.04118, over 972185.40 frames.], batch size: 22, lr: 3.81e-04
+2022-05-05 06:50:45,415 INFO [train.py:715] (3/8) Epoch 5, batch 19450, loss[loss=0.155, simple_loss=0.2151, pruned_loss=0.04751, over 4840.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2232, pruned_loss=0.04096, over 972055.28 frames.], batch size: 30, lr: 3.81e-04
+2022-05-05 06:51:25,053 INFO [train.py:715] (3/8) Epoch 5, batch 19500, loss[loss=0.148, simple_loss=0.2381, pruned_loss=0.02899, over 4922.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2228, pruned_loss=0.04115, over 972099.71 frames.], batch size: 29, lr: 3.81e-04
+2022-05-05 06:52:03,849 INFO [train.py:715] (3/8) Epoch 5, batch 19550, loss[loss=0.1466, simple_loss=0.2174, pruned_loss=0.03791, over 4984.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2234, pruned_loss=0.0415, over 971732.60 frames.], batch size: 35, lr: 3.81e-04
+2022-05-05 06:52:42,736 INFO [train.py:715] (3/8) Epoch 5, batch 19600, loss[loss=0.1451, simple_loss=0.2236, pruned_loss=0.0333, over 4887.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2244, pruned_loss=0.0421, over 970618.57 frames.], batch size: 19, lr: 3.81e-04
+2022-05-05 06:53:21,191 INFO [train.py:715] (3/8) Epoch 5, batch 19650, loss[loss=0.107, simple_loss=0.1727, pruned_loss=0.02065, over 4781.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2229, pruned_loss=0.04126, over 970036.62 frames.], batch size: 12, lr: 3.81e-04
+2022-05-05 06:54:00,675 INFO [train.py:715] (3/8) Epoch 5, batch 19700, loss[loss=0.1565, simple_loss=0.2202, pruned_loss=0.04641, over 4750.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2228, pruned_loss=0.04105, over 971105.13 frames.], batch size: 16, lr: 3.81e-04
+2022-05-05 06:54:39,904 INFO [train.py:715] (3/8) Epoch 5, batch 19750, loss[loss=0.1949, simple_loss=0.2505, pruned_loss=0.06965, over 4980.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2235, pruned_loss=0.0414, over 971708.35 frames.], batch size: 39, lr: 3.81e-04
+2022-05-05 06:55:17,844 INFO [train.py:715] (3/8) Epoch 5, batch 19800, loss[loss=0.1875, simple_loss=0.2533, pruned_loss=0.06083, over 4938.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2229, pruned_loss=0.04079, over 971768.53 frames.], batch size: 39, lr: 3.81e-04
+2022-05-05 06:55:56,846 INFO [train.py:715] (3/8) Epoch 5, batch 19850, loss[loss=0.1709, simple_loss=0.2376, pruned_loss=0.05214, over 4907.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04135, over 972527.13 frames.], batch size: 19, lr: 3.81e-04
+2022-05-05 06:56:35,744 INFO [train.py:715] (3/8) Epoch 5, batch 19900, loss[loss=0.1536, simple_loss=0.2229, pruned_loss=0.04214, over 4935.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.04092, over 972768.15 frames.], batch size: 18, lr: 3.81e-04
+2022-05-05 06:57:14,682 INFO [train.py:715] (3/8) Epoch 5, batch 19950, loss[loss=0.15, simple_loss=0.2246, pruned_loss=0.03768, over 4787.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2226, pruned_loss=0.0411, over 973297.50 frames.], batch size: 18, lr: 3.81e-04
+2022-05-05 06:57:53,119 INFO [train.py:715] (3/8) Epoch 5, batch 20000, loss[loss=0.1588, simple_loss=0.2428, pruned_loss=0.03741, over 4919.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2222, pruned_loss=0.04067, over 973111.48 frames.], batch size: 39, lr: 3.81e-04
+2022-05-05 06:58:32,599 INFO [train.py:715] (3/8) Epoch 5, batch 20050, loss[loss=0.1498, simple_loss=0.2333, pruned_loss=0.03314, over 4772.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2227, pruned_loss=0.04108, over 972863.01 frames.], batch size: 18, lr: 3.81e-04
+2022-05-05 06:59:12,131 INFO [train.py:715] (3/8) Epoch 5, batch 20100, loss[loss=0.1764, simple_loss=0.2473, pruned_loss=0.05281, over 4955.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2232, pruned_loss=0.04108, over 972808.80 frames.], batch size: 24, lr: 3.80e-04
+2022-05-05 06:59:50,437 INFO [train.py:715] (3/8) Epoch 5, batch 20150, loss[loss=0.1513, simple_loss=0.2266, pruned_loss=0.03799, over 4928.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2221, pruned_loss=0.04031, over 972491.46 frames.], batch size: 18, lr: 3.80e-04
+2022-05-05 07:00:30,260 INFO [train.py:715] (3/8) Epoch 5, batch 20200, loss[loss=0.1784, simple_loss=0.2502, pruned_loss=0.05333, over 4941.00 frames.], tot_loss[loss=0.152, simple_loss=0.2227, pruned_loss=0.04059, over 972683.26 frames.], batch size: 39, lr: 3.80e-04
+2022-05-05 07:01:09,276 INFO [train.py:715] (3/8) Epoch 5, batch 20250, loss[loss=0.1263, simple_loss=0.2001, pruned_loss=0.0262, over 4878.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2214, pruned_loss=0.0401, over 972636.22 frames.], batch size: 22, lr: 3.80e-04
+2022-05-05 07:01:47,788 INFO [train.py:715] (3/8) Epoch 5, batch 20300, loss[loss=0.1406, simple_loss=0.198, pruned_loss=0.04155, over 4805.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04025, over 973170.04 frames.], batch size: 13, lr: 3.80e-04
+2022-05-05 07:02:25,749 INFO [train.py:715] (3/8) Epoch 5, batch 20350, loss[loss=0.1606, simple_loss=0.2273, pruned_loss=0.04697, over 4686.00 frames.], tot_loss[loss=0.1513, simple_loss=0.222, pruned_loss=0.0403, over 972407.88 frames.], batch size: 15, lr: 3.80e-04
+2022-05-05 07:03:04,305 INFO [train.py:715] (3/8) Epoch 5, batch 20400, loss[loss=0.1412, simple_loss=0.22, pruned_loss=0.03117, over 4910.00 frames.], tot_loss[loss=0.152, simple_loss=0.223, pruned_loss=0.04049, over 972355.02 frames.], batch size: 18, lr: 3.80e-04
+2022-05-05 07:03:43,174 INFO [train.py:715] (3/8) Epoch 5, batch 20450, loss[loss=0.1211, simple_loss=0.2005, pruned_loss=0.02085, over 4837.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.04086, over 972547.55 frames.], batch size: 13, lr: 3.80e-04
+2022-05-05 07:04:21,313 INFO [train.py:715] (3/8) Epoch 5, batch 20500, loss[loss=0.138, simple_loss=0.205, pruned_loss=0.03553, over 4805.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2219, pruned_loss=0.03997, over 972667.05 frames.], batch size: 21, lr: 3.80e-04
+2022-05-05 07:05:00,718 INFO [train.py:715] (3/8) Epoch 5, batch 20550, loss[loss=0.1472, simple_loss=0.2181, pruned_loss=0.03812, over 4978.00 frames.], tot_loss[loss=0.1507, simple_loss=0.222, pruned_loss=0.03965, over 972871.27 frames.], batch size: 25, lr: 3.80e-04
+2022-05-05 07:05:39,984 INFO [train.py:715] (3/8) Epoch 5, batch 20600, loss[loss=0.1609, simple_loss=0.2292, pruned_loss=0.04629, over 4793.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2222, pruned_loss=0.03953, over 972654.06 frames.], batch size: 24, lr: 3.80e-04
+2022-05-05 07:06:18,977 INFO [train.py:715] (3/8) Epoch 5, batch 20650, loss[loss=0.1579, simple_loss=0.2338, pruned_loss=0.04099, over 4968.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2225, pruned_loss=0.03953, over 972966.77 frames.], batch size: 28, lr: 3.80e-04
+2022-05-05 07:06:58,195 INFO [train.py:715] (3/8) Epoch 5, batch 20700, loss[loss=0.1558, simple_loss=0.2308, pruned_loss=0.04045, over 4919.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2222, pruned_loss=0.03975, over 973260.17 frames.], batch size: 18, lr: 3.80e-04
+2022-05-05 07:07:36,962 INFO [train.py:715] (3/8) Epoch 5, batch 20750, loss[loss=0.1531, simple_loss=0.2285, pruned_loss=0.03885, over 4703.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2226, pruned_loss=0.04048, over 972876.58 frames.], batch size: 15, lr: 3.80e-04
+2022-05-05 07:08:16,383 INFO [train.py:715] (3/8) Epoch 5, batch 20800, loss[loss=0.1573, simple_loss=0.2301, pruned_loss=0.04227, over 4801.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2225, pruned_loss=0.0405, over 972852.41 frames.], batch size: 21, lr: 3.80e-04
+2022-05-05 07:08:55,023 INFO [train.py:715] (3/8) Epoch 5, batch 20850, loss[loss=0.1426, simple_loss=0.2189, pruned_loss=0.03317, over 4832.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2222, pruned_loss=0.04049, over 972516.28 frames.], batch size: 15, lr: 3.80e-04
+2022-05-05 07:09:34,328 INFO [train.py:715] (3/8) Epoch 5, batch 20900, loss[loss=0.1522, simple_loss=0.2317, pruned_loss=0.03634, over 4916.00 frames.], tot_loss[loss=0.151, simple_loss=0.2218, pruned_loss=0.0401, over 973151.22 frames.], batch size: 23, lr: 3.80e-04
+2022-05-05 07:10:12,903 INFO [train.py:715] (3/8) Epoch 5, batch 20950, loss[loss=0.1442, simple_loss=0.2035, pruned_loss=0.0424, over 4845.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2218, pruned_loss=0.04025, over 972984.38 frames.], batch size: 30, lr: 3.80e-04
+2022-05-05 07:10:51,486 INFO [train.py:715] (3/8) Epoch 5, batch 21000, loss[loss=0.145, simple_loss=0.2084, pruned_loss=0.04082, over 4880.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2217, pruned_loss=0.04039, over 973019.47 frames.], batch size: 32, lr: 3.80e-04
+2022-05-05 07:10:51,487 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 07:11:01,469 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.1101, simple_loss=0.1954, pruned_loss=0.01242, over 914524.00 frames.
+2022-05-05 07:11:40,513 INFO [train.py:715] (3/8) Epoch 5, batch 21050, loss[loss=0.1375, simple_loss=0.2016, pruned_loss=0.03671, over 4809.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2222, pruned_loss=0.04023, over 972463.14 frames.], batch size: 13, lr: 3.80e-04
+2022-05-05 07:12:19,699 INFO [train.py:715] (3/8) Epoch 5, batch 21100, loss[loss=0.1768, simple_loss=0.2337, pruned_loss=0.05991, over 4877.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2223, pruned_loss=0.04044, over 972112.74 frames.], batch size: 32, lr: 3.79e-04
+2022-05-05 07:12:58,342 INFO [train.py:715] (3/8) Epoch 5, batch 21150, loss[loss=0.1235, simple_loss=0.2005, pruned_loss=0.0233, over 4843.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04013, over 972000.29 frames.], batch size: 30, lr: 3.79e-04
+2022-05-05 07:13:37,167 INFO [train.py:715] (3/8) Epoch 5, batch 21200, loss[loss=0.1866, simple_loss=0.2508, pruned_loss=0.06122, over 4980.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2217, pruned_loss=0.04032, over 973168.46 frames.], batch size: 35, lr: 3.79e-04
+2022-05-05 07:14:15,842 INFO [train.py:715] (3/8) Epoch 5, batch 21250, loss[loss=0.1397, simple_loss=0.2146, pruned_loss=0.03241, over 4801.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2224, pruned_loss=0.04069, over 972630.59 frames.], batch size: 21, lr: 3.79e-04
+2022-05-05 07:14:54,663 INFO [train.py:715] (3/8) Epoch 5, batch 21300, loss[loss=0.1303, simple_loss=0.2061, pruned_loss=0.02721, over 4770.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2229, pruned_loss=0.04122, over 971948.94 frames.], batch size: 17, lr: 3.79e-04
+2022-05-05 07:15:33,335 INFO [train.py:715] (3/8) Epoch 5, batch 21350, loss[loss=0.1388, simple_loss=0.1999, pruned_loss=0.03884, over 4846.00 frames.], tot_loss[loss=0.152, simple_loss=0.2221, pruned_loss=0.04088, over 971984.68 frames.], batch size: 32, lr: 3.79e-04
+2022-05-05 07:16:11,913 INFO [train.py:715] (3/8) Epoch 5, batch 21400, loss[loss=0.1512, simple_loss=0.2232, pruned_loss=0.03963, over 4914.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04103, over 972306.18 frames.], batch size: 18, lr: 3.79e-04
+2022-05-05 07:16:50,974 INFO [train.py:715] (3/8) Epoch 5, batch 21450, loss[loss=0.1366, simple_loss=0.2079, pruned_loss=0.03266, over 4826.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2236, pruned_loss=0.04095, over 972657.08 frames.], batch size: 30, lr: 3.79e-04
+2022-05-05 07:17:29,100 INFO [train.py:715] (3/8) Epoch 5, batch 21500, loss[loss=0.171, simple_loss=0.2316, pruned_loss=0.0552, over 4964.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2227, pruned_loss=0.04053, over 971723.64 frames.], batch size: 24, lr: 3.79e-04
+2022-05-05 07:18:08,223 INFO [train.py:715] (3/8) Epoch 5, batch 21550, loss[loss=0.1252, simple_loss=0.1856, pruned_loss=0.03234, over 4819.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2228, pruned_loss=0.04054, over 972119.63 frames.], batch size: 13, lr: 3.79e-04
+2022-05-05 07:18:46,744 INFO [train.py:715] (3/8) Epoch 5, batch 21600, loss[loss=0.1495, simple_loss=0.2174, pruned_loss=0.04082, over 4971.00 frames.], tot_loss[loss=0.152, simple_loss=0.2228, pruned_loss=0.04058, over 972633.79 frames.], batch size: 33, lr: 3.79e-04
+2022-05-05 07:19:25,823 INFO [train.py:715] (3/8) Epoch 5, batch 21650, loss[loss=0.1528, simple_loss=0.2241, pruned_loss=0.04074, over 4775.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2234, pruned_loss=0.04091, over 972476.25 frames.], batch size: 18, lr: 3.79e-04
+2022-05-05 07:20:04,069 INFO [train.py:715] (3/8) Epoch 5, batch 21700, loss[loss=0.1437, simple_loss=0.2135, pruned_loss=0.03694, over 4874.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2237, pruned_loss=0.04109, over 972973.90 frames.], batch size: 22, lr: 3.79e-04
+2022-05-05 07:20:42,467 INFO [train.py:715] (3/8) Epoch 5, batch 21750, loss[loss=0.1634, simple_loss=0.2262, pruned_loss=0.05026, over 4978.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.0408, over 973258.75 frames.], batch size: 40, lr: 3.79e-04
+2022-05-05 07:21:20,818 INFO [train.py:715] (3/8) Epoch 5, batch 21800, loss[loss=0.1456, simple_loss=0.2232, pruned_loss=0.034, over 4787.00 frames.], tot_loss[loss=0.152, simple_loss=0.2221, pruned_loss=0.04092, over 973416.82 frames.], batch size: 17, lr: 3.79e-04
+2022-05-05 07:22:00,030 INFO [train.py:715] (3/8) Epoch 5, batch 21850, loss[loss=0.1491, simple_loss=0.223, pruned_loss=0.03757, over 4929.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2228, pruned_loss=0.04123, over 972552.40 frames.], batch size: 21, lr: 3.79e-04
+2022-05-05 07:22:38,258 INFO [train.py:715] (3/8) Epoch 5, batch 21900, loss[loss=0.1615, simple_loss=0.2368, pruned_loss=0.04307, over 4799.00 frames.], tot_loss[loss=0.153, simple_loss=0.2236, pruned_loss=0.04117, over 972943.16 frames.], batch size: 21, lr: 3.79e-04
+2022-05-05 07:23:16,810 INFO [train.py:715] (3/8) Epoch 5, batch 21950, loss[loss=0.1367, simple_loss=0.202, pruned_loss=0.03566, over 4818.00 frames.], tot_loss[loss=0.152, simple_loss=0.2227, pruned_loss=0.04059, over 972976.99 frames.], batch size: 13, lr: 3.79e-04
+2022-05-05 07:23:55,217 INFO [train.py:715] (3/8) Epoch 5, batch 22000, loss[loss=0.1426, simple_loss=0.2124, pruned_loss=0.03637, over 4965.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2225, pruned_loss=0.04023, over 973837.15 frames.], batch size: 24, lr: 3.79e-04
+2022-05-05 07:24:34,725 INFO [train.py:715] (3/8) Epoch 5, batch 22050, loss[loss=0.1381, simple_loss=0.2027, pruned_loss=0.0368, over 4789.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2227, pruned_loss=0.03997, over 973460.25 frames.], batch size: 13, lr: 3.79e-04
+2022-05-05 07:25:13,187 INFO [train.py:715] (3/8) Epoch 5, batch 22100, loss[loss=0.1661, simple_loss=0.2469, pruned_loss=0.04267, over 4904.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2227, pruned_loss=0.03983, over 972734.28 frames.], batch size: 17, lr: 3.79e-04
+2022-05-05 07:25:52,416 INFO [train.py:715] (3/8) Epoch 5, batch 22150, loss[loss=0.1603, simple_loss=0.2328, pruned_loss=0.04389, over 4926.00 frames.], tot_loss[loss=0.151, simple_loss=0.2222, pruned_loss=0.03992, over 972448.61 frames.], batch size: 19, lr: 3.78e-04
+2022-05-05 07:26:31,444 INFO [train.py:715] (3/8) Epoch 5, batch 22200, loss[loss=0.2112, simple_loss=0.2742, pruned_loss=0.0741, over 4860.00 frames.], tot_loss[loss=0.1513, simple_loss=0.222, pruned_loss=0.04025, over 972699.38 frames.], batch size: 16, lr: 3.78e-04
+2022-05-05 07:27:11,165 INFO [train.py:715] (3/8) Epoch 5, batch 22250, loss[loss=0.1464, simple_loss=0.2095, pruned_loss=0.0416, over 4985.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2226, pruned_loss=0.04046, over 972176.48 frames.], batch size: 31, lr: 3.78e-04
+2022-05-05 07:27:50,342 INFO [train.py:715] (3/8) Epoch 5, batch 22300, loss[loss=0.1542, simple_loss=0.2323, pruned_loss=0.038, over 4897.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2227, pruned_loss=0.04022, over 972144.93 frames.], batch size: 18, lr: 3.78e-04
+2022-05-05 07:28:28,460 INFO [train.py:715] (3/8) Epoch 5, batch 22350, loss[loss=0.1603, simple_loss=0.2376, pruned_loss=0.04155, over 4974.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2229, pruned_loss=0.04019, over 972044.78 frames.], batch size: 35, lr: 3.78e-04
+2022-05-05 07:29:06,834 INFO [train.py:715] (3/8) Epoch 5, batch 22400, loss[loss=0.1699, simple_loss=0.2406, pruned_loss=0.04954, over 4802.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2234, pruned_loss=0.04005, over 972035.67 frames.], batch size: 21, lr: 3.78e-04
+2022-05-05 07:29:45,743 INFO [train.py:715] (3/8) Epoch 5, batch 22450, loss[loss=0.151, simple_loss=0.2298, pruned_loss=0.03616, over 4886.00 frames.], tot_loss[loss=0.152, simple_loss=0.2231, pruned_loss=0.0405, over 971665.80 frames.], batch size: 20, lr: 3.78e-04
+2022-05-05 07:30:25,210 INFO [train.py:715] (3/8) Epoch 5, batch 22500, loss[loss=0.1691, simple_loss=0.2314, pruned_loss=0.05335, over 4748.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2221, pruned_loss=0.04027, over 972829.11 frames.], batch size: 19, lr: 3.78e-04
+2022-05-05 07:31:03,488 INFO [train.py:715] (3/8) Epoch 5, batch 22550, loss[loss=0.1486, simple_loss=0.227, pruned_loss=0.03507, over 4937.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04038, over 972602.87 frames.], batch size: 39, lr: 3.78e-04
+2022-05-05 07:31:42,558 INFO [train.py:715] (3/8) Epoch 5, batch 22600, loss[loss=0.1506, simple_loss=0.2228, pruned_loss=0.03922, over 4827.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2209, pruned_loss=0.03989, over 971879.50 frames.], batch size: 26, lr: 3.78e-04
+2022-05-05 07:32:21,687 INFO [train.py:715] (3/8) Epoch 5, batch 22650, loss[loss=0.1445, simple_loss=0.2272, pruned_loss=0.03089, over 4829.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03973, over 971502.45 frames.], batch size: 25, lr: 3.78e-04
+2022-05-05 07:33:00,844 INFO [train.py:715] (3/8) Epoch 5, batch 22700, loss[loss=0.128, simple_loss=0.2021, pruned_loss=0.02692, over 4818.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2216, pruned_loss=0.03968, over 971947.95 frames.], batch size: 14, lr: 3.78e-04
+2022-05-05 07:33:39,169 INFO [train.py:715] (3/8) Epoch 5, batch 22750, loss[loss=0.1628, simple_loss=0.2429, pruned_loss=0.04132, over 4772.00 frames.], tot_loss[loss=0.1509, simple_loss=0.222, pruned_loss=0.03987, over 973046.91 frames.], batch size: 18, lr: 3.78e-04
+2022-05-05 07:34:18,365 INFO [train.py:715] (3/8) Epoch 5, batch 22800, loss[loss=0.1228, simple_loss=0.1936, pruned_loss=0.02602, over 4873.00 frames.], tot_loss[loss=0.151, simple_loss=0.222, pruned_loss=0.03995, over 972506.85 frames.], batch size: 20, lr: 3.78e-04
+2022-05-05 07:34:57,943 INFO [train.py:715] (3/8) Epoch 5, batch 22850, loss[loss=0.1515, simple_loss=0.2157, pruned_loss=0.0436, over 4928.00 frames.], tot_loss[loss=0.1522, simple_loss=0.223, pruned_loss=0.04066, over 971751.86 frames.], batch size: 18, lr: 3.78e-04
+2022-05-05 07:35:36,333 INFO [train.py:715] (3/8) Epoch 5, batch 22900, loss[loss=0.1737, simple_loss=0.2547, pruned_loss=0.04638, over 4919.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2228, pruned_loss=0.0404, over 971402.09 frames.], batch size: 18, lr: 3.78e-04
+2022-05-05 07:36:15,067 INFO [train.py:715] (3/8) Epoch 5, batch 22950, loss[loss=0.1471, simple_loss=0.2179, pruned_loss=0.03812, over 4926.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2234, pruned_loss=0.04118, over 971045.94 frames.], batch size: 29, lr: 3.78e-04
+2022-05-05 07:36:54,409 INFO [train.py:715] (3/8) Epoch 5, batch 23000, loss[loss=0.1618, simple_loss=0.2396, pruned_loss=0.04206, over 4865.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2236, pruned_loss=0.04167, over 970753.37 frames.], batch size: 20, lr: 3.78e-04
+2022-05-05 07:37:33,574 INFO [train.py:715] (3/8) Epoch 5, batch 23050, loss[loss=0.1681, simple_loss=0.2485, pruned_loss=0.04386, over 4827.00 frames.], tot_loss[loss=0.153, simple_loss=0.2236, pruned_loss=0.0412, over 971642.08 frames.], batch size: 25, lr: 3.78e-04
+2022-05-05 07:38:12,017 INFO [train.py:715] (3/8) Epoch 5, batch 23100, loss[loss=0.1356, simple_loss=0.2115, pruned_loss=0.02984, over 4742.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2233, pruned_loss=0.04107, over 970444.69 frames.], batch size: 16, lr: 3.78e-04
+2022-05-05 07:38:51,178 INFO [train.py:715] (3/8) Epoch 5, batch 23150, loss[loss=0.1785, simple_loss=0.2443, pruned_loss=0.05631, over 4861.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.04079, over 970307.67 frames.], batch size: 22, lr: 3.78e-04
+2022-05-05 07:39:30,785 INFO [train.py:715] (3/8) Epoch 5, batch 23200, loss[loss=0.1296, simple_loss=0.2063, pruned_loss=0.02647, over 4810.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2224, pruned_loss=0.04053, over 970378.84 frames.], batch size: 21, lr: 3.77e-04
+2022-05-05 07:40:09,160 INFO [train.py:715] (3/8) Epoch 5, batch 23250, loss[loss=0.1363, simple_loss=0.2114, pruned_loss=0.03056, over 4685.00 frames.], tot_loss[loss=0.1516, simple_loss=0.222, pruned_loss=0.04058, over 970927.96 frames.], batch size: 15, lr: 3.77e-04
+2022-05-05 07:40:47,782 INFO [train.py:715] (3/8) Epoch 5, batch 23300, loss[loss=0.1816, simple_loss=0.2435, pruned_loss=0.05985, over 4966.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2206, pruned_loss=0.03985, over 971928.04 frames.], batch size: 39, lr: 3.77e-04
+2022-05-05 07:41:27,166 INFO [train.py:715] (3/8) Epoch 5, batch 23350, loss[loss=0.1497, simple_loss=0.2188, pruned_loss=0.04033, over 4761.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2198, pruned_loss=0.03937, over 972145.27 frames.], batch size: 16, lr: 3.77e-04
+2022-05-05 07:42:05,802 INFO [train.py:715] (3/8) Epoch 5, batch 23400, loss[loss=0.1549, simple_loss=0.2434, pruned_loss=0.03316, over 4944.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.03945, over 973121.48 frames.], batch size: 24, lr: 3.77e-04
+2022-05-05 07:42:44,253 INFO [train.py:715] (3/8) Epoch 5, batch 23450, loss[loss=0.1327, simple_loss=0.2021, pruned_loss=0.03164, over 4808.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2214, pruned_loss=0.03986, over 972813.15 frames.], batch size: 21, lr: 3.77e-04
+2022-05-05 07:43:22,953 INFO [train.py:715] (3/8) Epoch 5, batch 23500, loss[loss=0.1347, simple_loss=0.2064, pruned_loss=0.03149, over 4769.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2216, pruned_loss=0.04057, over 971441.27 frames.], batch size: 18, lr: 3.77e-04
+2022-05-05 07:44:02,011 INFO [train.py:715] (3/8) Epoch 5, batch 23550, loss[loss=0.1411, simple_loss=0.2187, pruned_loss=0.03175, over 4837.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2208, pruned_loss=0.03984, over 971768.68 frames.], batch size: 12, lr: 3.77e-04
+2022-05-05 07:44:40,888 INFO [train.py:715] (3/8) Epoch 5, batch 23600, loss[loss=0.1386, simple_loss=0.21, pruned_loss=0.03359, over 4986.00 frames.], tot_loss[loss=0.1517, simple_loss=0.222, pruned_loss=0.04071, over 972435.33 frames.], batch size: 28, lr: 3.77e-04
+2022-05-05 07:45:19,395 INFO [train.py:715] (3/8) Epoch 5, batch 23650, loss[loss=0.1752, simple_loss=0.2328, pruned_loss=0.05879, over 4881.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2224, pruned_loss=0.04093, over 972753.54 frames.], batch size: 16, lr: 3.77e-04
+2022-05-05 07:45:58,898 INFO [train.py:715] (3/8) Epoch 5, batch 23700, loss[loss=0.1393, simple_loss=0.2131, pruned_loss=0.03275, over 4753.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2229, pruned_loss=0.0412, over 973566.67 frames.], batch size: 19, lr: 3.77e-04
+2022-05-05 07:46:37,474 INFO [train.py:715] (3/8) Epoch 5, batch 23750, loss[loss=0.1724, simple_loss=0.2409, pruned_loss=0.0519, over 4883.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.04092, over 972459.54 frames.], batch size: 20, lr: 3.77e-04
+2022-05-05 07:47:16,505 INFO [train.py:715] (3/8) Epoch 5, batch 23800, loss[loss=0.1379, simple_loss=0.2105, pruned_loss=0.0327, over 4848.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2232, pruned_loss=0.04079, over 972194.71 frames.], batch size: 20, lr: 3.77e-04
+2022-05-05 07:47:55,209 INFO [train.py:715] (3/8) Epoch 5, batch 23850, loss[loss=0.1632, simple_loss=0.2352, pruned_loss=0.04565, over 4873.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2236, pruned_loss=0.04133, over 972431.20 frames.], batch size: 16, lr: 3.77e-04
+2022-05-05 07:48:34,416 INFO [train.py:715] (3/8) Epoch 5, batch 23900, loss[loss=0.194, simple_loss=0.2629, pruned_loss=0.06257, over 4843.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2241, pruned_loss=0.04145, over 972114.43 frames.], batch size: 15, lr: 3.77e-04
+2022-05-05 07:49:13,372 INFO [train.py:715] (3/8) Epoch 5, batch 23950, loss[loss=0.1639, simple_loss=0.229, pruned_loss=0.04936, over 4811.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04138, over 972079.88 frames.], batch size: 27, lr: 3.77e-04
+2022-05-05 07:49:51,763 INFO [train.py:715] (3/8) Epoch 5, batch 24000, loss[loss=0.1522, simple_loss=0.2381, pruned_loss=0.03313, over 4872.00 frames.], tot_loss[loss=0.1525, simple_loss=0.223, pruned_loss=0.04099, over 971328.36 frames.], batch size: 20, lr: 3.77e-04
+2022-05-05 07:49:51,763 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 07:50:02,183 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.11, simple_loss=0.1955, pruned_loss=0.0123, over 914524.00 frames.
+2022-05-05 07:50:40,725 INFO [train.py:715] (3/8) Epoch 5, batch 24050, loss[loss=0.1609, simple_loss=0.2251, pruned_loss=0.04832, over 4914.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.041, over 971608.89 frames.], batch size: 17, lr: 3.77e-04
+2022-05-05 07:51:20,435 INFO [train.py:715] (3/8) Epoch 5, batch 24100, loss[loss=0.1431, simple_loss=0.2212, pruned_loss=0.03247, over 4944.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04099, over 971909.39 frames.], batch size: 21, lr: 3.77e-04
+2022-05-05 07:51:59,183 INFO [train.py:715] (3/8) Epoch 5, batch 24150, loss[loss=0.156, simple_loss=0.2243, pruned_loss=0.04384, over 4840.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2232, pruned_loss=0.0406, over 972030.55 frames.], batch size: 15, lr: 3.77e-04
+2022-05-05 07:52:37,496 INFO [train.py:715] (3/8) Epoch 5, batch 24200, loss[loss=0.1391, simple_loss=0.2087, pruned_loss=0.03471, over 4969.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2223, pruned_loss=0.04023, over 971322.61 frames.], batch size: 31, lr: 3.77e-04
+2022-05-05 07:53:16,811 INFO [train.py:715] (3/8) Epoch 5, batch 24250, loss[loss=0.2172, simple_loss=0.2896, pruned_loss=0.07238, over 4862.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2229, pruned_loss=0.04074, over 971193.64 frames.], batch size: 20, lr: 3.76e-04
+2022-05-05 07:53:55,923 INFO [train.py:715] (3/8) Epoch 5, batch 24300, loss[loss=0.1114, simple_loss=0.1914, pruned_loss=0.0157, over 4813.00 frames.], tot_loss[loss=0.1522, simple_loss=0.223, pruned_loss=0.04064, over 970825.99 frames.], batch size: 25, lr: 3.76e-04
+2022-05-05 07:54:34,806 INFO [train.py:715] (3/8) Epoch 5, batch 24350, loss[loss=0.1129, simple_loss=0.181, pruned_loss=0.02237, over 4891.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2235, pruned_loss=0.04079, over 972033.48 frames.], batch size: 22, lr: 3.76e-04
+2022-05-05 07:55:13,057 INFO [train.py:715] (3/8) Epoch 5, batch 24400, loss[loss=0.1256, simple_loss=0.2062, pruned_loss=0.02255, over 4975.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2237, pruned_loss=0.04086, over 973284.39 frames.], batch size: 28, lr: 3.76e-04
+2022-05-05 07:55:52,740 INFO [train.py:715] (3/8) Epoch 5, batch 24450, loss[loss=0.1583, simple_loss=0.2342, pruned_loss=0.04119, over 4990.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2226, pruned_loss=0.04038, over 972900.60 frames.], batch size: 28, lr: 3.76e-04
+2022-05-05 07:56:30,707 INFO [train.py:715] (3/8) Epoch 5, batch 24500, loss[loss=0.1585, simple_loss=0.2242, pruned_loss=0.04644, over 4795.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.04076, over 972536.33 frames.], batch size: 18, lr: 3.76e-04
+2022-05-05 07:57:09,366 INFO [train.py:715] (3/8) Epoch 5, batch 24550, loss[loss=0.1476, simple_loss=0.208, pruned_loss=0.04361, over 4750.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2237, pruned_loss=0.04145, over 972912.25 frames.], batch size: 16, lr: 3.76e-04
+2022-05-05 07:57:48,732 INFO [train.py:715] (3/8) Epoch 5, batch 24600, loss[loss=0.1534, simple_loss=0.2162, pruned_loss=0.04531, over 4927.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2236, pruned_loss=0.04145, over 973161.23 frames.], batch size: 35, lr: 3.76e-04
+2022-05-05 07:58:27,793 INFO [train.py:715] (3/8) Epoch 5, batch 24650, loss[loss=0.1835, simple_loss=0.2601, pruned_loss=0.0534, over 4848.00 frames.], tot_loss[loss=0.1525, simple_loss=0.223, pruned_loss=0.04103, over 972399.42 frames.], batch size: 30, lr: 3.76e-04
+2022-05-05 07:59:06,982 INFO [train.py:715] (3/8) Epoch 5, batch 24700, loss[loss=0.1357, simple_loss=0.2082, pruned_loss=0.03166, over 4896.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.04074, over 972940.58 frames.], batch size: 19, lr: 3.76e-04
+2022-05-05 07:59:45,116 INFO [train.py:715] (3/8) Epoch 5, batch 24750, loss[loss=0.18, simple_loss=0.2495, pruned_loss=0.05519, over 4699.00 frames.], tot_loss[loss=0.152, simple_loss=0.2229, pruned_loss=0.04051, over 972357.26 frames.], batch size: 15, lr: 3.76e-04
+2022-05-05 08:00:24,684 INFO [train.py:715] (3/8) Epoch 5, batch 24800, loss[loss=0.1125, simple_loss=0.1752, pruned_loss=0.02487, over 4863.00 frames.], tot_loss[loss=0.1522, simple_loss=0.223, pruned_loss=0.0407, over 971643.71 frames.], batch size: 13, lr: 3.76e-04
+2022-05-05 08:01:03,114 INFO [train.py:715] (3/8) Epoch 5, batch 24850, loss[loss=0.1319, simple_loss=0.2023, pruned_loss=0.03069, over 4973.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2224, pruned_loss=0.04018, over 972158.79 frames.], batch size: 24, lr: 3.76e-04
+2022-05-05 08:01:41,876 INFO [train.py:715] (3/8) Epoch 5, batch 24900, loss[loss=0.1658, simple_loss=0.2296, pruned_loss=0.05104, over 4917.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2222, pruned_loss=0.04033, over 972600.03 frames.], batch size: 17, lr: 3.76e-04
+2022-05-05 08:02:21,427 INFO [train.py:715] (3/8) Epoch 5, batch 24950, loss[loss=0.1422, simple_loss=0.2248, pruned_loss=0.02979, over 4981.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2215, pruned_loss=0.03958, over 973321.43 frames.], batch size: 24, lr: 3.76e-04
+2022-05-05 08:03:00,476 INFO [train.py:715] (3/8) Epoch 5, batch 25000, loss[loss=0.1208, simple_loss=0.1873, pruned_loss=0.02711, over 4855.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2214, pruned_loss=0.03962, over 974146.82 frames.], batch size: 30, lr: 3.76e-04
+2022-05-05 08:03:39,039 INFO [train.py:715] (3/8) Epoch 5, batch 25050, loss[loss=0.1416, simple_loss=0.2204, pruned_loss=0.03137, over 4896.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2219, pruned_loss=0.03978, over 973728.45 frames.], batch size: 22, lr: 3.76e-04
+2022-05-05 08:04:17,284 INFO [train.py:715] (3/8) Epoch 5, batch 25100, loss[loss=0.1438, simple_loss=0.218, pruned_loss=0.03477, over 4954.00 frames.], tot_loss[loss=0.1519, simple_loss=0.223, pruned_loss=0.04038, over 973045.76 frames.], batch size: 14, lr: 3.76e-04
+2022-05-05 08:04:57,543 INFO [train.py:715] (3/8) Epoch 5, batch 25150, loss[loss=0.1783, simple_loss=0.2463, pruned_loss=0.05516, over 4983.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2223, pruned_loss=0.04021, over 973263.45 frames.], batch size: 15, lr: 3.76e-04
+2022-05-05 08:05:35,728 INFO [train.py:715] (3/8) Epoch 5, batch 25200, loss[loss=0.1646, simple_loss=0.224, pruned_loss=0.05256, over 4752.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2223, pruned_loss=0.04037, over 973195.56 frames.], batch size: 14, lr: 3.76e-04
+2022-05-05 08:06:14,578 INFO [train.py:715] (3/8) Epoch 5, batch 25250, loss[loss=0.1355, simple_loss=0.2125, pruned_loss=0.0293, over 4960.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2227, pruned_loss=0.04071, over 973012.25 frames.], batch size: 24, lr: 3.76e-04
+2022-05-05 08:06:53,403 INFO [train.py:715] (3/8) Epoch 5, batch 25300, loss[loss=0.1867, simple_loss=0.2476, pruned_loss=0.0629, over 4692.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2239, pruned_loss=0.04126, over 972819.60 frames.], batch size: 15, lr: 3.75e-04
+2022-05-05 08:07:31,747 INFO [train.py:715] (3/8) Epoch 5, batch 25350, loss[loss=0.1727, simple_loss=0.2356, pruned_loss=0.05489, over 4837.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2237, pruned_loss=0.04143, over 972799.31 frames.], batch size: 15, lr: 3.75e-04
+2022-05-05 08:08:10,249 INFO [train.py:715] (3/8) Epoch 5, batch 25400, loss[loss=0.1452, simple_loss=0.2252, pruned_loss=0.03256, over 4973.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2237, pruned_loss=0.04154, over 973124.03 frames.], batch size: 15, lr: 3.75e-04
+2022-05-05 08:08:49,164 INFO [train.py:715] (3/8) Epoch 5, batch 25450, loss[loss=0.1604, simple_loss=0.2308, pruned_loss=0.04498, over 4923.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2243, pruned_loss=0.04147, over 972716.85 frames.], batch size: 23, lr: 3.75e-04
+2022-05-05 08:09:28,362 INFO [train.py:715] (3/8) Epoch 5, batch 25500, loss[loss=0.1639, simple_loss=0.2466, pruned_loss=0.04059, over 4769.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2246, pruned_loss=0.04163, over 973131.52 frames.], batch size: 17, lr: 3.75e-04
+2022-05-05 08:10:07,143 INFO [train.py:715] (3/8) Epoch 5, batch 25550, loss[loss=0.1563, simple_loss=0.2296, pruned_loss=0.04153, over 4884.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2234, pruned_loss=0.04113, over 972390.22 frames.], batch size: 22, lr: 3.75e-04
+2022-05-05 08:10:45,634 INFO [train.py:715] (3/8) Epoch 5, batch 25600, loss[loss=0.1468, simple_loss=0.2211, pruned_loss=0.03627, over 4838.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2235, pruned_loss=0.0411, over 972622.09 frames.], batch size: 13, lr: 3.75e-04
+2022-05-05 08:11:24,704 INFO [train.py:715] (3/8) Epoch 5, batch 25650, loss[loss=0.1529, simple_loss=0.2281, pruned_loss=0.03884, over 4837.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.04075, over 972168.41 frames.], batch size: 15, lr: 3.75e-04
+2022-05-05 08:12:03,094 INFO [train.py:715] (3/8) Epoch 5, batch 25700, loss[loss=0.185, simple_loss=0.2604, pruned_loss=0.05481, over 4794.00 frames.], tot_loss[loss=0.152, simple_loss=0.2228, pruned_loss=0.04066, over 971955.53 frames.], batch size: 21, lr: 3.75e-04
+2022-05-05 08:12:41,265 INFO [train.py:715] (3/8) Epoch 5, batch 25750, loss[loss=0.1605, simple_loss=0.2258, pruned_loss=0.04764, over 4973.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2231, pruned_loss=0.04065, over 972296.74 frames.], batch size: 35, lr: 3.75e-04
+2022-05-05 08:13:20,738 INFO [train.py:715] (3/8) Epoch 5, batch 25800, loss[loss=0.1498, simple_loss=0.2233, pruned_loss=0.03813, over 4869.00 frames.], tot_loss[loss=0.152, simple_loss=0.2228, pruned_loss=0.04053, over 972946.24 frames.], batch size: 20, lr: 3.75e-04
+2022-05-05 08:13:59,833 INFO [train.py:715] (3/8) Epoch 5, batch 25850, loss[loss=0.159, simple_loss=0.2336, pruned_loss=0.04216, over 4802.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2224, pruned_loss=0.04026, over 973238.86 frames.], batch size: 21, lr: 3.75e-04
+2022-05-05 08:14:38,590 INFO [train.py:715] (3/8) Epoch 5, batch 25900, loss[loss=0.1319, simple_loss=0.203, pruned_loss=0.03036, over 4856.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2226, pruned_loss=0.04048, over 973414.66 frames.], batch size: 20, lr: 3.75e-04
+2022-05-05 08:15:17,124 INFO [train.py:715] (3/8) Epoch 5, batch 25950, loss[loss=0.1254, simple_loss=0.1919, pruned_loss=0.02949, over 4991.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2218, pruned_loss=0.04004, over 973805.50 frames.], batch size: 14, lr: 3.75e-04
+2022-05-05 08:15:58,602 INFO [train.py:715] (3/8) Epoch 5, batch 26000, loss[loss=0.1258, simple_loss=0.2015, pruned_loss=0.02501, over 4798.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2208, pruned_loss=0.03945, over 972801.91 frames.], batch size: 24, lr: 3.75e-04
+2022-05-05 08:16:37,294 INFO [train.py:715] (3/8) Epoch 5, batch 26050, loss[loss=0.1537, simple_loss=0.2194, pruned_loss=0.04404, over 4953.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2216, pruned_loss=0.03981, over 972514.98 frames.], batch size: 21, lr: 3.75e-04
+2022-05-05 08:17:15,759 INFO [train.py:715] (3/8) Epoch 5, batch 26100, loss[loss=0.152, simple_loss=0.2164, pruned_loss=0.04382, over 4947.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04013, over 972746.81 frames.], batch size: 21, lr: 3.75e-04
+2022-05-05 08:17:54,716 INFO [train.py:715] (3/8) Epoch 5, batch 26150, loss[loss=0.1833, simple_loss=0.2476, pruned_loss=0.05946, over 4927.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03963, over 972325.01 frames.], batch size: 39, lr: 3.75e-04
+2022-05-05 08:18:33,048 INFO [train.py:715] (3/8) Epoch 5, batch 26200, loss[loss=0.1513, simple_loss=0.2342, pruned_loss=0.03425, over 4875.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2205, pruned_loss=0.03928, over 972504.86 frames.], batch size: 20, lr: 3.75e-04
+2022-05-05 08:19:12,106 INFO [train.py:715] (3/8) Epoch 5, batch 26250, loss[loss=0.1313, simple_loss=0.199, pruned_loss=0.03177, over 4842.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2194, pruned_loss=0.0388, over 972044.98 frames.], batch size: 30, lr: 3.75e-04
+2022-05-05 08:19:51,346 INFO [train.py:715] (3/8) Epoch 5, batch 26300, loss[loss=0.1534, simple_loss=0.219, pruned_loss=0.0439, over 4940.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2201, pruned_loss=0.03935, over 972524.01 frames.], batch size: 21, lr: 3.75e-04
+2022-05-05 08:20:30,626 INFO [train.py:715] (3/8) Epoch 5, batch 26350, loss[loss=0.1547, simple_loss=0.2258, pruned_loss=0.04181, over 4786.00 frames.], tot_loss[loss=0.1504, simple_loss=0.221, pruned_loss=0.03988, over 972019.62 frames.], batch size: 21, lr: 3.74e-04
+2022-05-05 08:21:09,422 INFO [train.py:715] (3/8) Epoch 5, batch 26400, loss[loss=0.1304, simple_loss=0.2112, pruned_loss=0.02483, over 4894.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2218, pruned_loss=0.03978, over 972257.78 frames.], batch size: 22, lr: 3.74e-04
+2022-05-05 08:21:48,033 INFO [train.py:715] (3/8) Epoch 5, batch 26450, loss[loss=0.1249, simple_loss=0.2051, pruned_loss=0.02236, over 4871.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.0399, over 971929.81 frames.], batch size: 22, lr: 3.74e-04
+2022-05-05 08:22:26,956 INFO [train.py:715] (3/8) Epoch 5, batch 26500, loss[loss=0.1399, simple_loss=0.2162, pruned_loss=0.03178, over 4895.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2222, pruned_loss=0.04036, over 972392.76 frames.], batch size: 19, lr: 3.74e-04
+2022-05-05 08:23:06,040 INFO [train.py:715] (3/8) Epoch 5, batch 26550, loss[loss=0.1491, simple_loss=0.2229, pruned_loss=0.03762, over 4796.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03972, over 971745.73 frames.], batch size: 14, lr: 3.74e-04
+2022-05-05 08:23:44,737 INFO [train.py:715] (3/8) Epoch 5, batch 26600, loss[loss=0.156, simple_loss=0.2363, pruned_loss=0.03782, over 4860.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.03919, over 971781.75 frames.], batch size: 20, lr: 3.74e-04
+2022-05-05 08:24:24,183 INFO [train.py:715] (3/8) Epoch 5, batch 26650, loss[loss=0.1727, simple_loss=0.2308, pruned_loss=0.05731, over 4780.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.03935, over 971910.92 frames.], batch size: 18, lr: 3.74e-04
+2022-05-05 08:25:02,984 INFO [train.py:715] (3/8) Epoch 5, batch 26700, loss[loss=0.1242, simple_loss=0.1968, pruned_loss=0.02584, over 4982.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2211, pruned_loss=0.03991, over 972839.47 frames.], batch size: 24, lr: 3.74e-04
+2022-05-05 08:25:41,811 INFO [train.py:715] (3/8) Epoch 5, batch 26750, loss[loss=0.1796, simple_loss=0.2419, pruned_loss=0.05866, over 4938.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2212, pruned_loss=0.04029, over 972344.89 frames.], batch size: 21, lr: 3.74e-04
+2022-05-05 08:26:20,201 INFO [train.py:715] (3/8) Epoch 5, batch 26800, loss[loss=0.1259, simple_loss=0.1972, pruned_loss=0.02732, over 4775.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2219, pruned_loss=0.04085, over 971984.31 frames.], batch size: 18, lr: 3.74e-04
+2022-05-05 08:26:59,360 INFO [train.py:715] (3/8) Epoch 5, batch 26850, loss[loss=0.1674, simple_loss=0.2402, pruned_loss=0.04735, over 4928.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2214, pruned_loss=0.04053, over 971693.07 frames.], batch size: 18, lr: 3.74e-04
+2022-05-05 08:27:38,337 INFO [train.py:715] (3/8) Epoch 5, batch 26900, loss[loss=0.1633, simple_loss=0.2257, pruned_loss=0.05041, over 4870.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2212, pruned_loss=0.04057, over 971142.70 frames.], batch size: 16, lr: 3.74e-04
+2022-05-05 08:28:17,271 INFO [train.py:715] (3/8) Epoch 5, batch 26950, loss[loss=0.153, simple_loss=0.2225, pruned_loss=0.04174, over 4949.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2207, pruned_loss=0.04038, over 971809.93 frames.], batch size: 24, lr: 3.74e-04
+2022-05-05 08:28:55,974 INFO [train.py:715] (3/8) Epoch 5, batch 27000, loss[loss=0.1446, simple_loss=0.2256, pruned_loss=0.03177, over 4914.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2209, pruned_loss=0.04046, over 971949.93 frames.], batch size: 17, lr: 3.74e-04
+2022-05-05 08:28:55,975 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 08:29:05,775 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.1098, simple_loss=0.195, pruned_loss=0.01232, over 914524.00 frames.
+2022-05-05 08:29:45,278 INFO [train.py:715] (3/8) Epoch 5, batch 27050, loss[loss=0.1456, simple_loss=0.2179, pruned_loss=0.03665, over 4758.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2214, pruned_loss=0.04079, over 972523.92 frames.], batch size: 19, lr: 3.74e-04
+2022-05-05 08:30:24,755 INFO [train.py:715] (3/8) Epoch 5, batch 27100, loss[loss=0.1471, simple_loss=0.2176, pruned_loss=0.03826, over 4803.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2219, pruned_loss=0.04078, over 972274.03 frames.], batch size: 26, lr: 3.74e-04
+2022-05-05 08:31:04,149 INFO [train.py:715] (3/8) Epoch 5, batch 27150, loss[loss=0.1484, simple_loss=0.2129, pruned_loss=0.04197, over 4823.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2224, pruned_loss=0.04108, over 972154.63 frames.], batch size: 15, lr: 3.74e-04
+2022-05-05 08:31:42,962 INFO [train.py:715] (3/8) Epoch 5, batch 27200, loss[loss=0.2029, simple_loss=0.2752, pruned_loss=0.06532, over 4774.00 frames.], tot_loss[loss=0.153, simple_loss=0.2231, pruned_loss=0.04147, over 971972.68 frames.], batch size: 17, lr: 3.74e-04
+2022-05-05 08:32:22,585 INFO [train.py:715] (3/8) Epoch 5, batch 27250, loss[loss=0.1292, simple_loss=0.197, pruned_loss=0.03071, over 4898.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2235, pruned_loss=0.0416, over 971128.24 frames.], batch size: 17, lr: 3.74e-04
+2022-05-05 08:33:01,563 INFO [train.py:715] (3/8) Epoch 5, batch 27300, loss[loss=0.1277, simple_loss=0.2027, pruned_loss=0.02637, over 4781.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2239, pruned_loss=0.04165, over 971435.04 frames.], batch size: 17, lr: 3.74e-04
+2022-05-05 08:33:40,120 INFO [train.py:715] (3/8) Epoch 5, batch 27350, loss[loss=0.1358, simple_loss=0.218, pruned_loss=0.02681, over 4926.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2237, pruned_loss=0.04166, over 971853.55 frames.], batch size: 29, lr: 3.74e-04
+2022-05-05 08:34:18,986 INFO [train.py:715] (3/8) Epoch 5, batch 27400, loss[loss=0.1541, simple_loss=0.216, pruned_loss=0.04608, over 4699.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.04095, over 971861.27 frames.], batch size: 15, lr: 3.74e-04
+2022-05-05 08:34:58,264 INFO [train.py:715] (3/8) Epoch 5, batch 27450, loss[loss=0.1531, simple_loss=0.2207, pruned_loss=0.04278, over 4966.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2223, pruned_loss=0.04073, over 972552.88 frames.], batch size: 24, lr: 3.73e-04
+2022-05-05 08:35:38,045 INFO [train.py:715] (3/8) Epoch 5, batch 27500, loss[loss=0.1683, simple_loss=0.2404, pruned_loss=0.04808, over 4808.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2219, pruned_loss=0.04054, over 972412.48 frames.], batch size: 21, lr: 3.73e-04
+2022-05-05 08:36:16,527 INFO [train.py:715] (3/8) Epoch 5, batch 27550, loss[loss=0.1417, simple_loss=0.2179, pruned_loss=0.03271, over 4988.00 frames.], tot_loss[loss=0.1506, simple_loss=0.221, pruned_loss=0.04004, over 971666.20 frames.], batch size: 28, lr: 3.73e-04
+2022-05-05 08:36:55,899 INFO [train.py:715] (3/8) Epoch 5, batch 27600, loss[loss=0.1285, simple_loss=0.1973, pruned_loss=0.02982, over 4857.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2213, pruned_loss=0.04026, over 972814.53 frames.], batch size: 30, lr: 3.73e-04
+2022-05-05 08:37:34,977 INFO [train.py:715] (3/8) Epoch 5, batch 27650, loss[loss=0.1667, simple_loss=0.2407, pruned_loss=0.04628, over 4761.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2215, pruned_loss=0.04065, over 972074.01 frames.], batch size: 19, lr: 3.73e-04
+2022-05-05 08:38:13,250 INFO [train.py:715] (3/8) Epoch 5, batch 27700, loss[loss=0.1548, simple_loss=0.2144, pruned_loss=0.0476, over 4961.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2225, pruned_loss=0.0412, over 972599.33 frames.], batch size: 35, lr: 3.73e-04
+2022-05-05 08:38:52,830 INFO [train.py:715] (3/8) Epoch 5, batch 27750, loss[loss=0.2065, simple_loss=0.2661, pruned_loss=0.07341, over 4778.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2211, pruned_loss=0.04034, over 972540.32 frames.], batch size: 18, lr: 3.73e-04
+2022-05-05 08:39:32,592 INFO [train.py:715] (3/8) Epoch 5, batch 27800, loss[loss=0.1821, simple_loss=0.2395, pruned_loss=0.06236, over 4804.00 frames.], tot_loss[loss=0.1515, simple_loss=0.222, pruned_loss=0.04051, over 973464.88 frames.], batch size: 13, lr: 3.73e-04
+2022-05-05 08:40:11,944 INFO [train.py:715] (3/8) Epoch 5, batch 27850, loss[loss=0.1474, simple_loss=0.2147, pruned_loss=0.04007, over 4875.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2219, pruned_loss=0.04035, over 973880.43 frames.], batch size: 22, lr: 3.73e-04
+2022-05-05 08:40:50,653 INFO [train.py:715] (3/8) Epoch 5, batch 27900, loss[loss=0.1579, simple_loss=0.2209, pruned_loss=0.04742, over 4836.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.04016, over 972753.19 frames.], batch size: 12, lr: 3.73e-04
+2022-05-05 08:41:29,600 INFO [train.py:715] (3/8) Epoch 5, batch 27950, loss[loss=0.1481, simple_loss=0.2146, pruned_loss=0.04074, over 4922.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2212, pruned_loss=0.03999, over 973738.90 frames.], batch size: 18, lr: 3.73e-04
+2022-05-05 08:42:09,043 INFO [train.py:715] (3/8) Epoch 5, batch 28000, loss[loss=0.1555, simple_loss=0.2211, pruned_loss=0.04495, over 4981.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2217, pruned_loss=0.04058, over 973144.38 frames.], batch size: 20, lr: 3.73e-04
+2022-05-05 08:42:47,129 INFO [train.py:715] (3/8) Epoch 5, batch 28050, loss[loss=0.151, simple_loss=0.2246, pruned_loss=0.03869, over 4937.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2228, pruned_loss=0.04133, over 973400.50 frames.], batch size: 21, lr: 3.73e-04
+2022-05-05 08:43:25,855 INFO [train.py:715] (3/8) Epoch 5, batch 28100, loss[loss=0.1446, simple_loss=0.2223, pruned_loss=0.03341, over 4988.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2234, pruned_loss=0.04166, over 973445.29 frames.], batch size: 28, lr: 3.73e-04
+2022-05-05 08:44:04,997 INFO [train.py:715] (3/8) Epoch 5, batch 28150, loss[loss=0.1492, simple_loss=0.229, pruned_loss=0.0347, over 4818.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2229, pruned_loss=0.04096, over 973397.06 frames.], batch size: 21, lr: 3.73e-04
+2022-05-05 08:44:43,938 INFO [train.py:715] (3/8) Epoch 5, batch 28200, loss[loss=0.1694, simple_loss=0.2392, pruned_loss=0.04977, over 4919.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.04079, over 973478.51 frames.], batch size: 17, lr: 3.73e-04
+2022-05-05 08:45:22,622 INFO [train.py:715] (3/8) Epoch 5, batch 28250, loss[loss=0.1316, simple_loss=0.2019, pruned_loss=0.03068, over 4893.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04044, over 972556.25 frames.], batch size: 19, lr: 3.73e-04
+2022-05-05 08:46:01,488 INFO [train.py:715] (3/8) Epoch 5, batch 28300, loss[loss=0.1428, simple_loss=0.2095, pruned_loss=0.03802, over 4887.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2224, pruned_loss=0.04055, over 972929.19 frames.], batch size: 16, lr: 3.73e-04
+2022-05-05 08:46:39,905 INFO [train.py:715] (3/8) Epoch 5, batch 28350, loss[loss=0.1629, simple_loss=0.2259, pruned_loss=0.04995, over 4839.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2229, pruned_loss=0.04064, over 972420.82 frames.], batch size: 30, lr: 3.73e-04
+2022-05-05 08:47:18,555 INFO [train.py:715] (3/8) Epoch 5, batch 28400, loss[loss=0.1606, simple_loss=0.2444, pruned_loss=0.03835, over 4810.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2225, pruned_loss=0.04044, over 972617.92 frames.], batch size: 25, lr: 3.73e-04
+2022-05-05 08:47:57,680 INFO [train.py:715] (3/8) Epoch 5, batch 28450, loss[loss=0.1736, simple_loss=0.2479, pruned_loss=0.04966, over 4776.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2225, pruned_loss=0.0404, over 972710.55 frames.], batch size: 18, lr: 3.73e-04
+2022-05-05 08:48:36,727 INFO [train.py:715] (3/8) Epoch 5, batch 28500, loss[loss=0.1414, simple_loss=0.211, pruned_loss=0.0359, over 4950.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2224, pruned_loss=0.03995, over 972881.87 frames.], batch size: 39, lr: 3.72e-04
+2022-05-05 08:49:15,938 INFO [train.py:715] (3/8) Epoch 5, batch 28550, loss[loss=0.1472, simple_loss=0.2334, pruned_loss=0.03053, over 4844.00 frames.], tot_loss[loss=0.151, simple_loss=0.2223, pruned_loss=0.03985, over 973003.18 frames.], batch size: 20, lr: 3.72e-04
+2022-05-05 08:49:54,628 INFO [train.py:715] (3/8) Epoch 5, batch 28600, loss[loss=0.1346, simple_loss=0.2146, pruned_loss=0.02737, over 4815.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2218, pruned_loss=0.03944, over 973187.32 frames.], batch size: 26, lr: 3.72e-04
+2022-05-05 08:50:34,060 INFO [train.py:715] (3/8) Epoch 5, batch 28650, loss[loss=0.1486, simple_loss=0.2209, pruned_loss=0.03818, over 4745.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2207, pruned_loss=0.03918, over 973953.70 frames.], batch size: 16, lr: 3.72e-04
+2022-05-05 08:51:12,501 INFO [train.py:715] (3/8) Epoch 5, batch 28700, loss[loss=0.1383, simple_loss=0.2125, pruned_loss=0.03207, over 4815.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2213, pruned_loss=0.03956, over 974181.18 frames.], batch size: 26, lr: 3.72e-04
+2022-05-05 08:51:51,352 INFO [train.py:715] (3/8) Epoch 5, batch 28750, loss[loss=0.1422, simple_loss=0.2165, pruned_loss=0.03389, over 4784.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2216, pruned_loss=0.04, over 972831.70 frames.], batch size: 17, lr: 3.72e-04
+2022-05-05 08:52:30,119 INFO [train.py:715] (3/8) Epoch 5, batch 28800, loss[loss=0.1812, simple_loss=0.2575, pruned_loss=0.05242, over 4980.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2231, pruned_loss=0.04035, over 973041.41 frames.], batch size: 15, lr: 3.72e-04
+2022-05-05 08:53:09,039 INFO [train.py:715] (3/8) Epoch 5, batch 28850, loss[loss=0.1276, simple_loss=0.2047, pruned_loss=0.02529, over 4935.00 frames.], tot_loss[loss=0.1512, simple_loss=0.222, pruned_loss=0.04014, over 972131.08 frames.], batch size: 23, lr: 3.72e-04
+2022-05-05 08:53:47,816 INFO [train.py:715] (3/8) Epoch 5, batch 28900, loss[loss=0.14, simple_loss=0.2123, pruned_loss=0.03389, over 4764.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04033, over 971479.84 frames.], batch size: 19, lr: 3.72e-04
+2022-05-05 08:54:26,497 INFO [train.py:715] (3/8) Epoch 5, batch 28950, loss[loss=0.1668, simple_loss=0.2359, pruned_loss=0.04883, over 4796.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2222, pruned_loss=0.04057, over 971342.28 frames.], batch size: 21, lr: 3.72e-04
+2022-05-05 08:55:05,610 INFO [train.py:715] (3/8) Epoch 5, batch 29000, loss[loss=0.1381, simple_loss=0.2019, pruned_loss=0.03714, over 4775.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2222, pruned_loss=0.04069, over 971077.37 frames.], batch size: 18, lr: 3.72e-04
+2022-05-05 08:55:43,854 INFO [train.py:715] (3/8) Epoch 5, batch 29050, loss[loss=0.1754, simple_loss=0.2418, pruned_loss=0.05448, over 4781.00 frames.], tot_loss[loss=0.152, simple_loss=0.2229, pruned_loss=0.04055, over 971645.94 frames.], batch size: 17, lr: 3.72e-04
+2022-05-05 08:56:22,924 INFO [train.py:715] (3/8) Epoch 5, batch 29100, loss[loss=0.1504, simple_loss=0.2172, pruned_loss=0.04187, over 4776.00 frames.], tot_loss[loss=0.152, simple_loss=0.2228, pruned_loss=0.04062, over 971632.48 frames.], batch size: 14, lr: 3.72e-04
+2022-05-05 08:57:01,739 INFO [train.py:715] (3/8) Epoch 5, batch 29150, loss[loss=0.1297, simple_loss=0.2006, pruned_loss=0.02943, over 4806.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2215, pruned_loss=0.03982, over 971588.38 frames.], batch size: 12, lr: 3.72e-04
+2022-05-05 08:57:40,488 INFO [train.py:715] (3/8) Epoch 5, batch 29200, loss[loss=0.1479, simple_loss=0.2173, pruned_loss=0.03925, over 4925.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2213, pruned_loss=0.04029, over 971970.47 frames.], batch size: 18, lr: 3.72e-04
+2022-05-05 08:58:19,233 INFO [train.py:715] (3/8) Epoch 5, batch 29250, loss[loss=0.1207, simple_loss=0.1944, pruned_loss=0.02353, over 4786.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2202, pruned_loss=0.03949, over 971967.72 frames.], batch size: 12, lr: 3.72e-04
+2022-05-05 08:58:57,799 INFO [train.py:715] (3/8) Epoch 5, batch 29300, loss[loss=0.1554, simple_loss=0.2249, pruned_loss=0.04298, over 4864.00 frames.], tot_loss[loss=0.15, simple_loss=0.2205, pruned_loss=0.03975, over 971870.10 frames.], batch size: 32, lr: 3.72e-04
+2022-05-05 08:59:37,059 INFO [train.py:715] (3/8) Epoch 5, batch 29350, loss[loss=0.2202, simple_loss=0.2845, pruned_loss=0.0779, over 4873.00 frames.], tot_loss[loss=0.151, simple_loss=0.2214, pruned_loss=0.04026, over 971821.41 frames.], batch size: 22, lr: 3.72e-04
+2022-05-05 09:00:15,739 INFO [train.py:715] (3/8) Epoch 5, batch 29400, loss[loss=0.1623, simple_loss=0.239, pruned_loss=0.0428, over 4931.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2218, pruned_loss=0.04044, over 971534.33 frames.], batch size: 23, lr: 3.72e-04
+2022-05-05 09:00:54,489 INFO [train.py:715] (3/8) Epoch 5, batch 29450, loss[loss=0.1568, simple_loss=0.2329, pruned_loss=0.04032, over 4884.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2227, pruned_loss=0.04088, over 971864.27 frames.], batch size: 22, lr: 3.72e-04
+2022-05-05 09:01:34,122 INFO [train.py:715] (3/8) Epoch 5, batch 29500, loss[loss=0.2049, simple_loss=0.26, pruned_loss=0.07485, over 4984.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2232, pruned_loss=0.04102, over 972530.49 frames.], batch size: 14, lr: 3.72e-04
+2022-05-05 09:02:13,204 INFO [train.py:715] (3/8) Epoch 5, batch 29550, loss[loss=0.1589, simple_loss=0.2321, pruned_loss=0.04288, over 4879.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2224, pruned_loss=0.0409, over 972432.33 frames.], batch size: 13, lr: 3.72e-04
+2022-05-05 09:02:52,389 INFO [train.py:715] (3/8) Epoch 5, batch 29600, loss[loss=0.1652, simple_loss=0.2428, pruned_loss=0.04379, over 4774.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2228, pruned_loss=0.04082, over 972365.73 frames.], batch size: 17, lr: 3.71e-04
+2022-05-05 09:03:31,059 INFO [train.py:715] (3/8) Epoch 5, batch 29650, loss[loss=0.1301, simple_loss=0.2028, pruned_loss=0.02864, over 4880.00 frames.], tot_loss[loss=0.1521, simple_loss=0.223, pruned_loss=0.04062, over 972318.00 frames.], batch size: 22, lr: 3.71e-04
+2022-05-05 09:04:09,889 INFO [train.py:715] (3/8) Epoch 5, batch 29700, loss[loss=0.1746, simple_loss=0.2292, pruned_loss=0.05998, over 4825.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2237, pruned_loss=0.04096, over 971998.07 frames.], batch size: 30, lr: 3.71e-04
+2022-05-05 09:04:48,812 INFO [train.py:715] (3/8) Epoch 5, batch 29750, loss[loss=0.1774, simple_loss=0.238, pruned_loss=0.05834, over 4968.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2244, pruned_loss=0.04153, over 972337.82 frames.], batch size: 24, lr: 3.71e-04
+2022-05-05 09:05:27,383 INFO [train.py:715] (3/8) Epoch 5, batch 29800, loss[loss=0.1802, simple_loss=0.2559, pruned_loss=0.05219, over 4779.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2245, pruned_loss=0.04157, over 971995.75 frames.], batch size: 17, lr: 3.71e-04
+2022-05-05 09:06:05,621 INFO [train.py:715] (3/8) Epoch 5, batch 29850, loss[loss=0.167, simple_loss=0.2363, pruned_loss=0.04885, over 4967.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2239, pruned_loss=0.04143, over 971450.07 frames.], batch size: 35, lr: 3.71e-04
+2022-05-05 09:06:44,670 INFO [train.py:715] (3/8) Epoch 5, batch 29900, loss[loss=0.1356, simple_loss=0.2103, pruned_loss=0.03045, over 4984.00 frames.], tot_loss[loss=0.1532, simple_loss=0.224, pruned_loss=0.04121, over 971693.49 frames.], batch size: 28, lr: 3.71e-04
+2022-05-05 09:07:24,016 INFO [train.py:715] (3/8) Epoch 5, batch 29950, loss[loss=0.156, simple_loss=0.2226, pruned_loss=0.04474, over 4763.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2228, pruned_loss=0.04046, over 972002.64 frames.], batch size: 18, lr: 3.71e-04
+2022-05-05 09:08:02,571 INFO [train.py:715] (3/8) Epoch 5, batch 30000, loss[loss=0.1443, simple_loss=0.216, pruned_loss=0.03636, over 4939.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2232, pruned_loss=0.04048, over 972006.80 frames.], batch size: 35, lr: 3.71e-04
+2022-05-05 09:08:02,571 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 09:08:12,296 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.11, simple_loss=0.1953, pruned_loss=0.01241, over 914524.00 frames.
+2022-05-05 09:08:51,329 INFO [train.py:715] (3/8) Epoch 5, batch 30050, loss[loss=0.1307, simple_loss=0.2078, pruned_loss=0.02677, over 4945.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2236, pruned_loss=0.04083, over 972364.60 frames.], batch size: 29, lr: 3.71e-04
+2022-05-05 09:09:31,492 INFO [train.py:715] (3/8) Epoch 5, batch 30100, loss[loss=0.1361, simple_loss=0.2203, pruned_loss=0.02592, over 4931.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2238, pruned_loss=0.04092, over 971820.99 frames.], batch size: 29, lr: 3.71e-04
+2022-05-05 09:10:10,291 INFO [train.py:715] (3/8) Epoch 5, batch 30150, loss[loss=0.1738, simple_loss=0.2322, pruned_loss=0.05774, over 4661.00 frames.], tot_loss[loss=0.152, simple_loss=0.223, pruned_loss=0.04055, over 971839.44 frames.], batch size: 13, lr: 3.71e-04
+2022-05-05 09:10:48,820 INFO [train.py:715] (3/8) Epoch 5, batch 30200, loss[loss=0.1384, simple_loss=0.2021, pruned_loss=0.0373, over 4848.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.04091, over 971491.58 frames.], batch size: 20, lr: 3.71e-04
+2022-05-05 09:11:27,805 INFO [train.py:715] (3/8) Epoch 5, batch 30250, loss[loss=0.1205, simple_loss=0.1931, pruned_loss=0.02399, over 4787.00 frames.], tot_loss[loss=0.1522, simple_loss=0.223, pruned_loss=0.04072, over 971555.80 frames.], batch size: 12, lr: 3.71e-04
+2022-05-05 09:12:06,781 INFO [train.py:715] (3/8) Epoch 5, batch 30300, loss[loss=0.2074, simple_loss=0.2634, pruned_loss=0.07568, over 4847.00 frames.], tot_loss[loss=0.1535, simple_loss=0.224, pruned_loss=0.04152, over 971715.86 frames.], batch size: 20, lr: 3.71e-04
+2022-05-05 09:12:45,784 INFO [train.py:715] (3/8) Epoch 5, batch 30350, loss[loss=0.1487, simple_loss=0.2224, pruned_loss=0.03747, over 4819.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2233, pruned_loss=0.04091, over 972337.41 frames.], batch size: 27, lr: 3.71e-04
+2022-05-05 09:13:24,287 INFO [train.py:715] (3/8) Epoch 5, batch 30400, loss[loss=0.1454, simple_loss=0.223, pruned_loss=0.0339, over 4844.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2232, pruned_loss=0.04086, over 972812.89 frames.], batch size: 13, lr: 3.71e-04
+2022-05-05 09:14:03,375 INFO [train.py:715] (3/8) Epoch 5, batch 30450, loss[loss=0.1587, simple_loss=0.2383, pruned_loss=0.03951, over 4935.00 frames.], tot_loss[loss=0.1528, simple_loss=0.224, pruned_loss=0.04085, over 973174.60 frames.], batch size: 39, lr: 3.71e-04
+2022-05-05 09:14:42,246 INFO [train.py:715] (3/8) Epoch 5, batch 30500, loss[loss=0.1609, simple_loss=0.2416, pruned_loss=0.04013, over 4942.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2238, pruned_loss=0.04091, over 973836.47 frames.], batch size: 21, lr: 3.71e-04
+2022-05-05 09:15:20,923 INFO [train.py:715] (3/8) Epoch 5, batch 30550, loss[loss=0.152, simple_loss=0.2246, pruned_loss=0.03972, over 4880.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2237, pruned_loss=0.0406, over 972680.30 frames.], batch size: 22, lr: 3.71e-04
+2022-05-05 09:15:58,928 INFO [train.py:715] (3/8) Epoch 5, batch 30600, loss[loss=0.1591, simple_loss=0.241, pruned_loss=0.03855, over 4925.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2241, pruned_loss=0.04053, over 973042.43 frames.], batch size: 29, lr: 3.71e-04
+2022-05-05 09:16:37,781 INFO [train.py:715] (3/8) Epoch 5, batch 30650, loss[loss=0.1349, simple_loss=0.2105, pruned_loss=0.02967, over 4758.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2239, pruned_loss=0.04081, over 973115.59 frames.], batch size: 19, lr: 3.71e-04
+2022-05-05 09:17:16,915 INFO [train.py:715] (3/8) Epoch 5, batch 30700, loss[loss=0.1676, simple_loss=0.2383, pruned_loss=0.04844, over 4966.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.04086, over 973033.57 frames.], batch size: 15, lr: 3.70e-04
+2022-05-05 09:17:55,174 INFO [train.py:715] (3/8) Epoch 5, batch 30750, loss[loss=0.1835, simple_loss=0.2591, pruned_loss=0.05393, over 4877.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.04091, over 973620.66 frames.], batch size: 16, lr: 3.70e-04
+2022-05-05 09:18:33,969 INFO [train.py:715] (3/8) Epoch 5, batch 30800, loss[loss=0.1787, simple_loss=0.2459, pruned_loss=0.05581, over 4898.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2229, pruned_loss=0.04083, over 972649.19 frames.], batch size: 19, lr: 3.70e-04
+2022-05-05 09:19:12,986 INFO [train.py:715] (3/8) Epoch 5, batch 30850, loss[loss=0.1167, simple_loss=0.1813, pruned_loss=0.02604, over 4825.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2228, pruned_loss=0.04065, over 972737.12 frames.], batch size: 13, lr: 3.70e-04
+2022-05-05 09:19:51,005 INFO [train.py:715] (3/8) Epoch 5, batch 30900, loss[loss=0.125, simple_loss=0.1957, pruned_loss=0.02714, over 4926.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04067, over 972714.48 frames.], batch size: 23, lr: 3.70e-04
+2022-05-05 09:20:29,874 INFO [train.py:715] (3/8) Epoch 5, batch 30950, loss[loss=0.1832, simple_loss=0.2578, pruned_loss=0.0543, over 4707.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2222, pruned_loss=0.04061, over 972533.53 frames.], batch size: 15, lr: 3.70e-04
+2022-05-05 09:21:09,515 INFO [train.py:715] (3/8) Epoch 5, batch 31000, loss[loss=0.1525, simple_loss=0.2258, pruned_loss=0.03959, over 4797.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2228, pruned_loss=0.04084, over 972656.49 frames.], batch size: 25, lr: 3.70e-04
+2022-05-05 09:21:48,975 INFO [train.py:715] (3/8) Epoch 5, batch 31050, loss[loss=0.1186, simple_loss=0.2005, pruned_loss=0.01834, over 4825.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2227, pruned_loss=0.04113, over 972316.92 frames.], batch size: 26, lr: 3.70e-04
+2022-05-05 09:22:27,593 INFO [train.py:715] (3/8) Epoch 5, batch 31100, loss[loss=0.17, simple_loss=0.2417, pruned_loss=0.04914, over 4801.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2223, pruned_loss=0.04047, over 971837.88 frames.], batch size: 21, lr: 3.70e-04
+2022-05-05 09:23:06,678 INFO [train.py:715] (3/8) Epoch 5, batch 31150, loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03266, over 4852.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2223, pruned_loss=0.04057, over 972318.45 frames.], batch size: 20, lr: 3.70e-04
+2022-05-05 09:23:45,593 INFO [train.py:715] (3/8) Epoch 5, batch 31200, loss[loss=0.1331, simple_loss=0.2088, pruned_loss=0.02872, over 4842.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2223, pruned_loss=0.04056, over 972814.82 frames.], batch size: 26, lr: 3.70e-04
+2022-05-05 09:24:24,057 INFO [train.py:715] (3/8) Epoch 5, batch 31250, loss[loss=0.1382, simple_loss=0.2187, pruned_loss=0.02888, over 4907.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2229, pruned_loss=0.04092, over 973126.41 frames.], batch size: 19, lr: 3.70e-04
+2022-05-05 09:25:02,648 INFO [train.py:715] (3/8) Epoch 5, batch 31300, loss[loss=0.1385, simple_loss=0.2005, pruned_loss=0.0382, over 4743.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2227, pruned_loss=0.04062, over 972375.87 frames.], batch size: 16, lr: 3.70e-04
+2022-05-05 09:25:41,535 INFO [train.py:715] (3/8) Epoch 5, batch 31350, loss[loss=0.13, simple_loss=0.2115, pruned_loss=0.02426, over 4895.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04013, over 973389.42 frames.], batch size: 17, lr: 3.70e-04
+2022-05-05 09:26:20,318 INFO [train.py:715] (3/8) Epoch 5, batch 31400, loss[loss=0.1494, simple_loss=0.2165, pruned_loss=0.04114, over 4886.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2216, pruned_loss=0.04024, over 973055.48 frames.], batch size: 16, lr: 3.70e-04
+2022-05-05 09:26:59,040 INFO [train.py:715] (3/8) Epoch 5, batch 31450, loss[loss=0.1244, simple_loss=0.2075, pruned_loss=0.02067, over 4789.00 frames.], tot_loss[loss=0.1504, simple_loss=0.221, pruned_loss=0.03993, over 973013.18 frames.], batch size: 24, lr: 3.70e-04
+2022-05-05 09:27:37,866 INFO [train.py:715] (3/8) Epoch 5, batch 31500, loss[loss=0.1411, simple_loss=0.1972, pruned_loss=0.04248, over 4974.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2212, pruned_loss=0.03997, over 973039.98 frames.], batch size: 15, lr: 3.70e-04
+2022-05-05 09:28:16,786 INFO [train.py:715] (3/8) Epoch 5, batch 31550, loss[loss=0.1587, simple_loss=0.2348, pruned_loss=0.0413, over 4948.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2201, pruned_loss=0.03938, over 972670.02 frames.], batch size: 39, lr: 3.70e-04
+2022-05-05 09:28:55,560 INFO [train.py:715] (3/8) Epoch 5, batch 31600, loss[loss=0.1572, simple_loss=0.2295, pruned_loss=0.04244, over 4970.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03978, over 972087.02 frames.], batch size: 14, lr: 3.70e-04
+2022-05-05 09:29:34,424 INFO [train.py:715] (3/8) Epoch 5, batch 31650, loss[loss=0.1645, simple_loss=0.2345, pruned_loss=0.04726, over 4776.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2212, pruned_loss=0.03963, over 972178.78 frames.], batch size: 18, lr: 3.70e-04
+2022-05-05 09:30:13,323 INFO [train.py:715] (3/8) Epoch 5, batch 31700, loss[loss=0.1155, simple_loss=0.1921, pruned_loss=0.01942, over 4836.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2212, pruned_loss=0.03953, over 971916.04 frames.], batch size: 15, lr: 3.70e-04
+2022-05-05 09:30:52,059 INFO [train.py:715] (3/8) Epoch 5, batch 31750, loss[loss=0.1382, simple_loss=0.2099, pruned_loss=0.03322, over 4829.00 frames.], tot_loss[loss=0.1494, simple_loss=0.221, pruned_loss=0.03884, over 971882.28 frames.], batch size: 12, lr: 3.70e-04
+2022-05-05 09:31:31,172 INFO [train.py:715] (3/8) Epoch 5, batch 31800, loss[loss=0.1395, simple_loss=0.2082, pruned_loss=0.03546, over 4967.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2217, pruned_loss=0.03941, over 972000.66 frames.], batch size: 39, lr: 3.69e-04
+2022-05-05 09:32:09,905 INFO [train.py:715] (3/8) Epoch 5, batch 31850, loss[loss=0.139, simple_loss=0.2099, pruned_loss=0.03405, over 4991.00 frames.], tot_loss[loss=0.1499, simple_loss=0.221, pruned_loss=0.03936, over 972289.29 frames.], batch size: 16, lr: 3.69e-04
+2022-05-05 09:32:49,447 INFO [train.py:715] (3/8) Epoch 5, batch 31900, loss[loss=0.1254, simple_loss=0.198, pruned_loss=0.02641, over 4804.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2204, pruned_loss=0.03914, over 972369.96 frames.], batch size: 26, lr: 3.69e-04
+2022-05-05 09:33:28,134 INFO [train.py:715] (3/8) Epoch 5, batch 31950, loss[loss=0.1586, simple_loss=0.2303, pruned_loss=0.04349, over 4948.00 frames.], tot_loss[loss=0.1506, simple_loss=0.222, pruned_loss=0.03965, over 972400.62 frames.], batch size: 35, lr: 3.69e-04
+2022-05-05 09:34:06,674 INFO [train.py:715] (3/8) Epoch 5, batch 32000, loss[loss=0.1771, simple_loss=0.2564, pruned_loss=0.04895, over 4954.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2227, pruned_loss=0.0401, over 972311.78 frames.], batch size: 24, lr: 3.69e-04
+2022-05-05 09:34:45,046 INFO [train.py:715] (3/8) Epoch 5, batch 32050, loss[loss=0.1571, simple_loss=0.2328, pruned_loss=0.04071, over 4809.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2222, pruned_loss=0.03967, over 971644.78 frames.], batch size: 25, lr: 3.69e-04
+2022-05-05 09:35:24,095 INFO [train.py:715] (3/8) Epoch 5, batch 32100, loss[loss=0.1624, simple_loss=0.24, pruned_loss=0.04239, over 4971.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2222, pruned_loss=0.03998, over 972508.43 frames.], batch size: 15, lr: 3.69e-04
+2022-05-05 09:36:02,965 INFO [train.py:715] (3/8) Epoch 5, batch 32150, loss[loss=0.1563, simple_loss=0.2331, pruned_loss=0.03978, over 4759.00 frames.], tot_loss[loss=0.151, simple_loss=0.2223, pruned_loss=0.0399, over 973245.56 frames.], batch size: 19, lr: 3.69e-04
+2022-05-05 09:36:41,522 INFO [train.py:715] (3/8) Epoch 5, batch 32200, loss[loss=0.1525, simple_loss=0.2271, pruned_loss=0.03902, over 4923.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2222, pruned_loss=0.03999, over 973096.04 frames.], batch size: 18, lr: 3.69e-04
+2022-05-05 09:37:20,075 INFO [train.py:715] (3/8) Epoch 5, batch 32250, loss[loss=0.1447, simple_loss=0.2087, pruned_loss=0.04032, over 4975.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04043, over 972883.57 frames.], batch size: 25, lr: 3.69e-04
+2022-05-05 09:37:59,209 INFO [train.py:715] (3/8) Epoch 5, batch 32300, loss[loss=0.1912, simple_loss=0.259, pruned_loss=0.06168, over 4804.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2223, pruned_loss=0.04054, over 972894.86 frames.], batch size: 21, lr: 3.69e-04
+2022-05-05 09:38:37,803 INFO [train.py:715] (3/8) Epoch 5, batch 32350, loss[loss=0.1397, simple_loss=0.2096, pruned_loss=0.03489, over 4839.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2221, pruned_loss=0.04063, over 972127.40 frames.], batch size: 32, lr: 3.69e-04
+2022-05-05 09:39:16,505 INFO [train.py:715] (3/8) Epoch 5, batch 32400, loss[loss=0.1541, simple_loss=0.2307, pruned_loss=0.03877, over 4913.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2216, pruned_loss=0.04044, over 971018.86 frames.], batch size: 18, lr: 3.69e-04
+2022-05-05 09:39:55,117 INFO [train.py:715] (3/8) Epoch 5, batch 32450, loss[loss=0.1629, simple_loss=0.2335, pruned_loss=0.0461, over 4939.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2224, pruned_loss=0.04045, over 971684.90 frames.], batch size: 23, lr: 3.69e-04
+2022-05-05 09:40:33,913 INFO [train.py:715] (3/8) Epoch 5, batch 32500, loss[loss=0.1495, simple_loss=0.2176, pruned_loss=0.04074, over 4859.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04062, over 971262.00 frames.], batch size: 20, lr: 3.69e-04
+2022-05-05 09:41:13,468 INFO [train.py:715] (3/8) Epoch 5, batch 32550, loss[loss=0.1117, simple_loss=0.183, pruned_loss=0.02022, over 4980.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2218, pruned_loss=0.04031, over 971880.68 frames.], batch size: 14, lr: 3.69e-04
+2022-05-05 09:41:51,932 INFO [train.py:715] (3/8) Epoch 5, batch 32600, loss[loss=0.1354, simple_loss=0.2087, pruned_loss=0.03102, over 4961.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2222, pruned_loss=0.04036, over 971905.70 frames.], batch size: 24, lr: 3.69e-04
+2022-05-05 09:42:30,726 INFO [train.py:715] (3/8) Epoch 5, batch 32650, loss[loss=0.1515, simple_loss=0.2281, pruned_loss=0.03748, over 4888.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2222, pruned_loss=0.04061, over 971014.49 frames.], batch size: 19, lr: 3.69e-04
+2022-05-05 09:43:09,271 INFO [train.py:715] (3/8) Epoch 5, batch 32700, loss[loss=0.1478, simple_loss=0.2264, pruned_loss=0.03463, over 4841.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2224, pruned_loss=0.04075, over 971991.52 frames.], batch size: 13, lr: 3.69e-04
+2022-05-05 09:43:47,572 INFO [train.py:715] (3/8) Epoch 5, batch 32750, loss[loss=0.187, simple_loss=0.2535, pruned_loss=0.06024, over 4983.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2221, pruned_loss=0.04018, over 972140.07 frames.], batch size: 25, lr: 3.69e-04
+2022-05-05 09:44:26,287 INFO [train.py:715] (3/8) Epoch 5, batch 32800, loss[loss=0.1761, simple_loss=0.2456, pruned_loss=0.05336, over 4778.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2216, pruned_loss=0.03995, over 972025.96 frames.], batch size: 17, lr: 3.69e-04
+2022-05-05 09:45:05,106 INFO [train.py:715] (3/8) Epoch 5, batch 32850, loss[loss=0.121, simple_loss=0.184, pruned_loss=0.02896, over 4983.00 frames.], tot_loss[loss=0.152, simple_loss=0.2224, pruned_loss=0.0408, over 972628.45 frames.], batch size: 14, lr: 3.69e-04
+2022-05-05 09:45:44,050 INFO [train.py:715] (3/8) Epoch 5, batch 32900, loss[loss=0.1418, simple_loss=0.2156, pruned_loss=0.03404, over 4966.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2218, pruned_loss=0.0402, over 972260.22 frames.], batch size: 39, lr: 3.69e-04
+2022-05-05 09:46:22,922 INFO [train.py:715] (3/8) Epoch 5, batch 32950, loss[loss=0.142, simple_loss=0.2226, pruned_loss=0.03071, over 4943.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2221, pruned_loss=0.04068, over 971789.77 frames.], batch size: 23, lr: 3.68e-04
+2022-05-05 09:47:01,974 INFO [train.py:715] (3/8) Epoch 5, batch 33000, loss[loss=0.1537, simple_loss=0.2317, pruned_loss=0.03784, over 4954.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2216, pruned_loss=0.04037, over 971930.72 frames.], batch size: 39, lr: 3.68e-04
+2022-05-05 09:47:01,974 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 09:47:11,684 INFO [train.py:742] (3/8) Epoch 5, validation: loss=0.1099, simple_loss=0.1951, pruned_loss=0.01236, over 914524.00 frames.
+2022-05-05 09:47:50,705 INFO [train.py:715] (3/8) Epoch 5, batch 33050, loss[loss=0.1211, simple_loss=0.1879, pruned_loss=0.02717, over 4797.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2209, pruned_loss=0.03998, over 971893.20 frames.], batch size: 14, lr: 3.68e-04
+2022-05-05 09:48:29,615 INFO [train.py:715] (3/8) Epoch 5, batch 33100, loss[loss=0.1387, simple_loss=0.213, pruned_loss=0.0322, over 4952.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2213, pruned_loss=0.04042, over 972439.50 frames.], batch size: 21, lr: 3.68e-04
+2022-05-05 09:49:07,621 INFO [train.py:715] (3/8) Epoch 5, batch 33150, loss[loss=0.1614, simple_loss=0.2371, pruned_loss=0.04285, over 4711.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2224, pruned_loss=0.0412, over 972180.85 frames.], batch size: 15, lr: 3.68e-04
+2022-05-05 09:49:46,218 INFO [train.py:715] (3/8) Epoch 5, batch 33200, loss[loss=0.1475, simple_loss=0.2261, pruned_loss=0.03449, over 4947.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2229, pruned_loss=0.04146, over 971820.54 frames.], batch size: 21, lr: 3.68e-04
+2022-05-05 09:50:25,079 INFO [train.py:715] (3/8) Epoch 5, batch 33250, loss[loss=0.1805, simple_loss=0.2563, pruned_loss=0.05239, over 4968.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2236, pruned_loss=0.04192, over 971882.85 frames.], batch size: 24, lr: 3.68e-04
+2022-05-05 09:51:03,570 INFO [train.py:715] (3/8) Epoch 5, batch 33300, loss[loss=0.185, simple_loss=0.2396, pruned_loss=0.06524, over 4978.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2223, pruned_loss=0.04142, over 972730.92 frames.], batch size: 35, lr: 3.68e-04
+2022-05-05 09:51:41,938 INFO [train.py:715] (3/8) Epoch 5, batch 33350, loss[loss=0.1428, simple_loss=0.2156, pruned_loss=0.03499, over 4785.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2216, pruned_loss=0.04061, over 973031.04 frames.], batch size: 18, lr: 3.68e-04
+2022-05-05 09:52:21,209 INFO [train.py:715] (3/8) Epoch 5, batch 33400, loss[loss=0.1391, simple_loss=0.2097, pruned_loss=0.03425, over 4774.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2227, pruned_loss=0.04102, over 972012.07 frames.], batch size: 18, lr: 3.68e-04
+2022-05-05 09:52:59,901 INFO [train.py:715] (3/8) Epoch 5, batch 33450, loss[loss=0.1542, simple_loss=0.226, pruned_loss=0.04123, over 4915.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2218, pruned_loss=0.04068, over 972798.17 frames.], batch size: 23, lr: 3.68e-04
+2022-05-05 09:53:38,252 INFO [train.py:715] (3/8) Epoch 5, batch 33500, loss[loss=0.1377, simple_loss=0.2037, pruned_loss=0.03583, over 4857.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2218, pruned_loss=0.04069, over 972755.48 frames.], batch size: 30, lr: 3.68e-04
+2022-05-05 09:54:16,985 INFO [train.py:715] (3/8) Epoch 5, batch 33550, loss[loss=0.1634, simple_loss=0.2281, pruned_loss=0.04934, over 4845.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2218, pruned_loss=0.04098, over 972568.85 frames.], batch size: 32, lr: 3.68e-04
+2022-05-05 09:54:55,689 INFO [train.py:715] (3/8) Epoch 5, batch 33600, loss[loss=0.1925, simple_loss=0.2623, pruned_loss=0.06138, over 4905.00 frames.], tot_loss[loss=0.1527, simple_loss=0.223, pruned_loss=0.04115, over 972207.76 frames.], batch size: 17, lr: 3.68e-04
+2022-05-05 09:55:34,353 INFO [train.py:715] (3/8) Epoch 5, batch 33650, loss[loss=0.1638, simple_loss=0.2326, pruned_loss=0.04746, over 4830.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2233, pruned_loss=0.04128, over 972283.82 frames.], batch size: 15, lr: 3.68e-04
+2022-05-05 09:56:12,632 INFO [train.py:715] (3/8) Epoch 5, batch 33700, loss[loss=0.1463, simple_loss=0.2144, pruned_loss=0.03915, over 4822.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2237, pruned_loss=0.0414, over 971815.61 frames.], batch size: 25, lr: 3.68e-04
+2022-05-05 09:56:51,513 INFO [train.py:715] (3/8) Epoch 5, batch 33750, loss[loss=0.1377, simple_loss=0.2258, pruned_loss=0.02485, over 4991.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2229, pruned_loss=0.04136, over 971942.40 frames.], batch size: 26, lr: 3.68e-04
+2022-05-05 09:57:30,147 INFO [train.py:715] (3/8) Epoch 5, batch 33800, loss[loss=0.1629, simple_loss=0.2223, pruned_loss=0.05175, over 4770.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2221, pruned_loss=0.04113, over 971274.25 frames.], batch size: 14, lr: 3.68e-04
+2022-05-05 09:58:09,141 INFO [train.py:715] (3/8) Epoch 5, batch 33850, loss[loss=0.1536, simple_loss=0.2332, pruned_loss=0.03695, over 4958.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2212, pruned_loss=0.04027, over 972275.60 frames.], batch size: 39, lr: 3.68e-04
+2022-05-05 09:58:47,624 INFO [train.py:715] (3/8) Epoch 5, batch 33900, loss[loss=0.1494, simple_loss=0.2062, pruned_loss=0.0463, over 4700.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2211, pruned_loss=0.04052, over 972263.87 frames.], batch size: 15, lr: 3.68e-04
+2022-05-05 09:59:25,961 INFO [train.py:715] (3/8) Epoch 5, batch 33950, loss[loss=0.1565, simple_loss=0.2247, pruned_loss=0.04414, over 4804.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2209, pruned_loss=0.04018, over 972939.06 frames.], batch size: 14, lr: 3.68e-04
+2022-05-05 10:00:06,990 INFO [train.py:715] (3/8) Epoch 5, batch 34000, loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03329, over 4814.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2204, pruned_loss=0.03993, over 972345.97 frames.], batch size: 26, lr: 3.68e-04
+2022-05-05 10:00:45,230 INFO [train.py:715] (3/8) Epoch 5, batch 34050, loss[loss=0.1762, simple_loss=0.2379, pruned_loss=0.05722, over 4844.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2197, pruned_loss=0.03985, over 972062.46 frames.], batch size: 30, lr: 3.67e-04
+2022-05-05 10:01:23,921 INFO [train.py:715] (3/8) Epoch 5, batch 34100, loss[loss=0.156, simple_loss=0.2284, pruned_loss=0.04178, over 4956.00 frames.], tot_loss[loss=0.15, simple_loss=0.2201, pruned_loss=0.03996, over 972017.63 frames.], batch size: 24, lr: 3.67e-04
+2022-05-05 10:02:02,748 INFO [train.py:715] (3/8) Epoch 5, batch 34150, loss[loss=0.1724, simple_loss=0.2433, pruned_loss=0.05071, over 4915.00 frames.], tot_loss[loss=0.1508, simple_loss=0.221, pruned_loss=0.04029, over 972749.88 frames.], batch size: 18, lr: 3.67e-04
+2022-05-05 10:02:41,108 INFO [train.py:715] (3/8) Epoch 5, batch 34200, loss[loss=0.1556, simple_loss=0.2213, pruned_loss=0.04495, over 4839.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2211, pruned_loss=0.04036, over 972681.24 frames.], batch size: 30, lr: 3.67e-04
+2022-05-05 10:03:20,095 INFO [train.py:715] (3/8) Epoch 5, batch 34250, loss[loss=0.109, simple_loss=0.1811, pruned_loss=0.01841, over 4793.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2212, pruned_loss=0.04002, over 972434.01 frames.], batch size: 12, lr: 3.67e-04
+2022-05-05 10:03:58,246 INFO [train.py:715] (3/8) Epoch 5, batch 34300, loss[loss=0.1636, simple_loss=0.2295, pruned_loss=0.0488, over 4924.00 frames.], tot_loss[loss=0.151, simple_loss=0.2212, pruned_loss=0.04038, over 972763.22 frames.], batch size: 17, lr: 3.67e-04
+2022-05-05 10:04:36,909 INFO [train.py:715] (3/8) Epoch 5, batch 34350, loss[loss=0.1546, simple_loss=0.2271, pruned_loss=0.04105, over 4917.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2217, pruned_loss=0.04048, over 972096.80 frames.], batch size: 29, lr: 3.67e-04
+2022-05-05 10:05:14,796 INFO [train.py:715] (3/8) Epoch 5, batch 34400, loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.02879, over 4803.00 frames.], tot_loss[loss=0.151, simple_loss=0.2218, pruned_loss=0.04014, over 971496.59 frames.], batch size: 21, lr: 3.67e-04
+2022-05-05 10:05:53,763 INFO [train.py:715] (3/8) Epoch 5, batch 34450, loss[loss=0.1725, simple_loss=0.2431, pruned_loss=0.05091, over 4835.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.0402, over 971357.28 frames.], batch size: 30, lr: 3.67e-04
+2022-05-05 10:06:32,733 INFO [train.py:715] (3/8) Epoch 5, batch 34500, loss[loss=0.1664, simple_loss=0.2434, pruned_loss=0.04473, over 4964.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04022, over 970863.11 frames.], batch size: 21, lr: 3.67e-04
+2022-05-05 10:07:11,202 INFO [train.py:715] (3/8) Epoch 5, batch 34550, loss[loss=0.1587, simple_loss=0.2225, pruned_loss=0.04741, over 4779.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2223, pruned_loss=0.04046, over 970551.56 frames.], batch size: 14, lr: 3.67e-04
+2022-05-05 10:07:49,951 INFO [train.py:715] (3/8) Epoch 5, batch 34600, loss[loss=0.1529, simple_loss=0.2169, pruned_loss=0.04441, over 4840.00 frames.], tot_loss[loss=0.1513, simple_loss=0.222, pruned_loss=0.04037, over 971233.16 frames.], batch size: 32, lr: 3.67e-04
+2022-05-05 10:08:28,654 INFO [train.py:715] (3/8) Epoch 5, batch 34650, loss[loss=0.1568, simple_loss=0.2323, pruned_loss=0.04062, over 4879.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2214, pruned_loss=0.04013, over 971842.12 frames.], batch size: 22, lr: 3.67e-04
+2022-05-05 10:09:07,579 INFO [train.py:715] (3/8) Epoch 5, batch 34700, loss[loss=0.1739, simple_loss=0.2529, pruned_loss=0.04744, over 4941.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2225, pruned_loss=0.04046, over 971789.83 frames.], batch size: 39, lr: 3.67e-04
+2022-05-05 10:09:44,906 INFO [train.py:715] (3/8) Epoch 5, batch 34750, loss[loss=0.1439, simple_loss=0.2205, pruned_loss=0.03362, over 4968.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2235, pruned_loss=0.04098, over 971987.99 frames.], batch size: 24, lr: 3.67e-04
+2022-05-05 10:10:21,601 INFO [train.py:715] (3/8) Epoch 5, batch 34800, loss[loss=0.1464, simple_loss=0.2137, pruned_loss=0.03955, over 4764.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2205, pruned_loss=0.04, over 970372.07 frames.], batch size: 14, lr: 3.67e-04
+2022-05-05 10:11:11,224 INFO [train.py:715] (3/8) Epoch 6, batch 0, loss[loss=0.1556, simple_loss=0.2137, pruned_loss=0.04878, over 4884.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2137, pruned_loss=0.04878, over 4884.00 frames.], batch size: 32, lr: 3.46e-04
+2022-05-05 10:11:50,190 INFO [train.py:715] (3/8) Epoch 6, batch 50, loss[loss=0.1536, simple_loss=0.2267, pruned_loss=0.04026, over 4939.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2206, pruned_loss=0.04153, over 219463.55 frames.], batch size: 18, lr: 3.46e-04
+2022-05-05 10:12:29,110 INFO [train.py:715] (3/8) Epoch 6, batch 100, loss[loss=0.1649, simple_loss=0.2193, pruned_loss=0.05525, over 4837.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2203, pruned_loss=0.04007, over 386295.39 frames.], batch size: 32, lr: 3.46e-04
+2022-05-05 10:13:08,350 INFO [train.py:715] (3/8) Epoch 6, batch 150, loss[loss=0.1506, simple_loss=0.216, pruned_loss=0.04267, over 4878.00 frames.], tot_loss[loss=0.15, simple_loss=0.2204, pruned_loss=0.03979, over 516774.13 frames.], batch size: 22, lr: 3.46e-04
+2022-05-05 10:13:47,633 INFO [train.py:715] (3/8) Epoch 6, batch 200, loss[loss=0.1613, simple_loss=0.2141, pruned_loss=0.05424, over 4858.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2211, pruned_loss=0.03989, over 618785.82 frames.], batch size: 32, lr: 3.45e-04
+2022-05-05 10:14:26,643 INFO [train.py:715] (3/8) Epoch 6, batch 250, loss[loss=0.1679, simple_loss=0.2369, pruned_loss=0.04946, over 4778.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2202, pruned_loss=0.03946, over 697697.29 frames.], batch size: 19, lr: 3.45e-04
+2022-05-05 10:15:05,462 INFO [train.py:715] (3/8) Epoch 6, batch 300, loss[loss=0.1453, simple_loss=0.2154, pruned_loss=0.03763, over 4749.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2193, pruned_loss=0.0385, over 757735.38 frames.], batch size: 12, lr: 3.45e-04
+2022-05-05 10:15:44,472 INFO [train.py:715] (3/8) Epoch 6, batch 350, loss[loss=0.1387, simple_loss=0.2163, pruned_loss=0.03054, over 4885.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2191, pruned_loss=0.03831, over 805113.14 frames.], batch size: 19, lr: 3.45e-04
+2022-05-05 10:16:23,655 INFO [train.py:715] (3/8) Epoch 6, batch 400, loss[loss=0.1738, simple_loss=0.2417, pruned_loss=0.05299, over 4886.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03888, over 842395.32 frames.], batch size: 22, lr: 3.45e-04
+2022-05-05 10:17:02,412 INFO [train.py:715] (3/8) Epoch 6, batch 450, loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.03409, over 4798.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2202, pruned_loss=0.03877, over 871092.48 frames.], batch size: 26, lr: 3.45e-04
+2022-05-05 10:17:41,008 INFO [train.py:715] (3/8) Epoch 6, batch 500, loss[loss=0.1627, simple_loss=0.2225, pruned_loss=0.05148, over 4990.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2203, pruned_loss=0.03917, over 893320.24 frames.], batch size: 14, lr: 3.45e-04
+2022-05-05 10:18:20,498 INFO [train.py:715] (3/8) Epoch 6, batch 550, loss[loss=0.1452, simple_loss=0.2228, pruned_loss=0.03384, over 4757.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2196, pruned_loss=0.03866, over 911085.96 frames.], batch size: 16, lr: 3.45e-04
+2022-05-05 10:18:59,386 INFO [train.py:715] (3/8) Epoch 6, batch 600, loss[loss=0.1673, simple_loss=0.2407, pruned_loss=0.047, over 4804.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2206, pruned_loss=0.03898, over 925049.08 frames.], batch size: 25, lr: 3.45e-04
+2022-05-05 10:19:38,405 INFO [train.py:715] (3/8) Epoch 6, batch 650, loss[loss=0.1873, simple_loss=0.2634, pruned_loss=0.05561, over 4921.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03985, over 935915.30 frames.], batch size: 23, lr: 3.45e-04
+2022-05-05 10:20:17,490 INFO [train.py:715] (3/8) Epoch 6, batch 700, loss[loss=0.1905, simple_loss=0.251, pruned_loss=0.06501, over 4971.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.03963, over 944673.53 frames.], batch size: 14, lr: 3.45e-04
+2022-05-05 10:20:57,082 INFO [train.py:715] (3/8) Epoch 6, batch 750, loss[loss=0.1438, simple_loss=0.2092, pruned_loss=0.0392, over 4787.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2217, pruned_loss=0.03986, over 950655.91 frames.], batch size: 21, lr: 3.45e-04
+2022-05-05 10:21:35,857 INFO [train.py:715] (3/8) Epoch 6, batch 800, loss[loss=0.1406, simple_loss=0.2066, pruned_loss=0.03733, over 4872.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03931, over 955447.61 frames.], batch size: 16, lr: 3.45e-04
+2022-05-05 10:22:14,571 INFO [train.py:715] (3/8) Epoch 6, batch 850, loss[loss=0.1514, simple_loss=0.2256, pruned_loss=0.03857, over 4946.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2209, pruned_loss=0.0393, over 959996.12 frames.], batch size: 21, lr: 3.45e-04
+2022-05-05 10:22:54,105 INFO [train.py:715] (3/8) Epoch 6, batch 900, loss[loss=0.1566, simple_loss=0.2191, pruned_loss=0.047, over 4865.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2203, pruned_loss=0.03926, over 962119.52 frames.], batch size: 32, lr: 3.45e-04
+2022-05-05 10:23:33,398 INFO [train.py:715] (3/8) Epoch 6, batch 950, loss[loss=0.1646, simple_loss=0.227, pruned_loss=0.05107, over 4691.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2205, pruned_loss=0.03924, over 963929.97 frames.], batch size: 15, lr: 3.45e-04
+2022-05-05 10:24:12,122 INFO [train.py:715] (3/8) Epoch 6, batch 1000, loss[loss=0.1608, simple_loss=0.2149, pruned_loss=0.05336, over 4791.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2212, pruned_loss=0.03954, over 965927.18 frames.], batch size: 17, lr: 3.45e-04
+2022-05-05 10:24:51,184 INFO [train.py:715] (3/8) Epoch 6, batch 1050, loss[loss=0.1529, simple_loss=0.221, pruned_loss=0.04243, over 4866.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.0396, over 967252.96 frames.], batch size: 22, lr: 3.45e-04
+2022-05-05 10:25:30,704 INFO [train.py:715] (3/8) Epoch 6, batch 1100, loss[loss=0.182, simple_loss=0.2489, pruned_loss=0.05759, over 4963.00 frames.], tot_loss[loss=0.15, simple_loss=0.2211, pruned_loss=0.03942, over 969032.50 frames.], batch size: 39, lr: 3.45e-04
+2022-05-05 10:26:09,925 INFO [train.py:715] (3/8) Epoch 6, batch 1150, loss[loss=0.1489, simple_loss=0.2276, pruned_loss=0.03516, over 4844.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2221, pruned_loss=0.04007, over 970253.79 frames.], batch size: 15, lr: 3.45e-04
+2022-05-05 10:26:48,493 INFO [train.py:715] (3/8) Epoch 6, batch 1200, loss[loss=0.1279, simple_loss=0.2035, pruned_loss=0.02621, over 4823.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2217, pruned_loss=0.03963, over 970231.44 frames.], batch size: 26, lr: 3.45e-04
+2022-05-05 10:27:28,194 INFO [train.py:715] (3/8) Epoch 6, batch 1250, loss[loss=0.1914, simple_loss=0.2529, pruned_loss=0.06501, over 4958.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2215, pruned_loss=0.04, over 969975.42 frames.], batch size: 15, lr: 3.45e-04
+2022-05-05 10:28:07,471 INFO [train.py:715] (3/8) Epoch 6, batch 1300, loss[loss=0.1619, simple_loss=0.2362, pruned_loss=0.04379, over 4703.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2215, pruned_loss=0.04003, over 970515.08 frames.], batch size: 15, lr: 3.45e-04
+2022-05-05 10:28:46,065 INFO [train.py:715] (3/8) Epoch 6, batch 1350, loss[loss=0.1291, simple_loss=0.1958, pruned_loss=0.03124, over 4936.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2218, pruned_loss=0.0403, over 970891.79 frames.], batch size: 23, lr: 3.45e-04
+2022-05-05 10:29:24,990 INFO [train.py:715] (3/8) Epoch 6, batch 1400, loss[loss=0.1932, simple_loss=0.2622, pruned_loss=0.06213, over 4910.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2226, pruned_loss=0.04059, over 970415.01 frames.], batch size: 19, lr: 3.45e-04
+2022-05-05 10:30:04,140 INFO [train.py:715] (3/8) Epoch 6, batch 1450, loss[loss=0.1393, simple_loss=0.2139, pruned_loss=0.03236, over 4974.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.03968, over 970983.61 frames.], batch size: 28, lr: 3.44e-04
+2022-05-05 10:30:42,813 INFO [train.py:715] (3/8) Epoch 6, batch 1500, loss[loss=0.1603, simple_loss=0.2172, pruned_loss=0.05169, over 4931.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2207, pruned_loss=0.03944, over 971834.86 frames.], batch size: 29, lr: 3.44e-04
+2022-05-05 10:31:21,217 INFO [train.py:715] (3/8) Epoch 6, batch 1550, loss[loss=0.1601, simple_loss=0.2291, pruned_loss=0.04556, over 4848.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03964, over 972333.48 frames.], batch size: 20, lr: 3.44e-04
+2022-05-05 10:32:00,472 INFO [train.py:715] (3/8) Epoch 6, batch 1600, loss[loss=0.1388, simple_loss=0.2215, pruned_loss=0.028, over 4764.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03957, over 972898.94 frames.], batch size: 19, lr: 3.44e-04
+2022-05-05 10:32:40,007 INFO [train.py:715] (3/8) Epoch 6, batch 1650, loss[loss=0.1391, simple_loss=0.213, pruned_loss=0.03254, over 4969.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03975, over 973529.11 frames.], batch size: 35, lr: 3.44e-04
+2022-05-05 10:33:18,413 INFO [train.py:715] (3/8) Epoch 6, batch 1700, loss[loss=0.1384, simple_loss=0.2054, pruned_loss=0.03571, over 4786.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2211, pruned_loss=0.03976, over 972834.69 frames.], batch size: 17, lr: 3.44e-04
+2022-05-05 10:33:57,729 INFO [train.py:715] (3/8) Epoch 6, batch 1750, loss[loss=0.1472, simple_loss=0.2201, pruned_loss=0.03713, over 4928.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2216, pruned_loss=0.03972, over 972279.70 frames.], batch size: 21, lr: 3.44e-04
+2022-05-05 10:34:37,322 INFO [train.py:715] (3/8) Epoch 6, batch 1800, loss[loss=0.1435, simple_loss=0.2125, pruned_loss=0.03727, over 4780.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2215, pruned_loss=0.03993, over 971866.09 frames.], batch size: 14, lr: 3.44e-04
+2022-05-05 10:35:16,402 INFO [train.py:715] (3/8) Epoch 6, batch 1850, loss[loss=0.1512, simple_loss=0.2152, pruned_loss=0.04362, over 4865.00 frames.], tot_loss[loss=0.152, simple_loss=0.2224, pruned_loss=0.04084, over 971782.20 frames.], batch size: 32, lr: 3.44e-04
+2022-05-05 10:35:54,731 INFO [train.py:715] (3/8) Epoch 6, batch 1900, loss[loss=0.1283, simple_loss=0.2038, pruned_loss=0.02636, over 4858.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2218, pruned_loss=0.04022, over 971985.66 frames.], batch size: 20, lr: 3.44e-04
+2022-05-05 10:36:34,277 INFO [train.py:715] (3/8) Epoch 6, batch 1950, loss[loss=0.129, simple_loss=0.1901, pruned_loss=0.03397, over 4768.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.0402, over 972600.64 frames.], batch size: 18, lr: 3.44e-04
+2022-05-05 10:37:13,034 INFO [train.py:715] (3/8) Epoch 6, batch 2000, loss[loss=0.1431, simple_loss=0.2247, pruned_loss=0.03074, over 4802.00 frames.], tot_loss[loss=0.151, simple_loss=0.2216, pruned_loss=0.04018, over 972536.00 frames.], batch size: 21, lr: 3.44e-04
+2022-05-05 10:37:52,082 INFO [train.py:715] (3/8) Epoch 6, batch 2050, loss[loss=0.1116, simple_loss=0.1788, pruned_loss=0.02222, over 4800.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04044, over 972050.02 frames.], batch size: 12, lr: 3.44e-04
+2022-05-05 10:38:30,928 INFO [train.py:715] (3/8) Epoch 6, batch 2100, loss[loss=0.1395, simple_loss=0.2164, pruned_loss=0.03129, over 4976.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2212, pruned_loss=0.04023, over 972514.38 frames.], batch size: 15, lr: 3.44e-04
+2022-05-05 10:39:10,113 INFO [train.py:715] (3/8) Epoch 6, batch 2150, loss[loss=0.1572, simple_loss=0.2175, pruned_loss=0.04841, over 4971.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2209, pruned_loss=0.03993, over 972976.55 frames.], batch size: 15, lr: 3.44e-04
+2022-05-05 10:39:49,074 INFO [train.py:715] (3/8) Epoch 6, batch 2200, loss[loss=0.1473, simple_loss=0.2206, pruned_loss=0.03699, over 4984.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04007, over 973386.32 frames.], batch size: 24, lr: 3.44e-04
+2022-05-05 10:40:27,528 INFO [train.py:715] (3/8) Epoch 6, batch 2250, loss[loss=0.1472, simple_loss=0.2254, pruned_loss=0.03453, over 4702.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2212, pruned_loss=0.03986, over 973109.82 frames.], batch size: 15, lr: 3.44e-04
+2022-05-05 10:41:06,875 INFO [train.py:715] (3/8) Epoch 6, batch 2300, loss[loss=0.1666, simple_loss=0.2329, pruned_loss=0.05011, over 4958.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2219, pruned_loss=0.03981, over 972234.30 frames.], batch size: 35, lr: 3.44e-04
+2022-05-05 10:41:45,980 INFO [train.py:715] (3/8) Epoch 6, batch 2350, loss[loss=0.1546, simple_loss=0.2338, pruned_loss=0.03774, over 4900.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2213, pruned_loss=0.03955, over 972799.04 frames.], batch size: 19, lr: 3.44e-04
+2022-05-05 10:42:24,704 INFO [train.py:715] (3/8) Epoch 6, batch 2400, loss[loss=0.1547, simple_loss=0.2304, pruned_loss=0.03953, over 4963.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03935, over 973083.02 frames.], batch size: 24, lr: 3.44e-04
+2022-05-05 10:43:03,445 INFO [train.py:715] (3/8) Epoch 6, batch 2450, loss[loss=0.1367, simple_loss=0.2114, pruned_loss=0.03096, over 4794.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2202, pruned_loss=0.03901, over 973217.12 frames.], batch size: 17, lr: 3.44e-04
+2022-05-05 10:43:42,676 INFO [train.py:715] (3/8) Epoch 6, batch 2500, loss[loss=0.1803, simple_loss=0.251, pruned_loss=0.0548, over 4808.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2203, pruned_loss=0.03915, over 972922.63 frames.], batch size: 21, lr: 3.44e-04
+2022-05-05 10:44:21,861 INFO [train.py:715] (3/8) Epoch 6, batch 2550, loss[loss=0.1305, simple_loss=0.2026, pruned_loss=0.02924, over 4854.00 frames.], tot_loss[loss=0.15, simple_loss=0.2212, pruned_loss=0.03944, over 972130.38 frames.], batch size: 15, lr: 3.44e-04
+2022-05-05 10:45:00,769 INFO [train.py:715] (3/8) Epoch 6, batch 2600, loss[loss=0.1623, simple_loss=0.2284, pruned_loss=0.04807, over 4888.00 frames.], tot_loss[loss=0.15, simple_loss=0.2211, pruned_loss=0.0394, over 972556.86 frames.], batch size: 22, lr: 3.44e-04
+2022-05-05 10:45:40,393 INFO [train.py:715] (3/8) Epoch 6, batch 2650, loss[loss=0.1337, simple_loss=0.2089, pruned_loss=0.02925, over 4801.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2225, pruned_loss=0.04026, over 972834.07 frames.], batch size: 24, lr: 3.43e-04
+2022-05-05 10:46:19,961 INFO [train.py:715] (3/8) Epoch 6, batch 2700, loss[loss=0.1596, simple_loss=0.2411, pruned_loss=0.03903, over 4821.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2223, pruned_loss=0.04012, over 973229.50 frames.], batch size: 27, lr: 3.43e-04
+2022-05-05 10:46:58,103 INFO [train.py:715] (3/8) Epoch 6, batch 2750, loss[loss=0.1508, simple_loss=0.2144, pruned_loss=0.04361, over 4946.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2224, pruned_loss=0.04015, over 973520.96 frames.], batch size: 21, lr: 3.43e-04
+2022-05-05 10:47:37,113 INFO [train.py:715] (3/8) Epoch 6, batch 2800, loss[loss=0.1647, simple_loss=0.2328, pruned_loss=0.04828, over 4848.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.03987, over 972741.29 frames.], batch size: 30, lr: 3.43e-04
+2022-05-05 10:48:16,470 INFO [train.py:715] (3/8) Epoch 6, batch 2850, loss[loss=0.1309, simple_loss=0.193, pruned_loss=0.03445, over 4824.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2216, pruned_loss=0.03986, over 972759.34 frames.], batch size: 12, lr: 3.43e-04
+2022-05-05 10:48:55,298 INFO [train.py:715] (3/8) Epoch 6, batch 2900, loss[loss=0.1377, simple_loss=0.2094, pruned_loss=0.03301, over 4786.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.04021, over 973107.64 frames.], batch size: 14, lr: 3.43e-04
+2022-05-05 10:49:33,638 INFO [train.py:715] (3/8) Epoch 6, batch 2950, loss[loss=0.1478, simple_loss=0.2229, pruned_loss=0.03633, over 4822.00 frames.], tot_loss[loss=0.1515, simple_loss=0.222, pruned_loss=0.04054, over 972704.57 frames.], batch size: 25, lr: 3.43e-04
+2022-05-05 10:50:12,868 INFO [train.py:715] (3/8) Epoch 6, batch 3000, loss[loss=0.1389, simple_loss=0.2185, pruned_loss=0.0296, over 4845.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2223, pruned_loss=0.04058, over 972858.05 frames.], batch size: 20, lr: 3.43e-04
+2022-05-05 10:50:12,868 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 10:50:22,538 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1095, simple_loss=0.1945, pruned_loss=0.01223, over 914524.00 frames.
+2022-05-05 10:51:02,173 INFO [train.py:715] (3/8) Epoch 6, batch 3050, loss[loss=0.1695, simple_loss=0.239, pruned_loss=0.05001, over 4894.00 frames.], tot_loss[loss=0.152, simple_loss=0.2226, pruned_loss=0.0407, over 972822.78 frames.], batch size: 22, lr: 3.43e-04
+2022-05-05 10:51:41,566 INFO [train.py:715] (3/8) Epoch 6, batch 3100, loss[loss=0.1557, simple_loss=0.2384, pruned_loss=0.03648, over 4872.00 frames.], tot_loss[loss=0.152, simple_loss=0.2225, pruned_loss=0.04076, over 972805.22 frames.], batch size: 16, lr: 3.43e-04
+2022-05-05 10:52:20,132 INFO [train.py:715] (3/8) Epoch 6, batch 3150, loss[loss=0.178, simple_loss=0.2468, pruned_loss=0.05463, over 4801.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2227, pruned_loss=0.04082, over 972425.22 frames.], batch size: 24, lr: 3.43e-04
+2022-05-05 10:52:58,780 INFO [train.py:715] (3/8) Epoch 6, batch 3200, loss[loss=0.1224, simple_loss=0.2001, pruned_loss=0.0224, over 4816.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2228, pruned_loss=0.0412, over 971874.75 frames.], batch size: 25, lr: 3.43e-04
+2022-05-05 10:53:38,607 INFO [train.py:715] (3/8) Epoch 6, batch 3250, loss[loss=0.1136, simple_loss=0.1817, pruned_loss=0.02274, over 4988.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2217, pruned_loss=0.04007, over 972066.43 frames.], batch size: 28, lr: 3.43e-04
+2022-05-05 10:54:17,333 INFO [train.py:715] (3/8) Epoch 6, batch 3300, loss[loss=0.1203, simple_loss=0.1848, pruned_loss=0.02793, over 4967.00 frames.], tot_loss[loss=0.1501, simple_loss=0.221, pruned_loss=0.03958, over 971723.37 frames.], batch size: 24, lr: 3.43e-04
+2022-05-05 10:54:55,862 INFO [train.py:715] (3/8) Epoch 6, batch 3350, loss[loss=0.1323, simple_loss=0.2086, pruned_loss=0.028, over 4788.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2203, pruned_loss=0.03907, over 972388.65 frames.], batch size: 14, lr: 3.43e-04
+2022-05-05 10:55:35,258 INFO [train.py:715] (3/8) Epoch 6, batch 3400, loss[loss=0.1524, simple_loss=0.2196, pruned_loss=0.04259, over 4943.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2217, pruned_loss=0.03975, over 973126.18 frames.], batch size: 15, lr: 3.43e-04
+2022-05-05 10:56:14,434 INFO [train.py:715] (3/8) Epoch 6, batch 3450, loss[loss=0.1488, simple_loss=0.2115, pruned_loss=0.04306, over 4737.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2217, pruned_loss=0.03954, over 973299.68 frames.], batch size: 16, lr: 3.43e-04
+2022-05-05 10:56:52,541 INFO [train.py:715] (3/8) Epoch 6, batch 3500, loss[loss=0.1518, simple_loss=0.23, pruned_loss=0.03679, over 4692.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2205, pruned_loss=0.03896, over 972546.35 frames.], batch size: 15, lr: 3.43e-04
+2022-05-05 10:57:31,369 INFO [train.py:715] (3/8) Epoch 6, batch 3550, loss[loss=0.1441, simple_loss=0.2171, pruned_loss=0.03556, over 4943.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2217, pruned_loss=0.03962, over 972224.68 frames.], batch size: 23, lr: 3.43e-04
+2022-05-05 10:58:10,830 INFO [train.py:715] (3/8) Epoch 6, batch 3600, loss[loss=0.1693, simple_loss=0.2443, pruned_loss=0.04721, over 4765.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2217, pruned_loss=0.03947, over 971857.86 frames.], batch size: 16, lr: 3.43e-04
+2022-05-05 10:58:49,771 INFO [train.py:715] (3/8) Epoch 6, batch 3650, loss[loss=0.1505, simple_loss=0.2211, pruned_loss=0.0399, over 4829.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2215, pruned_loss=0.03916, over 972289.04 frames.], batch size: 15, lr: 3.43e-04
+2022-05-05 10:59:27,965 INFO [train.py:715] (3/8) Epoch 6, batch 3700, loss[loss=0.1381, simple_loss=0.2133, pruned_loss=0.03145, over 4682.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2215, pruned_loss=0.03938, over 972041.07 frames.], batch size: 15, lr: 3.43e-04
+2022-05-05 11:00:07,226 INFO [train.py:715] (3/8) Epoch 6, batch 3750, loss[loss=0.1527, simple_loss=0.2275, pruned_loss=0.03893, over 4914.00 frames.], tot_loss[loss=0.1495, simple_loss=0.221, pruned_loss=0.03901, over 971390.91 frames.], batch size: 23, lr: 3.43e-04
+2022-05-05 11:00:46,317 INFO [train.py:715] (3/8) Epoch 6, batch 3800, loss[loss=0.129, simple_loss=0.1929, pruned_loss=0.03256, over 4891.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2202, pruned_loss=0.03879, over 971932.87 frames.], batch size: 16, lr: 3.43e-04
+2022-05-05 11:01:24,437 INFO [train.py:715] (3/8) Epoch 6, batch 3850, loss[loss=0.132, simple_loss=0.2028, pruned_loss=0.03061, over 4989.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2202, pruned_loss=0.03898, over 972218.65 frames.], batch size: 28, lr: 3.43e-04
+2022-05-05 11:02:03,350 INFO [train.py:715] (3/8) Epoch 6, batch 3900, loss[loss=0.1544, simple_loss=0.2221, pruned_loss=0.04331, over 4964.00 frames.], tot_loss[loss=0.149, simple_loss=0.2197, pruned_loss=0.03919, over 972033.06 frames.], batch size: 39, lr: 3.42e-04
+2022-05-05 11:02:42,645 INFO [train.py:715] (3/8) Epoch 6, batch 3950, loss[loss=0.1577, simple_loss=0.2192, pruned_loss=0.04811, over 4751.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2204, pruned_loss=0.0399, over 971529.36 frames.], batch size: 12, lr: 3.42e-04
+2022-05-05 11:03:21,706 INFO [train.py:715] (3/8) Epoch 6, batch 4000, loss[loss=0.1268, simple_loss=0.198, pruned_loss=0.0278, over 4757.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2204, pruned_loss=0.03994, over 970965.05 frames.], batch size: 19, lr: 3.42e-04
+2022-05-05 11:04:00,014 INFO [train.py:715] (3/8) Epoch 6, batch 4050, loss[loss=0.1706, simple_loss=0.2332, pruned_loss=0.05403, over 4969.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2198, pruned_loss=0.03955, over 972214.99 frames.], batch size: 15, lr: 3.42e-04
+2022-05-05 11:04:39,115 INFO [train.py:715] (3/8) Epoch 6, batch 4100, loss[loss=0.1418, simple_loss=0.2149, pruned_loss=0.03437, over 4860.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2206, pruned_loss=0.04025, over 971479.75 frames.], batch size: 32, lr: 3.42e-04
+2022-05-05 11:05:17,851 INFO [train.py:715] (3/8) Epoch 6, batch 4150, loss[loss=0.1331, simple_loss=0.2004, pruned_loss=0.03293, over 4972.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2208, pruned_loss=0.0401, over 971795.21 frames.], batch size: 15, lr: 3.42e-04
+2022-05-05 11:05:56,006 INFO [train.py:715] (3/8) Epoch 6, batch 4200, loss[loss=0.1743, simple_loss=0.2414, pruned_loss=0.05361, over 4794.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2197, pruned_loss=0.03956, over 971793.57 frames.], batch size: 18, lr: 3.42e-04
+2022-05-05 11:06:34,725 INFO [train.py:715] (3/8) Epoch 6, batch 4250, loss[loss=0.1552, simple_loss=0.2314, pruned_loss=0.03947, over 4964.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2196, pruned_loss=0.03928, over 972153.44 frames.], batch size: 14, lr: 3.42e-04
+2022-05-05 11:07:13,787 INFO [train.py:715] (3/8) Epoch 6, batch 4300, loss[loss=0.1397, simple_loss=0.2079, pruned_loss=0.03574, over 4853.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2201, pruned_loss=0.03955, over 971603.97 frames.], batch size: 20, lr: 3.42e-04
+2022-05-05 11:07:52,585 INFO [train.py:715] (3/8) Epoch 6, batch 4350, loss[loss=0.1713, simple_loss=0.2361, pruned_loss=0.05326, over 4797.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2203, pruned_loss=0.03963, over 971171.59 frames.], batch size: 12, lr: 3.42e-04
+2022-05-05 11:08:30,489 INFO [train.py:715] (3/8) Epoch 6, batch 4400, loss[loss=0.1633, simple_loss=0.2257, pruned_loss=0.0505, over 4810.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2204, pruned_loss=0.03945, over 971894.76 frames.], batch size: 25, lr: 3.42e-04
+2022-05-05 11:09:08,943 INFO [train.py:715] (3/8) Epoch 6, batch 4450, loss[loss=0.1203, simple_loss=0.1955, pruned_loss=0.02253, over 4886.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03947, over 971985.36 frames.], batch size: 22, lr: 3.42e-04
+2022-05-05 11:09:48,071 INFO [train.py:715] (3/8) Epoch 6, batch 4500, loss[loss=0.1471, simple_loss=0.2156, pruned_loss=0.03929, over 4825.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2208, pruned_loss=0.03954, over 971030.05 frames.], batch size: 15, lr: 3.42e-04
+2022-05-05 11:10:26,354 INFO [train.py:715] (3/8) Epoch 6, batch 4550, loss[loss=0.1526, simple_loss=0.2223, pruned_loss=0.04141, over 4981.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2204, pruned_loss=0.03927, over 971020.68 frames.], batch size: 33, lr: 3.42e-04
+2022-05-05 11:11:04,819 INFO [train.py:715] (3/8) Epoch 6, batch 4600, loss[loss=0.1436, simple_loss=0.2208, pruned_loss=0.03317, over 4779.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03952, over 971079.61 frames.], batch size: 17, lr: 3.42e-04
+2022-05-05 11:11:44,224 INFO [train.py:715] (3/8) Epoch 6, batch 4650, loss[loss=0.1595, simple_loss=0.228, pruned_loss=0.04552, over 4984.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2207, pruned_loss=0.03955, over 970839.36 frames.], batch size: 15, lr: 3.42e-04
+2022-05-05 11:12:23,349 INFO [train.py:715] (3/8) Epoch 6, batch 4700, loss[loss=0.1662, simple_loss=0.2462, pruned_loss=0.04314, over 4882.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03961, over 971258.81 frames.], batch size: 22, lr: 3.42e-04
+2022-05-05 11:13:01,630 INFO [train.py:715] (3/8) Epoch 6, batch 4750, loss[loss=0.1458, simple_loss=0.2266, pruned_loss=0.0325, over 4901.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2201, pruned_loss=0.03944, over 971284.43 frames.], batch size: 19, lr: 3.42e-04
+2022-05-05 11:13:40,646 INFO [train.py:715] (3/8) Epoch 6, batch 4800, loss[loss=0.1434, simple_loss=0.2178, pruned_loss=0.03451, over 4924.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2193, pruned_loss=0.03908, over 971348.13 frames.], batch size: 23, lr: 3.42e-04
+2022-05-05 11:14:19,739 INFO [train.py:715] (3/8) Epoch 6, batch 4850, loss[loss=0.1873, simple_loss=0.2512, pruned_loss=0.06171, over 4853.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2201, pruned_loss=0.03939, over 971997.26 frames.], batch size: 32, lr: 3.42e-04
+2022-05-05 11:14:58,284 INFO [train.py:715] (3/8) Epoch 6, batch 4900, loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03542, over 4946.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2207, pruned_loss=0.03972, over 971666.85 frames.], batch size: 29, lr: 3.42e-04
+2022-05-05 11:15:37,163 INFO [train.py:715] (3/8) Epoch 6, batch 4950, loss[loss=0.1374, simple_loss=0.2157, pruned_loss=0.02955, over 4762.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2209, pruned_loss=0.04001, over 971790.05 frames.], batch size: 19, lr: 3.42e-04
+2022-05-05 11:16:16,919 INFO [train.py:715] (3/8) Epoch 6, batch 5000, loss[loss=0.1432, simple_loss=0.222, pruned_loss=0.03223, over 4883.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2212, pruned_loss=0.03993, over 971596.29 frames.], batch size: 19, lr: 3.42e-04
+2022-05-05 11:16:55,991 INFO [train.py:715] (3/8) Epoch 6, batch 5050, loss[loss=0.1589, simple_loss=0.224, pruned_loss=0.04683, over 4636.00 frames.], tot_loss[loss=0.1505, simple_loss=0.221, pruned_loss=0.03995, over 971108.84 frames.], batch size: 13, lr: 3.42e-04
+2022-05-05 11:17:34,331 INFO [train.py:715] (3/8) Epoch 6, batch 5100, loss[loss=0.1431, simple_loss=0.2108, pruned_loss=0.03773, over 4793.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2199, pruned_loss=0.03921, over 971988.40 frames.], batch size: 21, lr: 3.42e-04
+2022-05-05 11:18:13,254 INFO [train.py:715] (3/8) Epoch 6, batch 5150, loss[loss=0.1355, simple_loss=0.2147, pruned_loss=0.02813, over 4912.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2198, pruned_loss=0.03889, over 971981.11 frames.], batch size: 19, lr: 3.41e-04
+2022-05-05 11:18:52,359 INFO [train.py:715] (3/8) Epoch 6, batch 5200, loss[loss=0.1309, simple_loss=0.2021, pruned_loss=0.02983, over 4933.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2197, pruned_loss=0.03848, over 972033.48 frames.], batch size: 23, lr: 3.41e-04
+2022-05-05 11:19:30,492 INFO [train.py:715] (3/8) Epoch 6, batch 5250, loss[loss=0.1226, simple_loss=0.2022, pruned_loss=0.02145, over 4743.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03839, over 971900.94 frames.], batch size: 16, lr: 3.41e-04
+2022-05-05 11:20:09,575 INFO [train.py:715] (3/8) Epoch 6, batch 5300, loss[loss=0.1121, simple_loss=0.1919, pruned_loss=0.0161, over 4785.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03882, over 971773.24 frames.], batch size: 17, lr: 3.41e-04
+2022-05-05 11:20:48,894 INFO [train.py:715] (3/8) Epoch 6, batch 5350, loss[loss=0.1443, simple_loss=0.2263, pruned_loss=0.03119, over 4821.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.03856, over 972552.06 frames.], batch size: 13, lr: 3.41e-04
+2022-05-05 11:21:27,965 INFO [train.py:715] (3/8) Epoch 6, batch 5400, loss[loss=0.1417, simple_loss=0.2102, pruned_loss=0.03663, over 4700.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2205, pruned_loss=0.03929, over 972063.04 frames.], batch size: 15, lr: 3.41e-04
+2022-05-05 11:22:06,519 INFO [train.py:715] (3/8) Epoch 6, batch 5450, loss[loss=0.1611, simple_loss=0.2308, pruned_loss=0.04568, over 4738.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2213, pruned_loss=0.03961, over 972383.40 frames.], batch size: 16, lr: 3.41e-04
+2022-05-05 11:22:45,316 INFO [train.py:715] (3/8) Epoch 6, batch 5500, loss[loss=0.1378, simple_loss=0.2056, pruned_loss=0.03496, over 4905.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2216, pruned_loss=0.03955, over 971441.46 frames.], batch size: 17, lr: 3.41e-04
+2022-05-05 11:23:24,191 INFO [train.py:715] (3/8) Epoch 6, batch 5550, loss[loss=0.1415, simple_loss=0.221, pruned_loss=0.03099, over 4696.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2214, pruned_loss=0.03984, over 971541.91 frames.], batch size: 15, lr: 3.41e-04
+2022-05-05 11:24:02,781 INFO [train.py:715] (3/8) Epoch 6, batch 5600, loss[loss=0.1853, simple_loss=0.2456, pruned_loss=0.06255, over 4862.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.03977, over 972744.13 frames.], batch size: 38, lr: 3.41e-04
+2022-05-05 11:24:42,273 INFO [train.py:715] (3/8) Epoch 6, batch 5650, loss[loss=0.1468, simple_loss=0.2155, pruned_loss=0.0391, over 4801.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03934, over 972802.44 frames.], batch size: 21, lr: 3.41e-04
+2022-05-05 11:25:21,625 INFO [train.py:715] (3/8) Epoch 6, batch 5700, loss[loss=0.1879, simple_loss=0.2539, pruned_loss=0.06094, over 4913.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.03931, over 973196.97 frames.], batch size: 39, lr: 3.41e-04
+2022-05-05 11:26:00,241 INFO [train.py:715] (3/8) Epoch 6, batch 5750, loss[loss=0.1765, simple_loss=0.2381, pruned_loss=0.05748, over 4985.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.0395, over 973763.97 frames.], batch size: 14, lr: 3.41e-04
+2022-05-05 11:26:38,644 INFO [train.py:715] (3/8) Epoch 6, batch 5800, loss[loss=0.1487, simple_loss=0.2218, pruned_loss=0.03778, over 4928.00 frames.], tot_loss[loss=0.15, simple_loss=0.2209, pruned_loss=0.03956, over 973606.59 frames.], batch size: 35, lr: 3.41e-04
+2022-05-05 11:27:17,535 INFO [train.py:715] (3/8) Epoch 6, batch 5850, loss[loss=0.1627, simple_loss=0.2307, pruned_loss=0.04738, over 4936.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03971, over 972601.49 frames.], batch size: 29, lr: 3.41e-04
+2022-05-05 11:27:56,993 INFO [train.py:715] (3/8) Epoch 6, batch 5900, loss[loss=0.1424, simple_loss=0.2226, pruned_loss=0.03109, over 4842.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2208, pruned_loss=0.03951, over 971997.90 frames.], batch size: 25, lr: 3.41e-04
+2022-05-05 11:28:34,909 INFO [train.py:715] (3/8) Epoch 6, batch 5950, loss[loss=0.1361, simple_loss=0.2128, pruned_loss=0.02967, over 4769.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2211, pruned_loss=0.03997, over 972242.06 frames.], batch size: 19, lr: 3.41e-04
+2022-05-05 11:29:14,284 INFO [train.py:715] (3/8) Epoch 6, batch 6000, loss[loss=0.1685, simple_loss=0.2255, pruned_loss=0.05573, over 4752.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2208, pruned_loss=0.04003, over 972284.89 frames.], batch size: 16, lr: 3.41e-04
+2022-05-05 11:29:14,285 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 11:29:24,854 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1095, simple_loss=0.1945, pruned_loss=0.01229, over 914524.00 frames.
+2022-05-05 11:30:04,468 INFO [train.py:715] (3/8) Epoch 6, batch 6050, loss[loss=0.149, simple_loss=0.229, pruned_loss=0.03452, over 4973.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2206, pruned_loss=0.03992, over 972439.36 frames.], batch size: 28, lr: 3.41e-04
+2022-05-05 11:30:43,727 INFO [train.py:715] (3/8) Epoch 6, batch 6100, loss[loss=0.1553, simple_loss=0.2219, pruned_loss=0.04431, over 4815.00 frames.], tot_loss[loss=0.151, simple_loss=0.2215, pruned_loss=0.04029, over 972471.21 frames.], batch size: 26, lr: 3.41e-04
+2022-05-05 11:31:23,120 INFO [train.py:715] (3/8) Epoch 6, batch 6150, loss[loss=0.1462, simple_loss=0.2182, pruned_loss=0.03713, over 4845.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2216, pruned_loss=0.04045, over 972577.41 frames.], batch size: 15, lr: 3.41e-04
+2022-05-05 11:32:01,618 INFO [train.py:715] (3/8) Epoch 6, batch 6200, loss[loss=0.1646, simple_loss=0.2309, pruned_loss=0.04918, over 4982.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2217, pruned_loss=0.04064, over 972919.97 frames.], batch size: 15, lr: 3.41e-04
+2022-05-05 11:32:40,935 INFO [train.py:715] (3/8) Epoch 6, batch 6250, loss[loss=0.1103, simple_loss=0.1828, pruned_loss=0.01888, over 4799.00 frames.], tot_loss[loss=0.1505, simple_loss=0.221, pruned_loss=0.04003, over 973130.49 frames.], batch size: 12, lr: 3.41e-04
+2022-05-05 11:33:20,233 INFO [train.py:715] (3/8) Epoch 6, batch 6300, loss[loss=0.1509, simple_loss=0.2236, pruned_loss=0.03915, over 4870.00 frames.], tot_loss[loss=0.15, simple_loss=0.22, pruned_loss=0.03999, over 973131.63 frames.], batch size: 32, lr: 3.41e-04
+2022-05-05 11:33:58,706 INFO [train.py:715] (3/8) Epoch 6, batch 6350, loss[loss=0.1394, simple_loss=0.2165, pruned_loss=0.03115, over 4828.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2197, pruned_loss=0.03937, over 972360.73 frames.], batch size: 26, lr: 3.41e-04
+2022-05-05 11:34:37,341 INFO [train.py:715] (3/8) Epoch 6, batch 6400, loss[loss=0.157, simple_loss=0.2187, pruned_loss=0.04769, over 4789.00 frames.], tot_loss[loss=0.1497, simple_loss=0.22, pruned_loss=0.03966, over 972804.13 frames.], batch size: 18, lr: 3.40e-04
+2022-05-05 11:35:16,568 INFO [train.py:715] (3/8) Epoch 6, batch 6450, loss[loss=0.1319, simple_loss=0.2023, pruned_loss=0.0307, over 4921.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2213, pruned_loss=0.04008, over 972496.86 frames.], batch size: 19, lr: 3.40e-04
+2022-05-05 11:35:55,386 INFO [train.py:715] (3/8) Epoch 6, batch 6500, loss[loss=0.1462, simple_loss=0.2217, pruned_loss=0.03529, over 4976.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2213, pruned_loss=0.03992, over 972728.66 frames.], batch size: 28, lr: 3.40e-04
+2022-05-05 11:36:33,968 INFO [train.py:715] (3/8) Epoch 6, batch 6550, loss[loss=0.1363, simple_loss=0.2172, pruned_loss=0.02765, over 4984.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2204, pruned_loss=0.03932, over 973516.96 frames.], batch size: 25, lr: 3.40e-04
+2022-05-05 11:37:12,775 INFO [train.py:715] (3/8) Epoch 6, batch 6600, loss[loss=0.1485, simple_loss=0.226, pruned_loss=0.03551, over 4932.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2207, pruned_loss=0.03951, over 973558.59 frames.], batch size: 29, lr: 3.40e-04
+2022-05-05 11:37:52,973 INFO [train.py:715] (3/8) Epoch 6, batch 6650, loss[loss=0.1163, simple_loss=0.184, pruned_loss=0.02427, over 4775.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2208, pruned_loss=0.03912, over 973484.33 frames.], batch size: 17, lr: 3.40e-04
+2022-05-05 11:38:31,785 INFO [train.py:715] (3/8) Epoch 6, batch 6700, loss[loss=0.1328, simple_loss=0.2059, pruned_loss=0.02986, over 4951.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2201, pruned_loss=0.03859, over 972856.20 frames.], batch size: 35, lr: 3.40e-04
+2022-05-05 11:39:10,520 INFO [train.py:715] (3/8) Epoch 6, batch 6750, loss[loss=0.149, simple_loss=0.2103, pruned_loss=0.04384, over 4821.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2205, pruned_loss=0.03895, over 973161.51 frames.], batch size: 26, lr: 3.40e-04
+2022-05-05 11:39:49,805 INFO [train.py:715] (3/8) Epoch 6, batch 6800, loss[loss=0.1218, simple_loss=0.2019, pruned_loss=0.02088, over 4772.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03894, over 972317.16 frames.], batch size: 18, lr: 3.40e-04
+2022-05-05 11:40:28,790 INFO [train.py:715] (3/8) Epoch 6, batch 6850, loss[loss=0.1522, simple_loss=0.2121, pruned_loss=0.04615, over 4856.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2192, pruned_loss=0.03832, over 972481.52 frames.], batch size: 32, lr: 3.40e-04
+2022-05-05 11:41:06,841 INFO [train.py:715] (3/8) Epoch 6, batch 6900, loss[loss=0.1723, simple_loss=0.2441, pruned_loss=0.05026, over 4834.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2193, pruned_loss=0.03822, over 972771.23 frames.], batch size: 30, lr: 3.40e-04
+2022-05-05 11:41:45,913 INFO [train.py:715] (3/8) Epoch 6, batch 6950, loss[loss=0.1637, simple_loss=0.2304, pruned_loss=0.0485, over 4980.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2196, pruned_loss=0.03874, over 973246.13 frames.], batch size: 35, lr: 3.40e-04
+2022-05-05 11:42:25,620 INFO [train.py:715] (3/8) Epoch 6, batch 7000, loss[loss=0.1466, simple_loss=0.215, pruned_loss=0.03909, over 4697.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2196, pruned_loss=0.03869, over 972101.17 frames.], batch size: 15, lr: 3.40e-04
+2022-05-05 11:43:04,218 INFO [train.py:715] (3/8) Epoch 6, batch 7050, loss[loss=0.1544, simple_loss=0.221, pruned_loss=0.04392, over 4757.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03851, over 971660.98 frames.], batch size: 19, lr: 3.40e-04
+2022-05-05 11:43:42,732 INFO [train.py:715] (3/8) Epoch 6, batch 7100, loss[loss=0.1344, simple_loss=0.2185, pruned_loss=0.02519, over 4800.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2203, pruned_loss=0.03903, over 972629.67 frames.], batch size: 25, lr: 3.40e-04
+2022-05-05 11:44:25,533 INFO [train.py:715] (3/8) Epoch 6, batch 7150, loss[loss=0.1671, simple_loss=0.2349, pruned_loss=0.04968, over 4765.00 frames.], tot_loss[loss=0.149, simple_loss=0.2198, pruned_loss=0.03906, over 972689.22 frames.], batch size: 14, lr: 3.40e-04
+2022-05-05 11:45:04,231 INFO [train.py:715] (3/8) Epoch 6, batch 7200, loss[loss=0.1585, simple_loss=0.2221, pruned_loss=0.04742, over 4853.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2204, pruned_loss=0.03911, over 972361.39 frames.], batch size: 20, lr: 3.40e-04
+2022-05-05 11:45:42,697 INFO [train.py:715] (3/8) Epoch 6, batch 7250, loss[loss=0.1518, simple_loss=0.2302, pruned_loss=0.03667, over 4750.00 frames.], tot_loss[loss=0.149, simple_loss=0.2201, pruned_loss=0.03898, over 972912.94 frames.], batch size: 16, lr: 3.40e-04
+2022-05-05 11:46:21,449 INFO [train.py:715] (3/8) Epoch 6, batch 7300, loss[loss=0.1438, simple_loss=0.2141, pruned_loss=0.0367, over 4911.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03929, over 972617.21 frames.], batch size: 17, lr: 3.40e-04
+2022-05-05 11:47:01,051 INFO [train.py:715] (3/8) Epoch 6, batch 7350, loss[loss=0.1578, simple_loss=0.2207, pruned_loss=0.04742, over 4894.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2209, pruned_loss=0.03919, over 973560.14 frames.], batch size: 17, lr: 3.40e-04
+2022-05-05 11:47:38,861 INFO [train.py:715] (3/8) Epoch 6, batch 7400, loss[loss=0.1515, simple_loss=0.2259, pruned_loss=0.03858, over 4867.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2204, pruned_loss=0.03912, over 973450.25 frames.], batch size: 22, lr: 3.40e-04
+2022-05-05 11:48:18,378 INFO [train.py:715] (3/8) Epoch 6, batch 7450, loss[loss=0.1795, simple_loss=0.2385, pruned_loss=0.06024, over 4972.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.03929, over 973250.93 frames.], batch size: 15, lr: 3.40e-04
+2022-05-05 11:48:56,992 INFO [train.py:715] (3/8) Epoch 6, batch 7500, loss[loss=0.1422, simple_loss=0.2105, pruned_loss=0.03691, over 4986.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2212, pruned_loss=0.03953, over 972801.98 frames.], batch size: 31, lr: 3.40e-04
+2022-05-05 11:49:35,694 INFO [train.py:715] (3/8) Epoch 6, batch 7550, loss[loss=0.1387, simple_loss=0.2154, pruned_loss=0.031, over 4785.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2212, pruned_loss=0.03954, over 972281.61 frames.], batch size: 17, lr: 3.40e-04
+2022-05-05 11:50:14,634 INFO [train.py:715] (3/8) Epoch 6, batch 7600, loss[loss=0.1412, simple_loss=0.217, pruned_loss=0.03268, over 4685.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.03964, over 971564.20 frames.], batch size: 15, lr: 3.40e-04
+2022-05-05 11:50:53,762 INFO [train.py:715] (3/8) Epoch 6, batch 7650, loss[loss=0.142, simple_loss=0.2089, pruned_loss=0.03754, over 4805.00 frames.], tot_loss[loss=0.151, simple_loss=0.2218, pruned_loss=0.04011, over 971471.53 frames.], batch size: 21, lr: 3.40e-04
+2022-05-05 11:51:33,382 INFO [train.py:715] (3/8) Epoch 6, batch 7700, loss[loss=0.1655, simple_loss=0.2276, pruned_loss=0.05172, over 4983.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2211, pruned_loss=0.03969, over 971050.60 frames.], batch size: 35, lr: 3.39e-04
+2022-05-05 11:52:11,590 INFO [train.py:715] (3/8) Epoch 6, batch 7750, loss[loss=0.1645, simple_loss=0.228, pruned_loss=0.05048, over 4973.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2214, pruned_loss=0.04, over 972437.42 frames.], batch size: 39, lr: 3.39e-04
+2022-05-05 11:52:51,084 INFO [train.py:715] (3/8) Epoch 6, batch 7800, loss[loss=0.1656, simple_loss=0.2278, pruned_loss=0.05164, over 4923.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2208, pruned_loss=0.03992, over 972527.60 frames.], batch size: 39, lr: 3.39e-04
+2022-05-05 11:53:30,018 INFO [train.py:715] (3/8) Epoch 6, batch 7850, loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.0293, over 4806.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2211, pruned_loss=0.03999, over 973215.70 frames.], batch size: 13, lr: 3.39e-04
+2022-05-05 11:54:08,585 INFO [train.py:715] (3/8) Epoch 6, batch 7900, loss[loss=0.1942, simple_loss=0.2674, pruned_loss=0.06053, over 4789.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2224, pruned_loss=0.04011, over 972648.61 frames.], batch size: 18, lr: 3.39e-04
+2022-05-05 11:54:47,342 INFO [train.py:715] (3/8) Epoch 6, batch 7950, loss[loss=0.1439, simple_loss=0.2152, pruned_loss=0.03629, over 4888.00 frames.], tot_loss[loss=0.1504, simple_loss=0.222, pruned_loss=0.03945, over 972725.73 frames.], batch size: 16, lr: 3.39e-04
+2022-05-05 11:55:26,523 INFO [train.py:715] (3/8) Epoch 6, batch 8000, loss[loss=0.1292, simple_loss=0.2018, pruned_loss=0.02828, over 4941.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2213, pruned_loss=0.03925, over 972850.90 frames.], batch size: 21, lr: 3.39e-04
+2022-05-05 11:56:05,893 INFO [train.py:715] (3/8) Epoch 6, batch 8050, loss[loss=0.1389, simple_loss=0.2053, pruned_loss=0.03631, over 4643.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2214, pruned_loss=0.03939, over 971898.47 frames.], batch size: 13, lr: 3.39e-04
+2022-05-05 11:56:43,894 INFO [train.py:715] (3/8) Epoch 6, batch 8100, loss[loss=0.1331, simple_loss=0.2172, pruned_loss=0.02456, over 4962.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2204, pruned_loss=0.03895, over 971701.90 frames.], batch size: 24, lr: 3.39e-04
+2022-05-05 11:57:22,884 INFO [train.py:715] (3/8) Epoch 6, batch 8150, loss[loss=0.1958, simple_loss=0.2535, pruned_loss=0.06903, over 4912.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2207, pruned_loss=0.03899, over 971385.73 frames.], batch size: 17, lr: 3.39e-04
+2022-05-05 11:58:01,957 INFO [train.py:715] (3/8) Epoch 6, batch 8200, loss[loss=0.1731, simple_loss=0.2424, pruned_loss=0.05189, over 4703.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2211, pruned_loss=0.03896, over 972111.32 frames.], batch size: 15, lr: 3.39e-04
+2022-05-05 11:58:41,277 INFO [train.py:715] (3/8) Epoch 6, batch 8250, loss[loss=0.1468, simple_loss=0.2266, pruned_loss=0.03353, over 4703.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2208, pruned_loss=0.03893, over 971220.67 frames.], batch size: 15, lr: 3.39e-04
+2022-05-05 11:59:19,579 INFO [train.py:715] (3/8) Epoch 6, batch 8300, loss[loss=0.1417, simple_loss=0.2129, pruned_loss=0.03519, over 4838.00 frames.], tot_loss[loss=0.1496, simple_loss=0.221, pruned_loss=0.03911, over 972206.64 frames.], batch size: 27, lr: 3.39e-04
+2022-05-05 11:59:58,760 INFO [train.py:715] (3/8) Epoch 6, batch 8350, loss[loss=0.1437, simple_loss=0.2202, pruned_loss=0.0336, over 4841.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2216, pruned_loss=0.03931, over 973020.18 frames.], batch size: 13, lr: 3.39e-04
+2022-05-05 12:00:37,620 INFO [train.py:715] (3/8) Epoch 6, batch 8400, loss[loss=0.1463, simple_loss=0.2236, pruned_loss=0.03445, over 4763.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2219, pruned_loss=0.03964, over 972758.62 frames.], batch size: 19, lr: 3.39e-04
+2022-05-05 12:01:15,842 INFO [train.py:715] (3/8) Epoch 6, batch 8450, loss[loss=0.1172, simple_loss=0.1917, pruned_loss=0.02137, over 4757.00 frames.], tot_loss[loss=0.15, simple_loss=0.2212, pruned_loss=0.03942, over 972416.14 frames.], batch size: 12, lr: 3.39e-04
+2022-05-05 12:01:54,985 INFO [train.py:715] (3/8) Epoch 6, batch 8500, loss[loss=0.1214, simple_loss=0.1958, pruned_loss=0.0235, over 4902.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03971, over 972236.55 frames.], batch size: 19, lr: 3.39e-04
+2022-05-05 12:02:33,548 INFO [train.py:715] (3/8) Epoch 6, batch 8550, loss[loss=0.1375, simple_loss=0.2151, pruned_loss=0.02993, over 4917.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2212, pruned_loss=0.03977, over 972903.38 frames.], batch size: 18, lr: 3.39e-04
+2022-05-05 12:03:12,440 INFO [train.py:715] (3/8) Epoch 6, batch 8600, loss[loss=0.1491, simple_loss=0.2174, pruned_loss=0.04038, over 4892.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.03956, over 972577.93 frames.], batch size: 19, lr: 3.39e-04
+2022-05-05 12:03:50,309 INFO [train.py:715] (3/8) Epoch 6, batch 8650, loss[loss=0.1709, simple_loss=0.2441, pruned_loss=0.04887, over 4975.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2213, pruned_loss=0.03968, over 973664.65 frames.], batch size: 15, lr: 3.39e-04
+2022-05-05 12:04:29,735 INFO [train.py:715] (3/8) Epoch 6, batch 8700, loss[loss=0.1314, simple_loss=0.2011, pruned_loss=0.03086, over 4962.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2215, pruned_loss=0.03983, over 973597.32 frames.], batch size: 14, lr: 3.39e-04
+2022-05-05 12:05:08,432 INFO [train.py:715] (3/8) Epoch 6, batch 8750, loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03056, over 4761.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2209, pruned_loss=0.03914, over 973224.73 frames.], batch size: 16, lr: 3.39e-04
+2022-05-05 12:05:46,862 INFO [train.py:715] (3/8) Epoch 6, batch 8800, loss[loss=0.1877, simple_loss=0.2509, pruned_loss=0.0622, over 4865.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2207, pruned_loss=0.03892, over 973563.72 frames.], batch size: 32, lr: 3.39e-04
+2022-05-05 12:06:25,683 INFO [train.py:715] (3/8) Epoch 6, batch 8850, loss[loss=0.1664, simple_loss=0.2454, pruned_loss=0.04371, over 4779.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2207, pruned_loss=0.03948, over 973409.74 frames.], batch size: 18, lr: 3.39e-04
+2022-05-05 12:07:04,757 INFO [train.py:715] (3/8) Epoch 6, batch 8900, loss[loss=0.1516, simple_loss=0.2245, pruned_loss=0.03929, over 4911.00 frames.], tot_loss[loss=0.1498, simple_loss=0.221, pruned_loss=0.03926, over 973285.37 frames.], batch size: 17, lr: 3.39e-04
+2022-05-05 12:07:43,995 INFO [train.py:715] (3/8) Epoch 6, batch 8950, loss[loss=0.1758, simple_loss=0.2444, pruned_loss=0.05355, over 4922.00 frames.], tot_loss[loss=0.151, simple_loss=0.2224, pruned_loss=0.03976, over 973256.70 frames.], batch size: 39, lr: 3.38e-04
+2022-05-05 12:08:22,492 INFO [train.py:715] (3/8) Epoch 6, batch 9000, loss[loss=0.1377, simple_loss=0.2176, pruned_loss=0.02893, over 4805.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2218, pruned_loss=0.03982, over 973271.62 frames.], batch size: 24, lr: 3.38e-04
+2022-05-05 12:08:22,493 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 12:08:35,890 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1094, simple_loss=0.1946, pruned_loss=0.01213, over 914524.00 frames.
+2022-05-05 12:09:14,898 INFO [train.py:715] (3/8) Epoch 6, batch 9050, loss[loss=0.1542, simple_loss=0.2199, pruned_loss=0.0443, over 4782.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2219, pruned_loss=0.03978, over 973450.06 frames.], batch size: 17, lr: 3.38e-04
+2022-05-05 12:09:53,936 INFO [train.py:715] (3/8) Epoch 6, batch 9100, loss[loss=0.156, simple_loss=0.2192, pruned_loss=0.04637, over 4847.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2217, pruned_loss=0.03981, over 972904.14 frames.], batch size: 20, lr: 3.38e-04
+2022-05-05 12:10:33,369 INFO [train.py:715] (3/8) Epoch 6, batch 9150, loss[loss=0.1756, simple_loss=0.2516, pruned_loss=0.04982, over 4776.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04045, over 972937.75 frames.], batch size: 18, lr: 3.38e-04
+2022-05-05 12:11:11,396 INFO [train.py:715] (3/8) Epoch 6, batch 9200, loss[loss=0.1515, simple_loss=0.2326, pruned_loss=0.03517, over 4979.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2221, pruned_loss=0.03978, over 972731.31 frames.], batch size: 25, lr: 3.38e-04
+2022-05-05 12:11:50,804 INFO [train.py:715] (3/8) Epoch 6, batch 9250, loss[loss=0.132, simple_loss=0.2095, pruned_loss=0.0273, over 4810.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2222, pruned_loss=0.03998, over 972553.31 frames.], batch size: 21, lr: 3.38e-04
+2022-05-05 12:12:29,885 INFO [train.py:715] (3/8) Epoch 6, batch 9300, loss[loss=0.1709, simple_loss=0.2384, pruned_loss=0.05171, over 4702.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2222, pruned_loss=0.04, over 972041.13 frames.], batch size: 15, lr: 3.38e-04
+2022-05-05 12:13:08,404 INFO [train.py:715] (3/8) Epoch 6, batch 9350, loss[loss=0.1366, simple_loss=0.2136, pruned_loss=0.02985, over 4926.00 frames.], tot_loss[loss=0.1508, simple_loss=0.222, pruned_loss=0.03981, over 972135.81 frames.], batch size: 17, lr: 3.38e-04
+2022-05-05 12:13:47,632 INFO [train.py:715] (3/8) Epoch 6, batch 9400, loss[loss=0.1572, simple_loss=0.226, pruned_loss=0.04422, over 4774.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2226, pruned_loss=0.04019, over 973139.69 frames.], batch size: 19, lr: 3.38e-04
+2022-05-05 12:14:26,441 INFO [train.py:715] (3/8) Epoch 6, batch 9450, loss[loss=0.1652, simple_loss=0.235, pruned_loss=0.0477, over 4841.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2214, pruned_loss=0.03955, over 973826.81 frames.], batch size: 34, lr: 3.38e-04
+2022-05-05 12:15:05,764 INFO [train.py:715] (3/8) Epoch 6, batch 9500, loss[loss=0.1614, simple_loss=0.2331, pruned_loss=0.04482, over 4850.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.03957, over 972978.11 frames.], batch size: 30, lr: 3.38e-04
+2022-05-05 12:15:44,435 INFO [train.py:715] (3/8) Epoch 6, batch 9550, loss[loss=0.1265, simple_loss=0.207, pruned_loss=0.02297, over 4925.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.03933, over 972247.58 frames.], batch size: 29, lr: 3.38e-04
+2022-05-05 12:16:23,402 INFO [train.py:715] (3/8) Epoch 6, batch 9600, loss[loss=0.1578, simple_loss=0.2361, pruned_loss=0.03982, over 4803.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2211, pruned_loss=0.03929, over 971708.87 frames.], batch size: 25, lr: 3.38e-04
+2022-05-05 12:17:02,129 INFO [train.py:715] (3/8) Epoch 6, batch 9650, loss[loss=0.1483, simple_loss=0.2228, pruned_loss=0.03692, over 4797.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2207, pruned_loss=0.03879, over 971962.92 frames.], batch size: 25, lr: 3.38e-04
+2022-05-05 12:17:40,455 INFO [train.py:715] (3/8) Epoch 6, batch 9700, loss[loss=0.1457, simple_loss=0.221, pruned_loss=0.03519, over 4793.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2203, pruned_loss=0.03878, over 973051.82 frames.], batch size: 18, lr: 3.38e-04
+2022-05-05 12:18:19,757 INFO [train.py:715] (3/8) Epoch 6, batch 9750, loss[loss=0.1521, simple_loss=0.2244, pruned_loss=0.03988, over 4801.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2209, pruned_loss=0.03922, over 972613.27 frames.], batch size: 21, lr: 3.38e-04
+2022-05-05 12:18:59,480 INFO [train.py:715] (3/8) Epoch 6, batch 9800, loss[loss=0.1755, simple_loss=0.2501, pruned_loss=0.05045, over 4896.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2214, pruned_loss=0.03956, over 972958.30 frames.], batch size: 17, lr: 3.38e-04
+2022-05-05 12:19:39,849 INFO [train.py:715] (3/8) Epoch 6, batch 9850, loss[loss=0.1341, simple_loss=0.2138, pruned_loss=0.02721, over 4886.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2219, pruned_loss=0.03993, over 972803.08 frames.], batch size: 22, lr: 3.38e-04
+2022-05-05 12:20:18,999 INFO [train.py:715] (3/8) Epoch 6, batch 9900, loss[loss=0.1812, simple_loss=0.2527, pruned_loss=0.05485, over 4960.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.03961, over 973559.00 frames.], batch size: 14, lr: 3.38e-04
+2022-05-05 12:20:59,137 INFO [train.py:715] (3/8) Epoch 6, batch 9950, loss[loss=0.1397, simple_loss=0.2043, pruned_loss=0.03755, over 4883.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2215, pruned_loss=0.03966, over 973241.80 frames.], batch size: 22, lr: 3.38e-04
+2022-05-05 12:21:39,158 INFO [train.py:715] (3/8) Epoch 6, batch 10000, loss[loss=0.149, simple_loss=0.2169, pruned_loss=0.04049, over 4954.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2204, pruned_loss=0.03895, over 973442.62 frames.], batch size: 24, lr: 3.38e-04
+2022-05-05 12:22:17,403 INFO [train.py:715] (3/8) Epoch 6, batch 10050, loss[loss=0.1874, simple_loss=0.2403, pruned_loss=0.06728, over 4947.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03895, over 974081.48 frames.], batch size: 29, lr: 3.38e-04
+2022-05-05 12:22:56,775 INFO [train.py:715] (3/8) Epoch 6, batch 10100, loss[loss=0.1933, simple_loss=0.2474, pruned_loss=0.06961, over 4896.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2199, pruned_loss=0.03895, over 973616.73 frames.], batch size: 17, lr: 3.38e-04
+2022-05-05 12:23:34,993 INFO [train.py:715] (3/8) Epoch 6, batch 10150, loss[loss=0.1194, simple_loss=0.184, pruned_loss=0.02745, over 4769.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2198, pruned_loss=0.03919, over 974026.34 frames.], batch size: 12, lr: 3.38e-04
+2022-05-05 12:24:14,031 INFO [train.py:715] (3/8) Epoch 6, batch 10200, loss[loss=0.1367, simple_loss=0.2, pruned_loss=0.03671, over 4990.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2201, pruned_loss=0.03917, over 973996.56 frames.], batch size: 14, lr: 3.38e-04
+2022-05-05 12:24:52,553 INFO [train.py:715] (3/8) Epoch 6, batch 10250, loss[loss=0.1586, simple_loss=0.2327, pruned_loss=0.04228, over 4822.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2196, pruned_loss=0.03835, over 974151.69 frames.], batch size: 27, lr: 3.37e-04
+2022-05-05 12:25:31,642 INFO [train.py:715] (3/8) Epoch 6, batch 10300, loss[loss=0.1311, simple_loss=0.209, pruned_loss=0.02654, over 4894.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2196, pruned_loss=0.03866, over 973269.68 frames.], batch size: 22, lr: 3.37e-04
+2022-05-05 12:26:10,142 INFO [train.py:715] (3/8) Epoch 6, batch 10350, loss[loss=0.1764, simple_loss=0.2464, pruned_loss=0.05322, over 4898.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2192, pruned_loss=0.03859, over 972441.55 frames.], batch size: 22, lr: 3.37e-04
+2022-05-05 12:26:49,278 INFO [train.py:715] (3/8) Epoch 6, batch 10400, loss[loss=0.1363, simple_loss=0.2069, pruned_loss=0.03282, over 4818.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2197, pruned_loss=0.03874, over 972161.44 frames.], batch size: 13, lr: 3.37e-04
+2022-05-05 12:27:27,709 INFO [train.py:715] (3/8) Epoch 6, batch 10450, loss[loss=0.1296, simple_loss=0.2112, pruned_loss=0.02401, over 4956.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2201, pruned_loss=0.0388, over 972477.29 frames.], batch size: 24, lr: 3.37e-04
+2022-05-05 12:28:06,362 INFO [train.py:715] (3/8) Epoch 6, batch 10500, loss[loss=0.1854, simple_loss=0.2538, pruned_loss=0.05851, over 4759.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2204, pruned_loss=0.03925, over 971801.21 frames.], batch size: 16, lr: 3.37e-04
+2022-05-05 12:28:45,430 INFO [train.py:715] (3/8) Epoch 6, batch 10550, loss[loss=0.12, simple_loss=0.1995, pruned_loss=0.02028, over 4947.00 frames.], tot_loss[loss=0.149, simple_loss=0.22, pruned_loss=0.03904, over 972102.31 frames.], batch size: 21, lr: 3.37e-04
+2022-05-05 12:29:23,699 INFO [train.py:715] (3/8) Epoch 6, batch 10600, loss[loss=0.1804, simple_loss=0.2551, pruned_loss=0.05291, over 4787.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03876, over 972407.49 frames.], batch size: 17, lr: 3.37e-04
+2022-05-05 12:30:02,909 INFO [train.py:715] (3/8) Epoch 6, batch 10650, loss[loss=0.1289, simple_loss=0.211, pruned_loss=0.02337, over 4951.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2199, pruned_loss=0.03886, over 972100.49 frames.], batch size: 21, lr: 3.37e-04
+2022-05-05 12:30:41,619 INFO [train.py:715] (3/8) Epoch 6, batch 10700, loss[loss=0.1299, simple_loss=0.2174, pruned_loss=0.02119, over 4773.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2207, pruned_loss=0.03907, over 971901.54 frames.], batch size: 18, lr: 3.37e-04
+2022-05-05 12:31:20,570 INFO [train.py:715] (3/8) Epoch 6, batch 10750, loss[loss=0.1501, simple_loss=0.2198, pruned_loss=0.04018, over 4829.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.03863, over 971085.91 frames.], batch size: 15, lr: 3.37e-04
+2022-05-05 12:31:59,031 INFO [train.py:715] (3/8) Epoch 6, batch 10800, loss[loss=0.171, simple_loss=0.2397, pruned_loss=0.05122, over 4981.00 frames.], tot_loss[loss=0.149, simple_loss=0.2197, pruned_loss=0.03912, over 971754.29 frames.], batch size: 25, lr: 3.37e-04
+2022-05-05 12:32:37,567 INFO [train.py:715] (3/8) Epoch 6, batch 10850, loss[loss=0.1452, simple_loss=0.2085, pruned_loss=0.04098, over 4899.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2194, pruned_loss=0.03906, over 972176.33 frames.], batch size: 16, lr: 3.37e-04
+2022-05-05 12:33:15,994 INFO [train.py:715] (3/8) Epoch 6, batch 10900, loss[loss=0.1414, simple_loss=0.2224, pruned_loss=0.03015, over 4748.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2198, pruned_loss=0.03885, over 971615.46 frames.], batch size: 16, lr: 3.37e-04
+2022-05-05 12:33:54,114 INFO [train.py:715] (3/8) Epoch 6, batch 10950, loss[loss=0.1395, simple_loss=0.2194, pruned_loss=0.02977, over 4723.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2198, pruned_loss=0.03876, over 972191.92 frames.], batch size: 16, lr: 3.37e-04
+2022-05-05 12:34:33,266 INFO [train.py:715] (3/8) Epoch 6, batch 11000, loss[loss=0.1391, simple_loss=0.209, pruned_loss=0.03459, over 4876.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2199, pruned_loss=0.03871, over 972746.42 frames.], batch size: 20, lr: 3.37e-04
+2022-05-05 12:35:11,628 INFO [train.py:715] (3/8) Epoch 6, batch 11050, loss[loss=0.1496, simple_loss=0.2226, pruned_loss=0.03834, over 4698.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2207, pruned_loss=0.03921, over 972705.46 frames.], batch size: 15, lr: 3.37e-04
+2022-05-05 12:35:50,638 INFO [train.py:715] (3/8) Epoch 6, batch 11100, loss[loss=0.1641, simple_loss=0.2326, pruned_loss=0.0478, over 4933.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.03917, over 972598.01 frames.], batch size: 18, lr: 3.37e-04
+2022-05-05 12:36:29,028 INFO [train.py:715] (3/8) Epoch 6, batch 11150, loss[loss=0.1516, simple_loss=0.2326, pruned_loss=0.03532, over 4838.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2206, pruned_loss=0.03934, over 972100.13 frames.], batch size: 25, lr: 3.37e-04
+2022-05-05 12:37:07,407 INFO [train.py:715] (3/8) Epoch 6, batch 11200, loss[loss=0.1188, simple_loss=0.1921, pruned_loss=0.02272, over 4960.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2198, pruned_loss=0.03919, over 972241.85 frames.], batch size: 15, lr: 3.37e-04
+2022-05-05 12:37:45,842 INFO [train.py:715] (3/8) Epoch 6, batch 11250, loss[loss=0.1351, simple_loss=0.2068, pruned_loss=0.0317, over 4823.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2196, pruned_loss=0.03927, over 971650.04 frames.], batch size: 13, lr: 3.37e-04
+2022-05-05 12:38:24,403 INFO [train.py:715] (3/8) Epoch 6, batch 11300, loss[loss=0.1617, simple_loss=0.233, pruned_loss=0.04515, over 4745.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2186, pruned_loss=0.03877, over 971895.77 frames.], batch size: 16, lr: 3.37e-04
+2022-05-05 12:39:03,682 INFO [train.py:715] (3/8) Epoch 6, batch 11350, loss[loss=0.1535, simple_loss=0.2163, pruned_loss=0.04536, over 4914.00 frames.], tot_loss[loss=0.1484, simple_loss=0.219, pruned_loss=0.03888, over 971482.48 frames.], batch size: 18, lr: 3.37e-04
+2022-05-05 12:39:42,621 INFO [train.py:715] (3/8) Epoch 6, batch 11400, loss[loss=0.1979, simple_loss=0.263, pruned_loss=0.06637, over 4781.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2193, pruned_loss=0.03911, over 971626.53 frames.], batch size: 17, lr: 3.37e-04
+2022-05-05 12:40:21,683 INFO [train.py:715] (3/8) Epoch 6, batch 11450, loss[loss=0.1384, simple_loss=0.2063, pruned_loss=0.03525, over 4749.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2197, pruned_loss=0.03907, over 972430.11 frames.], batch size: 19, lr: 3.37e-04
+2022-05-05 12:40:59,949 INFO [train.py:715] (3/8) Epoch 6, batch 11500, loss[loss=0.1492, simple_loss=0.213, pruned_loss=0.04265, over 4947.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03879, over 972472.36 frames.], batch size: 21, lr: 3.37e-04
+2022-05-05 12:41:38,299 INFO [train.py:715] (3/8) Epoch 6, batch 11550, loss[loss=0.1191, simple_loss=0.2071, pruned_loss=0.01548, over 4830.00 frames.], tot_loss[loss=0.148, simple_loss=0.2191, pruned_loss=0.03843, over 972447.42 frames.], batch size: 27, lr: 3.36e-04
+2022-05-05 12:42:17,677 INFO [train.py:715] (3/8) Epoch 6, batch 11600, loss[loss=0.1621, simple_loss=0.2378, pruned_loss=0.04319, over 4873.00 frames.], tot_loss[loss=0.149, simple_loss=0.2203, pruned_loss=0.0389, over 972658.35 frames.], batch size: 22, lr: 3.36e-04
+2022-05-05 12:42:56,130 INFO [train.py:715] (3/8) Epoch 6, batch 11650, loss[loss=0.1683, simple_loss=0.2308, pruned_loss=0.05291, over 4922.00 frames.], tot_loss[loss=0.149, simple_loss=0.2201, pruned_loss=0.0389, over 972752.69 frames.], batch size: 23, lr: 3.36e-04
+2022-05-05 12:43:34,996 INFO [train.py:715] (3/8) Epoch 6, batch 11700, loss[loss=0.1464, simple_loss=0.2188, pruned_loss=0.03694, over 4699.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2202, pruned_loss=0.03904, over 972202.92 frames.], batch size: 15, lr: 3.36e-04
+2022-05-05 12:44:13,939 INFO [train.py:715] (3/8) Epoch 6, batch 11750, loss[loss=0.1554, simple_loss=0.2308, pruned_loss=0.04, over 4942.00 frames.], tot_loss[loss=0.15, simple_loss=0.2211, pruned_loss=0.03944, over 972073.87 frames.], batch size: 21, lr: 3.36e-04
+2022-05-05 12:44:53,168 INFO [train.py:715] (3/8) Epoch 6, batch 11800, loss[loss=0.1694, simple_loss=0.2338, pruned_loss=0.05254, over 4854.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2207, pruned_loss=0.03908, over 972294.84 frames.], batch size: 30, lr: 3.36e-04
+2022-05-05 12:45:31,848 INFO [train.py:715] (3/8) Epoch 6, batch 11850, loss[loss=0.1652, simple_loss=0.2397, pruned_loss=0.04533, over 4859.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2205, pruned_loss=0.03889, over 971800.53 frames.], batch size: 32, lr: 3.36e-04
+2022-05-05 12:46:10,417 INFO [train.py:715] (3/8) Epoch 6, batch 11900, loss[loss=0.1366, simple_loss=0.2034, pruned_loss=0.03492, over 4912.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2204, pruned_loss=0.03902, over 972656.18 frames.], batch size: 18, lr: 3.36e-04
+2022-05-05 12:46:49,725 INFO [train.py:715] (3/8) Epoch 6, batch 11950, loss[loss=0.1468, simple_loss=0.2145, pruned_loss=0.03957, over 4750.00 frames.], tot_loss[loss=0.149, simple_loss=0.2205, pruned_loss=0.03872, over 973125.31 frames.], batch size: 19, lr: 3.36e-04
+2022-05-05 12:47:28,221 INFO [train.py:715] (3/8) Epoch 6, batch 12000, loss[loss=0.1654, simple_loss=0.2431, pruned_loss=0.04387, over 4926.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2212, pruned_loss=0.03918, over 973682.51 frames.], batch size: 29, lr: 3.36e-04
+2022-05-05 12:47:28,221 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 12:47:37,944 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1091, simple_loss=0.1942, pruned_loss=0.01199, over 914524.00 frames.
+2022-05-05 12:48:16,697 INFO [train.py:715] (3/8) Epoch 6, batch 12050, loss[loss=0.1096, simple_loss=0.1744, pruned_loss=0.02242, over 4914.00 frames.], tot_loss[loss=0.149, simple_loss=0.2201, pruned_loss=0.03899, over 972883.64 frames.], batch size: 18, lr: 3.36e-04
+2022-05-05 12:48:56,375 INFO [train.py:715] (3/8) Epoch 6, batch 12100, loss[loss=0.1561, simple_loss=0.2265, pruned_loss=0.04283, over 4867.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2211, pruned_loss=0.03928, over 972748.88 frames.], batch size: 20, lr: 3.36e-04
+2022-05-05 12:49:35,321 INFO [train.py:715] (3/8) Epoch 6, batch 12150, loss[loss=0.1357, simple_loss=0.2075, pruned_loss=0.03198, over 4857.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2214, pruned_loss=0.0396, over 972551.16 frames.], batch size: 20, lr: 3.36e-04
+2022-05-05 12:50:14,107 INFO [train.py:715] (3/8) Epoch 6, batch 12200, loss[loss=0.1949, simple_loss=0.2755, pruned_loss=0.05715, over 4793.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2216, pruned_loss=0.03991, over 972815.94 frames.], batch size: 17, lr: 3.36e-04
+2022-05-05 12:50:53,315 INFO [train.py:715] (3/8) Epoch 6, batch 12250, loss[loss=0.1531, simple_loss=0.2184, pruned_loss=0.04392, over 4986.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.0402, over 971596.54 frames.], batch size: 28, lr: 3.36e-04
+2022-05-05 12:51:32,109 INFO [train.py:715] (3/8) Epoch 6, batch 12300, loss[loss=0.1456, simple_loss=0.2117, pruned_loss=0.03974, over 4855.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2215, pruned_loss=0.03963, over 971890.55 frames.], batch size: 32, lr: 3.36e-04
+2022-05-05 12:52:11,887 INFO [train.py:715] (3/8) Epoch 6, batch 12350, loss[loss=0.1881, simple_loss=0.2618, pruned_loss=0.0572, over 4900.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2226, pruned_loss=0.03977, over 971894.23 frames.], batch size: 19, lr: 3.36e-04
+2022-05-05 12:52:50,509 INFO [train.py:715] (3/8) Epoch 6, batch 12400, loss[loss=0.144, simple_loss=0.2091, pruned_loss=0.03944, over 4780.00 frames.], tot_loss[loss=0.151, simple_loss=0.222, pruned_loss=0.03998, over 970803.38 frames.], batch size: 14, lr: 3.36e-04
+2022-05-05 12:53:29,626 INFO [train.py:715] (3/8) Epoch 6, batch 12450, loss[loss=0.1372, simple_loss=0.2174, pruned_loss=0.02852, over 4934.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2213, pruned_loss=0.03957, over 971202.61 frames.], batch size: 21, lr: 3.36e-04
+2022-05-05 12:54:08,744 INFO [train.py:715] (3/8) Epoch 6, batch 12500, loss[loss=0.1687, simple_loss=0.2414, pruned_loss=0.04802, over 4929.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2218, pruned_loss=0.04005, over 971185.92 frames.], batch size: 29, lr: 3.36e-04
+2022-05-05 12:54:47,051 INFO [train.py:715] (3/8) Epoch 6, batch 12550, loss[loss=0.1242, simple_loss=0.2043, pruned_loss=0.02203, over 4966.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2215, pruned_loss=0.04038, over 971389.76 frames.], batch size: 24, lr: 3.36e-04
+2022-05-05 12:55:26,410 INFO [train.py:715] (3/8) Epoch 6, batch 12600, loss[loss=0.12, simple_loss=0.1954, pruned_loss=0.02226, over 4893.00 frames.], tot_loss[loss=0.15, simple_loss=0.2208, pruned_loss=0.03961, over 971230.42 frames.], batch size: 22, lr: 3.36e-04
+2022-05-05 12:56:05,094 INFO [train.py:715] (3/8) Epoch 6, batch 12650, loss[loss=0.1637, simple_loss=0.2361, pruned_loss=0.04566, over 4979.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2202, pruned_loss=0.03925, over 971355.32 frames.], batch size: 15, lr: 3.36e-04
+2022-05-05 12:56:43,910 INFO [train.py:715] (3/8) Epoch 6, batch 12700, loss[loss=0.1538, simple_loss=0.2245, pruned_loss=0.04158, over 4920.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03961, over 971308.46 frames.], batch size: 18, lr: 3.36e-04
+2022-05-05 12:57:22,046 INFO [train.py:715] (3/8) Epoch 6, batch 12750, loss[loss=0.1673, simple_loss=0.2288, pruned_loss=0.05285, over 4776.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2202, pruned_loss=0.03946, over 971616.54 frames.], batch size: 17, lr: 3.36e-04
+2022-05-05 12:58:01,008 INFO [train.py:715] (3/8) Epoch 6, batch 12800, loss[loss=0.1724, simple_loss=0.2561, pruned_loss=0.04437, over 4950.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2208, pruned_loss=0.03947, over 972103.35 frames.], batch size: 29, lr: 3.36e-04
+2022-05-05 12:58:39,732 INFO [train.py:715] (3/8) Epoch 6, batch 12850, loss[loss=0.1587, simple_loss=0.2192, pruned_loss=0.04908, over 4832.00 frames.], tot_loss[loss=0.15, simple_loss=0.2211, pruned_loss=0.03946, over 972224.83 frames.], batch size: 13, lr: 3.35e-04
+2022-05-05 12:59:18,383 INFO [train.py:715] (3/8) Epoch 6, batch 12900, loss[loss=0.1652, simple_loss=0.235, pruned_loss=0.04772, over 4765.00 frames.], tot_loss[loss=0.1502, simple_loss=0.221, pruned_loss=0.0397, over 971964.54 frames.], batch size: 14, lr: 3.35e-04
+2022-05-05 12:59:58,336 INFO [train.py:715] (3/8) Epoch 6, batch 12950, loss[loss=0.1372, simple_loss=0.2243, pruned_loss=0.02501, over 4812.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.03962, over 972984.21 frames.], batch size: 26, lr: 3.35e-04
+2022-05-05 13:00:37,483 INFO [train.py:715] (3/8) Epoch 6, batch 13000, loss[loss=0.145, simple_loss=0.2096, pruned_loss=0.04023, over 4973.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2203, pruned_loss=0.03939, over 972760.98 frames.], batch size: 31, lr: 3.35e-04
+2022-05-05 13:01:16,474 INFO [train.py:715] (3/8) Epoch 6, batch 13050, loss[loss=0.1616, simple_loss=0.2312, pruned_loss=0.04601, over 4639.00 frames.], tot_loss[loss=0.1493, simple_loss=0.22, pruned_loss=0.03931, over 972495.82 frames.], batch size: 13, lr: 3.35e-04
+2022-05-05 13:01:54,766 INFO [train.py:715] (3/8) Epoch 6, batch 13100, loss[loss=0.1271, simple_loss=0.1972, pruned_loss=0.02848, over 4867.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2205, pruned_loss=0.03924, over 972564.31 frames.], batch size: 20, lr: 3.35e-04
+2022-05-05 13:02:34,349 INFO [train.py:715] (3/8) Epoch 6, batch 13150, loss[loss=0.156, simple_loss=0.2186, pruned_loss=0.04671, over 4837.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2208, pruned_loss=0.03949, over 972491.27 frames.], batch size: 30, lr: 3.35e-04
+2022-05-05 13:03:12,923 INFO [train.py:715] (3/8) Epoch 6, batch 13200, loss[loss=0.1166, simple_loss=0.1972, pruned_loss=0.01797, over 4888.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2212, pruned_loss=0.03965, over 972702.59 frames.], batch size: 19, lr: 3.35e-04
+2022-05-05 13:03:51,764 INFO [train.py:715] (3/8) Epoch 6, batch 13250, loss[loss=0.1578, simple_loss=0.2325, pruned_loss=0.04159, over 4899.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2211, pruned_loss=0.03992, over 972627.63 frames.], batch size: 19, lr: 3.35e-04
+2022-05-05 13:04:30,642 INFO [train.py:715] (3/8) Epoch 6, batch 13300, loss[loss=0.1479, simple_loss=0.2169, pruned_loss=0.03944, over 4922.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.0396, over 972285.44 frames.], batch size: 39, lr: 3.35e-04
+2022-05-05 13:05:09,757 INFO [train.py:715] (3/8) Epoch 6, batch 13350, loss[loss=0.1588, simple_loss=0.2339, pruned_loss=0.04182, over 4755.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2203, pruned_loss=0.03976, over 972697.64 frames.], batch size: 12, lr: 3.35e-04
+2022-05-05 13:05:48,886 INFO [train.py:715] (3/8) Epoch 6, batch 13400, loss[loss=0.212, simple_loss=0.2743, pruned_loss=0.07486, over 4774.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2206, pruned_loss=0.03985, over 972472.32 frames.], batch size: 17, lr: 3.35e-04
+2022-05-05 13:06:27,484 INFO [train.py:715] (3/8) Epoch 6, batch 13450, loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03366, over 4989.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2208, pruned_loss=0.03995, over 972736.28 frames.], batch size: 25, lr: 3.35e-04
+2022-05-05 13:07:07,012 INFO [train.py:715] (3/8) Epoch 6, batch 13500, loss[loss=0.1314, simple_loss=0.2134, pruned_loss=0.02475, over 4876.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2207, pruned_loss=0.0399, over 972809.97 frames.], batch size: 22, lr: 3.35e-04
+2022-05-05 13:07:45,023 INFO [train.py:715] (3/8) Epoch 6, batch 13550, loss[loss=0.1428, simple_loss=0.2142, pruned_loss=0.03567, over 4839.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03975, over 972667.07 frames.], batch size: 30, lr: 3.35e-04
+2022-05-05 13:08:23,967 INFO [train.py:715] (3/8) Epoch 6, batch 13600, loss[loss=0.1587, simple_loss=0.2285, pruned_loss=0.04448, over 4864.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2206, pruned_loss=0.03926, over 972900.26 frames.], batch size: 32, lr: 3.35e-04
+2022-05-05 13:09:03,111 INFO [train.py:715] (3/8) Epoch 6, batch 13650, loss[loss=0.1239, simple_loss=0.1993, pruned_loss=0.02425, over 4816.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03877, over 971808.83 frames.], batch size: 25, lr: 3.35e-04
+2022-05-05 13:09:42,437 INFO [train.py:715] (3/8) Epoch 6, batch 13700, loss[loss=0.1465, simple_loss=0.2108, pruned_loss=0.0411, over 4833.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2197, pruned_loss=0.0385, over 971327.56 frames.], batch size: 13, lr: 3.35e-04
+2022-05-05 13:10:21,545 INFO [train.py:715] (3/8) Epoch 6, batch 13750, loss[loss=0.1513, simple_loss=0.2203, pruned_loss=0.04118, over 4799.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2195, pruned_loss=0.03856, over 970963.11 frames.], batch size: 14, lr: 3.35e-04
+2022-05-05 13:11:00,146 INFO [train.py:715] (3/8) Epoch 6, batch 13800, loss[loss=0.1306, simple_loss=0.208, pruned_loss=0.0266, over 4988.00 frames.], tot_loss[loss=0.148, simple_loss=0.2196, pruned_loss=0.03825, over 970507.62 frames.], batch size: 15, lr: 3.35e-04
+2022-05-05 13:11:40,116 INFO [train.py:715] (3/8) Epoch 6, batch 13850, loss[loss=0.1428, simple_loss=0.2191, pruned_loss=0.03325, over 4814.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2192, pruned_loss=0.03804, over 970852.81 frames.], batch size: 26, lr: 3.35e-04
+2022-05-05 13:12:18,449 INFO [train.py:715] (3/8) Epoch 6, batch 13900, loss[loss=0.1394, simple_loss=0.2107, pruned_loss=0.0341, over 4819.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2189, pruned_loss=0.03794, over 970954.25 frames.], batch size: 14, lr: 3.35e-04
+2022-05-05 13:12:57,462 INFO [train.py:715] (3/8) Epoch 6, batch 13950, loss[loss=0.159, simple_loss=0.234, pruned_loss=0.042, over 4958.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03741, over 971874.77 frames.], batch size: 15, lr: 3.35e-04
+2022-05-05 13:13:36,062 INFO [train.py:715] (3/8) Epoch 6, batch 14000, loss[loss=0.1488, simple_loss=0.206, pruned_loss=0.0458, over 4960.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2191, pruned_loss=0.03793, over 971892.04 frames.], batch size: 35, lr: 3.35e-04
+2022-05-05 13:14:15,111 INFO [train.py:715] (3/8) Epoch 6, batch 14050, loss[loss=0.1355, simple_loss=0.2067, pruned_loss=0.03214, over 4963.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2191, pruned_loss=0.0381, over 972253.75 frames.], batch size: 24, lr: 3.35e-04
+2022-05-05 13:14:53,531 INFO [train.py:715] (3/8) Epoch 6, batch 14100, loss[loss=0.1376, simple_loss=0.2097, pruned_loss=0.03277, over 4989.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2194, pruned_loss=0.03795, over 972443.63 frames.], batch size: 26, lr: 3.35e-04
+2022-05-05 13:15:32,016 INFO [train.py:715] (3/8) Epoch 6, batch 14150, loss[loss=0.1301, simple_loss=0.2023, pruned_loss=0.02899, over 4914.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2208, pruned_loss=0.0385, over 972234.01 frames.], batch size: 17, lr: 3.35e-04
+2022-05-05 13:16:11,449 INFO [train.py:715] (3/8) Epoch 6, batch 14200, loss[loss=0.1481, simple_loss=0.2357, pruned_loss=0.03022, over 4827.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2206, pruned_loss=0.03836, over 971829.36 frames.], batch size: 27, lr: 3.34e-04
+2022-05-05 13:16:50,087 INFO [train.py:715] (3/8) Epoch 6, batch 14250, loss[loss=0.1524, simple_loss=0.2194, pruned_loss=0.04275, over 4916.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2205, pruned_loss=0.03856, over 972381.28 frames.], batch size: 17, lr: 3.34e-04
+2022-05-05 13:17:29,124 INFO [train.py:715] (3/8) Epoch 6, batch 14300, loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.0301, over 4985.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2205, pruned_loss=0.03845, over 972554.05 frames.], batch size: 28, lr: 3.34e-04
+2022-05-05 13:18:07,582 INFO [train.py:715] (3/8) Epoch 6, batch 14350, loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.03792, over 4757.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2204, pruned_loss=0.03829, over 972233.84 frames.], batch size: 16, lr: 3.34e-04
+2022-05-05 13:18:47,507 INFO [train.py:715] (3/8) Epoch 6, batch 14400, loss[loss=0.17, simple_loss=0.2422, pruned_loss=0.04892, over 4776.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2203, pruned_loss=0.03825, over 973100.29 frames.], batch size: 18, lr: 3.34e-04
+2022-05-05 13:19:25,857 INFO [train.py:715] (3/8) Epoch 6, batch 14450, loss[loss=0.1212, simple_loss=0.1903, pruned_loss=0.0261, over 4693.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03895, over 973382.08 frames.], batch size: 15, lr: 3.34e-04
+2022-05-05 13:20:04,246 INFO [train.py:715] (3/8) Epoch 6, batch 14500, loss[loss=0.1328, simple_loss=0.1911, pruned_loss=0.03726, over 4987.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2197, pruned_loss=0.03857, over 972841.00 frames.], batch size: 14, lr: 3.34e-04
+2022-05-05 13:20:43,936 INFO [train.py:715] (3/8) Epoch 6, batch 14550, loss[loss=0.1544, simple_loss=0.2301, pruned_loss=0.03935, over 4843.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03888, over 973137.91 frames.], batch size: 32, lr: 3.34e-04
+2022-05-05 13:21:22,652 INFO [train.py:715] (3/8) Epoch 6, batch 14600, loss[loss=0.1603, simple_loss=0.2327, pruned_loss=0.04398, over 4919.00 frames.], tot_loss[loss=0.1499, simple_loss=0.221, pruned_loss=0.0394, over 973382.74 frames.], batch size: 23, lr: 3.34e-04
+2022-05-05 13:22:01,119 INFO [train.py:715] (3/8) Epoch 6, batch 14650, loss[loss=0.1236, simple_loss=0.1969, pruned_loss=0.02515, over 4897.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2207, pruned_loss=0.03902, over 972794.48 frames.], batch size: 17, lr: 3.34e-04
+2022-05-05 13:22:40,131 INFO [train.py:715] (3/8) Epoch 6, batch 14700, loss[loss=0.168, simple_loss=0.2567, pruned_loss=0.03968, over 4808.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2208, pruned_loss=0.0391, over 972198.34 frames.], batch size: 26, lr: 3.34e-04
+2022-05-05 13:23:19,675 INFO [train.py:715] (3/8) Epoch 6, batch 14750, loss[loss=0.1492, simple_loss=0.2201, pruned_loss=0.03913, over 4771.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2194, pruned_loss=0.03854, over 971891.17 frames.], batch size: 18, lr: 3.34e-04
+2022-05-05 13:23:57,831 INFO [train.py:715] (3/8) Epoch 6, batch 14800, loss[loss=0.1368, simple_loss=0.2045, pruned_loss=0.03456, over 4757.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2203, pruned_loss=0.03927, over 972529.48 frames.], batch size: 19, lr: 3.34e-04
+2022-05-05 13:24:35,995 INFO [train.py:715] (3/8) Epoch 6, batch 14850, loss[loss=0.1456, simple_loss=0.212, pruned_loss=0.0396, over 4917.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2201, pruned_loss=0.03938, over 971900.07 frames.], batch size: 18, lr: 3.34e-04
+2022-05-05 13:25:15,105 INFO [train.py:715] (3/8) Epoch 6, batch 14900, loss[loss=0.1935, simple_loss=0.2534, pruned_loss=0.06684, over 4802.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2207, pruned_loss=0.03929, over 972148.32 frames.], batch size: 21, lr: 3.34e-04
+2022-05-05 13:25:53,359 INFO [train.py:715] (3/8) Epoch 6, batch 14950, loss[loss=0.1338, simple_loss=0.2042, pruned_loss=0.03168, over 4801.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03897, over 972808.65 frames.], batch size: 13, lr: 3.34e-04
+2022-05-05 13:26:32,025 INFO [train.py:715] (3/8) Epoch 6, batch 15000, loss[loss=0.1473, simple_loss=0.2261, pruned_loss=0.03428, over 4839.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2203, pruned_loss=0.03908, over 971935.44 frames.], batch size: 26, lr: 3.34e-04
+2022-05-05 13:26:32,026 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 13:26:41,818 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1091, simple_loss=0.1941, pruned_loss=0.01202, over 914524.00 frames.
+2022-05-05 13:27:20,600 INFO [train.py:715] (3/8) Epoch 6, batch 15050, loss[loss=0.158, simple_loss=0.2371, pruned_loss=0.03946, over 4982.00 frames.], tot_loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03881, over 972058.15 frames.], batch size: 25, lr: 3.34e-04
+2022-05-05 13:27:59,351 INFO [train.py:715] (3/8) Epoch 6, batch 15100, loss[loss=0.1254, simple_loss=0.1975, pruned_loss=0.02665, over 4822.00 frames.], tot_loss[loss=0.1486, simple_loss=0.22, pruned_loss=0.0386, over 971772.67 frames.], batch size: 27, lr: 3.34e-04
+2022-05-05 13:28:41,263 INFO [train.py:715] (3/8) Epoch 6, batch 15150, loss[loss=0.1553, simple_loss=0.2276, pruned_loss=0.0415, over 4958.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03849, over 972313.15 frames.], batch size: 24, lr: 3.34e-04
+2022-05-05 13:29:19,830 INFO [train.py:715] (3/8) Epoch 6, batch 15200, loss[loss=0.1567, simple_loss=0.2306, pruned_loss=0.04137, over 4889.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2205, pruned_loss=0.03846, over 972916.50 frames.], batch size: 22, lr: 3.34e-04
+2022-05-05 13:29:58,374 INFO [train.py:715] (3/8) Epoch 6, batch 15250, loss[loss=0.1484, simple_loss=0.2239, pruned_loss=0.03642, over 4959.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2202, pruned_loss=0.03833, over 972188.15 frames.], batch size: 24, lr: 3.34e-04
+2022-05-05 13:30:37,907 INFO [train.py:715] (3/8) Epoch 6, batch 15300, loss[loss=0.1735, simple_loss=0.2374, pruned_loss=0.05486, over 4791.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2191, pruned_loss=0.03811, over 972714.38 frames.], batch size: 18, lr: 3.34e-04
+2022-05-05 13:31:15,932 INFO [train.py:715] (3/8) Epoch 6, batch 15350, loss[loss=0.1664, simple_loss=0.2373, pruned_loss=0.04771, over 4827.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.03815, over 972554.22 frames.], batch size: 15, lr: 3.34e-04
+2022-05-05 13:31:54,942 INFO [train.py:715] (3/8) Epoch 6, batch 15400, loss[loss=0.1337, simple_loss=0.2034, pruned_loss=0.032, over 4895.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2205, pruned_loss=0.03883, over 972955.45 frames.], batch size: 17, lr: 3.34e-04
+2022-05-05 13:32:33,864 INFO [train.py:715] (3/8) Epoch 6, batch 15450, loss[loss=0.1507, simple_loss=0.2267, pruned_loss=0.0373, over 4759.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03878, over 971798.10 frames.], batch size: 19, lr: 3.34e-04
+2022-05-05 13:33:13,327 INFO [train.py:715] (3/8) Epoch 6, batch 15500, loss[loss=0.1523, simple_loss=0.2203, pruned_loss=0.04212, over 4782.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2199, pruned_loss=0.03864, over 971109.37 frames.], batch size: 17, lr: 3.34e-04
+2022-05-05 13:33:51,504 INFO [train.py:715] (3/8) Epoch 6, batch 15550, loss[loss=0.164, simple_loss=0.2385, pruned_loss=0.04478, over 4904.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.03917, over 970266.22 frames.], batch size: 19, lr: 3.33e-04
+2022-05-05 13:34:30,398 INFO [train.py:715] (3/8) Epoch 6, batch 15600, loss[loss=0.1516, simple_loss=0.2173, pruned_loss=0.04297, over 4910.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.03938, over 970684.76 frames.], batch size: 17, lr: 3.33e-04
+2022-05-05 13:35:09,327 INFO [train.py:715] (3/8) Epoch 6, batch 15650, loss[loss=0.1302, simple_loss=0.2032, pruned_loss=0.02856, over 4970.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2201, pruned_loss=0.03891, over 971058.28 frames.], batch size: 14, lr: 3.33e-04
+2022-05-05 13:35:47,369 INFO [train.py:715] (3/8) Epoch 6, batch 15700, loss[loss=0.1442, simple_loss=0.2181, pruned_loss=0.03515, over 4939.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2199, pruned_loss=0.03925, over 971918.63 frames.], batch size: 21, lr: 3.33e-04
+2022-05-05 13:36:26,052 INFO [train.py:715] (3/8) Epoch 6, batch 15750, loss[loss=0.1511, simple_loss=0.2211, pruned_loss=0.04054, over 4952.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2196, pruned_loss=0.03906, over 972259.84 frames.], batch size: 24, lr: 3.33e-04
+2022-05-05 13:37:04,792 INFO [train.py:715] (3/8) Epoch 6, batch 15800, loss[loss=0.1267, simple_loss=0.1959, pruned_loss=0.02874, over 4802.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2202, pruned_loss=0.03916, over 972316.80 frames.], batch size: 26, lr: 3.33e-04
+2022-05-05 13:37:43,838 INFO [train.py:715] (3/8) Epoch 6, batch 15850, loss[loss=0.1585, simple_loss=0.2254, pruned_loss=0.0458, over 4840.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2203, pruned_loss=0.0391, over 972175.48 frames.], batch size: 30, lr: 3.33e-04
+2022-05-05 13:38:22,283 INFO [train.py:715] (3/8) Epoch 6, batch 15900, loss[loss=0.1486, simple_loss=0.2281, pruned_loss=0.03459, over 4792.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03881, over 971474.53 frames.], batch size: 14, lr: 3.33e-04
+2022-05-05 13:39:00,647 INFO [train.py:715] (3/8) Epoch 6, batch 15950, loss[loss=0.1442, simple_loss=0.2136, pruned_loss=0.0374, over 4772.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2195, pruned_loss=0.03859, over 971030.37 frames.], batch size: 19, lr: 3.33e-04
+2022-05-05 13:39:39,974 INFO [train.py:715] (3/8) Epoch 6, batch 16000, loss[loss=0.1428, simple_loss=0.2108, pruned_loss=0.03744, over 4872.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2203, pruned_loss=0.03862, over 971046.35 frames.], batch size: 16, lr: 3.33e-04
+2022-05-05 13:40:18,433 INFO [train.py:715] (3/8) Epoch 6, batch 16050, loss[loss=0.1421, simple_loss=0.2256, pruned_loss=0.02926, over 4880.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2198, pruned_loss=0.03823, over 971263.21 frames.], batch size: 16, lr: 3.33e-04
+2022-05-05 13:40:56,906 INFO [train.py:715] (3/8) Epoch 6, batch 16100, loss[loss=0.1249, simple_loss=0.2068, pruned_loss=0.02146, over 4765.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2198, pruned_loss=0.03791, over 971461.30 frames.], batch size: 17, lr: 3.33e-04
+2022-05-05 13:41:35,296 INFO [train.py:715] (3/8) Epoch 6, batch 16150, loss[loss=0.1733, simple_loss=0.2337, pruned_loss=0.05645, over 4947.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2196, pruned_loss=0.03782, over 971333.37 frames.], batch size: 35, lr: 3.33e-04
+2022-05-05 13:42:14,798 INFO [train.py:715] (3/8) Epoch 6, batch 16200, loss[loss=0.1298, simple_loss=0.2106, pruned_loss=0.0245, over 4791.00 frames.], tot_loss[loss=0.1471, simple_loss=0.219, pruned_loss=0.0376, over 971297.22 frames.], batch size: 13, lr: 3.33e-04
+2022-05-05 13:42:53,109 INFO [train.py:715] (3/8) Epoch 6, batch 16250, loss[loss=0.2166, simple_loss=0.2977, pruned_loss=0.06778, over 4925.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2196, pruned_loss=0.03783, over 971334.35 frames.], batch size: 18, lr: 3.33e-04
+2022-05-05 13:43:31,727 INFO [train.py:715] (3/8) Epoch 6, batch 16300, loss[loss=0.1376, simple_loss=0.2066, pruned_loss=0.03427, over 4744.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2194, pruned_loss=0.03764, over 971595.44 frames.], batch size: 16, lr: 3.33e-04
+2022-05-05 13:44:11,203 INFO [train.py:715] (3/8) Epoch 6, batch 16350, loss[loss=0.1491, simple_loss=0.2227, pruned_loss=0.03772, over 4977.00 frames.], tot_loss[loss=0.149, simple_loss=0.2209, pruned_loss=0.03851, over 971824.82 frames.], batch size: 14, lr: 3.33e-04
+2022-05-05 13:44:49,508 INFO [train.py:715] (3/8) Epoch 6, batch 16400, loss[loss=0.1411, simple_loss=0.2064, pruned_loss=0.0379, over 4812.00 frames.], tot_loss[loss=0.15, simple_loss=0.2217, pruned_loss=0.03917, over 971230.31 frames.], batch size: 14, lr: 3.33e-04
+2022-05-05 13:45:28,824 INFO [train.py:715] (3/8) Epoch 6, batch 16450, loss[loss=0.1417, simple_loss=0.2091, pruned_loss=0.03718, over 4954.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2215, pruned_loss=0.03945, over 971221.50 frames.], batch size: 35, lr: 3.33e-04
+2022-05-05 13:46:07,628 INFO [train.py:715] (3/8) Epoch 6, batch 16500, loss[loss=0.1468, simple_loss=0.213, pruned_loss=0.04033, over 4909.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2211, pruned_loss=0.03925, over 970284.24 frames.], batch size: 19, lr: 3.33e-04
+2022-05-05 13:46:46,577 INFO [train.py:715] (3/8) Epoch 6, batch 16550, loss[loss=0.1576, simple_loss=0.2354, pruned_loss=0.03991, over 4941.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2201, pruned_loss=0.03902, over 971540.88 frames.], batch size: 18, lr: 3.33e-04
+2022-05-05 13:47:24,414 INFO [train.py:715] (3/8) Epoch 6, batch 16600, loss[loss=0.1655, simple_loss=0.2266, pruned_loss=0.05217, over 4752.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2213, pruned_loss=0.04008, over 971672.36 frames.], batch size: 16, lr: 3.33e-04
+2022-05-05 13:48:03,153 INFO [train.py:715] (3/8) Epoch 6, batch 16650, loss[loss=0.1559, simple_loss=0.2346, pruned_loss=0.03857, over 4751.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03987, over 971402.01 frames.], batch size: 16, lr: 3.33e-04
+2022-05-05 13:48:42,813 INFO [train.py:715] (3/8) Epoch 6, batch 16700, loss[loss=0.1615, simple_loss=0.2204, pruned_loss=0.0513, over 4755.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2206, pruned_loss=0.03936, over 971806.20 frames.], batch size: 19, lr: 3.33e-04
+2022-05-05 13:49:21,220 INFO [train.py:715] (3/8) Epoch 6, batch 16750, loss[loss=0.1568, simple_loss=0.2337, pruned_loss=0.03991, over 4835.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03959, over 971824.07 frames.], batch size: 30, lr: 3.33e-04
+2022-05-05 13:50:00,119 INFO [train.py:715] (3/8) Epoch 6, batch 16800, loss[loss=0.1581, simple_loss=0.2372, pruned_loss=0.03944, over 4834.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03954, over 972783.10 frames.], batch size: 15, lr: 3.33e-04
+2022-05-05 13:50:39,326 INFO [train.py:715] (3/8) Epoch 6, batch 16850, loss[loss=0.1455, simple_loss=0.2235, pruned_loss=0.03373, over 4865.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03952, over 972168.21 frames.], batch size: 20, lr: 3.33e-04
+2022-05-05 13:51:19,121 INFO [train.py:715] (3/8) Epoch 6, batch 16900, loss[loss=0.1714, simple_loss=0.2501, pruned_loss=0.04632, over 4835.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2206, pruned_loss=0.03909, over 971967.52 frames.], batch size: 15, lr: 3.32e-04
+2022-05-05 13:51:57,174 INFO [train.py:715] (3/8) Epoch 6, batch 16950, loss[loss=0.1274, simple_loss=0.2088, pruned_loss=0.023, over 4894.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2202, pruned_loss=0.03939, over 972265.20 frames.], batch size: 19, lr: 3.32e-04
+2022-05-05 13:52:36,231 INFO [train.py:715] (3/8) Epoch 6, batch 17000, loss[loss=0.1861, simple_loss=0.2572, pruned_loss=0.05747, over 4904.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2206, pruned_loss=0.0395, over 972637.50 frames.], batch size: 17, lr: 3.32e-04
+2022-05-05 13:53:15,748 INFO [train.py:715] (3/8) Epoch 6, batch 17050, loss[loss=0.1493, simple_loss=0.2091, pruned_loss=0.04471, over 4921.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2206, pruned_loss=0.03939, over 972848.76 frames.], batch size: 18, lr: 3.32e-04
+2022-05-05 13:53:53,902 INFO [train.py:715] (3/8) Epoch 6, batch 17100, loss[loss=0.1435, simple_loss=0.219, pruned_loss=0.03397, over 4887.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2201, pruned_loss=0.03903, over 973174.58 frames.], batch size: 22, lr: 3.32e-04
+2022-05-05 13:54:32,774 INFO [train.py:715] (3/8) Epoch 6, batch 17150, loss[loss=0.1378, simple_loss=0.2084, pruned_loss=0.03356, over 4806.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2199, pruned_loss=0.03895, over 973509.10 frames.], batch size: 25, lr: 3.32e-04
+2022-05-05 13:55:11,750 INFO [train.py:715] (3/8) Epoch 6, batch 17200, loss[loss=0.1403, simple_loss=0.214, pruned_loss=0.03333, over 4838.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2202, pruned_loss=0.03913, over 973079.42 frames.], batch size: 30, lr: 3.32e-04
+2022-05-05 13:55:51,112 INFO [train.py:715] (3/8) Epoch 6, batch 17250, loss[loss=0.1554, simple_loss=0.2321, pruned_loss=0.03939, over 4793.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2202, pruned_loss=0.03904, over 972482.03 frames.], batch size: 24, lr: 3.32e-04
+2022-05-05 13:56:29,075 INFO [train.py:715] (3/8) Epoch 6, batch 17300, loss[loss=0.1418, simple_loss=0.2218, pruned_loss=0.03088, over 4762.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2206, pruned_loss=0.03883, over 972412.27 frames.], batch size: 16, lr: 3.32e-04
+2022-05-05 13:57:07,892 INFO [train.py:715] (3/8) Epoch 6, batch 17350, loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03105, over 4893.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2211, pruned_loss=0.03888, over 972901.48 frames.], batch size: 19, lr: 3.32e-04
+2022-05-05 13:57:47,278 INFO [train.py:715] (3/8) Epoch 6, batch 17400, loss[loss=0.1399, simple_loss=0.2135, pruned_loss=0.03319, over 4873.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2208, pruned_loss=0.03896, over 972647.82 frames.], batch size: 22, lr: 3.32e-04
+2022-05-05 13:58:26,212 INFO [train.py:715] (3/8) Epoch 6, batch 17450, loss[loss=0.1275, simple_loss=0.2031, pruned_loss=0.02596, over 4971.00 frames.], tot_loss[loss=0.1498, simple_loss=0.221, pruned_loss=0.03926, over 972929.72 frames.], batch size: 24, lr: 3.32e-04
+2022-05-05 13:59:04,829 INFO [train.py:715] (3/8) Epoch 6, batch 17500, loss[loss=0.1679, simple_loss=0.2244, pruned_loss=0.05573, over 4992.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2201, pruned_loss=0.03888, over 971835.29 frames.], batch size: 14, lr: 3.32e-04
+2022-05-05 13:59:43,980 INFO [train.py:715] (3/8) Epoch 6, batch 17550, loss[loss=0.1769, simple_loss=0.2405, pruned_loss=0.05668, over 4989.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2207, pruned_loss=0.03888, over 972144.14 frames.], batch size: 31, lr: 3.32e-04
+2022-05-05 14:00:23,863 INFO [train.py:715] (3/8) Epoch 6, batch 17600, loss[loss=0.1252, simple_loss=0.1986, pruned_loss=0.02595, over 4916.00 frames.], tot_loss[loss=0.1495, simple_loss=0.221, pruned_loss=0.03902, over 972421.45 frames.], batch size: 18, lr: 3.32e-04
+2022-05-05 14:01:01,424 INFO [train.py:715] (3/8) Epoch 6, batch 17650, loss[loss=0.1293, simple_loss=0.203, pruned_loss=0.02779, over 4815.00 frames.], tot_loss[loss=0.1494, simple_loss=0.221, pruned_loss=0.03885, over 972726.35 frames.], batch size: 26, lr: 3.32e-04
+2022-05-05 14:01:40,865 INFO [train.py:715] (3/8) Epoch 6, batch 17700, loss[loss=0.1509, simple_loss=0.2221, pruned_loss=0.0398, over 4765.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2211, pruned_loss=0.03922, over 973282.84 frames.], batch size: 14, lr: 3.32e-04
+2022-05-05 14:02:20,251 INFO [train.py:715] (3/8) Epoch 6, batch 17750, loss[loss=0.1178, simple_loss=0.1987, pruned_loss=0.01846, over 4832.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2212, pruned_loss=0.0396, over 972715.06 frames.], batch size: 26, lr: 3.32e-04
+2022-05-05 14:02:58,606 INFO [train.py:715] (3/8) Epoch 6, batch 17800, loss[loss=0.1836, simple_loss=0.2405, pruned_loss=0.06333, over 4888.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2218, pruned_loss=0.04028, over 972384.59 frames.], batch size: 32, lr: 3.32e-04
+2022-05-05 14:03:37,539 INFO [train.py:715] (3/8) Epoch 6, batch 17850, loss[loss=0.143, simple_loss=0.2125, pruned_loss=0.03673, over 4749.00 frames.], tot_loss[loss=0.15, simple_loss=0.2203, pruned_loss=0.0398, over 971666.48 frames.], batch size: 16, lr: 3.32e-04
+2022-05-05 14:04:16,746 INFO [train.py:715] (3/8) Epoch 6, batch 17900, loss[loss=0.2164, simple_loss=0.2811, pruned_loss=0.07583, over 4817.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2204, pruned_loss=0.03994, over 972032.83 frames.], batch size: 15, lr: 3.32e-04
+2022-05-05 14:04:56,309 INFO [train.py:715] (3/8) Epoch 6, batch 17950, loss[loss=0.1578, simple_loss=0.2395, pruned_loss=0.03811, over 4937.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2197, pruned_loss=0.03951, over 972431.94 frames.], batch size: 21, lr: 3.32e-04
+2022-05-05 14:05:34,137 INFO [train.py:715] (3/8) Epoch 6, batch 18000, loss[loss=0.1444, simple_loss=0.2283, pruned_loss=0.03028, over 4833.00 frames.], tot_loss[loss=0.149, simple_loss=0.2196, pruned_loss=0.03918, over 972677.65 frames.], batch size: 26, lr: 3.32e-04
+2022-05-05 14:05:34,138 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 14:05:43,883 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1087, simple_loss=0.1939, pruned_loss=0.0118, over 914524.00 frames.
+2022-05-05 14:06:22,337 INFO [train.py:715] (3/8) Epoch 6, batch 18050, loss[loss=0.1379, simple_loss=0.2085, pruned_loss=0.03368, over 4801.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2202, pruned_loss=0.03941, over 972786.14 frames.], batch size: 12, lr: 3.32e-04
+2022-05-05 14:07:01,819 INFO [train.py:715] (3/8) Epoch 6, batch 18100, loss[loss=0.142, simple_loss=0.2075, pruned_loss=0.03828, over 4889.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2199, pruned_loss=0.03914, over 972206.18 frames.], batch size: 19, lr: 3.32e-04
+2022-05-05 14:07:41,269 INFO [train.py:715] (3/8) Epoch 6, batch 18150, loss[loss=0.1289, simple_loss=0.1945, pruned_loss=0.03168, over 4830.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2205, pruned_loss=0.03937, over 972590.81 frames.], batch size: 25, lr: 3.32e-04
+2022-05-05 14:08:19,365 INFO [train.py:715] (3/8) Epoch 6, batch 18200, loss[loss=0.1186, simple_loss=0.2012, pruned_loss=0.01802, over 4824.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2204, pruned_loss=0.03917, over 972788.78 frames.], batch size: 26, lr: 3.32e-04
+2022-05-05 14:08:58,866 INFO [train.py:715] (3/8) Epoch 6, batch 18250, loss[loss=0.1417, simple_loss=0.208, pruned_loss=0.03767, over 4984.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03976, over 972100.68 frames.], batch size: 14, lr: 3.31e-04
+2022-05-05 14:09:38,213 INFO [train.py:715] (3/8) Epoch 6, batch 18300, loss[loss=0.1264, simple_loss=0.2044, pruned_loss=0.0242, over 4811.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03954, over 971223.86 frames.], batch size: 27, lr: 3.31e-04
+2022-05-05 14:10:17,261 INFO [train.py:715] (3/8) Epoch 6, batch 18350, loss[loss=0.151, simple_loss=0.2308, pruned_loss=0.03562, over 4980.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2221, pruned_loss=0.04043, over 972557.16 frames.], batch size: 25, lr: 3.31e-04
+2022-05-05 14:10:55,622 INFO [train.py:715] (3/8) Epoch 6, batch 18400, loss[loss=0.1572, simple_loss=0.225, pruned_loss=0.04468, over 4959.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2217, pruned_loss=0.04036, over 972243.15 frames.], batch size: 15, lr: 3.31e-04
+2022-05-05 14:11:34,891 INFO [train.py:715] (3/8) Epoch 6, batch 18450, loss[loss=0.1435, simple_loss=0.2084, pruned_loss=0.0393, over 4778.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2208, pruned_loss=0.03977, over 970970.95 frames.], batch size: 18, lr: 3.31e-04
+2022-05-05 14:12:14,318 INFO [train.py:715] (3/8) Epoch 6, batch 18500, loss[loss=0.135, simple_loss=0.2099, pruned_loss=0.0301, over 4922.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2212, pruned_loss=0.03967, over 970954.72 frames.], batch size: 29, lr: 3.31e-04
+2022-05-05 14:12:52,317 INFO [train.py:715] (3/8) Epoch 6, batch 18550, loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03143, over 4876.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2208, pruned_loss=0.03873, over 970900.14 frames.], batch size: 16, lr: 3.31e-04
+2022-05-05 14:13:31,751 INFO [train.py:715] (3/8) Epoch 6, batch 18600, loss[loss=0.1557, simple_loss=0.2271, pruned_loss=0.0422, over 4821.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2209, pruned_loss=0.03872, over 971453.40 frames.], batch size: 26, lr: 3.31e-04
+2022-05-05 14:14:10,848 INFO [train.py:715] (3/8) Epoch 6, batch 18650, loss[loss=0.1568, simple_loss=0.2289, pruned_loss=0.04229, over 4889.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2205, pruned_loss=0.03885, over 972171.42 frames.], batch size: 22, lr: 3.31e-04
+2022-05-05 14:14:50,392 INFO [train.py:715] (3/8) Epoch 6, batch 18700, loss[loss=0.1325, simple_loss=0.21, pruned_loss=0.0275, over 4897.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2201, pruned_loss=0.0387, over 971577.87 frames.], batch size: 39, lr: 3.31e-04
+2022-05-05 14:15:28,529 INFO [train.py:715] (3/8) Epoch 6, batch 18750, loss[loss=0.1297, simple_loss=0.1961, pruned_loss=0.03165, over 4879.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2201, pruned_loss=0.03852, over 972473.68 frames.], batch size: 16, lr: 3.31e-04
+2022-05-05 14:16:07,702 INFO [train.py:715] (3/8) Epoch 6, batch 18800, loss[loss=0.1609, simple_loss=0.2398, pruned_loss=0.041, over 4852.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2198, pruned_loss=0.03802, over 974162.94 frames.], batch size: 30, lr: 3.31e-04
+2022-05-05 14:16:47,207 INFO [train.py:715] (3/8) Epoch 6, batch 18850, loss[loss=0.1588, simple_loss=0.2218, pruned_loss=0.04794, over 4924.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2197, pruned_loss=0.03841, over 973296.51 frames.], batch size: 18, lr: 3.31e-04
+2022-05-05 14:17:25,255 INFO [train.py:715] (3/8) Epoch 6, batch 18900, loss[loss=0.1145, simple_loss=0.1923, pruned_loss=0.01837, over 4965.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2204, pruned_loss=0.0385, over 973594.41 frames.], batch size: 14, lr: 3.31e-04
+2022-05-05 14:18:04,843 INFO [train.py:715] (3/8) Epoch 6, batch 18950, loss[loss=0.173, simple_loss=0.226, pruned_loss=0.05999, over 4806.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2194, pruned_loss=0.03817, over 973592.62 frames.], batch size: 21, lr: 3.31e-04
+2022-05-05 14:18:43,971 INFO [train.py:715] (3/8) Epoch 6, batch 19000, loss[loss=0.1339, simple_loss=0.2032, pruned_loss=0.03227, over 4973.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2187, pruned_loss=0.03784, over 973104.33 frames.], batch size: 25, lr: 3.31e-04
+2022-05-05 14:19:23,157 INFO [train.py:715] (3/8) Epoch 6, batch 19050, loss[loss=0.2123, simple_loss=0.2687, pruned_loss=0.07795, over 4930.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03794, over 973259.70 frames.], batch size: 23, lr: 3.31e-04
+2022-05-05 14:20:01,544 INFO [train.py:715] (3/8) Epoch 6, batch 19100, loss[loss=0.1229, simple_loss=0.1905, pruned_loss=0.02763, over 4966.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2191, pruned_loss=0.03801, over 973007.85 frames.], batch size: 28, lr: 3.31e-04
+2022-05-05 14:20:40,517 INFO [train.py:715] (3/8) Epoch 6, batch 19150, loss[loss=0.1546, simple_loss=0.23, pruned_loss=0.03958, over 4865.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03855, over 972957.59 frames.], batch size: 20, lr: 3.31e-04
+2022-05-05 14:21:20,170 INFO [train.py:715] (3/8) Epoch 6, batch 19200, loss[loss=0.1805, simple_loss=0.2477, pruned_loss=0.05665, over 4952.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2187, pruned_loss=0.03845, over 972123.16 frames.], batch size: 39, lr: 3.31e-04
+2022-05-05 14:21:58,237 INFO [train.py:715] (3/8) Epoch 6, batch 19250, loss[loss=0.1545, simple_loss=0.226, pruned_loss=0.04148, over 4840.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2188, pruned_loss=0.03868, over 972207.94 frames.], batch size: 15, lr: 3.31e-04
+2022-05-05 14:22:37,141 INFO [train.py:715] (3/8) Epoch 6, batch 19300, loss[loss=0.1258, simple_loss=0.1995, pruned_loss=0.02606, over 4914.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2198, pruned_loss=0.03901, over 973123.57 frames.], batch size: 17, lr: 3.31e-04
+2022-05-05 14:23:16,402 INFO [train.py:715] (3/8) Epoch 6, batch 19350, loss[loss=0.1752, simple_loss=0.2422, pruned_loss=0.05414, over 4826.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2195, pruned_loss=0.03896, over 972621.97 frames.], batch size: 26, lr: 3.31e-04
+2022-05-05 14:23:54,992 INFO [train.py:715] (3/8) Epoch 6, batch 19400, loss[loss=0.1565, simple_loss=0.2218, pruned_loss=0.04563, over 4804.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2192, pruned_loss=0.03856, over 971695.85 frames.], batch size: 13, lr: 3.31e-04
+2022-05-05 14:24:33,671 INFO [train.py:715] (3/8) Epoch 6, batch 19450, loss[loss=0.1602, simple_loss=0.2287, pruned_loss=0.04588, over 4756.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2195, pruned_loss=0.03897, over 972743.24 frames.], batch size: 19, lr: 3.31e-04
+2022-05-05 14:25:13,067 INFO [train.py:715] (3/8) Epoch 6, batch 19500, loss[loss=0.1532, simple_loss=0.2143, pruned_loss=0.04604, over 4834.00 frames.], tot_loss[loss=0.1484, simple_loss=0.219, pruned_loss=0.03884, over 972168.60 frames.], batch size: 30, lr: 3.31e-04
+2022-05-05 14:25:51,973 INFO [train.py:715] (3/8) Epoch 6, batch 19550, loss[loss=0.1462, simple_loss=0.2114, pruned_loss=0.04046, over 4762.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2193, pruned_loss=0.03891, over 972274.59 frames.], batch size: 19, lr: 3.31e-04
+2022-05-05 14:26:30,333 INFO [train.py:715] (3/8) Epoch 6, batch 19600, loss[loss=0.1609, simple_loss=0.2212, pruned_loss=0.05028, over 4828.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03875, over 972684.23 frames.], batch size: 30, lr: 3.31e-04
+2022-05-05 14:27:09,231 INFO [train.py:715] (3/8) Epoch 6, batch 19650, loss[loss=0.167, simple_loss=0.2329, pruned_loss=0.05051, over 4970.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2199, pruned_loss=0.03848, over 972233.35 frames.], batch size: 35, lr: 3.30e-04
+2022-05-05 14:27:48,353 INFO [train.py:715] (3/8) Epoch 6, batch 19700, loss[loss=0.1422, simple_loss=0.2188, pruned_loss=0.03284, over 4788.00 frames.], tot_loss[loss=0.1487, simple_loss=0.22, pruned_loss=0.03873, over 972264.35 frames.], batch size: 18, lr: 3.30e-04
+2022-05-05 14:28:27,134 INFO [train.py:715] (3/8) Epoch 6, batch 19750, loss[loss=0.1898, simple_loss=0.2598, pruned_loss=0.05986, over 4839.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2203, pruned_loss=0.03878, over 972276.29 frames.], batch size: 15, lr: 3.30e-04
+2022-05-05 14:29:05,246 INFO [train.py:715] (3/8) Epoch 6, batch 19800, loss[loss=0.1564, simple_loss=0.2225, pruned_loss=0.04516, over 4864.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2206, pruned_loss=0.03928, over 971616.98 frames.], batch size: 30, lr: 3.30e-04
+2022-05-05 14:29:44,600 INFO [train.py:715] (3/8) Epoch 6, batch 19850, loss[loss=0.1773, simple_loss=0.2513, pruned_loss=0.05162, over 4795.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.0394, over 972273.24 frames.], batch size: 24, lr: 3.30e-04
+2022-05-05 14:30:24,342 INFO [train.py:715] (3/8) Epoch 6, batch 19900, loss[loss=0.1301, simple_loss=0.2049, pruned_loss=0.02761, over 4811.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.03961, over 972412.76 frames.], batch size: 25, lr: 3.30e-04
+2022-05-05 14:31:02,425 INFO [train.py:715] (3/8) Epoch 6, batch 19950, loss[loss=0.1829, simple_loss=0.2559, pruned_loss=0.05494, over 4837.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2219, pruned_loss=0.03994, over 973234.40 frames.], batch size: 32, lr: 3.30e-04
+2022-05-05 14:31:41,549 INFO [train.py:715] (3/8) Epoch 6, batch 20000, loss[loss=0.1412, simple_loss=0.2044, pruned_loss=0.039, over 4696.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2206, pruned_loss=0.03936, over 973184.49 frames.], batch size: 15, lr: 3.30e-04
+2022-05-05 14:32:21,023 INFO [train.py:715] (3/8) Epoch 6, batch 20050, loss[loss=0.1288, simple_loss=0.2096, pruned_loss=0.02401, over 4705.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2206, pruned_loss=0.03945, over 972791.43 frames.], batch size: 15, lr: 3.30e-04
+2022-05-05 14:32:59,453 INFO [train.py:715] (3/8) Epoch 6, batch 20100, loss[loss=0.1615, simple_loss=0.2446, pruned_loss=0.03925, over 4933.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2198, pruned_loss=0.03897, over 972449.30 frames.], batch size: 39, lr: 3.30e-04
+2022-05-05 14:33:38,527 INFO [train.py:715] (3/8) Epoch 6, batch 20150, loss[loss=0.1678, simple_loss=0.2503, pruned_loss=0.04271, over 4788.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2208, pruned_loss=0.03936, over 972505.85 frames.], batch size: 18, lr: 3.30e-04
+2022-05-05 14:34:17,809 INFO [train.py:715] (3/8) Epoch 6, batch 20200, loss[loss=0.1445, simple_loss=0.2251, pruned_loss=0.03194, over 4791.00 frames.], tot_loss[loss=0.1499, simple_loss=0.221, pruned_loss=0.03938, over 972796.86 frames.], batch size: 18, lr: 3.30e-04
+2022-05-05 14:34:56,736 INFO [train.py:715] (3/8) Epoch 6, batch 20250, loss[loss=0.134, simple_loss=0.1922, pruned_loss=0.03788, over 4770.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03968, over 972637.38 frames.], batch size: 14, lr: 3.30e-04
+2022-05-05 14:35:35,498 INFO [train.py:715] (3/8) Epoch 6, batch 20300, loss[loss=0.1611, simple_loss=0.2407, pruned_loss=0.04073, over 4869.00 frames.], tot_loss[loss=0.1511, simple_loss=0.222, pruned_loss=0.04004, over 972564.18 frames.], batch size: 20, lr: 3.30e-04
+2022-05-05 14:36:14,861 INFO [train.py:715] (3/8) Epoch 6, batch 20350, loss[loss=0.1355, simple_loss=0.2062, pruned_loss=0.03234, over 4987.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2211, pruned_loss=0.03941, over 972779.99 frames.], batch size: 28, lr: 3.30e-04
+2022-05-05 14:36:54,306 INFO [train.py:715] (3/8) Epoch 6, batch 20400, loss[loss=0.135, simple_loss=0.2045, pruned_loss=0.03273, over 4707.00 frames.], tot_loss[loss=0.1498, simple_loss=0.221, pruned_loss=0.03934, over 971901.81 frames.], batch size: 15, lr: 3.30e-04
+2022-05-05 14:37:32,666 INFO [train.py:715] (3/8) Epoch 6, batch 20450, loss[loss=0.1315, simple_loss=0.1979, pruned_loss=0.03252, over 4896.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2204, pruned_loss=0.0393, over 971832.13 frames.], batch size: 17, lr: 3.30e-04
+2022-05-05 14:38:11,469 INFO [train.py:715] (3/8) Epoch 6, batch 20500, loss[loss=0.1564, simple_loss=0.2334, pruned_loss=0.03967, over 4946.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03935, over 971995.94 frames.], batch size: 21, lr: 3.30e-04
+2022-05-05 14:38:50,531 INFO [train.py:715] (3/8) Epoch 6, batch 20550, loss[loss=0.1315, simple_loss=0.2135, pruned_loss=0.02477, over 4852.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2208, pruned_loss=0.03897, over 973051.43 frames.], batch size: 20, lr: 3.30e-04
+2022-05-05 14:39:29,697 INFO [train.py:715] (3/8) Epoch 6, batch 20600, loss[loss=0.1834, simple_loss=0.2587, pruned_loss=0.0541, over 4903.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2209, pruned_loss=0.03892, over 972997.31 frames.], batch size: 19, lr: 3.30e-04
+2022-05-05 14:40:07,961 INFO [train.py:715] (3/8) Epoch 6, batch 20650, loss[loss=0.1408, simple_loss=0.2142, pruned_loss=0.03367, over 4901.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03882, over 972724.86 frames.], batch size: 23, lr: 3.30e-04
+2022-05-05 14:40:46,653 INFO [train.py:715] (3/8) Epoch 6, batch 20700, loss[loss=0.148, simple_loss=0.2095, pruned_loss=0.04328, over 4872.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03877, over 972734.50 frames.], batch size: 39, lr: 3.30e-04
+2022-05-05 14:41:25,992 INFO [train.py:715] (3/8) Epoch 6, batch 20750, loss[loss=0.1193, simple_loss=0.1931, pruned_loss=0.02276, over 4757.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2195, pruned_loss=0.03831, over 971692.07 frames.], batch size: 16, lr: 3.30e-04
+2022-05-05 14:42:04,394 INFO [train.py:715] (3/8) Epoch 6, batch 20800, loss[loss=0.1491, simple_loss=0.2173, pruned_loss=0.04043, over 4759.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2198, pruned_loss=0.03824, over 971588.21 frames.], batch size: 19, lr: 3.30e-04
+2022-05-05 14:42:43,608 INFO [train.py:715] (3/8) Epoch 6, batch 20850, loss[loss=0.1607, simple_loss=0.2289, pruned_loss=0.04629, over 4923.00 frames.], tot_loss[loss=0.1486, simple_loss=0.22, pruned_loss=0.03859, over 971605.98 frames.], batch size: 18, lr: 3.30e-04
+2022-05-05 14:43:22,882 INFO [train.py:715] (3/8) Epoch 6, batch 20900, loss[loss=0.1956, simple_loss=0.2546, pruned_loss=0.06835, over 4975.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2198, pruned_loss=0.03868, over 971698.03 frames.], batch size: 39, lr: 3.30e-04
+2022-05-05 14:44:02,109 INFO [train.py:715] (3/8) Epoch 6, batch 20950, loss[loss=0.1292, simple_loss=0.2021, pruned_loss=0.02815, over 4947.00 frames.], tot_loss[loss=0.148, simple_loss=0.2192, pruned_loss=0.03837, over 971927.23 frames.], batch size: 23, lr: 3.30e-04
+2022-05-05 14:44:40,092 INFO [train.py:715] (3/8) Epoch 6, batch 21000, loss[loss=0.1607, simple_loss=0.2321, pruned_loss=0.04468, over 4903.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.03816, over 972339.90 frames.], batch size: 17, lr: 3.29e-04
+2022-05-05 14:44:40,093 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 14:44:51,876 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1089, simple_loss=0.1939, pruned_loss=0.01192, over 914524.00 frames.
+2022-05-05 14:45:30,117 INFO [train.py:715] (3/8) Epoch 6, batch 21050, loss[loss=0.1639, simple_loss=0.241, pruned_loss=0.04339, over 4884.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03772, over 972411.30 frames.], batch size: 19, lr: 3.29e-04
+2022-05-05 14:46:09,486 INFO [train.py:715] (3/8) Epoch 6, batch 21100, loss[loss=0.1316, simple_loss=0.1924, pruned_loss=0.03534, over 4962.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03806, over 972336.52 frames.], batch size: 21, lr: 3.29e-04
+2022-05-05 14:46:48,889 INFO [train.py:715] (3/8) Epoch 6, batch 21150, loss[loss=0.1909, simple_loss=0.2483, pruned_loss=0.06682, over 4876.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03779, over 971783.61 frames.], batch size: 32, lr: 3.29e-04
+2022-05-05 14:47:27,345 INFO [train.py:715] (3/8) Epoch 6, batch 21200, loss[loss=0.1557, simple_loss=0.23, pruned_loss=0.04068, over 4782.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2193, pruned_loss=0.03796, over 971883.68 frames.], batch size: 17, lr: 3.29e-04
+2022-05-05 14:48:06,354 INFO [train.py:715] (3/8) Epoch 6, batch 21250, loss[loss=0.1676, simple_loss=0.2368, pruned_loss=0.04916, over 4686.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2193, pruned_loss=0.03817, over 972128.33 frames.], batch size: 15, lr: 3.29e-04
+2022-05-05 14:48:45,978 INFO [train.py:715] (3/8) Epoch 6, batch 21300, loss[loss=0.1858, simple_loss=0.2434, pruned_loss=0.06417, over 4695.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2201, pruned_loss=0.03875, over 971880.64 frames.], batch size: 15, lr: 3.29e-04
+2022-05-05 14:49:24,956 INFO [train.py:715] (3/8) Epoch 6, batch 21350, loss[loss=0.1382, simple_loss=0.2078, pruned_loss=0.03432, over 4838.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2197, pruned_loss=0.03876, over 972182.18 frames.], batch size: 15, lr: 3.29e-04
+2022-05-05 14:50:03,788 INFO [train.py:715] (3/8) Epoch 6, batch 21400, loss[loss=0.1631, simple_loss=0.2357, pruned_loss=0.04521, over 4985.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2199, pruned_loss=0.03866, over 972103.67 frames.], batch size: 16, lr: 3.29e-04
+2022-05-05 14:50:42,551 INFO [train.py:715] (3/8) Epoch 6, batch 21450, loss[loss=0.1479, simple_loss=0.2101, pruned_loss=0.04286, over 4914.00 frames.], tot_loss[loss=0.148, simple_loss=0.2194, pruned_loss=0.03827, over 971671.43 frames.], batch size: 17, lr: 3.29e-04
+2022-05-05 14:51:21,822 INFO [train.py:715] (3/8) Epoch 6, batch 21500, loss[loss=0.1481, simple_loss=0.2232, pruned_loss=0.03648, over 4883.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03792, over 971001.85 frames.], batch size: 22, lr: 3.29e-04
+2022-05-05 14:52:00,294 INFO [train.py:715] (3/8) Epoch 6, batch 21550, loss[loss=0.1586, simple_loss=0.2248, pruned_loss=0.04622, over 4868.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2189, pruned_loss=0.03796, over 970723.91 frames.], batch size: 30, lr: 3.29e-04
+2022-05-05 14:52:39,313 INFO [train.py:715] (3/8) Epoch 6, batch 21600, loss[loss=0.1531, simple_loss=0.2266, pruned_loss=0.03976, over 4978.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03849, over 971768.31 frames.], batch size: 28, lr: 3.29e-04
+2022-05-05 14:53:18,465 INFO [train.py:715] (3/8) Epoch 6, batch 21650, loss[loss=0.1531, simple_loss=0.2201, pruned_loss=0.04309, over 4934.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2208, pruned_loss=0.03904, over 972191.18 frames.], batch size: 29, lr: 3.29e-04
+2022-05-05 14:53:57,744 INFO [train.py:715] (3/8) Epoch 6, batch 21700, loss[loss=0.1877, simple_loss=0.2504, pruned_loss=0.06254, over 4934.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2206, pruned_loss=0.03893, over 973303.13 frames.], batch size: 18, lr: 3.29e-04
+2022-05-05 14:54:36,456 INFO [train.py:715] (3/8) Epoch 6, batch 21750, loss[loss=0.1482, simple_loss=0.2168, pruned_loss=0.03984, over 4851.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2201, pruned_loss=0.03855, over 972461.90 frames.], batch size: 30, lr: 3.29e-04
+2022-05-05 14:55:15,315 INFO [train.py:715] (3/8) Epoch 6, batch 21800, loss[loss=0.1341, simple_loss=0.2056, pruned_loss=0.03132, over 4951.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2204, pruned_loss=0.03867, over 972521.24 frames.], batch size: 35, lr: 3.29e-04
+2022-05-05 14:55:54,106 INFO [train.py:715] (3/8) Epoch 6, batch 21850, loss[loss=0.1638, simple_loss=0.2264, pruned_loss=0.05058, over 4909.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03859, over 972827.22 frames.], batch size: 17, lr: 3.29e-04
+2022-05-05 14:56:32,647 INFO [train.py:715] (3/8) Epoch 6, batch 21900, loss[loss=0.1808, simple_loss=0.2525, pruned_loss=0.05452, over 4946.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2206, pruned_loss=0.03863, over 973208.16 frames.], batch size: 29, lr: 3.29e-04
+2022-05-05 14:57:11,519 INFO [train.py:715] (3/8) Epoch 6, batch 21950, loss[loss=0.151, simple_loss=0.2256, pruned_loss=0.03826, over 4872.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2207, pruned_loss=0.03887, over 972473.99 frames.], batch size: 32, lr: 3.29e-04
+2022-05-05 14:57:50,236 INFO [train.py:715] (3/8) Epoch 6, batch 22000, loss[loss=0.1905, simple_loss=0.2721, pruned_loss=0.05447, over 4832.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2203, pruned_loss=0.0387, over 972557.58 frames.], batch size: 15, lr: 3.29e-04
+2022-05-05 14:58:29,944 INFO [train.py:715] (3/8) Epoch 6, batch 22050, loss[loss=0.1914, simple_loss=0.2555, pruned_loss=0.06362, over 4901.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03854, over 973465.75 frames.], batch size: 22, lr: 3.29e-04
+2022-05-05 14:59:08,261 INFO [train.py:715] (3/8) Epoch 6, batch 22100, loss[loss=0.1329, simple_loss=0.2029, pruned_loss=0.03145, over 4948.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2194, pruned_loss=0.03851, over 972816.41 frames.], batch size: 35, lr: 3.29e-04
+2022-05-05 14:59:47,063 INFO [train.py:715] (3/8) Epoch 6, batch 22150, loss[loss=0.1582, simple_loss=0.2364, pruned_loss=0.04, over 4864.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2192, pruned_loss=0.03803, over 972526.41 frames.], batch size: 32, lr: 3.29e-04
+2022-05-05 15:00:26,256 INFO [train.py:715] (3/8) Epoch 6, batch 22200, loss[loss=0.1707, simple_loss=0.2388, pruned_loss=0.05131, over 4815.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2191, pruned_loss=0.03822, over 971705.27 frames.], batch size: 15, lr: 3.29e-04
+2022-05-05 15:01:04,918 INFO [train.py:715] (3/8) Epoch 6, batch 22250, loss[loss=0.1481, simple_loss=0.2137, pruned_loss=0.04121, over 4804.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2203, pruned_loss=0.03881, over 972242.69 frames.], batch size: 21, lr: 3.29e-04
+2022-05-05 15:01:43,598 INFO [train.py:715] (3/8) Epoch 6, batch 22300, loss[loss=0.1407, simple_loss=0.2277, pruned_loss=0.02685, over 4889.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2208, pruned_loss=0.03845, over 972805.89 frames.], batch size: 19, lr: 3.29e-04
+2022-05-05 15:02:22,657 INFO [train.py:715] (3/8) Epoch 6, batch 22350, loss[loss=0.1273, simple_loss=0.203, pruned_loss=0.02576, over 4738.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2201, pruned_loss=0.03853, over 972662.42 frames.], batch size: 16, lr: 3.29e-04
+2022-05-05 15:03:02,004 INFO [train.py:715] (3/8) Epoch 6, batch 22400, loss[loss=0.1373, simple_loss=0.2126, pruned_loss=0.03107, over 4926.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2202, pruned_loss=0.03862, over 972535.86 frames.], batch size: 21, lr: 3.29e-04
+2022-05-05 15:03:40,491 INFO [train.py:715] (3/8) Epoch 6, batch 22450, loss[loss=0.1554, simple_loss=0.2214, pruned_loss=0.04473, over 4977.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03842, over 972613.85 frames.], batch size: 15, lr: 3.28e-04
+2022-05-05 15:04:19,441 INFO [train.py:715] (3/8) Epoch 6, batch 22500, loss[loss=0.17, simple_loss=0.2388, pruned_loss=0.05056, over 4982.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2194, pruned_loss=0.03865, over 972455.27 frames.], batch size: 33, lr: 3.28e-04
+2022-05-05 15:04:58,760 INFO [train.py:715] (3/8) Epoch 6, batch 22550, loss[loss=0.1399, simple_loss=0.2054, pruned_loss=0.03719, over 4793.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2193, pruned_loss=0.03853, over 972891.28 frames.], batch size: 21, lr: 3.28e-04
+2022-05-05 15:05:37,179 INFO [train.py:715] (3/8) Epoch 6, batch 22600, loss[loss=0.1344, simple_loss=0.2024, pruned_loss=0.03322, over 4796.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2195, pruned_loss=0.0384, over 972806.23 frames.], batch size: 24, lr: 3.28e-04
+2022-05-05 15:06:16,007 INFO [train.py:715] (3/8) Epoch 6, batch 22650, loss[loss=0.1678, simple_loss=0.2302, pruned_loss=0.05263, over 4924.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2191, pruned_loss=0.03809, over 972001.89 frames.], batch size: 21, lr: 3.28e-04
+2022-05-05 15:06:54,604 INFO [train.py:715] (3/8) Epoch 6, batch 22700, loss[loss=0.1519, simple_loss=0.2289, pruned_loss=0.03745, over 4979.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2198, pruned_loss=0.03816, over 973186.43 frames.], batch size: 24, lr: 3.28e-04
+2022-05-05 15:07:33,406 INFO [train.py:715] (3/8) Epoch 6, batch 22750, loss[loss=0.1479, simple_loss=0.2198, pruned_loss=0.03804, over 4958.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2206, pruned_loss=0.03887, over 972927.72 frames.], batch size: 25, lr: 3.28e-04
+2022-05-05 15:08:11,868 INFO [train.py:715] (3/8) Epoch 6, batch 22800, loss[loss=0.1346, simple_loss=0.2077, pruned_loss=0.0308, over 4815.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2206, pruned_loss=0.03861, over 972698.68 frames.], batch size: 24, lr: 3.28e-04
+2022-05-05 15:08:50,376 INFO [train.py:715] (3/8) Epoch 6, batch 22850, loss[loss=0.1715, simple_loss=0.2357, pruned_loss=0.05364, over 4846.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03893, over 972749.69 frames.], batch size: 15, lr: 3.28e-04
+2022-05-05 15:09:29,028 INFO [train.py:715] (3/8) Epoch 6, batch 22900, loss[loss=0.1472, simple_loss=0.2213, pruned_loss=0.03652, over 4955.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.0392, over 973034.98 frames.], batch size: 14, lr: 3.28e-04
+2022-05-05 15:10:08,157 INFO [train.py:715] (3/8) Epoch 6, batch 22950, loss[loss=0.1354, simple_loss=0.1978, pruned_loss=0.0365, over 4962.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2205, pruned_loss=0.03903, over 972528.46 frames.], batch size: 14, lr: 3.28e-04
+2022-05-05 15:10:46,572 INFO [train.py:715] (3/8) Epoch 6, batch 23000, loss[loss=0.1268, simple_loss=0.2048, pruned_loss=0.0244, over 4773.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.0386, over 972703.28 frames.], batch size: 14, lr: 3.28e-04
+2022-05-05 15:11:25,826 INFO [train.py:715] (3/8) Epoch 6, batch 23050, loss[loss=0.1322, simple_loss=0.1969, pruned_loss=0.03376, over 4860.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03857, over 972649.11 frames.], batch size: 20, lr: 3.28e-04
+2022-05-05 15:12:05,300 INFO [train.py:715] (3/8) Epoch 6, batch 23100, loss[loss=0.142, simple_loss=0.2169, pruned_loss=0.03359, over 4864.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03846, over 973079.60 frames.], batch size: 16, lr: 3.28e-04
+2022-05-05 15:12:46,120 INFO [train.py:715] (3/8) Epoch 6, batch 23150, loss[loss=0.1087, simple_loss=0.1847, pruned_loss=0.0164, over 4954.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03839, over 972341.44 frames.], batch size: 29, lr: 3.28e-04
+2022-05-05 15:13:25,467 INFO [train.py:715] (3/8) Epoch 6, batch 23200, loss[loss=0.1549, simple_loss=0.2281, pruned_loss=0.04084, over 4775.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2198, pruned_loss=0.03893, over 972347.46 frames.], batch size: 14, lr: 3.28e-04
+2022-05-05 15:14:04,866 INFO [train.py:715] (3/8) Epoch 6, batch 23250, loss[loss=0.1332, simple_loss=0.2186, pruned_loss=0.02394, over 4872.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2195, pruned_loss=0.03863, over 972183.62 frames.], batch size: 16, lr: 3.28e-04
+2022-05-05 15:14:43,526 INFO [train.py:715] (3/8) Epoch 6, batch 23300, loss[loss=0.1692, simple_loss=0.2303, pruned_loss=0.05402, over 4856.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03853, over 971585.83 frames.], batch size: 20, lr: 3.28e-04
+2022-05-05 15:15:21,521 INFO [train.py:715] (3/8) Epoch 6, batch 23350, loss[loss=0.175, simple_loss=0.229, pruned_loss=0.0605, over 4899.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2194, pruned_loss=0.03852, over 971813.32 frames.], batch size: 39, lr: 3.28e-04
+2022-05-05 15:16:00,570 INFO [train.py:715] (3/8) Epoch 6, batch 23400, loss[loss=0.1592, simple_loss=0.2422, pruned_loss=0.03809, over 4896.00 frames.], tot_loss[loss=0.148, simple_loss=0.2193, pruned_loss=0.03833, over 971990.50 frames.], batch size: 17, lr: 3.28e-04
+2022-05-05 15:16:40,147 INFO [train.py:715] (3/8) Epoch 6, batch 23450, loss[loss=0.1385, simple_loss=0.2096, pruned_loss=0.03371, over 4991.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2189, pruned_loss=0.0382, over 971826.89 frames.], batch size: 20, lr: 3.28e-04
+2022-05-05 15:17:19,121 INFO [train.py:715] (3/8) Epoch 6, batch 23500, loss[loss=0.1399, simple_loss=0.2108, pruned_loss=0.03449, over 4782.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03783, over 971668.15 frames.], batch size: 17, lr: 3.28e-04
+2022-05-05 15:17:58,302 INFO [train.py:715] (3/8) Epoch 6, batch 23550, loss[loss=0.1257, simple_loss=0.1981, pruned_loss=0.02662, over 4949.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03724, over 971383.63 frames.], batch size: 21, lr: 3.28e-04
+2022-05-05 15:18:37,514 INFO [train.py:715] (3/8) Epoch 6, batch 23600, loss[loss=0.1729, simple_loss=0.2351, pruned_loss=0.0554, over 4867.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03773, over 971468.67 frames.], batch size: 32, lr: 3.28e-04
+2022-05-05 15:19:16,255 INFO [train.py:715] (3/8) Epoch 6, batch 23650, loss[loss=0.1649, simple_loss=0.231, pruned_loss=0.04944, over 4688.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2197, pruned_loss=0.0382, over 972025.22 frames.], batch size: 15, lr: 3.28e-04
+2022-05-05 15:19:54,390 INFO [train.py:715] (3/8) Epoch 6, batch 23700, loss[loss=0.1759, simple_loss=0.2382, pruned_loss=0.05675, over 4866.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2196, pruned_loss=0.03823, over 972697.93 frames.], batch size: 38, lr: 3.28e-04
+2022-05-05 15:20:33,415 INFO [train.py:715] (3/8) Epoch 6, batch 23750, loss[loss=0.1084, simple_loss=0.1796, pruned_loss=0.01856, over 4778.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2192, pruned_loss=0.03791, over 971886.64 frames.], batch size: 12, lr: 3.28e-04
+2022-05-05 15:21:12,835 INFO [train.py:715] (3/8) Epoch 6, batch 23800, loss[loss=0.129, simple_loss=0.1991, pruned_loss=0.02944, over 4809.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2192, pruned_loss=0.0381, over 970836.57 frames.], batch size: 13, lr: 3.28e-04
+2022-05-05 15:21:51,202 INFO [train.py:715] (3/8) Epoch 6, batch 23850, loss[loss=0.1602, simple_loss=0.235, pruned_loss=0.04273, over 4700.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2203, pruned_loss=0.03863, over 971001.54 frames.], batch size: 15, lr: 3.27e-04
+2022-05-05 15:22:29,815 INFO [train.py:715] (3/8) Epoch 6, batch 23900, loss[loss=0.1615, simple_loss=0.2488, pruned_loss=0.03716, over 4971.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2201, pruned_loss=0.03839, over 970711.20 frames.], batch size: 15, lr: 3.27e-04
+2022-05-05 15:23:08,544 INFO [train.py:715] (3/8) Epoch 6, batch 23950, loss[loss=0.136, simple_loss=0.2053, pruned_loss=0.03339, over 4846.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2191, pruned_loss=0.03767, over 971325.42 frames.], batch size: 30, lr: 3.27e-04
+2022-05-05 15:23:47,218 INFO [train.py:715] (3/8) Epoch 6, batch 24000, loss[loss=0.1461, simple_loss=0.2229, pruned_loss=0.03466, over 4931.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2191, pruned_loss=0.03767, over 971597.99 frames.], batch size: 21, lr: 3.27e-04
+2022-05-05 15:23:47,219 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 15:23:58,202 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1089, simple_loss=0.1939, pruned_loss=0.01195, over 914524.00 frames.
+2022-05-05 15:24:36,968 INFO [train.py:715] (3/8) Epoch 6, batch 24050, loss[loss=0.156, simple_loss=0.2316, pruned_loss=0.04023, over 4984.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2189, pruned_loss=0.03781, over 972104.62 frames.], batch size: 25, lr: 3.27e-04
+2022-05-05 15:25:15,031 INFO [train.py:715] (3/8) Epoch 6, batch 24100, loss[loss=0.1472, simple_loss=0.2175, pruned_loss=0.03844, over 4919.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2191, pruned_loss=0.03792, over 971948.24 frames.], batch size: 19, lr: 3.27e-04
+2022-05-05 15:25:53,706 INFO [train.py:715] (3/8) Epoch 6, batch 24150, loss[loss=0.1619, simple_loss=0.2321, pruned_loss=0.04582, over 4854.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03737, over 972039.56 frames.], batch size: 15, lr: 3.27e-04
+2022-05-05 15:26:32,799 INFO [train.py:715] (3/8) Epoch 6, batch 24200, loss[loss=0.1121, simple_loss=0.1884, pruned_loss=0.01791, over 4924.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2176, pruned_loss=0.03706, over 971733.76 frames.], batch size: 23, lr: 3.27e-04
+2022-05-05 15:27:10,719 INFO [train.py:715] (3/8) Epoch 6, batch 24250, loss[loss=0.1398, simple_loss=0.1964, pruned_loss=0.04155, over 4874.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2171, pruned_loss=0.03693, over 972753.89 frames.], batch size: 16, lr: 3.27e-04
+2022-05-05 15:27:49,115 INFO [train.py:715] (3/8) Epoch 6, batch 24300, loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03053, over 4950.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2181, pruned_loss=0.03762, over 973428.76 frames.], batch size: 23, lr: 3.27e-04
+2022-05-05 15:28:28,042 INFO [train.py:715] (3/8) Epoch 6, batch 24350, loss[loss=0.1156, simple_loss=0.1836, pruned_loss=0.02381, over 4785.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2183, pruned_loss=0.03793, over 973537.47 frames.], batch size: 14, lr: 3.27e-04
+2022-05-05 15:29:07,159 INFO [train.py:715] (3/8) Epoch 6, batch 24400, loss[loss=0.1291, simple_loss=0.208, pruned_loss=0.02504, over 4831.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2189, pruned_loss=0.03808, over 973563.40 frames.], batch size: 15, lr: 3.27e-04
+2022-05-05 15:29:45,511 INFO [train.py:715] (3/8) Epoch 6, batch 24450, loss[loss=0.1617, simple_loss=0.229, pruned_loss=0.04718, over 4980.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2197, pruned_loss=0.03808, over 972785.51 frames.], batch size: 28, lr: 3.27e-04
+2022-05-05 15:30:24,119 INFO [train.py:715] (3/8) Epoch 6, batch 24500, loss[loss=0.1561, simple_loss=0.231, pruned_loss=0.04064, over 4916.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2191, pruned_loss=0.03775, over 972326.60 frames.], batch size: 17, lr: 3.27e-04
+2022-05-05 15:31:03,937 INFO [train.py:715] (3/8) Epoch 6, batch 24550, loss[loss=0.1289, simple_loss=0.2022, pruned_loss=0.02784, over 4940.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2184, pruned_loss=0.0376, over 971169.52 frames.], batch size: 29, lr: 3.27e-04
+2022-05-05 15:31:42,161 INFO [train.py:715] (3/8) Epoch 6, batch 24600, loss[loss=0.1343, simple_loss=0.2037, pruned_loss=0.0325, over 4741.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03805, over 972442.60 frames.], batch size: 16, lr: 3.27e-04
+2022-05-05 15:32:21,360 INFO [train.py:715] (3/8) Epoch 6, batch 24650, loss[loss=0.1461, simple_loss=0.2222, pruned_loss=0.03499, over 4804.00 frames.], tot_loss[loss=0.147, simple_loss=0.2181, pruned_loss=0.03788, over 972857.50 frames.], batch size: 25, lr: 3.27e-04
+2022-05-05 15:33:00,612 INFO [train.py:715] (3/8) Epoch 6, batch 24700, loss[loss=0.157, simple_loss=0.229, pruned_loss=0.04249, over 4872.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2182, pruned_loss=0.03813, over 973070.35 frames.], batch size: 22, lr: 3.27e-04
+2022-05-05 15:33:39,471 INFO [train.py:715] (3/8) Epoch 6, batch 24750, loss[loss=0.1736, simple_loss=0.2362, pruned_loss=0.05551, over 4692.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2189, pruned_loss=0.03803, over 971842.69 frames.], batch size: 15, lr: 3.27e-04
+2022-05-05 15:34:17,834 INFO [train.py:715] (3/8) Epoch 6, batch 24800, loss[loss=0.1678, simple_loss=0.2415, pruned_loss=0.04702, over 4791.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2197, pruned_loss=0.03865, over 972030.98 frames.], batch size: 17, lr: 3.27e-04
+2022-05-05 15:34:56,838 INFO [train.py:715] (3/8) Epoch 6, batch 24850, loss[loss=0.1369, simple_loss=0.2135, pruned_loss=0.03017, over 4927.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2183, pruned_loss=0.0381, over 972102.16 frames.], batch size: 29, lr: 3.27e-04
+2022-05-05 15:35:36,647 INFO [train.py:715] (3/8) Epoch 6, batch 24900, loss[loss=0.1652, simple_loss=0.2256, pruned_loss=0.05235, over 4984.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2199, pruned_loss=0.03871, over 972787.50 frames.], batch size: 35, lr: 3.27e-04
+2022-05-05 15:36:14,919 INFO [train.py:715] (3/8) Epoch 6, batch 24950, loss[loss=0.1572, simple_loss=0.2333, pruned_loss=0.04054, over 4834.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03973, over 973759.89 frames.], batch size: 15, lr: 3.27e-04
+2022-05-05 15:36:53,555 INFO [train.py:715] (3/8) Epoch 6, batch 25000, loss[loss=0.1271, simple_loss=0.1973, pruned_loss=0.02849, over 4904.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2207, pruned_loss=0.03925, over 973760.10 frames.], batch size: 19, lr: 3.27e-04
+2022-05-05 15:37:32,636 INFO [train.py:715] (3/8) Epoch 6, batch 25050, loss[loss=0.1361, simple_loss=0.2063, pruned_loss=0.03294, over 4791.00 frames.], tot_loss[loss=0.1484, simple_loss=0.22, pruned_loss=0.03846, over 974048.67 frames.], batch size: 17, lr: 3.27e-04
+2022-05-05 15:38:11,570 INFO [train.py:715] (3/8) Epoch 6, batch 25100, loss[loss=0.1088, simple_loss=0.1758, pruned_loss=0.02089, over 4755.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2202, pruned_loss=0.03855, over 973901.92 frames.], batch size: 12, lr: 3.27e-04
+2022-05-05 15:38:50,094 INFO [train.py:715] (3/8) Epoch 6, batch 25150, loss[loss=0.168, simple_loss=0.2427, pruned_loss=0.04661, over 4938.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2204, pruned_loss=0.03909, over 973700.53 frames.], batch size: 21, lr: 3.27e-04
+2022-05-05 15:39:28,932 INFO [train.py:715] (3/8) Epoch 6, batch 25200, loss[loss=0.1435, simple_loss=0.2161, pruned_loss=0.03547, over 4793.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2203, pruned_loss=0.03908, over 973172.90 frames.], batch size: 24, lr: 3.27e-04
+2022-05-05 15:40:07,779 INFO [train.py:715] (3/8) Epoch 6, batch 25250, loss[loss=0.1254, simple_loss=0.2024, pruned_loss=0.02422, over 4823.00 frames.], tot_loss[loss=0.149, simple_loss=0.2206, pruned_loss=0.03873, over 971935.34 frames.], batch size: 26, lr: 3.26e-04
+2022-05-05 15:40:46,084 INFO [train.py:715] (3/8) Epoch 6, batch 25300, loss[loss=0.1651, simple_loss=0.2307, pruned_loss=0.0497, over 4823.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2196, pruned_loss=0.03864, over 971420.98 frames.], batch size: 15, lr: 3.26e-04
+2022-05-05 15:41:24,368 INFO [train.py:715] (3/8) Epoch 6, batch 25350, loss[loss=0.1315, simple_loss=0.1895, pruned_loss=0.03681, over 4856.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2194, pruned_loss=0.03846, over 972006.30 frames.], batch size: 32, lr: 3.26e-04
+2022-05-05 15:42:03,174 INFO [train.py:715] (3/8) Epoch 6, batch 25400, loss[loss=0.1679, simple_loss=0.2408, pruned_loss=0.0475, over 4773.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2191, pruned_loss=0.03799, over 972362.24 frames.], batch size: 18, lr: 3.26e-04
+2022-05-05 15:42:41,994 INFO [train.py:715] (3/8) Epoch 6, batch 25450, loss[loss=0.1236, simple_loss=0.2018, pruned_loss=0.02273, over 4859.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2203, pruned_loss=0.03828, over 972171.70 frames.], batch size: 20, lr: 3.26e-04
+2022-05-05 15:43:20,091 INFO [train.py:715] (3/8) Epoch 6, batch 25500, loss[loss=0.115, simple_loss=0.1901, pruned_loss=0.01991, over 4782.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2192, pruned_loss=0.03814, over 971631.03 frames.], batch size: 14, lr: 3.26e-04
+2022-05-05 15:43:58,583 INFO [train.py:715] (3/8) Epoch 6, batch 25550, loss[loss=0.144, simple_loss=0.2121, pruned_loss=0.038, over 4900.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2212, pruned_loss=0.03929, over 972166.05 frames.], batch size: 19, lr: 3.26e-04
+2022-05-05 15:44:37,703 INFO [train.py:715] (3/8) Epoch 6, batch 25600, loss[loss=0.1428, simple_loss=0.2141, pruned_loss=0.03571, over 4863.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2209, pruned_loss=0.03936, over 972281.00 frames.], batch size: 30, lr: 3.26e-04
+2022-05-05 15:45:15,937 INFO [train.py:715] (3/8) Epoch 6, batch 25650, loss[loss=0.1495, simple_loss=0.2234, pruned_loss=0.0378, over 4849.00 frames.], tot_loss[loss=0.15, simple_loss=0.2214, pruned_loss=0.03933, over 972365.46 frames.], batch size: 30, lr: 3.26e-04
+2022-05-05 15:45:54,740 INFO [train.py:715] (3/8) Epoch 6, batch 25700, loss[loss=0.1826, simple_loss=0.2446, pruned_loss=0.06027, over 4776.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2212, pruned_loss=0.03919, over 972349.10 frames.], batch size: 19, lr: 3.26e-04
+2022-05-05 15:46:34,044 INFO [train.py:715] (3/8) Epoch 6, batch 25750, loss[loss=0.1434, simple_loss=0.2116, pruned_loss=0.03757, over 4913.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2217, pruned_loss=0.03948, over 973080.97 frames.], batch size: 18, lr: 3.26e-04
+2022-05-05 15:47:12,320 INFO [train.py:715] (3/8) Epoch 6, batch 25800, loss[loss=0.1536, simple_loss=0.2118, pruned_loss=0.04775, over 4801.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03951, over 973273.30 frames.], batch size: 21, lr: 3.26e-04
+2022-05-05 15:47:50,577 INFO [train.py:715] (3/8) Epoch 6, batch 25850, loss[loss=0.163, simple_loss=0.2374, pruned_loss=0.04427, over 4776.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2208, pruned_loss=0.0395, over 973155.52 frames.], batch size: 14, lr: 3.26e-04
+2022-05-05 15:48:29,220 INFO [train.py:715] (3/8) Epoch 6, batch 25900, loss[loss=0.15, simple_loss=0.2189, pruned_loss=0.04057, over 4794.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2205, pruned_loss=0.03922, over 972542.67 frames.], batch size: 17, lr: 3.26e-04
+2022-05-05 15:49:08,368 INFO [train.py:715] (3/8) Epoch 6, batch 25950, loss[loss=0.1452, simple_loss=0.2117, pruned_loss=0.03941, over 4742.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2207, pruned_loss=0.03938, over 972795.68 frames.], batch size: 16, lr: 3.26e-04
+2022-05-05 15:49:46,039 INFO [train.py:715] (3/8) Epoch 6, batch 26000, loss[loss=0.1248, simple_loss=0.1933, pruned_loss=0.02812, over 4813.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2204, pruned_loss=0.03948, over 973127.35 frames.], batch size: 13, lr: 3.26e-04
+2022-05-05 15:50:24,229 INFO [train.py:715] (3/8) Epoch 6, batch 26050, loss[loss=0.1406, simple_loss=0.2074, pruned_loss=0.03687, over 4820.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2201, pruned_loss=0.03921, over 973045.46 frames.], batch size: 15, lr: 3.26e-04
+2022-05-05 15:51:03,226 INFO [train.py:715] (3/8) Epoch 6, batch 26100, loss[loss=0.1599, simple_loss=0.2308, pruned_loss=0.04447, over 4861.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2196, pruned_loss=0.03932, over 973281.74 frames.], batch size: 30, lr: 3.26e-04
+2022-05-05 15:51:41,623 INFO [train.py:715] (3/8) Epoch 6, batch 26150, loss[loss=0.1567, simple_loss=0.2157, pruned_loss=0.04885, over 4893.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2199, pruned_loss=0.03935, over 972664.98 frames.], batch size: 19, lr: 3.26e-04
+2022-05-05 15:52:20,123 INFO [train.py:715] (3/8) Epoch 6, batch 26200, loss[loss=0.1598, simple_loss=0.2216, pruned_loss=0.04903, over 4817.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2199, pruned_loss=0.03917, over 972678.72 frames.], batch size: 26, lr: 3.26e-04
+2022-05-05 15:52:58,596 INFO [train.py:715] (3/8) Epoch 6, batch 26250, loss[loss=0.1671, simple_loss=0.2471, pruned_loss=0.0435, over 4783.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2193, pruned_loss=0.03874, over 973214.87 frames.], batch size: 18, lr: 3.26e-04
+2022-05-05 15:53:37,251 INFO [train.py:715] (3/8) Epoch 6, batch 26300, loss[loss=0.1312, simple_loss=0.2101, pruned_loss=0.02612, over 4881.00 frames.], tot_loss[loss=0.148, simple_loss=0.2189, pruned_loss=0.03855, over 973322.00 frames.], batch size: 22, lr: 3.26e-04
+2022-05-05 15:54:15,325 INFO [train.py:715] (3/8) Epoch 6, batch 26350, loss[loss=0.142, simple_loss=0.2189, pruned_loss=0.03253, over 4976.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.03794, over 973241.89 frames.], batch size: 25, lr: 3.26e-04
+2022-05-05 15:54:53,794 INFO [train.py:715] (3/8) Epoch 6, batch 26400, loss[loss=0.1311, simple_loss=0.2066, pruned_loss=0.02777, over 4972.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2179, pruned_loss=0.03777, over 972252.85 frames.], batch size: 14, lr: 3.26e-04
+2022-05-05 15:55:33,107 INFO [train.py:715] (3/8) Epoch 6, batch 26450, loss[loss=0.1522, simple_loss=0.2253, pruned_loss=0.03951, over 4988.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03779, over 973308.95 frames.], batch size: 15, lr: 3.26e-04
+2022-05-05 15:56:11,693 INFO [train.py:715] (3/8) Epoch 6, batch 26500, loss[loss=0.1245, simple_loss=0.1984, pruned_loss=0.02533, over 4866.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2194, pruned_loss=0.03816, over 973534.11 frames.], batch size: 20, lr: 3.26e-04
+2022-05-05 15:56:50,069 INFO [train.py:715] (3/8) Epoch 6, batch 26550, loss[loss=0.1529, simple_loss=0.2253, pruned_loss=0.04029, over 4975.00 frames.], tot_loss[loss=0.147, simple_loss=0.2186, pruned_loss=0.03769, over 973506.89 frames.], batch size: 14, lr: 3.26e-04
+2022-05-05 15:57:28,900 INFO [train.py:715] (3/8) Epoch 6, batch 26600, loss[loss=0.1647, simple_loss=0.2459, pruned_loss=0.04169, over 4938.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2193, pruned_loss=0.03787, over 973769.52 frames.], batch size: 21, lr: 3.26e-04
+2022-05-05 15:58:07,541 INFO [train.py:715] (3/8) Epoch 6, batch 26650, loss[loss=0.1508, simple_loss=0.2208, pruned_loss=0.04038, over 4823.00 frames.], tot_loss[loss=0.1483, simple_loss=0.22, pruned_loss=0.03837, over 973602.88 frames.], batch size: 27, lr: 3.26e-04
+2022-05-05 15:58:46,267 INFO [train.py:715] (3/8) Epoch 6, batch 26700, loss[loss=0.1894, simple_loss=0.2527, pruned_loss=0.06308, over 4922.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2195, pruned_loss=0.03846, over 972550.45 frames.], batch size: 18, lr: 3.25e-04
+2022-05-05 15:59:24,554 INFO [train.py:715] (3/8) Epoch 6, batch 26750, loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.03786, over 4870.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2197, pruned_loss=0.03834, over 972629.63 frames.], batch size: 22, lr: 3.25e-04
+2022-05-05 16:00:03,783 INFO [train.py:715] (3/8) Epoch 6, batch 26800, loss[loss=0.1601, simple_loss=0.2318, pruned_loss=0.04414, over 4840.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2194, pruned_loss=0.03836, over 972397.85 frames.], batch size: 30, lr: 3.25e-04
+2022-05-05 16:00:41,899 INFO [train.py:715] (3/8) Epoch 6, batch 26850, loss[loss=0.1419, simple_loss=0.2075, pruned_loss=0.0381, over 4830.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.03782, over 972312.34 frames.], batch size: 26, lr: 3.25e-04
+2022-05-05 16:01:20,552 INFO [train.py:715] (3/8) Epoch 6, batch 26900, loss[loss=0.1475, simple_loss=0.2122, pruned_loss=0.04137, over 4957.00 frames.], tot_loss[loss=0.148, simple_loss=0.2192, pruned_loss=0.03837, over 973134.98 frames.], batch size: 15, lr: 3.25e-04
+2022-05-05 16:01:59,792 INFO [train.py:715] (3/8) Epoch 6, batch 26950, loss[loss=0.1888, simple_loss=0.2437, pruned_loss=0.06692, over 4776.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2196, pruned_loss=0.03865, over 973418.09 frames.], batch size: 14, lr: 3.25e-04
+2022-05-05 16:02:39,039 INFO [train.py:715] (3/8) Epoch 6, batch 27000, loss[loss=0.1406, simple_loss=0.2129, pruned_loss=0.03412, over 4812.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2194, pruned_loss=0.03867, over 973120.50 frames.], batch size: 25, lr: 3.25e-04
+2022-05-05 16:02:39,040 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 16:02:48,795 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1088, simple_loss=0.1938, pruned_loss=0.01188, over 914524.00 frames.
+2022-05-05 16:03:28,075 INFO [train.py:715] (3/8) Epoch 6, batch 27050, loss[loss=0.1572, simple_loss=0.2252, pruned_loss=0.04466, over 4697.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2184, pruned_loss=0.03852, over 971929.22 frames.], batch size: 15, lr: 3.25e-04
+2022-05-05 16:04:06,806 INFO [train.py:715] (3/8) Epoch 6, batch 27100, loss[loss=0.1618, simple_loss=0.2212, pruned_loss=0.05124, over 4779.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2186, pruned_loss=0.03852, over 971862.32 frames.], batch size: 18, lr: 3.25e-04
+2022-05-05 16:04:45,441 INFO [train.py:715] (3/8) Epoch 6, batch 27150, loss[loss=0.1721, simple_loss=0.2335, pruned_loss=0.05529, over 4838.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03958, over 972083.24 frames.], batch size: 30, lr: 3.25e-04
+2022-05-05 16:05:25,175 INFO [train.py:715] (3/8) Epoch 6, batch 27200, loss[loss=0.1269, simple_loss=0.209, pruned_loss=0.02245, over 4820.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2195, pruned_loss=0.03878, over 971308.56 frames.], batch size: 26, lr: 3.25e-04
+2022-05-05 16:06:03,411 INFO [train.py:715] (3/8) Epoch 6, batch 27250, loss[loss=0.1532, simple_loss=0.2299, pruned_loss=0.03823, over 4760.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2193, pruned_loss=0.03862, over 971624.83 frames.], batch size: 19, lr: 3.25e-04
+2022-05-05 16:06:43,062 INFO [train.py:715] (3/8) Epoch 6, batch 27300, loss[loss=0.1531, simple_loss=0.2288, pruned_loss=0.03869, over 4926.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03878, over 971718.15 frames.], batch size: 19, lr: 3.25e-04
+2022-05-05 16:07:22,055 INFO [train.py:715] (3/8) Epoch 6, batch 27350, loss[loss=0.1251, simple_loss=0.2019, pruned_loss=0.02415, over 4929.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2199, pruned_loss=0.03831, over 972631.15 frames.], batch size: 23, lr: 3.25e-04
+2022-05-05 16:08:01,165 INFO [train.py:715] (3/8) Epoch 6, batch 27400, loss[loss=0.1805, simple_loss=0.246, pruned_loss=0.05753, over 4779.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2218, pruned_loss=0.03896, over 972372.31 frames.], batch size: 18, lr: 3.25e-04
+2022-05-05 16:08:39,771 INFO [train.py:715] (3/8) Epoch 6, batch 27450, loss[loss=0.1267, simple_loss=0.2054, pruned_loss=0.02399, over 4766.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2215, pruned_loss=0.03876, over 971546.90 frames.], batch size: 19, lr: 3.25e-04
+2022-05-05 16:09:18,813 INFO [train.py:715] (3/8) Epoch 6, batch 27500, loss[loss=0.1419, simple_loss=0.2205, pruned_loss=0.03168, over 4964.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2204, pruned_loss=0.03827, over 972112.76 frames.], batch size: 15, lr: 3.25e-04
+2022-05-05 16:09:58,187 INFO [train.py:715] (3/8) Epoch 6, batch 27550, loss[loss=0.1401, simple_loss=0.2092, pruned_loss=0.03549, over 4903.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2207, pruned_loss=0.03853, over 971692.80 frames.], batch size: 19, lr: 3.25e-04
+2022-05-05 16:10:36,912 INFO [train.py:715] (3/8) Epoch 6, batch 27600, loss[loss=0.1369, simple_loss=0.2057, pruned_loss=0.03409, over 4743.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2203, pruned_loss=0.03852, over 971416.15 frames.], batch size: 16, lr: 3.25e-04
+2022-05-05 16:11:15,426 INFO [train.py:715] (3/8) Epoch 6, batch 27650, loss[loss=0.1531, simple_loss=0.2229, pruned_loss=0.04165, over 4774.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03879, over 971924.73 frames.], batch size: 19, lr: 3.25e-04
+2022-05-05 16:11:54,437 INFO [train.py:715] (3/8) Epoch 6, batch 27700, loss[loss=0.1423, simple_loss=0.2181, pruned_loss=0.03329, over 4884.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2196, pruned_loss=0.03879, over 971221.29 frames.], batch size: 16, lr: 3.25e-04
+2022-05-05 16:12:32,979 INFO [train.py:715] (3/8) Epoch 6, batch 27750, loss[loss=0.1476, simple_loss=0.2283, pruned_loss=0.03345, over 4755.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2194, pruned_loss=0.03866, over 971313.68 frames.], batch size: 16, lr: 3.25e-04
+2022-05-05 16:13:12,186 INFO [train.py:715] (3/8) Epoch 6, batch 27800, loss[loss=0.1454, simple_loss=0.2247, pruned_loss=0.03302, over 4921.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2187, pruned_loss=0.03801, over 972337.51 frames.], batch size: 18, lr: 3.25e-04
+2022-05-05 16:13:51,238 INFO [train.py:715] (3/8) Epoch 6, batch 27850, loss[loss=0.1563, simple_loss=0.2304, pruned_loss=0.04105, over 4692.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03778, over 972214.51 frames.], batch size: 15, lr: 3.25e-04
+2022-05-05 16:14:30,896 INFO [train.py:715] (3/8) Epoch 6, batch 27900, loss[loss=0.15, simple_loss=0.2116, pruned_loss=0.0442, over 4865.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2187, pruned_loss=0.03802, over 972214.96 frames.], batch size: 34, lr: 3.25e-04
+2022-05-05 16:15:09,373 INFO [train.py:715] (3/8) Epoch 6, batch 27950, loss[loss=0.1613, simple_loss=0.2102, pruned_loss=0.0562, over 4754.00 frames.], tot_loss[loss=0.1468, simple_loss=0.218, pruned_loss=0.03783, over 971834.02 frames.], batch size: 12, lr: 3.25e-04
+2022-05-05 16:15:48,253 INFO [train.py:715] (3/8) Epoch 6, batch 28000, loss[loss=0.1766, simple_loss=0.243, pruned_loss=0.05514, over 4800.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2182, pruned_loss=0.03794, over 972061.06 frames.], batch size: 21, lr: 3.25e-04
+2022-05-05 16:16:27,394 INFO [train.py:715] (3/8) Epoch 6, batch 28050, loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.0379, over 4942.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2189, pruned_loss=0.03833, over 971998.19 frames.], batch size: 21, lr: 3.25e-04
+2022-05-05 16:17:06,026 INFO [train.py:715] (3/8) Epoch 6, batch 28100, loss[loss=0.1481, simple_loss=0.2213, pruned_loss=0.0375, over 4868.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03844, over 972679.79 frames.], batch size: 16, lr: 3.25e-04
+2022-05-05 16:17:44,949 INFO [train.py:715] (3/8) Epoch 6, batch 28150, loss[loss=0.1252, simple_loss=0.1972, pruned_loss=0.02656, over 4781.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2201, pruned_loss=0.03851, over 972587.50 frames.], batch size: 12, lr: 3.24e-04
+2022-05-05 16:18:24,088 INFO [train.py:715] (3/8) Epoch 6, batch 28200, loss[loss=0.1588, simple_loss=0.2221, pruned_loss=0.04781, over 4802.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2197, pruned_loss=0.0387, over 971601.01 frames.], batch size: 21, lr: 3.24e-04
+2022-05-05 16:19:03,410 INFO [train.py:715] (3/8) Epoch 6, batch 28250, loss[loss=0.1447, simple_loss=0.2303, pruned_loss=0.02951, over 4989.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2197, pruned_loss=0.03876, over 972272.25 frames.], batch size: 26, lr: 3.24e-04
+2022-05-05 16:19:41,794 INFO [train.py:715] (3/8) Epoch 6, batch 28300, loss[loss=0.1432, simple_loss=0.2163, pruned_loss=0.03508, over 4896.00 frames.], tot_loss[loss=0.15, simple_loss=0.2208, pruned_loss=0.03957, over 973024.55 frames.], batch size: 16, lr: 3.24e-04
+2022-05-05 16:20:20,027 INFO [train.py:715] (3/8) Epoch 6, batch 28350, loss[loss=0.1647, simple_loss=0.2253, pruned_loss=0.05205, over 4907.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2205, pruned_loss=0.03949, over 973295.42 frames.], batch size: 19, lr: 3.24e-04
+2022-05-05 16:20:59,874 INFO [train.py:715] (3/8) Epoch 6, batch 28400, loss[loss=0.1449, simple_loss=0.2241, pruned_loss=0.03286, over 4890.00 frames.], tot_loss[loss=0.149, simple_loss=0.2201, pruned_loss=0.03894, over 973832.89 frames.], batch size: 22, lr: 3.24e-04
+2022-05-05 16:21:38,666 INFO [train.py:715] (3/8) Epoch 6, batch 28450, loss[loss=0.1444, simple_loss=0.214, pruned_loss=0.0374, over 4895.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2198, pruned_loss=0.03887, over 973878.67 frames.], batch size: 19, lr: 3.24e-04
+2022-05-05 16:22:17,507 INFO [train.py:715] (3/8) Epoch 6, batch 28500, loss[loss=0.1641, simple_loss=0.2339, pruned_loss=0.04721, over 4915.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2196, pruned_loss=0.03864, over 972769.53 frames.], batch size: 17, lr: 3.24e-04
+2022-05-05 16:22:56,651 INFO [train.py:715] (3/8) Epoch 6, batch 28550, loss[loss=0.1515, simple_loss=0.2131, pruned_loss=0.04496, over 4931.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2198, pruned_loss=0.03867, over 973425.49 frames.], batch size: 23, lr: 3.24e-04
+2022-05-05 16:23:36,089 INFO [train.py:715] (3/8) Epoch 6, batch 28600, loss[loss=0.1564, simple_loss=0.2262, pruned_loss=0.04329, over 4971.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03857, over 973743.22 frames.], batch size: 15, lr: 3.24e-04
+2022-05-05 16:24:14,189 INFO [train.py:715] (3/8) Epoch 6, batch 28650, loss[loss=0.1481, simple_loss=0.216, pruned_loss=0.04013, over 4855.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03813, over 973435.89 frames.], batch size: 32, lr: 3.24e-04
+2022-05-05 16:24:52,993 INFO [train.py:715] (3/8) Epoch 6, batch 28700, loss[loss=0.1304, simple_loss=0.2, pruned_loss=0.03038, over 4978.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2206, pruned_loss=0.03891, over 973348.72 frames.], batch size: 14, lr: 3.24e-04
+2022-05-05 16:25:32,173 INFO [train.py:715] (3/8) Epoch 6, batch 28750, loss[loss=0.1386, simple_loss=0.2144, pruned_loss=0.03141, over 4936.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2207, pruned_loss=0.03906, over 973569.34 frames.], batch size: 29, lr: 3.24e-04
+2022-05-05 16:26:10,897 INFO [train.py:715] (3/8) Epoch 6, batch 28800, loss[loss=0.1888, simple_loss=0.2602, pruned_loss=0.05867, over 4868.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2214, pruned_loss=0.0398, over 973181.09 frames.], batch size: 22, lr: 3.24e-04
+2022-05-05 16:26:49,767 INFO [train.py:715] (3/8) Epoch 6, batch 28850, loss[loss=0.1661, simple_loss=0.2358, pruned_loss=0.04825, over 4896.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2213, pruned_loss=0.03986, over 973063.01 frames.], batch size: 39, lr: 3.24e-04
+2022-05-05 16:27:28,068 INFO [train.py:715] (3/8) Epoch 6, batch 28900, loss[loss=0.161, simple_loss=0.2315, pruned_loss=0.04527, over 4948.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2206, pruned_loss=0.03932, over 973737.65 frames.], batch size: 21, lr: 3.24e-04
+2022-05-05 16:28:07,515 INFO [train.py:715] (3/8) Epoch 6, batch 28950, loss[loss=0.1239, simple_loss=0.202, pruned_loss=0.0229, over 4946.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03852, over 972983.96 frames.], batch size: 24, lr: 3.24e-04
+2022-05-05 16:28:45,749 INFO [train.py:715] (3/8) Epoch 6, batch 29000, loss[loss=0.2005, simple_loss=0.2608, pruned_loss=0.07011, over 4967.00 frames.], tot_loss[loss=0.148, simple_loss=0.2191, pruned_loss=0.03847, over 973457.71 frames.], batch size: 14, lr: 3.24e-04
+2022-05-05 16:29:23,902 INFO [train.py:715] (3/8) Epoch 6, batch 29050, loss[loss=0.1408, simple_loss=0.2115, pruned_loss=0.03505, over 4816.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2193, pruned_loss=0.03854, over 973176.83 frames.], batch size: 12, lr: 3.24e-04
+2022-05-05 16:30:02,951 INFO [train.py:715] (3/8) Epoch 6, batch 29100, loss[loss=0.1166, simple_loss=0.1915, pruned_loss=0.02081, over 4978.00 frames.], tot_loss[loss=0.1475, simple_loss=0.219, pruned_loss=0.03805, over 973507.08 frames.], batch size: 24, lr: 3.24e-04
+2022-05-05 16:30:41,836 INFO [train.py:715] (3/8) Epoch 6, batch 29150, loss[loss=0.1567, simple_loss=0.2267, pruned_loss=0.04337, over 4866.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2193, pruned_loss=0.03812, over 972579.21 frames.], batch size: 20, lr: 3.24e-04
+2022-05-05 16:31:20,669 INFO [train.py:715] (3/8) Epoch 6, batch 29200, loss[loss=0.1188, simple_loss=0.1851, pruned_loss=0.02626, over 4891.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2188, pruned_loss=0.03823, over 972809.69 frames.], batch size: 18, lr: 3.24e-04
+2022-05-05 16:31:59,885 INFO [train.py:715] (3/8) Epoch 6, batch 29250, loss[loss=0.1308, simple_loss=0.2105, pruned_loss=0.02551, over 4899.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2181, pruned_loss=0.03781, over 973115.48 frames.], batch size: 19, lr: 3.24e-04
+2022-05-05 16:32:39,921 INFO [train.py:715] (3/8) Epoch 6, batch 29300, loss[loss=0.164, simple_loss=0.2236, pruned_loss=0.05216, over 4788.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03792, over 971643.99 frames.], batch size: 14, lr: 3.24e-04
+2022-05-05 16:33:18,206 INFO [train.py:715] (3/8) Epoch 6, batch 29350, loss[loss=0.1729, simple_loss=0.2358, pruned_loss=0.05503, over 4934.00 frames.], tot_loss[loss=0.147, simple_loss=0.2187, pruned_loss=0.03767, over 971916.69 frames.], batch size: 18, lr: 3.24e-04
+2022-05-05 16:33:57,192 INFO [train.py:715] (3/8) Epoch 6, batch 29400, loss[loss=0.1673, simple_loss=0.2293, pruned_loss=0.05261, over 4956.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03784, over 971637.31 frames.], batch size: 21, lr: 3.24e-04
+2022-05-05 16:34:36,595 INFO [train.py:715] (3/8) Epoch 6, batch 29450, loss[loss=0.1633, simple_loss=0.2236, pruned_loss=0.05152, over 4983.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2185, pruned_loss=0.03826, over 972666.59 frames.], batch size: 14, lr: 3.24e-04
+2022-05-05 16:35:15,803 INFO [train.py:715] (3/8) Epoch 6, batch 29500, loss[loss=0.1408, simple_loss=0.2031, pruned_loss=0.03923, over 4837.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2186, pruned_loss=0.03855, over 972295.49 frames.], batch size: 15, lr: 3.24e-04
+2022-05-05 16:35:53,791 INFO [train.py:715] (3/8) Epoch 6, batch 29550, loss[loss=0.1629, simple_loss=0.2351, pruned_loss=0.04539, over 4871.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2188, pruned_loss=0.03842, over 972394.19 frames.], batch size: 20, lr: 3.24e-04
+2022-05-05 16:36:33,143 INFO [train.py:715] (3/8) Epoch 6, batch 29600, loss[loss=0.1586, simple_loss=0.2438, pruned_loss=0.0367, over 4886.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03814, over 971723.37 frames.], batch size: 22, lr: 3.24e-04
+2022-05-05 16:37:12,530 INFO [train.py:715] (3/8) Epoch 6, batch 29650, loss[loss=0.1385, simple_loss=0.2139, pruned_loss=0.03154, over 4912.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2186, pruned_loss=0.03805, over 971858.67 frames.], batch size: 17, lr: 3.23e-04
+2022-05-05 16:37:51,063 INFO [train.py:715] (3/8) Epoch 6, batch 29700, loss[loss=0.1678, simple_loss=0.235, pruned_loss=0.05024, over 4850.00 frames.], tot_loss[loss=0.147, simple_loss=0.2186, pruned_loss=0.03773, over 970969.39 frames.], batch size: 20, lr: 3.23e-04
+2022-05-05 16:38:29,761 INFO [train.py:715] (3/8) Epoch 6, batch 29750, loss[loss=0.1525, simple_loss=0.2217, pruned_loss=0.04159, over 4789.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2188, pruned_loss=0.03748, over 972139.51 frames.], batch size: 18, lr: 3.23e-04
+2022-05-05 16:39:08,775 INFO [train.py:715] (3/8) Epoch 6, batch 29800, loss[loss=0.1661, simple_loss=0.2266, pruned_loss=0.05279, over 4700.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2194, pruned_loss=0.03801, over 972022.08 frames.], batch size: 15, lr: 3.23e-04
+2022-05-05 16:39:48,205 INFO [train.py:715] (3/8) Epoch 6, batch 29850, loss[loss=0.1674, simple_loss=0.2275, pruned_loss=0.05369, over 4916.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2187, pruned_loss=0.03808, over 972200.17 frames.], batch size: 29, lr: 3.23e-04
+2022-05-05 16:40:26,713 INFO [train.py:715] (3/8) Epoch 6, batch 29900, loss[loss=0.1545, simple_loss=0.2083, pruned_loss=0.05035, over 4764.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2188, pruned_loss=0.0381, over 971835.68 frames.], batch size: 12, lr: 3.23e-04
+2022-05-05 16:41:05,700 INFO [train.py:715] (3/8) Epoch 6, batch 29950, loss[loss=0.1716, simple_loss=0.2459, pruned_loss=0.04859, over 4952.00 frames.], tot_loss[loss=0.148, simple_loss=0.2193, pruned_loss=0.03831, over 971482.62 frames.], batch size: 21, lr: 3.23e-04
+2022-05-05 16:41:45,057 INFO [train.py:715] (3/8) Epoch 6, batch 30000, loss[loss=0.1404, simple_loss=0.2077, pruned_loss=0.03656, over 4965.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2181, pruned_loss=0.03783, over 971656.02 frames.], batch size: 28, lr: 3.23e-04
+2022-05-05 16:41:45,058 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 16:41:54,713 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1088, simple_loss=0.1938, pruned_loss=0.0119, over 914524.00 frames.
+2022-05-05 16:42:34,423 INFO [train.py:715] (3/8) Epoch 6, batch 30050, loss[loss=0.1909, simple_loss=0.2447, pruned_loss=0.06859, over 4801.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2183, pruned_loss=0.03775, over 972267.07 frames.], batch size: 12, lr: 3.23e-04
+2022-05-05 16:43:12,815 INFO [train.py:715] (3/8) Epoch 6, batch 30100, loss[loss=0.1561, simple_loss=0.2197, pruned_loss=0.04628, over 4744.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.03789, over 971503.32 frames.], batch size: 19, lr: 3.23e-04
+2022-05-05 16:43:51,566 INFO [train.py:715] (3/8) Epoch 6, batch 30150, loss[loss=0.1687, simple_loss=0.2299, pruned_loss=0.0537, over 4952.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.03766, over 971718.07 frames.], batch size: 15, lr: 3.23e-04
+2022-05-05 16:44:30,966 INFO [train.py:715] (3/8) Epoch 6, batch 30200, loss[loss=0.1627, simple_loss=0.226, pruned_loss=0.04976, over 4934.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03793, over 971860.94 frames.], batch size: 23, lr: 3.23e-04
+2022-05-05 16:45:10,342 INFO [train.py:715] (3/8) Epoch 6, batch 30250, loss[loss=0.1259, simple_loss=0.1892, pruned_loss=0.03131, over 4908.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03847, over 971616.43 frames.], batch size: 17, lr: 3.23e-04
+2022-05-05 16:45:48,512 INFO [train.py:715] (3/8) Epoch 6, batch 30300, loss[loss=0.1709, simple_loss=0.238, pruned_loss=0.05192, over 4760.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2194, pruned_loss=0.03897, over 972780.49 frames.], batch size: 16, lr: 3.23e-04
+2022-05-05 16:46:27,517 INFO [train.py:715] (3/8) Epoch 6, batch 30350, loss[loss=0.1414, simple_loss=0.2082, pruned_loss=0.03728, over 4821.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2187, pruned_loss=0.03848, over 972275.57 frames.], batch size: 26, lr: 3.23e-04
+2022-05-05 16:47:06,586 INFO [train.py:715] (3/8) Epoch 6, batch 30400, loss[loss=0.1244, simple_loss=0.2011, pruned_loss=0.02389, over 4914.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2193, pruned_loss=0.03877, over 972232.65 frames.], batch size: 17, lr: 3.23e-04
+2022-05-05 16:47:45,262 INFO [train.py:715] (3/8) Epoch 6, batch 30450, loss[loss=0.1526, simple_loss=0.2212, pruned_loss=0.042, over 4837.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2189, pruned_loss=0.03837, over 971665.47 frames.], batch size: 30, lr: 3.23e-04
+2022-05-05 16:48:23,948 INFO [train.py:715] (3/8) Epoch 6, batch 30500, loss[loss=0.1765, simple_loss=0.2438, pruned_loss=0.05461, over 4988.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2186, pruned_loss=0.03857, over 972352.35 frames.], batch size: 15, lr: 3.23e-04
+2022-05-05 16:49:02,695 INFO [train.py:715] (3/8) Epoch 6, batch 30550, loss[loss=0.1526, simple_loss=0.2258, pruned_loss=0.03973, over 4883.00 frames.], tot_loss[loss=0.148, simple_loss=0.219, pruned_loss=0.03849, over 972011.32 frames.], batch size: 16, lr: 3.23e-04
+2022-05-05 16:49:41,852 INFO [train.py:715] (3/8) Epoch 6, batch 30600, loss[loss=0.1263, simple_loss=0.1916, pruned_loss=0.03049, over 4814.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.03867, over 972628.32 frames.], batch size: 12, lr: 3.23e-04
+2022-05-05 16:50:20,395 INFO [train.py:715] (3/8) Epoch 6, batch 30650, loss[loss=0.1845, simple_loss=0.2592, pruned_loss=0.05492, over 4829.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2187, pruned_loss=0.03841, over 972488.97 frames.], batch size: 15, lr: 3.23e-04
+2022-05-05 16:50:59,233 INFO [train.py:715] (3/8) Epoch 6, batch 30700, loss[loss=0.1577, simple_loss=0.2339, pruned_loss=0.04073, over 4977.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2184, pruned_loss=0.03802, over 971962.21 frames.], batch size: 24, lr: 3.23e-04
+2022-05-05 16:51:38,190 INFO [train.py:715] (3/8) Epoch 6, batch 30750, loss[loss=0.1169, simple_loss=0.1953, pruned_loss=0.01925, over 4864.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03805, over 972983.67 frames.], batch size: 20, lr: 3.23e-04
+2022-05-05 16:52:17,035 INFO [train.py:715] (3/8) Epoch 6, batch 30800, loss[loss=0.1404, simple_loss=0.2116, pruned_loss=0.03456, over 4839.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03779, over 972175.27 frames.], batch size: 15, lr: 3.23e-04
+2022-05-05 16:52:55,441 INFO [train.py:715] (3/8) Epoch 6, batch 30850, loss[loss=0.1465, simple_loss=0.2254, pruned_loss=0.0338, over 4909.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2192, pruned_loss=0.03832, over 971310.53 frames.], batch size: 22, lr: 3.23e-04
+2022-05-05 16:53:34,168 INFO [train.py:715] (3/8) Epoch 6, batch 30900, loss[loss=0.1525, simple_loss=0.2205, pruned_loss=0.0423, over 4905.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03855, over 970479.98 frames.], batch size: 17, lr: 3.23e-04
+2022-05-05 16:54:13,772 INFO [train.py:715] (3/8) Epoch 6, batch 30950, loss[loss=0.1717, simple_loss=0.2404, pruned_loss=0.05153, over 4887.00 frames.], tot_loss[loss=0.149, simple_loss=0.2205, pruned_loss=0.03877, over 970883.76 frames.], batch size: 39, lr: 3.23e-04
+2022-05-05 16:54:51,908 INFO [train.py:715] (3/8) Epoch 6, batch 31000, loss[loss=0.1532, simple_loss=0.216, pruned_loss=0.04515, over 4805.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2211, pruned_loss=0.03935, over 971556.48 frames.], batch size: 12, lr: 3.23e-04
+2022-05-05 16:55:30,913 INFO [train.py:715] (3/8) Epoch 6, batch 31050, loss[loss=0.1361, simple_loss=0.2054, pruned_loss=0.03338, over 4825.00 frames.], tot_loss[loss=0.15, simple_loss=0.2214, pruned_loss=0.03931, over 970833.41 frames.], batch size: 13, lr: 3.23e-04
+2022-05-05 16:56:10,165 INFO [train.py:715] (3/8) Epoch 6, batch 31100, loss[loss=0.1594, simple_loss=0.2321, pruned_loss=0.04335, over 4704.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2202, pruned_loss=0.0393, over 971436.00 frames.], batch size: 15, lr: 3.22e-04
+2022-05-05 16:56:51,377 INFO [train.py:715] (3/8) Epoch 6, batch 31150, loss[loss=0.1545, simple_loss=0.2329, pruned_loss=0.0381, over 4940.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2205, pruned_loss=0.03893, over 971328.04 frames.], batch size: 21, lr: 3.22e-04
+2022-05-05 16:57:30,157 INFO [train.py:715] (3/8) Epoch 6, batch 31200, loss[loss=0.129, simple_loss=0.1926, pruned_loss=0.03274, over 4987.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2205, pruned_loss=0.03926, over 971899.21 frames.], batch size: 14, lr: 3.22e-04
+2022-05-05 16:58:09,412 INFO [train.py:715] (3/8) Epoch 6, batch 31250, loss[loss=0.1224, simple_loss=0.1971, pruned_loss=0.02383, over 4919.00 frames.], tot_loss[loss=0.15, simple_loss=0.2212, pruned_loss=0.03939, over 971839.63 frames.], batch size: 18, lr: 3.22e-04
+2022-05-05 16:58:48,245 INFO [train.py:715] (3/8) Epoch 6, batch 31300, loss[loss=0.1322, simple_loss=0.194, pruned_loss=0.0352, over 4840.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2209, pruned_loss=0.03919, over 971878.19 frames.], batch size: 12, lr: 3.22e-04
+2022-05-05 16:59:27,121 INFO [train.py:715] (3/8) Epoch 6, batch 31350, loss[loss=0.1499, simple_loss=0.2228, pruned_loss=0.03856, over 4986.00 frames.], tot_loss[loss=0.1499, simple_loss=0.221, pruned_loss=0.03943, over 972510.78 frames.], batch size: 28, lr: 3.22e-04
+2022-05-05 17:00:06,355 INFO [train.py:715] (3/8) Epoch 6, batch 31400, loss[loss=0.152, simple_loss=0.2137, pruned_loss=0.04519, over 4825.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03932, over 972139.89 frames.], batch size: 13, lr: 3.22e-04
+2022-05-05 17:00:45,702 INFO [train.py:715] (3/8) Epoch 6, batch 31450, loss[loss=0.1555, simple_loss=0.226, pruned_loss=0.04249, over 4832.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03858, over 972150.51 frames.], batch size: 13, lr: 3.22e-04
+2022-05-05 17:01:23,994 INFO [train.py:715] (3/8) Epoch 6, batch 31500, loss[loss=0.172, simple_loss=0.2341, pruned_loss=0.05497, over 4905.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2202, pruned_loss=0.03879, over 971975.94 frames.], batch size: 19, lr: 3.22e-04
+2022-05-05 17:02:02,415 INFO [train.py:715] (3/8) Epoch 6, batch 31550, loss[loss=0.1476, simple_loss=0.2126, pruned_loss=0.04127, over 4784.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2191, pruned_loss=0.03833, over 972540.74 frames.], batch size: 18, lr: 3.22e-04
+2022-05-05 17:02:41,957 INFO [train.py:715] (3/8) Epoch 6, batch 31600, loss[loss=0.1281, simple_loss=0.1988, pruned_loss=0.02868, over 4857.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.03862, over 972765.52 frames.], batch size: 30, lr: 3.22e-04
+2022-05-05 17:03:21,197 INFO [train.py:715] (3/8) Epoch 6, batch 31650, loss[loss=0.1627, simple_loss=0.224, pruned_loss=0.05071, over 4890.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2194, pruned_loss=0.03855, over 973106.57 frames.], batch size: 19, lr: 3.22e-04
+2022-05-05 17:03:59,733 INFO [train.py:715] (3/8) Epoch 6, batch 31700, loss[loss=0.1681, simple_loss=0.2427, pruned_loss=0.04671, over 4981.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.0382, over 973876.52 frames.], batch size: 15, lr: 3.22e-04
+2022-05-05 17:04:38,254 INFO [train.py:715] (3/8) Epoch 6, batch 31750, loss[loss=0.1785, simple_loss=0.2442, pruned_loss=0.05641, over 4986.00 frames.], tot_loss[loss=0.148, simple_loss=0.2196, pruned_loss=0.03818, over 973697.44 frames.], batch size: 15, lr: 3.22e-04
+2022-05-05 17:05:17,757 INFO [train.py:715] (3/8) Epoch 6, batch 31800, loss[loss=0.1472, simple_loss=0.2166, pruned_loss=0.03896, over 4975.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2204, pruned_loss=0.03857, over 972988.66 frames.], batch size: 35, lr: 3.22e-04
+2022-05-05 17:05:56,240 INFO [train.py:715] (3/8) Epoch 6, batch 31850, loss[loss=0.1344, simple_loss=0.2103, pruned_loss=0.02927, over 4853.00 frames.], tot_loss[loss=0.1475, simple_loss=0.219, pruned_loss=0.03802, over 972959.69 frames.], batch size: 20, lr: 3.22e-04
+2022-05-05 17:06:34,777 INFO [train.py:715] (3/8) Epoch 6, batch 31900, loss[loss=0.1391, simple_loss=0.2172, pruned_loss=0.03053, over 4748.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03812, over 972707.02 frames.], batch size: 19, lr: 3.22e-04
+2022-05-05 17:07:13,870 INFO [train.py:715] (3/8) Epoch 6, batch 31950, loss[loss=0.2102, simple_loss=0.277, pruned_loss=0.07176, over 4877.00 frames.], tot_loss[loss=0.147, simple_loss=0.2186, pruned_loss=0.0377, over 972206.02 frames.], batch size: 16, lr: 3.22e-04
+2022-05-05 17:07:52,488 INFO [train.py:715] (3/8) Epoch 6, batch 32000, loss[loss=0.1921, simple_loss=0.2503, pruned_loss=0.06692, over 4917.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2193, pruned_loss=0.0382, over 972043.73 frames.], batch size: 18, lr: 3.22e-04
+2022-05-05 17:08:31,940 INFO [train.py:715] (3/8) Epoch 6, batch 32050, loss[loss=0.1482, simple_loss=0.2141, pruned_loss=0.04114, over 4806.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03846, over 972114.60 frames.], batch size: 13, lr: 3.22e-04
+2022-05-05 17:09:11,463 INFO [train.py:715] (3/8) Epoch 6, batch 32100, loss[loss=0.1483, simple_loss=0.2254, pruned_loss=0.03558, over 4941.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2201, pruned_loss=0.03871, over 972799.05 frames.], batch size: 21, lr: 3.22e-04
+2022-05-05 17:09:50,462 INFO [train.py:715] (3/8) Epoch 6, batch 32150, loss[loss=0.1473, simple_loss=0.2182, pruned_loss=0.03815, over 4791.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2192, pruned_loss=0.03793, over 973657.72 frames.], batch size: 14, lr: 3.22e-04
+2022-05-05 17:10:28,958 INFO [train.py:715] (3/8) Epoch 6, batch 32200, loss[loss=0.1629, simple_loss=0.2302, pruned_loss=0.04785, over 4787.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2208, pruned_loss=0.03865, over 974070.29 frames.], batch size: 17, lr: 3.22e-04
+2022-05-05 17:11:08,027 INFO [train.py:715] (3/8) Epoch 6, batch 32250, loss[loss=0.1334, simple_loss=0.2054, pruned_loss=0.03073, over 4978.00 frames.], tot_loss[loss=0.149, simple_loss=0.2208, pruned_loss=0.03858, over 973341.35 frames.], batch size: 14, lr: 3.22e-04
+2022-05-05 17:11:46,851 INFO [train.py:715] (3/8) Epoch 6, batch 32300, loss[loss=0.1362, simple_loss=0.2076, pruned_loss=0.03245, over 4771.00 frames.], tot_loss[loss=0.1478, simple_loss=0.22, pruned_loss=0.03777, over 972302.44 frames.], batch size: 19, lr: 3.22e-04
+2022-05-05 17:12:26,142 INFO [train.py:715] (3/8) Epoch 6, batch 32350, loss[loss=0.2012, simple_loss=0.2539, pruned_loss=0.0743, over 4829.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2197, pruned_loss=0.03791, over 972618.08 frames.], batch size: 13, lr: 3.22e-04
+2022-05-05 17:13:04,503 INFO [train.py:715] (3/8) Epoch 6, batch 32400, loss[loss=0.1245, simple_loss=0.1987, pruned_loss=0.02514, over 4830.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2191, pruned_loss=0.03778, over 972323.44 frames.], batch size: 26, lr: 3.22e-04
+2022-05-05 17:13:43,924 INFO [train.py:715] (3/8) Epoch 6, batch 32450, loss[loss=0.1732, simple_loss=0.2313, pruned_loss=0.05751, over 4851.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2189, pruned_loss=0.03808, over 972664.45 frames.], batch size: 34, lr: 3.22e-04
+2022-05-05 17:14:23,269 INFO [train.py:715] (3/8) Epoch 6, batch 32500, loss[loss=0.1406, simple_loss=0.211, pruned_loss=0.03508, over 4913.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2187, pruned_loss=0.03809, over 971944.57 frames.], batch size: 18, lr: 3.22e-04
+2022-05-05 17:15:01,982 INFO [train.py:715] (3/8) Epoch 6, batch 32550, loss[loss=0.1505, simple_loss=0.2239, pruned_loss=0.03856, over 4812.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2185, pruned_loss=0.03799, over 970742.13 frames.], batch size: 15, lr: 3.22e-04
+2022-05-05 17:15:40,778 INFO [train.py:715] (3/8) Epoch 6, batch 32600, loss[loss=0.1234, simple_loss=0.2, pruned_loss=0.02337, over 4843.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2176, pruned_loss=0.03756, over 971329.33 frames.], batch size: 15, lr: 3.21e-04
+2022-05-05 17:16:19,209 INFO [train.py:715] (3/8) Epoch 6, batch 32650, loss[loss=0.1282, simple_loss=0.2002, pruned_loss=0.02806, over 4929.00 frames.], tot_loss[loss=0.1467, simple_loss=0.218, pruned_loss=0.03767, over 972353.28 frames.], batch size: 35, lr: 3.21e-04
+2022-05-05 17:16:57,839 INFO [train.py:715] (3/8) Epoch 6, batch 32700, loss[loss=0.1461, simple_loss=0.2195, pruned_loss=0.03637, over 4871.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2185, pruned_loss=0.03749, over 972927.59 frames.], batch size: 20, lr: 3.21e-04
+2022-05-05 17:17:35,887 INFO [train.py:715] (3/8) Epoch 6, batch 32750, loss[loss=0.1173, simple_loss=0.1976, pruned_loss=0.01847, over 4748.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03678, over 972384.95 frames.], batch size: 19, lr: 3.21e-04
+2022-05-05 17:18:14,603 INFO [train.py:715] (3/8) Epoch 6, batch 32800, loss[loss=0.1721, simple_loss=0.2327, pruned_loss=0.05575, over 4970.00 frames.], tot_loss[loss=0.1464, simple_loss=0.218, pruned_loss=0.0374, over 972462.47 frames.], batch size: 15, lr: 3.21e-04
+2022-05-05 17:18:53,199 INFO [train.py:715] (3/8) Epoch 6, batch 32850, loss[loss=0.1326, simple_loss=0.2059, pruned_loss=0.02961, over 4778.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2174, pruned_loss=0.03747, over 972654.95 frames.], batch size: 18, lr: 3.21e-04
+2022-05-05 17:19:31,605 INFO [train.py:715] (3/8) Epoch 6, batch 32900, loss[loss=0.1307, simple_loss=0.2008, pruned_loss=0.0303, over 4842.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2179, pruned_loss=0.03727, over 972616.14 frames.], batch size: 32, lr: 3.21e-04
+2022-05-05 17:20:09,698 INFO [train.py:715] (3/8) Epoch 6, batch 32950, loss[loss=0.1722, simple_loss=0.2256, pruned_loss=0.05946, over 4849.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03746, over 972207.87 frames.], batch size: 32, lr: 3.21e-04
+2022-05-05 17:20:48,507 INFO [train.py:715] (3/8) Epoch 6, batch 33000, loss[loss=0.1578, simple_loss=0.2273, pruned_loss=0.04413, over 4912.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03741, over 972059.54 frames.], batch size: 18, lr: 3.21e-04
+2022-05-05 17:20:48,507 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 17:20:58,109 INFO [train.py:742] (3/8) Epoch 6, validation: loss=0.1087, simple_loss=0.1938, pruned_loss=0.01183, over 914524.00 frames.
+2022-05-05 17:21:36,674 INFO [train.py:715] (3/8) Epoch 6, batch 33050, loss[loss=0.1804, simple_loss=0.2396, pruned_loss=0.06056, over 4744.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.03763, over 972012.18 frames.], batch size: 12, lr: 3.21e-04
+2022-05-05 17:22:15,262 INFO [train.py:715] (3/8) Epoch 6, batch 33100, loss[loss=0.1573, simple_loss=0.2372, pruned_loss=0.03869, over 4886.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.03784, over 972023.63 frames.], batch size: 16, lr: 3.21e-04
+2022-05-05 17:22:53,010 INFO [train.py:715] (3/8) Epoch 6, batch 33150, loss[loss=0.1688, simple_loss=0.2485, pruned_loss=0.0445, over 4802.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2175, pruned_loss=0.03743, over 971874.13 frames.], batch size: 21, lr: 3.21e-04
+2022-05-05 17:23:31,897 INFO [train.py:715] (3/8) Epoch 6, batch 33200, loss[loss=0.1596, simple_loss=0.2365, pruned_loss=0.0413, over 4943.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2183, pruned_loss=0.03832, over 972843.81 frames.], batch size: 35, lr: 3.21e-04
+2022-05-05 17:24:10,786 INFO [train.py:715] (3/8) Epoch 6, batch 33250, loss[loss=0.1459, simple_loss=0.2224, pruned_loss=0.03472, over 4986.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2181, pruned_loss=0.03777, over 973127.81 frames.], batch size: 25, lr: 3.21e-04
+2022-05-05 17:24:49,863 INFO [train.py:715] (3/8) Epoch 6, batch 33300, loss[loss=0.1434, simple_loss=0.2211, pruned_loss=0.03288, over 4758.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03809, over 973768.67 frames.], batch size: 19, lr: 3.21e-04
+2022-05-05 17:25:28,469 INFO [train.py:715] (3/8) Epoch 6, batch 33350, loss[loss=0.1295, simple_loss=0.2106, pruned_loss=0.02414, over 4808.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2181, pruned_loss=0.03787, over 972923.76 frames.], batch size: 26, lr: 3.21e-04
+2022-05-05 17:26:07,934 INFO [train.py:715] (3/8) Epoch 6, batch 33400, loss[loss=0.1372, simple_loss=0.2169, pruned_loss=0.02881, over 4958.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2183, pruned_loss=0.03773, over 972950.81 frames.], batch size: 24, lr: 3.21e-04
+2022-05-05 17:26:47,026 INFO [train.py:715] (3/8) Epoch 6, batch 33450, loss[loss=0.1799, simple_loss=0.2415, pruned_loss=0.05912, over 4899.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.0374, over 972860.09 frames.], batch size: 18, lr: 3.21e-04
+2022-05-05 17:27:25,291 INFO [train.py:715] (3/8) Epoch 6, batch 33500, loss[loss=0.1523, simple_loss=0.2228, pruned_loss=0.04097, over 4970.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03718, over 972715.72 frames.], batch size: 35, lr: 3.21e-04
+2022-05-05 17:28:04,314 INFO [train.py:715] (3/8) Epoch 6, batch 33550, loss[loss=0.1184, simple_loss=0.1945, pruned_loss=0.02117, over 4839.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2184, pruned_loss=0.03716, over 972571.26 frames.], batch size: 13, lr: 3.21e-04
+2022-05-05 17:28:43,723 INFO [train.py:715] (3/8) Epoch 6, batch 33600, loss[loss=0.1463, simple_loss=0.2161, pruned_loss=0.0382, over 4988.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03702, over 972674.74 frames.], batch size: 20, lr: 3.21e-04
+2022-05-05 17:29:22,677 INFO [train.py:715] (3/8) Epoch 6, batch 33650, loss[loss=0.1262, simple_loss=0.1979, pruned_loss=0.02718, over 4862.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2182, pruned_loss=0.0372, over 972201.88 frames.], batch size: 30, lr: 3.21e-04
+2022-05-05 17:30:01,275 INFO [train.py:715] (3/8) Epoch 6, batch 33700, loss[loss=0.1549, simple_loss=0.2303, pruned_loss=0.03971, over 4741.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2181, pruned_loss=0.03682, over 971805.47 frames.], batch size: 12, lr: 3.21e-04
+2022-05-05 17:30:39,883 INFO [train.py:715] (3/8) Epoch 6, batch 33750, loss[loss=0.1433, simple_loss=0.2216, pruned_loss=0.0325, over 4962.00 frames.], tot_loss[loss=0.1468, simple_loss=0.219, pruned_loss=0.03729, over 972256.04 frames.], batch size: 24, lr: 3.21e-04
+2022-05-05 17:31:19,207 INFO [train.py:715] (3/8) Epoch 6, batch 33800, loss[loss=0.1514, simple_loss=0.2238, pruned_loss=0.03947, over 4976.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2194, pruned_loss=0.03756, over 971736.33 frames.], batch size: 25, lr: 3.21e-04
+2022-05-05 17:31:58,018 INFO [train.py:715] (3/8) Epoch 6, batch 33850, loss[loss=0.1233, simple_loss=0.1916, pruned_loss=0.0275, over 4924.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2192, pruned_loss=0.03766, over 971856.77 frames.], batch size: 29, lr: 3.21e-04
+2022-05-05 17:32:36,704 INFO [train.py:715] (3/8) Epoch 6, batch 33900, loss[loss=0.1639, simple_loss=0.2314, pruned_loss=0.04822, over 4850.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2193, pruned_loss=0.03775, over 972561.75 frames.], batch size: 30, lr: 3.21e-04
+2022-05-05 17:33:16,048 INFO [train.py:715] (3/8) Epoch 6, batch 33950, loss[loss=0.1769, simple_loss=0.2517, pruned_loss=0.05112, over 4920.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2195, pruned_loss=0.038, over 971990.61 frames.], batch size: 23, lr: 3.21e-04
+2022-05-05 17:33:55,028 INFO [train.py:715] (3/8) Epoch 6, batch 34000, loss[loss=0.1314, simple_loss=0.2044, pruned_loss=0.02926, over 4937.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03853, over 972350.71 frames.], batch size: 29, lr: 3.21e-04
+2022-05-05 17:34:33,701 INFO [train.py:715] (3/8) Epoch 6, batch 34050, loss[loss=0.1197, simple_loss=0.1929, pruned_loss=0.02328, over 4803.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.0382, over 972519.63 frames.], batch size: 13, lr: 3.21e-04
+2022-05-05 17:35:12,982 INFO [train.py:715] (3/8) Epoch 6, batch 34100, loss[loss=0.1476, simple_loss=0.2248, pruned_loss=0.03517, over 4966.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2202, pruned_loss=0.03831, over 973452.58 frames.], batch size: 21, lr: 3.20e-04
+2022-05-05 17:35:51,936 INFO [train.py:715] (3/8) Epoch 6, batch 34150, loss[loss=0.166, simple_loss=0.2234, pruned_loss=0.05432, over 4840.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03813, over 973265.02 frames.], batch size: 13, lr: 3.20e-04
+2022-05-05 17:36:30,536 INFO [train.py:715] (3/8) Epoch 6, batch 34200, loss[loss=0.1298, simple_loss=0.198, pruned_loss=0.03079, over 4789.00 frames.], tot_loss[loss=0.1473, simple_loss=0.219, pruned_loss=0.03782, over 972159.66 frames.], batch size: 24, lr: 3.20e-04
+2022-05-05 17:37:09,177 INFO [train.py:715] (3/8) Epoch 6, batch 34250, loss[loss=0.1426, simple_loss=0.2123, pruned_loss=0.03643, over 4929.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2197, pruned_loss=0.03804, over 972335.97 frames.], batch size: 29, lr: 3.20e-04
+2022-05-05 17:37:48,389 INFO [train.py:715] (3/8) Epoch 6, batch 34300, loss[loss=0.1547, simple_loss=0.2268, pruned_loss=0.04128, over 4791.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2195, pruned_loss=0.03783, over 972729.53 frames.], batch size: 17, lr: 3.20e-04
+2022-05-05 17:38:26,981 INFO [train.py:715] (3/8) Epoch 6, batch 34350, loss[loss=0.1181, simple_loss=0.1914, pruned_loss=0.02245, over 4834.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.0378, over 972192.83 frames.], batch size: 13, lr: 3.20e-04
+2022-05-05 17:39:05,619 INFO [train.py:715] (3/8) Epoch 6, batch 34400, loss[loss=0.144, simple_loss=0.2167, pruned_loss=0.03564, over 4792.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2188, pruned_loss=0.03805, over 972121.22 frames.], batch size: 14, lr: 3.20e-04
+2022-05-05 17:39:45,299 INFO [train.py:715] (3/8) Epoch 6, batch 34450, loss[loss=0.1487, simple_loss=0.2183, pruned_loss=0.03954, over 4916.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03753, over 971401.44 frames.], batch size: 18, lr: 3.20e-04
+2022-05-05 17:40:24,040 INFO [train.py:715] (3/8) Epoch 6, batch 34500, loss[loss=0.138, simple_loss=0.2071, pruned_loss=0.03444, over 4774.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2193, pruned_loss=0.03786, over 971931.35 frames.], batch size: 18, lr: 3.20e-04
+2022-05-05 17:41:02,892 INFO [train.py:715] (3/8) Epoch 6, batch 34550, loss[loss=0.1405, simple_loss=0.2107, pruned_loss=0.03514, over 4881.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2202, pruned_loss=0.03855, over 971989.34 frames.], batch size: 22, lr: 3.20e-04
+2022-05-05 17:41:41,806 INFO [train.py:715] (3/8) Epoch 6, batch 34600, loss[loss=0.149, simple_loss=0.2233, pruned_loss=0.03737, over 4831.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2215, pruned_loss=0.03882, over 971967.65 frames.], batch size: 13, lr: 3.20e-04
+2022-05-05 17:42:20,616 INFO [train.py:715] (3/8) Epoch 6, batch 34650, loss[loss=0.1529, simple_loss=0.2136, pruned_loss=0.04609, over 4771.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2203, pruned_loss=0.03833, over 971460.18 frames.], batch size: 12, lr: 3.20e-04
+2022-05-05 17:42:59,315 INFO [train.py:715] (3/8) Epoch 6, batch 34700, loss[loss=0.1004, simple_loss=0.159, pruned_loss=0.02089, over 4794.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2191, pruned_loss=0.0377, over 970791.83 frames.], batch size: 12, lr: 3.20e-04
+2022-05-05 17:43:37,148 INFO [train.py:715] (3/8) Epoch 6, batch 34750, loss[loss=0.1128, simple_loss=0.1859, pruned_loss=0.01985, over 4789.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03755, over 971159.04 frames.], batch size: 18, lr: 3.20e-04
+2022-05-05 17:44:13,983 INFO [train.py:715] (3/8) Epoch 6, batch 34800, loss[loss=0.1185, simple_loss=0.1785, pruned_loss=0.02925, over 4773.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03699, over 971252.49 frames.], batch size: 12, lr: 3.20e-04
+2022-05-05 17:45:04,005 INFO [train.py:715] (3/8) Epoch 7, batch 0, loss[loss=0.1593, simple_loss=0.2248, pruned_loss=0.04693, over 4911.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2248, pruned_loss=0.04693, over 4911.00 frames.], batch size: 17, lr: 3.03e-04
+2022-05-05 17:45:42,574 INFO [train.py:715] (3/8) Epoch 7, batch 50, loss[loss=0.1427, simple_loss=0.2041, pruned_loss=0.04061, over 4832.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2176, pruned_loss=0.03934, over 219044.59 frames.], batch size: 13, lr: 3.03e-04
+2022-05-05 17:46:21,356 INFO [train.py:715] (3/8) Epoch 7, batch 100, loss[loss=0.1361, simple_loss=0.205, pruned_loss=0.03358, over 4966.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03879, over 385763.88 frames.], batch size: 24, lr: 3.03e-04
+2022-05-05 17:47:00,258 INFO [train.py:715] (3/8) Epoch 7, batch 150, loss[loss=0.136, simple_loss=0.203, pruned_loss=0.03444, over 4989.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.03824, over 516200.57 frames.], batch size: 25, lr: 3.03e-04
+2022-05-05 17:47:39,937 INFO [train.py:715] (3/8) Epoch 7, batch 200, loss[loss=0.1425, simple_loss=0.2186, pruned_loss=0.03317, over 4870.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2195, pruned_loss=0.03884, over 617768.72 frames.], batch size: 22, lr: 3.03e-04
+2022-05-05 17:48:18,722 INFO [train.py:715] (3/8) Epoch 7, batch 250, loss[loss=0.09433, simple_loss=0.1612, pruned_loss=0.01372, over 4810.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2183, pruned_loss=0.03834, over 697555.78 frames.], batch size: 12, lr: 3.03e-04
+2022-05-05 17:48:58,169 INFO [train.py:715] (3/8) Epoch 7, batch 300, loss[loss=0.1564, simple_loss=0.236, pruned_loss=0.03836, over 4933.00 frames.], tot_loss[loss=0.147, simple_loss=0.2185, pruned_loss=0.03775, over 758993.39 frames.], batch size: 29, lr: 3.02e-04
+2022-05-05 17:49:36,849 INFO [train.py:715] (3/8) Epoch 7, batch 350, loss[loss=0.1268, simple_loss=0.203, pruned_loss=0.02532, over 4864.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2173, pruned_loss=0.0371, over 806540.82 frames.], batch size: 20, lr: 3.02e-04
+2022-05-05 17:50:16,224 INFO [train.py:715] (3/8) Epoch 7, batch 400, loss[loss=0.1415, simple_loss=0.2178, pruned_loss=0.03259, over 4935.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03755, over 843514.06 frames.], batch size: 21, lr: 3.02e-04
+2022-05-05 17:50:54,886 INFO [train.py:715] (3/8) Epoch 7, batch 450, loss[loss=0.1507, simple_loss=0.2185, pruned_loss=0.04147, over 4960.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.0377, over 872261.65 frames.], batch size: 21, lr: 3.02e-04
+2022-05-05 17:51:33,738 INFO [train.py:715] (3/8) Epoch 7, batch 500, loss[loss=0.128, simple_loss=0.1995, pruned_loss=0.02824, over 4777.00 frames.], tot_loss[loss=0.147, simple_loss=0.2185, pruned_loss=0.0377, over 893815.61 frames.], batch size: 18, lr: 3.02e-04
+2022-05-05 17:52:12,472 INFO [train.py:715] (3/8) Epoch 7, batch 550, loss[loss=0.139, simple_loss=0.205, pruned_loss=0.03652, over 4810.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2189, pruned_loss=0.03729, over 912061.63 frames.], batch size: 15, lr: 3.02e-04
+2022-05-05 17:52:51,636 INFO [train.py:715] (3/8) Epoch 7, batch 600, loss[loss=0.1616, simple_loss=0.2262, pruned_loss=0.04848, over 4888.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2194, pruned_loss=0.03811, over 926574.54 frames.], batch size: 22, lr: 3.02e-04
+2022-05-05 17:53:29,945 INFO [train.py:715] (3/8) Epoch 7, batch 650, loss[loss=0.1081, simple_loss=0.183, pruned_loss=0.01659, over 4774.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2197, pruned_loss=0.03799, over 937118.12 frames.], batch size: 12, lr: 3.02e-04
+2022-05-05 17:54:08,326 INFO [train.py:715] (3/8) Epoch 7, batch 700, loss[loss=0.146, simple_loss=0.2105, pruned_loss=0.04078, over 4961.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2192, pruned_loss=0.03777, over 944883.88 frames.], batch size: 35, lr: 3.02e-04
+2022-05-05 17:54:47,593 INFO [train.py:715] (3/8) Epoch 7, batch 750, loss[loss=0.2212, simple_loss=0.281, pruned_loss=0.0807, over 4886.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03755, over 951782.10 frames.], batch size: 16, lr: 3.02e-04
+2022-05-05 17:55:26,298 INFO [train.py:715] (3/8) Epoch 7, batch 800, loss[loss=0.1517, simple_loss=0.2341, pruned_loss=0.03464, over 4934.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03747, over 956292.15 frames.], batch size: 29, lr: 3.02e-04
+2022-05-05 17:56:04,986 INFO [train.py:715] (3/8) Epoch 7, batch 850, loss[loss=0.1226, simple_loss=0.1973, pruned_loss=0.02391, over 4924.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2184, pruned_loss=0.03749, over 959499.92 frames.], batch size: 18, lr: 3.02e-04
+2022-05-05 17:56:44,239 INFO [train.py:715] (3/8) Epoch 7, batch 900, loss[loss=0.1329, simple_loss=0.2201, pruned_loss=0.02289, over 4916.00 frames.], tot_loss[loss=0.147, simple_loss=0.219, pruned_loss=0.03754, over 962263.75 frames.], batch size: 23, lr: 3.02e-04
+2022-05-05 17:57:23,221 INFO [train.py:715] (3/8) Epoch 7, batch 950, loss[loss=0.1291, simple_loss=0.2025, pruned_loss=0.02787, over 4850.00 frames.], tot_loss[loss=0.147, simple_loss=0.2186, pruned_loss=0.03768, over 965073.28 frames.], batch size: 30, lr: 3.02e-04
+2022-05-05 17:58:01,725 INFO [train.py:715] (3/8) Epoch 7, batch 1000, loss[loss=0.1396, simple_loss=0.2001, pruned_loss=0.03954, over 4696.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03777, over 966782.26 frames.], batch size: 15, lr: 3.02e-04
+2022-05-05 17:58:40,407 INFO [train.py:715] (3/8) Epoch 7, batch 1050, loss[loss=0.1138, simple_loss=0.1874, pruned_loss=0.02007, over 4656.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03786, over 966991.49 frames.], batch size: 13, lr: 3.02e-04
+2022-05-05 17:59:19,624 INFO [train.py:715] (3/8) Epoch 7, batch 1100, loss[loss=0.1198, simple_loss=0.1849, pruned_loss=0.02735, over 4829.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2183, pruned_loss=0.03774, over 967738.63 frames.], batch size: 15, lr: 3.02e-04
+2022-05-05 17:59:57,782 INFO [train.py:715] (3/8) Epoch 7, batch 1150, loss[loss=0.1273, simple_loss=0.1935, pruned_loss=0.03051, over 4689.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.03745, over 969033.02 frames.], batch size: 15, lr: 3.02e-04
+2022-05-05 18:00:36,963 INFO [train.py:715] (3/8) Epoch 7, batch 1200, loss[loss=0.1434, simple_loss=0.2123, pruned_loss=0.03723, over 4963.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03757, over 970382.46 frames.], batch size: 14, lr: 3.02e-04
+2022-05-05 18:01:16,053 INFO [train.py:715] (3/8) Epoch 7, batch 1250, loss[loss=0.1324, simple_loss=0.2006, pruned_loss=0.03213, over 4933.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.0372, over 970909.07 frames.], batch size: 29, lr: 3.02e-04
+2022-05-05 18:01:55,184 INFO [train.py:715] (3/8) Epoch 7, batch 1300, loss[loss=0.1506, simple_loss=0.2362, pruned_loss=0.0325, over 4790.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2182, pruned_loss=0.03769, over 971649.02 frames.], batch size: 18, lr: 3.02e-04
+2022-05-05 18:02:33,763 INFO [train.py:715] (3/8) Epoch 7, batch 1350, loss[loss=0.1252, simple_loss=0.1978, pruned_loss=0.02628, over 4912.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03777, over 971967.46 frames.], batch size: 17, lr: 3.02e-04
+2022-05-05 18:03:12,553 INFO [train.py:715] (3/8) Epoch 7, batch 1400, loss[loss=0.129, simple_loss=0.2064, pruned_loss=0.02583, over 4989.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2185, pruned_loss=0.03792, over 971620.32 frames.], batch size: 20, lr: 3.02e-04
+2022-05-05 18:03:51,641 INFO [train.py:715] (3/8) Epoch 7, batch 1450, loss[loss=0.1799, simple_loss=0.2501, pruned_loss=0.05481, over 4873.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2187, pruned_loss=0.0382, over 971077.70 frames.], batch size: 39, lr: 3.02e-04
+2022-05-05 18:04:29,771 INFO [train.py:715] (3/8) Epoch 7, batch 1500, loss[loss=0.1656, simple_loss=0.2306, pruned_loss=0.05036, over 4978.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2187, pruned_loss=0.03796, over 971531.43 frames.], batch size: 28, lr: 3.02e-04
+2022-05-05 18:05:08,980 INFO [train.py:715] (3/8) Epoch 7, batch 1550, loss[loss=0.1519, simple_loss=0.2131, pruned_loss=0.04537, over 4975.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2179, pruned_loss=0.03767, over 972078.64 frames.], batch size: 35, lr: 3.02e-04
+2022-05-05 18:05:47,788 INFO [train.py:715] (3/8) Epoch 7, batch 1600, loss[loss=0.124, simple_loss=0.1949, pruned_loss=0.02655, over 4692.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2174, pruned_loss=0.03749, over 972024.33 frames.], batch size: 15, lr: 3.02e-04
+2022-05-05 18:06:26,681 INFO [train.py:715] (3/8) Epoch 7, batch 1650, loss[loss=0.1451, simple_loss=0.2091, pruned_loss=0.04058, over 4976.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2178, pruned_loss=0.03753, over 971673.69 frames.], batch size: 15, lr: 3.02e-04
+2022-05-05 18:07:05,256 INFO [train.py:715] (3/8) Epoch 7, batch 1700, loss[loss=0.1134, simple_loss=0.1891, pruned_loss=0.01888, over 4896.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2176, pruned_loss=0.0374, over 971091.98 frames.], batch size: 22, lr: 3.02e-04
+2022-05-05 18:07:44,161 INFO [train.py:715] (3/8) Epoch 7, batch 1750, loss[loss=0.1347, simple_loss=0.2033, pruned_loss=0.03305, over 4835.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03692, over 971629.14 frames.], batch size: 12, lr: 3.02e-04
+2022-05-05 18:08:24,138 INFO [train.py:715] (3/8) Epoch 7, batch 1800, loss[loss=0.1536, simple_loss=0.2346, pruned_loss=0.0363, over 4947.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03739, over 972185.63 frames.], batch size: 39, lr: 3.02e-04
+2022-05-05 18:09:03,071 INFO [train.py:715] (3/8) Epoch 7, batch 1850, loss[loss=0.1139, simple_loss=0.1859, pruned_loss=0.02092, over 4783.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.0375, over 972244.00 frames.], batch size: 12, lr: 3.02e-04
+2022-05-05 18:09:41,926 INFO [train.py:715] (3/8) Epoch 7, batch 1900, loss[loss=0.1325, simple_loss=0.2092, pruned_loss=0.02794, over 4781.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.0374, over 972089.37 frames.], batch size: 18, lr: 3.01e-04
+2022-05-05 18:10:20,111 INFO [train.py:715] (3/8) Epoch 7, batch 1950, loss[loss=0.1638, simple_loss=0.2364, pruned_loss=0.04563, over 4857.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.0377, over 972898.25 frames.], batch size: 30, lr: 3.01e-04
+2022-05-05 18:10:59,289 INFO [train.py:715] (3/8) Epoch 7, batch 2000, loss[loss=0.1643, simple_loss=0.2283, pruned_loss=0.0501, over 4874.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2188, pruned_loss=0.03803, over 973622.31 frames.], batch size: 32, lr: 3.01e-04
+2022-05-05 18:11:37,486 INFO [train.py:715] (3/8) Epoch 7, batch 2050, loss[loss=0.1865, simple_loss=0.2527, pruned_loss=0.06017, over 4877.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03751, over 973923.34 frames.], batch size: 32, lr: 3.01e-04
+2022-05-05 18:12:16,138 INFO [train.py:715] (3/8) Epoch 7, batch 2100, loss[loss=0.1822, simple_loss=0.2456, pruned_loss=0.0594, over 4912.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03806, over 974565.08 frames.], batch size: 18, lr: 3.01e-04
+2022-05-05 18:12:54,592 INFO [train.py:715] (3/8) Epoch 7, batch 2150, loss[loss=0.1427, simple_loss=0.2045, pruned_loss=0.04044, over 4841.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2181, pruned_loss=0.03752, over 974279.98 frames.], batch size: 12, lr: 3.01e-04
+2022-05-05 18:13:32,800 INFO [train.py:715] (3/8) Epoch 7, batch 2200, loss[loss=0.1568, simple_loss=0.2292, pruned_loss=0.04222, over 4875.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2185, pruned_loss=0.03818, over 974046.46 frames.], batch size: 20, lr: 3.01e-04
+2022-05-05 18:14:11,048 INFO [train.py:715] (3/8) Epoch 7, batch 2250, loss[loss=0.1159, simple_loss=0.1889, pruned_loss=0.02146, over 4973.00 frames.], tot_loss[loss=0.1469, simple_loss=0.218, pruned_loss=0.03793, over 974467.99 frames.], batch size: 15, lr: 3.01e-04
+2022-05-05 18:14:50,048 INFO [train.py:715] (3/8) Epoch 7, batch 2300, loss[loss=0.1534, simple_loss=0.2162, pruned_loss=0.04531, over 4902.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2185, pruned_loss=0.03819, over 974475.46 frames.], batch size: 17, lr: 3.01e-04
+2022-05-05 18:15:29,528 INFO [train.py:715] (3/8) Epoch 7, batch 2350, loss[loss=0.1376, simple_loss=0.2167, pruned_loss=0.02924, over 4988.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2179, pruned_loss=0.0382, over 974151.16 frames.], batch size: 25, lr: 3.01e-04
+2022-05-05 18:16:08,317 INFO [train.py:715] (3/8) Epoch 7, batch 2400, loss[loss=0.1358, simple_loss=0.207, pruned_loss=0.03229, over 4877.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2183, pruned_loss=0.03839, over 973976.80 frames.], batch size: 16, lr: 3.01e-04
+2022-05-05 18:16:46,789 INFO [train.py:715] (3/8) Epoch 7, batch 2450, loss[loss=0.117, simple_loss=0.1897, pruned_loss=0.02212, over 4787.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2185, pruned_loss=0.03821, over 974112.12 frames.], batch size: 18, lr: 3.01e-04
+2022-05-05 18:17:25,560 INFO [train.py:715] (3/8) Epoch 7, batch 2500, loss[loss=0.171, simple_loss=0.2389, pruned_loss=0.05156, over 4775.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2179, pruned_loss=0.03748, over 973166.31 frames.], batch size: 19, lr: 3.01e-04
+2022-05-05 18:18:03,862 INFO [train.py:715] (3/8) Epoch 7, batch 2550, loss[loss=0.1429, simple_loss=0.2157, pruned_loss=0.03511, over 4802.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2184, pruned_loss=0.0376, over 973085.53 frames.], batch size: 21, lr: 3.01e-04
+2022-05-05 18:18:42,384 INFO [train.py:715] (3/8) Epoch 7, batch 2600, loss[loss=0.159, simple_loss=0.2373, pruned_loss=0.04037, over 4777.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03757, over 972183.12 frames.], batch size: 19, lr: 3.01e-04
+2022-05-05 18:19:21,119 INFO [train.py:715] (3/8) Epoch 7, batch 2650, loss[loss=0.1509, simple_loss=0.2173, pruned_loss=0.0422, over 4824.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.0373, over 971578.54 frames.], batch size: 15, lr: 3.01e-04
+2022-05-05 18:19:59,710 INFO [train.py:715] (3/8) Epoch 7, batch 2700, loss[loss=0.1368, simple_loss=0.203, pruned_loss=0.03532, over 4903.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.037, over 972079.47 frames.], batch size: 17, lr: 3.01e-04
+2022-05-05 18:20:37,585 INFO [train.py:715] (3/8) Epoch 7, batch 2750, loss[loss=0.1603, simple_loss=0.2338, pruned_loss=0.0434, over 4971.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2179, pruned_loss=0.03735, over 971767.14 frames.], batch size: 15, lr: 3.01e-04
+2022-05-05 18:21:16,373 INFO [train.py:715] (3/8) Epoch 7, batch 2800, loss[loss=0.1276, simple_loss=0.2037, pruned_loss=0.0257, over 4989.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2172, pruned_loss=0.03704, over 972057.22 frames.], batch size: 28, lr: 3.01e-04
+2022-05-05 18:21:55,733 INFO [train.py:715] (3/8) Epoch 7, batch 2850, loss[loss=0.1224, simple_loss=0.1961, pruned_loss=0.02433, over 4951.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2169, pruned_loss=0.03692, over 971564.28 frames.], batch size: 29, lr: 3.01e-04
+2022-05-05 18:22:35,310 INFO [train.py:715] (3/8) Epoch 7, batch 2900, loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03353, over 4883.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2166, pruned_loss=0.03658, over 972581.04 frames.], batch size: 22, lr: 3.01e-04
+2022-05-05 18:23:14,210 INFO [train.py:715] (3/8) Epoch 7, batch 2950, loss[loss=0.1387, simple_loss=0.2061, pruned_loss=0.03569, over 4718.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03604, over 972285.56 frames.], batch size: 15, lr: 3.01e-04
+2022-05-05 18:23:53,378 INFO [train.py:715] (3/8) Epoch 7, batch 3000, loss[loss=0.1563, simple_loss=0.2358, pruned_loss=0.03834, over 4685.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2164, pruned_loss=0.03693, over 971967.98 frames.], batch size: 15, lr: 3.01e-04
+2022-05-05 18:23:53,379 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 18:24:04,766 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.1084, simple_loss=0.1933, pruned_loss=0.01171, over 914524.00 frames.
+2022-05-05 18:24:44,251 INFO [train.py:715] (3/8) Epoch 7, batch 3050, loss[loss=0.1277, simple_loss=0.1984, pruned_loss=0.02848, over 4861.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2159, pruned_loss=0.03655, over 972597.70 frames.], batch size: 32, lr: 3.01e-04
+2022-05-05 18:25:23,060 INFO [train.py:715] (3/8) Epoch 7, batch 3100, loss[loss=0.1765, simple_loss=0.251, pruned_loss=0.05098, over 4918.00 frames.], tot_loss[loss=0.146, simple_loss=0.2173, pruned_loss=0.03732, over 973569.10 frames.], batch size: 39, lr: 3.01e-04
+2022-05-05 18:26:01,759 INFO [train.py:715] (3/8) Epoch 7, batch 3150, loss[loss=0.1508, simple_loss=0.2312, pruned_loss=0.03517, over 4807.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03747, over 973253.31 frames.], batch size: 25, lr: 3.01e-04
+2022-05-05 18:26:39,662 INFO [train.py:715] (3/8) Epoch 7, batch 3200, loss[loss=0.1385, simple_loss=0.2039, pruned_loss=0.03658, over 4643.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03735, over 973288.00 frames.], batch size: 13, lr: 3.01e-04
+2022-05-05 18:27:17,887 INFO [train.py:715] (3/8) Epoch 7, batch 3250, loss[loss=0.1673, simple_loss=0.2434, pruned_loss=0.04562, over 4974.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03726, over 973187.14 frames.], batch size: 15, lr: 3.01e-04
+2022-05-05 18:27:56,437 INFO [train.py:715] (3/8) Epoch 7, batch 3300, loss[loss=0.1432, simple_loss=0.2189, pruned_loss=0.03375, over 4757.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2178, pruned_loss=0.03727, over 971907.47 frames.], batch size: 16, lr: 3.01e-04
+2022-05-05 18:28:35,031 INFO [train.py:715] (3/8) Epoch 7, batch 3350, loss[loss=0.1215, simple_loss=0.1949, pruned_loss=0.02408, over 4955.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03735, over 971958.20 frames.], batch size: 14, lr: 3.01e-04
+2022-05-05 18:29:13,822 INFO [train.py:715] (3/8) Epoch 7, batch 3400, loss[loss=0.1322, simple_loss=0.2044, pruned_loss=0.03005, over 4977.00 frames.], tot_loss[loss=0.1468, simple_loss=0.218, pruned_loss=0.03778, over 972513.33 frames.], batch size: 28, lr: 3.01e-04
+2022-05-05 18:29:52,250 INFO [train.py:715] (3/8) Epoch 7, batch 3450, loss[loss=0.1106, simple_loss=0.1842, pruned_loss=0.01848, over 4939.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2177, pruned_loss=0.03785, over 972303.44 frames.], batch size: 29, lr: 3.01e-04
+2022-05-05 18:30:31,305 INFO [train.py:715] (3/8) Epoch 7, batch 3500, loss[loss=0.1473, simple_loss=0.2079, pruned_loss=0.04341, over 4867.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2181, pruned_loss=0.03835, over 972785.03 frames.], batch size: 16, lr: 3.01e-04
+2022-05-05 18:31:09,924 INFO [train.py:715] (3/8) Epoch 7, batch 3550, loss[loss=0.1473, simple_loss=0.2191, pruned_loss=0.03779, over 4815.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2179, pruned_loss=0.0384, over 972051.79 frames.], batch size: 26, lr: 3.00e-04
+2022-05-05 18:31:48,695 INFO [train.py:715] (3/8) Epoch 7, batch 3600, loss[loss=0.1376, simple_loss=0.2125, pruned_loss=0.03139, over 4927.00 frames.], tot_loss[loss=0.147, simple_loss=0.2179, pruned_loss=0.03799, over 972828.49 frames.], batch size: 21, lr: 3.00e-04
+2022-05-05 18:32:27,425 INFO [train.py:715] (3/8) Epoch 7, batch 3650, loss[loss=0.1387, simple_loss=0.205, pruned_loss=0.03617, over 4904.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2179, pruned_loss=0.03788, over 972977.91 frames.], batch size: 18, lr: 3.00e-04
+2022-05-05 18:33:06,463 INFO [train.py:715] (3/8) Epoch 7, batch 3700, loss[loss=0.1319, simple_loss=0.2042, pruned_loss=0.02981, over 4859.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03817, over 973013.78 frames.], batch size: 20, lr: 3.00e-04
+2022-05-05 18:33:45,233 INFO [train.py:715] (3/8) Epoch 7, batch 3750, loss[loss=0.1244, simple_loss=0.1956, pruned_loss=0.02659, over 4861.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2184, pruned_loss=0.03816, over 973186.25 frames.], batch size: 16, lr: 3.00e-04
+2022-05-05 18:34:23,491 INFO [train.py:715] (3/8) Epoch 7, batch 3800, loss[loss=0.1526, simple_loss=0.2208, pruned_loss=0.04219, over 4748.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2189, pruned_loss=0.03801, over 973101.23 frames.], batch size: 16, lr: 3.00e-04
+2022-05-05 18:35:01,655 INFO [train.py:715] (3/8) Epoch 7, batch 3850, loss[loss=0.1168, simple_loss=0.1951, pruned_loss=0.01928, over 4983.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03791, over 973490.49 frames.], batch size: 25, lr: 3.00e-04
+2022-05-05 18:35:39,927 INFO [train.py:715] (3/8) Epoch 7, batch 3900, loss[loss=0.1214, simple_loss=0.2064, pruned_loss=0.01823, over 4931.00 frames.], tot_loss[loss=0.148, simple_loss=0.2196, pruned_loss=0.03819, over 973108.10 frames.], batch size: 29, lr: 3.00e-04
+2022-05-05 18:36:18,413 INFO [train.py:715] (3/8) Epoch 7, batch 3950, loss[loss=0.1391, simple_loss=0.2178, pruned_loss=0.03015, over 4921.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.03817, over 972459.38 frames.], batch size: 22, lr: 3.00e-04
+2022-05-05 18:36:57,037 INFO [train.py:715] (3/8) Epoch 7, batch 4000, loss[loss=0.2009, simple_loss=0.2631, pruned_loss=0.06934, over 4838.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2189, pruned_loss=0.03786, over 972582.52 frames.], batch size: 15, lr: 3.00e-04
+2022-05-05 18:37:35,136 INFO [train.py:715] (3/8) Epoch 7, batch 4050, loss[loss=0.1382, simple_loss=0.2146, pruned_loss=0.03087, over 4972.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2188, pruned_loss=0.03748, over 973474.81 frames.], batch size: 24, lr: 3.00e-04
+2022-05-05 18:38:14,046 INFO [train.py:715] (3/8) Epoch 7, batch 4100, loss[loss=0.1198, simple_loss=0.2002, pruned_loss=0.01974, over 4768.00 frames.], tot_loss[loss=0.147, simple_loss=0.219, pruned_loss=0.03744, over 972990.39 frames.], batch size: 19, lr: 3.00e-04
+2022-05-05 18:38:52,569 INFO [train.py:715] (3/8) Epoch 7, batch 4150, loss[loss=0.1443, simple_loss=0.2147, pruned_loss=0.0369, over 4813.00 frames.], tot_loss[loss=0.1471, simple_loss=0.219, pruned_loss=0.03766, over 972467.03 frames.], batch size: 25, lr: 3.00e-04
+2022-05-05 18:39:31,259 INFO [train.py:715] (3/8) Epoch 7, batch 4200, loss[loss=0.1509, simple_loss=0.2245, pruned_loss=0.03867, over 4986.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2185, pruned_loss=0.03765, over 973117.01 frames.], batch size: 33, lr: 3.00e-04
+2022-05-05 18:40:09,112 INFO [train.py:715] (3/8) Epoch 7, batch 4250, loss[loss=0.1495, simple_loss=0.2292, pruned_loss=0.03488, over 4940.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.03786, over 972919.38 frames.], batch size: 21, lr: 3.00e-04
+2022-05-05 18:40:47,951 INFO [train.py:715] (3/8) Epoch 7, batch 4300, loss[loss=0.1564, simple_loss=0.2236, pruned_loss=0.04461, over 4822.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2187, pruned_loss=0.03792, over 972496.36 frames.], batch size: 15, lr: 3.00e-04
+2022-05-05 18:41:28,766 INFO [train.py:715] (3/8) Epoch 7, batch 4350, loss[loss=0.119, simple_loss=0.1906, pruned_loss=0.02374, over 4803.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03773, over 972893.00 frames.], batch size: 21, lr: 3.00e-04
+2022-05-05 18:42:07,272 INFO [train.py:715] (3/8) Epoch 7, batch 4400, loss[loss=0.15, simple_loss=0.2297, pruned_loss=0.03512, over 4905.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2188, pruned_loss=0.03806, over 972888.82 frames.], batch size: 19, lr: 3.00e-04
+2022-05-05 18:42:46,327 INFO [train.py:715] (3/8) Epoch 7, batch 4450, loss[loss=0.1029, simple_loss=0.1751, pruned_loss=0.01537, over 4766.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03812, over 972887.11 frames.], batch size: 14, lr: 3.00e-04
+2022-05-05 18:43:25,195 INFO [train.py:715] (3/8) Epoch 7, batch 4500, loss[loss=0.1475, simple_loss=0.2231, pruned_loss=0.03595, over 4874.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.03768, over 972976.37 frames.], batch size: 16, lr: 3.00e-04
+2022-05-05 18:44:03,953 INFO [train.py:715] (3/8) Epoch 7, batch 4550, loss[loss=0.1778, simple_loss=0.247, pruned_loss=0.05425, over 4826.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2189, pruned_loss=0.03765, over 973315.40 frames.], batch size: 25, lr: 3.00e-04
+2022-05-05 18:44:42,554 INFO [train.py:715] (3/8) Epoch 7, batch 4600, loss[loss=0.1807, simple_loss=0.264, pruned_loss=0.0487, over 4920.00 frames.], tot_loss[loss=0.1471, simple_loss=0.219, pruned_loss=0.0376, over 973000.21 frames.], batch size: 18, lr: 3.00e-04
+2022-05-05 18:45:21,325 INFO [train.py:715] (3/8) Epoch 7, batch 4650, loss[loss=0.1157, simple_loss=0.19, pruned_loss=0.02067, over 4774.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2187, pruned_loss=0.03784, over 971994.57 frames.], batch size: 14, lr: 3.00e-04
+2022-05-05 18:45:59,788 INFO [train.py:715] (3/8) Epoch 7, batch 4700, loss[loss=0.1622, simple_loss=0.2418, pruned_loss=0.04133, over 4893.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03757, over 971852.22 frames.], batch size: 17, lr: 3.00e-04
+2022-05-05 18:46:37,972 INFO [train.py:715] (3/8) Epoch 7, batch 4750, loss[loss=0.1555, simple_loss=0.2458, pruned_loss=0.03263, over 4822.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2184, pruned_loss=0.03762, over 971552.00 frames.], batch size: 26, lr: 3.00e-04
+2022-05-05 18:47:17,154 INFO [train.py:715] (3/8) Epoch 7, batch 4800, loss[loss=0.1555, simple_loss=0.2242, pruned_loss=0.04341, over 4983.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03751, over 971940.08 frames.], batch size: 35, lr: 3.00e-04
+2022-05-05 18:47:55,561 INFO [train.py:715] (3/8) Epoch 7, batch 4850, loss[loss=0.1428, simple_loss=0.2231, pruned_loss=0.03123, over 4984.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2179, pruned_loss=0.03713, over 971606.84 frames.], batch size: 26, lr: 3.00e-04
+2022-05-05 18:48:34,304 INFO [train.py:715] (3/8) Epoch 7, batch 4900, loss[loss=0.1559, simple_loss=0.2127, pruned_loss=0.04952, over 4962.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03738, over 971865.69 frames.], batch size: 14, lr: 3.00e-04
+2022-05-05 18:49:12,737 INFO [train.py:715] (3/8) Epoch 7, batch 4950, loss[loss=0.1409, simple_loss=0.2177, pruned_loss=0.03209, over 4930.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2176, pruned_loss=0.03712, over 971377.12 frames.], batch size: 23, lr: 3.00e-04
+2022-05-05 18:49:51,777 INFO [train.py:715] (3/8) Epoch 7, batch 5000, loss[loss=0.1546, simple_loss=0.2347, pruned_loss=0.03727, over 4962.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2177, pruned_loss=0.0374, over 971484.17 frames.], batch size: 24, lr: 3.00e-04
+2022-05-05 18:50:30,773 INFO [train.py:715] (3/8) Epoch 7, batch 5050, loss[loss=0.1326, simple_loss=0.2103, pruned_loss=0.02741, over 4935.00 frames.], tot_loss[loss=0.1469, simple_loss=0.218, pruned_loss=0.03786, over 972112.65 frames.], batch size: 29, lr: 3.00e-04
+2022-05-05 18:51:09,370 INFO [train.py:715] (3/8) Epoch 7, batch 5100, loss[loss=0.1447, simple_loss=0.2284, pruned_loss=0.03051, over 4753.00 frames.], tot_loss[loss=0.1467, simple_loss=0.218, pruned_loss=0.03773, over 971643.00 frames.], batch size: 16, lr: 3.00e-04
+2022-05-05 18:51:48,428 INFO [train.py:715] (3/8) Epoch 7, batch 5150, loss[loss=0.1379, simple_loss=0.2125, pruned_loss=0.03164, over 4765.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2177, pruned_loss=0.03734, over 972144.01 frames.], batch size: 19, lr: 3.00e-04
+2022-05-05 18:52:27,136 INFO [train.py:715] (3/8) Epoch 7, batch 5200, loss[loss=0.1362, simple_loss=0.2103, pruned_loss=0.03105, over 4845.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2173, pruned_loss=0.03723, over 972637.43 frames.], batch size: 15, lr: 2.99e-04
+2022-05-05 18:53:06,164 INFO [train.py:715] (3/8) Epoch 7, batch 5250, loss[loss=0.1487, simple_loss=0.219, pruned_loss=0.03922, over 4926.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2174, pruned_loss=0.03703, over 973051.18 frames.], batch size: 18, lr: 2.99e-04
+2022-05-05 18:53:44,792 INFO [train.py:715] (3/8) Epoch 7, batch 5300, loss[loss=0.1382, simple_loss=0.2067, pruned_loss=0.03481, over 4862.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2182, pruned_loss=0.03711, over 973959.49 frames.], batch size: 39, lr: 2.99e-04
+2022-05-05 18:54:24,158 INFO [train.py:715] (3/8) Epoch 7, batch 5350, loss[loss=0.1662, simple_loss=0.2367, pruned_loss=0.04788, over 4821.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2185, pruned_loss=0.03713, over 974221.09 frames.], batch size: 27, lr: 2.99e-04
+2022-05-05 18:55:02,366 INFO [train.py:715] (3/8) Epoch 7, batch 5400, loss[loss=0.1904, simple_loss=0.2648, pruned_loss=0.05802, over 4876.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2191, pruned_loss=0.03727, over 973968.05 frames.], batch size: 22, lr: 2.99e-04
+2022-05-05 18:55:41,211 INFO [train.py:715] (3/8) Epoch 7, batch 5450, loss[loss=0.1534, simple_loss=0.2335, pruned_loss=0.03661, over 4922.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2191, pruned_loss=0.03683, over 974557.46 frames.], batch size: 29, lr: 2.99e-04
+2022-05-05 18:56:20,342 INFO [train.py:715] (3/8) Epoch 7, batch 5500, loss[loss=0.1432, simple_loss=0.216, pruned_loss=0.03525, over 4769.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2196, pruned_loss=0.0375, over 974030.50 frames.], batch size: 19, lr: 2.99e-04
+2022-05-05 18:56:59,129 INFO [train.py:715] (3/8) Epoch 7, batch 5550, loss[loss=0.1982, simple_loss=0.2697, pruned_loss=0.06335, over 4904.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2185, pruned_loss=0.0371, over 974100.91 frames.], batch size: 39, lr: 2.99e-04
+2022-05-05 18:57:38,239 INFO [train.py:715] (3/8) Epoch 7, batch 5600, loss[loss=0.1581, simple_loss=0.2344, pruned_loss=0.04086, over 4773.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2186, pruned_loss=0.03706, over 973640.90 frames.], batch size: 17, lr: 2.99e-04
+2022-05-05 18:58:17,279 INFO [train.py:715] (3/8) Epoch 7, batch 5650, loss[loss=0.1765, simple_loss=0.2412, pruned_loss=0.05595, over 4927.00 frames.], tot_loss[loss=0.146, simple_loss=0.2183, pruned_loss=0.03687, over 973537.73 frames.], batch size: 23, lr: 2.99e-04
+2022-05-05 18:58:56,368 INFO [train.py:715] (3/8) Epoch 7, batch 5700, loss[loss=0.1231, simple_loss=0.1854, pruned_loss=0.03037, over 4819.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2183, pruned_loss=0.03709, over 973820.58 frames.], batch size: 13, lr: 2.99e-04
+2022-05-05 18:59:34,749 INFO [train.py:715] (3/8) Epoch 7, batch 5750, loss[loss=0.1931, simple_loss=0.2413, pruned_loss=0.07248, over 4740.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03707, over 972884.55 frames.], batch size: 16, lr: 2.99e-04
+2022-05-05 19:00:12,900 INFO [train.py:715] (3/8) Epoch 7, batch 5800, loss[loss=0.171, simple_loss=0.2235, pruned_loss=0.05925, over 4829.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2176, pruned_loss=0.03734, over 972994.67 frames.], batch size: 30, lr: 2.99e-04
+2022-05-05 19:00:52,630 INFO [train.py:715] (3/8) Epoch 7, batch 5850, loss[loss=0.1665, simple_loss=0.2277, pruned_loss=0.05268, over 4834.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03744, over 973087.75 frames.], batch size: 25, lr: 2.99e-04
+2022-05-05 19:01:30,924 INFO [train.py:715] (3/8) Epoch 7, batch 5900, loss[loss=0.1536, simple_loss=0.229, pruned_loss=0.03913, over 4902.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2176, pruned_loss=0.03734, over 972889.88 frames.], batch size: 18, lr: 2.99e-04
+2022-05-05 19:02:09,960 INFO [train.py:715] (3/8) Epoch 7, batch 5950, loss[loss=0.1245, simple_loss=0.2035, pruned_loss=0.02271, over 4799.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2176, pruned_loss=0.03743, over 973228.06 frames.], batch size: 25, lr: 2.99e-04
+2022-05-05 19:02:48,384 INFO [train.py:715] (3/8) Epoch 7, batch 6000, loss[loss=0.1708, simple_loss=0.2349, pruned_loss=0.05333, over 4971.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03701, over 972768.58 frames.], batch size: 24, lr: 2.99e-04
+2022-05-05 19:02:48,385 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 19:02:58,046 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.1085, simple_loss=0.1933, pruned_loss=0.0119, over 914524.00 frames.
+2022-05-05 19:03:36,917 INFO [train.py:715] (3/8) Epoch 7, batch 6050, loss[loss=0.1528, simple_loss=0.2299, pruned_loss=0.03787, over 4869.00 frames.], tot_loss[loss=0.146, simple_loss=0.2179, pruned_loss=0.03711, over 973124.39 frames.], batch size: 16, lr: 2.99e-04
+2022-05-05 19:04:16,081 INFO [train.py:715] (3/8) Epoch 7, batch 6100, loss[loss=0.1741, simple_loss=0.2477, pruned_loss=0.05025, over 4768.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.0374, over 973314.08 frames.], batch size: 17, lr: 2.99e-04
+2022-05-05 19:04:55,379 INFO [train.py:715] (3/8) Epoch 7, batch 6150, loss[loss=0.1624, simple_loss=0.2385, pruned_loss=0.0432, over 4890.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03703, over 973058.20 frames.], batch size: 19, lr: 2.99e-04
+2022-05-05 19:05:33,828 INFO [train.py:715] (3/8) Epoch 7, batch 6200, loss[loss=0.1754, simple_loss=0.2503, pruned_loss=0.05025, over 4986.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2169, pruned_loss=0.03712, over 973188.47 frames.], batch size: 39, lr: 2.99e-04
+2022-05-05 19:06:13,680 INFO [train.py:715] (3/8) Epoch 7, batch 6250, loss[loss=0.1716, simple_loss=0.2488, pruned_loss=0.04719, over 4930.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2165, pruned_loss=0.03697, over 973484.90 frames.], batch size: 29, lr: 2.99e-04
+2022-05-05 19:06:52,575 INFO [train.py:715] (3/8) Epoch 7, batch 6300, loss[loss=0.1407, simple_loss=0.2111, pruned_loss=0.03513, over 4841.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2167, pruned_loss=0.03682, over 974289.95 frames.], batch size: 32, lr: 2.99e-04
+2022-05-05 19:07:30,973 INFO [train.py:715] (3/8) Epoch 7, batch 6350, loss[loss=0.1401, simple_loss=0.2255, pruned_loss=0.02735, over 4910.00 frames.], tot_loss[loss=0.1463, simple_loss=0.218, pruned_loss=0.0373, over 974412.78 frames.], batch size: 23, lr: 2.99e-04
+2022-05-05 19:08:10,031 INFO [train.py:715] (3/8) Epoch 7, batch 6400, loss[loss=0.1344, simple_loss=0.2178, pruned_loss=0.0255, over 4773.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2179, pruned_loss=0.03739, over 973458.24 frames.], batch size: 18, lr: 2.99e-04
+2022-05-05 19:08:49,046 INFO [train.py:715] (3/8) Epoch 7, batch 6450, loss[loss=0.1399, simple_loss=0.2153, pruned_loss=0.03223, over 4970.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2168, pruned_loss=0.03674, over 973978.69 frames.], batch size: 28, lr: 2.99e-04
+2022-05-05 19:09:27,585 INFO [train.py:715] (3/8) Epoch 7, batch 6500, loss[loss=0.1524, simple_loss=0.2341, pruned_loss=0.03531, over 4939.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.03699, over 973941.99 frames.], batch size: 29, lr: 2.99e-04
+2022-05-05 19:10:06,574 INFO [train.py:715] (3/8) Epoch 7, batch 6550, loss[loss=0.1445, simple_loss=0.2116, pruned_loss=0.03872, over 4690.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03684, over 973040.21 frames.], batch size: 15, lr: 2.99e-04
+2022-05-05 19:10:46,393 INFO [train.py:715] (3/8) Epoch 7, batch 6600, loss[loss=0.1452, simple_loss=0.2185, pruned_loss=0.03598, over 4943.00 frames.], tot_loss[loss=0.1453, simple_loss=0.217, pruned_loss=0.03679, over 972625.68 frames.], batch size: 29, lr: 2.99e-04
+2022-05-05 19:11:25,242 INFO [train.py:715] (3/8) Epoch 7, batch 6650, loss[loss=0.1344, simple_loss=0.2042, pruned_loss=0.03235, over 4974.00 frames.], tot_loss[loss=0.146, simple_loss=0.2176, pruned_loss=0.03724, over 972437.75 frames.], batch size: 35, lr: 2.99e-04
+2022-05-05 19:12:04,476 INFO [train.py:715] (3/8) Epoch 7, batch 6700, loss[loss=0.1552, simple_loss=0.2284, pruned_loss=0.04099, over 4885.00 frames.], tot_loss[loss=0.1454, simple_loss=0.217, pruned_loss=0.03693, over 972915.15 frames.], batch size: 19, lr: 2.99e-04
+2022-05-05 19:12:43,222 INFO [train.py:715] (3/8) Epoch 7, batch 6750, loss[loss=0.1188, simple_loss=0.1911, pruned_loss=0.02327, over 4754.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.03762, over 972465.81 frames.], batch size: 19, lr: 2.99e-04
+2022-05-05 19:13:22,216 INFO [train.py:715] (3/8) Epoch 7, batch 6800, loss[loss=0.1408, simple_loss=0.2168, pruned_loss=0.03235, over 4834.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03753, over 971844.30 frames.], batch size: 12, lr: 2.99e-04
+2022-05-05 19:14:00,586 INFO [train.py:715] (3/8) Epoch 7, batch 6850, loss[loss=0.1446, simple_loss=0.2142, pruned_loss=0.03752, over 4699.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03752, over 972626.00 frames.], batch size: 15, lr: 2.99e-04
+2022-05-05 19:14:39,179 INFO [train.py:715] (3/8) Epoch 7, batch 6900, loss[loss=0.1526, simple_loss=0.2274, pruned_loss=0.03891, over 4909.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.0376, over 972548.53 frames.], batch size: 18, lr: 2.98e-04
+2022-05-05 19:15:18,699 INFO [train.py:715] (3/8) Epoch 7, batch 6950, loss[loss=0.1475, simple_loss=0.2138, pruned_loss=0.04062, over 4793.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03696, over 972416.23 frames.], batch size: 17, lr: 2.98e-04
+2022-05-05 19:15:56,858 INFO [train.py:715] (3/8) Epoch 7, batch 7000, loss[loss=0.146, simple_loss=0.2185, pruned_loss=0.03675, over 4984.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03667, over 971971.06 frames.], batch size: 15, lr: 2.98e-04
+2022-05-05 19:16:35,558 INFO [train.py:715] (3/8) Epoch 7, batch 7050, loss[loss=0.1444, simple_loss=0.2197, pruned_loss=0.03458, over 4911.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.03657, over 972643.32 frames.], batch size: 19, lr: 2.98e-04
+2022-05-05 19:17:14,121 INFO [train.py:715] (3/8) Epoch 7, batch 7100, loss[loss=0.145, simple_loss=0.2271, pruned_loss=0.03142, over 4958.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.0371, over 972888.93 frames.], batch size: 21, lr: 2.98e-04
+2022-05-05 19:17:52,400 INFO [train.py:715] (3/8) Epoch 7, batch 7150, loss[loss=0.1304, simple_loss=0.1979, pruned_loss=0.03144, over 4839.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2174, pruned_loss=0.03668, over 972954.79 frames.], batch size: 15, lr: 2.98e-04
+2022-05-05 19:18:31,019 INFO [train.py:715] (3/8) Epoch 7, batch 7200, loss[loss=0.1277, simple_loss=0.2008, pruned_loss=0.02726, over 4815.00 frames.], tot_loss[loss=0.1454, simple_loss=0.217, pruned_loss=0.03694, over 972556.67 frames.], batch size: 12, lr: 2.98e-04
+2022-05-05 19:19:10,025 INFO [train.py:715] (3/8) Epoch 7, batch 7250, loss[loss=0.1511, simple_loss=0.2249, pruned_loss=0.03868, over 4792.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2176, pruned_loss=0.03749, over 972772.05 frames.], batch size: 21, lr: 2.98e-04
+2022-05-05 19:19:49,673 INFO [train.py:715] (3/8) Epoch 7, batch 7300, loss[loss=0.1446, simple_loss=0.2151, pruned_loss=0.03703, over 4785.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.03778, over 972246.11 frames.], batch size: 18, lr: 2.98e-04
+2022-05-05 19:20:28,210 INFO [train.py:715] (3/8) Epoch 7, batch 7350, loss[loss=0.1259, simple_loss=0.1971, pruned_loss=0.02733, over 4839.00 frames.], tot_loss[loss=0.146, simple_loss=0.2178, pruned_loss=0.03708, over 973262.88 frames.], batch size: 15, lr: 2.98e-04
+2022-05-05 19:21:06,663 INFO [train.py:715] (3/8) Epoch 7, batch 7400, loss[loss=0.1481, simple_loss=0.2164, pruned_loss=0.03985, over 4936.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2179, pruned_loss=0.03716, over 973288.26 frames.], batch size: 18, lr: 2.98e-04
+2022-05-05 19:21:45,792 INFO [train.py:715] (3/8) Epoch 7, batch 7450, loss[loss=0.1622, simple_loss=0.2332, pruned_loss=0.04556, over 4874.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03728, over 972500.54 frames.], batch size: 20, lr: 2.98e-04
+2022-05-05 19:22:24,000 INFO [train.py:715] (3/8) Epoch 7, batch 7500, loss[loss=0.1389, simple_loss=0.2036, pruned_loss=0.03705, over 4964.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.0371, over 972749.72 frames.], batch size: 35, lr: 2.98e-04
+2022-05-05 19:23:02,797 INFO [train.py:715] (3/8) Epoch 7, batch 7550, loss[loss=0.205, simple_loss=0.275, pruned_loss=0.06754, over 4683.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03735, over 972432.68 frames.], batch size: 15, lr: 2.98e-04
+2022-05-05 19:23:41,662 INFO [train.py:715] (3/8) Epoch 7, batch 7600, loss[loss=0.1505, simple_loss=0.2385, pruned_loss=0.03121, over 4886.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2186, pruned_loss=0.03743, over 972497.59 frames.], batch size: 19, lr: 2.98e-04
+2022-05-05 19:24:20,771 INFO [train.py:715] (3/8) Epoch 7, batch 7650, loss[loss=0.1498, simple_loss=0.22, pruned_loss=0.03978, over 4688.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2192, pruned_loss=0.03765, over 972270.14 frames.], batch size: 15, lr: 2.98e-04
+2022-05-05 19:24:59,079 INFO [train.py:715] (3/8) Epoch 7, batch 7700, loss[loss=0.1404, simple_loss=0.2106, pruned_loss=0.03506, over 4806.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2186, pruned_loss=0.03707, over 972908.02 frames.], batch size: 24, lr: 2.98e-04
+2022-05-05 19:25:38,046 INFO [train.py:715] (3/8) Epoch 7, batch 7750, loss[loss=0.1518, simple_loss=0.2195, pruned_loss=0.04199, over 4926.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2188, pruned_loss=0.03746, over 973028.20 frames.], batch size: 18, lr: 2.98e-04
+2022-05-05 19:26:17,070 INFO [train.py:715] (3/8) Epoch 7, batch 7800, loss[loss=0.1484, simple_loss=0.2158, pruned_loss=0.04051, over 4822.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2182, pruned_loss=0.03755, over 972271.91 frames.], batch size: 25, lr: 2.98e-04
+2022-05-05 19:26:55,230 INFO [train.py:715] (3/8) Epoch 7, batch 7850, loss[loss=0.1537, simple_loss=0.2241, pruned_loss=0.0416, over 4877.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2181, pruned_loss=0.03753, over 972571.36 frames.], batch size: 38, lr: 2.98e-04
+2022-05-05 19:27:34,429 INFO [train.py:715] (3/8) Epoch 7, batch 7900, loss[loss=0.1421, simple_loss=0.2167, pruned_loss=0.03372, over 4979.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.03784, over 973088.72 frames.], batch size: 28, lr: 2.98e-04
+2022-05-05 19:28:13,173 INFO [train.py:715] (3/8) Epoch 7, batch 7950, loss[loss=0.145, simple_loss=0.2301, pruned_loss=0.02998, over 4708.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2174, pruned_loss=0.03709, over 972475.11 frames.], batch size: 15, lr: 2.98e-04
+2022-05-05 19:28:52,649 INFO [train.py:715] (3/8) Epoch 7, batch 8000, loss[loss=0.1591, simple_loss=0.2353, pruned_loss=0.04142, over 4983.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2176, pruned_loss=0.0373, over 972144.38 frames.], batch size: 14, lr: 2.98e-04
+2022-05-05 19:29:30,737 INFO [train.py:715] (3/8) Epoch 7, batch 8050, loss[loss=0.1428, simple_loss=0.223, pruned_loss=0.03132, over 4985.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2172, pruned_loss=0.03712, over 971846.45 frames.], batch size: 25, lr: 2.98e-04
+2022-05-05 19:30:09,297 INFO [train.py:715] (3/8) Epoch 7, batch 8100, loss[loss=0.1524, simple_loss=0.2262, pruned_loss=0.03935, over 4965.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.0378, over 972920.24 frames.], batch size: 24, lr: 2.98e-04
+2022-05-05 19:30:48,380 INFO [train.py:715] (3/8) Epoch 7, batch 8150, loss[loss=0.161, simple_loss=0.2334, pruned_loss=0.04425, over 4866.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03755, over 972941.78 frames.], batch size: 20, lr: 2.98e-04
+2022-05-05 19:31:26,683 INFO [train.py:715] (3/8) Epoch 7, batch 8200, loss[loss=0.1465, simple_loss=0.223, pruned_loss=0.03503, over 4786.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.0378, over 973195.51 frames.], batch size: 18, lr: 2.98e-04
+2022-05-05 19:32:05,127 INFO [train.py:715] (3/8) Epoch 7, batch 8250, loss[loss=0.1804, simple_loss=0.24, pruned_loss=0.06036, over 4968.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2184, pruned_loss=0.03768, over 973720.35 frames.], batch size: 35, lr: 2.98e-04
+2022-05-05 19:32:43,781 INFO [train.py:715] (3/8) Epoch 7, batch 8300, loss[loss=0.1222, simple_loss=0.2018, pruned_loss=0.02126, over 4829.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.03739, over 973790.85 frames.], batch size: 26, lr: 2.98e-04
+2022-05-05 19:33:22,691 INFO [train.py:715] (3/8) Epoch 7, batch 8350, loss[loss=0.1489, simple_loss=0.2159, pruned_loss=0.04098, over 4979.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03774, over 973365.18 frames.], batch size: 14, lr: 2.98e-04
+2022-05-05 19:34:00,643 INFO [train.py:715] (3/8) Epoch 7, batch 8400, loss[loss=0.119, simple_loss=0.1919, pruned_loss=0.02307, over 4991.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.03741, over 972869.80 frames.], batch size: 14, lr: 2.98e-04
+2022-05-05 19:34:39,717 INFO [train.py:715] (3/8) Epoch 7, batch 8450, loss[loss=0.1626, simple_loss=0.2486, pruned_loss=0.03827, over 4875.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2191, pruned_loss=0.03752, over 972998.81 frames.], batch size: 22, lr: 2.98e-04
+2022-05-05 19:35:18,877 INFO [train.py:715] (3/8) Epoch 7, batch 8500, loss[loss=0.1445, simple_loss=0.22, pruned_loss=0.03447, over 4932.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2194, pruned_loss=0.03755, over 973101.91 frames.], batch size: 18, lr: 2.98e-04
+2022-05-05 19:35:58,056 INFO [train.py:715] (3/8) Epoch 7, batch 8550, loss[loss=0.1386, simple_loss=0.2086, pruned_loss=0.0343, over 4836.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2197, pruned_loss=0.03808, over 972902.99 frames.], batch size: 15, lr: 2.97e-04
+2022-05-05 19:36:36,295 INFO [train.py:715] (3/8) Epoch 7, batch 8600, loss[loss=0.1285, simple_loss=0.2023, pruned_loss=0.02739, over 4931.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.0374, over 971981.40 frames.], batch size: 18, lr: 2.97e-04
+2022-05-05 19:37:14,959 INFO [train.py:715] (3/8) Epoch 7, batch 8650, loss[loss=0.1333, simple_loss=0.2034, pruned_loss=0.03161, over 4747.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03702, over 972179.05 frames.], batch size: 16, lr: 2.97e-04
+2022-05-05 19:37:54,307 INFO [train.py:715] (3/8) Epoch 7, batch 8700, loss[loss=0.1412, simple_loss=0.2177, pruned_loss=0.0324, over 4898.00 frames.], tot_loss[loss=0.1463, simple_loss=0.218, pruned_loss=0.03727, over 971600.07 frames.], batch size: 17, lr: 2.97e-04
+2022-05-05 19:38:32,517 INFO [train.py:715] (3/8) Epoch 7, batch 8750, loss[loss=0.1267, simple_loss=0.1948, pruned_loss=0.02926, over 4768.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2174, pruned_loss=0.03705, over 972232.74 frames.], batch size: 12, lr: 2.97e-04
+2022-05-05 19:39:11,386 INFO [train.py:715] (3/8) Epoch 7, batch 8800, loss[loss=0.1432, simple_loss=0.2106, pruned_loss=0.03789, over 4819.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2184, pruned_loss=0.03749, over 972316.09 frames.], batch size: 25, lr: 2.97e-04
+2022-05-05 19:39:50,319 INFO [train.py:715] (3/8) Epoch 7, batch 8850, loss[loss=0.1519, simple_loss=0.2279, pruned_loss=0.03794, over 4844.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2195, pruned_loss=0.03807, over 972503.32 frames.], batch size: 34, lr: 2.97e-04
+2022-05-05 19:40:30,009 INFO [train.py:715] (3/8) Epoch 7, batch 8900, loss[loss=0.1385, simple_loss=0.2138, pruned_loss=0.03165, over 4948.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.0382, over 971660.24 frames.], batch size: 39, lr: 2.97e-04
+2022-05-05 19:41:08,238 INFO [train.py:715] (3/8) Epoch 7, batch 8950, loss[loss=0.1405, simple_loss=0.2197, pruned_loss=0.03068, over 4787.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2193, pruned_loss=0.03814, over 972050.95 frames.], batch size: 17, lr: 2.97e-04
+2022-05-05 19:41:46,836 INFO [train.py:715] (3/8) Epoch 7, batch 9000, loss[loss=0.1451, simple_loss=0.2093, pruned_loss=0.04048, over 4845.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2191, pruned_loss=0.03829, over 971954.37 frames.], batch size: 30, lr: 2.97e-04
+2022-05-05 19:41:46,836 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 19:41:56,559 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.1085, simple_loss=0.1932, pruned_loss=0.01192, over 914524.00 frames.
+2022-05-05 19:42:35,336 INFO [train.py:715] (3/8) Epoch 7, batch 9050, loss[loss=0.1213, simple_loss=0.1904, pruned_loss=0.02613, over 4934.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2196, pruned_loss=0.03802, over 971712.87 frames.], batch size: 23, lr: 2.97e-04
+2022-05-05 19:43:15,395 INFO [train.py:715] (3/8) Epoch 7, batch 9100, loss[loss=0.1899, simple_loss=0.2452, pruned_loss=0.06728, over 4948.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03771, over 971196.71 frames.], batch size: 39, lr: 2.97e-04
+2022-05-05 19:43:54,070 INFO [train.py:715] (3/8) Epoch 7, batch 9150, loss[loss=0.1486, simple_loss=0.2315, pruned_loss=0.03289, over 4830.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2185, pruned_loss=0.03799, over 971765.55 frames.], batch size: 26, lr: 2.97e-04
+2022-05-05 19:44:32,871 INFO [train.py:715] (3/8) Epoch 7, batch 9200, loss[loss=0.1245, simple_loss=0.2059, pruned_loss=0.02149, over 4752.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.03786, over 972128.18 frames.], batch size: 19, lr: 2.97e-04
+2022-05-05 19:45:12,207 INFO [train.py:715] (3/8) Epoch 7, batch 9250, loss[loss=0.1199, simple_loss=0.1958, pruned_loss=0.02199, over 4826.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2184, pruned_loss=0.03797, over 973292.82 frames.], batch size: 13, lr: 2.97e-04
+2022-05-05 19:45:51,291 INFO [train.py:715] (3/8) Epoch 7, batch 9300, loss[loss=0.1566, simple_loss=0.2213, pruned_loss=0.04597, over 4854.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.0378, over 973122.41 frames.], batch size: 13, lr: 2.97e-04
+2022-05-05 19:46:30,349 INFO [train.py:715] (3/8) Epoch 7, batch 9350, loss[loss=0.1645, simple_loss=0.2318, pruned_loss=0.04857, over 4808.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2187, pruned_loss=0.03831, over 972891.62 frames.], batch size: 25, lr: 2.97e-04
+2022-05-05 19:47:08,480 INFO [train.py:715] (3/8) Epoch 7, batch 9400, loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02873, over 4876.00 frames.], tot_loss[loss=0.147, simple_loss=0.2182, pruned_loss=0.03796, over 972706.39 frames.], batch size: 22, lr: 2.97e-04
+2022-05-05 19:47:48,271 INFO [train.py:715] (3/8) Epoch 7, batch 9450, loss[loss=0.1151, simple_loss=0.1881, pruned_loss=0.02109, over 4905.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03726, over 972757.27 frames.], batch size: 19, lr: 2.97e-04
+2022-05-05 19:48:27,279 INFO [train.py:715] (3/8) Epoch 7, batch 9500, loss[loss=0.1337, simple_loss=0.2096, pruned_loss=0.02891, over 4850.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2178, pruned_loss=0.03728, over 972864.31 frames.], batch size: 30, lr: 2.97e-04
+2022-05-05 19:49:05,879 INFO [train.py:715] (3/8) Epoch 7, batch 9550, loss[loss=0.1287, simple_loss=0.1979, pruned_loss=0.02972, over 4834.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03726, over 972942.28 frames.], batch size: 13, lr: 2.97e-04
+2022-05-05 19:49:44,840 INFO [train.py:715] (3/8) Epoch 7, batch 9600, loss[loss=0.1729, simple_loss=0.249, pruned_loss=0.04843, over 4700.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2188, pruned_loss=0.03734, over 972891.81 frames.], batch size: 15, lr: 2.97e-04
+2022-05-05 19:50:23,442 INFO [train.py:715] (3/8) Epoch 7, batch 9650, loss[loss=0.1229, simple_loss=0.2026, pruned_loss=0.02164, over 4967.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2188, pruned_loss=0.03756, over 972834.55 frames.], batch size: 14, lr: 2.97e-04
+2022-05-05 19:51:02,959 INFO [train.py:715] (3/8) Epoch 7, batch 9700, loss[loss=0.1437, simple_loss=0.2209, pruned_loss=0.03328, over 4898.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03706, over 972929.61 frames.], batch size: 17, lr: 2.97e-04
+2022-05-05 19:51:41,572 INFO [train.py:715] (3/8) Epoch 7, batch 9750, loss[loss=0.1557, simple_loss=0.2172, pruned_loss=0.04704, over 4765.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2175, pruned_loss=0.0369, over 972963.77 frames.], batch size: 19, lr: 2.97e-04
+2022-05-05 19:52:20,961 INFO [train.py:715] (3/8) Epoch 7, batch 9800, loss[loss=0.1225, simple_loss=0.1978, pruned_loss=0.02355, over 4867.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03717, over 973408.17 frames.], batch size: 16, lr: 2.97e-04
+2022-05-05 19:52:59,043 INFO [train.py:715] (3/8) Epoch 7, batch 9850, loss[loss=0.1351, simple_loss=0.1997, pruned_loss=0.03525, over 4986.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2181, pruned_loss=0.0371, over 973788.48 frames.], batch size: 14, lr: 2.97e-04
+2022-05-05 19:53:37,275 INFO [train.py:715] (3/8) Epoch 7, batch 9900, loss[loss=0.1585, simple_loss=0.2287, pruned_loss=0.04413, over 4689.00 frames.], tot_loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03654, over 972577.64 frames.], batch size: 15, lr: 2.97e-04
+2022-05-05 19:54:16,174 INFO [train.py:715] (3/8) Epoch 7, batch 9950, loss[loss=0.1367, simple_loss=0.2062, pruned_loss=0.03356, over 4981.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03602, over 972588.65 frames.], batch size: 25, lr: 2.97e-04
+2022-05-05 19:54:55,287 INFO [train.py:715] (3/8) Epoch 7, batch 10000, loss[loss=0.1413, simple_loss=0.2117, pruned_loss=0.03543, over 4933.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2161, pruned_loss=0.03644, over 971412.70 frames.], batch size: 35, lr: 2.97e-04
+2022-05-05 19:55:33,943 INFO [train.py:715] (3/8) Epoch 7, batch 10050, loss[loss=0.1669, simple_loss=0.2348, pruned_loss=0.04951, over 4907.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2163, pruned_loss=0.03635, over 971743.03 frames.], batch size: 17, lr: 2.97e-04
+2022-05-05 19:56:12,506 INFO [train.py:715] (3/8) Epoch 7, batch 10100, loss[loss=0.1626, simple_loss=0.2273, pruned_loss=0.04896, over 4910.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03617, over 971940.44 frames.], batch size: 17, lr: 2.97e-04
+2022-05-05 19:56:51,797 INFO [train.py:715] (3/8) Epoch 7, batch 10150, loss[loss=0.1555, simple_loss=0.223, pruned_loss=0.04407, over 4972.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2162, pruned_loss=0.0365, over 971574.94 frames.], batch size: 28, lr: 2.97e-04
+2022-05-05 19:57:30,413 INFO [train.py:715] (3/8) Epoch 7, batch 10200, loss[loss=0.1761, simple_loss=0.2357, pruned_loss=0.05825, over 4969.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2165, pruned_loss=0.03689, over 971410.49 frames.], batch size: 14, lr: 2.97e-04
+2022-05-05 19:58:09,060 INFO [train.py:715] (3/8) Epoch 7, batch 10250, loss[loss=0.1606, simple_loss=0.228, pruned_loss=0.04662, over 4872.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2169, pruned_loss=0.03693, over 971462.95 frames.], batch size: 20, lr: 2.96e-04
+2022-05-05 19:58:48,252 INFO [train.py:715] (3/8) Epoch 7, batch 10300, loss[loss=0.1353, simple_loss=0.2144, pruned_loss=0.02806, over 4868.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2179, pruned_loss=0.03732, over 970856.66 frames.], batch size: 22, lr: 2.96e-04
+2022-05-05 19:59:26,900 INFO [train.py:715] (3/8) Epoch 7, batch 10350, loss[loss=0.1655, simple_loss=0.2344, pruned_loss=0.04835, over 4914.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2178, pruned_loss=0.03752, over 971013.41 frames.], batch size: 18, lr: 2.96e-04
+2022-05-05 20:00:05,911 INFO [train.py:715] (3/8) Epoch 7, batch 10400, loss[loss=0.1332, simple_loss=0.2091, pruned_loss=0.02867, over 4820.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2182, pruned_loss=0.03771, over 970936.39 frames.], batch size: 25, lr: 2.96e-04
+2022-05-05 20:00:44,693 INFO [train.py:715] (3/8) Epoch 7, batch 10450, loss[loss=0.1135, simple_loss=0.1779, pruned_loss=0.02451, over 4819.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2177, pruned_loss=0.0374, over 971878.30 frames.], batch size: 13, lr: 2.96e-04
+2022-05-05 20:01:24,296 INFO [train.py:715] (3/8) Epoch 7, batch 10500, loss[loss=0.1268, simple_loss=0.1942, pruned_loss=0.02972, over 4714.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2188, pruned_loss=0.03734, over 972457.80 frames.], batch size: 15, lr: 2.96e-04
+2022-05-05 20:02:03,022 INFO [train.py:715] (3/8) Epoch 7, batch 10550, loss[loss=0.1624, simple_loss=0.2413, pruned_loss=0.04169, over 4820.00 frames.], tot_loss[loss=0.1459, simple_loss=0.218, pruned_loss=0.03688, over 972410.73 frames.], batch size: 26, lr: 2.96e-04
+2022-05-05 20:02:41,164 INFO [train.py:715] (3/8) Epoch 7, batch 10600, loss[loss=0.1583, simple_loss=0.2322, pruned_loss=0.04221, over 4972.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2177, pruned_loss=0.0365, over 972294.98 frames.], batch size: 15, lr: 2.96e-04
+2022-05-05 20:03:20,356 INFO [train.py:715] (3/8) Epoch 7, batch 10650, loss[loss=0.1413, simple_loss=0.2077, pruned_loss=0.03751, over 4931.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.03642, over 971932.70 frames.], batch size: 18, lr: 2.96e-04
+2022-05-05 20:03:59,394 INFO [train.py:715] (3/8) Epoch 7, batch 10700, loss[loss=0.1771, simple_loss=0.2405, pruned_loss=0.05683, over 4777.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03702, over 971742.94 frames.], batch size: 14, lr: 2.96e-04
+2022-05-05 20:04:38,881 INFO [train.py:715] (3/8) Epoch 7, batch 10750, loss[loss=0.1494, simple_loss=0.223, pruned_loss=0.03787, over 4838.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2184, pruned_loss=0.03751, over 972308.18 frames.], batch size: 15, lr: 2.96e-04
+2022-05-05 20:05:17,666 INFO [train.py:715] (3/8) Epoch 7, batch 10800, loss[loss=0.1768, simple_loss=0.2446, pruned_loss=0.0545, over 4747.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2174, pruned_loss=0.03701, over 971703.37 frames.], batch size: 16, lr: 2.96e-04
+2022-05-05 20:05:57,423 INFO [train.py:715] (3/8) Epoch 7, batch 10850, loss[loss=0.1519, simple_loss=0.2255, pruned_loss=0.0391, over 4815.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.0368, over 971914.87 frames.], batch size: 25, lr: 2.96e-04
+2022-05-05 20:06:35,666 INFO [train.py:715] (3/8) Epoch 7, batch 10900, loss[loss=0.1681, simple_loss=0.2252, pruned_loss=0.05548, over 4812.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.03694, over 972692.46 frames.], batch size: 15, lr: 2.96e-04
+2022-05-05 20:07:14,756 INFO [train.py:715] (3/8) Epoch 7, batch 10950, loss[loss=0.1713, simple_loss=0.2398, pruned_loss=0.05144, over 4953.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03705, over 972392.18 frames.], batch size: 15, lr: 2.96e-04
+2022-05-05 20:07:53,906 INFO [train.py:715] (3/8) Epoch 7, batch 11000, loss[loss=0.1359, simple_loss=0.2147, pruned_loss=0.02849, over 4983.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2179, pruned_loss=0.03662, over 972594.58 frames.], batch size: 15, lr: 2.96e-04
+2022-05-05 20:08:32,746 INFO [train.py:715] (3/8) Epoch 7, batch 11050, loss[loss=0.1323, simple_loss=0.203, pruned_loss=0.0308, over 4932.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2172, pruned_loss=0.03618, over 972036.61 frames.], batch size: 21, lr: 2.96e-04
+2022-05-05 20:09:11,470 INFO [train.py:715] (3/8) Epoch 7, batch 11100, loss[loss=0.1415, simple_loss=0.2108, pruned_loss=0.03606, over 4796.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2165, pruned_loss=0.03642, over 971726.24 frames.], batch size: 14, lr: 2.96e-04
+2022-05-05 20:09:50,082 INFO [train.py:715] (3/8) Epoch 7, batch 11150, loss[loss=0.1678, simple_loss=0.2374, pruned_loss=0.04913, over 4797.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2173, pruned_loss=0.03659, over 971273.54 frames.], batch size: 18, lr: 2.96e-04
+2022-05-05 20:10:29,709 INFO [train.py:715] (3/8) Epoch 7, batch 11200, loss[loss=0.1085, simple_loss=0.1765, pruned_loss=0.02021, over 4739.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.03685, over 971759.21 frames.], batch size: 12, lr: 2.96e-04
+2022-05-05 20:11:08,078 INFO [train.py:715] (3/8) Epoch 7, batch 11250, loss[loss=0.1344, simple_loss=0.2072, pruned_loss=0.0308, over 4789.00 frames.], tot_loss[loss=0.146, simple_loss=0.2178, pruned_loss=0.03708, over 971830.48 frames.], batch size: 17, lr: 2.96e-04
+2022-05-05 20:11:46,240 INFO [train.py:715] (3/8) Epoch 7, batch 11300, loss[loss=0.1675, simple_loss=0.2413, pruned_loss=0.04683, over 4855.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03691, over 971761.19 frames.], batch size: 32, lr: 2.96e-04
+2022-05-05 20:12:25,980 INFO [train.py:715] (3/8) Epoch 7, batch 11350, loss[loss=0.1267, simple_loss=0.1969, pruned_loss=0.02818, over 4864.00 frames.], tot_loss[loss=0.1455, simple_loss=0.217, pruned_loss=0.03698, over 972613.56 frames.], batch size: 32, lr: 2.96e-04
+2022-05-05 20:13:04,523 INFO [train.py:715] (3/8) Epoch 7, batch 11400, loss[loss=0.1449, simple_loss=0.2089, pruned_loss=0.04044, over 4781.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2164, pruned_loss=0.03666, over 972578.11 frames.], batch size: 14, lr: 2.96e-04
+2022-05-05 20:13:43,553 INFO [train.py:715] (3/8) Epoch 7, batch 11450, loss[loss=0.1277, simple_loss=0.2004, pruned_loss=0.02756, over 4951.00 frames.], tot_loss[loss=0.1446, simple_loss=0.216, pruned_loss=0.03657, over 973006.77 frames.], batch size: 29, lr: 2.96e-04
+2022-05-05 20:14:22,146 INFO [train.py:715] (3/8) Epoch 7, batch 11500, loss[loss=0.1303, simple_loss=0.2079, pruned_loss=0.02632, over 4774.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2162, pruned_loss=0.03634, over 973806.58 frames.], batch size: 17, lr: 2.96e-04
+2022-05-05 20:15:01,730 INFO [train.py:715] (3/8) Epoch 7, batch 11550, loss[loss=0.1282, simple_loss=0.2078, pruned_loss=0.02435, over 4828.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03603, over 973928.78 frames.], batch size: 26, lr: 2.96e-04
+2022-05-05 20:15:39,999 INFO [train.py:715] (3/8) Epoch 7, batch 11600, loss[loss=0.1333, simple_loss=0.2082, pruned_loss=0.02927, over 4693.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03552, over 973007.32 frames.], batch size: 15, lr: 2.96e-04
+2022-05-05 20:16:18,808 INFO [train.py:715] (3/8) Epoch 7, batch 11650, loss[loss=0.1335, simple_loss=0.2107, pruned_loss=0.02818, over 4772.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.03594, over 973168.81 frames.], batch size: 17, lr: 2.96e-04
+2022-05-05 20:16:58,204 INFO [train.py:715] (3/8) Epoch 7, batch 11700, loss[loss=0.138, simple_loss=0.2067, pruned_loss=0.03469, over 4978.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.0363, over 973061.28 frames.], batch size: 14, lr: 2.96e-04
+2022-05-05 20:17:36,280 INFO [train.py:715] (3/8) Epoch 7, batch 11750, loss[loss=0.1741, simple_loss=0.2463, pruned_loss=0.05095, over 4750.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2168, pruned_loss=0.03674, over 973058.78 frames.], batch size: 16, lr: 2.96e-04
+2022-05-05 20:18:15,077 INFO [train.py:715] (3/8) Epoch 7, batch 11800, loss[loss=0.1415, simple_loss=0.2071, pruned_loss=0.03798, over 4802.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2165, pruned_loss=0.03671, over 972737.46 frames.], batch size: 13, lr: 2.96e-04
+2022-05-05 20:18:54,266 INFO [train.py:715] (3/8) Epoch 7, batch 11850, loss[loss=0.1466, simple_loss=0.209, pruned_loss=0.04213, over 4701.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2164, pruned_loss=0.03663, over 972897.43 frames.], batch size: 15, lr: 2.96e-04
+2022-05-05 20:19:32,625 INFO [train.py:715] (3/8) Epoch 7, batch 11900, loss[loss=0.1327, simple_loss=0.2055, pruned_loss=0.02995, over 4832.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2165, pruned_loss=0.03666, over 972613.90 frames.], batch size: 13, lr: 2.96e-04
+2022-05-05 20:20:11,922 INFO [train.py:715] (3/8) Epoch 7, batch 11950, loss[loss=0.1336, simple_loss=0.199, pruned_loss=0.03414, over 4805.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2163, pruned_loss=0.03655, over 972784.54 frames.], batch size: 14, lr: 2.96e-04
+2022-05-05 20:20:50,622 INFO [train.py:715] (3/8) Epoch 7, batch 12000, loss[loss=0.1556, simple_loss=0.2127, pruned_loss=0.04928, over 4745.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2162, pruned_loss=0.03658, over 973156.87 frames.], batch size: 19, lr: 2.95e-04
+2022-05-05 20:20:50,622 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 20:21:00,227 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.108, simple_loss=0.193, pruned_loss=0.01154, over 914524.00 frames.
+2022-05-05 20:21:38,892 INFO [train.py:715] (3/8) Epoch 7, batch 12050, loss[loss=0.1469, simple_loss=0.2148, pruned_loss=0.03951, over 4688.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2169, pruned_loss=0.03674, over 972669.87 frames.], batch size: 15, lr: 2.95e-04
+2022-05-05 20:22:18,262 INFO [train.py:715] (3/8) Epoch 7, batch 12100, loss[loss=0.1604, simple_loss=0.2278, pruned_loss=0.04652, over 4917.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2169, pruned_loss=0.03644, over 972912.40 frames.], batch size: 17, lr: 2.95e-04
+2022-05-05 20:22:56,854 INFO [train.py:715] (3/8) Epoch 7, batch 12150, loss[loss=0.1288, simple_loss=0.197, pruned_loss=0.03027, over 4882.00 frames.], tot_loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03723, over 972974.58 frames.], batch size: 16, lr: 2.95e-04
+2022-05-05 20:23:35,618 INFO [train.py:715] (3/8) Epoch 7, batch 12200, loss[loss=0.1228, simple_loss=0.1921, pruned_loss=0.02677, over 4951.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2178, pruned_loss=0.03727, over 972220.00 frames.], batch size: 21, lr: 2.95e-04
+2022-05-05 20:24:14,745 INFO [train.py:715] (3/8) Epoch 7, batch 12250, loss[loss=0.1333, simple_loss=0.2046, pruned_loss=0.03105, over 4834.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03682, over 972677.40 frames.], batch size: 32, lr: 2.95e-04
+2022-05-05 20:24:53,359 INFO [train.py:715] (3/8) Epoch 7, batch 12300, loss[loss=0.1624, simple_loss=0.2339, pruned_loss=0.04544, over 4667.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2174, pruned_loss=0.03654, over 972520.60 frames.], batch size: 13, lr: 2.95e-04
+2022-05-05 20:25:35,088 INFO [train.py:715] (3/8) Epoch 7, batch 12350, loss[loss=0.1358, simple_loss=0.2102, pruned_loss=0.03071, over 4777.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2182, pruned_loss=0.03695, over 972379.50 frames.], batch size: 18, lr: 2.95e-04
+2022-05-05 20:26:13,787 INFO [train.py:715] (3/8) Epoch 7, batch 12400, loss[loss=0.1256, simple_loss=0.204, pruned_loss=0.02357, over 4688.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2188, pruned_loss=0.0372, over 971454.24 frames.], batch size: 15, lr: 2.95e-04
+2022-05-05 20:26:53,003 INFO [train.py:715] (3/8) Epoch 7, batch 12450, loss[loss=0.1302, simple_loss=0.2042, pruned_loss=0.02811, over 4962.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2179, pruned_loss=0.03685, over 972228.52 frames.], batch size: 39, lr: 2.95e-04
+2022-05-05 20:27:31,402 INFO [train.py:715] (3/8) Epoch 7, batch 12500, loss[loss=0.1352, simple_loss=0.2085, pruned_loss=0.03095, over 4794.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.03694, over 972312.79 frames.], batch size: 24, lr: 2.95e-04
+2022-05-05 20:28:10,097 INFO [train.py:715] (3/8) Epoch 7, batch 12550, loss[loss=0.1389, simple_loss=0.2066, pruned_loss=0.03558, over 4873.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.0371, over 972163.44 frames.], batch size: 22, lr: 2.95e-04
+2022-05-05 20:28:49,195 INFO [train.py:715] (3/8) Epoch 7, batch 12600, loss[loss=0.1363, simple_loss=0.2052, pruned_loss=0.03372, over 4864.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03734, over 972206.07 frames.], batch size: 20, lr: 2.95e-04
+2022-05-05 20:29:27,376 INFO [train.py:715] (3/8) Epoch 7, batch 12650, loss[loss=0.1476, simple_loss=0.22, pruned_loss=0.03762, over 4977.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2183, pruned_loss=0.0375, over 972476.29 frames.], batch size: 24, lr: 2.95e-04
+2022-05-05 20:30:06,578 INFO [train.py:715] (3/8) Epoch 7, batch 12700, loss[loss=0.1478, simple_loss=0.2219, pruned_loss=0.03688, over 4973.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2189, pruned_loss=0.03782, over 972749.99 frames.], batch size: 24, lr: 2.95e-04
+2022-05-05 20:30:44,740 INFO [train.py:715] (3/8) Epoch 7, batch 12750, loss[loss=0.1674, simple_loss=0.2424, pruned_loss=0.04623, over 4802.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03767, over 971919.59 frames.], batch size: 24, lr: 2.95e-04
+2022-05-05 20:31:23,967 INFO [train.py:715] (3/8) Epoch 7, batch 12800, loss[loss=0.145, simple_loss=0.2116, pruned_loss=0.03924, over 4777.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2182, pruned_loss=0.0376, over 971553.00 frames.], batch size: 18, lr: 2.95e-04
+2022-05-05 20:32:02,916 INFO [train.py:715] (3/8) Epoch 7, batch 12850, loss[loss=0.1478, simple_loss=0.2157, pruned_loss=0.03993, over 4953.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2178, pruned_loss=0.03786, over 971383.64 frames.], batch size: 21, lr: 2.95e-04
+2022-05-05 20:32:41,512 INFO [train.py:715] (3/8) Epoch 7, batch 12900, loss[loss=0.1607, simple_loss=0.2339, pruned_loss=0.04372, over 4896.00 frames.], tot_loss[loss=0.147, simple_loss=0.218, pruned_loss=0.03803, over 971600.18 frames.], batch size: 22, lr: 2.95e-04
+2022-05-05 20:33:20,984 INFO [train.py:715] (3/8) Epoch 7, batch 12950, loss[loss=0.1552, simple_loss=0.223, pruned_loss=0.04369, over 4871.00 frames.], tot_loss[loss=0.1468, simple_loss=0.218, pruned_loss=0.03783, over 971820.34 frames.], batch size: 20, lr: 2.95e-04
+2022-05-05 20:33:59,929 INFO [train.py:715] (3/8) Epoch 7, batch 13000, loss[loss=0.1574, simple_loss=0.2308, pruned_loss=0.04202, over 4916.00 frames.], tot_loss[loss=0.1467, simple_loss=0.218, pruned_loss=0.0377, over 971894.12 frames.], batch size: 23, lr: 2.95e-04
+2022-05-05 20:34:38,878 INFO [train.py:715] (3/8) Epoch 7, batch 13050, loss[loss=0.1215, simple_loss=0.1973, pruned_loss=0.02288, over 4777.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2179, pruned_loss=0.03749, over 971861.40 frames.], batch size: 12, lr: 2.95e-04
+2022-05-05 20:35:17,657 INFO [train.py:715] (3/8) Epoch 7, batch 13100, loss[loss=0.1292, simple_loss=0.2017, pruned_loss=0.02833, over 4934.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2177, pruned_loss=0.03738, over 971562.43 frames.], batch size: 29, lr: 2.95e-04
+2022-05-05 20:35:57,326 INFO [train.py:715] (3/8) Epoch 7, batch 13150, loss[loss=0.1296, simple_loss=0.2058, pruned_loss=0.02674, over 4814.00 frames.], tot_loss[loss=0.147, simple_loss=0.2188, pruned_loss=0.03763, over 971651.76 frames.], batch size: 12, lr: 2.95e-04
+2022-05-05 20:36:35,852 INFO [train.py:715] (3/8) Epoch 7, batch 13200, loss[loss=0.154, simple_loss=0.2294, pruned_loss=0.03931, over 4730.00 frames.], tot_loss[loss=0.1475, simple_loss=0.219, pruned_loss=0.03802, over 971980.74 frames.], batch size: 16, lr: 2.95e-04
+2022-05-05 20:37:15,491 INFO [train.py:715] (3/8) Epoch 7, batch 13250, loss[loss=0.1446, simple_loss=0.2081, pruned_loss=0.04059, over 4887.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03888, over 972715.43 frames.], batch size: 16, lr: 2.95e-04
+2022-05-05 20:37:54,876 INFO [train.py:715] (3/8) Epoch 7, batch 13300, loss[loss=0.1282, simple_loss=0.2128, pruned_loss=0.02178, over 4829.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.03856, over 972431.90 frames.], batch size: 15, lr: 2.95e-04
+2022-05-05 20:38:33,805 INFO [train.py:715] (3/8) Epoch 7, batch 13350, loss[loss=0.1283, simple_loss=0.205, pruned_loss=0.02583, over 4643.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2201, pruned_loss=0.03832, over 972894.96 frames.], batch size: 13, lr: 2.95e-04
+2022-05-05 20:39:12,812 INFO [train.py:715] (3/8) Epoch 7, batch 13400, loss[loss=0.1293, simple_loss=0.2028, pruned_loss=0.02788, over 4968.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2191, pruned_loss=0.03807, over 971810.82 frames.], batch size: 35, lr: 2.95e-04
+2022-05-05 20:39:51,470 INFO [train.py:715] (3/8) Epoch 7, batch 13450, loss[loss=0.1273, simple_loss=0.1937, pruned_loss=0.03039, over 4836.00 frames.], tot_loss[loss=0.1475, simple_loss=0.219, pruned_loss=0.03803, over 972252.18 frames.], batch size: 12, lr: 2.95e-04
+2022-05-05 20:40:30,903 INFO [train.py:715] (3/8) Epoch 7, batch 13500, loss[loss=0.1551, simple_loss=0.2364, pruned_loss=0.03691, over 4794.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03776, over 972072.01 frames.], batch size: 18, lr: 2.95e-04
+2022-05-05 20:41:09,548 INFO [train.py:715] (3/8) Epoch 7, batch 13550, loss[loss=0.1151, simple_loss=0.1868, pruned_loss=0.02169, over 4794.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03717, over 972017.89 frames.], batch size: 14, lr: 2.95e-04
+2022-05-05 20:41:48,025 INFO [train.py:715] (3/8) Epoch 7, batch 13600, loss[loss=0.1367, simple_loss=0.1988, pruned_loss=0.0373, over 4843.00 frames.], tot_loss[loss=0.146, simple_loss=0.2177, pruned_loss=0.03713, over 971928.63 frames.], batch size: 15, lr: 2.95e-04
+2022-05-05 20:42:26,946 INFO [train.py:715] (3/8) Epoch 7, batch 13650, loss[loss=0.1378, simple_loss=0.2139, pruned_loss=0.03089, over 4801.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2164, pruned_loss=0.0367, over 971867.14 frames.], batch size: 21, lr: 2.95e-04
+2022-05-05 20:43:05,965 INFO [train.py:715] (3/8) Epoch 7, batch 13700, loss[loss=0.1423, simple_loss=0.2124, pruned_loss=0.0361, over 4990.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2164, pruned_loss=0.03696, over 972368.63 frames.], batch size: 28, lr: 2.95e-04
+2022-05-05 20:43:44,963 INFO [train.py:715] (3/8) Epoch 7, batch 13750, loss[loss=0.1497, simple_loss=0.2072, pruned_loss=0.04606, over 4836.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2176, pruned_loss=0.0377, over 972795.40 frames.], batch size: 30, lr: 2.94e-04
+2022-05-05 20:44:23,923 INFO [train.py:715] (3/8) Epoch 7, batch 13800, loss[loss=0.1358, simple_loss=0.213, pruned_loss=0.02931, over 4975.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2175, pruned_loss=0.03791, over 972672.57 frames.], batch size: 25, lr: 2.94e-04
+2022-05-05 20:45:03,235 INFO [train.py:715] (3/8) Epoch 7, batch 13850, loss[loss=0.1029, simple_loss=0.1762, pruned_loss=0.01479, over 4982.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2172, pruned_loss=0.03752, over 972635.18 frames.], batch size: 14, lr: 2.94e-04
+2022-05-05 20:45:41,501 INFO [train.py:715] (3/8) Epoch 7, batch 13900, loss[loss=0.1286, simple_loss=0.2019, pruned_loss=0.02761, over 4811.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2168, pruned_loss=0.03711, over 972952.59 frames.], batch size: 27, lr: 2.94e-04
+2022-05-05 20:46:20,518 INFO [train.py:715] (3/8) Epoch 7, batch 13950, loss[loss=0.1582, simple_loss=0.2296, pruned_loss=0.0434, over 4835.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.0374, over 972436.26 frames.], batch size: 15, lr: 2.94e-04
+2022-05-05 20:46:59,562 INFO [train.py:715] (3/8) Epoch 7, batch 14000, loss[loss=0.1772, simple_loss=0.2358, pruned_loss=0.05927, over 4882.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2194, pruned_loss=0.03789, over 972089.76 frames.], batch size: 32, lr: 2.94e-04
+2022-05-05 20:47:38,924 INFO [train.py:715] (3/8) Epoch 7, batch 14050, loss[loss=0.1565, simple_loss=0.2166, pruned_loss=0.04821, over 4961.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2193, pruned_loss=0.03781, over 972216.40 frames.], batch size: 15, lr: 2.94e-04
+2022-05-05 20:48:18,051 INFO [train.py:715] (3/8) Epoch 7, batch 14100, loss[loss=0.1413, simple_loss=0.2134, pruned_loss=0.0346, over 4809.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03755, over 972395.79 frames.], batch size: 27, lr: 2.94e-04
+2022-05-05 20:48:56,864 INFO [train.py:715] (3/8) Epoch 7, batch 14150, loss[loss=0.1249, simple_loss=0.1995, pruned_loss=0.02517, over 4915.00 frames.], tot_loss[loss=0.148, simple_loss=0.2196, pruned_loss=0.03824, over 972540.89 frames.], batch size: 23, lr: 2.94e-04
+2022-05-05 20:49:36,152 INFO [train.py:715] (3/8) Epoch 7, batch 14200, loss[loss=0.136, simple_loss=0.2061, pruned_loss=0.03296, over 4966.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2187, pruned_loss=0.03781, over 972775.67 frames.], batch size: 25, lr: 2.94e-04
+2022-05-05 20:50:14,407 INFO [train.py:715] (3/8) Epoch 7, batch 14250, loss[loss=0.1459, simple_loss=0.2296, pruned_loss=0.03106, over 4915.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.03864, over 971871.63 frames.], batch size: 18, lr: 2.94e-04
+2022-05-05 20:50:53,729 INFO [train.py:715] (3/8) Epoch 7, batch 14300, loss[loss=0.1428, simple_loss=0.2204, pruned_loss=0.03257, over 4795.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03783, over 971739.48 frames.], batch size: 24, lr: 2.94e-04
+2022-05-05 20:51:33,008 INFO [train.py:715] (3/8) Epoch 7, batch 14350, loss[loss=0.1473, simple_loss=0.2055, pruned_loss=0.04453, over 4869.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03785, over 971842.84 frames.], batch size: 32, lr: 2.94e-04
+2022-05-05 20:52:12,027 INFO [train.py:715] (3/8) Epoch 7, batch 14400, loss[loss=0.1552, simple_loss=0.2209, pruned_loss=0.04472, over 4743.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2187, pruned_loss=0.03739, over 972297.54 frames.], batch size: 16, lr: 2.94e-04
+2022-05-05 20:52:50,729 INFO [train.py:715] (3/8) Epoch 7, batch 14450, loss[loss=0.1519, simple_loss=0.2192, pruned_loss=0.04233, over 4894.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2191, pruned_loss=0.03769, over 972448.00 frames.], batch size: 32, lr: 2.94e-04
+2022-05-05 20:53:29,522 INFO [train.py:715] (3/8) Epoch 7, batch 14500, loss[loss=0.13, simple_loss=0.194, pruned_loss=0.03296, over 4946.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2193, pruned_loss=0.03793, over 972657.10 frames.], batch size: 29, lr: 2.94e-04
+2022-05-05 20:54:09,108 INFO [train.py:715] (3/8) Epoch 7, batch 14550, loss[loss=0.1319, simple_loss=0.1984, pruned_loss=0.03268, over 4871.00 frames.], tot_loss[loss=0.1475, simple_loss=0.219, pruned_loss=0.03794, over 972656.03 frames.], batch size: 32, lr: 2.94e-04
+2022-05-05 20:54:47,913 INFO [train.py:715] (3/8) Epoch 7, batch 14600, loss[loss=0.1354, simple_loss=0.2118, pruned_loss=0.02949, over 4926.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2175, pruned_loss=0.03731, over 973258.40 frames.], batch size: 29, lr: 2.94e-04
+2022-05-05 20:55:26,853 INFO [train.py:715] (3/8) Epoch 7, batch 14650, loss[loss=0.1343, simple_loss=0.2071, pruned_loss=0.03073, over 4787.00 frames.], tot_loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03723, over 973198.75 frames.], batch size: 14, lr: 2.94e-04
+2022-05-05 20:56:05,809 INFO [train.py:715] (3/8) Epoch 7, batch 14700, loss[loss=0.178, simple_loss=0.2532, pruned_loss=0.05137, over 4941.00 frames.], tot_loss[loss=0.146, simple_loss=0.2174, pruned_loss=0.03729, over 973221.08 frames.], batch size: 23, lr: 2.94e-04
+2022-05-05 20:56:44,941 INFO [train.py:715] (3/8) Epoch 7, batch 14750, loss[loss=0.1543, simple_loss=0.2237, pruned_loss=0.04251, over 4794.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2172, pruned_loss=0.03715, over 973116.88 frames.], batch size: 18, lr: 2.94e-04
+2022-05-05 20:57:23,494 INFO [train.py:715] (3/8) Epoch 7, batch 14800, loss[loss=0.1207, simple_loss=0.1957, pruned_loss=0.0228, over 4986.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2169, pruned_loss=0.03675, over 972968.16 frames.], batch size: 25, lr: 2.94e-04
+2022-05-05 20:58:03,007 INFO [train.py:715] (3/8) Epoch 7, batch 14850, loss[loss=0.1718, simple_loss=0.2362, pruned_loss=0.05365, over 4854.00 frames.], tot_loss[loss=0.1452, simple_loss=0.217, pruned_loss=0.03673, over 972829.66 frames.], batch size: 32, lr: 2.94e-04
+2022-05-05 20:58:41,953 INFO [train.py:715] (3/8) Epoch 7, batch 14900, loss[loss=0.1364, simple_loss=0.2125, pruned_loss=0.03022, over 4854.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2162, pruned_loss=0.03659, over 973715.95 frames.], batch size: 20, lr: 2.94e-04
+2022-05-05 20:59:20,319 INFO [train.py:715] (3/8) Epoch 7, batch 14950, loss[loss=0.1816, simple_loss=0.2393, pruned_loss=0.06202, over 4903.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2164, pruned_loss=0.03683, over 973236.66 frames.], batch size: 17, lr: 2.94e-04
+2022-05-05 20:59:59,927 INFO [train.py:715] (3/8) Epoch 7, batch 15000, loss[loss=0.1456, simple_loss=0.2175, pruned_loss=0.03684, over 4858.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2173, pruned_loss=0.03728, over 973142.24 frames.], batch size: 20, lr: 2.94e-04
+2022-05-05 20:59:59,928 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 21:00:14,353 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.1083, simple_loss=0.1931, pruned_loss=0.01175, over 914524.00 frames.
+2022-05-05 21:00:53,497 INFO [train.py:715] (3/8) Epoch 7, batch 15050, loss[loss=0.1499, simple_loss=0.228, pruned_loss=0.03594, over 4940.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03722, over 972923.45 frames.], batch size: 29, lr: 2.94e-04
+2022-05-05 21:01:32,728 INFO [train.py:715] (3/8) Epoch 7, batch 15100, loss[loss=0.143, simple_loss=0.2045, pruned_loss=0.04072, over 4957.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03731, over 971969.92 frames.], batch size: 21, lr: 2.94e-04
+2022-05-05 21:02:11,975 INFO [train.py:715] (3/8) Epoch 7, batch 15150, loss[loss=0.1363, simple_loss=0.206, pruned_loss=0.03327, over 4858.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2187, pruned_loss=0.03743, over 972474.83 frames.], batch size: 20, lr: 2.94e-04
+2022-05-05 21:02:50,723 INFO [train.py:715] (3/8) Epoch 7, batch 15200, loss[loss=0.1538, simple_loss=0.2223, pruned_loss=0.04268, over 4924.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2186, pruned_loss=0.03761, over 972965.45 frames.], batch size: 29, lr: 2.94e-04
+2022-05-05 21:03:30,198 INFO [train.py:715] (3/8) Epoch 7, batch 15250, loss[loss=0.1326, simple_loss=0.2154, pruned_loss=0.02492, over 4926.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2186, pruned_loss=0.03745, over 973642.65 frames.], batch size: 29, lr: 2.94e-04
+2022-05-05 21:04:09,390 INFO [train.py:715] (3/8) Epoch 7, batch 15300, loss[loss=0.1329, simple_loss=0.1997, pruned_loss=0.03306, over 4889.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03771, over 973384.10 frames.], batch size: 16, lr: 2.94e-04
+2022-05-05 21:04:48,395 INFO [train.py:715] (3/8) Epoch 7, batch 15350, loss[loss=0.1853, simple_loss=0.2605, pruned_loss=0.05505, over 4923.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2192, pruned_loss=0.03807, over 973099.42 frames.], batch size: 23, lr: 2.94e-04
+2022-05-05 21:05:27,509 INFO [train.py:715] (3/8) Epoch 7, batch 15400, loss[loss=0.1323, simple_loss=0.2076, pruned_loss=0.02849, over 4784.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2197, pruned_loss=0.0381, over 973012.70 frames.], batch size: 17, lr: 2.94e-04
+2022-05-05 21:06:06,000 INFO [train.py:715] (3/8) Epoch 7, batch 15450, loss[loss=0.1643, simple_loss=0.2482, pruned_loss=0.04024, over 4895.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2193, pruned_loss=0.03783, over 973652.97 frames.], batch size: 17, lr: 2.94e-04
+2022-05-05 21:06:45,045 INFO [train.py:715] (3/8) Epoch 7, batch 15500, loss[loss=0.1662, simple_loss=0.2385, pruned_loss=0.04694, over 4952.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2195, pruned_loss=0.03786, over 973365.50 frames.], batch size: 21, lr: 2.93e-04
+2022-05-05 21:07:23,164 INFO [train.py:715] (3/8) Epoch 7, batch 15550, loss[loss=0.1683, simple_loss=0.2346, pruned_loss=0.05104, over 4891.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2196, pruned_loss=0.03764, over 972689.11 frames.], batch size: 22, lr: 2.93e-04
+2022-05-05 21:08:02,570 INFO [train.py:715] (3/8) Epoch 7, batch 15600, loss[loss=0.1458, simple_loss=0.2106, pruned_loss=0.04044, over 4796.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2197, pruned_loss=0.03804, over 972145.41 frames.], batch size: 13, lr: 2.93e-04
+2022-05-05 21:08:42,086 INFO [train.py:715] (3/8) Epoch 7, batch 15650, loss[loss=0.1296, simple_loss=0.198, pruned_loss=0.03061, over 4776.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2189, pruned_loss=0.0375, over 972403.82 frames.], batch size: 17, lr: 2.93e-04
+2022-05-05 21:09:20,365 INFO [train.py:715] (3/8) Epoch 7, batch 15700, loss[loss=0.1748, simple_loss=0.2506, pruned_loss=0.04954, over 4891.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03756, over 972723.92 frames.], batch size: 18, lr: 2.93e-04
+2022-05-05 21:09:59,359 INFO [train.py:715] (3/8) Epoch 7, batch 15750, loss[loss=0.1299, simple_loss=0.194, pruned_loss=0.03288, over 4705.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2194, pruned_loss=0.03781, over 972464.83 frames.], batch size: 15, lr: 2.93e-04
+2022-05-05 21:10:39,021 INFO [train.py:715] (3/8) Epoch 7, batch 15800, loss[loss=0.1284, simple_loss=0.2071, pruned_loss=0.02479, over 4935.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2189, pruned_loss=0.03734, over 972849.79 frames.], batch size: 29, lr: 2.93e-04
+2022-05-05 21:11:18,131 INFO [train.py:715] (3/8) Epoch 7, batch 15850, loss[loss=0.1539, simple_loss=0.2345, pruned_loss=0.0367, over 4850.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2187, pruned_loss=0.03726, over 972980.41 frames.], batch size: 30, lr: 2.93e-04
+2022-05-05 21:11:57,175 INFO [train.py:715] (3/8) Epoch 7, batch 15900, loss[loss=0.1629, simple_loss=0.2312, pruned_loss=0.04731, over 4951.00 frames.], tot_loss[loss=0.146, simple_loss=0.2183, pruned_loss=0.03689, over 973346.62 frames.], batch size: 39, lr: 2.93e-04
+2022-05-05 21:12:36,478 INFO [train.py:715] (3/8) Epoch 7, batch 15950, loss[loss=0.116, simple_loss=0.192, pruned_loss=0.02, over 4965.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03704, over 973662.25 frames.], batch size: 24, lr: 2.93e-04
+2022-05-05 21:13:15,930 INFO [train.py:715] (3/8) Epoch 7, batch 16000, loss[loss=0.1282, simple_loss=0.1904, pruned_loss=0.03301, over 4797.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2171, pruned_loss=0.03722, over 972460.08 frames.], batch size: 12, lr: 2.93e-04
+2022-05-05 21:13:54,030 INFO [train.py:715] (3/8) Epoch 7, batch 16050, loss[loss=0.1757, simple_loss=0.2298, pruned_loss=0.06077, over 4929.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2179, pruned_loss=0.03761, over 971886.76 frames.], batch size: 18, lr: 2.93e-04
+2022-05-05 21:14:33,355 INFO [train.py:715] (3/8) Epoch 7, batch 16100, loss[loss=0.1454, simple_loss=0.2137, pruned_loss=0.03854, over 4785.00 frames.], tot_loss[loss=0.146, simple_loss=0.2174, pruned_loss=0.03732, over 971990.52 frames.], batch size: 17, lr: 2.93e-04
+2022-05-05 21:15:12,279 INFO [train.py:715] (3/8) Epoch 7, batch 16150, loss[loss=0.1299, simple_loss=0.2013, pruned_loss=0.02924, over 4993.00 frames.], tot_loss[loss=0.1453, simple_loss=0.217, pruned_loss=0.03681, over 972213.47 frames.], batch size: 20, lr: 2.93e-04
+2022-05-05 21:15:50,931 INFO [train.py:715] (3/8) Epoch 7, batch 16200, loss[loss=0.1321, simple_loss=0.2031, pruned_loss=0.03055, over 4948.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2165, pruned_loss=0.03651, over 972504.44 frames.], batch size: 21, lr: 2.93e-04
+2022-05-05 21:16:30,080 INFO [train.py:715] (3/8) Epoch 7, batch 16250, loss[loss=0.1112, simple_loss=0.1847, pruned_loss=0.01886, over 4836.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2161, pruned_loss=0.03618, over 972253.32 frames.], batch size: 13, lr: 2.93e-04
+2022-05-05 21:17:08,725 INFO [train.py:715] (3/8) Epoch 7, batch 16300, loss[loss=0.1226, simple_loss=0.2039, pruned_loss=0.02059, over 4913.00 frames.], tot_loss[loss=0.1441, simple_loss=0.216, pruned_loss=0.03605, over 971944.89 frames.], batch size: 29, lr: 2.93e-04
+2022-05-05 21:17:48,274 INFO [train.py:715] (3/8) Epoch 7, batch 16350, loss[loss=0.1415, simple_loss=0.2122, pruned_loss=0.03539, over 4864.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2162, pruned_loss=0.03627, over 972202.20 frames.], batch size: 20, lr: 2.93e-04
+2022-05-05 21:18:26,610 INFO [train.py:715] (3/8) Epoch 7, batch 16400, loss[loss=0.1234, simple_loss=0.1945, pruned_loss=0.02614, over 4696.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.03637, over 971445.96 frames.], batch size: 15, lr: 2.93e-04
+2022-05-05 21:19:05,505 INFO [train.py:715] (3/8) Epoch 7, batch 16450, loss[loss=0.1136, simple_loss=0.1892, pruned_loss=0.01902, over 4818.00 frames.], tot_loss[loss=0.145, simple_loss=0.2166, pruned_loss=0.03665, over 971756.79 frames.], batch size: 26, lr: 2.93e-04
+2022-05-05 21:19:44,558 INFO [train.py:715] (3/8) Epoch 7, batch 16500, loss[loss=0.1408, simple_loss=0.222, pruned_loss=0.02981, over 4871.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03693, over 972190.17 frames.], batch size: 22, lr: 2.93e-04
+2022-05-05 21:20:22,828 INFO [train.py:715] (3/8) Epoch 7, batch 16550, loss[loss=0.1643, simple_loss=0.2353, pruned_loss=0.04672, over 4886.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2177, pruned_loss=0.03674, over 972236.99 frames.], batch size: 19, lr: 2.93e-04
+2022-05-05 21:21:02,231 INFO [train.py:715] (3/8) Epoch 7, batch 16600, loss[loss=0.1308, simple_loss=0.2094, pruned_loss=0.02608, over 4788.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.0363, over 971815.90 frames.], batch size: 17, lr: 2.93e-04
+2022-05-05 21:21:41,398 INFO [train.py:715] (3/8) Epoch 7, batch 16650, loss[loss=0.1474, simple_loss=0.2163, pruned_loss=0.0393, over 4781.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2168, pruned_loss=0.03642, over 971517.40 frames.], batch size: 17, lr: 2.93e-04
+2022-05-05 21:22:20,545 INFO [train.py:715] (3/8) Epoch 7, batch 16700, loss[loss=0.1722, simple_loss=0.2491, pruned_loss=0.04764, over 4852.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2173, pruned_loss=0.0365, over 971158.36 frames.], batch size: 15, lr: 2.93e-04
+2022-05-05 21:22:59,814 INFO [train.py:715] (3/8) Epoch 7, batch 16750, loss[loss=0.206, simple_loss=0.2678, pruned_loss=0.07212, over 4742.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2173, pruned_loss=0.03667, over 971038.08 frames.], batch size: 16, lr: 2.93e-04
+2022-05-05 21:23:38,670 INFO [train.py:715] (3/8) Epoch 7, batch 16800, loss[loss=0.1075, simple_loss=0.1712, pruned_loss=0.02189, over 4808.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03737, over 971285.58 frames.], batch size: 12, lr: 2.93e-04
+2022-05-05 21:24:17,714 INFO [train.py:715] (3/8) Epoch 7, batch 16850, loss[loss=0.1296, simple_loss=0.1981, pruned_loss=0.03052, over 4980.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2176, pruned_loss=0.03736, over 971861.55 frames.], batch size: 35, lr: 2.93e-04
+2022-05-05 21:24:56,999 INFO [train.py:715] (3/8) Epoch 7, batch 16900, loss[loss=0.1685, simple_loss=0.2309, pruned_loss=0.05311, over 4826.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2183, pruned_loss=0.03799, over 972137.93 frames.], batch size: 15, lr: 2.93e-04
+2022-05-05 21:25:36,248 INFO [train.py:715] (3/8) Epoch 7, batch 16950, loss[loss=0.1423, simple_loss=0.2101, pruned_loss=0.03721, over 4804.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2183, pruned_loss=0.03804, over 972435.19 frames.], batch size: 21, lr: 2.93e-04
+2022-05-05 21:26:14,896 INFO [train.py:715] (3/8) Epoch 7, batch 17000, loss[loss=0.1827, simple_loss=0.2513, pruned_loss=0.05711, over 4839.00 frames.], tot_loss[loss=0.148, simple_loss=0.2193, pruned_loss=0.03838, over 972365.17 frames.], batch size: 30, lr: 2.93e-04
+2022-05-05 21:26:54,054 INFO [train.py:715] (3/8) Epoch 7, batch 17050, loss[loss=0.1252, simple_loss=0.1986, pruned_loss=0.02593, over 4925.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2193, pruned_loss=0.03808, over 972017.41 frames.], batch size: 23, lr: 2.93e-04
+2022-05-05 21:27:32,507 INFO [train.py:715] (3/8) Epoch 7, batch 17100, loss[loss=0.1327, simple_loss=0.2027, pruned_loss=0.03132, over 4741.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03778, over 971908.32 frames.], batch size: 16, lr: 2.93e-04
+2022-05-05 21:28:11,646 INFO [train.py:715] (3/8) Epoch 7, batch 17150, loss[loss=0.1488, simple_loss=0.2242, pruned_loss=0.03668, over 4799.00 frames.], tot_loss[loss=0.148, simple_loss=0.22, pruned_loss=0.03803, over 971487.27 frames.], batch size: 21, lr: 2.93e-04
+2022-05-05 21:28:50,905 INFO [train.py:715] (3/8) Epoch 7, batch 17200, loss[loss=0.1178, simple_loss=0.1908, pruned_loss=0.02239, over 4799.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2188, pruned_loss=0.03733, over 971938.22 frames.], batch size: 12, lr: 2.93e-04
+2022-05-05 21:29:29,222 INFO [train.py:715] (3/8) Epoch 7, batch 17250, loss[loss=0.1766, simple_loss=0.2404, pruned_loss=0.05646, over 4951.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2188, pruned_loss=0.03752, over 972794.49 frames.], batch size: 21, lr: 2.92e-04
+2022-05-05 21:30:08,293 INFO [train.py:715] (3/8) Epoch 7, batch 17300, loss[loss=0.1271, simple_loss=0.2063, pruned_loss=0.02393, over 4791.00 frames.], tot_loss[loss=0.1467, simple_loss=0.219, pruned_loss=0.0372, over 972127.26 frames.], batch size: 24, lr: 2.92e-04
+2022-05-05 21:30:46,575 INFO [train.py:715] (3/8) Epoch 7, batch 17350, loss[loss=0.1393, simple_loss=0.2166, pruned_loss=0.03101, over 4945.00 frames.], tot_loss[loss=0.1481, simple_loss=0.22, pruned_loss=0.03807, over 971911.60 frames.], batch size: 24, lr: 2.92e-04
+2022-05-05 21:31:25,652 INFO [train.py:715] (3/8) Epoch 7, batch 17400, loss[loss=0.1402, simple_loss=0.2179, pruned_loss=0.03126, over 4920.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2199, pruned_loss=0.0384, over 972126.21 frames.], batch size: 29, lr: 2.92e-04
+2022-05-05 21:32:04,441 INFO [train.py:715] (3/8) Epoch 7, batch 17450, loss[loss=0.1717, simple_loss=0.2274, pruned_loss=0.05797, over 4819.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.0388, over 972055.30 frames.], batch size: 13, lr: 2.92e-04
+2022-05-05 21:32:43,218 INFO [train.py:715] (3/8) Epoch 7, batch 17500, loss[loss=0.1756, simple_loss=0.2451, pruned_loss=0.053, over 4937.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2181, pruned_loss=0.03819, over 971904.13 frames.], batch size: 29, lr: 2.92e-04
+2022-05-05 21:33:22,412 INFO [train.py:715] (3/8) Epoch 7, batch 17550, loss[loss=0.1288, simple_loss=0.1935, pruned_loss=0.03201, over 4771.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2183, pruned_loss=0.03803, over 972171.16 frames.], batch size: 14, lr: 2.92e-04
+2022-05-05 21:34:00,741 INFO [train.py:715] (3/8) Epoch 7, batch 17600, loss[loss=0.1791, simple_loss=0.2505, pruned_loss=0.05382, over 4938.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2182, pruned_loss=0.03797, over 971849.24 frames.], batch size: 21, lr: 2.92e-04
+2022-05-05 21:34:39,810 INFO [train.py:715] (3/8) Epoch 7, batch 17650, loss[loss=0.1385, simple_loss=0.2171, pruned_loss=0.02992, over 4894.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2178, pruned_loss=0.03777, over 971661.84 frames.], batch size: 19, lr: 2.92e-04
+2022-05-05 21:35:19,110 INFO [train.py:715] (3/8) Epoch 7, batch 17700, loss[loss=0.1512, simple_loss=0.2272, pruned_loss=0.03762, over 4907.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2176, pruned_loss=0.03732, over 971433.61 frames.], batch size: 19, lr: 2.92e-04
+2022-05-05 21:35:58,207 INFO [train.py:715] (3/8) Epoch 7, batch 17750, loss[loss=0.18, simple_loss=0.243, pruned_loss=0.05851, over 4969.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03717, over 972624.77 frames.], batch size: 15, lr: 2.92e-04
+2022-05-05 21:36:37,514 INFO [train.py:715] (3/8) Epoch 7, batch 17800, loss[loss=0.1314, simple_loss=0.2048, pruned_loss=0.02895, over 4794.00 frames.], tot_loss[loss=0.146, simple_loss=0.2176, pruned_loss=0.03721, over 972042.66 frames.], batch size: 17, lr: 2.92e-04
+2022-05-05 21:37:16,003 INFO [train.py:715] (3/8) Epoch 7, batch 17850, loss[loss=0.1264, simple_loss=0.2034, pruned_loss=0.02468, over 4947.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2174, pruned_loss=0.03744, over 972243.10 frames.], batch size: 21, lr: 2.92e-04
+2022-05-05 21:37:55,614 INFO [train.py:715] (3/8) Epoch 7, batch 17900, loss[loss=0.1666, simple_loss=0.2287, pruned_loss=0.05221, over 4901.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2175, pruned_loss=0.0376, over 972015.88 frames.], batch size: 19, lr: 2.92e-04
+2022-05-05 21:38:34,076 INFO [train.py:715] (3/8) Epoch 7, batch 17950, loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03271, over 4755.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2165, pruned_loss=0.03725, over 971284.69 frames.], batch size: 14, lr: 2.92e-04
+2022-05-05 21:39:13,133 INFO [train.py:715] (3/8) Epoch 7, batch 18000, loss[loss=0.1442, simple_loss=0.2096, pruned_loss=0.03936, over 4926.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2174, pruned_loss=0.03774, over 972136.25 frames.], batch size: 18, lr: 2.92e-04
+2022-05-05 21:39:13,133 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 21:39:22,793 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.1081, simple_loss=0.193, pruned_loss=0.01158, over 914524.00 frames.
+2022-05-05 21:40:01,811 INFO [train.py:715] (3/8) Epoch 7, batch 18050, loss[loss=0.1333, simple_loss=0.1957, pruned_loss=0.0355, over 4976.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2169, pruned_loss=0.0373, over 972639.84 frames.], batch size: 15, lr: 2.92e-04
+2022-05-05 21:40:41,009 INFO [train.py:715] (3/8) Epoch 7, batch 18100, loss[loss=0.1651, simple_loss=0.2307, pruned_loss=0.04981, over 4902.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03751, over 972552.85 frames.], batch size: 19, lr: 2.92e-04
+2022-05-05 21:41:19,569 INFO [train.py:715] (3/8) Epoch 7, batch 18150, loss[loss=0.1368, simple_loss=0.2036, pruned_loss=0.03504, over 4954.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2184, pruned_loss=0.03756, over 972583.55 frames.], batch size: 24, lr: 2.92e-04
+2022-05-05 21:41:57,882 INFO [train.py:715] (3/8) Epoch 7, batch 18200, loss[loss=0.1232, simple_loss=0.1945, pruned_loss=0.02595, over 4848.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2188, pruned_loss=0.03737, over 973121.40 frames.], batch size: 20, lr: 2.92e-04
+2022-05-05 21:42:36,256 INFO [train.py:715] (3/8) Epoch 7, batch 18250, loss[loss=0.1161, simple_loss=0.197, pruned_loss=0.01762, over 4823.00 frames.], tot_loss[loss=0.147, simple_loss=0.2187, pruned_loss=0.03767, over 973096.22 frames.], batch size: 27, lr: 2.92e-04
+2022-05-05 21:43:15,545 INFO [train.py:715] (3/8) Epoch 7, batch 18300, loss[loss=0.1269, simple_loss=0.2043, pruned_loss=0.02473, over 4948.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03725, over 973528.07 frames.], batch size: 21, lr: 2.92e-04
+2022-05-05 21:43:53,555 INFO [train.py:715] (3/8) Epoch 7, batch 18350, loss[loss=0.1599, simple_loss=0.2394, pruned_loss=0.04021, over 4976.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03733, over 973100.14 frames.], batch size: 24, lr: 2.92e-04
+2022-05-05 21:44:31,938 INFO [train.py:715] (3/8) Epoch 7, batch 18400, loss[loss=0.1671, simple_loss=0.2354, pruned_loss=0.0494, over 4808.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03757, over 973934.42 frames.], batch size: 25, lr: 2.92e-04
+2022-05-05 21:45:11,788 INFO [train.py:715] (3/8) Epoch 7, batch 18450, loss[loss=0.1514, simple_loss=0.2231, pruned_loss=0.03989, over 4753.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2185, pruned_loss=0.03723, over 973532.35 frames.], batch size: 16, lr: 2.92e-04
+2022-05-05 21:45:50,716 INFO [train.py:715] (3/8) Epoch 7, batch 18500, loss[loss=0.1359, simple_loss=0.2105, pruned_loss=0.03069, over 4766.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2191, pruned_loss=0.03738, over 973696.57 frames.], batch size: 14, lr: 2.92e-04
+2022-05-05 21:46:29,378 INFO [train.py:715] (3/8) Epoch 7, batch 18550, loss[loss=0.1536, simple_loss=0.2182, pruned_loss=0.04454, over 4701.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2186, pruned_loss=0.03685, over 973595.93 frames.], batch size: 15, lr: 2.92e-04
+2022-05-05 21:47:08,451 INFO [train.py:715] (3/8) Epoch 7, batch 18600, loss[loss=0.1313, simple_loss=0.1996, pruned_loss=0.03152, over 4654.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2176, pruned_loss=0.03646, over 973247.74 frames.], batch size: 13, lr: 2.92e-04
+2022-05-05 21:47:47,274 INFO [train.py:715] (3/8) Epoch 7, batch 18650, loss[loss=0.1455, simple_loss=0.2243, pruned_loss=0.03336, over 4928.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2176, pruned_loss=0.03647, over 973127.73 frames.], batch size: 29, lr: 2.92e-04
+2022-05-05 21:48:25,125 INFO [train.py:715] (3/8) Epoch 7, batch 18700, loss[loss=0.1234, simple_loss=0.2009, pruned_loss=0.02293, over 4863.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2173, pruned_loss=0.03621, over 972206.39 frames.], batch size: 20, lr: 2.92e-04
+2022-05-05 21:49:03,390 INFO [train.py:715] (3/8) Epoch 7, batch 18750, loss[loss=0.1181, simple_loss=0.1993, pruned_loss=0.01841, over 4838.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2175, pruned_loss=0.03621, over 972724.09 frames.], batch size: 26, lr: 2.92e-04
+2022-05-05 21:49:42,761 INFO [train.py:715] (3/8) Epoch 7, batch 18800, loss[loss=0.1214, simple_loss=0.196, pruned_loss=0.02342, over 4748.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2176, pruned_loss=0.03605, over 971628.37 frames.], batch size: 16, lr: 2.92e-04
+2022-05-05 21:50:21,360 INFO [train.py:715] (3/8) Epoch 7, batch 18850, loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02881, over 4812.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2173, pruned_loss=0.036, over 970860.36 frames.], batch size: 21, lr: 2.92e-04
+2022-05-05 21:50:59,416 INFO [train.py:715] (3/8) Epoch 7, batch 18900, loss[loss=0.1301, simple_loss=0.1999, pruned_loss=0.03011, over 4816.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2172, pruned_loss=0.03596, over 970330.71 frames.], batch size: 13, lr: 2.92e-04
+2022-05-05 21:51:36,461 INFO [train.py:715] (3/8) Epoch 7, batch 18950, loss[loss=0.1329, simple_loss=0.2191, pruned_loss=0.02332, over 4970.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2173, pruned_loss=0.03641, over 971389.95 frames.], batch size: 24, lr: 2.92e-04
+2022-05-05 21:52:14,914 INFO [train.py:715] (3/8) Epoch 7, batch 19000, loss[loss=0.2038, simple_loss=0.2677, pruned_loss=0.06998, over 4749.00 frames.], tot_loss[loss=0.145, simple_loss=0.2172, pruned_loss=0.03638, over 971734.76 frames.], batch size: 16, lr: 2.92e-04
+2022-05-05 21:52:52,516 INFO [train.py:715] (3/8) Epoch 7, batch 19050, loss[loss=0.1608, simple_loss=0.2319, pruned_loss=0.04486, over 4753.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2169, pruned_loss=0.03647, over 971707.15 frames.], batch size: 16, lr: 2.91e-04
+2022-05-05 21:53:30,743 INFO [train.py:715] (3/8) Epoch 7, batch 19100, loss[loss=0.1386, simple_loss=0.2152, pruned_loss=0.031, over 4808.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2164, pruned_loss=0.03615, over 971918.33 frames.], batch size: 12, lr: 2.91e-04
+2022-05-05 21:54:09,413 INFO [train.py:715] (3/8) Epoch 7, batch 19150, loss[loss=0.1324, simple_loss=0.2136, pruned_loss=0.02555, over 4987.00 frames.], tot_loss[loss=0.1452, simple_loss=0.217, pruned_loss=0.03667, over 972597.19 frames.], batch size: 28, lr: 2.91e-04
+2022-05-05 21:54:47,125 INFO [train.py:715] (3/8) Epoch 7, batch 19200, loss[loss=0.1627, simple_loss=0.2286, pruned_loss=0.04843, over 4804.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2173, pruned_loss=0.03689, over 972776.09 frames.], batch size: 14, lr: 2.91e-04
+2022-05-05 21:55:24,840 INFO [train.py:715] (3/8) Epoch 7, batch 19250, loss[loss=0.1418, simple_loss=0.2181, pruned_loss=0.03275, over 4741.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2181, pruned_loss=0.03686, over 972201.92 frames.], batch size: 16, lr: 2.91e-04
+2022-05-05 21:56:02,879 INFO [train.py:715] (3/8) Epoch 7, batch 19300, loss[loss=0.1343, simple_loss=0.2117, pruned_loss=0.02841, over 4928.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2186, pruned_loss=0.03687, over 972643.39 frames.], batch size: 29, lr: 2.91e-04
+2022-05-05 21:56:41,358 INFO [train.py:715] (3/8) Epoch 7, batch 19350, loss[loss=0.1248, simple_loss=0.1832, pruned_loss=0.03317, over 4824.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2169, pruned_loss=0.03605, over 972515.93 frames.], batch size: 13, lr: 2.91e-04
+2022-05-05 21:57:18,831 INFO [train.py:715] (3/8) Epoch 7, batch 19400, loss[loss=0.1272, simple_loss=0.2071, pruned_loss=0.02362, over 4817.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2176, pruned_loss=0.03653, over 972737.50 frames.], batch size: 25, lr: 2.91e-04
+2022-05-05 21:57:56,264 INFO [train.py:715] (3/8) Epoch 7, batch 19450, loss[loss=0.1477, simple_loss=0.214, pruned_loss=0.04068, over 4813.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03773, over 972349.28 frames.], batch size: 13, lr: 2.91e-04
+2022-05-05 21:58:34,323 INFO [train.py:715] (3/8) Epoch 7, batch 19500, loss[loss=0.1386, simple_loss=0.2113, pruned_loss=0.03295, over 4894.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03758, over 972717.32 frames.], batch size: 22, lr: 2.91e-04
+2022-05-05 21:59:11,842 INFO [train.py:715] (3/8) Epoch 7, batch 19550, loss[loss=0.1425, simple_loss=0.2221, pruned_loss=0.03144, over 4916.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2197, pruned_loss=0.03796, over 972598.98 frames.], batch size: 18, lr: 2.91e-04
+2022-05-05 21:59:49,564 INFO [train.py:715] (3/8) Epoch 7, batch 19600, loss[loss=0.1238, simple_loss=0.2037, pruned_loss=0.02196, over 4866.00 frames.], tot_loss[loss=0.1472, simple_loss=0.219, pruned_loss=0.03767, over 972556.99 frames.], batch size: 20, lr: 2.91e-04
+2022-05-05 22:00:27,125 INFO [train.py:715] (3/8) Epoch 7, batch 19650, loss[loss=0.1334, simple_loss=0.1948, pruned_loss=0.03603, over 4761.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03753, over 972812.36 frames.], batch size: 12, lr: 2.91e-04
+2022-05-05 22:01:05,538 INFO [train.py:715] (3/8) Epoch 7, batch 19700, loss[loss=0.1393, simple_loss=0.2098, pruned_loss=0.03444, over 4938.00 frames.], tot_loss[loss=0.147, simple_loss=0.2182, pruned_loss=0.03784, over 972852.98 frames.], batch size: 29, lr: 2.91e-04
+2022-05-05 22:01:42,746 INFO [train.py:715] (3/8) Epoch 7, batch 19750, loss[loss=0.1303, simple_loss=0.2038, pruned_loss=0.02841, over 4813.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2177, pruned_loss=0.0378, over 972302.10 frames.], batch size: 27, lr: 2.91e-04
+2022-05-05 22:02:20,223 INFO [train.py:715] (3/8) Epoch 7, batch 19800, loss[loss=0.1302, simple_loss=0.2156, pruned_loss=0.02244, over 4903.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2185, pruned_loss=0.03799, over 972084.05 frames.], batch size: 22, lr: 2.91e-04
+2022-05-05 22:02:58,035 INFO [train.py:715] (3/8) Epoch 7, batch 19850, loss[loss=0.1566, simple_loss=0.22, pruned_loss=0.04661, over 4772.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2175, pruned_loss=0.03729, over 971324.33 frames.], batch size: 14, lr: 2.91e-04
+2022-05-05 22:03:35,859 INFO [train.py:715] (3/8) Epoch 7, batch 19900, loss[loss=0.1472, simple_loss=0.219, pruned_loss=0.03774, over 4833.00 frames.], tot_loss[loss=0.146, simple_loss=0.2179, pruned_loss=0.03707, over 971354.64 frames.], batch size: 26, lr: 2.91e-04
+2022-05-05 22:04:12,821 INFO [train.py:715] (3/8) Epoch 7, batch 19950, loss[loss=0.1438, simple_loss=0.2144, pruned_loss=0.03666, over 4986.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03708, over 972443.14 frames.], batch size: 28, lr: 2.91e-04
+2022-05-05 22:04:50,681 INFO [train.py:715] (3/8) Epoch 7, batch 20000, loss[loss=0.1658, simple_loss=0.2339, pruned_loss=0.04881, over 4907.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03721, over 973079.21 frames.], batch size: 17, lr: 2.91e-04
+2022-05-05 22:05:28,964 INFO [train.py:715] (3/8) Epoch 7, batch 20050, loss[loss=0.1387, simple_loss=0.2127, pruned_loss=0.03231, over 4849.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03741, over 973564.42 frames.], batch size: 20, lr: 2.91e-04
+2022-05-05 22:06:06,298 INFO [train.py:715] (3/8) Epoch 7, batch 20100, loss[loss=0.1543, simple_loss=0.2358, pruned_loss=0.03644, over 4835.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2176, pruned_loss=0.03668, over 972776.68 frames.], batch size: 30, lr: 2.91e-04
+2022-05-05 22:06:43,748 INFO [train.py:715] (3/8) Epoch 7, batch 20150, loss[loss=0.1456, simple_loss=0.2192, pruned_loss=0.03602, over 4902.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03665, over 972003.75 frames.], batch size: 39, lr: 2.91e-04
+2022-05-05 22:07:21,915 INFO [train.py:715] (3/8) Epoch 7, batch 20200, loss[loss=0.1454, simple_loss=0.21, pruned_loss=0.04044, over 4841.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2179, pruned_loss=0.03672, over 972867.41 frames.], batch size: 20, lr: 2.91e-04
+2022-05-05 22:08:00,055 INFO [train.py:715] (3/8) Epoch 7, batch 20250, loss[loss=0.1423, simple_loss=0.2035, pruned_loss=0.04052, over 4984.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2184, pruned_loss=0.03726, over 973729.78 frames.], batch size: 14, lr: 2.91e-04
+2022-05-05 22:08:37,465 INFO [train.py:715] (3/8) Epoch 7, batch 20300, loss[loss=0.114, simple_loss=0.194, pruned_loss=0.01705, over 4816.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2187, pruned_loss=0.0373, over 973041.79 frames.], batch size: 25, lr: 2.91e-04
+2022-05-05 22:09:17,217 INFO [train.py:715] (3/8) Epoch 7, batch 20350, loss[loss=0.1488, simple_loss=0.224, pruned_loss=0.0368, over 4973.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2188, pruned_loss=0.0374, over 972635.84 frames.], batch size: 15, lr: 2.91e-04
+2022-05-05 22:09:55,129 INFO [train.py:715] (3/8) Epoch 7, batch 20400, loss[loss=0.148, simple_loss=0.2231, pruned_loss=0.03638, over 4832.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2185, pruned_loss=0.03728, over 972261.83 frames.], batch size: 27, lr: 2.91e-04
+2022-05-05 22:10:33,046 INFO [train.py:715] (3/8) Epoch 7, batch 20450, loss[loss=0.1646, simple_loss=0.2386, pruned_loss=0.04529, over 4958.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2177, pruned_loss=0.03692, over 971399.80 frames.], batch size: 24, lr: 2.91e-04
+2022-05-05 22:11:10,607 INFO [train.py:715] (3/8) Epoch 7, batch 20500, loss[loss=0.1571, simple_loss=0.2166, pruned_loss=0.04876, over 4870.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.03736, over 971397.02 frames.], batch size: 32, lr: 2.91e-04
+2022-05-05 22:11:48,692 INFO [train.py:715] (3/8) Epoch 7, batch 20550, loss[loss=0.1427, simple_loss=0.2237, pruned_loss=0.03089, over 4902.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2185, pruned_loss=0.03726, over 972533.39 frames.], batch size: 19, lr: 2.91e-04
+2022-05-05 22:12:26,842 INFO [train.py:715] (3/8) Epoch 7, batch 20600, loss[loss=0.1221, simple_loss=0.2016, pruned_loss=0.02137, over 4957.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03685, over 971770.49 frames.], batch size: 21, lr: 2.91e-04
+2022-05-05 22:13:04,070 INFO [train.py:715] (3/8) Epoch 7, batch 20650, loss[loss=0.1468, simple_loss=0.2193, pruned_loss=0.03714, over 4873.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.03643, over 971644.25 frames.], batch size: 20, lr: 2.91e-04
+2022-05-05 22:13:41,772 INFO [train.py:715] (3/8) Epoch 7, batch 20700, loss[loss=0.1369, simple_loss=0.2183, pruned_loss=0.02776, over 4951.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2163, pruned_loss=0.03636, over 972038.90 frames.], batch size: 39, lr: 2.91e-04
+2022-05-05 22:14:19,743 INFO [train.py:715] (3/8) Epoch 7, batch 20750, loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03191, over 4870.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2163, pruned_loss=0.03632, over 971552.01 frames.], batch size: 20, lr: 2.91e-04
+2022-05-05 22:14:57,389 INFO [train.py:715] (3/8) Epoch 7, batch 20800, loss[loss=0.1412, simple_loss=0.211, pruned_loss=0.0357, over 4746.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2156, pruned_loss=0.03627, over 971393.13 frames.], batch size: 16, lr: 2.91e-04
+2022-05-05 22:15:34,692 INFO [train.py:715] (3/8) Epoch 7, batch 20850, loss[loss=0.1558, simple_loss=0.2201, pruned_loss=0.04579, over 4785.00 frames.], tot_loss[loss=0.145, simple_loss=0.2165, pruned_loss=0.03676, over 971672.18 frames.], batch size: 18, lr: 2.90e-04
+2022-05-05 22:16:13,019 INFO [train.py:715] (3/8) Epoch 7, batch 20900, loss[loss=0.1444, simple_loss=0.2143, pruned_loss=0.03721, over 4838.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2159, pruned_loss=0.03633, over 971543.81 frames.], batch size: 30, lr: 2.90e-04
+2022-05-05 22:16:50,910 INFO [train.py:715] (3/8) Epoch 7, batch 20950, loss[loss=0.1357, simple_loss=0.2087, pruned_loss=0.0314, over 4871.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2154, pruned_loss=0.03596, over 970630.35 frames.], batch size: 20, lr: 2.90e-04
+2022-05-05 22:17:29,167 INFO [train.py:715] (3/8) Epoch 7, batch 21000, loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03196, over 4757.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.03598, over 972031.54 frames.], batch size: 19, lr: 2.90e-04
+2022-05-05 22:17:29,168 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 22:17:39,071 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.1082, simple_loss=0.193, pruned_loss=0.01169, over 914524.00 frames.
+2022-05-05 22:18:17,066 INFO [train.py:715] (3/8) Epoch 7, batch 21050, loss[loss=0.1519, simple_loss=0.2167, pruned_loss=0.04353, over 4878.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03649, over 972018.61 frames.], batch size: 22, lr: 2.90e-04
+2022-05-05 22:18:54,965 INFO [train.py:715] (3/8) Epoch 7, batch 21100, loss[loss=0.1341, simple_loss=0.2011, pruned_loss=0.03359, over 4690.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2171, pruned_loss=0.03612, over 971403.46 frames.], batch size: 15, lr: 2.90e-04
+2022-05-05 22:19:32,991 INFO [train.py:715] (3/8) Epoch 7, batch 21150, loss[loss=0.1701, simple_loss=0.2393, pruned_loss=0.05044, over 4949.00 frames.], tot_loss[loss=0.144, simple_loss=0.2168, pruned_loss=0.03556, over 971812.18 frames.], batch size: 21, lr: 2.90e-04
+2022-05-05 22:20:10,777 INFO [train.py:715] (3/8) Epoch 7, batch 21200, loss[loss=0.1579, simple_loss=0.2237, pruned_loss=0.04604, over 4784.00 frames.], tot_loss[loss=0.1444, simple_loss=0.217, pruned_loss=0.03592, over 971920.29 frames.], batch size: 18, lr: 2.90e-04
+2022-05-05 22:20:49,001 INFO [train.py:715] (3/8) Epoch 7, batch 21250, loss[loss=0.1736, simple_loss=0.2431, pruned_loss=0.05205, over 4802.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2177, pruned_loss=0.0361, over 972201.80 frames.], batch size: 15, lr: 2.90e-04
+2022-05-05 22:21:27,130 INFO [train.py:715] (3/8) Epoch 7, batch 21300, loss[loss=0.1576, simple_loss=0.232, pruned_loss=0.0416, over 4744.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2178, pruned_loss=0.0363, over 971837.46 frames.], batch size: 16, lr: 2.90e-04
+2022-05-05 22:22:04,501 INFO [train.py:715] (3/8) Epoch 7, batch 21350, loss[loss=0.1357, simple_loss=0.2083, pruned_loss=0.03152, over 4786.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2176, pruned_loss=0.03608, over 972364.14 frames.], batch size: 18, lr: 2.90e-04
+2022-05-05 22:22:42,288 INFO [train.py:715] (3/8) Epoch 7, batch 21400, loss[loss=0.1446, simple_loss=0.219, pruned_loss=0.03511, over 4983.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2179, pruned_loss=0.03616, over 972157.91 frames.], batch size: 14, lr: 2.90e-04
+2022-05-05 22:23:20,548 INFO [train.py:715] (3/8) Epoch 7, batch 21450, loss[loss=0.1852, simple_loss=0.2582, pruned_loss=0.05612, over 4864.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2182, pruned_loss=0.03658, over 972777.54 frames.], batch size: 16, lr: 2.90e-04
+2022-05-05 22:23:58,722 INFO [train.py:715] (3/8) Epoch 7, batch 21500, loss[loss=0.1529, simple_loss=0.2248, pruned_loss=0.04055, over 4966.00 frames.], tot_loss[loss=0.1455, simple_loss=0.218, pruned_loss=0.03645, over 971469.61 frames.], batch size: 24, lr: 2.90e-04
+2022-05-05 22:24:36,575 INFO [train.py:715] (3/8) Epoch 7, batch 21550, loss[loss=0.1477, simple_loss=0.2133, pruned_loss=0.04109, over 4767.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2171, pruned_loss=0.03603, over 971241.12 frames.], batch size: 12, lr: 2.90e-04
+2022-05-05 22:25:14,830 INFO [train.py:715] (3/8) Epoch 7, batch 21600, loss[loss=0.1722, simple_loss=0.2398, pruned_loss=0.05228, over 4928.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2163, pruned_loss=0.03571, over 970360.40 frames.], batch size: 23, lr: 2.90e-04
+2022-05-05 22:25:53,301 INFO [train.py:715] (3/8) Epoch 7, batch 21650, loss[loss=0.1189, simple_loss=0.1903, pruned_loss=0.02371, over 4961.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2164, pruned_loss=0.03547, over 971627.42 frames.], batch size: 35, lr: 2.90e-04
+2022-05-05 22:26:30,668 INFO [train.py:715] (3/8) Epoch 7, batch 21700, loss[loss=0.1746, simple_loss=0.244, pruned_loss=0.05264, over 4768.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2168, pruned_loss=0.03572, over 972085.30 frames.], batch size: 17, lr: 2.90e-04
+2022-05-05 22:27:08,759 INFO [train.py:715] (3/8) Epoch 7, batch 21750, loss[loss=0.1624, simple_loss=0.2304, pruned_loss=0.04722, over 4969.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03612, over 972007.14 frames.], batch size: 14, lr: 2.90e-04
+2022-05-05 22:27:46,871 INFO [train.py:715] (3/8) Epoch 7, batch 21800, loss[loss=0.1374, simple_loss=0.203, pruned_loss=0.03595, over 4702.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.0371, over 971662.77 frames.], batch size: 15, lr: 2.90e-04
+2022-05-05 22:28:24,963 INFO [train.py:715] (3/8) Epoch 7, batch 21850, loss[loss=0.1498, simple_loss=0.2183, pruned_loss=0.04063, over 4924.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2178, pruned_loss=0.03752, over 971353.96 frames.], batch size: 29, lr: 2.90e-04
+2022-05-05 22:29:02,873 INFO [train.py:715] (3/8) Epoch 7, batch 21900, loss[loss=0.1449, simple_loss=0.2055, pruned_loss=0.04213, over 4967.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.03784, over 971619.92 frames.], batch size: 15, lr: 2.90e-04
+2022-05-05 22:29:40,815 INFO [train.py:715] (3/8) Epoch 7, batch 21950, loss[loss=0.1604, simple_loss=0.225, pruned_loss=0.04786, over 4979.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2178, pruned_loss=0.03733, over 971561.89 frames.], batch size: 14, lr: 2.90e-04
+2022-05-05 22:30:19,543 INFO [train.py:715] (3/8) Epoch 7, batch 22000, loss[loss=0.107, simple_loss=0.1807, pruned_loss=0.01665, over 4685.00 frames.], tot_loss[loss=0.1454, simple_loss=0.217, pruned_loss=0.03692, over 971800.26 frames.], batch size: 15, lr: 2.90e-04
+2022-05-05 22:30:57,079 INFO [train.py:715] (3/8) Epoch 7, batch 22050, loss[loss=0.1381, simple_loss=0.214, pruned_loss=0.03109, over 4877.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03691, over 971170.68 frames.], batch size: 22, lr: 2.90e-04
+2022-05-05 22:31:35,218 INFO [train.py:715] (3/8) Epoch 7, batch 22100, loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03408, over 4984.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2165, pruned_loss=0.03659, over 971031.11 frames.], batch size: 14, lr: 2.90e-04
+2022-05-05 22:32:13,476 INFO [train.py:715] (3/8) Epoch 7, batch 22150, loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02989, over 4930.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2174, pruned_loss=0.03666, over 971103.91 frames.], batch size: 29, lr: 2.90e-04
+2022-05-05 22:32:51,985 INFO [train.py:715] (3/8) Epoch 7, batch 22200, loss[loss=0.1534, simple_loss=0.2256, pruned_loss=0.04062, over 4834.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2171, pruned_loss=0.03699, over 971189.29 frames.], batch size: 15, lr: 2.90e-04
+2022-05-05 22:33:29,482 INFO [train.py:715] (3/8) Epoch 7, batch 22250, loss[loss=0.1069, simple_loss=0.1829, pruned_loss=0.01546, over 4810.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2162, pruned_loss=0.03645, over 970819.02 frames.], batch size: 13, lr: 2.90e-04
+2022-05-05 22:34:07,238 INFO [train.py:715] (3/8) Epoch 7, batch 22300, loss[loss=0.1706, simple_loss=0.2264, pruned_loss=0.05736, over 4807.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2176, pruned_loss=0.03669, over 970581.38 frames.], batch size: 14, lr: 2.90e-04
+2022-05-05 22:34:45,535 INFO [train.py:715] (3/8) Epoch 7, batch 22350, loss[loss=0.1475, simple_loss=0.2299, pruned_loss=0.0326, over 4780.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2188, pruned_loss=0.03709, over 970487.66 frames.], batch size: 14, lr: 2.90e-04
+2022-05-05 22:35:22,813 INFO [train.py:715] (3/8) Epoch 7, batch 22400, loss[loss=0.1399, simple_loss=0.207, pruned_loss=0.03644, over 4915.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2192, pruned_loss=0.0375, over 970845.93 frames.], batch size: 29, lr: 2.90e-04
+2022-05-05 22:36:00,506 INFO [train.py:715] (3/8) Epoch 7, batch 22450, loss[loss=0.14, simple_loss=0.2229, pruned_loss=0.02855, over 4776.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2183, pruned_loss=0.03699, over 971529.74 frames.], batch size: 18, lr: 2.90e-04
+2022-05-05 22:36:38,650 INFO [train.py:715] (3/8) Epoch 7, batch 22500, loss[loss=0.145, simple_loss=0.2143, pruned_loss=0.03788, over 4966.00 frames.], tot_loss[loss=0.1461, simple_loss=0.218, pruned_loss=0.0371, over 971469.75 frames.], batch size: 39, lr: 2.90e-04
+2022-05-05 22:37:16,691 INFO [train.py:715] (3/8) Epoch 7, batch 22550, loss[loss=0.1588, simple_loss=0.2194, pruned_loss=0.04912, over 4832.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03702, over 972201.68 frames.], batch size: 13, lr: 2.90e-04
+2022-05-05 22:37:54,355 INFO [train.py:715] (3/8) Epoch 7, batch 22600, loss[loss=0.1239, simple_loss=0.1938, pruned_loss=0.02704, over 4835.00 frames.], tot_loss[loss=0.146, simple_loss=0.2174, pruned_loss=0.03727, over 972591.04 frames.], batch size: 15, lr: 2.90e-04
+2022-05-05 22:38:32,388 INFO [train.py:715] (3/8) Epoch 7, batch 22650, loss[loss=0.1209, simple_loss=0.2021, pruned_loss=0.01986, over 4824.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03779, over 972591.34 frames.], batch size: 25, lr: 2.90e-04
+2022-05-05 22:39:10,751 INFO [train.py:715] (3/8) Epoch 7, batch 22700, loss[loss=0.1471, simple_loss=0.2224, pruned_loss=0.0359, over 4975.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2201, pruned_loss=0.03835, over 972652.80 frames.], batch size: 28, lr: 2.89e-04
+2022-05-05 22:39:48,097 INFO [train.py:715] (3/8) Epoch 7, batch 22750, loss[loss=0.2044, simple_loss=0.2697, pruned_loss=0.06958, over 4888.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2195, pruned_loss=0.03814, over 973252.27 frames.], batch size: 22, lr: 2.89e-04
+2022-05-05 22:40:25,727 INFO [train.py:715] (3/8) Epoch 7, batch 22800, loss[loss=0.1274, simple_loss=0.2067, pruned_loss=0.02409, over 4943.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2192, pruned_loss=0.03772, over 972611.66 frames.], batch size: 23, lr: 2.89e-04
+2022-05-05 22:41:03,919 INFO [train.py:715] (3/8) Epoch 7, batch 22850, loss[loss=0.1769, simple_loss=0.2416, pruned_loss=0.05608, over 4829.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2195, pruned_loss=0.03775, over 972417.41 frames.], batch size: 15, lr: 2.89e-04
+2022-05-05 22:41:41,491 INFO [train.py:715] (3/8) Epoch 7, batch 22900, loss[loss=0.1693, simple_loss=0.2342, pruned_loss=0.05219, over 4956.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2197, pruned_loss=0.03809, over 973254.18 frames.], batch size: 15, lr: 2.89e-04
+2022-05-05 22:42:19,138 INFO [train.py:715] (3/8) Epoch 7, batch 22950, loss[loss=0.1728, simple_loss=0.2421, pruned_loss=0.05172, over 4965.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.03821, over 973150.69 frames.], batch size: 24, lr: 2.89e-04
+2022-05-05 22:42:57,046 INFO [train.py:715] (3/8) Epoch 7, batch 23000, loss[loss=0.1663, simple_loss=0.2384, pruned_loss=0.0471, over 4825.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2193, pruned_loss=0.03811, over 972709.43 frames.], batch size: 26, lr: 2.89e-04
+2022-05-05 22:43:35,194 INFO [train.py:715] (3/8) Epoch 7, batch 23050, loss[loss=0.1796, simple_loss=0.2685, pruned_loss=0.04534, over 4860.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03806, over 972624.71 frames.], batch size: 20, lr: 2.89e-04
+2022-05-05 22:44:12,640 INFO [train.py:715] (3/8) Epoch 7, batch 23100, loss[loss=0.1582, simple_loss=0.2371, pruned_loss=0.0397, over 4913.00 frames.], tot_loss[loss=0.148, simple_loss=0.2198, pruned_loss=0.0381, over 972369.95 frames.], batch size: 18, lr: 2.89e-04
+2022-05-05 22:44:49,936 INFO [train.py:715] (3/8) Epoch 7, batch 23150, loss[loss=0.1457, simple_loss=0.2058, pruned_loss=0.04282, over 4780.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2186, pruned_loss=0.03759, over 971717.37 frames.], batch size: 14, lr: 2.89e-04
+2022-05-05 22:45:28,254 INFO [train.py:715] (3/8) Epoch 7, batch 23200, loss[loss=0.153, simple_loss=0.2221, pruned_loss=0.04196, over 4955.00 frames.], tot_loss[loss=0.1472, simple_loss=0.219, pruned_loss=0.03775, over 972316.26 frames.], batch size: 35, lr: 2.89e-04
+2022-05-05 22:46:06,320 INFO [train.py:715] (3/8) Epoch 7, batch 23250, loss[loss=0.1438, simple_loss=0.2198, pruned_loss=0.03387, over 4913.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2186, pruned_loss=0.03743, over 971513.52 frames.], batch size: 17, lr: 2.89e-04
+2022-05-05 22:46:43,801 INFO [train.py:715] (3/8) Epoch 7, batch 23300, loss[loss=0.144, simple_loss=0.2186, pruned_loss=0.03474, over 4931.00 frames.], tot_loss[loss=0.147, simple_loss=0.2187, pruned_loss=0.03768, over 971867.99 frames.], batch size: 39, lr: 2.89e-04
+2022-05-05 22:47:22,581 INFO [train.py:715] (3/8) Epoch 7, batch 23350, loss[loss=0.1712, simple_loss=0.2268, pruned_loss=0.0578, over 4950.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03758, over 970480.05 frames.], batch size: 21, lr: 2.89e-04
+2022-05-05 22:48:01,698 INFO [train.py:715] (3/8) Epoch 7, batch 23400, loss[loss=0.1523, simple_loss=0.22, pruned_loss=0.04223, over 4910.00 frames.], tot_loss[loss=0.147, simple_loss=0.2186, pruned_loss=0.03774, over 971100.76 frames.], batch size: 19, lr: 2.89e-04
+2022-05-05 22:48:40,125 INFO [train.py:715] (3/8) Epoch 7, batch 23450, loss[loss=0.1171, simple_loss=0.1952, pruned_loss=0.01945, over 4962.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2179, pruned_loss=0.0372, over 971473.95 frames.], batch size: 24, lr: 2.89e-04
+2022-05-05 22:49:18,249 INFO [train.py:715] (3/8) Epoch 7, batch 23500, loss[loss=0.1453, simple_loss=0.2166, pruned_loss=0.03699, over 4916.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03758, over 971003.56 frames.], batch size: 29, lr: 2.89e-04
+2022-05-05 22:49:56,229 INFO [train.py:715] (3/8) Epoch 7, batch 23550, loss[loss=0.135, simple_loss=0.2138, pruned_loss=0.02812, over 4822.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03784, over 971700.22 frames.], batch size: 25, lr: 2.89e-04
+2022-05-05 22:50:34,439 INFO [train.py:715] (3/8) Epoch 7, batch 23600, loss[loss=0.1571, simple_loss=0.2239, pruned_loss=0.04522, over 4927.00 frames.], tot_loss[loss=0.1461, simple_loss=0.218, pruned_loss=0.03711, over 971868.55 frames.], batch size: 39, lr: 2.89e-04
+2022-05-05 22:51:11,417 INFO [train.py:715] (3/8) Epoch 7, batch 23650, loss[loss=0.1395, simple_loss=0.2183, pruned_loss=0.03033, over 4837.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03697, over 972292.00 frames.], batch size: 15, lr: 2.89e-04
+2022-05-05 22:51:49,267 INFO [train.py:715] (3/8) Epoch 7, batch 23700, loss[loss=0.1174, simple_loss=0.1861, pruned_loss=0.02439, over 4841.00 frames.], tot_loss[loss=0.1455, simple_loss=0.217, pruned_loss=0.037, over 972887.11 frames.], batch size: 13, lr: 2.89e-04
+2022-05-05 22:52:27,397 INFO [train.py:715] (3/8) Epoch 7, batch 23750, loss[loss=0.1551, simple_loss=0.221, pruned_loss=0.0446, over 4805.00 frames.], tot_loss[loss=0.1451, simple_loss=0.217, pruned_loss=0.03658, over 973192.05 frames.], batch size: 13, lr: 2.89e-04
+2022-05-05 22:53:04,578 INFO [train.py:715] (3/8) Epoch 7, batch 23800, loss[loss=0.1457, simple_loss=0.2232, pruned_loss=0.03405, over 4981.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2165, pruned_loss=0.03644, over 972094.37 frames.], batch size: 20, lr: 2.89e-04
+2022-05-05 22:53:42,352 INFO [train.py:715] (3/8) Epoch 7, batch 23850, loss[loss=0.1628, simple_loss=0.2406, pruned_loss=0.0425, over 4746.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2163, pruned_loss=0.03617, over 971728.88 frames.], batch size: 16, lr: 2.89e-04
+2022-05-05 22:54:21,023 INFO [train.py:715] (3/8) Epoch 7, batch 23900, loss[loss=0.1092, simple_loss=0.1836, pruned_loss=0.01742, over 4896.00 frames.], tot_loss[loss=0.144, simple_loss=0.2162, pruned_loss=0.03589, over 971070.96 frames.], batch size: 19, lr: 2.89e-04
+2022-05-05 22:54:59,167 INFO [train.py:715] (3/8) Epoch 7, batch 23950, loss[loss=0.1262, simple_loss=0.1982, pruned_loss=0.02707, over 4825.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03598, over 971333.15 frames.], batch size: 15, lr: 2.89e-04
+2022-05-05 22:55:36,639 INFO [train.py:715] (3/8) Epoch 7, batch 24000, loss[loss=0.139, simple_loss=0.2073, pruned_loss=0.03536, over 4869.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2164, pruned_loss=0.0361, over 970729.01 frames.], batch size: 16, lr: 2.89e-04
+2022-05-05 22:55:36,639 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 22:55:46,186 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.108, simple_loss=0.1929, pruned_loss=0.01156, over 914524.00 frames.
+2022-05-05 22:56:23,728 INFO [train.py:715] (3/8) Epoch 7, batch 24050, loss[loss=0.1489, simple_loss=0.2218, pruned_loss=0.03801, over 4895.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03669, over 971817.05 frames.], batch size: 18, lr: 2.89e-04
+2022-05-05 22:57:02,033 INFO [train.py:715] (3/8) Epoch 7, batch 24100, loss[loss=0.1551, simple_loss=0.2213, pruned_loss=0.04451, over 4931.00 frames.], tot_loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.03651, over 971314.14 frames.], batch size: 17, lr: 2.89e-04
+2022-05-05 22:57:40,437 INFO [train.py:715] (3/8) Epoch 7, batch 24150, loss[loss=0.1239, simple_loss=0.192, pruned_loss=0.02784, over 4941.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2168, pruned_loss=0.03687, over 971516.28 frames.], batch size: 24, lr: 2.89e-04
+2022-05-05 22:58:18,173 INFO [train.py:715] (3/8) Epoch 7, batch 24200, loss[loss=0.1525, simple_loss=0.2146, pruned_loss=0.04522, over 4981.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2168, pruned_loss=0.03686, over 971503.29 frames.], batch size: 15, lr: 2.89e-04
+2022-05-05 22:58:55,939 INFO [train.py:715] (3/8) Epoch 7, batch 24250, loss[loss=0.1309, simple_loss=0.1937, pruned_loss=0.03406, over 4782.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2166, pruned_loss=0.03702, over 972586.32 frames.], batch size: 14, lr: 2.89e-04
+2022-05-05 22:59:34,585 INFO [train.py:715] (3/8) Epoch 7, batch 24300, loss[loss=0.1474, simple_loss=0.2183, pruned_loss=0.03823, over 4903.00 frames.], tot_loss[loss=0.1445, simple_loss=0.216, pruned_loss=0.03648, over 972171.33 frames.], batch size: 19, lr: 2.89e-04
+2022-05-05 23:00:12,423 INFO [train.py:715] (3/8) Epoch 7, batch 24350, loss[loss=0.1716, simple_loss=0.2383, pruned_loss=0.05244, over 4960.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2161, pruned_loss=0.03645, over 972341.68 frames.], batch size: 24, lr: 2.89e-04
+2022-05-05 23:00:50,088 INFO [train.py:715] (3/8) Epoch 7, batch 24400, loss[loss=0.1472, simple_loss=0.2255, pruned_loss=0.03442, over 4841.00 frames.], tot_loss[loss=0.144, simple_loss=0.2158, pruned_loss=0.03609, over 972798.04 frames.], batch size: 20, lr: 2.89e-04
+2022-05-05 23:01:28,245 INFO [train.py:715] (3/8) Epoch 7, batch 24450, loss[loss=0.132, simple_loss=0.2125, pruned_loss=0.02577, over 4912.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2156, pruned_loss=0.03582, over 973045.10 frames.], batch size: 18, lr: 2.89e-04
+2022-05-05 23:02:06,218 INFO [train.py:715] (3/8) Epoch 7, batch 24500, loss[loss=0.1434, simple_loss=0.2172, pruned_loss=0.03474, over 4821.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2158, pruned_loss=0.0364, over 972459.16 frames.], batch size: 27, lr: 2.89e-04
+2022-05-05 23:02:43,833 INFO [train.py:715] (3/8) Epoch 7, batch 24550, loss[loss=0.1687, simple_loss=0.2313, pruned_loss=0.05304, over 4822.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2164, pruned_loss=0.03645, over 973255.16 frames.], batch size: 15, lr: 2.88e-04
+2022-05-05 23:03:22,004 INFO [train.py:715] (3/8) Epoch 7, batch 24600, loss[loss=0.1732, simple_loss=0.2393, pruned_loss=0.05353, over 4829.00 frames.], tot_loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03653, over 972519.46 frames.], batch size: 15, lr: 2.88e-04
+2022-05-05 23:04:01,123 INFO [train.py:715] (3/8) Epoch 7, batch 24650, loss[loss=0.1505, simple_loss=0.223, pruned_loss=0.03903, over 4941.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03678, over 972145.29 frames.], batch size: 39, lr: 2.88e-04
+2022-05-05 23:04:39,573 INFO [train.py:715] (3/8) Epoch 7, batch 24700, loss[loss=0.1752, simple_loss=0.2461, pruned_loss=0.05216, over 4981.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2179, pruned_loss=0.03691, over 972314.12 frames.], batch size: 25, lr: 2.88e-04
+2022-05-05 23:05:17,697 INFO [train.py:715] (3/8) Epoch 7, batch 24750, loss[loss=0.1536, simple_loss=0.2287, pruned_loss=0.0393, over 4838.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2176, pruned_loss=0.03676, over 972094.63 frames.], batch size: 15, lr: 2.88e-04
+2022-05-05 23:05:56,161 INFO [train.py:715] (3/8) Epoch 7, batch 24800, loss[loss=0.103, simple_loss=0.1801, pruned_loss=0.01292, over 4832.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03696, over 971687.66 frames.], batch size: 26, lr: 2.88e-04
+2022-05-05 23:06:35,235 INFO [train.py:715] (3/8) Epoch 7, batch 24850, loss[loss=0.1445, simple_loss=0.2193, pruned_loss=0.03489, over 4834.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03652, over 971603.99 frames.], batch size: 26, lr: 2.88e-04
+2022-05-05 23:07:13,825 INFO [train.py:715] (3/8) Epoch 7, batch 24900, loss[loss=0.1663, simple_loss=0.2442, pruned_loss=0.04421, over 4983.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2174, pruned_loss=0.03669, over 972618.28 frames.], batch size: 25, lr: 2.88e-04
+2022-05-05 23:07:53,088 INFO [train.py:715] (3/8) Epoch 7, batch 24950, loss[loss=0.1271, simple_loss=0.2052, pruned_loss=0.02448, over 4957.00 frames.], tot_loss[loss=0.1452, simple_loss=0.217, pruned_loss=0.03674, over 972906.29 frames.], batch size: 24, lr: 2.88e-04
+2022-05-05 23:08:32,940 INFO [train.py:715] (3/8) Epoch 7, batch 25000, loss[loss=0.1502, simple_loss=0.2227, pruned_loss=0.03882, over 4862.00 frames.], tot_loss[loss=0.1453, simple_loss=0.217, pruned_loss=0.0368, over 972902.10 frames.], batch size: 38, lr: 2.88e-04
+2022-05-05 23:09:12,209 INFO [train.py:715] (3/8) Epoch 7, batch 25050, loss[loss=0.1329, simple_loss=0.1982, pruned_loss=0.03377, over 4845.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2176, pruned_loss=0.03679, over 972559.72 frames.], batch size: 30, lr: 2.88e-04
+2022-05-05 23:09:51,233 INFO [train.py:715] (3/8) Epoch 7, batch 25100, loss[loss=0.1524, simple_loss=0.2345, pruned_loss=0.03517, over 4969.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2179, pruned_loss=0.03682, over 973084.72 frames.], batch size: 24, lr: 2.88e-04
+2022-05-05 23:10:31,399 INFO [train.py:715] (3/8) Epoch 7, batch 25150, loss[loss=0.1515, simple_loss=0.2256, pruned_loss=0.03871, over 4940.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2172, pruned_loss=0.03628, over 973725.24 frames.], batch size: 21, lr: 2.88e-04
+2022-05-05 23:11:11,711 INFO [train.py:715] (3/8) Epoch 7, batch 25200, loss[loss=0.145, simple_loss=0.2221, pruned_loss=0.03399, over 4861.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2175, pruned_loss=0.0364, over 973047.95 frames.], batch size: 20, lr: 2.88e-04
+2022-05-05 23:11:51,358 INFO [train.py:715] (3/8) Epoch 7, batch 25250, loss[loss=0.1484, simple_loss=0.2237, pruned_loss=0.0365, over 4778.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2176, pruned_loss=0.03625, over 973277.69 frames.], batch size: 18, lr: 2.88e-04
+2022-05-05 23:12:31,931 INFO [train.py:715] (3/8) Epoch 7, batch 25300, loss[loss=0.1504, simple_loss=0.2229, pruned_loss=0.03893, over 4808.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2182, pruned_loss=0.0366, over 973611.59 frames.], batch size: 25, lr: 2.88e-04
+2022-05-05 23:13:13,663 INFO [train.py:715] (3/8) Epoch 7, batch 25350, loss[loss=0.1517, simple_loss=0.2131, pruned_loss=0.04519, over 4772.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2177, pruned_loss=0.03658, over 973392.14 frames.], batch size: 18, lr: 2.88e-04
+2022-05-05 23:13:55,234 INFO [train.py:715] (3/8) Epoch 7, batch 25400, loss[loss=0.164, simple_loss=0.2366, pruned_loss=0.04576, over 4824.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2171, pruned_loss=0.03604, over 972331.09 frames.], batch size: 15, lr: 2.88e-04
+2022-05-05 23:14:36,167 INFO [train.py:715] (3/8) Epoch 7, batch 25450, loss[loss=0.1849, simple_loss=0.2471, pruned_loss=0.0614, over 4693.00 frames.], tot_loss[loss=0.144, simple_loss=0.2167, pruned_loss=0.03566, over 972463.07 frames.], batch size: 15, lr: 2.88e-04
+2022-05-05 23:15:18,363 INFO [train.py:715] (3/8) Epoch 7, batch 25500, loss[loss=0.1205, simple_loss=0.1995, pruned_loss=0.02069, over 4849.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2167, pruned_loss=0.03575, over 972482.40 frames.], batch size: 20, lr: 2.88e-04
+2022-05-05 23:16:00,249 INFO [train.py:715] (3/8) Epoch 7, batch 25550, loss[loss=0.1547, simple_loss=0.2271, pruned_loss=0.04108, over 4791.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2167, pruned_loss=0.03576, over 972072.00 frames.], batch size: 14, lr: 2.88e-04
+2022-05-05 23:16:41,009 INFO [train.py:715] (3/8) Epoch 7, batch 25600, loss[loss=0.1301, simple_loss=0.2049, pruned_loss=0.02763, over 4795.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2168, pruned_loss=0.03614, over 971599.18 frames.], batch size: 24, lr: 2.88e-04
+2022-05-05 23:17:22,272 INFO [train.py:715] (3/8) Epoch 7, batch 25650, loss[loss=0.1438, simple_loss=0.2102, pruned_loss=0.0387, over 4741.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2165, pruned_loss=0.03607, over 971697.09 frames.], batch size: 16, lr: 2.88e-04
+2022-05-05 23:18:03,672 INFO [train.py:715] (3/8) Epoch 7, batch 25700, loss[loss=0.13, simple_loss=0.2008, pruned_loss=0.02963, over 4797.00 frames.], tot_loss[loss=0.145, simple_loss=0.2168, pruned_loss=0.03665, over 972015.70 frames.], batch size: 21, lr: 2.88e-04
+2022-05-05 23:18:45,503 INFO [train.py:715] (3/8) Epoch 7, batch 25750, loss[loss=0.1702, simple_loss=0.2444, pruned_loss=0.04805, over 4754.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2168, pruned_loss=0.03682, over 971317.19 frames.], batch size: 16, lr: 2.88e-04
+2022-05-05 23:19:26,138 INFO [train.py:715] (3/8) Epoch 7, batch 25800, loss[loss=0.1437, simple_loss=0.2135, pruned_loss=0.03689, over 4923.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2171, pruned_loss=0.03718, over 971802.92 frames.], batch size: 39, lr: 2.88e-04
+2022-05-05 23:20:08,464 INFO [train.py:715] (3/8) Epoch 7, batch 25850, loss[loss=0.1332, simple_loss=0.2045, pruned_loss=0.031, over 4779.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2165, pruned_loss=0.03667, over 972312.22 frames.], batch size: 18, lr: 2.88e-04
+2022-05-05 23:20:50,394 INFO [train.py:715] (3/8) Epoch 7, batch 25900, loss[loss=0.1632, simple_loss=0.2228, pruned_loss=0.0518, over 4939.00 frames.], tot_loss[loss=0.145, simple_loss=0.2167, pruned_loss=0.03669, over 972089.77 frames.], batch size: 35, lr: 2.88e-04
+2022-05-05 23:21:31,301 INFO [train.py:715] (3/8) Epoch 7, batch 25950, loss[loss=0.1532, simple_loss=0.2233, pruned_loss=0.04153, over 4876.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2165, pruned_loss=0.03642, over 972232.71 frames.], batch size: 16, lr: 2.88e-04
+2022-05-05 23:22:12,746 INFO [train.py:715] (3/8) Epoch 7, batch 26000, loss[loss=0.1469, simple_loss=0.2218, pruned_loss=0.03598, over 4921.00 frames.], tot_loss[loss=0.145, simple_loss=0.2167, pruned_loss=0.03665, over 971969.16 frames.], batch size: 29, lr: 2.88e-04
+2022-05-05 23:22:54,190 INFO [train.py:715] (3/8) Epoch 7, batch 26050, loss[loss=0.1864, simple_loss=0.2665, pruned_loss=0.05316, over 4952.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2167, pruned_loss=0.03644, over 972243.05 frames.], batch size: 23, lr: 2.88e-04
+2022-05-05 23:23:36,145 INFO [train.py:715] (3/8) Epoch 7, batch 26100, loss[loss=0.2034, simple_loss=0.2726, pruned_loss=0.0671, over 4779.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03626, over 972363.18 frames.], batch size: 18, lr: 2.88e-04
+2022-05-05 23:24:16,472 INFO [train.py:715] (3/8) Epoch 7, batch 26150, loss[loss=0.1609, simple_loss=0.2301, pruned_loss=0.04587, over 4880.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2167, pruned_loss=0.03629, over 972665.05 frames.], batch size: 16, lr: 2.88e-04
+2022-05-05 23:24:57,987 INFO [train.py:715] (3/8) Epoch 7, batch 26200, loss[loss=0.1558, simple_loss=0.2366, pruned_loss=0.03752, over 4943.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2168, pruned_loss=0.03622, over 972819.02 frames.], batch size: 24, lr: 2.88e-04
+2022-05-05 23:25:39,234 INFO [train.py:715] (3/8) Epoch 7, batch 26250, loss[loss=0.1377, simple_loss=0.2102, pruned_loss=0.03254, over 4770.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.03649, over 972735.51 frames.], batch size: 18, lr: 2.88e-04
+2022-05-05 23:26:19,597 INFO [train.py:715] (3/8) Epoch 7, batch 26300, loss[loss=0.1599, simple_loss=0.2267, pruned_loss=0.04653, over 4776.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2168, pruned_loss=0.03629, over 972474.61 frames.], batch size: 14, lr: 2.88e-04
+2022-05-05 23:26:59,776 INFO [train.py:715] (3/8) Epoch 7, batch 26350, loss[loss=0.1327, simple_loss=0.1977, pruned_loss=0.03386, over 4892.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03638, over 972730.61 frames.], batch size: 17, lr: 2.88e-04
+2022-05-05 23:27:40,226 INFO [train.py:715] (3/8) Epoch 7, batch 26400, loss[loss=0.1429, simple_loss=0.2135, pruned_loss=0.03613, over 4830.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.03626, over 973265.55 frames.], batch size: 27, lr: 2.87e-04
+2022-05-05 23:28:20,884 INFO [train.py:715] (3/8) Epoch 7, batch 26450, loss[loss=0.154, simple_loss=0.2288, pruned_loss=0.03966, over 4763.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2173, pruned_loss=0.03618, over 972360.92 frames.], batch size: 19, lr: 2.87e-04
+2022-05-05 23:29:00,625 INFO [train.py:715] (3/8) Epoch 7, batch 26500, loss[loss=0.1293, simple_loss=0.1913, pruned_loss=0.03371, over 4733.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2173, pruned_loss=0.03658, over 972236.79 frames.], batch size: 12, lr: 2.87e-04
+2022-05-05 23:29:40,316 INFO [train.py:715] (3/8) Epoch 7, batch 26550, loss[loss=0.1811, simple_loss=0.2643, pruned_loss=0.04895, over 4747.00 frames.], tot_loss[loss=0.1458, simple_loss=0.218, pruned_loss=0.03678, over 970947.47 frames.], batch size: 19, lr: 2.87e-04
+2022-05-05 23:30:20,785 INFO [train.py:715] (3/8) Epoch 7, batch 26600, loss[loss=0.1443, simple_loss=0.218, pruned_loss=0.03529, over 4793.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.0365, over 970328.16 frames.], batch size: 21, lr: 2.87e-04
+2022-05-05 23:31:00,455 INFO [train.py:715] (3/8) Epoch 7, batch 26650, loss[loss=0.1572, simple_loss=0.2383, pruned_loss=0.03804, over 4909.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03753, over 970996.59 frames.], batch size: 17, lr: 2.87e-04
+2022-05-05 23:31:40,550 INFO [train.py:715] (3/8) Epoch 7, batch 26700, loss[loss=0.1104, simple_loss=0.1865, pruned_loss=0.01717, over 4797.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2186, pruned_loss=0.03732, over 970801.05 frames.], batch size: 12, lr: 2.87e-04
+2022-05-05 23:32:21,227 INFO [train.py:715] (3/8) Epoch 7, batch 26750, loss[loss=0.1917, simple_loss=0.2595, pruned_loss=0.06188, over 4896.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2181, pruned_loss=0.03718, over 972467.00 frames.], batch size: 39, lr: 2.87e-04
+2022-05-05 23:33:01,187 INFO [train.py:715] (3/8) Epoch 7, batch 26800, loss[loss=0.1629, simple_loss=0.2329, pruned_loss=0.04646, over 4817.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03719, over 972047.69 frames.], batch size: 25, lr: 2.87e-04
+2022-05-05 23:33:40,947 INFO [train.py:715] (3/8) Epoch 7, batch 26850, loss[loss=0.1328, simple_loss=0.1997, pruned_loss=0.033, over 4918.00 frames.], tot_loss[loss=0.146, simple_loss=0.2174, pruned_loss=0.0373, over 970692.98 frames.], batch size: 29, lr: 2.87e-04
+2022-05-05 23:34:21,586 INFO [train.py:715] (3/8) Epoch 7, batch 26900, loss[loss=0.1458, simple_loss=0.2145, pruned_loss=0.0386, over 4810.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2174, pruned_loss=0.03705, over 971541.08 frames.], batch size: 13, lr: 2.87e-04
+2022-05-05 23:35:02,611 INFO [train.py:715] (3/8) Epoch 7, batch 26950, loss[loss=0.1388, simple_loss=0.2036, pruned_loss=0.03702, over 4694.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03704, over 971350.65 frames.], batch size: 15, lr: 2.87e-04
+2022-05-05 23:35:42,945 INFO [train.py:715] (3/8) Epoch 7, batch 27000, loss[loss=0.1305, simple_loss=0.2156, pruned_loss=0.02272, over 4925.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2171, pruned_loss=0.03724, over 972003.98 frames.], batch size: 23, lr: 2.87e-04
+2022-05-05 23:35:42,946 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-05 23:35:52,667 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.108, simple_loss=0.1928, pruned_loss=0.01156, over 914524.00 frames.
+2022-05-05 23:36:33,216 INFO [train.py:715] (3/8) Epoch 7, batch 27050, loss[loss=0.1167, simple_loss=0.1889, pruned_loss=0.02226, over 4814.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2169, pruned_loss=0.03697, over 971279.80 frames.], batch size: 13, lr: 2.87e-04
+2022-05-05 23:37:14,380 INFO [train.py:715] (3/8) Epoch 7, batch 27100, loss[loss=0.1359, simple_loss=0.211, pruned_loss=0.03047, over 4808.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2171, pruned_loss=0.03721, over 971650.48 frames.], batch size: 13, lr: 2.87e-04
+2022-05-05 23:37:56,259 INFO [train.py:715] (3/8) Epoch 7, batch 27150, loss[loss=0.1274, simple_loss=0.1991, pruned_loss=0.02784, over 4753.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2164, pruned_loss=0.03701, over 971328.17 frames.], batch size: 16, lr: 2.87e-04
+2022-05-05 23:38:37,508 INFO [train.py:715] (3/8) Epoch 7, batch 27200, loss[loss=0.1636, simple_loss=0.2204, pruned_loss=0.05343, over 4751.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2158, pruned_loss=0.0368, over 972413.61 frames.], batch size: 16, lr: 2.87e-04
+2022-05-05 23:39:18,969 INFO [train.py:715] (3/8) Epoch 7, batch 27250, loss[loss=0.1496, simple_loss=0.2136, pruned_loss=0.04275, over 4920.00 frames.], tot_loss[loss=0.1448, simple_loss=0.216, pruned_loss=0.03677, over 971957.78 frames.], batch size: 39, lr: 2.87e-04
+2022-05-05 23:40:00,806 INFO [train.py:715] (3/8) Epoch 7, batch 27300, loss[loss=0.1735, simple_loss=0.2518, pruned_loss=0.04763, over 4807.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2166, pruned_loss=0.03732, over 971827.86 frames.], batch size: 25, lr: 2.87e-04
+2022-05-05 23:40:41,757 INFO [train.py:715] (3/8) Epoch 7, batch 27350, loss[loss=0.1364, simple_loss=0.2094, pruned_loss=0.03172, over 4958.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2167, pruned_loss=0.03708, over 972426.01 frames.], batch size: 24, lr: 2.87e-04
+2022-05-05 23:41:23,054 INFO [train.py:715] (3/8) Epoch 7, batch 27400, loss[loss=0.147, simple_loss=0.2159, pruned_loss=0.03904, over 4947.00 frames.], tot_loss[loss=0.145, simple_loss=0.2165, pruned_loss=0.03674, over 972921.88 frames.], batch size: 23, lr: 2.87e-04
+2022-05-05 23:42:04,088 INFO [train.py:715] (3/8) Epoch 7, batch 27450, loss[loss=0.1696, simple_loss=0.2469, pruned_loss=0.04616, over 4836.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2164, pruned_loss=0.03671, over 973753.14 frames.], batch size: 15, lr: 2.87e-04
+2022-05-05 23:42:45,308 INFO [train.py:715] (3/8) Epoch 7, batch 27500, loss[loss=0.1095, simple_loss=0.1794, pruned_loss=0.01986, over 4839.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2174, pruned_loss=0.03725, over 972634.19 frames.], batch size: 13, lr: 2.87e-04
+2022-05-05 23:43:25,879 INFO [train.py:715] (3/8) Epoch 7, batch 27550, loss[loss=0.1268, simple_loss=0.2009, pruned_loss=0.02634, over 4918.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2186, pruned_loss=0.038, over 972700.67 frames.], batch size: 18, lr: 2.87e-04
+2022-05-05 23:44:06,399 INFO [train.py:715] (3/8) Epoch 7, batch 27600, loss[loss=0.1483, simple_loss=0.223, pruned_loss=0.03675, over 4771.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2182, pruned_loss=0.03774, over 972337.28 frames.], batch size: 14, lr: 2.87e-04
+2022-05-05 23:44:47,784 INFO [train.py:715] (3/8) Epoch 7, batch 27650, loss[loss=0.1579, simple_loss=0.2238, pruned_loss=0.04596, over 4951.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03777, over 972484.83 frames.], batch size: 35, lr: 2.87e-04
+2022-05-05 23:45:28,508 INFO [train.py:715] (3/8) Epoch 7, batch 27700, loss[loss=0.1228, simple_loss=0.2012, pruned_loss=0.0222, over 4935.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2177, pruned_loss=0.0377, over 972830.04 frames.], batch size: 21, lr: 2.87e-04
+2022-05-05 23:46:09,238 INFO [train.py:715] (3/8) Epoch 7, batch 27750, loss[loss=0.1244, simple_loss=0.2045, pruned_loss=0.02219, over 4988.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03738, over 973115.93 frames.], batch size: 28, lr: 2.87e-04
+2022-05-05 23:46:50,121 INFO [train.py:715] (3/8) Epoch 7, batch 27800, loss[loss=0.1272, simple_loss=0.2026, pruned_loss=0.02591, over 4823.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03707, over 972855.52 frames.], batch size: 26, lr: 2.87e-04
+2022-05-05 23:47:31,332 INFO [train.py:715] (3/8) Epoch 7, batch 27850, loss[loss=0.1482, simple_loss=0.2169, pruned_loss=0.03978, over 4952.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03697, over 973162.13 frames.], batch size: 29, lr: 2.87e-04
+2022-05-05 23:48:11,398 INFO [train.py:715] (3/8) Epoch 7, batch 27900, loss[loss=0.1305, simple_loss=0.2097, pruned_loss=0.02569, over 4816.00 frames.], tot_loss[loss=0.146, simple_loss=0.2181, pruned_loss=0.03699, over 972894.03 frames.], batch size: 25, lr: 2.87e-04
+2022-05-05 23:48:52,355 INFO [train.py:715] (3/8) Epoch 7, batch 27950, loss[loss=0.1719, simple_loss=0.2446, pruned_loss=0.04963, over 4918.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03701, over 973421.14 frames.], batch size: 39, lr: 2.87e-04
+2022-05-05 23:49:33,549 INFO [train.py:715] (3/8) Epoch 7, batch 28000, loss[loss=0.1264, simple_loss=0.1863, pruned_loss=0.03328, over 4828.00 frames.], tot_loss[loss=0.1453, simple_loss=0.217, pruned_loss=0.03677, over 972767.44 frames.], batch size: 13, lr: 2.87e-04
+2022-05-05 23:50:14,240 INFO [train.py:715] (3/8) Epoch 7, batch 28050, loss[loss=0.1471, simple_loss=0.2261, pruned_loss=0.03406, over 4802.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2162, pruned_loss=0.03634, over 973320.33 frames.], batch size: 24, lr: 2.87e-04
+2022-05-05 23:50:54,405 INFO [train.py:715] (3/8) Epoch 7, batch 28100, loss[loss=0.1461, simple_loss=0.2154, pruned_loss=0.03842, over 4809.00 frames.], tot_loss[loss=0.1443, simple_loss=0.216, pruned_loss=0.03627, over 973060.24 frames.], batch size: 25, lr: 2.87e-04
+2022-05-05 23:51:35,211 INFO [train.py:715] (3/8) Epoch 7, batch 28150, loss[loss=0.1415, simple_loss=0.2215, pruned_loss=0.03073, over 4986.00 frames.], tot_loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.03658, over 973979.43 frames.], batch size: 28, lr: 2.87e-04
+2022-05-05 23:52:16,640 INFO [train.py:715] (3/8) Epoch 7, batch 28200, loss[loss=0.1346, simple_loss=0.2173, pruned_loss=0.02594, over 4844.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03621, over 974166.14 frames.], batch size: 20, lr: 2.87e-04
+2022-05-05 23:52:56,846 INFO [train.py:715] (3/8) Epoch 7, batch 28250, loss[loss=0.121, simple_loss=0.1955, pruned_loss=0.02322, over 4939.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.03634, over 973603.31 frames.], batch size: 21, lr: 2.87e-04
+2022-05-05 23:53:38,365 INFO [train.py:715] (3/8) Epoch 7, batch 28300, loss[loss=0.1673, simple_loss=0.2451, pruned_loss=0.04475, over 4802.00 frames.], tot_loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03728, over 973170.72 frames.], batch size: 17, lr: 2.86e-04
+2022-05-05 23:54:21,480 INFO [train.py:715] (3/8) Epoch 7, batch 28350, loss[loss=0.1675, simple_loss=0.2409, pruned_loss=0.04705, over 4814.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03694, over 973047.41 frames.], batch size: 21, lr: 2.86e-04
+2022-05-05 23:55:01,297 INFO [train.py:715] (3/8) Epoch 7, batch 28400, loss[loss=0.1129, simple_loss=0.1842, pruned_loss=0.02078, over 4851.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2177, pruned_loss=0.03747, over 972743.81 frames.], batch size: 13, lr: 2.86e-04
+2022-05-05 23:55:40,824 INFO [train.py:715] (3/8) Epoch 7, batch 28450, loss[loss=0.1182, simple_loss=0.1847, pruned_loss=0.02588, over 4765.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03748, over 972292.04 frames.], batch size: 14, lr: 2.86e-04
+2022-05-05 23:56:20,931 INFO [train.py:715] (3/8) Epoch 7, batch 28500, loss[loss=0.1535, simple_loss=0.2223, pruned_loss=0.04232, over 4748.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2173, pruned_loss=0.0372, over 971074.70 frames.], batch size: 19, lr: 2.86e-04
+2022-05-05 23:57:01,423 INFO [train.py:715] (3/8) Epoch 7, batch 28550, loss[loss=0.1464, simple_loss=0.217, pruned_loss=0.03791, over 4853.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2178, pruned_loss=0.03766, over 971629.13 frames.], batch size: 32, lr: 2.86e-04
+2022-05-05 23:57:41,415 INFO [train.py:715] (3/8) Epoch 7, batch 28600, loss[loss=0.1437, simple_loss=0.2192, pruned_loss=0.03409, over 4820.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03698, over 972053.64 frames.], batch size: 15, lr: 2.86e-04
+2022-05-05 23:58:21,633 INFO [train.py:715] (3/8) Epoch 7, batch 28650, loss[loss=0.1335, simple_loss=0.2055, pruned_loss=0.03075, over 4934.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2169, pruned_loss=0.03688, over 973270.36 frames.], batch size: 23, lr: 2.86e-04
+2022-05-05 23:59:03,071 INFO [train.py:715] (3/8) Epoch 7, batch 28700, loss[loss=0.1757, simple_loss=0.2466, pruned_loss=0.05239, over 4913.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03733, over 973835.44 frames.], batch size: 18, lr: 2.86e-04
+2022-05-05 23:59:43,952 INFO [train.py:715] (3/8) Epoch 7, batch 28750, loss[loss=0.1456, simple_loss=0.2177, pruned_loss=0.0368, over 4761.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2178, pruned_loss=0.03729, over 973522.09 frames.], batch size: 19, lr: 2.86e-04
+2022-05-06 00:00:24,190 INFO [train.py:715] (3/8) Epoch 7, batch 28800, loss[loss=0.1391, simple_loss=0.2205, pruned_loss=0.02885, over 4905.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2177, pruned_loss=0.03686, over 974165.79 frames.], batch size: 18, lr: 2.86e-04
+2022-05-06 00:01:04,803 INFO [train.py:715] (3/8) Epoch 7, batch 28850, loss[loss=0.1511, simple_loss=0.2101, pruned_loss=0.04612, over 4748.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03703, over 974110.40 frames.], batch size: 16, lr: 2.86e-04
+2022-05-06 00:01:45,171 INFO [train.py:715] (3/8) Epoch 7, batch 28900, loss[loss=0.1598, simple_loss=0.2306, pruned_loss=0.04449, over 4975.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2183, pruned_loss=0.03733, over 973818.86 frames.], batch size: 39, lr: 2.86e-04
+2022-05-06 00:02:24,694 INFO [train.py:715] (3/8) Epoch 7, batch 28950, loss[loss=0.147, simple_loss=0.2165, pruned_loss=0.03873, over 4821.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2182, pruned_loss=0.03772, over 973797.39 frames.], batch size: 25, lr: 2.86e-04
+2022-05-06 00:03:04,247 INFO [train.py:715] (3/8) Epoch 7, batch 29000, loss[loss=0.1375, simple_loss=0.222, pruned_loss=0.0265, over 4832.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2164, pruned_loss=0.03657, over 973423.89 frames.], batch size: 27, lr: 2.86e-04
+2022-05-06 00:03:44,907 INFO [train.py:715] (3/8) Epoch 7, batch 29050, loss[loss=0.1388, simple_loss=0.2185, pruned_loss=0.02953, over 4963.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2162, pruned_loss=0.03643, over 973892.74 frames.], batch size: 21, lr: 2.86e-04
+2022-05-06 00:04:24,475 INFO [train.py:715] (3/8) Epoch 7, batch 29100, loss[loss=0.1454, simple_loss=0.2252, pruned_loss=0.03282, over 4810.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2168, pruned_loss=0.03683, over 973113.24 frames.], batch size: 13, lr: 2.86e-04
+2022-05-06 00:05:04,251 INFO [train.py:715] (3/8) Epoch 7, batch 29150, loss[loss=0.1384, simple_loss=0.2124, pruned_loss=0.03223, over 4952.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2167, pruned_loss=0.03651, over 973070.93 frames.], batch size: 14, lr: 2.86e-04
+2022-05-06 00:05:44,141 INFO [train.py:715] (3/8) Epoch 7, batch 29200, loss[loss=0.1293, simple_loss=0.2034, pruned_loss=0.0276, over 4912.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2158, pruned_loss=0.03633, over 972952.05 frames.], batch size: 29, lr: 2.86e-04
+2022-05-06 00:06:24,419 INFO [train.py:715] (3/8) Epoch 7, batch 29250, loss[loss=0.1304, simple_loss=0.2046, pruned_loss=0.0281, over 4951.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2155, pruned_loss=0.03609, over 973086.32 frames.], batch size: 15, lr: 2.86e-04
+2022-05-06 00:07:04,326 INFO [train.py:715] (3/8) Epoch 7, batch 29300, loss[loss=0.1185, simple_loss=0.1838, pruned_loss=0.02656, over 4940.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2162, pruned_loss=0.03604, over 973001.93 frames.], batch size: 21, lr: 2.86e-04
+2022-05-06 00:07:44,014 INFO [train.py:715] (3/8) Epoch 7, batch 29350, loss[loss=0.1347, simple_loss=0.2029, pruned_loss=0.0333, over 4892.00 frames.], tot_loss[loss=0.1452, simple_loss=0.217, pruned_loss=0.03669, over 972990.95 frames.], batch size: 19, lr: 2.86e-04
+2022-05-06 00:08:24,276 INFO [train.py:715] (3/8) Epoch 7, batch 29400, loss[loss=0.1678, simple_loss=0.2459, pruned_loss=0.04481, over 4974.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2176, pruned_loss=0.037, over 972771.92 frames.], batch size: 25, lr: 2.86e-04
+2022-05-06 00:09:03,565 INFO [train.py:715] (3/8) Epoch 7, batch 29450, loss[loss=0.127, simple_loss=0.2145, pruned_loss=0.01975, over 4830.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2174, pruned_loss=0.03719, over 972236.63 frames.], batch size: 30, lr: 2.86e-04
+2022-05-06 00:09:43,845 INFO [train.py:715] (3/8) Epoch 7, batch 29500, loss[loss=0.119, simple_loss=0.2024, pruned_loss=0.0178, over 4984.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03699, over 972892.56 frames.], batch size: 28, lr: 2.86e-04
+2022-05-06 00:10:23,569 INFO [train.py:715] (3/8) Epoch 7, batch 29550, loss[loss=0.176, simple_loss=0.2398, pruned_loss=0.05608, over 4776.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2183, pruned_loss=0.03738, over 972685.63 frames.], batch size: 18, lr: 2.86e-04
+2022-05-06 00:11:03,253 INFO [train.py:715] (3/8) Epoch 7, batch 29600, loss[loss=0.1513, simple_loss=0.2174, pruned_loss=0.04257, over 4899.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2191, pruned_loss=0.03795, over 972154.95 frames.], batch size: 18, lr: 2.86e-04
+2022-05-06 00:11:43,208 INFO [train.py:715] (3/8) Epoch 7, batch 29650, loss[loss=0.1351, simple_loss=0.2017, pruned_loss=0.03424, over 4749.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.03762, over 972137.04 frames.], batch size: 16, lr: 2.86e-04
+2022-05-06 00:12:23,005 INFO [train.py:715] (3/8) Epoch 7, batch 29700, loss[loss=0.1809, simple_loss=0.2482, pruned_loss=0.05684, over 4910.00 frames.], tot_loss[loss=0.1468, simple_loss=0.218, pruned_loss=0.03785, over 972177.46 frames.], batch size: 39, lr: 2.86e-04
+2022-05-06 00:13:02,661 INFO [train.py:715] (3/8) Epoch 7, batch 29750, loss[loss=0.1531, simple_loss=0.2162, pruned_loss=0.04496, over 4768.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2186, pruned_loss=0.03822, over 971257.71 frames.], batch size: 18, lr: 2.86e-04
+2022-05-06 00:13:42,293 INFO [train.py:715] (3/8) Epoch 7, batch 29800, loss[loss=0.138, simple_loss=0.2117, pruned_loss=0.03214, over 4636.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.03786, over 971980.35 frames.], batch size: 13, lr: 2.86e-04
+2022-05-06 00:14:22,410 INFO [train.py:715] (3/8) Epoch 7, batch 29850, loss[loss=0.1312, simple_loss=0.2079, pruned_loss=0.02729, over 4820.00 frames.], tot_loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03729, over 972203.80 frames.], batch size: 12, lr: 2.86e-04
+2022-05-06 00:15:02,282 INFO [train.py:715] (3/8) Epoch 7, batch 29900, loss[loss=0.1312, simple_loss=0.2041, pruned_loss=0.02911, over 4984.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2173, pruned_loss=0.03719, over 972421.77 frames.], batch size: 28, lr: 2.86e-04
+2022-05-06 00:15:41,860 INFO [train.py:715] (3/8) Epoch 7, batch 29950, loss[loss=0.1451, simple_loss=0.2085, pruned_loss=0.04089, over 4736.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2171, pruned_loss=0.03722, over 972023.01 frames.], batch size: 16, lr: 2.86e-04
+2022-05-06 00:16:21,224 INFO [train.py:715] (3/8) Epoch 7, batch 30000, loss[loss=0.1529, simple_loss=0.2296, pruned_loss=0.03808, over 4842.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2177, pruned_loss=0.03758, over 973266.48 frames.], batch size: 15, lr: 2.86e-04
+2022-05-06 00:16:21,224 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 00:16:41,746 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.1081, simple_loss=0.1929, pruned_loss=0.01164, over 914524.00 frames.
+2022-05-06 00:17:21,553 INFO [train.py:715] (3/8) Epoch 7, batch 30050, loss[loss=0.1918, simple_loss=0.2543, pruned_loss=0.06466, over 4649.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2194, pruned_loss=0.03823, over 971935.85 frames.], batch size: 13, lr: 2.86e-04
+2022-05-06 00:18:00,850 INFO [train.py:715] (3/8) Epoch 7, batch 30100, loss[loss=0.1559, simple_loss=0.2343, pruned_loss=0.03882, over 4817.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03768, over 971753.85 frames.], batch size: 15, lr: 2.86e-04
+2022-05-06 00:18:40,786 INFO [train.py:715] (3/8) Epoch 7, batch 30150, loss[loss=0.1316, simple_loss=0.215, pruned_loss=0.02407, over 4922.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03733, over 971817.31 frames.], batch size: 18, lr: 2.86e-04
+2022-05-06 00:19:20,432 INFO [train.py:715] (3/8) Epoch 7, batch 30200, loss[loss=0.1496, simple_loss=0.2315, pruned_loss=0.03387, over 4797.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.0376, over 971082.83 frames.], batch size: 24, lr: 2.85e-04
+2022-05-06 00:20:00,692 INFO [train.py:715] (3/8) Epoch 7, batch 30250, loss[loss=0.1497, simple_loss=0.2243, pruned_loss=0.03758, over 4937.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2185, pruned_loss=0.03719, over 971124.99 frames.], batch size: 29, lr: 2.85e-04
+2022-05-06 00:20:39,864 INFO [train.py:715] (3/8) Epoch 7, batch 30300, loss[loss=0.1332, simple_loss=0.2058, pruned_loss=0.03025, over 4875.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2183, pruned_loss=0.03713, over 971682.53 frames.], batch size: 30, lr: 2.85e-04
+2022-05-06 00:21:19,492 INFO [train.py:715] (3/8) Epoch 7, batch 30350, loss[loss=0.09001, simple_loss=0.1637, pruned_loss=0.00817, over 4786.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2173, pruned_loss=0.0367, over 972289.56 frames.], batch size: 12, lr: 2.85e-04
+2022-05-06 00:21:58,986 INFO [train.py:715] (3/8) Epoch 7, batch 30400, loss[loss=0.1073, simple_loss=0.1832, pruned_loss=0.01572, over 4926.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.03659, over 972143.43 frames.], batch size: 18, lr: 2.85e-04
+2022-05-06 00:22:38,977 INFO [train.py:715] (3/8) Epoch 7, batch 30450, loss[loss=0.1163, simple_loss=0.1928, pruned_loss=0.01984, over 4984.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2167, pruned_loss=0.03647, over 972155.91 frames.], batch size: 25, lr: 2.85e-04
+2022-05-06 00:23:18,896 INFO [train.py:715] (3/8) Epoch 7, batch 30500, loss[loss=0.1507, simple_loss=0.2303, pruned_loss=0.03556, over 4912.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2178, pruned_loss=0.03685, over 972610.52 frames.], batch size: 17, lr: 2.85e-04
+2022-05-06 00:23:58,828 INFO [train.py:715] (3/8) Epoch 7, batch 30550, loss[loss=0.1412, simple_loss=0.2144, pruned_loss=0.03401, over 4776.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2175, pruned_loss=0.03689, over 972625.33 frames.], batch size: 18, lr: 2.85e-04
+2022-05-06 00:24:38,528 INFO [train.py:715] (3/8) Epoch 7, batch 30600, loss[loss=0.1429, simple_loss=0.2188, pruned_loss=0.03347, over 4975.00 frames.], tot_loss[loss=0.146, simple_loss=0.2178, pruned_loss=0.03707, over 973495.16 frames.], batch size: 14, lr: 2.85e-04
+2022-05-06 00:25:18,165 INFO [train.py:715] (3/8) Epoch 7, batch 30650, loss[loss=0.1577, simple_loss=0.2321, pruned_loss=0.04168, over 4965.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2177, pruned_loss=0.03683, over 972947.47 frames.], batch size: 35, lr: 2.85e-04
+2022-05-06 00:25:57,785 INFO [train.py:715] (3/8) Epoch 7, batch 30700, loss[loss=0.1216, simple_loss=0.2043, pruned_loss=0.01945, over 4803.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2183, pruned_loss=0.03708, over 972264.07 frames.], batch size: 18, lr: 2.85e-04
+2022-05-06 00:26:36,835 INFO [train.py:715] (3/8) Epoch 7, batch 30750, loss[loss=0.1311, simple_loss=0.201, pruned_loss=0.03056, over 4791.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2182, pruned_loss=0.03716, over 971643.91 frames.], batch size: 17, lr: 2.85e-04
+2022-05-06 00:27:15,902 INFO [train.py:715] (3/8) Epoch 7, batch 30800, loss[loss=0.1631, simple_loss=0.2243, pruned_loss=0.05097, over 4871.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03719, over 971808.62 frames.], batch size: 32, lr: 2.85e-04
+2022-05-06 00:27:55,685 INFO [train.py:715] (3/8) Epoch 7, batch 30850, loss[loss=0.1416, simple_loss=0.2137, pruned_loss=0.03476, over 4950.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03696, over 972013.63 frames.], batch size: 28, lr: 2.85e-04
+2022-05-06 00:28:35,191 INFO [train.py:715] (3/8) Epoch 7, batch 30900, loss[loss=0.1458, simple_loss=0.223, pruned_loss=0.03427, over 4798.00 frames.], tot_loss[loss=0.1457, simple_loss=0.218, pruned_loss=0.03676, over 971955.82 frames.], batch size: 24, lr: 2.85e-04
+2022-05-06 00:29:15,591 INFO [train.py:715] (3/8) Epoch 7, batch 30950, loss[loss=0.1109, simple_loss=0.1852, pruned_loss=0.01825, over 4789.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2183, pruned_loss=0.03719, over 971967.34 frames.], batch size: 12, lr: 2.85e-04
+2022-05-06 00:29:54,978 INFO [train.py:715] (3/8) Epoch 7, batch 31000, loss[loss=0.1227, simple_loss=0.196, pruned_loss=0.02466, over 4869.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.03736, over 971462.96 frames.], batch size: 22, lr: 2.85e-04
+2022-05-06 00:30:34,536 INFO [train.py:715] (3/8) Epoch 7, batch 31050, loss[loss=0.1404, simple_loss=0.2165, pruned_loss=0.03218, over 4689.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03711, over 971593.64 frames.], batch size: 15, lr: 2.85e-04
+2022-05-06 00:31:14,371 INFO [train.py:715] (3/8) Epoch 7, batch 31100, loss[loss=0.1678, simple_loss=0.2336, pruned_loss=0.05103, over 4773.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2174, pruned_loss=0.03696, over 971493.85 frames.], batch size: 17, lr: 2.85e-04
+2022-05-06 00:31:54,492 INFO [train.py:715] (3/8) Epoch 7, batch 31150, loss[loss=0.1475, simple_loss=0.2192, pruned_loss=0.03791, over 4648.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.03673, over 970781.60 frames.], batch size: 13, lr: 2.85e-04
+2022-05-06 00:32:33,845 INFO [train.py:715] (3/8) Epoch 7, batch 31200, loss[loss=0.1248, simple_loss=0.2003, pruned_loss=0.02463, over 4903.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2176, pruned_loss=0.0367, over 970827.20 frames.], batch size: 19, lr: 2.85e-04
+2022-05-06 00:33:13,812 INFO [train.py:715] (3/8) Epoch 7, batch 31250, loss[loss=0.144, simple_loss=0.2232, pruned_loss=0.03244, over 4784.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03671, over 970477.41 frames.], batch size: 18, lr: 2.85e-04
+2022-05-06 00:33:54,541 INFO [train.py:715] (3/8) Epoch 7, batch 31300, loss[loss=0.1186, simple_loss=0.1892, pruned_loss=0.02396, over 4850.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2162, pruned_loss=0.03583, over 971182.38 frames.], batch size: 20, lr: 2.85e-04
+2022-05-06 00:34:34,117 INFO [train.py:715] (3/8) Epoch 7, batch 31350, loss[loss=0.1172, simple_loss=0.1948, pruned_loss=0.01978, over 4750.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2162, pruned_loss=0.03564, over 971058.47 frames.], batch size: 12, lr: 2.85e-04
+2022-05-06 00:35:14,069 INFO [train.py:715] (3/8) Epoch 7, batch 31400, loss[loss=0.1444, simple_loss=0.2164, pruned_loss=0.03619, over 4827.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2166, pruned_loss=0.03588, over 971993.32 frames.], batch size: 26, lr: 2.85e-04
+2022-05-06 00:35:53,410 INFO [train.py:715] (3/8) Epoch 7, batch 31450, loss[loss=0.1132, simple_loss=0.1935, pruned_loss=0.0165, over 4802.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2166, pruned_loss=0.03566, over 972619.99 frames.], batch size: 21, lr: 2.85e-04
+2022-05-06 00:36:33,192 INFO [train.py:715] (3/8) Epoch 7, batch 31500, loss[loss=0.1554, simple_loss=0.2312, pruned_loss=0.03978, over 4701.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.03543, over 972481.52 frames.], batch size: 15, lr: 2.85e-04
+2022-05-06 00:37:12,315 INFO [train.py:715] (3/8) Epoch 7, batch 31550, loss[loss=0.1249, simple_loss=0.2032, pruned_loss=0.02328, over 4832.00 frames.], tot_loss[loss=0.1447, simple_loss=0.217, pruned_loss=0.03619, over 972034.47 frames.], batch size: 26, lr: 2.85e-04
+2022-05-06 00:37:52,279 INFO [train.py:715] (3/8) Epoch 7, batch 31600, loss[loss=0.1481, simple_loss=0.2306, pruned_loss=0.03279, over 4801.00 frames.], tot_loss[loss=0.144, simple_loss=0.2167, pruned_loss=0.03564, over 972857.20 frames.], batch size: 21, lr: 2.85e-04
+2022-05-06 00:38:32,099 INFO [train.py:715] (3/8) Epoch 7, batch 31650, loss[loss=0.1371, simple_loss=0.2086, pruned_loss=0.03281, over 4833.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2164, pruned_loss=0.03531, over 973750.12 frames.], batch size: 15, lr: 2.85e-04
+2022-05-06 00:39:11,521 INFO [train.py:715] (3/8) Epoch 7, batch 31700, loss[loss=0.1451, simple_loss=0.2068, pruned_loss=0.0417, over 4938.00 frames.], tot_loss[loss=0.144, simple_loss=0.2167, pruned_loss=0.0357, over 973402.25 frames.], batch size: 23, lr: 2.85e-04
+2022-05-06 00:39:51,227 INFO [train.py:715] (3/8) Epoch 7, batch 31750, loss[loss=0.1205, simple_loss=0.1999, pruned_loss=0.02057, over 4821.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03679, over 972721.25 frames.], batch size: 26, lr: 2.85e-04
+2022-05-06 00:40:30,491 INFO [train.py:715] (3/8) Epoch 7, batch 31800, loss[loss=0.1572, simple_loss=0.2221, pruned_loss=0.04613, over 4966.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.03634, over 973705.20 frames.], batch size: 24, lr: 2.85e-04
+2022-05-06 00:41:09,603 INFO [train.py:715] (3/8) Epoch 7, batch 31850, loss[loss=0.1436, simple_loss=0.2224, pruned_loss=0.03242, over 4821.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.036, over 973906.94 frames.], batch size: 25, lr: 2.85e-04
+2022-05-06 00:41:49,864 INFO [train.py:715] (3/8) Epoch 7, batch 31900, loss[loss=0.1218, simple_loss=0.1939, pruned_loss=0.02487, over 4917.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.0354, over 973078.07 frames.], batch size: 18, lr: 2.85e-04
+2022-05-06 00:42:30,604 INFO [train.py:715] (3/8) Epoch 7, batch 31950, loss[loss=0.1339, simple_loss=0.2137, pruned_loss=0.02709, over 4874.00 frames.], tot_loss[loss=0.143, simple_loss=0.2152, pruned_loss=0.03537, over 973331.90 frames.], batch size: 16, lr: 2.85e-04
+2022-05-06 00:43:11,066 INFO [train.py:715] (3/8) Epoch 7, batch 32000, loss[loss=0.1707, simple_loss=0.2307, pruned_loss=0.05533, over 4774.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.03605, over 973516.43 frames.], batch size: 12, lr: 2.85e-04
+2022-05-06 00:43:50,742 INFO [train.py:715] (3/8) Epoch 7, batch 32050, loss[loss=0.2018, simple_loss=0.284, pruned_loss=0.05976, over 4861.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03648, over 973094.30 frames.], batch size: 20, lr: 2.85e-04
+2022-05-06 00:44:30,664 INFO [train.py:715] (3/8) Epoch 7, batch 32100, loss[loss=0.1502, simple_loss=0.2173, pruned_loss=0.04156, over 4986.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.0363, over 972421.77 frames.], batch size: 26, lr: 2.85e-04
+2022-05-06 00:45:10,478 INFO [train.py:715] (3/8) Epoch 7, batch 32150, loss[loss=0.1323, simple_loss=0.2084, pruned_loss=0.02815, over 4986.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2162, pruned_loss=0.03638, over 972055.87 frames.], batch size: 25, lr: 2.84e-04
+2022-05-06 00:45:50,031 INFO [train.py:715] (3/8) Epoch 7, batch 32200, loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02835, over 4960.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2154, pruned_loss=0.03608, over 972371.26 frames.], batch size: 24, lr: 2.84e-04
+2022-05-06 00:46:29,881 INFO [train.py:715] (3/8) Epoch 7, batch 32250, loss[loss=0.1512, simple_loss=0.2225, pruned_loss=0.03996, over 4968.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2158, pruned_loss=0.03613, over 972581.46 frames.], batch size: 24, lr: 2.84e-04
+2022-05-06 00:47:09,674 INFO [train.py:715] (3/8) Epoch 7, batch 32300, loss[loss=0.1617, simple_loss=0.2322, pruned_loss=0.04555, over 4823.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03603, over 972503.98 frames.], batch size: 26, lr: 2.84e-04
+2022-05-06 00:47:50,012 INFO [train.py:715] (3/8) Epoch 7, batch 32350, loss[loss=0.1459, simple_loss=0.2145, pruned_loss=0.03868, over 4984.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03586, over 972332.63 frames.], batch size: 28, lr: 2.84e-04
+2022-05-06 00:48:29,371 INFO [train.py:715] (3/8) Epoch 7, batch 32400, loss[loss=0.1498, simple_loss=0.2191, pruned_loss=0.0402, over 4793.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03569, over 972761.96 frames.], batch size: 14, lr: 2.84e-04
+2022-05-06 00:49:09,263 INFO [train.py:715] (3/8) Epoch 7, batch 32450, loss[loss=0.1331, simple_loss=0.2081, pruned_loss=0.02902, over 4824.00 frames.], tot_loss[loss=0.1449, simple_loss=0.217, pruned_loss=0.03641, over 972360.08 frames.], batch size: 27, lr: 2.84e-04
+2022-05-06 00:49:48,736 INFO [train.py:715] (3/8) Epoch 7, batch 32500, loss[loss=0.1556, simple_loss=0.2304, pruned_loss=0.04041, over 4984.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2162, pruned_loss=0.03601, over 971755.73 frames.], batch size: 15, lr: 2.84e-04
+2022-05-06 00:50:28,301 INFO [train.py:715] (3/8) Epoch 7, batch 32550, loss[loss=0.1866, simple_loss=0.2468, pruned_loss=0.06318, over 4732.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.03623, over 971044.13 frames.], batch size: 16, lr: 2.84e-04
+2022-05-06 00:51:08,057 INFO [train.py:715] (3/8) Epoch 7, batch 32600, loss[loss=0.1388, simple_loss=0.2099, pruned_loss=0.03386, over 4802.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2165, pruned_loss=0.03688, over 971221.59 frames.], batch size: 24, lr: 2.84e-04
+2022-05-06 00:51:47,564 INFO [train.py:715] (3/8) Epoch 7, batch 32650, loss[loss=0.1143, simple_loss=0.197, pruned_loss=0.01585, over 4944.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2165, pruned_loss=0.03667, over 971747.43 frames.], batch size: 21, lr: 2.84e-04
+2022-05-06 00:52:27,386 INFO [train.py:715] (3/8) Epoch 7, batch 32700, loss[loss=0.1054, simple_loss=0.1678, pruned_loss=0.0215, over 4788.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2166, pruned_loss=0.03705, over 971725.69 frames.], batch size: 12, lr: 2.84e-04
+2022-05-06 00:53:06,818 INFO [train.py:715] (3/8) Epoch 7, batch 32750, loss[loss=0.137, simple_loss=0.2196, pruned_loss=0.02723, over 4923.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2168, pruned_loss=0.0368, over 972120.69 frames.], batch size: 18, lr: 2.84e-04
+2022-05-06 00:53:47,304 INFO [train.py:715] (3/8) Epoch 7, batch 32800, loss[loss=0.1446, simple_loss=0.2035, pruned_loss=0.04288, over 4749.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2166, pruned_loss=0.03687, over 971615.36 frames.], batch size: 16, lr: 2.84e-04
+2022-05-06 00:54:27,991 INFO [train.py:715] (3/8) Epoch 7, batch 32850, loss[loss=0.1311, simple_loss=0.2051, pruned_loss=0.02856, over 4953.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2168, pruned_loss=0.037, over 971945.85 frames.], batch size: 35, lr: 2.84e-04
+2022-05-06 00:55:08,137 INFO [train.py:715] (3/8) Epoch 7, batch 32900, loss[loss=0.1367, simple_loss=0.208, pruned_loss=0.03264, over 4937.00 frames.], tot_loss[loss=0.1446, simple_loss=0.216, pruned_loss=0.03653, over 971948.14 frames.], batch size: 21, lr: 2.84e-04
+2022-05-06 00:55:48,470 INFO [train.py:715] (3/8) Epoch 7, batch 32950, loss[loss=0.1434, simple_loss=0.2052, pruned_loss=0.04079, over 4841.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2172, pruned_loss=0.03725, over 972608.95 frames.], batch size: 15, lr: 2.84e-04
+2022-05-06 00:56:28,430 INFO [train.py:715] (3/8) Epoch 7, batch 33000, loss[loss=0.1404, simple_loss=0.2089, pruned_loss=0.03593, over 4755.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2171, pruned_loss=0.03732, over 971966.34 frames.], batch size: 19, lr: 2.84e-04
+2022-05-06 00:56:28,431 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 00:56:38,008 INFO [train.py:742] (3/8) Epoch 7, validation: loss=0.108, simple_loss=0.1927, pruned_loss=0.01164, over 914524.00 frames.
+2022-05-06 00:57:17,518 INFO [train.py:715] (3/8) Epoch 7, batch 33050, loss[loss=0.1518, simple_loss=0.224, pruned_loss=0.03985, over 4769.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2168, pruned_loss=0.03716, over 971704.35 frames.], batch size: 12, lr: 2.84e-04
+2022-05-06 00:57:57,502 INFO [train.py:715] (3/8) Epoch 7, batch 33100, loss[loss=0.1748, simple_loss=0.2438, pruned_loss=0.05297, over 4880.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2171, pruned_loss=0.03717, over 972712.37 frames.], batch size: 17, lr: 2.84e-04
+2022-05-06 00:58:36,953 INFO [train.py:715] (3/8) Epoch 7, batch 33150, loss[loss=0.1239, simple_loss=0.1947, pruned_loss=0.02653, over 4974.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2162, pruned_loss=0.03647, over 972778.46 frames.], batch size: 35, lr: 2.84e-04
+2022-05-06 00:59:16,723 INFO [train.py:715] (3/8) Epoch 7, batch 33200, loss[loss=0.1276, simple_loss=0.1984, pruned_loss=0.02843, over 4832.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2155, pruned_loss=0.03596, over 972625.31 frames.], batch size: 15, lr: 2.84e-04
+2022-05-06 00:59:56,295 INFO [train.py:715] (3/8) Epoch 7, batch 33250, loss[loss=0.1421, simple_loss=0.2086, pruned_loss=0.03778, over 4954.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.03626, over 972861.92 frames.], batch size: 15, lr: 2.84e-04
+2022-05-06 01:00:35,756 INFO [train.py:715] (3/8) Epoch 7, batch 33300, loss[loss=0.1362, simple_loss=0.2136, pruned_loss=0.02944, over 4783.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03614, over 973141.40 frames.], batch size: 18, lr: 2.84e-04
+2022-05-06 01:01:15,276 INFO [train.py:715] (3/8) Epoch 7, batch 33350, loss[loss=0.1287, simple_loss=0.2136, pruned_loss=0.02191, over 4896.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2158, pruned_loss=0.03574, over 972487.41 frames.], batch size: 19, lr: 2.84e-04
+2022-05-06 01:01:55,574 INFO [train.py:715] (3/8) Epoch 7, batch 33400, loss[loss=0.1406, simple_loss=0.2037, pruned_loss=0.03876, over 4979.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2168, pruned_loss=0.03604, over 972695.84 frames.], batch size: 15, lr: 2.84e-04
+2022-05-06 01:02:35,670 INFO [train.py:715] (3/8) Epoch 7, batch 33450, loss[loss=0.1586, simple_loss=0.2278, pruned_loss=0.04474, over 4914.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2169, pruned_loss=0.03606, over 972684.47 frames.], batch size: 17, lr: 2.84e-04
+2022-05-06 01:03:16,254 INFO [train.py:715] (3/8) Epoch 7, batch 33500, loss[loss=0.1538, simple_loss=0.2286, pruned_loss=0.03952, over 4961.00 frames.], tot_loss[loss=0.145, simple_loss=0.2175, pruned_loss=0.03625, over 971937.03 frames.], batch size: 24, lr: 2.84e-04
+2022-05-06 01:03:56,833 INFO [train.py:715] (3/8) Epoch 7, batch 33550, loss[loss=0.1225, simple_loss=0.1978, pruned_loss=0.02359, over 4765.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2175, pruned_loss=0.03663, over 973123.23 frames.], batch size: 14, lr: 2.84e-04
+2022-05-06 01:04:37,435 INFO [train.py:715] (3/8) Epoch 7, batch 33600, loss[loss=0.128, simple_loss=0.1968, pruned_loss=0.02963, over 4957.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2177, pruned_loss=0.0367, over 973236.35 frames.], batch size: 14, lr: 2.84e-04
+2022-05-06 01:05:17,936 INFO [train.py:715] (3/8) Epoch 7, batch 33650, loss[loss=0.1506, simple_loss=0.2138, pruned_loss=0.04374, over 4778.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2167, pruned_loss=0.03669, over 972261.18 frames.], batch size: 14, lr: 2.84e-04
+2022-05-06 01:05:57,809 INFO [train.py:715] (3/8) Epoch 7, batch 33700, loss[loss=0.1381, simple_loss=0.2054, pruned_loss=0.0354, over 4832.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03625, over 971594.55 frames.], batch size: 15, lr: 2.84e-04
+2022-05-06 01:06:37,962 INFO [train.py:715] (3/8) Epoch 7, batch 33750, loss[loss=0.1263, simple_loss=0.2027, pruned_loss=0.02493, over 4881.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2162, pruned_loss=0.03634, over 972077.91 frames.], batch size: 22, lr: 2.84e-04
+2022-05-06 01:07:17,445 INFO [train.py:715] (3/8) Epoch 7, batch 33800, loss[loss=0.1269, simple_loss=0.2081, pruned_loss=0.02287, over 4878.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03671, over 972203.12 frames.], batch size: 20, lr: 2.84e-04
+2022-05-06 01:07:58,048 INFO [train.py:715] (3/8) Epoch 7, batch 33850, loss[loss=0.122, simple_loss=0.1903, pruned_loss=0.02684, over 4780.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2163, pruned_loss=0.03633, over 972191.13 frames.], batch size: 17, lr: 2.84e-04
+2022-05-06 01:08:37,726 INFO [train.py:715] (3/8) Epoch 7, batch 33900, loss[loss=0.1494, simple_loss=0.222, pruned_loss=0.03836, over 4909.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03602, over 972286.08 frames.], batch size: 17, lr: 2.84e-04
+2022-05-06 01:09:17,828 INFO [train.py:715] (3/8) Epoch 7, batch 33950, loss[loss=0.1505, simple_loss=0.2231, pruned_loss=0.03896, over 4859.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03616, over 971917.28 frames.], batch size: 30, lr: 2.84e-04
+2022-05-06 01:09:57,287 INFO [train.py:715] (3/8) Epoch 7, batch 34000, loss[loss=0.1788, simple_loss=0.2402, pruned_loss=0.05869, over 4887.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03607, over 972711.97 frames.], batch size: 19, lr: 2.84e-04
+2022-05-06 01:10:37,474 INFO [train.py:715] (3/8) Epoch 7, batch 34050, loss[loss=0.1831, simple_loss=0.2467, pruned_loss=0.05972, over 4830.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2168, pruned_loss=0.03599, over 973280.18 frames.], batch size: 15, lr: 2.84e-04
+2022-05-06 01:11:17,479 INFO [train.py:715] (3/8) Epoch 7, batch 34100, loss[loss=0.1386, simple_loss=0.2069, pruned_loss=0.03511, over 4903.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2177, pruned_loss=0.037, over 972504.01 frames.], batch size: 19, lr: 2.83e-04
+2022-05-06 01:11:56,982 INFO [train.py:715] (3/8) Epoch 7, batch 34150, loss[loss=0.1451, simple_loss=0.2141, pruned_loss=0.03803, over 4885.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2171, pruned_loss=0.03695, over 971925.17 frames.], batch size: 32, lr: 2.83e-04
+2022-05-06 01:12:37,404 INFO [train.py:715] (3/8) Epoch 7, batch 34200, loss[loss=0.1608, simple_loss=0.2257, pruned_loss=0.04796, over 4959.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2171, pruned_loss=0.03696, over 971115.88 frames.], batch size: 15, lr: 2.83e-04
+2022-05-06 01:13:17,640 INFO [train.py:715] (3/8) Epoch 7, batch 34250, loss[loss=0.155, simple_loss=0.2223, pruned_loss=0.04382, over 4932.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2169, pruned_loss=0.03649, over 970704.98 frames.], batch size: 35, lr: 2.83e-04
+2022-05-06 01:13:58,298 INFO [train.py:715] (3/8) Epoch 7, batch 34300, loss[loss=0.1212, simple_loss=0.1984, pruned_loss=0.02201, over 4807.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03604, over 970390.78 frames.], batch size: 25, lr: 2.83e-04
+2022-05-06 01:14:38,118 INFO [train.py:715] (3/8) Epoch 7, batch 34350, loss[loss=0.1429, simple_loss=0.2103, pruned_loss=0.03778, over 4828.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2161, pruned_loss=0.03632, over 971114.81 frames.], batch size: 13, lr: 2.83e-04
+2022-05-06 01:15:18,246 INFO [train.py:715] (3/8) Epoch 7, batch 34400, loss[loss=0.1301, simple_loss=0.2053, pruned_loss=0.0275, over 4880.00 frames.], tot_loss[loss=0.1432, simple_loss=0.215, pruned_loss=0.03565, over 971538.73 frames.], batch size: 22, lr: 2.83e-04
+2022-05-06 01:15:58,918 INFO [train.py:715] (3/8) Epoch 7, batch 34450, loss[loss=0.1339, simple_loss=0.2009, pruned_loss=0.03344, over 4847.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2162, pruned_loss=0.03623, over 971584.49 frames.], batch size: 32, lr: 2.83e-04
+2022-05-06 01:16:38,146 INFO [train.py:715] (3/8) Epoch 7, batch 34500, loss[loss=0.1398, simple_loss=0.2171, pruned_loss=0.0312, over 4976.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2167, pruned_loss=0.03625, over 971740.90 frames.], batch size: 15, lr: 2.83e-04
+2022-05-06 01:17:18,211 INFO [train.py:715] (3/8) Epoch 7, batch 34550, loss[loss=0.1544, simple_loss=0.2339, pruned_loss=0.03744, over 4928.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03573, over 971843.60 frames.], batch size: 23, lr: 2.83e-04
+2022-05-06 01:17:58,849 INFO [train.py:715] (3/8) Epoch 7, batch 34600, loss[loss=0.1455, simple_loss=0.2177, pruned_loss=0.03666, over 4941.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.03646, over 972673.93 frames.], batch size: 21, lr: 2.83e-04
+2022-05-06 01:18:38,815 INFO [train.py:715] (3/8) Epoch 7, batch 34650, loss[loss=0.1297, simple_loss=0.2082, pruned_loss=0.02559, over 4801.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2179, pruned_loss=0.03691, over 972611.05 frames.], batch size: 14, lr: 2.83e-04
+2022-05-06 01:19:19,025 INFO [train.py:715] (3/8) Epoch 7, batch 34700, loss[loss=0.1384, simple_loss=0.2055, pruned_loss=0.03564, over 4934.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2178, pruned_loss=0.03684, over 972341.58 frames.], batch size: 21, lr: 2.83e-04
+2022-05-06 01:19:57,502 INFO [train.py:715] (3/8) Epoch 7, batch 34750, loss[loss=0.1441, simple_loss=0.2228, pruned_loss=0.03269, over 4923.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2177, pruned_loss=0.03684, over 972614.21 frames.], batch size: 23, lr: 2.83e-04
+2022-05-06 01:20:35,931 INFO [train.py:715] (3/8) Epoch 7, batch 34800, loss[loss=0.1352, simple_loss=0.1988, pruned_loss=0.03585, over 4762.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2158, pruned_loss=0.03619, over 972075.72 frames.], batch size: 12, lr: 2.83e-04
+2022-05-06 01:21:27,012 INFO [train.py:715] (3/8) Epoch 8, batch 0, loss[loss=0.1675, simple_loss=0.2472, pruned_loss=0.04389, over 4926.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2472, pruned_loss=0.04389, over 4926.00 frames.], batch size: 29, lr: 2.69e-04
+2022-05-06 01:22:06,297 INFO [train.py:715] (3/8) Epoch 8, batch 50, loss[loss=0.1488, simple_loss=0.2167, pruned_loss=0.04043, over 4752.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2196, pruned_loss=0.03743, over 218915.81 frames.], batch size: 19, lr: 2.69e-04
+2022-05-06 01:22:47,064 INFO [train.py:715] (3/8) Epoch 8, batch 100, loss[loss=0.1462, simple_loss=0.2186, pruned_loss=0.0369, over 4737.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03742, over 386209.62 frames.], batch size: 16, lr: 2.69e-04
+2022-05-06 01:23:26,802 INFO [train.py:715] (3/8) Epoch 8, batch 150, loss[loss=0.1475, simple_loss=0.2195, pruned_loss=0.03775, over 4784.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03651, over 516004.48 frames.], batch size: 18, lr: 2.69e-04
+2022-05-06 01:24:07,304 INFO [train.py:715] (3/8) Epoch 8, batch 200, loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03064, over 4963.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03601, over 616788.43 frames.], batch size: 24, lr: 2.69e-04
+2022-05-06 01:24:47,114 INFO [train.py:715] (3/8) Epoch 8, batch 250, loss[loss=0.1394, simple_loss=0.2205, pruned_loss=0.02915, over 4964.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2161, pruned_loss=0.0355, over 695607.39 frames.], batch size: 24, lr: 2.69e-04
+2022-05-06 01:25:27,373 INFO [train.py:715] (3/8) Epoch 8, batch 300, loss[loss=0.1191, simple_loss=0.1896, pruned_loss=0.02433, over 4976.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03576, over 757072.52 frames.], batch size: 28, lr: 2.69e-04
+2022-05-06 01:26:07,153 INFO [train.py:715] (3/8) Epoch 8, batch 350, loss[loss=0.1418, simple_loss=0.2043, pruned_loss=0.0397, over 4774.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2149, pruned_loss=0.03549, over 804563.93 frames.], batch size: 14, lr: 2.69e-04
+2022-05-06 01:26:46,035 INFO [train.py:715] (3/8) Epoch 8, batch 400, loss[loss=0.1423, simple_loss=0.217, pruned_loss=0.03382, over 4814.00 frames.], tot_loss[loss=0.144, simple_loss=0.2158, pruned_loss=0.0361, over 842296.14 frames.], batch size: 25, lr: 2.69e-04
+2022-05-06 01:27:26,632 INFO [train.py:715] (3/8) Epoch 8, batch 450, loss[loss=0.1387, simple_loss=0.21, pruned_loss=0.03369, over 4660.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2151, pruned_loss=0.03528, over 870878.75 frames.], batch size: 13, lr: 2.69e-04
+2022-05-06 01:28:06,605 INFO [train.py:715] (3/8) Epoch 8, batch 500, loss[loss=0.1564, simple_loss=0.2335, pruned_loss=0.03962, over 4933.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03514, over 892757.83 frames.], batch size: 21, lr: 2.69e-04
+2022-05-06 01:28:47,245 INFO [train.py:715] (3/8) Epoch 8, batch 550, loss[loss=0.1563, simple_loss=0.2275, pruned_loss=0.04257, over 4818.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03582, over 909713.66 frames.], batch size: 13, lr: 2.69e-04
+2022-05-06 01:29:26,912 INFO [train.py:715] (3/8) Epoch 8, batch 600, loss[loss=0.1437, simple_loss=0.2173, pruned_loss=0.03512, over 4771.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03514, over 923528.97 frames.], batch size: 17, lr: 2.69e-04
+2022-05-06 01:30:07,133 INFO [train.py:715] (3/8) Epoch 8, batch 650, loss[loss=0.1158, simple_loss=0.191, pruned_loss=0.02026, over 4856.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2146, pruned_loss=0.0352, over 934898.74 frames.], batch size: 15, lr: 2.68e-04
+2022-05-06 01:30:47,386 INFO [train.py:715] (3/8) Epoch 8, batch 700, loss[loss=0.1591, simple_loss=0.2245, pruned_loss=0.0468, over 4754.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2154, pruned_loss=0.03557, over 943951.63 frames.], batch size: 18, lr: 2.68e-04
+2022-05-06 01:31:27,083 INFO [train.py:715] (3/8) Epoch 8, batch 750, loss[loss=0.1263, simple_loss=0.2001, pruned_loss=0.0263, over 4750.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.03566, over 950217.55 frames.], batch size: 16, lr: 2.68e-04
+2022-05-06 01:32:07,144 INFO [train.py:715] (3/8) Epoch 8, batch 800, loss[loss=0.1598, simple_loss=0.2344, pruned_loss=0.04259, over 4862.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.0358, over 955924.59 frames.], batch size: 16, lr: 2.68e-04
+2022-05-06 01:32:47,135 INFO [train.py:715] (3/8) Epoch 8, batch 850, loss[loss=0.152, simple_loss=0.2156, pruned_loss=0.04418, over 4796.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.03608, over 959697.65 frames.], batch size: 24, lr: 2.68e-04
+2022-05-06 01:33:28,548 INFO [train.py:715] (3/8) Epoch 8, batch 900, loss[loss=0.1351, simple_loss=0.2106, pruned_loss=0.0298, over 4797.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03561, over 961732.92 frames.], batch size: 21, lr: 2.68e-04
+2022-05-06 01:34:08,657 INFO [train.py:715] (3/8) Epoch 8, batch 950, loss[loss=0.1456, simple_loss=0.2093, pruned_loss=0.04094, over 4904.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2155, pruned_loss=0.03601, over 963498.99 frames.], batch size: 19, lr: 2.68e-04
+2022-05-06 01:34:49,699 INFO [train.py:715] (3/8) Epoch 8, batch 1000, loss[loss=0.1566, simple_loss=0.2256, pruned_loss=0.04376, over 4965.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2158, pruned_loss=0.03647, over 966477.10 frames.], batch size: 39, lr: 2.68e-04
+2022-05-06 01:35:30,786 INFO [train.py:715] (3/8) Epoch 8, batch 1050, loss[loss=0.1529, simple_loss=0.2317, pruned_loss=0.03707, over 4932.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2163, pruned_loss=0.03636, over 967671.98 frames.], batch size: 18, lr: 2.68e-04
+2022-05-06 01:36:11,906 INFO [train.py:715] (3/8) Epoch 8, batch 1100, loss[loss=0.1311, simple_loss=0.2098, pruned_loss=0.02621, over 4789.00 frames.], tot_loss[loss=0.1445, simple_loss=0.216, pruned_loss=0.03649, over 968257.36 frames.], batch size: 21, lr: 2.68e-04
+2022-05-06 01:36:52,404 INFO [train.py:715] (3/8) Epoch 8, batch 1150, loss[loss=0.1326, simple_loss=0.2007, pruned_loss=0.03223, over 4933.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2157, pruned_loss=0.03643, over 969462.93 frames.], batch size: 23, lr: 2.68e-04
+2022-05-06 01:37:33,429 INFO [train.py:715] (3/8) Epoch 8, batch 1200, loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03075, over 4963.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03599, over 970549.57 frames.], batch size: 15, lr: 2.68e-04
+2022-05-06 01:38:14,755 INFO [train.py:715] (3/8) Epoch 8, batch 1250, loss[loss=0.1435, simple_loss=0.2156, pruned_loss=0.03567, over 4877.00 frames.], tot_loss[loss=0.1442, simple_loss=0.216, pruned_loss=0.03621, over 970587.98 frames.], batch size: 22, lr: 2.68e-04
+2022-05-06 01:38:55,093 INFO [train.py:715] (3/8) Epoch 8, batch 1300, loss[loss=0.1501, simple_loss=0.2205, pruned_loss=0.03982, over 4905.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2161, pruned_loss=0.03613, over 971154.64 frames.], batch size: 17, lr: 2.68e-04
+2022-05-06 01:39:36,452 INFO [train.py:715] (3/8) Epoch 8, batch 1350, loss[loss=0.1679, simple_loss=0.2305, pruned_loss=0.05269, over 4972.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2158, pruned_loss=0.03615, over 971966.46 frames.], batch size: 15, lr: 2.68e-04
+2022-05-06 01:40:17,099 INFO [train.py:715] (3/8) Epoch 8, batch 1400, loss[loss=0.1425, simple_loss=0.2152, pruned_loss=0.03495, over 4945.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2158, pruned_loss=0.03622, over 971983.38 frames.], batch size: 18, lr: 2.68e-04
+2022-05-06 01:40:57,934 INFO [train.py:715] (3/8) Epoch 8, batch 1450, loss[loss=0.1537, simple_loss=0.2166, pruned_loss=0.04534, over 4845.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2163, pruned_loss=0.03671, over 972048.32 frames.], batch size: 32, lr: 2.68e-04
+2022-05-06 01:41:37,779 INFO [train.py:715] (3/8) Epoch 8, batch 1500, loss[loss=0.1574, simple_loss=0.2208, pruned_loss=0.04697, over 4746.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2167, pruned_loss=0.03683, over 972370.72 frames.], batch size: 16, lr: 2.68e-04
+2022-05-06 01:42:20,412 INFO [train.py:715] (3/8) Epoch 8, batch 1550, loss[loss=0.1714, simple_loss=0.2459, pruned_loss=0.04847, over 4751.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2181, pruned_loss=0.03758, over 972937.54 frames.], batch size: 16, lr: 2.68e-04
+2022-05-06 01:43:00,533 INFO [train.py:715] (3/8) Epoch 8, batch 1600, loss[loss=0.1652, simple_loss=0.2385, pruned_loss=0.04597, over 4745.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2176, pruned_loss=0.03726, over 972344.39 frames.], batch size: 16, lr: 2.68e-04
+2022-05-06 01:43:39,975 INFO [train.py:715] (3/8) Epoch 8, batch 1650, loss[loss=0.1476, simple_loss=0.2073, pruned_loss=0.044, over 4746.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03693, over 972471.55 frames.], batch size: 16, lr: 2.68e-04
+2022-05-06 01:44:20,195 INFO [train.py:715] (3/8) Epoch 8, batch 1700, loss[loss=0.141, simple_loss=0.209, pruned_loss=0.0365, over 4844.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03677, over 971959.69 frames.], batch size: 15, lr: 2.68e-04
+2022-05-06 01:44:59,608 INFO [train.py:715] (3/8) Epoch 8, batch 1750, loss[loss=0.1486, simple_loss=0.2124, pruned_loss=0.04242, over 4979.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.03655, over 971545.98 frames.], batch size: 15, lr: 2.68e-04
+2022-05-06 01:45:39,056 INFO [train.py:715] (3/8) Epoch 8, batch 1800, loss[loss=0.144, simple_loss=0.2139, pruned_loss=0.03703, over 4946.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2172, pruned_loss=0.03694, over 971299.80 frames.], batch size: 23, lr: 2.68e-04
+2022-05-06 01:46:18,116 INFO [train.py:715] (3/8) Epoch 8, batch 1850, loss[loss=0.1131, simple_loss=0.1942, pruned_loss=0.01596, over 4897.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2166, pruned_loss=0.03676, over 971830.06 frames.], batch size: 19, lr: 2.68e-04
+2022-05-06 01:46:57,512 INFO [train.py:715] (3/8) Epoch 8, batch 1900, loss[loss=0.1714, simple_loss=0.243, pruned_loss=0.04988, over 4911.00 frames.], tot_loss[loss=0.1466, simple_loss=0.218, pruned_loss=0.03756, over 972352.82 frames.], batch size: 18, lr: 2.68e-04
+2022-05-06 01:47:37,013 INFO [train.py:715] (3/8) Epoch 8, batch 1950, loss[loss=0.183, simple_loss=0.245, pruned_loss=0.06046, over 4945.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2182, pruned_loss=0.03808, over 972939.68 frames.], batch size: 35, lr: 2.68e-04
+2022-05-06 01:48:16,134 INFO [train.py:715] (3/8) Epoch 8, batch 2000, loss[loss=0.1152, simple_loss=0.1882, pruned_loss=0.02109, over 4926.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2181, pruned_loss=0.03749, over 972994.97 frames.], batch size: 23, lr: 2.68e-04
+2022-05-06 01:48:56,148 INFO [train.py:715] (3/8) Epoch 8, batch 2050, loss[loss=0.1168, simple_loss=0.1936, pruned_loss=0.01998, over 4984.00 frames.], tot_loss[loss=0.1453, simple_loss=0.217, pruned_loss=0.03681, over 974006.86 frames.], batch size: 25, lr: 2.68e-04
+2022-05-06 01:49:35,102 INFO [train.py:715] (3/8) Epoch 8, batch 2100, loss[loss=0.1332, simple_loss=0.2087, pruned_loss=0.02881, over 4978.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2162, pruned_loss=0.03638, over 973663.14 frames.], batch size: 15, lr: 2.68e-04
+2022-05-06 01:50:14,046 INFO [train.py:715] (3/8) Epoch 8, batch 2150, loss[loss=0.1448, simple_loss=0.2282, pruned_loss=0.03065, over 4968.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2158, pruned_loss=0.03623, over 972894.19 frames.], batch size: 15, lr: 2.68e-04
+2022-05-06 01:50:53,035 INFO [train.py:715] (3/8) Epoch 8, batch 2200, loss[loss=0.1486, simple_loss=0.2159, pruned_loss=0.04069, over 4858.00 frames.], tot_loss[loss=0.1444, simple_loss=0.216, pruned_loss=0.03641, over 972343.83 frames.], batch size: 32, lr: 2.68e-04
+2022-05-06 01:51:32,661 INFO [train.py:715] (3/8) Epoch 8, batch 2250, loss[loss=0.15, simple_loss=0.2251, pruned_loss=0.03752, over 4977.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2166, pruned_loss=0.03683, over 972892.60 frames.], batch size: 25, lr: 2.68e-04
+2022-05-06 01:52:12,077 INFO [train.py:715] (3/8) Epoch 8, batch 2300, loss[loss=0.1215, simple_loss=0.1923, pruned_loss=0.02534, over 4980.00 frames.], tot_loss[loss=0.1445, simple_loss=0.216, pruned_loss=0.03648, over 972756.38 frames.], batch size: 39, lr: 2.68e-04
+2022-05-06 01:52:50,788 INFO [train.py:715] (3/8) Epoch 8, batch 2350, loss[loss=0.1397, simple_loss=0.2159, pruned_loss=0.03178, over 4945.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2159, pruned_loss=0.0362, over 972810.71 frames.], batch size: 29, lr: 2.68e-04
+2022-05-06 01:53:30,841 INFO [train.py:715] (3/8) Epoch 8, batch 2400, loss[loss=0.1555, simple_loss=0.2189, pruned_loss=0.04599, over 4961.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2159, pruned_loss=0.03624, over 972499.06 frames.], batch size: 14, lr: 2.68e-04
+2022-05-06 01:54:10,338 INFO [train.py:715] (3/8) Epoch 8, batch 2450, loss[loss=0.1543, simple_loss=0.222, pruned_loss=0.04327, over 4866.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03694, over 973424.05 frames.], batch size: 32, lr: 2.68e-04
+2022-05-06 01:54:49,892 INFO [train.py:715] (3/8) Epoch 8, batch 2500, loss[loss=0.1473, simple_loss=0.2244, pruned_loss=0.03505, over 4933.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03611, over 972907.31 frames.], batch size: 23, lr: 2.68e-04
+2022-05-06 01:55:28,675 INFO [train.py:715] (3/8) Epoch 8, batch 2550, loss[loss=0.15, simple_loss=0.2192, pruned_loss=0.04037, over 4895.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2163, pruned_loss=0.03642, over 971934.14 frames.], batch size: 18, lr: 2.68e-04
+2022-05-06 01:56:08,304 INFO [train.py:715] (3/8) Epoch 8, batch 2600, loss[loss=0.1478, simple_loss=0.22, pruned_loss=0.03778, over 4949.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2167, pruned_loss=0.03674, over 972433.75 frames.], batch size: 21, lr: 2.68e-04
+2022-05-06 01:56:47,550 INFO [train.py:715] (3/8) Epoch 8, batch 2650, loss[loss=0.1557, simple_loss=0.2211, pruned_loss=0.04517, over 4950.00 frames.], tot_loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.03652, over 973089.95 frames.], batch size: 24, lr: 2.68e-04
+2022-05-06 01:57:27,030 INFO [train.py:715] (3/8) Epoch 8, batch 2700, loss[loss=0.1576, simple_loss=0.2327, pruned_loss=0.04122, over 4768.00 frames.], tot_loss[loss=0.145, simple_loss=0.2172, pruned_loss=0.03636, over 972848.92 frames.], batch size: 14, lr: 2.68e-04
+2022-05-06 01:58:06,373 INFO [train.py:715] (3/8) Epoch 8, batch 2750, loss[loss=0.1343, simple_loss=0.1937, pruned_loss=0.03751, over 4961.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03598, over 972883.55 frames.], batch size: 15, lr: 2.67e-04
+2022-05-06 01:58:45,749 INFO [train.py:715] (3/8) Epoch 8, batch 2800, loss[loss=0.1404, simple_loss=0.2006, pruned_loss=0.04015, over 4788.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03611, over 973265.46 frames.], batch size: 14, lr: 2.67e-04
+2022-05-06 01:59:24,996 INFO [train.py:715] (3/8) Epoch 8, batch 2850, loss[loss=0.1264, simple_loss=0.1988, pruned_loss=0.027, over 4781.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03574, over 974354.39 frames.], batch size: 18, lr: 2.67e-04
+2022-05-06 02:00:03,843 INFO [train.py:715] (3/8) Epoch 8, batch 2900, loss[loss=0.1285, simple_loss=0.1975, pruned_loss=0.02982, over 4834.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03553, over 973682.91 frames.], batch size: 15, lr: 2.67e-04
+2022-05-06 02:00:43,805 INFO [train.py:715] (3/8) Epoch 8, batch 2950, loss[loss=0.1475, simple_loss=0.2207, pruned_loss=0.03721, over 4977.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03556, over 973090.25 frames.], batch size: 35, lr: 2.67e-04
+2022-05-06 02:01:22,466 INFO [train.py:715] (3/8) Epoch 8, batch 3000, loss[loss=0.1412, simple_loss=0.2103, pruned_loss=0.03608, over 4828.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03544, over 972543.40 frames.], batch size: 12, lr: 2.67e-04
+2022-05-06 02:01:22,466 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 02:01:32,129 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1076, simple_loss=0.1923, pruned_loss=0.0115, over 914524.00 frames.
+2022-05-06 02:02:11,365 INFO [train.py:715] (3/8) Epoch 8, batch 3050, loss[loss=0.1406, simple_loss=0.2146, pruned_loss=0.03325, over 4902.00 frames.], tot_loss[loss=0.143, simple_loss=0.2157, pruned_loss=0.03516, over 972147.47 frames.], batch size: 19, lr: 2.67e-04
+2022-05-06 02:02:50,370 INFO [train.py:715] (3/8) Epoch 8, batch 3100, loss[loss=0.1254, simple_loss=0.2021, pruned_loss=0.02433, over 4914.00 frames.], tot_loss[loss=0.144, simple_loss=0.2167, pruned_loss=0.03562, over 972325.92 frames.], batch size: 18, lr: 2.67e-04
+2022-05-06 02:03:29,323 INFO [train.py:715] (3/8) Epoch 8, batch 3150, loss[loss=0.1565, simple_loss=0.2363, pruned_loss=0.03837, over 4827.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2168, pruned_loss=0.03571, over 972266.49 frames.], batch size: 15, lr: 2.67e-04
+2022-05-06 02:04:09,031 INFO [train.py:715] (3/8) Epoch 8, batch 3200, loss[loss=0.1494, simple_loss=0.2212, pruned_loss=0.03874, over 4968.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2179, pruned_loss=0.03597, over 972155.94 frames.], batch size: 35, lr: 2.67e-04
+2022-05-06 02:04:48,447 INFO [train.py:715] (3/8) Epoch 8, batch 3250, loss[loss=0.1383, simple_loss=0.2039, pruned_loss=0.03637, over 4898.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2169, pruned_loss=0.03592, over 973051.49 frames.], batch size: 19, lr: 2.67e-04
+2022-05-06 02:05:28,481 INFO [train.py:715] (3/8) Epoch 8, batch 3300, loss[loss=0.1332, simple_loss=0.2066, pruned_loss=0.02994, over 4917.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2169, pruned_loss=0.03576, over 973385.11 frames.], batch size: 17, lr: 2.67e-04
+2022-05-06 02:06:08,844 INFO [train.py:715] (3/8) Epoch 8, batch 3350, loss[loss=0.1777, simple_loss=0.2243, pruned_loss=0.06557, over 4785.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03507, over 972676.82 frames.], batch size: 12, lr: 2.67e-04
+2022-05-06 02:06:49,937 INFO [train.py:715] (3/8) Epoch 8, batch 3400, loss[loss=0.1284, simple_loss=0.1917, pruned_loss=0.03258, over 4774.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.03568, over 972927.13 frames.], batch size: 18, lr: 2.67e-04
+2022-05-06 02:07:30,801 INFO [train.py:715] (3/8) Epoch 8, batch 3450, loss[loss=0.1209, simple_loss=0.1998, pruned_loss=0.02103, over 4841.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.03563, over 972302.76 frames.], batch size: 26, lr: 2.67e-04
+2022-05-06 02:08:11,009 INFO [train.py:715] (3/8) Epoch 8, batch 3500, loss[loss=0.1624, simple_loss=0.2366, pruned_loss=0.04413, over 4852.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2175, pruned_loss=0.03633, over 971453.65 frames.], batch size: 20, lr: 2.67e-04
+2022-05-06 02:08:52,348 INFO [train.py:715] (3/8) Epoch 8, batch 3550, loss[loss=0.117, simple_loss=0.1922, pruned_loss=0.02095, over 4980.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2174, pruned_loss=0.03592, over 972198.94 frames.], batch size: 28, lr: 2.67e-04
+2022-05-06 02:09:33,205 INFO [train.py:715] (3/8) Epoch 8, batch 3600, loss[loss=0.1317, simple_loss=0.2038, pruned_loss=0.02977, over 4812.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2159, pruned_loss=0.03543, over 972151.72 frames.], batch size: 21, lr: 2.67e-04
+2022-05-06 02:10:13,456 INFO [train.py:715] (3/8) Epoch 8, batch 3650, loss[loss=0.1222, simple_loss=0.1981, pruned_loss=0.02311, over 4929.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03529, over 972709.50 frames.], batch size: 21, lr: 2.67e-04
+2022-05-06 02:10:53,935 INFO [train.py:715] (3/8) Epoch 8, batch 3700, loss[loss=0.1298, simple_loss=0.2024, pruned_loss=0.02858, over 4908.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2146, pruned_loss=0.03533, over 972587.55 frames.], batch size: 18, lr: 2.67e-04
+2022-05-06 02:11:34,280 INFO [train.py:715] (3/8) Epoch 8, batch 3750, loss[loss=0.1252, simple_loss=0.1841, pruned_loss=0.03317, over 4966.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2147, pruned_loss=0.03536, over 972357.65 frames.], batch size: 14, lr: 2.67e-04
+2022-05-06 02:12:13,644 INFO [train.py:715] (3/8) Epoch 8, batch 3800, loss[loss=0.1156, simple_loss=0.1874, pruned_loss=0.02192, over 4985.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2152, pruned_loss=0.03562, over 973203.21 frames.], batch size: 28, lr: 2.67e-04
+2022-05-06 02:12:54,034 INFO [train.py:715] (3/8) Epoch 8, batch 3850, loss[loss=0.1268, simple_loss=0.1946, pruned_loss=0.02948, over 4967.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2144, pruned_loss=0.03538, over 973475.77 frames.], batch size: 24, lr: 2.67e-04
+2022-05-06 02:13:34,223 INFO [train.py:715] (3/8) Epoch 8, batch 3900, loss[loss=0.1405, simple_loss=0.2126, pruned_loss=0.03419, over 4974.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03587, over 973223.23 frames.], batch size: 24, lr: 2.67e-04
+2022-05-06 02:14:14,990 INFO [train.py:715] (3/8) Epoch 8, batch 3950, loss[loss=0.1503, simple_loss=0.2069, pruned_loss=0.04689, over 4937.00 frames.], tot_loss[loss=0.1437, simple_loss=0.215, pruned_loss=0.03618, over 973088.52 frames.], batch size: 23, lr: 2.67e-04
+2022-05-06 02:14:54,903 INFO [train.py:715] (3/8) Epoch 8, batch 4000, loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02938, over 4936.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2149, pruned_loss=0.03576, over 972539.52 frames.], batch size: 35, lr: 2.67e-04
+2022-05-06 02:15:35,359 INFO [train.py:715] (3/8) Epoch 8, batch 4050, loss[loss=0.1273, simple_loss=0.1937, pruned_loss=0.03046, over 4913.00 frames.], tot_loss[loss=0.144, simple_loss=0.2157, pruned_loss=0.03613, over 972766.69 frames.], batch size: 23, lr: 2.67e-04
+2022-05-06 02:16:16,174 INFO [train.py:715] (3/8) Epoch 8, batch 4100, loss[loss=0.1333, simple_loss=0.2052, pruned_loss=0.0307, over 4922.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2159, pruned_loss=0.03632, over 972818.22 frames.], batch size: 23, lr: 2.67e-04
+2022-05-06 02:16:55,925 INFO [train.py:715] (3/8) Epoch 8, batch 4150, loss[loss=0.1208, simple_loss=0.2068, pruned_loss=0.01745, over 4883.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2156, pruned_loss=0.03633, over 972397.38 frames.], batch size: 16, lr: 2.67e-04
+2022-05-06 02:17:35,660 INFO [train.py:715] (3/8) Epoch 8, batch 4200, loss[loss=0.1641, simple_loss=0.2257, pruned_loss=0.05123, over 4839.00 frames.], tot_loss[loss=0.143, simple_loss=0.2148, pruned_loss=0.03563, over 972820.87 frames.], batch size: 30, lr: 2.67e-04
+2022-05-06 02:18:15,234 INFO [train.py:715] (3/8) Epoch 8, batch 4250, loss[loss=0.1439, simple_loss=0.2226, pruned_loss=0.03257, over 4991.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2143, pruned_loss=0.0357, over 972869.09 frames.], batch size: 20, lr: 2.67e-04
+2022-05-06 02:18:54,986 INFO [train.py:715] (3/8) Epoch 8, batch 4300, loss[loss=0.129, simple_loss=0.2027, pruned_loss=0.02761, over 4995.00 frames.], tot_loss[loss=0.143, simple_loss=0.215, pruned_loss=0.03547, over 972621.00 frames.], batch size: 14, lr: 2.67e-04
+2022-05-06 02:19:34,151 INFO [train.py:715] (3/8) Epoch 8, batch 4350, loss[loss=0.1314, simple_loss=0.2108, pruned_loss=0.02606, over 4784.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.036, over 973097.83 frames.], batch size: 17, lr: 2.67e-04
+2022-05-06 02:20:13,543 INFO [train.py:715] (3/8) Epoch 8, batch 4400, loss[loss=0.154, simple_loss=0.2299, pruned_loss=0.03902, over 4861.00 frames.], tot_loss[loss=0.145, simple_loss=0.2168, pruned_loss=0.03658, over 972642.85 frames.], batch size: 22, lr: 2.67e-04
+2022-05-06 02:20:53,463 INFO [train.py:715] (3/8) Epoch 8, batch 4450, loss[loss=0.15, simple_loss=0.219, pruned_loss=0.04046, over 4966.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2157, pruned_loss=0.03608, over 972329.51 frames.], batch size: 15, lr: 2.67e-04
+2022-05-06 02:21:33,238 INFO [train.py:715] (3/8) Epoch 8, batch 4500, loss[loss=0.1213, simple_loss=0.1932, pruned_loss=0.02473, over 4837.00 frames.], tot_loss[loss=0.1441, simple_loss=0.216, pruned_loss=0.03611, over 971750.78 frames.], batch size: 30, lr: 2.67e-04
+2022-05-06 02:22:12,202 INFO [train.py:715] (3/8) Epoch 8, batch 4550, loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02975, over 4907.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.03592, over 971881.58 frames.], batch size: 17, lr: 2.67e-04
+2022-05-06 02:22:52,185 INFO [train.py:715] (3/8) Epoch 8, batch 4600, loss[loss=0.1932, simple_loss=0.2537, pruned_loss=0.06639, over 4696.00 frames.], tot_loss[loss=0.1442, simple_loss=0.216, pruned_loss=0.03616, over 971879.90 frames.], batch size: 15, lr: 2.67e-04
+2022-05-06 02:23:31,720 INFO [train.py:715] (3/8) Epoch 8, batch 4650, loss[loss=0.1568, simple_loss=0.2376, pruned_loss=0.03798, over 4756.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03576, over 971688.41 frames.], batch size: 19, lr: 2.67e-04
+2022-05-06 02:24:11,300 INFO [train.py:715] (3/8) Epoch 8, batch 4700, loss[loss=0.1388, simple_loss=0.2033, pruned_loss=0.0371, over 4778.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03602, over 972340.36 frames.], batch size: 12, lr: 2.67e-04
+2022-05-06 02:24:50,830 INFO [train.py:715] (3/8) Epoch 8, batch 4750, loss[loss=0.1301, simple_loss=0.199, pruned_loss=0.03059, over 4872.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03593, over 972237.06 frames.], batch size: 16, lr: 2.67e-04
+2022-05-06 02:25:30,490 INFO [train.py:715] (3/8) Epoch 8, batch 4800, loss[loss=0.102, simple_loss=0.1713, pruned_loss=0.01634, over 4769.00 frames.], tot_loss[loss=0.1434, simple_loss=0.215, pruned_loss=0.03591, over 971647.00 frames.], batch size: 12, lr: 2.67e-04
+2022-05-06 02:26:10,388 INFO [train.py:715] (3/8) Epoch 8, batch 4850, loss[loss=0.1181, simple_loss=0.18, pruned_loss=0.02806, over 4785.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2152, pruned_loss=0.03631, over 972290.66 frames.], batch size: 14, lr: 2.66e-04
+2022-05-06 02:26:49,519 INFO [train.py:715] (3/8) Epoch 8, batch 4900, loss[loss=0.1647, simple_loss=0.2486, pruned_loss=0.04041, over 4897.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2155, pruned_loss=0.03639, over 972321.80 frames.], batch size: 19, lr: 2.66e-04
+2022-05-06 02:27:29,277 INFO [train.py:715] (3/8) Epoch 8, batch 4950, loss[loss=0.1516, simple_loss=0.2253, pruned_loss=0.03897, over 4924.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2155, pruned_loss=0.03654, over 972421.70 frames.], batch size: 23, lr: 2.66e-04
+2022-05-06 02:28:08,940 INFO [train.py:715] (3/8) Epoch 8, batch 5000, loss[loss=0.1263, simple_loss=0.1984, pruned_loss=0.02713, over 4933.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2157, pruned_loss=0.03639, over 971621.69 frames.], batch size: 23, lr: 2.66e-04
+2022-05-06 02:28:47,812 INFO [train.py:715] (3/8) Epoch 8, batch 5050, loss[loss=0.158, simple_loss=0.2214, pruned_loss=0.04734, over 4768.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03637, over 971625.49 frames.], batch size: 14, lr: 2.66e-04
+2022-05-06 02:29:26,960 INFO [train.py:715] (3/8) Epoch 8, batch 5100, loss[loss=0.1382, simple_loss=0.2124, pruned_loss=0.03196, over 4826.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.0362, over 971965.99 frames.], batch size: 26, lr: 2.66e-04
+2022-05-06 02:30:06,424 INFO [train.py:715] (3/8) Epoch 8, batch 5150, loss[loss=0.1529, simple_loss=0.2184, pruned_loss=0.04371, over 4922.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.0359, over 972539.51 frames.], batch size: 23, lr: 2.66e-04
+2022-05-06 02:30:45,328 INFO [train.py:715] (3/8) Epoch 8, batch 5200, loss[loss=0.139, simple_loss=0.2098, pruned_loss=0.03416, over 4877.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2168, pruned_loss=0.03595, over 973348.37 frames.], batch size: 32, lr: 2.66e-04
+2022-05-06 02:31:24,026 INFO [train.py:715] (3/8) Epoch 8, batch 5250, loss[loss=0.2115, simple_loss=0.2817, pruned_loss=0.0707, over 4821.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2172, pruned_loss=0.03617, over 973425.93 frames.], batch size: 15, lr: 2.66e-04
+2022-05-06 02:32:04,133 INFO [train.py:715] (3/8) Epoch 8, batch 5300, loss[loss=0.1322, simple_loss=0.2012, pruned_loss=0.03158, over 4981.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2175, pruned_loss=0.03646, over 972762.44 frames.], batch size: 28, lr: 2.66e-04
+2022-05-06 02:32:43,757 INFO [train.py:715] (3/8) Epoch 8, batch 5350, loss[loss=0.1208, simple_loss=0.1891, pruned_loss=0.02626, over 4810.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2169, pruned_loss=0.0362, over 973349.77 frames.], batch size: 13, lr: 2.66e-04
+2022-05-06 02:33:23,694 INFO [train.py:715] (3/8) Epoch 8, batch 5400, loss[loss=0.1286, simple_loss=0.1962, pruned_loss=0.03044, over 4896.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2173, pruned_loss=0.03656, over 972331.93 frames.], batch size: 19, lr: 2.66e-04
+2022-05-06 02:34:04,180 INFO [train.py:715] (3/8) Epoch 8, batch 5450, loss[loss=0.1238, simple_loss=0.1901, pruned_loss=0.02874, over 4836.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03677, over 972754.13 frames.], batch size: 20, lr: 2.66e-04
+2022-05-06 02:34:44,675 INFO [train.py:715] (3/8) Epoch 8, batch 5500, loss[loss=0.1716, simple_loss=0.2319, pruned_loss=0.05565, over 4960.00 frames.], tot_loss[loss=0.1453, simple_loss=0.217, pruned_loss=0.0368, over 973080.28 frames.], batch size: 15, lr: 2.66e-04
+2022-05-06 02:35:24,969 INFO [train.py:715] (3/8) Epoch 8, batch 5550, loss[loss=0.1384, simple_loss=0.2099, pruned_loss=0.03349, over 4767.00 frames.], tot_loss[loss=0.1458, simple_loss=0.218, pruned_loss=0.03683, over 973156.47 frames.], batch size: 18, lr: 2.66e-04
+2022-05-06 02:36:04,809 INFO [train.py:715] (3/8) Epoch 8, batch 5600, loss[loss=0.1561, simple_loss=0.2179, pruned_loss=0.04718, over 4835.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.0364, over 972854.68 frames.], batch size: 15, lr: 2.66e-04
+2022-05-06 02:36:44,876 INFO [train.py:715] (3/8) Epoch 8, batch 5650, loss[loss=0.1525, simple_loss=0.2192, pruned_loss=0.04289, over 4804.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.03655, over 973111.11 frames.], batch size: 14, lr: 2.66e-04
+2022-05-06 02:37:24,000 INFO [train.py:715] (3/8) Epoch 8, batch 5700, loss[loss=0.157, simple_loss=0.2219, pruned_loss=0.04607, over 4969.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2179, pruned_loss=0.03665, over 973361.45 frames.], batch size: 35, lr: 2.66e-04
+2022-05-06 02:38:03,513 INFO [train.py:715] (3/8) Epoch 8, batch 5750, loss[loss=0.173, simple_loss=0.2372, pruned_loss=0.05437, over 4988.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2178, pruned_loss=0.03675, over 973574.32 frames.], batch size: 28, lr: 2.66e-04
+2022-05-06 02:38:42,300 INFO [train.py:715] (3/8) Epoch 8, batch 5800, loss[loss=0.1272, simple_loss=0.2066, pruned_loss=0.02388, over 4981.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2174, pruned_loss=0.03663, over 973423.02 frames.], batch size: 14, lr: 2.66e-04
+2022-05-06 02:39:21,798 INFO [train.py:715] (3/8) Epoch 8, batch 5850, loss[loss=0.162, simple_loss=0.2297, pruned_loss=0.04712, over 4903.00 frames.], tot_loss[loss=0.145, simple_loss=0.2163, pruned_loss=0.0368, over 973121.51 frames.], batch size: 39, lr: 2.66e-04
+2022-05-06 02:40:00,569 INFO [train.py:715] (3/8) Epoch 8, batch 5900, loss[loss=0.1568, simple_loss=0.2292, pruned_loss=0.04226, over 4910.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2154, pruned_loss=0.03613, over 971913.12 frames.], batch size: 17, lr: 2.66e-04
+2022-05-06 02:40:40,147 INFO [train.py:715] (3/8) Epoch 8, batch 5950, loss[loss=0.1486, simple_loss=0.2124, pruned_loss=0.04242, over 4967.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2154, pruned_loss=0.03575, over 972534.08 frames.], batch size: 14, lr: 2.66e-04
+2022-05-06 02:41:20,032 INFO [train.py:715] (3/8) Epoch 8, batch 6000, loss[loss=0.1519, simple_loss=0.224, pruned_loss=0.03985, over 4903.00 frames.], tot_loss[loss=0.1434, simple_loss=0.215, pruned_loss=0.03592, over 972480.62 frames.], batch size: 17, lr: 2.66e-04
+2022-05-06 02:41:20,032 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 02:41:29,607 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1075, simple_loss=0.1921, pruned_loss=0.01146, over 914524.00 frames.
+2022-05-06 02:42:09,069 INFO [train.py:715] (3/8) Epoch 8, batch 6050, loss[loss=0.1634, simple_loss=0.2409, pruned_loss=0.04292, over 4934.00 frames.], tot_loss[loss=0.144, simple_loss=0.2156, pruned_loss=0.03624, over 972784.45 frames.], batch size: 21, lr: 2.66e-04
+2022-05-06 02:42:48,767 INFO [train.py:715] (3/8) Epoch 8, batch 6100, loss[loss=0.1529, simple_loss=0.229, pruned_loss=0.03842, over 4898.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2154, pruned_loss=0.03652, over 972014.92 frames.], batch size: 18, lr: 2.66e-04
+2022-05-06 02:43:28,430 INFO [train.py:715] (3/8) Epoch 8, batch 6150, loss[loss=0.1325, simple_loss=0.2101, pruned_loss=0.02747, over 4796.00 frames.], tot_loss[loss=0.1436, simple_loss=0.215, pruned_loss=0.03612, over 972091.22 frames.], batch size: 21, lr: 2.66e-04
+2022-05-06 02:44:08,983 INFO [train.py:715] (3/8) Epoch 8, batch 6200, loss[loss=0.1342, simple_loss=0.2095, pruned_loss=0.02946, over 4936.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2154, pruned_loss=0.03638, over 972898.76 frames.], batch size: 23, lr: 2.66e-04
+2022-05-06 02:44:49,471 INFO [train.py:715] (3/8) Epoch 8, batch 6250, loss[loss=0.1414, simple_loss=0.2062, pruned_loss=0.03831, over 4888.00 frames.], tot_loss[loss=0.143, simple_loss=0.2147, pruned_loss=0.03568, over 973680.76 frames.], batch size: 16, lr: 2.66e-04
+2022-05-06 02:45:29,140 INFO [train.py:715] (3/8) Epoch 8, batch 6300, loss[loss=0.1523, simple_loss=0.2253, pruned_loss=0.0396, over 4955.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2145, pruned_loss=0.0356, over 972579.27 frames.], batch size: 35, lr: 2.66e-04
+2022-05-06 02:46:08,062 INFO [train.py:715] (3/8) Epoch 8, batch 6350, loss[loss=0.1336, simple_loss=0.2127, pruned_loss=0.0272, over 4876.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03594, over 972511.96 frames.], batch size: 32, lr: 2.66e-04
+2022-05-06 02:46:47,827 INFO [train.py:715] (3/8) Epoch 8, batch 6400, loss[loss=0.143, simple_loss=0.2163, pruned_loss=0.03485, over 4842.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.03569, over 972137.56 frames.], batch size: 15, lr: 2.66e-04
+2022-05-06 02:47:27,063 INFO [train.py:715] (3/8) Epoch 8, batch 6450, loss[loss=0.1372, simple_loss=0.2111, pruned_loss=0.03162, over 4866.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2158, pruned_loss=0.03582, over 972662.78 frames.], batch size: 16, lr: 2.66e-04
+2022-05-06 02:48:06,516 INFO [train.py:715] (3/8) Epoch 8, batch 6500, loss[loss=0.1446, simple_loss=0.2074, pruned_loss=0.04094, over 4829.00 frames.], tot_loss[loss=0.1441, simple_loss=0.216, pruned_loss=0.03614, over 973227.39 frames.], batch size: 13, lr: 2.66e-04
+2022-05-06 02:48:45,637 INFO [train.py:715] (3/8) Epoch 8, batch 6550, loss[loss=0.1529, simple_loss=0.2196, pruned_loss=0.04312, over 4883.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03582, over 973531.82 frames.], batch size: 30, lr: 2.66e-04
+2022-05-06 02:49:25,294 INFO [train.py:715] (3/8) Epoch 8, batch 6600, loss[loss=0.1165, simple_loss=0.185, pruned_loss=0.02396, over 4796.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2153, pruned_loss=0.03554, over 972634.80 frames.], batch size: 17, lr: 2.66e-04
+2022-05-06 02:50:04,619 INFO [train.py:715] (3/8) Epoch 8, batch 6650, loss[loss=0.1669, simple_loss=0.234, pruned_loss=0.04993, over 4919.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03588, over 972512.47 frames.], batch size: 39, lr: 2.66e-04
+2022-05-06 02:50:43,401 INFO [train.py:715] (3/8) Epoch 8, batch 6700, loss[loss=0.1481, simple_loss=0.2145, pruned_loss=0.04087, over 4768.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03572, over 972961.80 frames.], batch size: 14, lr: 2.66e-04
+2022-05-06 02:51:23,631 INFO [train.py:715] (3/8) Epoch 8, batch 6750, loss[loss=0.1632, simple_loss=0.2264, pruned_loss=0.05, over 4859.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03634, over 973053.80 frames.], batch size: 20, lr: 2.66e-04
+2022-05-06 02:52:03,056 INFO [train.py:715] (3/8) Epoch 8, batch 6800, loss[loss=0.1256, simple_loss=0.2082, pruned_loss=0.02149, over 4821.00 frames.], tot_loss[loss=0.1447, simple_loss=0.217, pruned_loss=0.03618, over 973117.08 frames.], batch size: 26, lr: 2.66e-04
+2022-05-06 02:52:42,028 INFO [train.py:715] (3/8) Epoch 8, batch 6850, loss[loss=0.145, simple_loss=0.2119, pruned_loss=0.039, over 4704.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.03646, over 973458.23 frames.], batch size: 15, lr: 2.66e-04
+2022-05-06 02:53:21,945 INFO [train.py:715] (3/8) Epoch 8, batch 6900, loss[loss=0.1379, simple_loss=0.2176, pruned_loss=0.02911, over 4690.00 frames.], tot_loss[loss=0.1449, simple_loss=0.217, pruned_loss=0.03638, over 973137.23 frames.], batch size: 15, lr: 2.66e-04
+2022-05-06 02:54:02,358 INFO [train.py:715] (3/8) Epoch 8, batch 6950, loss[loss=0.1556, simple_loss=0.2192, pruned_loss=0.04597, over 4850.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03683, over 972334.03 frames.], batch size: 15, lr: 2.66e-04
+2022-05-06 02:54:42,173 INFO [train.py:715] (3/8) Epoch 8, batch 7000, loss[loss=0.1354, simple_loss=0.2003, pruned_loss=0.03521, over 4939.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2169, pruned_loss=0.03671, over 972103.59 frames.], batch size: 23, lr: 2.65e-04
+2022-05-06 02:55:21,782 INFO [train.py:715] (3/8) Epoch 8, batch 7050, loss[loss=0.1308, simple_loss=0.1977, pruned_loss=0.03189, over 4741.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2158, pruned_loss=0.03632, over 972106.05 frames.], batch size: 16, lr: 2.65e-04
+2022-05-06 02:56:01,472 INFO [train.py:715] (3/8) Epoch 8, batch 7100, loss[loss=0.1361, simple_loss=0.2134, pruned_loss=0.0294, over 4696.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03615, over 971888.55 frames.], batch size: 15, lr: 2.65e-04
+2022-05-06 02:56:41,142 INFO [train.py:715] (3/8) Epoch 8, batch 7150, loss[loss=0.1833, simple_loss=0.2601, pruned_loss=0.05328, over 4778.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2163, pruned_loss=0.03664, over 971900.70 frames.], batch size: 18, lr: 2.65e-04
+2022-05-06 02:57:20,444 INFO [train.py:715] (3/8) Epoch 8, batch 7200, loss[loss=0.1434, simple_loss=0.2214, pruned_loss=0.03272, over 4889.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.03623, over 972603.99 frames.], batch size: 22, lr: 2.65e-04
+2022-05-06 02:57:59,449 INFO [train.py:715] (3/8) Epoch 8, batch 7250, loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03068, over 4871.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2162, pruned_loss=0.03624, over 973042.51 frames.], batch size: 32, lr: 2.65e-04
+2022-05-06 02:58:39,555 INFO [train.py:715] (3/8) Epoch 8, batch 7300, loss[loss=0.1135, simple_loss=0.1882, pruned_loss=0.01942, over 4925.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2158, pruned_loss=0.03566, over 973653.54 frames.], batch size: 23, lr: 2.65e-04
+2022-05-06 02:59:18,928 INFO [train.py:715] (3/8) Epoch 8, batch 7350, loss[loss=0.1282, simple_loss=0.2008, pruned_loss=0.02783, over 4993.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2151, pruned_loss=0.03586, over 973731.61 frames.], batch size: 14, lr: 2.65e-04
+2022-05-06 02:59:58,520 INFO [train.py:715] (3/8) Epoch 8, batch 7400, loss[loss=0.1656, simple_loss=0.2248, pruned_loss=0.05321, over 4987.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2151, pruned_loss=0.0359, over 973710.96 frames.], batch size: 15, lr: 2.65e-04
+2022-05-06 03:00:38,454 INFO [train.py:715] (3/8) Epoch 8, batch 7450, loss[loss=0.1423, simple_loss=0.2159, pruned_loss=0.03435, over 4779.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2157, pruned_loss=0.03594, over 973392.76 frames.], batch size: 17, lr: 2.65e-04
+2022-05-06 03:01:18,182 INFO [train.py:715] (3/8) Epoch 8, batch 7500, loss[loss=0.152, simple_loss=0.2108, pruned_loss=0.04665, over 4991.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2167, pruned_loss=0.03661, over 973164.00 frames.], batch size: 14, lr: 2.65e-04
+2022-05-06 03:01:57,872 INFO [train.py:715] (3/8) Epoch 8, batch 7550, loss[loss=0.1208, simple_loss=0.1891, pruned_loss=0.02629, over 4735.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2163, pruned_loss=0.03659, over 972039.61 frames.], batch size: 16, lr: 2.65e-04
+2022-05-06 03:02:37,819 INFO [train.py:715] (3/8) Epoch 8, batch 7600, loss[loss=0.1138, simple_loss=0.1861, pruned_loss=0.02081, over 4761.00 frames.], tot_loss[loss=0.144, simple_loss=0.2156, pruned_loss=0.03617, over 972412.78 frames.], batch size: 12, lr: 2.65e-04
+2022-05-06 03:03:17,988 INFO [train.py:715] (3/8) Epoch 8, batch 7650, loss[loss=0.1465, simple_loss=0.2238, pruned_loss=0.03465, over 4823.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.0351, over 971997.84 frames.], batch size: 13, lr: 2.65e-04
+2022-05-06 03:03:57,438 INFO [train.py:715] (3/8) Epoch 8, batch 7700, loss[loss=0.1612, simple_loss=0.2372, pruned_loss=0.04256, over 4920.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.03502, over 971998.38 frames.], batch size: 18, lr: 2.65e-04
+2022-05-06 03:04:36,612 INFO [train.py:715] (3/8) Epoch 8, batch 7750, loss[loss=0.1429, simple_loss=0.2133, pruned_loss=0.03629, over 4892.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03552, over 972666.86 frames.], batch size: 22, lr: 2.65e-04
+2022-05-06 03:05:16,799 INFO [train.py:715] (3/8) Epoch 8, batch 7800, loss[loss=0.1249, simple_loss=0.2081, pruned_loss=0.02087, over 4785.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03555, over 972098.50 frames.], batch size: 12, lr: 2.65e-04
+2022-05-06 03:05:56,864 INFO [train.py:715] (3/8) Epoch 8, batch 7850, loss[loss=0.1645, simple_loss=0.2345, pruned_loss=0.04728, over 4863.00 frames.], tot_loss[loss=0.1427, simple_loss=0.215, pruned_loss=0.0352, over 971902.36 frames.], batch size: 16, lr: 2.65e-04
+2022-05-06 03:06:35,514 INFO [train.py:715] (3/8) Epoch 8, batch 7900, loss[loss=0.1541, simple_loss=0.2189, pruned_loss=0.04462, over 4785.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03599, over 972531.77 frames.], batch size: 18, lr: 2.65e-04
+2022-05-06 03:07:15,006 INFO [train.py:715] (3/8) Epoch 8, batch 7950, loss[loss=0.1108, simple_loss=0.1681, pruned_loss=0.02678, over 4823.00 frames.], tot_loss[loss=0.1439, simple_loss=0.216, pruned_loss=0.03589, over 972491.23 frames.], batch size: 13, lr: 2.65e-04
+2022-05-06 03:07:54,690 INFO [train.py:715] (3/8) Epoch 8, batch 8000, loss[loss=0.1121, simple_loss=0.1931, pruned_loss=0.01558, over 4866.00 frames.], tot_loss[loss=0.145, simple_loss=0.2167, pruned_loss=0.03663, over 971355.59 frames.], batch size: 22, lr: 2.65e-04
+2022-05-06 03:08:33,646 INFO [train.py:715] (3/8) Epoch 8, batch 8050, loss[loss=0.1221, simple_loss=0.1997, pruned_loss=0.02228, over 4892.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.03614, over 971181.47 frames.], batch size: 19, lr: 2.65e-04
+2022-05-06 03:09:12,021 INFO [train.py:715] (3/8) Epoch 8, batch 8100, loss[loss=0.1235, simple_loss=0.1936, pruned_loss=0.02668, over 4894.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.03619, over 971404.68 frames.], batch size: 16, lr: 2.65e-04
+2022-05-06 03:09:51,245 INFO [train.py:715] (3/8) Epoch 8, batch 8150, loss[loss=0.1578, simple_loss=0.2233, pruned_loss=0.04617, over 4976.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2162, pruned_loss=0.03622, over 972194.05 frames.], batch size: 35, lr: 2.65e-04
+2022-05-06 03:10:31,279 INFO [train.py:715] (3/8) Epoch 8, batch 8200, loss[loss=0.1236, simple_loss=0.1962, pruned_loss=0.0255, over 4856.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03586, over 972021.82 frames.], batch size: 20, lr: 2.65e-04
+2022-05-06 03:11:09,920 INFO [train.py:715] (3/8) Epoch 8, batch 8250, loss[loss=0.1431, simple_loss=0.213, pruned_loss=0.03658, over 4861.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03599, over 972294.05 frames.], batch size: 16, lr: 2.65e-04
+2022-05-06 03:11:48,870 INFO [train.py:715] (3/8) Epoch 8, batch 8300, loss[loss=0.1482, simple_loss=0.2229, pruned_loss=0.03673, over 4960.00 frames.], tot_loss[loss=0.1449, simple_loss=0.217, pruned_loss=0.03641, over 972268.83 frames.], batch size: 35, lr: 2.65e-04
+2022-05-06 03:12:28,296 INFO [train.py:715] (3/8) Epoch 8, batch 8350, loss[loss=0.1324, simple_loss=0.2078, pruned_loss=0.02853, over 4869.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2165, pruned_loss=0.03641, over 972382.82 frames.], batch size: 20, lr: 2.65e-04
+2022-05-06 03:13:07,309 INFO [train.py:715] (3/8) Epoch 8, batch 8400, loss[loss=0.1189, simple_loss=0.19, pruned_loss=0.02384, over 4696.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2165, pruned_loss=0.03639, over 972233.35 frames.], batch size: 15, lr: 2.65e-04
+2022-05-06 03:13:45,967 INFO [train.py:715] (3/8) Epoch 8, batch 8450, loss[loss=0.1319, simple_loss=0.1947, pruned_loss=0.03449, over 4878.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03608, over 972711.77 frames.], batch size: 13, lr: 2.65e-04
+2022-05-06 03:14:25,532 INFO [train.py:715] (3/8) Epoch 8, batch 8500, loss[loss=0.1607, simple_loss=0.2313, pruned_loss=0.04501, over 4891.00 frames.], tot_loss[loss=0.1439, simple_loss=0.216, pruned_loss=0.03587, over 972915.16 frames.], batch size: 22, lr: 2.65e-04
+2022-05-06 03:15:05,499 INFO [train.py:715] (3/8) Epoch 8, batch 8550, loss[loss=0.1491, simple_loss=0.2158, pruned_loss=0.04124, over 4852.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03581, over 973627.10 frames.], batch size: 32, lr: 2.65e-04
+2022-05-06 03:15:44,163 INFO [train.py:715] (3/8) Epoch 8, batch 8600, loss[loss=0.137, simple_loss=0.2074, pruned_loss=0.03331, over 4901.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03546, over 972984.53 frames.], batch size: 19, lr: 2.65e-04
+2022-05-06 03:16:23,281 INFO [train.py:715] (3/8) Epoch 8, batch 8650, loss[loss=0.1531, simple_loss=0.2181, pruned_loss=0.04407, over 4774.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03553, over 972471.83 frames.], batch size: 14, lr: 2.65e-04
+2022-05-06 03:17:02,901 INFO [train.py:715] (3/8) Epoch 8, batch 8700, loss[loss=0.1469, simple_loss=0.2173, pruned_loss=0.03823, over 4936.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03582, over 972302.37 frames.], batch size: 29, lr: 2.65e-04
+2022-05-06 03:17:41,699 INFO [train.py:715] (3/8) Epoch 8, batch 8750, loss[loss=0.1783, simple_loss=0.2432, pruned_loss=0.05667, over 4823.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2156, pruned_loss=0.03588, over 972359.86 frames.], batch size: 15, lr: 2.65e-04
+2022-05-06 03:18:20,672 INFO [train.py:715] (3/8) Epoch 8, batch 8800, loss[loss=0.1356, simple_loss=0.2119, pruned_loss=0.0296, over 4757.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03602, over 972692.57 frames.], batch size: 19, lr: 2.65e-04
+2022-05-06 03:19:00,219 INFO [train.py:715] (3/8) Epoch 8, batch 8850, loss[loss=0.1337, simple_loss=0.2173, pruned_loss=0.02504, over 4963.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03585, over 972669.06 frames.], batch size: 24, lr: 2.65e-04
+2022-05-06 03:19:39,728 INFO [train.py:715] (3/8) Epoch 8, batch 8900, loss[loss=0.1399, simple_loss=0.2089, pruned_loss=0.03549, over 4897.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2166, pruned_loss=0.03593, over 972631.56 frames.], batch size: 22, lr: 2.65e-04
+2022-05-06 03:20:18,231 INFO [train.py:715] (3/8) Epoch 8, batch 8950, loss[loss=0.1254, simple_loss=0.2023, pruned_loss=0.02427, over 4916.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2167, pruned_loss=0.0359, over 972361.98 frames.], batch size: 18, lr: 2.65e-04
+2022-05-06 03:20:57,340 INFO [train.py:715] (3/8) Epoch 8, batch 9000, loss[loss=0.1407, simple_loss=0.2148, pruned_loss=0.03332, over 4984.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2165, pruned_loss=0.036, over 972333.30 frames.], batch size: 24, lr: 2.65e-04
+2022-05-06 03:20:57,341 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 03:21:06,881 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1075, simple_loss=0.1922, pruned_loss=0.01144, over 914524.00 frames.
+2022-05-06 03:21:46,745 INFO [train.py:715] (3/8) Epoch 8, batch 9050, loss[loss=0.1432, simple_loss=0.2105, pruned_loss=0.03795, over 4965.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.0357, over 972213.86 frames.], batch size: 14, lr: 2.65e-04
+2022-05-06 03:22:26,224 INFO [train.py:715] (3/8) Epoch 8, batch 9100, loss[loss=0.1417, simple_loss=0.2101, pruned_loss=0.03665, over 4846.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2158, pruned_loss=0.03648, over 972901.89 frames.], batch size: 32, lr: 2.65e-04
+2022-05-06 03:23:05,921 INFO [train.py:715] (3/8) Epoch 8, batch 9150, loss[loss=0.1794, simple_loss=0.2502, pruned_loss=0.05431, over 4872.00 frames.], tot_loss[loss=0.1433, simple_loss=0.215, pruned_loss=0.03582, over 972392.20 frames.], batch size: 38, lr: 2.64e-04
+2022-05-06 03:23:44,125 INFO [train.py:715] (3/8) Epoch 8, batch 9200, loss[loss=0.1419, simple_loss=0.2159, pruned_loss=0.03396, over 4913.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2153, pruned_loss=0.03611, over 971719.52 frames.], batch size: 17, lr: 2.64e-04
+2022-05-06 03:24:23,666 INFO [train.py:715] (3/8) Epoch 8, batch 9250, loss[loss=0.1558, simple_loss=0.226, pruned_loss=0.04282, over 4909.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2153, pruned_loss=0.03604, over 972209.85 frames.], batch size: 19, lr: 2.64e-04
+2022-05-06 03:25:03,200 INFO [train.py:715] (3/8) Epoch 8, batch 9300, loss[loss=0.1565, simple_loss=0.2214, pruned_loss=0.04582, over 4806.00 frames.], tot_loss[loss=0.144, simple_loss=0.2157, pruned_loss=0.03613, over 972586.47 frames.], batch size: 25, lr: 2.64e-04
+2022-05-06 03:25:42,060 INFO [train.py:715] (3/8) Epoch 8, batch 9350, loss[loss=0.1462, simple_loss=0.2186, pruned_loss=0.03692, over 4837.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03582, over 972593.02 frames.], batch size: 15, lr: 2.64e-04
+2022-05-06 03:26:20,916 INFO [train.py:715] (3/8) Epoch 8, batch 9400, loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.0317, over 4915.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2153, pruned_loss=0.03574, over 970894.53 frames.], batch size: 23, lr: 2.64e-04
+2022-05-06 03:27:00,378 INFO [train.py:715] (3/8) Epoch 8, batch 9450, loss[loss=0.1538, simple_loss=0.2325, pruned_loss=0.03758, over 4941.00 frames.], tot_loss[loss=0.143, simple_loss=0.215, pruned_loss=0.03553, over 970988.21 frames.], batch size: 21, lr: 2.64e-04
+2022-05-06 03:27:40,542 INFO [train.py:715] (3/8) Epoch 8, batch 9500, loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03293, over 4885.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2156, pruned_loss=0.03597, over 970829.66 frames.], batch size: 22, lr: 2.64e-04
+2022-05-06 03:28:21,698 INFO [train.py:715] (3/8) Epoch 8, batch 9550, loss[loss=0.1598, simple_loss=0.2254, pruned_loss=0.04709, over 4921.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2155, pruned_loss=0.03595, over 971297.85 frames.], batch size: 17, lr: 2.64e-04
+2022-05-06 03:29:01,737 INFO [train.py:715] (3/8) Epoch 8, batch 9600, loss[loss=0.1628, simple_loss=0.2391, pruned_loss=0.04324, over 4883.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2157, pruned_loss=0.03623, over 971119.33 frames.], batch size: 22, lr: 2.64e-04
+2022-05-06 03:29:41,772 INFO [train.py:715] (3/8) Epoch 8, batch 9650, loss[loss=0.1653, simple_loss=0.22, pruned_loss=0.05529, over 4787.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2146, pruned_loss=0.03553, over 970825.26 frames.], batch size: 18, lr: 2.64e-04
+2022-05-06 03:30:21,100 INFO [train.py:715] (3/8) Epoch 8, batch 9700, loss[loss=0.128, simple_loss=0.2038, pruned_loss=0.02611, over 4830.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2149, pruned_loss=0.03565, over 970767.04 frames.], batch size: 26, lr: 2.64e-04
+2022-05-06 03:30:59,865 INFO [train.py:715] (3/8) Epoch 8, batch 9750, loss[loss=0.1434, simple_loss=0.22, pruned_loss=0.0334, over 4947.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2143, pruned_loss=0.03537, over 971092.03 frames.], batch size: 29, lr: 2.64e-04
+2022-05-06 03:31:39,478 INFO [train.py:715] (3/8) Epoch 8, batch 9800, loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03403, over 4762.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2151, pruned_loss=0.03579, over 971606.32 frames.], batch size: 14, lr: 2.64e-04
+2022-05-06 03:32:18,970 INFO [train.py:715] (3/8) Epoch 8, batch 9850, loss[loss=0.1626, simple_loss=0.2347, pruned_loss=0.04528, over 4824.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2154, pruned_loss=0.03588, over 971504.74 frames.], batch size: 25, lr: 2.64e-04
+2022-05-06 03:32:58,276 INFO [train.py:715] (3/8) Epoch 8, batch 9900, loss[loss=0.1404, simple_loss=0.2188, pruned_loss=0.03096, over 4762.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.03609, over 972307.44 frames.], batch size: 19, lr: 2.64e-04
+2022-05-06 03:33:37,621 INFO [train.py:715] (3/8) Epoch 8, batch 9950, loss[loss=0.1287, simple_loss=0.2018, pruned_loss=0.02775, over 4935.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03576, over 972528.17 frames.], batch size: 23, lr: 2.64e-04
+2022-05-06 03:34:17,530 INFO [train.py:715] (3/8) Epoch 8, batch 10000, loss[loss=0.1527, simple_loss=0.2277, pruned_loss=0.03878, over 4836.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03585, over 972577.94 frames.], batch size: 26, lr: 2.64e-04
+2022-05-06 03:34:56,512 INFO [train.py:715] (3/8) Epoch 8, batch 10050, loss[loss=0.1499, simple_loss=0.2214, pruned_loss=0.03917, over 4988.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03613, over 972614.53 frames.], batch size: 24, lr: 2.64e-04
+2022-05-06 03:35:35,063 INFO [train.py:715] (3/8) Epoch 8, batch 10100, loss[loss=0.1362, simple_loss=0.2183, pruned_loss=0.02709, over 4795.00 frames.], tot_loss[loss=0.1442, simple_loss=0.216, pruned_loss=0.03622, over 972825.74 frames.], batch size: 21, lr: 2.64e-04
+2022-05-06 03:36:15,139 INFO [train.py:715] (3/8) Epoch 8, batch 10150, loss[loss=0.2052, simple_loss=0.2567, pruned_loss=0.07684, over 4838.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03606, over 972444.31 frames.], batch size: 15, lr: 2.64e-04
+2022-05-06 03:36:55,128 INFO [train.py:715] (3/8) Epoch 8, batch 10200, loss[loss=0.1507, simple_loss=0.2295, pruned_loss=0.03592, over 4934.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2159, pruned_loss=0.03597, over 971424.20 frames.], batch size: 23, lr: 2.64e-04
+2022-05-06 03:37:34,623 INFO [train.py:715] (3/8) Epoch 8, batch 10250, loss[loss=0.1419, simple_loss=0.2137, pruned_loss=0.03499, over 4853.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03573, over 971971.56 frames.], batch size: 32, lr: 2.64e-04
+2022-05-06 03:38:14,431 INFO [train.py:715] (3/8) Epoch 8, batch 10300, loss[loss=0.1714, simple_loss=0.2376, pruned_loss=0.05261, over 4775.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2165, pruned_loss=0.03554, over 971171.56 frames.], batch size: 18, lr: 2.64e-04
+2022-05-06 03:38:53,951 INFO [train.py:715] (3/8) Epoch 8, batch 10350, loss[loss=0.1356, simple_loss=0.2185, pruned_loss=0.02632, over 4827.00 frames.], tot_loss[loss=0.143, simple_loss=0.2158, pruned_loss=0.03507, over 971135.73 frames.], batch size: 15, lr: 2.64e-04
+2022-05-06 03:39:32,637 INFO [train.py:715] (3/8) Epoch 8, batch 10400, loss[loss=0.1456, simple_loss=0.2127, pruned_loss=0.03923, over 4817.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2153, pruned_loss=0.03517, over 970556.29 frames.], batch size: 13, lr: 2.64e-04
+2022-05-06 03:40:12,241 INFO [train.py:715] (3/8) Epoch 8, batch 10450, loss[loss=0.1385, simple_loss=0.2106, pruned_loss=0.03322, over 4970.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03507, over 970522.12 frames.], batch size: 15, lr: 2.64e-04
+2022-05-06 03:40:51,306 INFO [train.py:715] (3/8) Epoch 8, batch 10500, loss[loss=0.1376, simple_loss=0.2082, pruned_loss=0.03349, over 4824.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03434, over 970639.06 frames.], batch size: 15, lr: 2.64e-04
+2022-05-06 03:41:30,155 INFO [train.py:715] (3/8) Epoch 8, batch 10550, loss[loss=0.1301, simple_loss=0.1954, pruned_loss=0.03239, over 4790.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03413, over 971016.28 frames.], batch size: 14, lr: 2.64e-04
+2022-05-06 03:42:08,779 INFO [train.py:715] (3/8) Epoch 8, batch 10600, loss[loss=0.1496, simple_loss=0.2167, pruned_loss=0.04124, over 4844.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03426, over 970969.53 frames.], batch size: 34, lr: 2.64e-04
+2022-05-06 03:42:48,074 INFO [train.py:715] (3/8) Epoch 8, batch 10650, loss[loss=0.1387, simple_loss=0.2067, pruned_loss=0.03535, over 4942.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03573, over 971009.69 frames.], batch size: 29, lr: 2.64e-04
+2022-05-06 03:43:27,255 INFO [train.py:715] (3/8) Epoch 8, batch 10700, loss[loss=0.1413, simple_loss=0.2167, pruned_loss=0.03292, over 4980.00 frames.], tot_loss[loss=0.144, simple_loss=0.2162, pruned_loss=0.03588, over 972629.56 frames.], batch size: 35, lr: 2.64e-04
+2022-05-06 03:44:06,353 INFO [train.py:715] (3/8) Epoch 8, batch 10750, loss[loss=0.1368, simple_loss=0.204, pruned_loss=0.03477, over 4953.00 frames.], tot_loss[loss=0.144, simple_loss=0.2162, pruned_loss=0.03584, over 972924.38 frames.], batch size: 15, lr: 2.64e-04
+2022-05-06 03:44:46,295 INFO [train.py:715] (3/8) Epoch 8, batch 10800, loss[loss=0.1422, simple_loss=0.2117, pruned_loss=0.03632, over 4987.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03514, over 972594.47 frames.], batch size: 20, lr: 2.64e-04
+2022-05-06 03:45:26,102 INFO [train.py:715] (3/8) Epoch 8, batch 10850, loss[loss=0.1319, simple_loss=0.2102, pruned_loss=0.02683, over 4962.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2148, pruned_loss=0.03492, over 971712.81 frames.], batch size: 24, lr: 2.64e-04
+2022-05-06 03:46:05,370 INFO [train.py:715] (3/8) Epoch 8, batch 10900, loss[loss=0.1659, simple_loss=0.2447, pruned_loss=0.04355, over 4984.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2159, pruned_loss=0.03551, over 972850.67 frames.], batch size: 25, lr: 2.64e-04
+2022-05-06 03:46:44,375 INFO [train.py:715] (3/8) Epoch 8, batch 10950, loss[loss=0.1481, simple_loss=0.2275, pruned_loss=0.03434, over 4895.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03569, over 972829.63 frames.], batch size: 19, lr: 2.64e-04
+2022-05-06 03:47:24,374 INFO [train.py:715] (3/8) Epoch 8, batch 11000, loss[loss=0.1418, simple_loss=0.2223, pruned_loss=0.03066, over 4808.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2165, pruned_loss=0.03553, over 972360.13 frames.], batch size: 25, lr: 2.64e-04
+2022-05-06 03:48:03,909 INFO [train.py:715] (3/8) Epoch 8, batch 11050, loss[loss=0.1741, simple_loss=0.2438, pruned_loss=0.05222, over 4972.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2165, pruned_loss=0.03603, over 972344.88 frames.], batch size: 15, lr: 2.64e-04
+2022-05-06 03:48:42,671 INFO [train.py:715] (3/8) Epoch 8, batch 11100, loss[loss=0.1483, simple_loss=0.2166, pruned_loss=0.03998, over 4833.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03609, over 972807.48 frames.], batch size: 32, lr: 2.64e-04
+2022-05-06 03:49:22,145 INFO [train.py:715] (3/8) Epoch 8, batch 11150, loss[loss=0.1284, simple_loss=0.1977, pruned_loss=0.0295, over 4950.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03573, over 973640.27 frames.], batch size: 14, lr: 2.64e-04
+2022-05-06 03:50:01,939 INFO [train.py:715] (3/8) Epoch 8, batch 11200, loss[loss=0.1436, simple_loss=0.2195, pruned_loss=0.03384, over 4878.00 frames.], tot_loss[loss=0.144, simple_loss=0.2162, pruned_loss=0.03594, over 973140.94 frames.], batch size: 32, lr: 2.64e-04
+2022-05-06 03:50:40,566 INFO [train.py:715] (3/8) Epoch 8, batch 11250, loss[loss=0.1554, simple_loss=0.2208, pruned_loss=0.04502, over 4970.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2161, pruned_loss=0.0361, over 972814.56 frames.], batch size: 15, lr: 2.64e-04
+2022-05-06 03:51:19,591 INFO [train.py:715] (3/8) Epoch 8, batch 11300, loss[loss=0.136, simple_loss=0.2114, pruned_loss=0.0303, over 4816.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03529, over 971621.15 frames.], batch size: 27, lr: 2.64e-04
+2022-05-06 03:51:58,925 INFO [train.py:715] (3/8) Epoch 8, batch 11350, loss[loss=0.1611, simple_loss=0.2315, pruned_loss=0.04528, over 4787.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03499, over 971369.84 frames.], batch size: 12, lr: 2.63e-04
+2022-05-06 03:52:37,405 INFO [train.py:715] (3/8) Epoch 8, batch 11400, loss[loss=0.1757, simple_loss=0.2491, pruned_loss=0.05114, over 4954.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2156, pruned_loss=0.03571, over 972650.53 frames.], batch size: 24, lr: 2.63e-04
+2022-05-06 03:53:16,049 INFO [train.py:715] (3/8) Epoch 8, batch 11450, loss[loss=0.2043, simple_loss=0.2512, pruned_loss=0.07875, over 4756.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2152, pruned_loss=0.03587, over 972510.87 frames.], batch size: 19, lr: 2.63e-04
+2022-05-06 03:53:55,352 INFO [train.py:715] (3/8) Epoch 8, batch 11500, loss[loss=0.1651, simple_loss=0.2465, pruned_loss=0.04185, over 4927.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2167, pruned_loss=0.03627, over 972781.34 frames.], batch size: 21, lr: 2.63e-04
+2022-05-06 03:54:34,455 INFO [train.py:715] (3/8) Epoch 8, batch 11550, loss[loss=0.1705, simple_loss=0.2522, pruned_loss=0.04436, over 4993.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2167, pruned_loss=0.0362, over 972521.67 frames.], batch size: 14, lr: 2.63e-04
+2022-05-06 03:55:13,509 INFO [train.py:715] (3/8) Epoch 8, batch 11600, loss[loss=0.1248, simple_loss=0.1958, pruned_loss=0.02685, over 4784.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.03567, over 972769.40 frames.], batch size: 12, lr: 2.63e-04
+2022-05-06 03:55:53,444 INFO [train.py:715] (3/8) Epoch 8, batch 11650, loss[loss=0.1146, simple_loss=0.1969, pruned_loss=0.01611, over 4849.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.03538, over 973280.44 frames.], batch size: 15, lr: 2.63e-04
+2022-05-06 03:56:33,836 INFO [train.py:715] (3/8) Epoch 8, batch 11700, loss[loss=0.1247, simple_loss=0.2061, pruned_loss=0.02169, over 4791.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03582, over 974112.85 frames.], batch size: 24, lr: 2.63e-04
+2022-05-06 03:57:13,267 INFO [train.py:715] (3/8) Epoch 8, batch 11750, loss[loss=0.1329, simple_loss=0.2172, pruned_loss=0.0243, over 4736.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03594, over 973412.95 frames.], batch size: 16, lr: 2.63e-04
+2022-05-06 03:57:52,305 INFO [train.py:715] (3/8) Epoch 8, batch 11800, loss[loss=0.1552, simple_loss=0.2231, pruned_loss=0.04361, over 4789.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2153, pruned_loss=0.03554, over 973339.66 frames.], batch size: 24, lr: 2.63e-04
+2022-05-06 03:58:32,048 INFO [train.py:715] (3/8) Epoch 8, batch 11850, loss[loss=0.1499, simple_loss=0.2172, pruned_loss=0.04127, over 4975.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2156, pruned_loss=0.0359, over 972973.30 frames.], batch size: 15, lr: 2.63e-04
+2022-05-06 03:59:11,747 INFO [train.py:715] (3/8) Epoch 8, batch 11900, loss[loss=0.1615, simple_loss=0.2324, pruned_loss=0.04528, over 4983.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03601, over 973085.90 frames.], batch size: 15, lr: 2.63e-04
+2022-05-06 03:59:51,345 INFO [train.py:715] (3/8) Epoch 8, batch 11950, loss[loss=0.1751, simple_loss=0.241, pruned_loss=0.05467, over 4789.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03598, over 972738.58 frames.], batch size: 14, lr: 2.63e-04
+2022-05-06 04:00:30,530 INFO [train.py:715] (3/8) Epoch 8, batch 12000, loss[loss=0.1406, simple_loss=0.2141, pruned_loss=0.03355, over 4813.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03543, over 972147.59 frames.], batch size: 24, lr: 2.63e-04
+2022-05-06 04:00:30,530 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 04:00:40,090 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1076, simple_loss=0.1923, pruned_loss=0.0115, over 914524.00 frames.
+2022-05-06 04:01:19,839 INFO [train.py:715] (3/8) Epoch 8, batch 12050, loss[loss=0.1362, simple_loss=0.2235, pruned_loss=0.02442, over 4907.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.03562, over 972404.44 frames.], batch size: 17, lr: 2.63e-04
+2022-05-06 04:01:59,446 INFO [train.py:715] (3/8) Epoch 8, batch 12100, loss[loss=0.189, simple_loss=0.249, pruned_loss=0.06449, over 4983.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2157, pruned_loss=0.03539, over 972504.83 frames.], batch size: 14, lr: 2.63e-04
+2022-05-06 04:02:38,519 INFO [train.py:715] (3/8) Epoch 8, batch 12150, loss[loss=0.1651, simple_loss=0.2343, pruned_loss=0.04794, over 4863.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03573, over 973053.10 frames.], batch size: 32, lr: 2.63e-04
+2022-05-06 04:03:17,590 INFO [train.py:715] (3/8) Epoch 8, batch 12200, loss[loss=0.1087, simple_loss=0.1695, pruned_loss=0.02392, over 4777.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2156, pruned_loss=0.03514, over 973177.68 frames.], batch size: 12, lr: 2.63e-04
+2022-05-06 04:03:57,171 INFO [train.py:715] (3/8) Epoch 8, batch 12250, loss[loss=0.1123, simple_loss=0.1788, pruned_loss=0.0229, over 4736.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.03498, over 973244.37 frames.], batch size: 12, lr: 2.63e-04
+2022-05-06 04:04:36,391 INFO [train.py:715] (3/8) Epoch 8, batch 12300, loss[loss=0.1434, simple_loss=0.2163, pruned_loss=0.03518, over 4696.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03488, over 972341.20 frames.], batch size: 15, lr: 2.63e-04
+2022-05-06 04:05:15,233 INFO [train.py:715] (3/8) Epoch 8, batch 12350, loss[loss=0.1403, simple_loss=0.2115, pruned_loss=0.03456, over 4800.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2152, pruned_loss=0.0356, over 972238.91 frames.], batch size: 14, lr: 2.63e-04
+2022-05-06 04:05:54,659 INFO [train.py:715] (3/8) Epoch 8, batch 12400, loss[loss=0.1478, simple_loss=0.2179, pruned_loss=0.03881, over 4901.00 frames.], tot_loss[loss=0.144, simple_loss=0.2156, pruned_loss=0.03614, over 972757.88 frames.], batch size: 17, lr: 2.63e-04
+2022-05-06 04:06:34,252 INFO [train.py:715] (3/8) Epoch 8, batch 12450, loss[loss=0.1057, simple_loss=0.1696, pruned_loss=0.02093, over 4769.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2162, pruned_loss=0.03663, over 971899.83 frames.], batch size: 12, lr: 2.63e-04
+2022-05-06 04:07:13,257 INFO [train.py:715] (3/8) Epoch 8, batch 12500, loss[loss=0.1752, simple_loss=0.2386, pruned_loss=0.05586, over 4752.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2169, pruned_loss=0.03707, over 971958.61 frames.], batch size: 19, lr: 2.63e-04
+2022-05-06 04:07:52,123 INFO [train.py:715] (3/8) Epoch 8, batch 12550, loss[loss=0.1334, simple_loss=0.1979, pruned_loss=0.03441, over 4836.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2173, pruned_loss=0.03716, over 971548.48 frames.], batch size: 30, lr: 2.63e-04
+2022-05-06 04:08:31,832 INFO [train.py:715] (3/8) Epoch 8, batch 12600, loss[loss=0.1525, simple_loss=0.2284, pruned_loss=0.03829, over 4776.00 frames.], tot_loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03728, over 970890.35 frames.], batch size: 18, lr: 2.63e-04
+2022-05-06 04:09:10,878 INFO [train.py:715] (3/8) Epoch 8, batch 12650, loss[loss=0.1545, simple_loss=0.2201, pruned_loss=0.04444, over 4971.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2173, pruned_loss=0.03714, over 971532.47 frames.], batch size: 28, lr: 2.63e-04
+2022-05-06 04:09:50,738 INFO [train.py:715] (3/8) Epoch 8, batch 12700, loss[loss=0.145, simple_loss=0.2138, pruned_loss=0.03809, over 4814.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2164, pruned_loss=0.0365, over 971015.95 frames.], batch size: 14, lr: 2.63e-04
+2022-05-06 04:10:30,122 INFO [train.py:715] (3/8) Epoch 8, batch 12750, loss[loss=0.1704, simple_loss=0.257, pruned_loss=0.04185, over 4773.00 frames.], tot_loss[loss=0.144, simple_loss=0.2158, pruned_loss=0.03614, over 971384.42 frames.], batch size: 17, lr: 2.63e-04
+2022-05-06 04:11:10,320 INFO [train.py:715] (3/8) Epoch 8, batch 12800, loss[loss=0.1904, simple_loss=0.2632, pruned_loss=0.05884, over 4950.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2149, pruned_loss=0.0357, over 971920.52 frames.], batch size: 29, lr: 2.63e-04
+2022-05-06 04:11:48,983 INFO [train.py:715] (3/8) Epoch 8, batch 12850, loss[loss=0.1577, simple_loss=0.2336, pruned_loss=0.04088, over 4877.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2154, pruned_loss=0.03609, over 972504.30 frames.], batch size: 16, lr: 2.63e-04
+2022-05-06 04:12:28,016 INFO [train.py:715] (3/8) Epoch 8, batch 12900, loss[loss=0.149, simple_loss=0.2169, pruned_loss=0.04054, over 4965.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2155, pruned_loss=0.0363, over 971621.31 frames.], batch size: 15, lr: 2.63e-04
+2022-05-06 04:13:07,523 INFO [train.py:715] (3/8) Epoch 8, batch 12950, loss[loss=0.1824, simple_loss=0.258, pruned_loss=0.05342, over 4879.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2152, pruned_loss=0.03609, over 972449.77 frames.], batch size: 22, lr: 2.63e-04
+2022-05-06 04:13:46,911 INFO [train.py:715] (3/8) Epoch 8, batch 13000, loss[loss=0.205, simple_loss=0.2533, pruned_loss=0.07839, over 4831.00 frames.], tot_loss[loss=0.143, simple_loss=0.2147, pruned_loss=0.0357, over 971934.14 frames.], batch size: 13, lr: 2.63e-04
+2022-05-06 04:14:26,215 INFO [train.py:715] (3/8) Epoch 8, batch 13050, loss[loss=0.1314, simple_loss=0.207, pruned_loss=0.02787, over 4800.00 frames.], tot_loss[loss=0.144, simple_loss=0.2157, pruned_loss=0.03618, over 971868.73 frames.], batch size: 12, lr: 2.63e-04
+2022-05-06 04:15:05,643 INFO [train.py:715] (3/8) Epoch 8, batch 13100, loss[loss=0.1927, simple_loss=0.2717, pruned_loss=0.05679, over 4772.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03573, over 972980.15 frames.], batch size: 18, lr: 2.63e-04
+2022-05-06 04:15:45,375 INFO [train.py:715] (3/8) Epoch 8, batch 13150, loss[loss=0.1462, simple_loss=0.2106, pruned_loss=0.04094, over 4738.00 frames.], tot_loss[loss=0.144, simple_loss=0.2162, pruned_loss=0.03589, over 972907.22 frames.], batch size: 16, lr: 2.63e-04
+2022-05-06 04:16:24,328 INFO [train.py:715] (3/8) Epoch 8, batch 13200, loss[loss=0.1229, simple_loss=0.1863, pruned_loss=0.0297, over 4870.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03549, over 973076.23 frames.], batch size: 13, lr: 2.63e-04
+2022-05-06 04:17:03,717 INFO [train.py:715] (3/8) Epoch 8, batch 13250, loss[loss=0.1629, simple_loss=0.2398, pruned_loss=0.04302, over 4991.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.03525, over 972326.87 frames.], batch size: 16, lr: 2.63e-04
+2022-05-06 04:17:43,334 INFO [train.py:715] (3/8) Epoch 8, batch 13300, loss[loss=0.114, simple_loss=0.183, pruned_loss=0.02253, over 4755.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03508, over 972808.39 frames.], batch size: 12, lr: 2.63e-04
+2022-05-06 04:18:22,355 INFO [train.py:715] (3/8) Epoch 8, batch 13350, loss[loss=0.1658, simple_loss=0.2369, pruned_loss=0.04736, over 4887.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.03547, over 973475.48 frames.], batch size: 38, lr: 2.63e-04
+2022-05-06 04:19:01,000 INFO [train.py:715] (3/8) Epoch 8, batch 13400, loss[loss=0.1401, simple_loss=0.2118, pruned_loss=0.03418, over 4970.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03539, over 973190.57 frames.], batch size: 14, lr: 2.63e-04
+2022-05-06 04:19:39,798 INFO [train.py:715] (3/8) Epoch 8, batch 13450, loss[loss=0.1417, simple_loss=0.2126, pruned_loss=0.03539, over 4758.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.03513, over 973193.03 frames.], batch size: 16, lr: 2.63e-04
+2022-05-06 04:20:19,855 INFO [train.py:715] (3/8) Epoch 8, batch 13500, loss[loss=0.1013, simple_loss=0.169, pruned_loss=0.01685, over 4845.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03555, over 972687.22 frames.], batch size: 30, lr: 2.63e-04
+2022-05-06 04:20:58,643 INFO [train.py:715] (3/8) Epoch 8, batch 13550, loss[loss=0.1403, simple_loss=0.2121, pruned_loss=0.0342, over 4859.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2159, pruned_loss=0.03528, over 972324.81 frames.], batch size: 20, lr: 2.62e-04
+2022-05-06 04:21:37,841 INFO [train.py:715] (3/8) Epoch 8, batch 13600, loss[loss=0.112, simple_loss=0.1831, pruned_loss=0.0204, over 4634.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03546, over 972391.37 frames.], batch size: 13, lr: 2.62e-04
+2022-05-06 04:22:16,975 INFO [train.py:715] (3/8) Epoch 8, batch 13650, loss[loss=0.1375, simple_loss=0.2127, pruned_loss=0.03109, over 4813.00 frames.], tot_loss[loss=0.1436, simple_loss=0.216, pruned_loss=0.03561, over 971918.11 frames.], batch size: 25, lr: 2.62e-04
+2022-05-06 04:22:56,126 INFO [train.py:715] (3/8) Epoch 8, batch 13700, loss[loss=0.1506, simple_loss=0.2182, pruned_loss=0.04154, over 4855.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03584, over 971310.47 frames.], batch size: 20, lr: 2.62e-04
+2022-05-06 04:23:34,769 INFO [train.py:715] (3/8) Epoch 8, batch 13750, loss[loss=0.1282, simple_loss=0.1978, pruned_loss=0.02931, over 4899.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2162, pruned_loss=0.03555, over 971446.26 frames.], batch size: 19, lr: 2.62e-04
+2022-05-06 04:24:13,494 INFO [train.py:715] (3/8) Epoch 8, batch 13800, loss[loss=0.1407, simple_loss=0.2181, pruned_loss=0.03164, over 4800.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.03559, over 971925.60 frames.], batch size: 25, lr: 2.62e-04
+2022-05-06 04:24:52,945 INFO [train.py:715] (3/8) Epoch 8, batch 13850, loss[loss=0.1478, simple_loss=0.2144, pruned_loss=0.04056, over 4981.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2168, pruned_loss=0.03631, over 972825.95 frames.], batch size: 33, lr: 2.62e-04
+2022-05-06 04:25:31,240 INFO [train.py:715] (3/8) Epoch 8, batch 13900, loss[loss=0.1439, simple_loss=0.2145, pruned_loss=0.03666, over 4744.00 frames.], tot_loss[loss=0.146, simple_loss=0.2179, pruned_loss=0.03704, over 973762.43 frames.], batch size: 16, lr: 2.62e-04
+2022-05-06 04:26:10,335 INFO [train.py:715] (3/8) Epoch 8, batch 13950, loss[loss=0.1286, simple_loss=0.2011, pruned_loss=0.02804, over 4807.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2178, pruned_loss=0.03675, over 973463.49 frames.], batch size: 25, lr: 2.62e-04
+2022-05-06 04:26:49,429 INFO [train.py:715] (3/8) Epoch 8, batch 14000, loss[loss=0.1386, simple_loss=0.2006, pruned_loss=0.03827, over 4960.00 frames.], tot_loss[loss=0.1458, simple_loss=0.218, pruned_loss=0.03682, over 973949.52 frames.], batch size: 35, lr: 2.62e-04
+2022-05-06 04:27:28,487 INFO [train.py:715] (3/8) Epoch 8, batch 14050, loss[loss=0.1185, simple_loss=0.1853, pruned_loss=0.02586, over 4839.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2173, pruned_loss=0.03608, over 973648.90 frames.], batch size: 13, lr: 2.62e-04
+2022-05-06 04:28:06,678 INFO [train.py:715] (3/8) Epoch 8, batch 14100, loss[loss=0.1813, simple_loss=0.2585, pruned_loss=0.05203, over 4988.00 frames.], tot_loss[loss=0.145, simple_loss=0.2174, pruned_loss=0.03628, over 973799.19 frames.], batch size: 25, lr: 2.62e-04
+2022-05-06 04:28:45,331 INFO [train.py:715] (3/8) Epoch 8, batch 14150, loss[loss=0.1559, simple_loss=0.2333, pruned_loss=0.03919, over 4802.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2172, pruned_loss=0.03622, over 973540.99 frames.], batch size: 21, lr: 2.62e-04
+2022-05-06 04:29:25,594 INFO [train.py:715] (3/8) Epoch 8, batch 14200, loss[loss=0.1242, simple_loss=0.1893, pruned_loss=0.02956, over 4795.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2174, pruned_loss=0.03643, over 973540.35 frames.], batch size: 12, lr: 2.62e-04
+2022-05-06 04:30:04,165 INFO [train.py:715] (3/8) Epoch 8, batch 14250, loss[loss=0.15, simple_loss=0.2283, pruned_loss=0.03589, over 4800.00 frames.], tot_loss[loss=0.145, simple_loss=0.2174, pruned_loss=0.03634, over 973509.68 frames.], batch size: 21, lr: 2.62e-04
+2022-05-06 04:30:44,069 INFO [train.py:715] (3/8) Epoch 8, batch 14300, loss[loss=0.1348, simple_loss=0.2144, pruned_loss=0.02755, over 4826.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03608, over 973351.74 frames.], batch size: 26, lr: 2.62e-04
+2022-05-06 04:31:23,529 INFO [train.py:715] (3/8) Epoch 8, batch 14350, loss[loss=0.1329, simple_loss=0.2132, pruned_loss=0.02634, over 4796.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2168, pruned_loss=0.03567, over 972723.93 frames.], batch size: 21, lr: 2.62e-04
+2022-05-06 04:32:02,825 INFO [train.py:715] (3/8) Epoch 8, batch 14400, loss[loss=0.1709, simple_loss=0.2348, pruned_loss=0.05353, over 4908.00 frames.], tot_loss[loss=0.145, simple_loss=0.2172, pruned_loss=0.03643, over 972467.15 frames.], batch size: 18, lr: 2.62e-04
+2022-05-06 04:32:41,516 INFO [train.py:715] (3/8) Epoch 8, batch 14450, loss[loss=0.1688, simple_loss=0.2423, pruned_loss=0.04767, over 4782.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.03671, over 972421.28 frames.], batch size: 14, lr: 2.62e-04
+2022-05-06 04:33:20,780 INFO [train.py:715] (3/8) Epoch 8, batch 14500, loss[loss=0.1377, simple_loss=0.2204, pruned_loss=0.02743, over 4815.00 frames.], tot_loss[loss=0.146, simple_loss=0.2184, pruned_loss=0.0368, over 972150.67 frames.], batch size: 15, lr: 2.62e-04
+2022-05-06 04:34:00,252 INFO [train.py:715] (3/8) Epoch 8, batch 14550, loss[loss=0.1447, simple_loss=0.2268, pruned_loss=0.03134, over 4860.00 frames.], tot_loss[loss=0.146, simple_loss=0.2182, pruned_loss=0.03686, over 972565.83 frames.], batch size: 20, lr: 2.62e-04
+2022-05-06 04:34:38,288 INFO [train.py:715] (3/8) Epoch 8, batch 14600, loss[loss=0.1525, simple_loss=0.2185, pruned_loss=0.04322, over 4793.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2175, pruned_loss=0.03636, over 971831.08 frames.], batch size: 17, lr: 2.62e-04
+2022-05-06 04:35:17,876 INFO [train.py:715] (3/8) Epoch 8, batch 14650, loss[loss=0.1322, simple_loss=0.2082, pruned_loss=0.02808, over 4935.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2167, pruned_loss=0.03598, over 972353.78 frames.], batch size: 23, lr: 2.62e-04
+2022-05-06 04:35:57,139 INFO [train.py:715] (3/8) Epoch 8, batch 14700, loss[loss=0.1248, simple_loss=0.1954, pruned_loss=0.02711, over 4656.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2159, pruned_loss=0.03572, over 972011.08 frames.], batch size: 13, lr: 2.62e-04
+2022-05-06 04:36:35,956 INFO [train.py:715] (3/8) Epoch 8, batch 14750, loss[loss=0.1577, simple_loss=0.2206, pruned_loss=0.04746, over 4887.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03582, over 972708.41 frames.], batch size: 22, lr: 2.62e-04
+2022-05-06 04:37:14,352 INFO [train.py:715] (3/8) Epoch 8, batch 14800, loss[loss=0.1174, simple_loss=0.1927, pruned_loss=0.02105, over 4904.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03603, over 972088.11 frames.], batch size: 17, lr: 2.62e-04
+2022-05-06 04:37:54,164 INFO [train.py:715] (3/8) Epoch 8, batch 14850, loss[loss=0.1574, simple_loss=0.2284, pruned_loss=0.04314, over 4711.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.03618, over 972864.74 frames.], batch size: 15, lr: 2.62e-04
+2022-05-06 04:38:33,085 INFO [train.py:715] (3/8) Epoch 8, batch 14900, loss[loss=0.1531, simple_loss=0.221, pruned_loss=0.04256, over 4809.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03593, over 971612.59 frames.], batch size: 25, lr: 2.62e-04
+2022-05-06 04:39:11,870 INFO [train.py:715] (3/8) Epoch 8, batch 14950, loss[loss=0.1353, simple_loss=0.2072, pruned_loss=0.03168, over 4791.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2155, pruned_loss=0.03595, over 971337.89 frames.], batch size: 14, lr: 2.62e-04
+2022-05-06 04:39:51,073 INFO [train.py:715] (3/8) Epoch 8, batch 15000, loss[loss=0.1384, simple_loss=0.2062, pruned_loss=0.03527, over 4845.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2155, pruned_loss=0.03542, over 972296.74 frames.], batch size: 20, lr: 2.62e-04
+2022-05-06 04:39:51,074 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 04:40:00,792 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1076, simple_loss=0.1921, pruned_loss=0.01153, over 914524.00 frames.
+2022-05-06 04:40:40,558 INFO [train.py:715] (3/8) Epoch 8, batch 15050, loss[loss=0.155, simple_loss=0.2308, pruned_loss=0.03964, over 4985.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03566, over 972282.43 frames.], batch size: 35, lr: 2.62e-04
+2022-05-06 04:41:19,877 INFO [train.py:715] (3/8) Epoch 8, batch 15100, loss[loss=0.1046, simple_loss=0.1843, pruned_loss=0.01251, over 4931.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03576, over 972996.93 frames.], batch size: 29, lr: 2.62e-04
+2022-05-06 04:41:59,415 INFO [train.py:715] (3/8) Epoch 8, batch 15150, loss[loss=0.1352, simple_loss=0.2078, pruned_loss=0.03137, over 4980.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03545, over 973178.14 frames.], batch size: 25, lr: 2.62e-04
+2022-05-06 04:42:38,834 INFO [train.py:715] (3/8) Epoch 8, batch 15200, loss[loss=0.1135, simple_loss=0.1879, pruned_loss=0.01952, over 4786.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.0358, over 972215.18 frames.], batch size: 21, lr: 2.62e-04
+2022-05-06 04:43:18,560 INFO [train.py:715] (3/8) Epoch 8, batch 15250, loss[loss=0.132, simple_loss=0.1967, pruned_loss=0.03366, over 4810.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.03551, over 972281.12 frames.], batch size: 25, lr: 2.62e-04
+2022-05-06 04:43:58,535 INFO [train.py:715] (3/8) Epoch 8, batch 15300, loss[loss=0.1477, simple_loss=0.2176, pruned_loss=0.0389, over 4941.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03626, over 972080.55 frames.], batch size: 39, lr: 2.62e-04
+2022-05-06 04:44:37,109 INFO [train.py:715] (3/8) Epoch 8, batch 15350, loss[loss=0.1265, simple_loss=0.2028, pruned_loss=0.02508, over 4897.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2167, pruned_loss=0.03621, over 971548.12 frames.], batch size: 22, lr: 2.62e-04
+2022-05-06 04:45:16,994 INFO [train.py:715] (3/8) Epoch 8, batch 15400, loss[loss=0.1174, simple_loss=0.197, pruned_loss=0.01887, over 4808.00 frames.], tot_loss[loss=0.145, simple_loss=0.2172, pruned_loss=0.03636, over 971447.89 frames.], batch size: 24, lr: 2.62e-04
+2022-05-06 04:45:55,983 INFO [train.py:715] (3/8) Epoch 8, batch 15450, loss[loss=0.1319, simple_loss=0.2084, pruned_loss=0.02767, over 4761.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03602, over 971795.89 frames.], batch size: 19, lr: 2.62e-04
+2022-05-06 04:46:34,941 INFO [train.py:715] (3/8) Epoch 8, batch 15500, loss[loss=0.1222, simple_loss=0.1926, pruned_loss=0.02592, over 4750.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03511, over 971824.38 frames.], batch size: 19, lr: 2.62e-04
+2022-05-06 04:47:13,678 INFO [train.py:715] (3/8) Epoch 8, batch 15550, loss[loss=0.1307, simple_loss=0.2064, pruned_loss=0.02755, over 4944.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.03539, over 972017.67 frames.], batch size: 29, lr: 2.62e-04
+2022-05-06 04:47:52,421 INFO [train.py:715] (3/8) Epoch 8, batch 15600, loss[loss=0.1308, simple_loss=0.2065, pruned_loss=0.02759, over 4738.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03573, over 972019.96 frames.], batch size: 16, lr: 2.62e-04
+2022-05-06 04:48:32,584 INFO [train.py:715] (3/8) Epoch 8, batch 15650, loss[loss=0.1255, simple_loss=0.1974, pruned_loss=0.02683, over 4908.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03589, over 971949.21 frames.], batch size: 23, lr: 2.62e-04
+2022-05-06 04:49:11,088 INFO [train.py:715] (3/8) Epoch 8, batch 15700, loss[loss=0.1675, simple_loss=0.2447, pruned_loss=0.04517, over 4739.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03594, over 972156.34 frames.], batch size: 16, lr: 2.62e-04
+2022-05-06 04:49:50,914 INFO [train.py:715] (3/8) Epoch 8, batch 15750, loss[loss=0.1266, simple_loss=0.1936, pruned_loss=0.02977, over 4785.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.03614, over 971569.18 frames.], batch size: 12, lr: 2.62e-04
+2022-05-06 04:50:30,388 INFO [train.py:715] (3/8) Epoch 8, batch 15800, loss[loss=0.1266, simple_loss=0.2062, pruned_loss=0.02347, over 4928.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.03556, over 971883.56 frames.], batch size: 29, lr: 2.61e-04
+2022-05-06 04:51:09,453 INFO [train.py:715] (3/8) Epoch 8, batch 15850, loss[loss=0.1264, simple_loss=0.2007, pruned_loss=0.026, over 4781.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2165, pruned_loss=0.03585, over 972431.16 frames.], batch size: 17, lr: 2.61e-04
+2022-05-06 04:51:48,554 INFO [train.py:715] (3/8) Epoch 8, batch 15900, loss[loss=0.1532, simple_loss=0.2205, pruned_loss=0.04294, over 4963.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03662, over 972044.39 frames.], batch size: 24, lr: 2.61e-04
+2022-05-06 04:52:27,777 INFO [train.py:715] (3/8) Epoch 8, batch 15950, loss[loss=0.1258, simple_loss=0.2144, pruned_loss=0.01859, over 4865.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.03611, over 971411.02 frames.], batch size: 20, lr: 2.61e-04
+2022-05-06 04:53:07,057 INFO [train.py:715] (3/8) Epoch 8, batch 16000, loss[loss=0.154, simple_loss=0.2121, pruned_loss=0.04792, over 4786.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2167, pruned_loss=0.03588, over 971749.63 frames.], batch size: 18, lr: 2.61e-04
+2022-05-06 04:53:45,654 INFO [train.py:715] (3/8) Epoch 8, batch 16050, loss[loss=0.1738, simple_loss=0.256, pruned_loss=0.04583, over 4820.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2163, pruned_loss=0.03544, over 972473.86 frames.], batch size: 13, lr: 2.61e-04
+2022-05-06 04:54:25,524 INFO [train.py:715] (3/8) Epoch 8, batch 16100, loss[loss=0.1628, simple_loss=0.2314, pruned_loss=0.04714, over 4904.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2164, pruned_loss=0.03548, over 972606.24 frames.], batch size: 23, lr: 2.61e-04
+2022-05-06 04:55:04,003 INFO [train.py:715] (3/8) Epoch 8, batch 16150, loss[loss=0.1316, simple_loss=0.2009, pruned_loss=0.03113, over 4870.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03498, over 973330.49 frames.], batch size: 20, lr: 2.61e-04
+2022-05-06 04:55:43,546 INFO [train.py:715] (3/8) Epoch 8, batch 16200, loss[loss=0.1382, simple_loss=0.205, pruned_loss=0.03567, over 4730.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2162, pruned_loss=0.03531, over 972998.68 frames.], batch size: 16, lr: 2.61e-04
+2022-05-06 04:56:21,929 INFO [train.py:715] (3/8) Epoch 8, batch 16250, loss[loss=0.1519, simple_loss=0.2337, pruned_loss=0.03504, over 4745.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03527, over 972208.11 frames.], batch size: 19, lr: 2.61e-04
+2022-05-06 04:57:01,391 INFO [train.py:715] (3/8) Epoch 8, batch 16300, loss[loss=0.1484, simple_loss=0.2271, pruned_loss=0.0349, over 4800.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2171, pruned_loss=0.03598, over 971767.19 frames.], batch size: 14, lr: 2.61e-04
+2022-05-06 04:57:40,826 INFO [train.py:715] (3/8) Epoch 8, batch 16350, loss[loss=0.1544, simple_loss=0.223, pruned_loss=0.04292, over 4892.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2179, pruned_loss=0.03666, over 971544.90 frames.], batch size: 19, lr: 2.61e-04
+2022-05-06 04:58:19,597 INFO [train.py:715] (3/8) Epoch 8, batch 16400, loss[loss=0.1565, simple_loss=0.2178, pruned_loss=0.04755, over 4957.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03625, over 971701.74 frames.], batch size: 35, lr: 2.61e-04
+2022-05-06 04:58:58,711 INFO [train.py:715] (3/8) Epoch 8, batch 16450, loss[loss=0.1372, simple_loss=0.2069, pruned_loss=0.03378, over 4954.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.03591, over 970741.15 frames.], batch size: 35, lr: 2.61e-04
+2022-05-06 04:59:37,556 INFO [train.py:715] (3/8) Epoch 8, batch 16500, loss[loss=0.1449, simple_loss=0.2166, pruned_loss=0.03663, over 4702.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2163, pruned_loss=0.03649, over 970367.78 frames.], batch size: 15, lr: 2.61e-04
+2022-05-06 05:00:17,262 INFO [train.py:715] (3/8) Epoch 8, batch 16550, loss[loss=0.1496, simple_loss=0.2185, pruned_loss=0.04032, over 4689.00 frames.], tot_loss[loss=0.1443, simple_loss=0.216, pruned_loss=0.03628, over 971043.82 frames.], batch size: 15, lr: 2.61e-04
+2022-05-06 05:00:56,284 INFO [train.py:715] (3/8) Epoch 8, batch 16600, loss[loss=0.1741, simple_loss=0.2309, pruned_loss=0.05864, over 4966.00 frames.], tot_loss[loss=0.145, simple_loss=0.2166, pruned_loss=0.03668, over 972057.65 frames.], batch size: 35, lr: 2.61e-04
+2022-05-06 05:01:35,314 INFO [train.py:715] (3/8) Epoch 8, batch 16650, loss[loss=0.1272, simple_loss=0.2098, pruned_loss=0.02229, over 4818.00 frames.], tot_loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.03655, over 972168.88 frames.], batch size: 12, lr: 2.61e-04
+2022-05-06 05:02:14,554 INFO [train.py:715] (3/8) Epoch 8, batch 16700, loss[loss=0.1888, simple_loss=0.2642, pruned_loss=0.05668, over 4895.00 frames.], tot_loss[loss=0.146, simple_loss=0.2179, pruned_loss=0.03707, over 972496.72 frames.], batch size: 39, lr: 2.61e-04
+2022-05-06 05:02:53,473 INFO [train.py:715] (3/8) Epoch 8, batch 16750, loss[loss=0.1339, simple_loss=0.2139, pruned_loss=0.02697, over 4856.00 frames.], tot_loss[loss=0.1449, simple_loss=0.217, pruned_loss=0.03641, over 972715.23 frames.], batch size: 15, lr: 2.61e-04
+2022-05-06 05:03:33,069 INFO [train.py:715] (3/8) Epoch 8, batch 16800, loss[loss=0.1435, simple_loss=0.2209, pruned_loss=0.03304, over 4953.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03606, over 972284.05 frames.], batch size: 21, lr: 2.61e-04
+2022-05-06 05:04:12,044 INFO [train.py:715] (3/8) Epoch 8, batch 16850, loss[loss=0.1228, simple_loss=0.1911, pruned_loss=0.02724, over 4893.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2156, pruned_loss=0.03569, over 972140.47 frames.], batch size: 19, lr: 2.61e-04
+2022-05-06 05:04:51,958 INFO [train.py:715] (3/8) Epoch 8, batch 16900, loss[loss=0.2032, simple_loss=0.2636, pruned_loss=0.07146, over 4696.00 frames.], tot_loss[loss=0.143, simple_loss=0.2152, pruned_loss=0.03538, over 971990.92 frames.], batch size: 15, lr: 2.61e-04
+2022-05-06 05:05:30,452 INFO [train.py:715] (3/8) Epoch 8, batch 16950, loss[loss=0.1421, simple_loss=0.2305, pruned_loss=0.02679, over 4988.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03574, over 972094.12 frames.], batch size: 28, lr: 2.61e-04
+2022-05-06 05:06:10,149 INFO [train.py:715] (3/8) Epoch 8, batch 17000, loss[loss=0.1619, simple_loss=0.2294, pruned_loss=0.04715, over 4918.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2155, pruned_loss=0.03598, over 972758.74 frames.], batch size: 39, lr: 2.61e-04
+2022-05-06 05:06:49,663 INFO [train.py:715] (3/8) Epoch 8, batch 17050, loss[loss=0.1295, simple_loss=0.2045, pruned_loss=0.02725, over 4774.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2149, pruned_loss=0.03578, over 972594.73 frames.], batch size: 18, lr: 2.61e-04
+2022-05-06 05:07:28,337 INFO [train.py:715] (3/8) Epoch 8, batch 17100, loss[loss=0.1603, simple_loss=0.2367, pruned_loss=0.04198, over 4882.00 frames.], tot_loss[loss=0.1441, simple_loss=0.216, pruned_loss=0.03615, over 972955.15 frames.], batch size: 16, lr: 2.61e-04
+2022-05-06 05:08:08,034 INFO [train.py:715] (3/8) Epoch 8, batch 17150, loss[loss=0.121, simple_loss=0.2001, pruned_loss=0.02098, over 4814.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03574, over 972791.46 frames.], batch size: 26, lr: 2.61e-04
+2022-05-06 05:08:47,211 INFO [train.py:715] (3/8) Epoch 8, batch 17200, loss[loss=0.1509, simple_loss=0.2175, pruned_loss=0.04216, over 4897.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03545, over 972318.62 frames.], batch size: 39, lr: 2.61e-04
+2022-05-06 05:09:26,326 INFO [train.py:715] (3/8) Epoch 8, batch 17250, loss[loss=0.1533, simple_loss=0.2217, pruned_loss=0.04249, over 4763.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03575, over 973743.69 frames.], batch size: 12, lr: 2.61e-04
+2022-05-06 05:10:04,657 INFO [train.py:715] (3/8) Epoch 8, batch 17300, loss[loss=0.1247, simple_loss=0.193, pruned_loss=0.02818, over 4975.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2158, pruned_loss=0.03601, over 974400.36 frames.], batch size: 14, lr: 2.61e-04
+2022-05-06 05:10:44,495 INFO [train.py:715] (3/8) Epoch 8, batch 17350, loss[loss=0.1494, simple_loss=0.2102, pruned_loss=0.04424, over 4858.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.03605, over 972921.00 frames.], batch size: 32, lr: 2.61e-04
+2022-05-06 05:11:23,593 INFO [train.py:715] (3/8) Epoch 8, batch 17400, loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02839, over 4962.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03586, over 973953.44 frames.], batch size: 24, lr: 2.61e-04
+2022-05-06 05:12:02,692 INFO [train.py:715] (3/8) Epoch 8, batch 17450, loss[loss=0.1521, simple_loss=0.2189, pruned_loss=0.04267, over 4840.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03585, over 973406.39 frames.], batch size: 12, lr: 2.61e-04
+2022-05-06 05:12:42,123 INFO [train.py:715] (3/8) Epoch 8, batch 17500, loss[loss=0.1301, simple_loss=0.2104, pruned_loss=0.02493, over 4917.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2147, pruned_loss=0.03549, over 974329.92 frames.], batch size: 29, lr: 2.61e-04
+2022-05-06 05:13:23,167 INFO [train.py:715] (3/8) Epoch 8, batch 17550, loss[loss=0.1371, simple_loss=0.2139, pruned_loss=0.03012, over 4904.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03516, over 974391.54 frames.], batch size: 19, lr: 2.61e-04
+2022-05-06 05:14:02,977 INFO [train.py:715] (3/8) Epoch 8, batch 17600, loss[loss=0.1459, simple_loss=0.2172, pruned_loss=0.0373, over 4968.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2141, pruned_loss=0.03502, over 974763.78 frames.], batch size: 39, lr: 2.61e-04
+2022-05-06 05:14:41,724 INFO [train.py:715] (3/8) Epoch 8, batch 17650, loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03468, over 4856.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2145, pruned_loss=0.03513, over 975078.42 frames.], batch size: 32, lr: 2.61e-04
+2022-05-06 05:15:22,838 INFO [train.py:715] (3/8) Epoch 8, batch 17700, loss[loss=0.1514, simple_loss=0.2251, pruned_loss=0.0388, over 4925.00 frames.], tot_loss[loss=0.1421, simple_loss=0.214, pruned_loss=0.03508, over 974906.70 frames.], batch size: 18, lr: 2.61e-04
+2022-05-06 05:16:02,814 INFO [train.py:715] (3/8) Epoch 8, batch 17750, loss[loss=0.151, simple_loss=0.2236, pruned_loss=0.03922, over 4916.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2141, pruned_loss=0.03476, over 974544.49 frames.], batch size: 39, lr: 2.61e-04
+2022-05-06 05:16:43,290 INFO [train.py:715] (3/8) Epoch 8, batch 17800, loss[loss=0.1405, simple_loss=0.2056, pruned_loss=0.03769, over 4906.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03543, over 973389.97 frames.], batch size: 18, lr: 2.61e-04
+2022-05-06 05:17:23,945 INFO [train.py:715] (3/8) Epoch 8, batch 17850, loss[loss=0.1659, simple_loss=0.2279, pruned_loss=0.05197, over 4864.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03582, over 973374.05 frames.], batch size: 32, lr: 2.61e-04
+2022-05-06 05:18:04,811 INFO [train.py:715] (3/8) Epoch 8, batch 17900, loss[loss=0.1393, simple_loss=0.2156, pruned_loss=0.0315, over 4817.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03534, over 972945.98 frames.], batch size: 25, lr: 2.61e-04
+2022-05-06 05:18:46,218 INFO [train.py:715] (3/8) Epoch 8, batch 17950, loss[loss=0.1405, simple_loss=0.2124, pruned_loss=0.0343, over 4865.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2151, pruned_loss=0.03572, over 973191.45 frames.], batch size: 20, lr: 2.61e-04
+2022-05-06 05:19:26,621 INFO [train.py:715] (3/8) Epoch 8, batch 18000, loss[loss=0.1656, simple_loss=0.2311, pruned_loss=0.05003, over 4897.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2149, pruned_loss=0.03596, over 972275.63 frames.], batch size: 19, lr: 2.61e-04
+2022-05-06 05:19:26,622 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 05:19:36,397 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1073, simple_loss=0.1919, pruned_loss=0.01138, over 914524.00 frames.
+2022-05-06 05:20:17,012 INFO [train.py:715] (3/8) Epoch 8, batch 18050, loss[loss=0.1087, simple_loss=0.1833, pruned_loss=0.01709, over 4975.00 frames.], tot_loss[loss=0.1423, simple_loss=0.214, pruned_loss=0.0353, over 972448.42 frames.], batch size: 14, lr: 2.60e-04
+2022-05-06 05:20:59,052 INFO [train.py:715] (3/8) Epoch 8, batch 18100, loss[loss=0.1446, simple_loss=0.2104, pruned_loss=0.03942, over 4792.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2147, pruned_loss=0.03581, over 972314.30 frames.], batch size: 13, lr: 2.60e-04
+2022-05-06 05:21:40,103 INFO [train.py:715] (3/8) Epoch 8, batch 18150, loss[loss=0.1362, simple_loss=0.2106, pruned_loss=0.03088, over 4930.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2151, pruned_loss=0.03593, over 972772.32 frames.], batch size: 18, lr: 2.60e-04
+2022-05-06 05:22:21,017 INFO [train.py:715] (3/8) Epoch 8, batch 18200, loss[loss=0.145, simple_loss=0.2149, pruned_loss=0.03758, over 4762.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2154, pruned_loss=0.03615, over 972552.68 frames.], batch size: 19, lr: 2.60e-04
+2022-05-06 05:23:02,793 INFO [train.py:715] (3/8) Epoch 8, batch 18250, loss[loss=0.1281, simple_loss=0.2004, pruned_loss=0.02791, over 4766.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2154, pruned_loss=0.03595, over 972844.52 frames.], batch size: 17, lr: 2.60e-04
+2022-05-06 05:23:43,814 INFO [train.py:715] (3/8) Epoch 8, batch 18300, loss[loss=0.1531, simple_loss=0.2344, pruned_loss=0.03596, over 4979.00 frames.], tot_loss[loss=0.144, simple_loss=0.2155, pruned_loss=0.03627, over 972470.75 frames.], batch size: 25, lr: 2.60e-04
+2022-05-06 05:24:25,289 INFO [train.py:715] (3/8) Epoch 8, batch 18350, loss[loss=0.1316, simple_loss=0.213, pruned_loss=0.02511, over 4873.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2153, pruned_loss=0.03597, over 972878.57 frames.], batch size: 16, lr: 2.60e-04
+2022-05-06 05:25:06,145 INFO [train.py:715] (3/8) Epoch 8, batch 18400, loss[loss=0.1894, simple_loss=0.2528, pruned_loss=0.063, over 4905.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2163, pruned_loss=0.03649, over 972827.21 frames.], batch size: 18, lr: 2.60e-04
+2022-05-06 05:25:47,830 INFO [train.py:715] (3/8) Epoch 8, batch 18450, loss[loss=0.1486, simple_loss=0.2184, pruned_loss=0.03934, over 4844.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2165, pruned_loss=0.03651, over 972026.66 frames.], batch size: 15, lr: 2.60e-04
+2022-05-06 05:26:28,559 INFO [train.py:715] (3/8) Epoch 8, batch 18500, loss[loss=0.1363, simple_loss=0.207, pruned_loss=0.03281, over 4815.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2154, pruned_loss=0.03592, over 972100.78 frames.], batch size: 25, lr: 2.60e-04
+2022-05-06 05:27:08,966 INFO [train.py:715] (3/8) Epoch 8, batch 18550, loss[loss=0.1435, simple_loss=0.2106, pruned_loss=0.03816, over 4872.00 frames.], tot_loss[loss=0.1443, simple_loss=0.216, pruned_loss=0.03626, over 971743.75 frames.], batch size: 16, lr: 2.60e-04
+2022-05-06 05:27:50,214 INFO [train.py:715] (3/8) Epoch 8, batch 18600, loss[loss=0.1153, simple_loss=0.1885, pruned_loss=0.02106, over 4749.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03583, over 971246.82 frames.], batch size: 16, lr: 2.60e-04
+2022-05-06 05:28:30,417 INFO [train.py:715] (3/8) Epoch 8, batch 18650, loss[loss=0.1604, simple_loss=0.2272, pruned_loss=0.04683, over 4851.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2152, pruned_loss=0.03562, over 971460.25 frames.], batch size: 32, lr: 2.60e-04
+2022-05-06 05:29:09,922 INFO [train.py:715] (3/8) Epoch 8, batch 18700, loss[loss=0.1566, simple_loss=0.2207, pruned_loss=0.04628, over 4851.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2162, pruned_loss=0.03635, over 971336.32 frames.], batch size: 32, lr: 2.60e-04
+2022-05-06 05:29:49,892 INFO [train.py:715] (3/8) Epoch 8, batch 18750, loss[loss=0.1466, simple_loss=0.202, pruned_loss=0.04558, over 4818.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.0363, over 970798.41 frames.], batch size: 14, lr: 2.60e-04
+2022-05-06 05:30:30,985 INFO [train.py:715] (3/8) Epoch 8, batch 18800, loss[loss=0.1331, simple_loss=0.2006, pruned_loss=0.03285, over 4969.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2154, pruned_loss=0.03608, over 970242.47 frames.], batch size: 35, lr: 2.60e-04
+2022-05-06 05:31:10,611 INFO [train.py:715] (3/8) Epoch 8, batch 18850, loss[loss=0.1459, simple_loss=0.2247, pruned_loss=0.03358, over 4956.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2156, pruned_loss=0.03611, over 970970.51 frames.], batch size: 15, lr: 2.60e-04
+2022-05-06 05:31:50,015 INFO [train.py:715] (3/8) Epoch 8, batch 18900, loss[loss=0.1626, simple_loss=0.244, pruned_loss=0.04063, over 4905.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2154, pruned_loss=0.03601, over 971681.03 frames.], batch size: 17, lr: 2.60e-04
+2022-05-06 05:32:30,283 INFO [train.py:715] (3/8) Epoch 8, batch 18950, loss[loss=0.1129, simple_loss=0.1829, pruned_loss=0.02148, over 4763.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2155, pruned_loss=0.03598, over 972368.82 frames.], batch size: 19, lr: 2.60e-04
+2022-05-06 05:33:10,171 INFO [train.py:715] (3/8) Epoch 8, batch 19000, loss[loss=0.1563, simple_loss=0.2305, pruned_loss=0.04106, over 4838.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2154, pruned_loss=0.03621, over 972801.33 frames.], batch size: 15, lr: 2.60e-04
+2022-05-06 05:33:50,106 INFO [train.py:715] (3/8) Epoch 8, batch 19050, loss[loss=0.1478, simple_loss=0.2159, pruned_loss=0.03983, over 4776.00 frames.], tot_loss[loss=0.145, simple_loss=0.2165, pruned_loss=0.03669, over 972572.08 frames.], batch size: 14, lr: 2.60e-04
+2022-05-06 05:34:31,411 INFO [train.py:715] (3/8) Epoch 8, batch 19100, loss[loss=0.1411, simple_loss=0.2173, pruned_loss=0.03243, over 4847.00 frames.], tot_loss[loss=0.144, simple_loss=0.2156, pruned_loss=0.03615, over 972805.31 frames.], batch size: 30, lr: 2.60e-04
+2022-05-06 05:35:13,327 INFO [train.py:715] (3/8) Epoch 8, batch 19150, loss[loss=0.136, simple_loss=0.2051, pruned_loss=0.03343, over 4774.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2152, pruned_loss=0.03566, over 972473.32 frames.], batch size: 18, lr: 2.60e-04
+2022-05-06 05:35:55,000 INFO [train.py:715] (3/8) Epoch 8, batch 19200, loss[loss=0.1289, simple_loss=0.2003, pruned_loss=0.02874, over 4932.00 frames.], tot_loss[loss=0.143, simple_loss=0.2151, pruned_loss=0.03549, over 972690.12 frames.], batch size: 21, lr: 2.60e-04
+2022-05-06 05:36:35,250 INFO [train.py:715] (3/8) Epoch 8, batch 19250, loss[loss=0.1193, simple_loss=0.2027, pruned_loss=0.01795, over 4933.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03583, over 972155.72 frames.], batch size: 29, lr: 2.60e-04
+2022-05-06 05:37:17,448 INFO [train.py:715] (3/8) Epoch 8, batch 19300, loss[loss=0.1271, simple_loss=0.199, pruned_loss=0.02758, over 4793.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03565, over 972424.33 frames.], batch size: 24, lr: 2.60e-04
+2022-05-06 05:37:58,607 INFO [train.py:715] (3/8) Epoch 8, batch 19350, loss[loss=0.1321, simple_loss=0.1977, pruned_loss=0.03326, over 4793.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2158, pruned_loss=0.03623, over 972372.23 frames.], batch size: 12, lr: 2.60e-04
+2022-05-06 05:38:39,847 INFO [train.py:715] (3/8) Epoch 8, batch 19400, loss[loss=0.1545, simple_loss=0.2256, pruned_loss=0.0417, over 4750.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2158, pruned_loss=0.03631, over 971455.45 frames.], batch size: 16, lr: 2.60e-04
+2022-05-06 05:39:21,785 INFO [train.py:715] (3/8) Epoch 8, batch 19450, loss[loss=0.1409, simple_loss=0.2076, pruned_loss=0.03712, over 4923.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03606, over 971369.41 frames.], batch size: 18, lr: 2.60e-04
+2022-05-06 05:40:03,267 INFO [train.py:715] (3/8) Epoch 8, batch 19500, loss[loss=0.1384, simple_loss=0.2141, pruned_loss=0.03136, over 4911.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.03645, over 971473.80 frames.], batch size: 29, lr: 2.60e-04
+2022-05-06 05:40:44,554 INFO [train.py:715] (3/8) Epoch 8, batch 19550, loss[loss=0.1355, simple_loss=0.2043, pruned_loss=0.03333, over 4760.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03621, over 971380.38 frames.], batch size: 19, lr: 2.60e-04
+2022-05-06 05:41:25,026 INFO [train.py:715] (3/8) Epoch 8, batch 19600, loss[loss=0.1264, simple_loss=0.1988, pruned_loss=0.02703, over 4935.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03599, over 971226.51 frames.], batch size: 21, lr: 2.60e-04
+2022-05-06 05:42:06,540 INFO [train.py:715] (3/8) Epoch 8, batch 19650, loss[loss=0.1212, simple_loss=0.1923, pruned_loss=0.025, over 4832.00 frames.], tot_loss[loss=0.143, simple_loss=0.2152, pruned_loss=0.03541, over 971272.06 frames.], batch size: 13, lr: 2.60e-04
+2022-05-06 05:42:47,220 INFO [train.py:715] (3/8) Epoch 8, batch 19700, loss[loss=0.1241, simple_loss=0.1976, pruned_loss=0.02533, over 4883.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2149, pruned_loss=0.03546, over 971778.39 frames.], batch size: 22, lr: 2.60e-04
+2022-05-06 05:43:28,184 INFO [train.py:715] (3/8) Epoch 8, batch 19750, loss[loss=0.1465, simple_loss=0.2261, pruned_loss=0.0335, over 4955.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.0351, over 972149.82 frames.], batch size: 28, lr: 2.60e-04
+2022-05-06 05:44:09,860 INFO [train.py:715] (3/8) Epoch 8, batch 19800, loss[loss=0.1436, simple_loss=0.2247, pruned_loss=0.03121, over 4778.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.0347, over 971462.84 frames.], batch size: 19, lr: 2.60e-04
+2022-05-06 05:44:50,896 INFO [train.py:715] (3/8) Epoch 8, batch 19850, loss[loss=0.1124, simple_loss=0.179, pruned_loss=0.02291, over 4774.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03571, over 971978.27 frames.], batch size: 12, lr: 2.60e-04
+2022-05-06 05:45:31,214 INFO [train.py:715] (3/8) Epoch 8, batch 19900, loss[loss=0.1566, simple_loss=0.2241, pruned_loss=0.04453, over 4871.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2154, pruned_loss=0.03555, over 971899.13 frames.], batch size: 38, lr: 2.60e-04
+2022-05-06 05:46:10,974 INFO [train.py:715] (3/8) Epoch 8, batch 19950, loss[loss=0.1294, simple_loss=0.2112, pruned_loss=0.0238, over 4892.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03586, over 972016.31 frames.], batch size: 19, lr: 2.60e-04
+2022-05-06 05:46:51,593 INFO [train.py:715] (3/8) Epoch 8, batch 20000, loss[loss=0.1251, simple_loss=0.1919, pruned_loss=0.02913, over 4760.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2153, pruned_loss=0.03555, over 972460.66 frames.], batch size: 12, lr: 2.60e-04
+2022-05-06 05:47:32,110 INFO [train.py:715] (3/8) Epoch 8, batch 20050, loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.04082, over 4847.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03521, over 971983.93 frames.], batch size: 30, lr: 2.60e-04
+2022-05-06 05:48:12,624 INFO [train.py:715] (3/8) Epoch 8, batch 20100, loss[loss=0.1116, simple_loss=0.1778, pruned_loss=0.0227, over 4830.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03486, over 972081.35 frames.], batch size: 26, lr: 2.60e-04
+2022-05-06 05:48:53,761 INFO [train.py:715] (3/8) Epoch 8, batch 20150, loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02912, over 4932.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.03505, over 972156.58 frames.], batch size: 29, lr: 2.60e-04
+2022-05-06 05:49:34,576 INFO [train.py:715] (3/8) Epoch 8, batch 20200, loss[loss=0.1074, simple_loss=0.1759, pruned_loss=0.01949, over 4685.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03492, over 971618.10 frames.], batch size: 12, lr: 2.60e-04
+2022-05-06 05:50:15,441 INFO [train.py:715] (3/8) Epoch 8, batch 20250, loss[loss=0.151, simple_loss=0.2183, pruned_loss=0.04187, over 4836.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03487, over 971556.76 frames.], batch size: 30, lr: 2.60e-04
+2022-05-06 05:50:56,709 INFO [train.py:715] (3/8) Epoch 8, batch 20300, loss[loss=0.1251, simple_loss=0.1979, pruned_loss=0.02611, over 4986.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2151, pruned_loss=0.03525, over 971808.24 frames.], batch size: 25, lr: 2.60e-04
+2022-05-06 05:51:37,707 INFO [train.py:715] (3/8) Epoch 8, batch 20350, loss[loss=0.1557, simple_loss=0.2343, pruned_loss=0.03858, over 4821.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.0356, over 971486.90 frames.], batch size: 15, lr: 2.59e-04
+2022-05-06 05:52:18,258 INFO [train.py:715] (3/8) Epoch 8, batch 20400, loss[loss=0.1264, simple_loss=0.2014, pruned_loss=0.02573, over 4816.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.0352, over 971912.88 frames.], batch size: 15, lr: 2.59e-04
+2022-05-06 05:52:58,520 INFO [train.py:715] (3/8) Epoch 8, batch 20450, loss[loss=0.1506, simple_loss=0.2215, pruned_loss=0.03982, over 4744.00 frames.], tot_loss[loss=0.1439, simple_loss=0.216, pruned_loss=0.03588, over 971442.09 frames.], batch size: 16, lr: 2.59e-04
+2022-05-06 05:53:39,597 INFO [train.py:715] (3/8) Epoch 8, batch 20500, loss[loss=0.1771, simple_loss=0.2384, pruned_loss=0.05788, over 4853.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03588, over 971614.35 frames.], batch size: 34, lr: 2.59e-04
+2022-05-06 05:54:20,087 INFO [train.py:715] (3/8) Epoch 8, batch 20550, loss[loss=0.1554, simple_loss=0.2262, pruned_loss=0.04228, over 4916.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03615, over 972379.75 frames.], batch size: 39, lr: 2.59e-04
+2022-05-06 05:55:00,459 INFO [train.py:715] (3/8) Epoch 8, batch 20600, loss[loss=0.135, simple_loss=0.2127, pruned_loss=0.02866, over 4897.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2163, pruned_loss=0.03568, over 971913.16 frames.], batch size: 22, lr: 2.59e-04
+2022-05-06 05:55:41,411 INFO [train.py:715] (3/8) Epoch 8, batch 20650, loss[loss=0.1397, simple_loss=0.1958, pruned_loss=0.04182, over 4640.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.03565, over 972685.76 frames.], batch size: 13, lr: 2.59e-04
+2022-05-06 05:56:22,562 INFO [train.py:715] (3/8) Epoch 8, batch 20700, loss[loss=0.1355, simple_loss=0.2107, pruned_loss=0.03019, over 4852.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03535, over 972820.93 frames.], batch size: 30, lr: 2.59e-04
+2022-05-06 05:57:02,756 INFO [train.py:715] (3/8) Epoch 8, batch 20750, loss[loss=0.1435, simple_loss=0.2165, pruned_loss=0.0353, over 4938.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2168, pruned_loss=0.03586, over 972426.30 frames.], batch size: 23, lr: 2.59e-04
+2022-05-06 05:57:42,967 INFO [train.py:715] (3/8) Epoch 8, batch 20800, loss[loss=0.1271, simple_loss=0.2031, pruned_loss=0.0256, over 4832.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.03626, over 972761.50 frames.], batch size: 13, lr: 2.59e-04
+2022-05-06 05:58:24,025 INFO [train.py:715] (3/8) Epoch 8, batch 20850, loss[loss=0.1485, simple_loss=0.217, pruned_loss=0.04002, over 4753.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03596, over 972492.90 frames.], batch size: 14, lr: 2.59e-04
+2022-05-06 05:59:04,432 INFO [train.py:715] (3/8) Epoch 8, batch 20900, loss[loss=0.1358, simple_loss=0.2071, pruned_loss=0.03227, over 4971.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2169, pruned_loss=0.03606, over 973503.74 frames.], batch size: 35, lr: 2.59e-04
+2022-05-06 05:59:43,024 INFO [train.py:715] (3/8) Epoch 8, batch 20950, loss[loss=0.1229, simple_loss=0.1954, pruned_loss=0.02517, over 4744.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03616, over 973412.30 frames.], batch size: 12, lr: 2.59e-04
+2022-05-06 06:00:22,705 INFO [train.py:715] (3/8) Epoch 8, batch 21000, loss[loss=0.1309, simple_loss=0.2034, pruned_loss=0.02917, over 4846.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2158, pruned_loss=0.03565, over 973754.13 frames.], batch size: 20, lr: 2.59e-04
+2022-05-06 06:00:22,705 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 06:00:32,254 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1072, simple_loss=0.1919, pruned_loss=0.01129, over 914524.00 frames.
+2022-05-06 06:01:12,651 INFO [train.py:715] (3/8) Epoch 8, batch 21050, loss[loss=0.1604, simple_loss=0.2285, pruned_loss=0.04611, over 4938.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.03513, over 973647.57 frames.], batch size: 21, lr: 2.59e-04
+2022-05-06 06:01:52,992 INFO [train.py:715] (3/8) Epoch 8, batch 21100, loss[loss=0.1492, simple_loss=0.2223, pruned_loss=0.03806, over 4755.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03487, over 972589.46 frames.], batch size: 19, lr: 2.59e-04
+2022-05-06 06:02:31,463 INFO [train.py:715] (3/8) Epoch 8, batch 21150, loss[loss=0.1864, simple_loss=0.2418, pruned_loss=0.0655, over 4770.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03522, over 972234.11 frames.], batch size: 17, lr: 2.59e-04
+2022-05-06 06:03:10,261 INFO [train.py:715] (3/8) Epoch 8, batch 21200, loss[loss=0.1463, simple_loss=0.2173, pruned_loss=0.03763, over 4752.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2145, pruned_loss=0.03546, over 972203.82 frames.], batch size: 16, lr: 2.59e-04
+2022-05-06 06:03:49,965 INFO [train.py:715] (3/8) Epoch 8, batch 21250, loss[loss=0.1369, simple_loss=0.2029, pruned_loss=0.03542, over 4731.00 frames.], tot_loss[loss=0.1434, simple_loss=0.215, pruned_loss=0.03589, over 972265.24 frames.], batch size: 16, lr: 2.59e-04
+2022-05-06 06:04:29,231 INFO [train.py:715] (3/8) Epoch 8, batch 21300, loss[loss=0.1406, simple_loss=0.205, pruned_loss=0.03815, over 4776.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2151, pruned_loss=0.03606, over 972306.85 frames.], batch size: 14, lr: 2.59e-04
+2022-05-06 06:05:07,760 INFO [train.py:715] (3/8) Epoch 8, batch 21350, loss[loss=0.1221, simple_loss=0.1949, pruned_loss=0.02469, over 4812.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2142, pruned_loss=0.0352, over 972063.61 frames.], batch size: 25, lr: 2.59e-04
+2022-05-06 06:05:47,406 INFO [train.py:715] (3/8) Epoch 8, batch 21400, loss[loss=0.1482, simple_loss=0.2227, pruned_loss=0.03689, over 4920.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2142, pruned_loss=0.03515, over 970692.52 frames.], batch size: 18, lr: 2.59e-04
+2022-05-06 06:06:27,498 INFO [train.py:715] (3/8) Epoch 8, batch 21450, loss[loss=0.1697, simple_loss=0.2366, pruned_loss=0.05145, over 4745.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2136, pruned_loss=0.03496, over 971159.00 frames.], batch size: 19, lr: 2.59e-04
+2022-05-06 06:07:06,787 INFO [train.py:715] (3/8) Epoch 8, batch 21500, loss[loss=0.1644, simple_loss=0.2238, pruned_loss=0.0525, over 4831.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2144, pruned_loss=0.03522, over 970641.25 frames.], batch size: 15, lr: 2.59e-04
+2022-05-06 06:07:45,793 INFO [train.py:715] (3/8) Epoch 8, batch 21550, loss[loss=0.1326, simple_loss=0.1964, pruned_loss=0.03443, over 4841.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2149, pruned_loss=0.03537, over 970988.11 frames.], batch size: 15, lr: 2.59e-04
+2022-05-06 06:08:25,814 INFO [train.py:715] (3/8) Epoch 8, batch 21600, loss[loss=0.1228, simple_loss=0.1899, pruned_loss=0.02785, over 4975.00 frames.], tot_loss[loss=0.1431, simple_loss=0.215, pruned_loss=0.0356, over 971012.13 frames.], batch size: 33, lr: 2.59e-04
+2022-05-06 06:09:04,795 INFO [train.py:715] (3/8) Epoch 8, batch 21650, loss[loss=0.146, simple_loss=0.219, pruned_loss=0.03653, over 4951.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.03597, over 971660.91 frames.], batch size: 35, lr: 2.59e-04
+2022-05-06 06:09:43,494 INFO [train.py:715] (3/8) Epoch 8, batch 21700, loss[loss=0.1245, simple_loss=0.1933, pruned_loss=0.02785, over 4969.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03583, over 972612.64 frames.], batch size: 35, lr: 2.59e-04
+2022-05-06 06:10:23,860 INFO [train.py:715] (3/8) Epoch 8, batch 21750, loss[loss=0.1594, simple_loss=0.238, pruned_loss=0.04038, over 4891.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.03563, over 971804.43 frames.], batch size: 22, lr: 2.59e-04
+2022-05-06 06:11:03,700 INFO [train.py:715] (3/8) Epoch 8, batch 21800, loss[loss=0.1655, simple_loss=0.2319, pruned_loss=0.0496, over 4740.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03603, over 972175.35 frames.], batch size: 16, lr: 2.59e-04
+2022-05-06 06:11:42,817 INFO [train.py:715] (3/8) Epoch 8, batch 21850, loss[loss=0.1369, simple_loss=0.2132, pruned_loss=0.03028, over 4990.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03599, over 972918.00 frames.], batch size: 26, lr: 2.59e-04
+2022-05-06 06:12:21,178 INFO [train.py:715] (3/8) Epoch 8, batch 21900, loss[loss=0.1561, simple_loss=0.2236, pruned_loss=0.04427, over 4905.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2163, pruned_loss=0.03621, over 972672.83 frames.], batch size: 17, lr: 2.59e-04
+2022-05-06 06:13:00,617 INFO [train.py:715] (3/8) Epoch 8, batch 21950, loss[loss=0.1417, simple_loss=0.218, pruned_loss=0.03269, over 4904.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2156, pruned_loss=0.03577, over 973296.02 frames.], batch size: 18, lr: 2.59e-04
+2022-05-06 06:13:39,700 INFO [train.py:715] (3/8) Epoch 8, batch 22000, loss[loss=0.1508, simple_loss=0.2201, pruned_loss=0.04069, over 4854.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03565, over 973736.91 frames.], batch size: 32, lr: 2.59e-04
+2022-05-06 06:14:18,327 INFO [train.py:715] (3/8) Epoch 8, batch 22050, loss[loss=0.1363, simple_loss=0.2122, pruned_loss=0.03021, over 4841.00 frames.], tot_loss[loss=0.1431, simple_loss=0.215, pruned_loss=0.03555, over 973354.61 frames.], batch size: 30, lr: 2.59e-04
+2022-05-06 06:14:58,044 INFO [train.py:715] (3/8) Epoch 8, batch 22100, loss[loss=0.1412, simple_loss=0.2281, pruned_loss=0.02717, over 4737.00 frames.], tot_loss[loss=0.1442, simple_loss=0.216, pruned_loss=0.03617, over 973225.82 frames.], batch size: 16, lr: 2.59e-04
+2022-05-06 06:15:37,420 INFO [train.py:715] (3/8) Epoch 8, batch 22150, loss[loss=0.1937, simple_loss=0.26, pruned_loss=0.06374, over 4871.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2164, pruned_loss=0.03609, over 972236.08 frames.], batch size: 32, lr: 2.59e-04
+2022-05-06 06:16:16,521 INFO [train.py:715] (3/8) Epoch 8, batch 22200, loss[loss=0.1363, simple_loss=0.1996, pruned_loss=0.03653, over 4779.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2172, pruned_loss=0.03631, over 972824.58 frames.], batch size: 18, lr: 2.59e-04
+2022-05-06 06:16:55,351 INFO [train.py:715] (3/8) Epoch 8, batch 22250, loss[loss=0.1844, simple_loss=0.2564, pruned_loss=0.05621, over 4820.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2174, pruned_loss=0.03648, over 973037.58 frames.], batch size: 26, lr: 2.59e-04
+2022-05-06 06:17:34,565 INFO [train.py:715] (3/8) Epoch 8, batch 22300, loss[loss=0.1188, simple_loss=0.1977, pruned_loss=0.01998, over 4884.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2172, pruned_loss=0.03622, over 973045.46 frames.], batch size: 22, lr: 2.59e-04
+2022-05-06 06:18:13,309 INFO [train.py:715] (3/8) Epoch 8, batch 22350, loss[loss=0.1511, simple_loss=0.2289, pruned_loss=0.03665, over 4800.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03603, over 971499.10 frames.], batch size: 21, lr: 2.59e-04
+2022-05-06 06:18:51,905 INFO [train.py:715] (3/8) Epoch 8, batch 22400, loss[loss=0.1339, simple_loss=0.218, pruned_loss=0.02487, over 4964.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2166, pruned_loss=0.03562, over 971406.46 frames.], batch size: 24, lr: 2.59e-04
+2022-05-06 06:19:31,236 INFO [train.py:715] (3/8) Epoch 8, batch 22450, loss[loss=0.1415, simple_loss=0.2061, pruned_loss=0.03847, over 4765.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2162, pruned_loss=0.0355, over 971330.01 frames.], batch size: 17, lr: 2.59e-04
+2022-05-06 06:20:10,736 INFO [train.py:715] (3/8) Epoch 8, batch 22500, loss[loss=0.1226, simple_loss=0.1958, pruned_loss=0.02475, over 4797.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2155, pruned_loss=0.03545, over 972109.29 frames.], batch size: 21, lr: 2.59e-04
+2022-05-06 06:20:49,333 INFO [train.py:715] (3/8) Epoch 8, batch 22550, loss[loss=0.1433, simple_loss=0.2249, pruned_loss=0.03088, over 4809.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.03497, over 971940.07 frames.], batch size: 25, lr: 2.59e-04
+2022-05-06 06:21:28,254 INFO [train.py:715] (3/8) Epoch 8, batch 22600, loss[loss=0.1365, simple_loss=0.1984, pruned_loss=0.03725, over 4820.00 frames.], tot_loss[loss=0.142, simple_loss=0.2146, pruned_loss=0.03474, over 973437.20 frames.], batch size: 13, lr: 2.59e-04
+2022-05-06 06:22:07,733 INFO [train.py:715] (3/8) Epoch 8, batch 22650, loss[loss=0.1536, simple_loss=0.2342, pruned_loss=0.03654, over 4772.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03548, over 973015.90 frames.], batch size: 17, lr: 2.58e-04
+2022-05-06 06:22:46,461 INFO [train.py:715] (3/8) Epoch 8, batch 22700, loss[loss=0.1588, simple_loss=0.2359, pruned_loss=0.04085, over 4714.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2157, pruned_loss=0.03509, over 972562.71 frames.], batch size: 15, lr: 2.58e-04
+2022-05-06 06:23:24,782 INFO [train.py:715] (3/8) Epoch 8, batch 22750, loss[loss=0.1746, simple_loss=0.2375, pruned_loss=0.05583, over 4706.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03513, over 972887.12 frames.], batch size: 15, lr: 2.58e-04
+2022-05-06 06:24:04,601 INFO [train.py:715] (3/8) Epoch 8, batch 22800, loss[loss=0.1317, simple_loss=0.2113, pruned_loss=0.02603, over 4931.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2155, pruned_loss=0.03469, over 972773.28 frames.], batch size: 23, lr: 2.58e-04
+2022-05-06 06:24:43,771 INFO [train.py:715] (3/8) Epoch 8, batch 22850, loss[loss=0.1476, simple_loss=0.2253, pruned_loss=0.03492, over 4791.00 frames.], tot_loss[loss=0.143, simple_loss=0.2162, pruned_loss=0.03491, over 971785.59 frames.], batch size: 24, lr: 2.58e-04
+2022-05-06 06:25:22,842 INFO [train.py:715] (3/8) Epoch 8, batch 22900, loss[loss=0.1885, simple_loss=0.2489, pruned_loss=0.06401, over 4861.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2161, pruned_loss=0.03501, over 972742.44 frames.], batch size: 30, lr: 2.58e-04
+2022-05-06 06:26:01,957 INFO [train.py:715] (3/8) Epoch 8, batch 22950, loss[loss=0.1499, simple_loss=0.2122, pruned_loss=0.04378, over 4889.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2157, pruned_loss=0.03494, over 973116.07 frames.], batch size: 22, lr: 2.58e-04
+2022-05-06 06:26:41,733 INFO [train.py:715] (3/8) Epoch 8, batch 23000, loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03246, over 4829.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2153, pruned_loss=0.03464, over 972301.28 frames.], batch size: 26, lr: 2.58e-04
+2022-05-06 06:27:20,528 INFO [train.py:715] (3/8) Epoch 8, batch 23050, loss[loss=0.146, simple_loss=0.2252, pruned_loss=0.03339, over 4941.00 frames.], tot_loss[loss=0.1429, simple_loss=0.216, pruned_loss=0.03495, over 972783.01 frames.], batch size: 23, lr: 2.58e-04
+2022-05-06 06:27:59,220 INFO [train.py:715] (3/8) Epoch 8, batch 23100, loss[loss=0.1626, simple_loss=0.232, pruned_loss=0.04656, over 4699.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2161, pruned_loss=0.03518, over 972756.21 frames.], batch size: 15, lr: 2.58e-04
+2022-05-06 06:28:39,376 INFO [train.py:715] (3/8) Epoch 8, batch 23150, loss[loss=0.144, simple_loss=0.2093, pruned_loss=0.03933, over 4990.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2161, pruned_loss=0.03507, over 972297.50 frames.], batch size: 16, lr: 2.58e-04
+2022-05-06 06:29:18,754 INFO [train.py:715] (3/8) Epoch 8, batch 23200, loss[loss=0.168, simple_loss=0.2285, pruned_loss=0.05372, over 4793.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2155, pruned_loss=0.03508, over 972425.16 frames.], batch size: 17, lr: 2.58e-04
+2022-05-06 06:29:57,396 INFO [train.py:715] (3/8) Epoch 8, batch 23250, loss[loss=0.1362, simple_loss=0.2057, pruned_loss=0.0333, over 4926.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03555, over 972269.32 frames.], batch size: 35, lr: 2.58e-04
+2022-05-06 06:30:36,514 INFO [train.py:715] (3/8) Epoch 8, batch 23300, loss[loss=0.1645, simple_loss=0.2407, pruned_loss=0.04413, over 4777.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2153, pruned_loss=0.03516, over 972668.74 frames.], batch size: 17, lr: 2.58e-04
+2022-05-06 06:31:16,262 INFO [train.py:715] (3/8) Epoch 8, batch 23350, loss[loss=0.1627, simple_loss=0.2314, pruned_loss=0.04703, over 4874.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03536, over 973344.49 frames.], batch size: 16, lr: 2.58e-04
+2022-05-06 06:31:55,024 INFO [train.py:715] (3/8) Epoch 8, batch 23400, loss[loss=0.1762, simple_loss=0.2371, pruned_loss=0.05767, over 4976.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2145, pruned_loss=0.03533, over 973904.92 frames.], batch size: 31, lr: 2.58e-04
+2022-05-06 06:32:33,890 INFO [train.py:715] (3/8) Epoch 8, batch 23450, loss[loss=0.1282, simple_loss=0.195, pruned_loss=0.03072, over 4983.00 frames.], tot_loss[loss=0.142, simple_loss=0.214, pruned_loss=0.03503, over 973620.86 frames.], batch size: 28, lr: 2.58e-04
+2022-05-06 06:33:13,365 INFO [train.py:715] (3/8) Epoch 8, batch 23500, loss[loss=0.1265, simple_loss=0.2002, pruned_loss=0.02641, over 4822.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03455, over 972415.05 frames.], batch size: 15, lr: 2.58e-04
+2022-05-06 06:33:52,532 INFO [train.py:715] (3/8) Epoch 8, batch 23550, loss[loss=0.1595, simple_loss=0.232, pruned_loss=0.04351, over 4971.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03464, over 971707.16 frames.], batch size: 25, lr: 2.58e-04
+2022-05-06 06:34:31,318 INFO [train.py:715] (3/8) Epoch 8, batch 23600, loss[loss=0.1415, simple_loss=0.2153, pruned_loss=0.03387, over 4968.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03454, over 971634.92 frames.], batch size: 15, lr: 2.58e-04
+2022-05-06 06:35:10,239 INFO [train.py:715] (3/8) Epoch 8, batch 23650, loss[loss=0.1285, simple_loss=0.2007, pruned_loss=0.02808, over 4969.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03473, over 972654.17 frames.], batch size: 35, lr: 2.58e-04
+2022-05-06 06:35:50,047 INFO [train.py:715] (3/8) Epoch 8, batch 23700, loss[loss=0.1612, simple_loss=0.2246, pruned_loss=0.04894, over 4837.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03553, over 971939.16 frames.], batch size: 30, lr: 2.58e-04
+2022-05-06 06:36:28,663 INFO [train.py:715] (3/8) Epoch 8, batch 23750, loss[loss=0.1718, simple_loss=0.235, pruned_loss=0.05424, over 4902.00 frames.], tot_loss[loss=0.143, simple_loss=0.2151, pruned_loss=0.03541, over 972016.76 frames.], batch size: 39, lr: 2.58e-04
+2022-05-06 06:37:07,514 INFO [train.py:715] (3/8) Epoch 8, batch 23800, loss[loss=0.1632, simple_loss=0.2268, pruned_loss=0.04982, over 4853.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2163, pruned_loss=0.03613, over 971455.30 frames.], batch size: 20, lr: 2.58e-04
+2022-05-06 06:37:46,986 INFO [train.py:715] (3/8) Epoch 8, batch 23850, loss[loss=0.131, simple_loss=0.2047, pruned_loss=0.02861, over 4929.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03574, over 971437.76 frames.], batch size: 21, lr: 2.58e-04
+2022-05-06 06:38:26,640 INFO [train.py:715] (3/8) Epoch 8, batch 23900, loss[loss=0.1304, simple_loss=0.2085, pruned_loss=0.02611, over 4894.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2168, pruned_loss=0.03594, over 971931.79 frames.], batch size: 19, lr: 2.58e-04
+2022-05-06 06:39:05,505 INFO [train.py:715] (3/8) Epoch 8, batch 23950, loss[loss=0.1439, simple_loss=0.2169, pruned_loss=0.03542, over 4790.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2164, pruned_loss=0.03564, over 972364.25 frames.], batch size: 17, lr: 2.58e-04
+2022-05-06 06:39:44,888 INFO [train.py:715] (3/8) Epoch 8, batch 24000, loss[loss=0.1241, simple_loss=0.2003, pruned_loss=0.02395, over 4908.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2162, pruned_loss=0.03543, over 972280.12 frames.], batch size: 17, lr: 2.58e-04
+2022-05-06 06:39:44,889 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 06:39:54,529 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1075, simple_loss=0.192, pruned_loss=0.01146, over 914524.00 frames.
+2022-05-06 06:40:33,720 INFO [train.py:715] (3/8) Epoch 8, batch 24050, loss[loss=0.1344, simple_loss=0.2187, pruned_loss=0.02501, over 4816.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03598, over 971477.09 frames.], batch size: 27, lr: 2.58e-04
+2022-05-06 06:41:13,151 INFO [train.py:715] (3/8) Epoch 8, batch 24100, loss[loss=0.1463, simple_loss=0.2062, pruned_loss=0.04315, over 4851.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2167, pruned_loss=0.03626, over 971799.07 frames.], batch size: 32, lr: 2.58e-04
+2022-05-06 06:41:52,115 INFO [train.py:715] (3/8) Epoch 8, batch 24150, loss[loss=0.1708, simple_loss=0.2414, pruned_loss=0.05012, over 4839.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.0361, over 971587.47 frames.], batch size: 25, lr: 2.58e-04
+2022-05-06 06:42:31,049 INFO [train.py:715] (3/8) Epoch 8, batch 24200, loss[loss=0.121, simple_loss=0.1958, pruned_loss=0.02314, over 4790.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2154, pruned_loss=0.03557, over 971618.41 frames.], batch size: 14, lr: 2.58e-04
+2022-05-06 06:43:11,238 INFO [train.py:715] (3/8) Epoch 8, batch 24250, loss[loss=0.1257, simple_loss=0.1955, pruned_loss=0.02793, over 4775.00 frames.], tot_loss[loss=0.1427, simple_loss=0.215, pruned_loss=0.03521, over 972034.88 frames.], batch size: 14, lr: 2.58e-04
+2022-05-06 06:43:50,603 INFO [train.py:715] (3/8) Epoch 8, batch 24300, loss[loss=0.1654, simple_loss=0.2491, pruned_loss=0.04087, over 4925.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03446, over 972562.33 frames.], batch size: 23, lr: 2.58e-04
+2022-05-06 06:44:29,316 INFO [train.py:715] (3/8) Epoch 8, batch 24350, loss[loss=0.1434, simple_loss=0.215, pruned_loss=0.03588, over 4813.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03491, over 972198.21 frames.], batch size: 13, lr: 2.58e-04
+2022-05-06 06:45:08,117 INFO [train.py:715] (3/8) Epoch 8, batch 24400, loss[loss=0.1719, simple_loss=0.2372, pruned_loss=0.05329, over 4913.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03505, over 972424.93 frames.], batch size: 39, lr: 2.58e-04
+2022-05-06 06:45:47,152 INFO [train.py:715] (3/8) Epoch 8, batch 24450, loss[loss=0.159, simple_loss=0.2309, pruned_loss=0.04353, over 4930.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03513, over 971829.74 frames.], batch size: 18, lr: 2.58e-04
+2022-05-06 06:46:26,137 INFO [train.py:715] (3/8) Epoch 8, batch 24500, loss[loss=0.1702, simple_loss=0.2331, pruned_loss=0.05369, over 4783.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2139, pruned_loss=0.0347, over 971898.35 frames.], batch size: 14, lr: 2.58e-04
+2022-05-06 06:47:04,984 INFO [train.py:715] (3/8) Epoch 8, batch 24550, loss[loss=0.1497, simple_loss=0.2201, pruned_loss=0.03963, over 4919.00 frames.], tot_loss[loss=0.142, simple_loss=0.2144, pruned_loss=0.03486, over 971644.28 frames.], batch size: 23, lr: 2.58e-04
+2022-05-06 06:47:44,927 INFO [train.py:715] (3/8) Epoch 8, batch 24600, loss[loss=0.1408, simple_loss=0.2144, pruned_loss=0.03361, over 4919.00 frames.], tot_loss[loss=0.142, simple_loss=0.214, pruned_loss=0.03499, over 971573.31 frames.], batch size: 19, lr: 2.58e-04
+2022-05-06 06:48:24,237 INFO [train.py:715] (3/8) Epoch 8, batch 24650, loss[loss=0.1311, simple_loss=0.2141, pruned_loss=0.02401, over 4776.00 frames.], tot_loss[loss=0.141, simple_loss=0.2131, pruned_loss=0.03445, over 971118.85 frames.], batch size: 18, lr: 2.58e-04
+2022-05-06 06:49:02,876 INFO [train.py:715] (3/8) Epoch 8, batch 24700, loss[loss=0.1426, simple_loss=0.2286, pruned_loss=0.02825, over 4949.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2142, pruned_loss=0.03504, over 970689.20 frames.], batch size: 23, lr: 2.58e-04
+2022-05-06 06:49:42,048 INFO [train.py:715] (3/8) Epoch 8, batch 24750, loss[loss=0.1356, simple_loss=0.2197, pruned_loss=0.02572, over 4976.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03515, over 971893.07 frames.], batch size: 15, lr: 2.58e-04
+2022-05-06 06:50:21,622 INFO [train.py:715] (3/8) Epoch 8, batch 24800, loss[loss=0.1647, simple_loss=0.2347, pruned_loss=0.04739, over 4782.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.03517, over 971431.97 frames.], batch size: 18, lr: 2.58e-04
+2022-05-06 06:51:00,473 INFO [train.py:715] (3/8) Epoch 8, batch 24850, loss[loss=0.1794, simple_loss=0.2558, pruned_loss=0.05146, over 4862.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03484, over 971666.03 frames.], batch size: 16, lr: 2.58e-04
+2022-05-06 06:51:39,143 INFO [train.py:715] (3/8) Epoch 8, batch 24900, loss[loss=0.1342, simple_loss=0.2103, pruned_loss=0.02911, over 4875.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03507, over 971711.91 frames.], batch size: 22, lr: 2.58e-04
+2022-05-06 06:52:19,144 INFO [train.py:715] (3/8) Epoch 8, batch 24950, loss[loss=0.147, simple_loss=0.2161, pruned_loss=0.03902, over 4812.00 frames.], tot_loss[loss=0.1427, simple_loss=0.215, pruned_loss=0.03517, over 972173.62 frames.], batch size: 25, lr: 2.58e-04
+2022-05-06 06:52:58,630 INFO [train.py:715] (3/8) Epoch 8, batch 25000, loss[loss=0.1481, simple_loss=0.2229, pruned_loss=0.03665, over 4988.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.03536, over 971893.32 frames.], batch size: 15, lr: 2.57e-04
+2022-05-06 06:53:37,563 INFO [train.py:715] (3/8) Epoch 8, batch 25050, loss[loss=0.1277, simple_loss=0.1968, pruned_loss=0.02928, over 4898.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2145, pruned_loss=0.0351, over 971332.27 frames.], batch size: 17, lr: 2.57e-04
+2022-05-06 06:54:16,393 INFO [train.py:715] (3/8) Epoch 8, batch 25100, loss[loss=0.1879, simple_loss=0.2611, pruned_loss=0.0574, over 4892.00 frames.], tot_loss[loss=0.142, simple_loss=0.214, pruned_loss=0.03499, over 971250.31 frames.], batch size: 39, lr: 2.57e-04
+2022-05-06 06:54:55,808 INFO [train.py:715] (3/8) Epoch 8, batch 25150, loss[loss=0.1697, simple_loss=0.2369, pruned_loss=0.05124, over 4776.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03466, over 971273.31 frames.], batch size: 17, lr: 2.57e-04
+2022-05-06 06:55:34,832 INFO [train.py:715] (3/8) Epoch 8, batch 25200, loss[loss=0.1313, simple_loss=0.2119, pruned_loss=0.02534, over 4896.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2134, pruned_loss=0.03439, over 972380.92 frames.], batch size: 22, lr: 2.57e-04
+2022-05-06 06:56:13,823 INFO [train.py:715] (3/8) Epoch 8, batch 25250, loss[loss=0.1251, simple_loss=0.19, pruned_loss=0.0301, over 4735.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03471, over 972745.36 frames.], batch size: 12, lr: 2.57e-04
+2022-05-06 06:56:53,389 INFO [train.py:715] (3/8) Epoch 8, batch 25300, loss[loss=0.1072, simple_loss=0.1835, pruned_loss=0.01546, over 4770.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03439, over 972816.79 frames.], batch size: 19, lr: 2.57e-04
+2022-05-06 06:57:32,354 INFO [train.py:715] (3/8) Epoch 8, batch 25350, loss[loss=0.1494, simple_loss=0.2178, pruned_loss=0.04046, over 4847.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2136, pruned_loss=0.03448, over 973041.11 frames.], batch size: 30, lr: 2.57e-04
+2022-05-06 06:58:11,173 INFO [train.py:715] (3/8) Epoch 8, batch 25400, loss[loss=0.144, simple_loss=0.2221, pruned_loss=0.03296, over 4783.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03475, over 972806.71 frames.], batch size: 14, lr: 2.57e-04
+2022-05-06 06:58:50,228 INFO [train.py:715] (3/8) Epoch 8, batch 25450, loss[loss=0.1325, simple_loss=0.21, pruned_loss=0.0275, over 4777.00 frames.], tot_loss[loss=0.142, simple_loss=0.2142, pruned_loss=0.03488, over 972128.38 frames.], batch size: 18, lr: 2.57e-04
+2022-05-06 06:59:30,373 INFO [train.py:715] (3/8) Epoch 8, batch 25500, loss[loss=0.126, simple_loss=0.2063, pruned_loss=0.02286, over 4802.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03529, over 972543.03 frames.], batch size: 24, lr: 2.57e-04
+2022-05-06 07:00:12,380 INFO [train.py:715] (3/8) Epoch 8, batch 25550, loss[loss=0.1157, simple_loss=0.185, pruned_loss=0.0232, over 4898.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2165, pruned_loss=0.03545, over 972642.38 frames.], batch size: 19, lr: 2.57e-04
+2022-05-06 07:00:51,652 INFO [train.py:715] (3/8) Epoch 8, batch 25600, loss[loss=0.1278, simple_loss=0.1998, pruned_loss=0.02793, over 4892.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2167, pruned_loss=0.03557, over 972165.37 frames.], batch size: 22, lr: 2.57e-04
+2022-05-06 07:01:30,736 INFO [train.py:715] (3/8) Epoch 8, batch 25650, loss[loss=0.1301, simple_loss=0.1955, pruned_loss=0.03229, over 4912.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2156, pruned_loss=0.0351, over 972463.18 frames.], batch size: 17, lr: 2.57e-04
+2022-05-06 07:02:09,696 INFO [train.py:715] (3/8) Epoch 8, batch 25700, loss[loss=0.1429, simple_loss=0.2205, pruned_loss=0.03269, over 4810.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.03516, over 971817.54 frames.], batch size: 21, lr: 2.57e-04
+2022-05-06 07:02:48,866 INFO [train.py:715] (3/8) Epoch 8, batch 25750, loss[loss=0.1948, simple_loss=0.2553, pruned_loss=0.06716, over 4784.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03552, over 971355.76 frames.], batch size: 17, lr: 2.57e-04
+2022-05-06 07:03:27,688 INFO [train.py:715] (3/8) Epoch 8, batch 25800, loss[loss=0.1417, simple_loss=0.2164, pruned_loss=0.03348, over 4847.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2157, pruned_loss=0.03537, over 972359.93 frames.], batch size: 30, lr: 2.57e-04
+2022-05-06 07:04:06,656 INFO [train.py:715] (3/8) Epoch 8, batch 25850, loss[loss=0.1422, simple_loss=0.218, pruned_loss=0.03318, over 4784.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2168, pruned_loss=0.03623, over 971236.02 frames.], batch size: 18, lr: 2.57e-04
+2022-05-06 07:04:45,939 INFO [train.py:715] (3/8) Epoch 8, batch 25900, loss[loss=0.1521, simple_loss=0.2132, pruned_loss=0.04554, over 4958.00 frames.], tot_loss[loss=0.144, simple_loss=0.2158, pruned_loss=0.0361, over 970786.76 frames.], batch size: 14, lr: 2.57e-04
+2022-05-06 07:05:24,608 INFO [train.py:715] (3/8) Epoch 8, batch 25950, loss[loss=0.1398, simple_loss=0.2146, pruned_loss=0.03248, over 4972.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2154, pruned_loss=0.03591, over 970943.04 frames.], batch size: 40, lr: 2.57e-04
+2022-05-06 07:06:03,743 INFO [train.py:715] (3/8) Epoch 8, batch 26000, loss[loss=0.1021, simple_loss=0.174, pruned_loss=0.01507, over 4782.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2161, pruned_loss=0.03637, over 971902.81 frames.], batch size: 14, lr: 2.57e-04
+2022-05-06 07:06:42,910 INFO [train.py:715] (3/8) Epoch 8, batch 26050, loss[loss=0.1338, simple_loss=0.214, pruned_loss=0.02679, over 4957.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2153, pruned_loss=0.03579, over 972618.28 frames.], batch size: 28, lr: 2.57e-04
+2022-05-06 07:07:21,669 INFO [train.py:715] (3/8) Epoch 8, batch 26100, loss[loss=0.1437, simple_loss=0.2069, pruned_loss=0.04027, over 4947.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2148, pruned_loss=0.0355, over 972508.45 frames.], batch size: 21, lr: 2.57e-04
+2022-05-06 07:08:01,299 INFO [train.py:715] (3/8) Epoch 8, batch 26150, loss[loss=0.1213, simple_loss=0.1931, pruned_loss=0.02475, over 4921.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2148, pruned_loss=0.03594, over 971837.54 frames.], batch size: 21, lr: 2.57e-04
+2022-05-06 07:08:40,494 INFO [train.py:715] (3/8) Epoch 8, batch 26200, loss[loss=0.1284, simple_loss=0.1963, pruned_loss=0.0303, over 4924.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2147, pruned_loss=0.03573, over 972208.38 frames.], batch size: 18, lr: 2.57e-04
+2022-05-06 07:09:19,624 INFO [train.py:715] (3/8) Epoch 8, batch 26250, loss[loss=0.1423, simple_loss=0.2128, pruned_loss=0.03589, over 4777.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2146, pruned_loss=0.03542, over 972366.13 frames.], batch size: 18, lr: 2.57e-04
+2022-05-06 07:09:57,935 INFO [train.py:715] (3/8) Epoch 8, batch 26300, loss[loss=0.1408, simple_loss=0.2112, pruned_loss=0.03522, over 4764.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2144, pruned_loss=0.03551, over 971683.82 frames.], batch size: 19, lr: 2.57e-04
+2022-05-06 07:10:37,574 INFO [train.py:715] (3/8) Epoch 8, batch 26350, loss[loss=0.1573, simple_loss=0.2218, pruned_loss=0.0464, over 4930.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2143, pruned_loss=0.03504, over 971790.42 frames.], batch size: 23, lr: 2.57e-04
+2022-05-06 07:11:16,887 INFO [train.py:715] (3/8) Epoch 8, batch 26400, loss[loss=0.1412, simple_loss=0.2077, pruned_loss=0.03729, over 4754.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03546, over 971173.99 frames.], batch size: 19, lr: 2.57e-04
+2022-05-06 07:11:55,839 INFO [train.py:715] (3/8) Epoch 8, batch 26450, loss[loss=0.1299, simple_loss=0.2042, pruned_loss=0.02775, over 4975.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2151, pruned_loss=0.03567, over 971422.83 frames.], batch size: 40, lr: 2.57e-04
+2022-05-06 07:12:34,671 INFO [train.py:715] (3/8) Epoch 8, batch 26500, loss[loss=0.1529, simple_loss=0.2243, pruned_loss=0.04077, over 4933.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03578, over 970529.95 frames.], batch size: 18, lr: 2.57e-04
+2022-05-06 07:13:13,274 INFO [train.py:715] (3/8) Epoch 8, batch 26550, loss[loss=0.1243, simple_loss=0.1952, pruned_loss=0.02668, over 4694.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2162, pruned_loss=0.03584, over 970583.23 frames.], batch size: 15, lr: 2.57e-04
+2022-05-06 07:13:52,656 INFO [train.py:715] (3/8) Epoch 8, batch 26600, loss[loss=0.1242, simple_loss=0.1948, pruned_loss=0.02673, over 4960.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.03545, over 970478.52 frames.], batch size: 14, lr: 2.57e-04
+2022-05-06 07:14:30,715 INFO [train.py:715] (3/8) Epoch 8, batch 26650, loss[loss=0.1665, simple_loss=0.2315, pruned_loss=0.05069, over 4843.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.03521, over 970520.37 frames.], batch size: 32, lr: 2.57e-04
+2022-05-06 07:15:10,077 INFO [train.py:715] (3/8) Epoch 8, batch 26700, loss[loss=0.1042, simple_loss=0.174, pruned_loss=0.01721, over 4763.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2144, pruned_loss=0.03553, over 970545.17 frames.], batch size: 14, lr: 2.57e-04
+2022-05-06 07:15:49,150 INFO [train.py:715] (3/8) Epoch 8, batch 26750, loss[loss=0.1496, simple_loss=0.2154, pruned_loss=0.04193, over 4834.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2143, pruned_loss=0.03507, over 970800.21 frames.], batch size: 15, lr: 2.57e-04
+2022-05-06 07:16:27,932 INFO [train.py:715] (3/8) Epoch 8, batch 26800, loss[loss=0.1227, simple_loss=0.1989, pruned_loss=0.02321, over 4813.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2148, pruned_loss=0.03548, over 969556.87 frames.], batch size: 25, lr: 2.57e-04
+2022-05-06 07:17:07,165 INFO [train.py:715] (3/8) Epoch 8, batch 26850, loss[loss=0.123, simple_loss=0.1994, pruned_loss=0.02331, over 4946.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2142, pruned_loss=0.03502, over 970446.00 frames.], batch size: 21, lr: 2.57e-04
+2022-05-06 07:17:46,412 INFO [train.py:715] (3/8) Epoch 8, batch 26900, loss[loss=0.1514, simple_loss=0.2261, pruned_loss=0.0383, over 4970.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2144, pruned_loss=0.03532, over 971448.19 frames.], batch size: 35, lr: 2.57e-04
+2022-05-06 07:18:25,466 INFO [train.py:715] (3/8) Epoch 8, batch 26950, loss[loss=0.1307, simple_loss=0.1994, pruned_loss=0.03101, over 4932.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.03558, over 972036.87 frames.], batch size: 23, lr: 2.57e-04
+2022-05-06 07:19:04,350 INFO [train.py:715] (3/8) Epoch 8, batch 27000, loss[loss=0.1566, simple_loss=0.2314, pruned_loss=0.04088, over 4886.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2158, pruned_loss=0.03556, over 972258.99 frames.], batch size: 16, lr: 2.57e-04
+2022-05-06 07:19:04,351 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 07:19:13,678 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1072, simple_loss=0.1919, pruned_loss=0.01129, over 914524.00 frames.
+2022-05-06 07:19:52,526 INFO [train.py:715] (3/8) Epoch 8, batch 27050, loss[loss=0.1345, simple_loss=0.2035, pruned_loss=0.03277, over 4803.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03505, over 972138.51 frames.], batch size: 13, lr: 2.57e-04
+2022-05-06 07:20:31,872 INFO [train.py:715] (3/8) Epoch 8, batch 27100, loss[loss=0.111, simple_loss=0.1882, pruned_loss=0.01689, over 4757.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03529, over 972088.49 frames.], batch size: 19, lr: 2.57e-04
+2022-05-06 07:21:10,968 INFO [train.py:715] (3/8) Epoch 8, batch 27150, loss[loss=0.1528, simple_loss=0.2184, pruned_loss=0.04364, over 4898.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2141, pruned_loss=0.03523, over 973174.90 frames.], batch size: 17, lr: 2.57e-04
+2022-05-06 07:21:49,183 INFO [train.py:715] (3/8) Epoch 8, batch 27200, loss[loss=0.1293, simple_loss=0.2054, pruned_loss=0.0266, over 4818.00 frames.], tot_loss[loss=0.143, simple_loss=0.2149, pruned_loss=0.0356, over 973022.55 frames.], batch size: 27, lr: 2.57e-04
+2022-05-06 07:22:28,509 INFO [train.py:715] (3/8) Epoch 8, batch 27250, loss[loss=0.1318, simple_loss=0.2115, pruned_loss=0.02605, over 4890.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2145, pruned_loss=0.03523, over 972507.24 frames.], batch size: 19, lr: 2.57e-04
+2022-05-06 07:23:07,824 INFO [train.py:715] (3/8) Epoch 8, batch 27300, loss[loss=0.1778, simple_loss=0.252, pruned_loss=0.05175, over 4975.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2146, pruned_loss=0.03546, over 972956.02 frames.], batch size: 39, lr: 2.57e-04
+2022-05-06 07:23:46,494 INFO [train.py:715] (3/8) Epoch 8, batch 27350, loss[loss=0.1154, simple_loss=0.1842, pruned_loss=0.02326, over 4803.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2151, pruned_loss=0.03568, over 972712.47 frames.], batch size: 21, lr: 2.57e-04
+2022-05-06 07:24:25,183 INFO [train.py:715] (3/8) Epoch 8, batch 27400, loss[loss=0.1591, simple_loss=0.2257, pruned_loss=0.04628, over 4814.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2154, pruned_loss=0.03568, over 972323.37 frames.], batch size: 25, lr: 2.56e-04
+2022-05-06 07:25:04,322 INFO [train.py:715] (3/8) Epoch 8, batch 27450, loss[loss=0.1376, simple_loss=0.2038, pruned_loss=0.03573, over 4989.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03598, over 972769.99 frames.], batch size: 14, lr: 2.56e-04
+2022-05-06 07:25:43,017 INFO [train.py:715] (3/8) Epoch 8, batch 27500, loss[loss=0.1463, simple_loss=0.2052, pruned_loss=0.04371, over 4912.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.03526, over 972239.06 frames.], batch size: 17, lr: 2.56e-04
+2022-05-06 07:26:21,671 INFO [train.py:715] (3/8) Epoch 8, batch 27550, loss[loss=0.1383, simple_loss=0.2168, pruned_loss=0.02988, over 4949.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.03541, over 971796.96 frames.], batch size: 14, lr: 2.56e-04
+2022-05-06 07:27:01,334 INFO [train.py:715] (3/8) Epoch 8, batch 27600, loss[loss=0.1212, simple_loss=0.1987, pruned_loss=0.02181, over 4812.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03508, over 971852.12 frames.], batch size: 26, lr: 2.56e-04
+2022-05-06 07:27:40,428 INFO [train.py:715] (3/8) Epoch 8, batch 27650, loss[loss=0.1459, simple_loss=0.2203, pruned_loss=0.0358, over 4939.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03521, over 971305.25 frames.], batch size: 23, lr: 2.56e-04
+2022-05-06 07:28:19,091 INFO [train.py:715] (3/8) Epoch 8, batch 27700, loss[loss=0.1527, simple_loss=0.2179, pruned_loss=0.04376, over 4946.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03498, over 970787.29 frames.], batch size: 35, lr: 2.56e-04
+2022-05-06 07:28:58,323 INFO [train.py:715] (3/8) Epoch 8, batch 27750, loss[loss=0.1486, simple_loss=0.2227, pruned_loss=0.03729, over 4897.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03445, over 970677.81 frames.], batch size: 17, lr: 2.56e-04
+2022-05-06 07:29:38,021 INFO [train.py:715] (3/8) Epoch 8, batch 27800, loss[loss=0.1407, simple_loss=0.2202, pruned_loss=0.03065, over 4985.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.03506, over 971158.66 frames.], batch size: 26, lr: 2.56e-04
+2022-05-06 07:30:16,793 INFO [train.py:715] (3/8) Epoch 8, batch 27850, loss[loss=0.1764, simple_loss=0.2398, pruned_loss=0.05655, over 4973.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.03565, over 970997.41 frames.], batch size: 24, lr: 2.56e-04
+2022-05-06 07:30:54,916 INFO [train.py:715] (3/8) Epoch 8, batch 27900, loss[loss=0.1561, simple_loss=0.2283, pruned_loss=0.0419, over 4892.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03548, over 971338.80 frames.], batch size: 19, lr: 2.56e-04
+2022-05-06 07:31:34,147 INFO [train.py:715] (3/8) Epoch 8, batch 27950, loss[loss=0.1353, simple_loss=0.214, pruned_loss=0.02835, over 4789.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03538, over 970900.79 frames.], batch size: 24, lr: 2.56e-04
+2022-05-06 07:32:13,474 INFO [train.py:715] (3/8) Epoch 8, batch 28000, loss[loss=0.1648, simple_loss=0.2368, pruned_loss=0.04637, over 4816.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2162, pruned_loss=0.03553, over 971108.78 frames.], batch size: 27, lr: 2.56e-04
+2022-05-06 07:32:51,690 INFO [train.py:715] (3/8) Epoch 8, batch 28050, loss[loss=0.137, simple_loss=0.2112, pruned_loss=0.03133, over 4935.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.03538, over 971505.92 frames.], batch size: 29, lr: 2.56e-04
+2022-05-06 07:33:31,443 INFO [train.py:715] (3/8) Epoch 8, batch 28100, loss[loss=0.1356, simple_loss=0.2151, pruned_loss=0.02809, over 4849.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03526, over 972006.14 frames.], batch size: 20, lr: 2.56e-04
+2022-05-06 07:34:10,511 INFO [train.py:715] (3/8) Epoch 8, batch 28150, loss[loss=0.1148, simple_loss=0.1882, pruned_loss=0.02072, over 4944.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2153, pruned_loss=0.03521, over 971801.98 frames.], batch size: 21, lr: 2.56e-04
+2022-05-06 07:34:49,971 INFO [train.py:715] (3/8) Epoch 8, batch 28200, loss[loss=0.1395, simple_loss=0.2148, pruned_loss=0.03212, over 4875.00 frames.], tot_loss[loss=0.143, simple_loss=0.2154, pruned_loss=0.0353, over 973097.34 frames.], batch size: 16, lr: 2.56e-04
+2022-05-06 07:35:29,404 INFO [train.py:715] (3/8) Epoch 8, batch 28250, loss[loss=0.1384, simple_loss=0.2034, pruned_loss=0.03672, over 4751.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03506, over 972565.95 frames.], batch size: 16, lr: 2.56e-04
+2022-05-06 07:36:09,674 INFO [train.py:715] (3/8) Epoch 8, batch 28300, loss[loss=0.1312, simple_loss=0.212, pruned_loss=0.02521, over 4854.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2159, pruned_loss=0.03549, over 972307.65 frames.], batch size: 15, lr: 2.56e-04
+2022-05-06 07:36:49,592 INFO [train.py:715] (3/8) Epoch 8, batch 28350, loss[loss=0.1372, simple_loss=0.2142, pruned_loss=0.03008, over 4896.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.0366, over 972559.14 frames.], batch size: 22, lr: 2.56e-04
+2022-05-06 07:37:28,934 INFO [train.py:715] (3/8) Epoch 8, batch 28400, loss[loss=0.1801, simple_loss=0.2418, pruned_loss=0.05921, over 4877.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.03644, over 972119.87 frames.], batch size: 16, lr: 2.56e-04
+2022-05-06 07:38:08,996 INFO [train.py:715] (3/8) Epoch 8, batch 28450, loss[loss=0.127, simple_loss=0.1982, pruned_loss=0.02791, over 4924.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2167, pruned_loss=0.03645, over 972838.90 frames.], batch size: 23, lr: 2.56e-04
+2022-05-06 07:38:48,160 INFO [train.py:715] (3/8) Epoch 8, batch 28500, loss[loss=0.1192, simple_loss=0.2015, pruned_loss=0.0185, over 4976.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2162, pruned_loss=0.03645, over 973023.39 frames.], batch size: 35, lr: 2.56e-04
+2022-05-06 07:39:26,866 INFO [train.py:715] (3/8) Epoch 8, batch 28550, loss[loss=0.1301, simple_loss=0.2, pruned_loss=0.03008, over 4963.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03567, over 973914.43 frames.], batch size: 14, lr: 2.56e-04
+2022-05-06 07:40:05,724 INFO [train.py:715] (3/8) Epoch 8, batch 28600, loss[loss=0.1428, simple_loss=0.2033, pruned_loss=0.04113, over 4942.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2159, pruned_loss=0.03561, over 973270.79 frames.], batch size: 15, lr: 2.56e-04
+2022-05-06 07:40:45,401 INFO [train.py:715] (3/8) Epoch 8, batch 28650, loss[loss=0.1198, simple_loss=0.2009, pruned_loss=0.01935, over 4823.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03522, over 973422.73 frames.], batch size: 15, lr: 2.56e-04
+2022-05-06 07:41:24,254 INFO [train.py:715] (3/8) Epoch 8, batch 28700, loss[loss=0.1463, simple_loss=0.223, pruned_loss=0.0348, over 4901.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.03513, over 973180.67 frames.], batch size: 18, lr: 2.56e-04
+2022-05-06 07:42:02,602 INFO [train.py:715] (3/8) Epoch 8, batch 28750, loss[loss=0.1518, simple_loss=0.2232, pruned_loss=0.04019, over 4933.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.0347, over 972622.54 frames.], batch size: 21, lr: 2.56e-04
+2022-05-06 07:42:42,146 INFO [train.py:715] (3/8) Epoch 8, batch 28800, loss[loss=0.1444, simple_loss=0.2187, pruned_loss=0.03503, over 4866.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2157, pruned_loss=0.03503, over 971924.94 frames.], batch size: 16, lr: 2.56e-04
+2022-05-06 07:43:21,537 INFO [train.py:715] (3/8) Epoch 8, batch 28850, loss[loss=0.2, simple_loss=0.2508, pruned_loss=0.07462, over 4966.00 frames.], tot_loss[loss=0.144, simple_loss=0.2168, pruned_loss=0.03563, over 971673.87 frames.], batch size: 15, lr: 2.56e-04
+2022-05-06 07:44:00,550 INFO [train.py:715] (3/8) Epoch 8, batch 28900, loss[loss=0.1286, simple_loss=0.197, pruned_loss=0.03005, over 4857.00 frames.], tot_loss[loss=0.1442, simple_loss=0.217, pruned_loss=0.03567, over 971011.29 frames.], batch size: 20, lr: 2.56e-04
+2022-05-06 07:44:39,170 INFO [train.py:715] (3/8) Epoch 8, batch 28950, loss[loss=0.147, simple_loss=0.2158, pruned_loss=0.03908, over 4983.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2181, pruned_loss=0.03621, over 971655.78 frames.], batch size: 14, lr: 2.56e-04
+2022-05-06 07:45:18,519 INFO [train.py:715] (3/8) Epoch 8, batch 29000, loss[loss=0.121, simple_loss=0.1891, pruned_loss=0.02641, over 4865.00 frames.], tot_loss[loss=0.145, simple_loss=0.2177, pruned_loss=0.0361, over 971894.87 frames.], batch size: 20, lr: 2.56e-04
+2022-05-06 07:45:57,178 INFO [train.py:715] (3/8) Epoch 8, batch 29050, loss[loss=0.1013, simple_loss=0.1803, pruned_loss=0.01113, over 4786.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2168, pruned_loss=0.03572, over 971559.24 frames.], batch size: 12, lr: 2.56e-04
+2022-05-06 07:46:36,427 INFO [train.py:715] (3/8) Epoch 8, batch 29100, loss[loss=0.1465, simple_loss=0.2169, pruned_loss=0.03802, over 4828.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2168, pruned_loss=0.03603, over 970540.06 frames.], batch size: 13, lr: 2.56e-04
+2022-05-06 07:47:14,944 INFO [train.py:715] (3/8) Epoch 8, batch 29150, loss[loss=0.1469, simple_loss=0.2166, pruned_loss=0.0386, over 4913.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.03626, over 970527.29 frames.], batch size: 18, lr: 2.56e-04
+2022-05-06 07:47:54,242 INFO [train.py:715] (3/8) Epoch 8, batch 29200, loss[loss=0.1164, simple_loss=0.1988, pruned_loss=0.01701, over 4886.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.03639, over 970275.57 frames.], batch size: 22, lr: 2.56e-04
+2022-05-06 07:48:32,869 INFO [train.py:715] (3/8) Epoch 8, batch 29250, loss[loss=0.1456, simple_loss=0.2219, pruned_loss=0.03464, over 4963.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03594, over 970978.57 frames.], batch size: 24, lr: 2.56e-04
+2022-05-06 07:49:11,139 INFO [train.py:715] (3/8) Epoch 8, batch 29300, loss[loss=0.1624, simple_loss=0.2348, pruned_loss=0.04495, over 4800.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2169, pruned_loss=0.03609, over 971722.24 frames.], batch size: 21, lr: 2.56e-04
+2022-05-06 07:49:50,319 INFO [train.py:715] (3/8) Epoch 8, batch 29350, loss[loss=0.1284, simple_loss=0.202, pruned_loss=0.02738, over 4940.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2177, pruned_loss=0.03633, over 971578.12 frames.], batch size: 23, lr: 2.56e-04
+2022-05-06 07:50:29,149 INFO [train.py:715] (3/8) Epoch 8, batch 29400, loss[loss=0.1175, simple_loss=0.199, pruned_loss=0.01797, over 4923.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2165, pruned_loss=0.03569, over 970733.82 frames.], batch size: 18, lr: 2.56e-04
+2022-05-06 07:51:08,799 INFO [train.py:715] (3/8) Epoch 8, batch 29450, loss[loss=0.1386, simple_loss=0.2173, pruned_loss=0.02991, over 4707.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2165, pruned_loss=0.036, over 970988.96 frames.], batch size: 15, lr: 2.56e-04
+2022-05-06 07:51:48,080 INFO [train.py:715] (3/8) Epoch 8, batch 29500, loss[loss=0.1371, simple_loss=0.2138, pruned_loss=0.03026, over 4974.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2167, pruned_loss=0.03583, over 971241.36 frames.], batch size: 24, lr: 2.56e-04
+2022-05-06 07:52:27,548 INFO [train.py:715] (3/8) Epoch 8, batch 29550, loss[loss=0.1529, simple_loss=0.2246, pruned_loss=0.04065, over 4930.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.0355, over 971556.35 frames.], batch size: 29, lr: 2.56e-04
+2022-05-06 07:53:06,114 INFO [train.py:715] (3/8) Epoch 8, batch 29600, loss[loss=0.1299, simple_loss=0.1982, pruned_loss=0.03078, over 4975.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03566, over 971563.17 frames.], batch size: 24, lr: 2.56e-04
+2022-05-06 07:53:45,381 INFO [train.py:715] (3/8) Epoch 8, batch 29650, loss[loss=0.1551, simple_loss=0.2188, pruned_loss=0.04567, over 4777.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2156, pruned_loss=0.03507, over 972209.64 frames.], batch size: 18, lr: 2.56e-04
+2022-05-06 07:54:24,986 INFO [train.py:715] (3/8) Epoch 8, batch 29700, loss[loss=0.1399, simple_loss=0.217, pruned_loss=0.03142, over 4752.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2152, pruned_loss=0.03482, over 972670.24 frames.], batch size: 12, lr: 2.56e-04
+2022-05-06 07:55:03,541 INFO [train.py:715] (3/8) Epoch 8, batch 29750, loss[loss=0.146, simple_loss=0.2228, pruned_loss=0.03459, over 4815.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2155, pruned_loss=0.03466, over 972358.97 frames.], batch size: 25, lr: 2.56e-04
+2022-05-06 07:55:42,375 INFO [train.py:715] (3/8) Epoch 8, batch 29800, loss[loss=0.1666, simple_loss=0.2309, pruned_loss=0.05114, over 4912.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2156, pruned_loss=0.035, over 973104.08 frames.], batch size: 18, lr: 2.55e-04
+2022-05-06 07:56:21,282 INFO [train.py:715] (3/8) Epoch 8, batch 29850, loss[loss=0.1312, simple_loss=0.2121, pruned_loss=0.02517, over 4788.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03578, over 973515.77 frames.], batch size: 18, lr: 2.55e-04
+2022-05-06 07:57:00,652 INFO [train.py:715] (3/8) Epoch 8, batch 29900, loss[loss=0.1524, simple_loss=0.2244, pruned_loss=0.04017, over 4915.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2163, pruned_loss=0.03577, over 973966.25 frames.], batch size: 17, lr: 2.55e-04
+2022-05-06 07:57:39,545 INFO [train.py:715] (3/8) Epoch 8, batch 29950, loss[loss=0.1261, simple_loss=0.2023, pruned_loss=0.02491, over 4853.00 frames.], tot_loss[loss=0.145, simple_loss=0.2174, pruned_loss=0.0363, over 973052.01 frames.], batch size: 13, lr: 2.55e-04
+2022-05-06 07:58:18,653 INFO [train.py:715] (3/8) Epoch 8, batch 30000, loss[loss=0.1726, simple_loss=0.237, pruned_loss=0.0541, over 4763.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03604, over 973029.96 frames.], batch size: 14, lr: 2.55e-04
+2022-05-06 07:58:18,654 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 07:58:28,239 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1073, simple_loss=0.1918, pruned_loss=0.01141, over 914524.00 frames.
+2022-05-06 07:59:07,024 INFO [train.py:715] (3/8) Epoch 8, batch 30050, loss[loss=0.1293, simple_loss=0.2041, pruned_loss=0.02721, over 4951.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2166, pruned_loss=0.03581, over 973503.09 frames.], batch size: 21, lr: 2.55e-04
+2022-05-06 07:59:46,358 INFO [train.py:715] (3/8) Epoch 8, batch 30100, loss[loss=0.1235, simple_loss=0.2104, pruned_loss=0.01834, over 4971.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03554, over 973677.18 frames.], batch size: 14, lr: 2.55e-04
+2022-05-06 08:00:25,655 INFO [train.py:715] (3/8) Epoch 8, batch 30150, loss[loss=0.1483, simple_loss=0.215, pruned_loss=0.04083, over 4813.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2167, pruned_loss=0.03627, over 972756.52 frames.], batch size: 26, lr: 2.55e-04
+2022-05-06 08:01:04,253 INFO [train.py:715] (3/8) Epoch 8, batch 30200, loss[loss=0.1407, simple_loss=0.2163, pruned_loss=0.03255, over 4852.00 frames.], tot_loss[loss=0.1445, simple_loss=0.217, pruned_loss=0.03595, over 973332.66 frames.], batch size: 13, lr: 2.55e-04
+2022-05-06 08:01:43,183 INFO [train.py:715] (3/8) Epoch 8, batch 30250, loss[loss=0.1587, simple_loss=0.2272, pruned_loss=0.04508, over 4911.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2164, pruned_loss=0.03566, over 972984.65 frames.], batch size: 18, lr: 2.55e-04
+2022-05-06 08:02:22,868 INFO [train.py:715] (3/8) Epoch 8, batch 30300, loss[loss=0.1551, simple_loss=0.222, pruned_loss=0.04408, over 4983.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.03536, over 971750.64 frames.], batch size: 15, lr: 2.55e-04
+2022-05-06 08:03:01,869 INFO [train.py:715] (3/8) Epoch 8, batch 30350, loss[loss=0.1394, simple_loss=0.2168, pruned_loss=0.03095, over 4958.00 frames.], tot_loss[loss=0.143, simple_loss=0.2152, pruned_loss=0.03537, over 972174.51 frames.], batch size: 24, lr: 2.55e-04
+2022-05-06 08:03:40,563 INFO [train.py:715] (3/8) Epoch 8, batch 30400, loss[loss=0.1477, simple_loss=0.2196, pruned_loss=0.03794, over 4758.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2149, pruned_loss=0.03528, over 972440.03 frames.], batch size: 19, lr: 2.55e-04
+2022-05-06 08:04:19,870 INFO [train.py:715] (3/8) Epoch 8, batch 30450, loss[loss=0.1379, simple_loss=0.217, pruned_loss=0.02938, over 4860.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2145, pruned_loss=0.03503, over 972794.16 frames.], batch size: 20, lr: 2.55e-04
+2022-05-06 08:04:58,851 INFO [train.py:715] (3/8) Epoch 8, batch 30500, loss[loss=0.1639, simple_loss=0.2402, pruned_loss=0.04376, over 4934.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03475, over 972648.35 frames.], batch size: 39, lr: 2.55e-04
+2022-05-06 08:05:37,496 INFO [train.py:715] (3/8) Epoch 8, batch 30550, loss[loss=0.135, simple_loss=0.2145, pruned_loss=0.02773, over 4948.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03486, over 972998.47 frames.], batch size: 24, lr: 2.55e-04
+2022-05-06 08:06:16,534 INFO [train.py:715] (3/8) Epoch 8, batch 30600, loss[loss=0.1148, simple_loss=0.188, pruned_loss=0.02081, over 4810.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03484, over 973051.19 frames.], batch size: 13, lr: 2.55e-04
+2022-05-06 08:06:56,252 INFO [train.py:715] (3/8) Epoch 8, batch 30650, loss[loss=0.1364, simple_loss=0.2132, pruned_loss=0.02983, over 4973.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2138, pruned_loss=0.03469, over 972823.94 frames.], batch size: 24, lr: 2.55e-04
+2022-05-06 08:07:35,434 INFO [train.py:715] (3/8) Epoch 8, batch 30700, loss[loss=0.1363, simple_loss=0.2053, pruned_loss=0.03368, over 4888.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2138, pruned_loss=0.03477, over 972052.76 frames.], batch size: 19, lr: 2.55e-04
+2022-05-06 08:08:15,309 INFO [train.py:715] (3/8) Epoch 8, batch 30750, loss[loss=0.1363, simple_loss=0.2164, pruned_loss=0.02807, over 4894.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03454, over 971851.54 frames.], batch size: 19, lr: 2.55e-04
+2022-05-06 08:08:55,427 INFO [train.py:715] (3/8) Epoch 8, batch 30800, loss[loss=0.1934, simple_loss=0.2556, pruned_loss=0.06558, over 4785.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03479, over 971366.63 frames.], batch size: 17, lr: 2.55e-04
+2022-05-06 08:09:33,880 INFO [train.py:715] (3/8) Epoch 8, batch 30850, loss[loss=0.1403, simple_loss=0.2117, pruned_loss=0.03441, over 4821.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03493, over 972067.78 frames.], batch size: 27, lr: 2.55e-04
+2022-05-06 08:10:12,782 INFO [train.py:715] (3/8) Epoch 8, batch 30900, loss[loss=0.158, simple_loss=0.2249, pruned_loss=0.04558, over 4760.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03492, over 972563.28 frames.], batch size: 19, lr: 2.55e-04
+2022-05-06 08:10:52,546 INFO [train.py:715] (3/8) Epoch 8, batch 30950, loss[loss=0.1665, simple_loss=0.2306, pruned_loss=0.05118, over 4918.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03487, over 972807.83 frames.], batch size: 35, lr: 2.55e-04
+2022-05-06 08:11:32,560 INFO [train.py:715] (3/8) Epoch 8, batch 31000, loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03457, over 4748.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2156, pruned_loss=0.03516, over 972619.02 frames.], batch size: 16, lr: 2.55e-04
+2022-05-06 08:12:11,801 INFO [train.py:715] (3/8) Epoch 8, batch 31050, loss[loss=0.1304, simple_loss=0.2035, pruned_loss=0.02867, over 4756.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03552, over 972588.77 frames.], batch size: 16, lr: 2.55e-04
+2022-05-06 08:12:51,404 INFO [train.py:715] (3/8) Epoch 8, batch 31100, loss[loss=0.1411, simple_loss=0.2072, pruned_loss=0.03749, over 4895.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2161, pruned_loss=0.0359, over 972565.69 frames.], batch size: 19, lr: 2.55e-04
+2022-05-06 08:13:30,939 INFO [train.py:715] (3/8) Epoch 8, batch 31150, loss[loss=0.1395, simple_loss=0.2128, pruned_loss=0.03309, over 4949.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03589, over 972099.87 frames.], batch size: 24, lr: 2.55e-04
+2022-05-06 08:14:09,970 INFO [train.py:715] (3/8) Epoch 8, batch 31200, loss[loss=0.1347, simple_loss=0.2066, pruned_loss=0.0314, over 4882.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03567, over 972523.01 frames.], batch size: 22, lr: 2.55e-04
+2022-05-06 08:14:48,713 INFO [train.py:715] (3/8) Epoch 8, batch 31250, loss[loss=0.1523, simple_loss=0.2272, pruned_loss=0.03867, over 4959.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03503, over 972000.67 frames.], batch size: 24, lr: 2.55e-04
+2022-05-06 08:15:28,183 INFO [train.py:715] (3/8) Epoch 8, batch 31300, loss[loss=0.1396, simple_loss=0.2075, pruned_loss=0.0359, over 4809.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03519, over 971892.89 frames.], batch size: 21, lr: 2.55e-04
+2022-05-06 08:16:07,666 INFO [train.py:715] (3/8) Epoch 8, batch 31350, loss[loss=0.138, simple_loss=0.212, pruned_loss=0.03198, over 4957.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2153, pruned_loss=0.03529, over 972964.82 frames.], batch size: 15, lr: 2.55e-04
+2022-05-06 08:16:46,297 INFO [train.py:715] (3/8) Epoch 8, batch 31400, loss[loss=0.1266, simple_loss=0.193, pruned_loss=0.03008, over 4857.00 frames.], tot_loss[loss=0.143, simple_loss=0.2154, pruned_loss=0.03527, over 973012.62 frames.], batch size: 32, lr: 2.55e-04
+2022-05-06 08:17:25,752 INFO [train.py:715] (3/8) Epoch 8, batch 31450, loss[loss=0.1505, simple_loss=0.2313, pruned_loss=0.03478, over 4874.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03545, over 972856.48 frames.], batch size: 16, lr: 2.55e-04
+2022-05-06 08:18:05,873 INFO [train.py:715] (3/8) Epoch 8, batch 31500, loss[loss=0.1366, simple_loss=0.2141, pruned_loss=0.02956, over 4953.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03553, over 973444.32 frames.], batch size: 24, lr: 2.55e-04
+2022-05-06 08:18:45,116 INFO [train.py:715] (3/8) Epoch 8, batch 31550, loss[loss=0.1489, simple_loss=0.2302, pruned_loss=0.03385, over 4792.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03581, over 973515.28 frames.], batch size: 18, lr: 2.55e-04
+2022-05-06 08:19:24,103 INFO [train.py:715] (3/8) Epoch 8, batch 31600, loss[loss=0.1299, simple_loss=0.2077, pruned_loss=0.02609, over 4985.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.03539, over 973387.84 frames.], batch size: 28, lr: 2.55e-04
+2022-05-06 08:20:03,753 INFO [train.py:715] (3/8) Epoch 8, batch 31650, loss[loss=0.1443, simple_loss=0.207, pruned_loss=0.04077, over 4765.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.03557, over 972512.07 frames.], batch size: 19, lr: 2.55e-04
+2022-05-06 08:20:43,074 INFO [train.py:715] (3/8) Epoch 8, batch 31700, loss[loss=0.1283, simple_loss=0.1974, pruned_loss=0.02962, over 4838.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03618, over 972690.05 frames.], batch size: 13, lr: 2.55e-04
+2022-05-06 08:21:22,756 INFO [train.py:715] (3/8) Epoch 8, batch 31750, loss[loss=0.2087, simple_loss=0.2825, pruned_loss=0.06751, over 4884.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03582, over 972797.21 frames.], batch size: 38, lr: 2.55e-04
+2022-05-06 08:22:01,966 INFO [train.py:715] (3/8) Epoch 8, batch 31800, loss[loss=0.1573, simple_loss=0.2317, pruned_loss=0.04144, over 4757.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2162, pruned_loss=0.03563, over 972393.98 frames.], batch size: 19, lr: 2.55e-04
+2022-05-06 08:22:41,011 INFO [train.py:715] (3/8) Epoch 8, batch 31850, loss[loss=0.1282, simple_loss=0.2032, pruned_loss=0.02664, over 4883.00 frames.], tot_loss[loss=0.144, simple_loss=0.2162, pruned_loss=0.03595, over 973016.57 frames.], batch size: 16, lr: 2.55e-04
+2022-05-06 08:23:19,922 INFO [train.py:715] (3/8) Epoch 8, batch 31900, loss[loss=0.1474, simple_loss=0.226, pruned_loss=0.03441, over 4959.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03576, over 972648.63 frames.], batch size: 24, lr: 2.55e-04
+2022-05-06 08:23:58,316 INFO [train.py:715] (3/8) Epoch 8, batch 31950, loss[loss=0.1314, simple_loss=0.2073, pruned_loss=0.02775, over 4948.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2157, pruned_loss=0.0352, over 973243.20 frames.], batch size: 24, lr: 2.55e-04
+2022-05-06 08:24:37,606 INFO [train.py:715] (3/8) Epoch 8, batch 32000, loss[loss=0.1093, simple_loss=0.183, pruned_loss=0.01781, over 4820.00 frames.], tot_loss[loss=0.144, simple_loss=0.2165, pruned_loss=0.03571, over 972722.08 frames.], batch size: 25, lr: 2.55e-04
+2022-05-06 08:25:17,171 INFO [train.py:715] (3/8) Epoch 8, batch 32050, loss[loss=0.127, simple_loss=0.2025, pruned_loss=0.02576, over 4900.00 frames.], tot_loss[loss=0.144, simple_loss=0.2165, pruned_loss=0.03575, over 971487.72 frames.], batch size: 17, lr: 2.55e-04
+2022-05-06 08:25:55,736 INFO [train.py:715] (3/8) Epoch 8, batch 32100, loss[loss=0.1352, simple_loss=0.212, pruned_loss=0.02916, over 4886.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2161, pruned_loss=0.0353, over 971162.89 frames.], batch size: 19, lr: 2.55e-04
+2022-05-06 08:26:34,466 INFO [train.py:715] (3/8) Epoch 8, batch 32150, loss[loss=0.1619, simple_loss=0.234, pruned_loss=0.04489, over 4799.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2165, pruned_loss=0.0356, over 971428.56 frames.], batch size: 21, lr: 2.55e-04
+2022-05-06 08:27:14,045 INFO [train.py:715] (3/8) Epoch 8, batch 32200, loss[loss=0.1528, simple_loss=0.2187, pruned_loss=0.0435, over 4956.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2165, pruned_loss=0.03564, over 971521.40 frames.], batch size: 35, lr: 2.54e-04
+2022-05-06 08:27:52,860 INFO [train.py:715] (3/8) Epoch 8, batch 32250, loss[loss=0.1294, simple_loss=0.2014, pruned_loss=0.02875, over 4813.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.03539, over 971365.05 frames.], batch size: 25, lr: 2.54e-04
+2022-05-06 08:28:32,333 INFO [train.py:715] (3/8) Epoch 8, batch 32300, loss[loss=0.1284, simple_loss=0.2063, pruned_loss=0.0253, over 4944.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03589, over 972382.45 frames.], batch size: 29, lr: 2.54e-04
+2022-05-06 08:29:11,541 INFO [train.py:715] (3/8) Epoch 8, batch 32350, loss[loss=0.1309, simple_loss=0.1991, pruned_loss=0.03134, over 4793.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2162, pruned_loss=0.03537, over 972148.21 frames.], batch size: 24, lr: 2.54e-04
+2022-05-06 08:29:51,458 INFO [train.py:715] (3/8) Epoch 8, batch 32400, loss[loss=0.1409, simple_loss=0.2164, pruned_loss=0.03275, over 4967.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2154, pruned_loss=0.03487, over 971486.30 frames.], batch size: 24, lr: 2.54e-04
+2022-05-06 08:30:30,382 INFO [train.py:715] (3/8) Epoch 8, batch 32450, loss[loss=0.1877, simple_loss=0.258, pruned_loss=0.05863, over 4923.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03474, over 972552.69 frames.], batch size: 18, lr: 2.54e-04
+2022-05-06 08:31:09,401 INFO [train.py:715] (3/8) Epoch 8, batch 32500, loss[loss=0.1847, simple_loss=0.2648, pruned_loss=0.05234, over 4866.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2146, pruned_loss=0.03432, over 972585.26 frames.], batch size: 20, lr: 2.54e-04
+2022-05-06 08:31:48,951 INFO [train.py:715] (3/8) Epoch 8, batch 32550, loss[loss=0.144, simple_loss=0.2053, pruned_loss=0.04129, over 4765.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.03409, over 973164.83 frames.], batch size: 18, lr: 2.54e-04
+2022-05-06 08:32:27,500 INFO [train.py:715] (3/8) Epoch 8, batch 32600, loss[loss=0.1171, simple_loss=0.2001, pruned_loss=0.01705, over 4970.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03398, over 972043.21 frames.], batch size: 15, lr: 2.54e-04
+2022-05-06 08:33:06,728 INFO [train.py:715] (3/8) Epoch 8, batch 32650, loss[loss=0.1298, simple_loss=0.205, pruned_loss=0.02731, over 4830.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03425, over 972494.92 frames.], batch size: 30, lr: 2.54e-04
+2022-05-06 08:33:45,980 INFO [train.py:715] (3/8) Epoch 8, batch 32700, loss[loss=0.139, simple_loss=0.2057, pruned_loss=0.03613, over 4750.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03435, over 972159.76 frames.], batch size: 14, lr: 2.54e-04
+2022-05-06 08:34:26,178 INFO [train.py:715] (3/8) Epoch 8, batch 32750, loss[loss=0.1592, simple_loss=0.2345, pruned_loss=0.04195, over 4909.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03444, over 972023.32 frames.], batch size: 39, lr: 2.54e-04
+2022-05-06 08:35:04,666 INFO [train.py:715] (3/8) Epoch 8, batch 32800, loss[loss=0.1847, simple_loss=0.2604, pruned_loss=0.05448, over 4836.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2137, pruned_loss=0.03454, over 971906.00 frames.], batch size: 15, lr: 2.54e-04
+2022-05-06 08:35:43,308 INFO [train.py:715] (3/8) Epoch 8, batch 32850, loss[loss=0.1433, simple_loss=0.2181, pruned_loss=0.03422, over 4893.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03483, over 971926.41 frames.], batch size: 19, lr: 2.54e-04
+2022-05-06 08:36:22,461 INFO [train.py:715] (3/8) Epoch 8, batch 32900, loss[loss=0.1348, simple_loss=0.2008, pruned_loss=0.03438, over 4920.00 frames.], tot_loss[loss=0.1419, simple_loss=0.214, pruned_loss=0.0349, over 971375.90 frames.], batch size: 29, lr: 2.54e-04
+2022-05-06 08:37:00,746 INFO [train.py:715] (3/8) Epoch 8, batch 32950, loss[loss=0.143, simple_loss=0.2188, pruned_loss=0.03354, over 4801.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2144, pruned_loss=0.03541, over 971463.52 frames.], batch size: 24, lr: 2.54e-04
+2022-05-06 08:37:39,629 INFO [train.py:715] (3/8) Epoch 8, batch 33000, loss[loss=0.1101, simple_loss=0.187, pruned_loss=0.01654, over 4959.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03531, over 970977.42 frames.], batch size: 21, lr: 2.54e-04
+2022-05-06 08:37:39,630 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 08:37:52,639 INFO [train.py:742] (3/8) Epoch 8, validation: loss=0.1071, simple_loss=0.1917, pruned_loss=0.01126, over 914524.00 frames.
+2022-05-06 08:38:31,971 INFO [train.py:715] (3/8) Epoch 8, batch 33050, loss[loss=0.1384, simple_loss=0.2141, pruned_loss=0.03133, over 4815.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2145, pruned_loss=0.03542, over 970947.25 frames.], batch size: 15, lr: 2.54e-04
+2022-05-06 08:39:10,828 INFO [train.py:715] (3/8) Epoch 8, batch 33100, loss[loss=0.1532, simple_loss=0.211, pruned_loss=0.04765, over 4946.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2141, pruned_loss=0.03505, over 971710.80 frames.], batch size: 21, lr: 2.54e-04
+2022-05-06 08:39:50,123 INFO [train.py:715] (3/8) Epoch 8, batch 33150, loss[loss=0.1632, simple_loss=0.2315, pruned_loss=0.04744, over 4881.00 frames.], tot_loss[loss=0.143, simple_loss=0.2151, pruned_loss=0.03546, over 971231.84 frames.], batch size: 22, lr: 2.54e-04
+2022-05-06 08:40:28,831 INFO [train.py:715] (3/8) Epoch 8, batch 33200, loss[loss=0.1549, simple_loss=0.2254, pruned_loss=0.04221, over 4808.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2144, pruned_loss=0.03499, over 971743.98 frames.], batch size: 21, lr: 2.54e-04
+2022-05-06 08:41:08,504 INFO [train.py:715] (3/8) Epoch 8, batch 33250, loss[loss=0.1215, simple_loss=0.2015, pruned_loss=0.02074, over 4700.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03525, over 971705.27 frames.], batch size: 15, lr: 2.54e-04
+2022-05-06 08:41:48,103 INFO [train.py:715] (3/8) Epoch 8, batch 33300, loss[loss=0.1391, simple_loss=0.2212, pruned_loss=0.02846, over 4924.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.0354, over 971638.11 frames.], batch size: 23, lr: 2.54e-04
+2022-05-06 08:42:26,901 INFO [train.py:715] (3/8) Epoch 8, batch 33350, loss[loss=0.1462, simple_loss=0.2267, pruned_loss=0.03282, over 4935.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03516, over 972168.38 frames.], batch size: 23, lr: 2.54e-04
+2022-05-06 08:43:06,262 INFO [train.py:715] (3/8) Epoch 8, batch 33400, loss[loss=0.164, simple_loss=0.2365, pruned_loss=0.04573, over 4766.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2147, pruned_loss=0.03459, over 971382.42 frames.], batch size: 19, lr: 2.54e-04
+2022-05-06 08:43:45,177 INFO [train.py:715] (3/8) Epoch 8, batch 33450, loss[loss=0.1618, simple_loss=0.2259, pruned_loss=0.04885, over 4905.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2151, pruned_loss=0.03476, over 971464.80 frames.], batch size: 17, lr: 2.54e-04
+2022-05-06 08:44:24,008 INFO [train.py:715] (3/8) Epoch 8, batch 33500, loss[loss=0.1429, simple_loss=0.2176, pruned_loss=0.03415, over 4739.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03524, over 972052.05 frames.], batch size: 16, lr: 2.54e-04
+2022-05-06 08:45:05,008 INFO [train.py:715] (3/8) Epoch 8, batch 33550, loss[loss=0.1241, simple_loss=0.1972, pruned_loss=0.02551, over 4839.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2157, pruned_loss=0.03528, over 972171.52 frames.], batch size: 13, lr: 2.54e-04
+2022-05-06 08:45:44,463 INFO [train.py:715] (3/8) Epoch 8, batch 33600, loss[loss=0.1432, simple_loss=0.2179, pruned_loss=0.03428, over 4781.00 frames.], tot_loss[loss=0.143, simple_loss=0.2158, pruned_loss=0.03508, over 972331.30 frames.], batch size: 19, lr: 2.54e-04
+2022-05-06 08:46:23,909 INFO [train.py:715] (3/8) Epoch 8, batch 33650, loss[loss=0.2254, simple_loss=0.2875, pruned_loss=0.08163, over 4961.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03568, over 971877.56 frames.], batch size: 35, lr: 2.54e-04
+2022-05-06 08:47:02,975 INFO [train.py:715] (3/8) Epoch 8, batch 33700, loss[loss=0.1611, simple_loss=0.235, pruned_loss=0.04366, over 4908.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03551, over 972230.46 frames.], batch size: 17, lr: 2.54e-04
+2022-05-06 08:47:41,963 INFO [train.py:715] (3/8) Epoch 8, batch 33750, loss[loss=0.1518, simple_loss=0.2237, pruned_loss=0.03992, over 4779.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.03525, over 972854.55 frames.], batch size: 14, lr: 2.54e-04
+2022-05-06 08:48:20,686 INFO [train.py:715] (3/8) Epoch 8, batch 33800, loss[loss=0.1246, simple_loss=0.1987, pruned_loss=0.0252, over 4932.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03493, over 973335.92 frames.], batch size: 18, lr: 2.54e-04
+2022-05-06 08:48:59,304 INFO [train.py:715] (3/8) Epoch 8, batch 33850, loss[loss=0.1318, simple_loss=0.2001, pruned_loss=0.03177, over 4886.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.0353, over 973105.60 frames.], batch size: 32, lr: 2.54e-04
+2022-05-06 08:49:38,115 INFO [train.py:715] (3/8) Epoch 8, batch 33900, loss[loss=0.14, simple_loss=0.215, pruned_loss=0.03254, over 4777.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.0353, over 972689.54 frames.], batch size: 17, lr: 2.54e-04
+2022-05-06 08:50:17,040 INFO [train.py:715] (3/8) Epoch 8, batch 33950, loss[loss=0.1321, simple_loss=0.2109, pruned_loss=0.0266, over 4957.00 frames.], tot_loss[loss=0.143, simple_loss=0.2157, pruned_loss=0.03518, over 973074.80 frames.], batch size: 21, lr: 2.54e-04
+2022-05-06 08:50:56,634 INFO [train.py:715] (3/8) Epoch 8, batch 34000, loss[loss=0.1297, simple_loss=0.2103, pruned_loss=0.02455, over 4911.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.035, over 973561.69 frames.], batch size: 17, lr: 2.54e-04
+2022-05-06 08:51:35,548 INFO [train.py:715] (3/8) Epoch 8, batch 34050, loss[loss=0.1502, simple_loss=0.2271, pruned_loss=0.03666, over 4751.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2151, pruned_loss=0.03473, over 973560.60 frames.], batch size: 16, lr: 2.54e-04
+2022-05-06 08:52:14,817 INFO [train.py:715] (3/8) Epoch 8, batch 34100, loss[loss=0.1399, simple_loss=0.2119, pruned_loss=0.03394, over 4822.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03475, over 973302.26 frames.], batch size: 15, lr: 2.54e-04
+2022-05-06 08:52:53,780 INFO [train.py:715] (3/8) Epoch 8, batch 34150, loss[loss=0.134, simple_loss=0.2021, pruned_loss=0.03293, over 4814.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.0351, over 972994.43 frames.], batch size: 15, lr: 2.54e-04
+2022-05-06 08:53:32,397 INFO [train.py:715] (3/8) Epoch 8, batch 34200, loss[loss=0.1889, simple_loss=0.2545, pruned_loss=0.06167, over 4790.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03442, over 972453.81 frames.], batch size: 18, lr: 2.54e-04
+2022-05-06 08:54:11,303 INFO [train.py:715] (3/8) Epoch 8, batch 34250, loss[loss=0.1104, simple_loss=0.1844, pruned_loss=0.01825, over 4780.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03462, over 972894.97 frames.], batch size: 12, lr: 2.54e-04
+2022-05-06 08:54:50,276 INFO [train.py:715] (3/8) Epoch 8, batch 34300, loss[loss=0.1306, simple_loss=0.2118, pruned_loss=0.02464, over 4779.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03459, over 972427.25 frames.], batch size: 18, lr: 2.54e-04
+2022-05-06 08:55:29,026 INFO [train.py:715] (3/8) Epoch 8, batch 34350, loss[loss=0.1371, simple_loss=0.2222, pruned_loss=0.02607, over 4861.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03504, over 972655.08 frames.], batch size: 20, lr: 2.54e-04
+2022-05-06 08:56:07,454 INFO [train.py:715] (3/8) Epoch 8, batch 34400, loss[loss=0.1331, simple_loss=0.2129, pruned_loss=0.02668, over 4856.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.035, over 972648.23 frames.], batch size: 32, lr: 2.54e-04
+2022-05-06 08:56:46,677 INFO [train.py:715] (3/8) Epoch 8, batch 34450, loss[loss=0.152, simple_loss=0.22, pruned_loss=0.04202, over 4829.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2156, pruned_loss=0.0349, over 973022.98 frames.], batch size: 15, lr: 2.54e-04
+2022-05-06 08:57:26,051 INFO [train.py:715] (3/8) Epoch 8, batch 34500, loss[loss=0.1472, simple_loss=0.218, pruned_loss=0.03817, over 4953.00 frames.], tot_loss[loss=0.1429, simple_loss=0.216, pruned_loss=0.03489, over 972279.05 frames.], batch size: 24, lr: 2.54e-04
+2022-05-06 08:58:04,290 INFO [train.py:715] (3/8) Epoch 8, batch 34550, loss[loss=0.1569, simple_loss=0.2282, pruned_loss=0.04282, over 4772.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2164, pruned_loss=0.03546, over 972506.95 frames.], batch size: 17, lr: 2.54e-04
+2022-05-06 08:58:42,924 INFO [train.py:715] (3/8) Epoch 8, batch 34600, loss[loss=0.1609, simple_loss=0.2339, pruned_loss=0.04396, over 4928.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2171, pruned_loss=0.03604, over 973229.46 frames.], batch size: 29, lr: 2.54e-04
+2022-05-06 08:59:21,846 INFO [train.py:715] (3/8) Epoch 8, batch 34650, loss[loss=0.1584, simple_loss=0.2382, pruned_loss=0.03937, over 4801.00 frames.], tot_loss[loss=0.144, simple_loss=0.2168, pruned_loss=0.0356, over 972761.36 frames.], batch size: 24, lr: 2.53e-04
+2022-05-06 09:00:01,504 INFO [train.py:715] (3/8) Epoch 8, batch 34700, loss[loss=0.1486, simple_loss=0.2208, pruned_loss=0.03817, over 4833.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2167, pruned_loss=0.03583, over 972586.01 frames.], batch size: 15, lr: 2.53e-04
+2022-05-06 09:00:38,665 INFO [train.py:715] (3/8) Epoch 8, batch 34750, loss[loss=0.1754, simple_loss=0.2386, pruned_loss=0.0561, over 4964.00 frames.], tot_loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03646, over 972133.54 frames.], batch size: 24, lr: 2.53e-04
+2022-05-06 09:01:15,264 INFO [train.py:715] (3/8) Epoch 8, batch 34800, loss[loss=0.1252, simple_loss=0.1998, pruned_loss=0.02527, over 4780.00 frames.], tot_loss[loss=0.1431, simple_loss=0.215, pruned_loss=0.03562, over 971101.37 frames.], batch size: 12, lr: 2.53e-04
+2022-05-06 09:02:04,639 INFO [train.py:715] (3/8) Epoch 9, batch 0, loss[loss=0.1161, simple_loss=0.1918, pruned_loss=0.02016, over 4971.00 frames.], tot_loss[loss=0.1161, simple_loss=0.1918, pruned_loss=0.02016, over 4971.00 frames.], batch size: 25, lr: 2.42e-04
+2022-05-06 09:02:43,974 INFO [train.py:715] (3/8) Epoch 9, batch 50, loss[loss=0.1518, simple_loss=0.2225, pruned_loss=0.04059, over 4775.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03407, over 218578.69 frames.], batch size: 14, lr: 2.41e-04
+2022-05-06 09:03:23,611 INFO [train.py:715] (3/8) Epoch 9, batch 100, loss[loss=0.1513, simple_loss=0.2232, pruned_loss=0.03967, over 4865.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2146, pruned_loss=0.03551, over 385901.76 frames.], batch size: 30, lr: 2.41e-04
+2022-05-06 09:04:02,105 INFO [train.py:715] (3/8) Epoch 9, batch 150, loss[loss=0.1117, simple_loss=0.1747, pruned_loss=0.02439, over 4765.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2156, pruned_loss=0.03652, over 515820.80 frames.], batch size: 12, lr: 2.41e-04
+2022-05-06 09:04:42,542 INFO [train.py:715] (3/8) Epoch 9, batch 200, loss[loss=0.1293, simple_loss=0.2034, pruned_loss=0.02753, over 4941.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2149, pruned_loss=0.03544, over 616790.99 frames.], batch size: 35, lr: 2.41e-04
+2022-05-06 09:05:21,803 INFO [train.py:715] (3/8) Epoch 9, batch 250, loss[loss=0.1456, simple_loss=0.2167, pruned_loss=0.03722, over 4910.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03568, over 695971.61 frames.], batch size: 18, lr: 2.41e-04
+2022-05-06 09:06:01,097 INFO [train.py:715] (3/8) Epoch 9, batch 300, loss[loss=0.1323, simple_loss=0.2073, pruned_loss=0.0287, over 4792.00 frames.], tot_loss[loss=0.143, simple_loss=0.2153, pruned_loss=0.03536, over 757686.56 frames.], batch size: 18, lr: 2.41e-04
+2022-05-06 09:06:40,659 INFO [train.py:715] (3/8) Epoch 9, batch 350, loss[loss=0.131, simple_loss=0.1993, pruned_loss=0.0313, over 4833.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.035, over 805363.68 frames.], batch size: 13, lr: 2.41e-04
+2022-05-06 09:07:20,402 INFO [train.py:715] (3/8) Epoch 9, batch 400, loss[loss=0.1696, simple_loss=0.24, pruned_loss=0.04958, over 4832.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03512, over 842449.13 frames.], batch size: 15, lr: 2.41e-04
+2022-05-06 09:07:59,733 INFO [train.py:715] (3/8) Epoch 9, batch 450, loss[loss=0.1419, simple_loss=0.2092, pruned_loss=0.03727, over 4771.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.03536, over 871961.96 frames.], batch size: 18, lr: 2.41e-04
+2022-05-06 09:08:38,888 INFO [train.py:715] (3/8) Epoch 9, batch 500, loss[loss=0.1418, simple_loss=0.2109, pruned_loss=0.03638, over 4885.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2152, pruned_loss=0.03494, over 894087.06 frames.], batch size: 32, lr: 2.41e-04
+2022-05-06 09:09:19,203 INFO [train.py:715] (3/8) Epoch 9, batch 550, loss[loss=0.1599, simple_loss=0.2313, pruned_loss=0.04427, over 4933.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03468, over 911572.72 frames.], batch size: 21, lr: 2.41e-04
+2022-05-06 09:09:58,810 INFO [train.py:715] (3/8) Epoch 9, batch 600, loss[loss=0.1169, simple_loss=0.1879, pruned_loss=0.023, over 4808.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03483, over 925574.74 frames.], batch size: 12, lr: 2.41e-04
+2022-05-06 09:10:37,826 INFO [train.py:715] (3/8) Epoch 9, batch 650, loss[loss=0.1507, simple_loss=0.2167, pruned_loss=0.04238, over 4983.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03459, over 935671.35 frames.], batch size: 35, lr: 2.41e-04
+2022-05-06 09:11:16,916 INFO [train.py:715] (3/8) Epoch 9, batch 700, loss[loss=0.1337, simple_loss=0.2093, pruned_loss=0.02905, over 4807.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.0343, over 943607.41 frames.], batch size: 24, lr: 2.41e-04
+2022-05-06 09:11:56,396 INFO [train.py:715] (3/8) Epoch 9, batch 750, loss[loss=0.1463, simple_loss=0.2286, pruned_loss=0.03194, over 4831.00 frames.], tot_loss[loss=0.142, simple_loss=0.2146, pruned_loss=0.03469, over 949920.45 frames.], batch size: 30, lr: 2.41e-04
+2022-05-06 09:12:35,540 INFO [train.py:715] (3/8) Epoch 9, batch 800, loss[loss=0.1561, simple_loss=0.2382, pruned_loss=0.03698, over 4811.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.03499, over 954795.72 frames.], batch size: 25, lr: 2.41e-04
+2022-05-06 09:13:14,320 INFO [train.py:715] (3/8) Epoch 9, batch 850, loss[loss=0.144, simple_loss=0.2177, pruned_loss=0.03517, over 4711.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03505, over 958185.70 frames.], batch size: 15, lr: 2.41e-04
+2022-05-06 09:13:53,318 INFO [train.py:715] (3/8) Epoch 9, batch 900, loss[loss=0.1716, simple_loss=0.2506, pruned_loss=0.04631, over 4973.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03481, over 961756.47 frames.], batch size: 15, lr: 2.41e-04
+2022-05-06 09:14:32,596 INFO [train.py:715] (3/8) Epoch 9, batch 950, loss[loss=0.1922, simple_loss=0.2572, pruned_loss=0.06359, over 4844.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03521, over 963367.33 frames.], batch size: 15, lr: 2.41e-04
+2022-05-06 09:15:12,212 INFO [train.py:715] (3/8) Epoch 9, batch 1000, loss[loss=0.1388, simple_loss=0.2176, pruned_loss=0.02995, over 4904.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03491, over 964392.61 frames.], batch size: 19, lr: 2.41e-04
+2022-05-06 09:15:50,366 INFO [train.py:715] (3/8) Epoch 9, batch 1050, loss[loss=0.1496, simple_loss=0.2245, pruned_loss=0.03734, over 4967.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2141, pruned_loss=0.03474, over 966390.37 frames.], batch size: 23, lr: 2.41e-04
+2022-05-06 09:16:30,512 INFO [train.py:715] (3/8) Epoch 9, batch 1100, loss[loss=0.1389, simple_loss=0.2035, pruned_loss=0.03714, over 4967.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03471, over 967051.72 frames.], batch size: 14, lr: 2.41e-04
+2022-05-06 09:17:10,347 INFO [train.py:715] (3/8) Epoch 9, batch 1150, loss[loss=0.1582, simple_loss=0.2303, pruned_loss=0.04303, over 4774.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.0348, over 968841.51 frames.], batch size: 14, lr: 2.41e-04
+2022-05-06 09:17:49,484 INFO [train.py:715] (3/8) Epoch 9, batch 1200, loss[loss=0.1586, simple_loss=0.2257, pruned_loss=0.04573, over 4864.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2157, pruned_loss=0.0352, over 969640.70 frames.], batch size: 32, lr: 2.41e-04
+2022-05-06 09:18:28,819 INFO [train.py:715] (3/8) Epoch 9, batch 1250, loss[loss=0.1574, simple_loss=0.2311, pruned_loss=0.04181, over 4861.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03583, over 969968.09 frames.], batch size: 20, lr: 2.41e-04
+2022-05-06 09:19:08,559 INFO [train.py:715] (3/8) Epoch 9, batch 1300, loss[loss=0.1107, simple_loss=0.1891, pruned_loss=0.01619, over 4771.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2157, pruned_loss=0.03554, over 970566.02 frames.], batch size: 18, lr: 2.41e-04
+2022-05-06 09:19:48,097 INFO [train.py:715] (3/8) Epoch 9, batch 1350, loss[loss=0.1166, simple_loss=0.1998, pruned_loss=0.01665, over 4788.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2161, pruned_loss=0.03534, over 970587.14 frames.], batch size: 21, lr: 2.41e-04
+2022-05-06 09:20:26,898 INFO [train.py:715] (3/8) Epoch 9, batch 1400, loss[loss=0.1463, simple_loss=0.2146, pruned_loss=0.039, over 4770.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2161, pruned_loss=0.03515, over 970796.89 frames.], batch size: 14, lr: 2.41e-04
+2022-05-06 09:21:06,502 INFO [train.py:715] (3/8) Epoch 9, batch 1450, loss[loss=0.1439, simple_loss=0.2046, pruned_loss=0.0416, over 4690.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2159, pruned_loss=0.03494, over 971163.04 frames.], batch size: 15, lr: 2.41e-04
+2022-05-06 09:21:45,310 INFO [train.py:715] (3/8) Epoch 9, batch 1500, loss[loss=0.1304, simple_loss=0.2011, pruned_loss=0.02986, over 4787.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2156, pruned_loss=0.03511, over 971063.58 frames.], batch size: 12, lr: 2.41e-04
+2022-05-06 09:22:24,145 INFO [train.py:715] (3/8) Epoch 9, batch 1550, loss[loss=0.1387, simple_loss=0.2101, pruned_loss=0.03365, over 4891.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03522, over 971741.90 frames.], batch size: 22, lr: 2.41e-04
+2022-05-06 09:23:03,177 INFO [train.py:715] (3/8) Epoch 9, batch 1600, loss[loss=0.1502, simple_loss=0.2193, pruned_loss=0.04058, over 4831.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.03536, over 972212.42 frames.], batch size: 15, lr: 2.41e-04
+2022-05-06 09:23:42,083 INFO [train.py:715] (3/8) Epoch 9, batch 1650, loss[loss=0.1164, simple_loss=0.1933, pruned_loss=0.01972, over 4968.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03548, over 973062.17 frames.], batch size: 15, lr: 2.41e-04
+2022-05-06 09:24:21,073 INFO [train.py:715] (3/8) Epoch 9, batch 1700, loss[loss=0.1507, simple_loss=0.2241, pruned_loss=0.03869, over 4900.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.03493, over 972127.26 frames.], batch size: 19, lr: 2.41e-04
+2022-05-06 09:25:00,146 INFO [train.py:715] (3/8) Epoch 9, batch 1750, loss[loss=0.1217, simple_loss=0.1918, pruned_loss=0.02576, over 4794.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2146, pruned_loss=0.03453, over 972588.40 frames.], batch size: 18, lr: 2.41e-04
+2022-05-06 09:25:39,674 INFO [train.py:715] (3/8) Epoch 9, batch 1800, loss[loss=0.1357, simple_loss=0.2023, pruned_loss=0.03453, over 4778.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03418, over 972708.05 frames.], batch size: 12, lr: 2.41e-04
+2022-05-06 09:26:18,855 INFO [train.py:715] (3/8) Epoch 9, batch 1850, loss[loss=0.1517, simple_loss=0.2233, pruned_loss=0.04002, over 4770.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03409, over 972129.72 frames.], batch size: 12, lr: 2.41e-04
+2022-05-06 09:26:57,985 INFO [train.py:715] (3/8) Epoch 9, batch 1900, loss[loss=0.1197, simple_loss=0.1882, pruned_loss=0.02557, over 4644.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2124, pruned_loss=0.03375, over 971019.31 frames.], batch size: 13, lr: 2.41e-04
+2022-05-06 09:27:37,989 INFO [train.py:715] (3/8) Epoch 9, batch 1950, loss[loss=0.1664, simple_loss=0.2313, pruned_loss=0.05072, over 4872.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2129, pruned_loss=0.03415, over 971589.72 frames.], batch size: 16, lr: 2.41e-04
+2022-05-06 09:28:17,647 INFO [train.py:715] (3/8) Epoch 9, batch 2000, loss[loss=0.1278, simple_loss=0.1982, pruned_loss=0.02871, over 4921.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03325, over 971404.83 frames.], batch size: 18, lr: 2.41e-04
+2022-05-06 09:28:56,804 INFO [train.py:715] (3/8) Epoch 9, batch 2050, loss[loss=0.1282, simple_loss=0.1889, pruned_loss=0.03378, over 4781.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03337, over 970762.43 frames.], batch size: 14, lr: 2.41e-04
+2022-05-06 09:29:35,325 INFO [train.py:715] (3/8) Epoch 9, batch 2100, loss[loss=0.1544, simple_loss=0.2352, pruned_loss=0.0368, over 4752.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.0341, over 970292.89 frames.], batch size: 19, lr: 2.41e-04
+2022-05-06 09:30:14,647 INFO [train.py:715] (3/8) Epoch 9, batch 2150, loss[loss=0.1189, simple_loss=0.1961, pruned_loss=0.02085, over 4928.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03416, over 970465.03 frames.], batch size: 18, lr: 2.41e-04
+2022-05-06 09:30:53,735 INFO [train.py:715] (3/8) Epoch 9, batch 2200, loss[loss=0.1489, simple_loss=0.2155, pruned_loss=0.04121, over 4775.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03502, over 970524.82 frames.], batch size: 18, lr: 2.41e-04
+2022-05-06 09:31:32,489 INFO [train.py:715] (3/8) Epoch 9, batch 2250, loss[loss=0.1452, simple_loss=0.2135, pruned_loss=0.03843, over 4830.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2148, pruned_loss=0.03477, over 971818.04 frames.], batch size: 26, lr: 2.41e-04
+2022-05-06 09:32:11,659 INFO [train.py:715] (3/8) Epoch 9, batch 2300, loss[loss=0.1227, simple_loss=0.1969, pruned_loss=0.02419, over 4818.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.0348, over 972170.61 frames.], batch size: 26, lr: 2.41e-04
+2022-05-06 09:32:50,737 INFO [train.py:715] (3/8) Epoch 9, batch 2350, loss[loss=0.1516, simple_loss=0.2218, pruned_loss=0.04067, over 4803.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2142, pruned_loss=0.035, over 971984.60 frames.], batch size: 24, lr: 2.41e-04
+2022-05-06 09:33:30,101 INFO [train.py:715] (3/8) Epoch 9, batch 2400, loss[loss=0.1446, simple_loss=0.2259, pruned_loss=0.03162, over 4904.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2146, pruned_loss=0.03529, over 972272.47 frames.], batch size: 18, lr: 2.41e-04
+2022-05-06 09:34:08,888 INFO [train.py:715] (3/8) Epoch 9, batch 2450, loss[loss=0.1553, simple_loss=0.2344, pruned_loss=0.03813, over 4992.00 frames.], tot_loss[loss=0.143, simple_loss=0.2148, pruned_loss=0.03559, over 971957.54 frames.], batch size: 15, lr: 2.41e-04
+2022-05-06 09:34:48,501 INFO [train.py:715] (3/8) Epoch 9, batch 2500, loss[loss=0.13, simple_loss=0.2187, pruned_loss=0.02063, over 4881.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2133, pruned_loss=0.03467, over 971711.33 frames.], batch size: 20, lr: 2.41e-04
+2022-05-06 09:35:27,023 INFO [train.py:715] (3/8) Epoch 9, batch 2550, loss[loss=0.1233, simple_loss=0.1962, pruned_loss=0.0252, over 4923.00 frames.], tot_loss[loss=0.142, simple_loss=0.214, pruned_loss=0.03505, over 972459.84 frames.], batch size: 18, lr: 2.41e-04
+2022-05-06 09:36:06,039 INFO [train.py:715] (3/8) Epoch 9, batch 2600, loss[loss=0.1283, simple_loss=0.2066, pruned_loss=0.02498, over 4707.00 frames.], tot_loss[loss=0.143, simple_loss=0.2152, pruned_loss=0.03537, over 972229.52 frames.], batch size: 15, lr: 2.41e-04
+2022-05-06 09:36:45,110 INFO [train.py:715] (3/8) Epoch 9, batch 2650, loss[loss=0.1527, simple_loss=0.218, pruned_loss=0.04372, over 4708.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03522, over 972965.92 frames.], batch size: 15, lr: 2.41e-04
+2022-05-06 09:37:24,474 INFO [train.py:715] (3/8) Epoch 9, batch 2700, loss[loss=0.1441, simple_loss=0.2236, pruned_loss=0.03231, over 4915.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03552, over 973148.80 frames.], batch size: 23, lr: 2.40e-04
+2022-05-06 09:38:03,295 INFO [train.py:715] (3/8) Epoch 9, batch 2750, loss[loss=0.135, simple_loss=0.2133, pruned_loss=0.02837, over 4952.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03548, over 973533.02 frames.], batch size: 21, lr: 2.40e-04
+2022-05-06 09:38:42,264 INFO [train.py:715] (3/8) Epoch 9, batch 2800, loss[loss=0.1478, simple_loss=0.2248, pruned_loss=0.03541, over 4894.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03494, over 972946.49 frames.], batch size: 17, lr: 2.40e-04
+2022-05-06 09:39:21,842 INFO [train.py:715] (3/8) Epoch 9, batch 2850, loss[loss=0.1456, simple_loss=0.215, pruned_loss=0.03816, over 4839.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03485, over 973592.14 frames.], batch size: 34, lr: 2.40e-04
+2022-05-06 09:40:00,908 INFO [train.py:715] (3/8) Epoch 9, batch 2900, loss[loss=0.1271, simple_loss=0.1962, pruned_loss=0.029, over 4878.00 frames.], tot_loss[loss=0.1427, simple_loss=0.215, pruned_loss=0.03523, over 972963.39 frames.], batch size: 32, lr: 2.40e-04
+2022-05-06 09:40:39,679 INFO [train.py:715] (3/8) Epoch 9, batch 2950, loss[loss=0.128, simple_loss=0.2043, pruned_loss=0.02588, over 4857.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2154, pruned_loss=0.03559, over 973512.44 frames.], batch size: 20, lr: 2.40e-04
+2022-05-06 09:41:18,904 INFO [train.py:715] (3/8) Epoch 9, batch 3000, loss[loss=0.1231, simple_loss=0.2016, pruned_loss=0.02232, over 4687.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03579, over 973496.01 frames.], batch size: 15, lr: 2.40e-04
+2022-05-06 09:41:18,905 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 09:41:28,534 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.1069, simple_loss=0.1915, pruned_loss=0.01118, over 914524.00 frames.
+2022-05-06 09:42:08,250 INFO [train.py:715] (3/8) Epoch 9, batch 3050, loss[loss=0.1338, simple_loss=0.2068, pruned_loss=0.03044, over 4949.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.0356, over 973257.76 frames.], batch size: 23, lr: 2.40e-04
+2022-05-06 09:42:47,739 INFO [train.py:715] (3/8) Epoch 9, batch 3100, loss[loss=0.1719, simple_loss=0.2459, pruned_loss=0.04891, over 4871.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.0351, over 972827.62 frames.], batch size: 16, lr: 2.40e-04
+2022-05-06 09:43:27,211 INFO [train.py:715] (3/8) Epoch 9, batch 3150, loss[loss=0.1455, simple_loss=0.2196, pruned_loss=0.03571, over 4950.00 frames.], tot_loss[loss=0.143, simple_loss=0.215, pruned_loss=0.03543, over 972331.47 frames.], batch size: 24, lr: 2.40e-04
+2022-05-06 09:44:06,424 INFO [train.py:715] (3/8) Epoch 9, batch 3200, loss[loss=0.1474, simple_loss=0.2251, pruned_loss=0.03488, over 4797.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2141, pruned_loss=0.03517, over 972470.00 frames.], batch size: 24, lr: 2.40e-04
+2022-05-06 09:44:45,579 INFO [train.py:715] (3/8) Epoch 9, batch 3250, loss[loss=0.1352, simple_loss=0.2081, pruned_loss=0.03114, over 4781.00 frames.], tot_loss[loss=0.1423, simple_loss=0.214, pruned_loss=0.03528, over 971980.54 frames.], batch size: 14, lr: 2.40e-04
+2022-05-06 09:45:24,840 INFO [train.py:715] (3/8) Epoch 9, batch 3300, loss[loss=0.1265, simple_loss=0.2038, pruned_loss=0.02459, over 4856.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2145, pruned_loss=0.03548, over 971876.69 frames.], batch size: 20, lr: 2.40e-04
+2022-05-06 09:46:03,661 INFO [train.py:715] (3/8) Epoch 9, batch 3350, loss[loss=0.1529, simple_loss=0.218, pruned_loss=0.04393, over 4987.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.03497, over 972339.19 frames.], batch size: 35, lr: 2.40e-04
+2022-05-06 09:46:42,964 INFO [train.py:715] (3/8) Epoch 9, batch 3400, loss[loss=0.1519, simple_loss=0.222, pruned_loss=0.04088, over 4947.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03493, over 972803.10 frames.], batch size: 39, lr: 2.40e-04
+2022-05-06 09:47:22,072 INFO [train.py:715] (3/8) Epoch 9, batch 3450, loss[loss=0.14, simple_loss=0.2102, pruned_loss=0.03486, over 4797.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.0352, over 971897.18 frames.], batch size: 17, lr: 2.40e-04
+2022-05-06 09:48:00,722 INFO [train.py:715] (3/8) Epoch 9, batch 3500, loss[loss=0.1213, simple_loss=0.1874, pruned_loss=0.02758, over 4976.00 frames.], tot_loss[loss=0.142, simple_loss=0.2144, pruned_loss=0.03477, over 972957.57 frames.], batch size: 31, lr: 2.40e-04
+2022-05-06 09:48:40,286 INFO [train.py:715] (3/8) Epoch 9, batch 3550, loss[loss=0.146, simple_loss=0.2313, pruned_loss=0.03038, over 4970.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2151, pruned_loss=0.03476, over 972194.45 frames.], batch size: 24, lr: 2.40e-04
+2022-05-06 09:49:19,724 INFO [train.py:715] (3/8) Epoch 9, batch 3600, loss[loss=0.1773, simple_loss=0.2439, pruned_loss=0.0554, over 4683.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03425, over 973007.60 frames.], batch size: 15, lr: 2.40e-04
+2022-05-06 09:49:59,015 INFO [train.py:715] (3/8) Epoch 9, batch 3650, loss[loss=0.1648, simple_loss=0.2418, pruned_loss=0.04387, over 4749.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03437, over 972687.25 frames.], batch size: 14, lr: 2.40e-04
+2022-05-06 09:50:37,659 INFO [train.py:715] (3/8) Epoch 9, batch 3700, loss[loss=0.1681, simple_loss=0.234, pruned_loss=0.05105, over 4903.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2144, pruned_loss=0.03452, over 972365.76 frames.], batch size: 18, lr: 2.40e-04
+2022-05-06 09:51:17,145 INFO [train.py:715] (3/8) Epoch 9, batch 3750, loss[loss=0.1235, simple_loss=0.1972, pruned_loss=0.02487, over 4828.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2158, pruned_loss=0.03516, over 972216.91 frames.], batch size: 26, lr: 2.40e-04
+2022-05-06 09:51:56,919 INFO [train.py:715] (3/8) Epoch 9, batch 3800, loss[loss=0.131, simple_loss=0.1963, pruned_loss=0.0329, over 4914.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03507, over 971857.65 frames.], batch size: 17, lr: 2.40e-04
+2022-05-06 09:52:35,339 INFO [train.py:715] (3/8) Epoch 9, batch 3850, loss[loss=0.2038, simple_loss=0.2699, pruned_loss=0.06886, over 4894.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03513, over 972182.30 frames.], batch size: 39, lr: 2.40e-04
+2022-05-06 09:53:14,342 INFO [train.py:715] (3/8) Epoch 9, batch 3900, loss[loss=0.1498, simple_loss=0.2324, pruned_loss=0.03361, over 4825.00 frames.], tot_loss[loss=0.142, simple_loss=0.2145, pruned_loss=0.03477, over 973180.82 frames.], batch size: 27, lr: 2.40e-04
+2022-05-06 09:53:53,825 INFO [train.py:715] (3/8) Epoch 9, batch 3950, loss[loss=0.1647, simple_loss=0.2309, pruned_loss=0.04932, over 4913.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.03539, over 973831.75 frames.], batch size: 18, lr: 2.40e-04
+2022-05-06 09:54:33,403 INFO [train.py:715] (3/8) Epoch 9, batch 4000, loss[loss=0.17, simple_loss=0.2291, pruned_loss=0.05539, over 4985.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03489, over 973137.65 frames.], batch size: 14, lr: 2.40e-04
+2022-05-06 09:55:12,125 INFO [train.py:715] (3/8) Epoch 9, batch 4050, loss[loss=0.1224, simple_loss=0.2064, pruned_loss=0.01925, over 4767.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.03489, over 973352.64 frames.], batch size: 19, lr: 2.40e-04
+2022-05-06 09:55:52,107 INFO [train.py:715] (3/8) Epoch 9, batch 4100, loss[loss=0.1687, simple_loss=0.2454, pruned_loss=0.04605, over 4754.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2137, pruned_loss=0.03477, over 973229.47 frames.], batch size: 16, lr: 2.40e-04
+2022-05-06 09:56:30,805 INFO [train.py:715] (3/8) Epoch 9, batch 4150, loss[loss=0.1535, simple_loss=0.2194, pruned_loss=0.04378, over 4990.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.03471, over 973204.33 frames.], batch size: 14, lr: 2.40e-04
+2022-05-06 09:57:10,159 INFO [train.py:715] (3/8) Epoch 9, batch 4200, loss[loss=0.149, simple_loss=0.2294, pruned_loss=0.03425, over 4900.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03423, over 973292.18 frames.], batch size: 19, lr: 2.40e-04
+2022-05-06 09:57:49,723 INFO [train.py:715] (3/8) Epoch 9, batch 4250, loss[loss=0.1559, simple_loss=0.2252, pruned_loss=0.04324, over 4775.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03496, over 972879.08 frames.], batch size: 17, lr: 2.40e-04
+2022-05-06 09:58:29,616 INFO [train.py:715] (3/8) Epoch 9, batch 4300, loss[loss=0.1427, simple_loss=0.2226, pruned_loss=0.03137, over 4732.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.03493, over 973115.71 frames.], batch size: 16, lr: 2.40e-04
+2022-05-06 09:59:09,596 INFO [train.py:715] (3/8) Epoch 9, batch 4350, loss[loss=0.1042, simple_loss=0.1759, pruned_loss=0.01627, over 4822.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.0345, over 973489.96 frames.], batch size: 12, lr: 2.40e-04
+2022-05-06 09:59:48,191 INFO [train.py:715] (3/8) Epoch 9, batch 4400, loss[loss=0.1401, simple_loss=0.2069, pruned_loss=0.03664, over 4809.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03438, over 973304.31 frames.], batch size: 13, lr: 2.40e-04
+2022-05-06 10:00:27,687 INFO [train.py:715] (3/8) Epoch 9, batch 4450, loss[loss=0.1196, simple_loss=0.19, pruned_loss=0.02463, over 4779.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03429, over 973193.27 frames.], batch size: 18, lr: 2.40e-04
+2022-05-06 10:01:06,480 INFO [train.py:715] (3/8) Epoch 9, batch 4500, loss[loss=0.1449, simple_loss=0.2193, pruned_loss=0.03527, over 4799.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03499, over 973113.76 frames.], batch size: 14, lr: 2.40e-04
+2022-05-06 10:01:45,449 INFO [train.py:715] (3/8) Epoch 9, batch 4550, loss[loss=0.2342, simple_loss=0.2971, pruned_loss=0.08567, over 4690.00 frames.], tot_loss[loss=0.1428, simple_loss=0.215, pruned_loss=0.03527, over 973063.73 frames.], batch size: 15, lr: 2.40e-04
+2022-05-06 10:02:24,724 INFO [train.py:715] (3/8) Epoch 9, batch 4600, loss[loss=0.1296, simple_loss=0.2084, pruned_loss=0.02542, over 4786.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.03532, over 972956.79 frames.], batch size: 18, lr: 2.40e-04
+2022-05-06 10:03:04,291 INFO [train.py:715] (3/8) Epoch 9, batch 4650, loss[loss=0.09845, simple_loss=0.1623, pruned_loss=0.01731, over 4799.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2144, pruned_loss=0.035, over 972309.39 frames.], batch size: 12, lr: 2.40e-04
+2022-05-06 10:03:43,903 INFO [train.py:715] (3/8) Epoch 9, batch 4700, loss[loss=0.2089, simple_loss=0.2634, pruned_loss=0.07723, over 4886.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2141, pruned_loss=0.0351, over 972432.02 frames.], batch size: 17, lr: 2.40e-04
+2022-05-06 10:04:22,847 INFO [train.py:715] (3/8) Epoch 9, batch 4750, loss[loss=0.1343, simple_loss=0.21, pruned_loss=0.02931, over 4901.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2133, pruned_loss=0.03461, over 972030.80 frames.], batch size: 17, lr: 2.40e-04
+2022-05-06 10:05:02,421 INFO [train.py:715] (3/8) Epoch 9, batch 4800, loss[loss=0.1394, simple_loss=0.218, pruned_loss=0.03037, over 4738.00 frames.], tot_loss[loss=0.1409, simple_loss=0.213, pruned_loss=0.03437, over 971683.56 frames.], batch size: 16, lr: 2.40e-04
+2022-05-06 10:05:41,421 INFO [train.py:715] (3/8) Epoch 9, batch 4850, loss[loss=0.1258, simple_loss=0.2012, pruned_loss=0.02522, over 4899.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2135, pruned_loss=0.03457, over 972074.42 frames.], batch size: 19, lr: 2.40e-04
+2022-05-06 10:06:20,853 INFO [train.py:715] (3/8) Epoch 9, batch 4900, loss[loss=0.1448, simple_loss=0.2221, pruned_loss=0.03378, over 4763.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03484, over 972429.36 frames.], batch size: 18, lr: 2.40e-04
+2022-05-06 10:06:59,737 INFO [train.py:715] (3/8) Epoch 9, batch 4950, loss[loss=0.1285, simple_loss=0.1987, pruned_loss=0.02919, over 4944.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03448, over 972642.70 frames.], batch size: 21, lr: 2.40e-04
+2022-05-06 10:07:39,115 INFO [train.py:715] (3/8) Epoch 9, batch 5000, loss[loss=0.1189, simple_loss=0.1894, pruned_loss=0.02415, over 4961.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2134, pruned_loss=0.03455, over 972080.56 frames.], batch size: 24, lr: 2.40e-04
+2022-05-06 10:08:18,415 INFO [train.py:715] (3/8) Epoch 9, batch 5050, loss[loss=0.1331, simple_loss=0.2111, pruned_loss=0.02759, over 4952.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03473, over 971959.90 frames.], batch size: 29, lr: 2.40e-04
+2022-05-06 10:08:57,173 INFO [train.py:715] (3/8) Epoch 9, batch 5100, loss[loss=0.1207, simple_loss=0.1952, pruned_loss=0.02309, over 4793.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03448, over 972000.37 frames.], batch size: 18, lr: 2.40e-04
+2022-05-06 10:09:36,561 INFO [train.py:715] (3/8) Epoch 9, batch 5150, loss[loss=0.1235, simple_loss=0.1907, pruned_loss=0.02814, over 4979.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2133, pruned_loss=0.03445, over 972178.85 frames.], batch size: 14, lr: 2.40e-04
+2022-05-06 10:10:15,463 INFO [train.py:715] (3/8) Epoch 9, batch 5200, loss[loss=0.1744, simple_loss=0.23, pruned_loss=0.05942, over 4977.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03424, over 972537.51 frames.], batch size: 14, lr: 2.40e-04
+2022-05-06 10:10:54,751 INFO [train.py:715] (3/8) Epoch 9, batch 5250, loss[loss=0.1345, simple_loss=0.1913, pruned_loss=0.03889, over 4838.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2129, pruned_loss=0.03426, over 972715.96 frames.], batch size: 30, lr: 2.40e-04
+2022-05-06 10:11:33,955 INFO [train.py:715] (3/8) Epoch 9, batch 5300, loss[loss=0.1369, simple_loss=0.2168, pruned_loss=0.02855, over 4890.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2126, pruned_loss=0.034, over 972831.50 frames.], batch size: 22, lr: 2.39e-04
+2022-05-06 10:12:13,445 INFO [train.py:715] (3/8) Epoch 9, batch 5350, loss[loss=0.1647, simple_loss=0.2441, pruned_loss=0.04262, over 4980.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2127, pruned_loss=0.03413, over 973088.77 frames.], batch size: 35, lr: 2.39e-04
+2022-05-06 10:12:52,102 INFO [train.py:715] (3/8) Epoch 9, batch 5400, loss[loss=0.1244, simple_loss=0.2036, pruned_loss=0.02256, over 4942.00 frames.], tot_loss[loss=0.1407, simple_loss=0.213, pruned_loss=0.03421, over 973027.13 frames.], batch size: 29, lr: 2.39e-04
+2022-05-06 10:13:30,898 INFO [train.py:715] (3/8) Epoch 9, batch 5450, loss[loss=0.1549, simple_loss=0.2281, pruned_loss=0.04089, over 4922.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2131, pruned_loss=0.0342, over 972587.76 frames.], batch size: 29, lr: 2.39e-04
+2022-05-06 10:14:10,213 INFO [train.py:715] (3/8) Epoch 9, batch 5500, loss[loss=0.1358, simple_loss=0.2006, pruned_loss=0.03555, over 4783.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03398, over 971944.52 frames.], batch size: 18, lr: 2.39e-04
+2022-05-06 10:14:49,301 INFO [train.py:715] (3/8) Epoch 9, batch 5550, loss[loss=0.1414, simple_loss=0.2119, pruned_loss=0.03545, over 4857.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2128, pruned_loss=0.03402, over 972981.69 frames.], batch size: 30, lr: 2.39e-04
+2022-05-06 10:15:28,466 INFO [train.py:715] (3/8) Epoch 9, batch 5600, loss[loss=0.1344, simple_loss=0.2055, pruned_loss=0.03162, over 4896.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03391, over 972487.29 frames.], batch size: 19, lr: 2.39e-04
+2022-05-06 10:16:07,459 INFO [train.py:715] (3/8) Epoch 9, batch 5650, loss[loss=0.1308, simple_loss=0.2044, pruned_loss=0.0286, over 4992.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03444, over 971934.28 frames.], batch size: 14, lr: 2.39e-04
+2022-05-06 10:16:47,096 INFO [train.py:715] (3/8) Epoch 9, batch 5700, loss[loss=0.1542, simple_loss=0.215, pruned_loss=0.04673, over 4800.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2136, pruned_loss=0.03462, over 972516.59 frames.], batch size: 21, lr: 2.39e-04
+2022-05-06 10:17:26,140 INFO [train.py:715] (3/8) Epoch 9, batch 5750, loss[loss=0.1228, simple_loss=0.193, pruned_loss=0.0263, over 4975.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2129, pruned_loss=0.03422, over 973189.94 frames.], batch size: 14, lr: 2.39e-04
+2022-05-06 10:18:04,787 INFO [train.py:715] (3/8) Epoch 9, batch 5800, loss[loss=0.1542, simple_loss=0.2203, pruned_loss=0.04408, over 4965.00 frames.], tot_loss[loss=0.142, simple_loss=0.2141, pruned_loss=0.03496, over 972889.44 frames.], batch size: 15, lr: 2.39e-04
+2022-05-06 10:18:44,314 INFO [train.py:715] (3/8) Epoch 9, batch 5850, loss[loss=0.1656, simple_loss=0.2316, pruned_loss=0.04985, over 4857.00 frames.], tot_loss[loss=0.1419, simple_loss=0.214, pruned_loss=0.03485, over 973379.95 frames.], batch size: 30, lr: 2.39e-04
+2022-05-06 10:19:23,128 INFO [train.py:715] (3/8) Epoch 9, batch 5900, loss[loss=0.1731, simple_loss=0.241, pruned_loss=0.0526, over 4750.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2133, pruned_loss=0.0348, over 972443.80 frames.], batch size: 19, lr: 2.39e-04
+2022-05-06 10:20:02,777 INFO [train.py:715] (3/8) Epoch 9, batch 5950, loss[loss=0.1193, simple_loss=0.1945, pruned_loss=0.02202, over 4813.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2134, pruned_loss=0.0346, over 971628.31 frames.], batch size: 24, lr: 2.39e-04
+2022-05-06 10:20:41,532 INFO [train.py:715] (3/8) Epoch 9, batch 6000, loss[loss=0.219, simple_loss=0.2648, pruned_loss=0.08663, over 4835.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03475, over 971943.22 frames.], batch size: 15, lr: 2.39e-04
+2022-05-06 10:20:41,533 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 10:20:51,193 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.107, simple_loss=0.1914, pruned_loss=0.0113, over 914524.00 frames.
+2022-05-06 10:21:30,882 INFO [train.py:715] (3/8) Epoch 9, batch 6050, loss[loss=0.1347, simple_loss=0.2056, pruned_loss=0.03194, over 4906.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2138, pruned_loss=0.03468, over 971516.46 frames.], batch size: 17, lr: 2.39e-04
+2022-05-06 10:22:10,752 INFO [train.py:715] (3/8) Epoch 9, batch 6100, loss[loss=0.1652, simple_loss=0.239, pruned_loss=0.04572, over 4967.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03438, over 972185.27 frames.], batch size: 15, lr: 2.39e-04
+2022-05-06 10:22:49,972 INFO [train.py:715] (3/8) Epoch 9, batch 6150, loss[loss=0.1117, simple_loss=0.1878, pruned_loss=0.01777, over 4933.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03448, over 973382.46 frames.], batch size: 29, lr: 2.39e-04
+2022-05-06 10:23:28,785 INFO [train.py:715] (3/8) Epoch 9, batch 6200, loss[loss=0.1312, simple_loss=0.2022, pruned_loss=0.03014, over 4913.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.0347, over 973701.67 frames.], batch size: 29, lr: 2.39e-04
+2022-05-06 10:24:08,424 INFO [train.py:715] (3/8) Epoch 9, batch 6250, loss[loss=0.1415, simple_loss=0.2234, pruned_loss=0.0298, over 4817.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03423, over 973203.98 frames.], batch size: 25, lr: 2.39e-04
+2022-05-06 10:24:47,205 INFO [train.py:715] (3/8) Epoch 9, batch 6300, loss[loss=0.1449, simple_loss=0.2084, pruned_loss=0.04071, over 4982.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2136, pruned_loss=0.03451, over 973358.44 frames.], batch size: 14, lr: 2.39e-04
+2022-05-06 10:25:26,321 INFO [train.py:715] (3/8) Epoch 9, batch 6350, loss[loss=0.1272, simple_loss=0.203, pruned_loss=0.02568, over 4748.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2139, pruned_loss=0.03481, over 973834.94 frames.], batch size: 16, lr: 2.39e-04
+2022-05-06 10:26:05,953 INFO [train.py:715] (3/8) Epoch 9, batch 6400, loss[loss=0.12, simple_loss=0.1852, pruned_loss=0.02737, over 4977.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2139, pruned_loss=0.03488, over 973183.28 frames.], batch size: 25, lr: 2.39e-04
+2022-05-06 10:26:46,098 INFO [train.py:715] (3/8) Epoch 9, batch 6450, loss[loss=0.1425, simple_loss=0.2045, pruned_loss=0.04027, over 4845.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2133, pruned_loss=0.0344, over 973544.97 frames.], batch size: 32, lr: 2.39e-04
+2022-05-06 10:27:25,423 INFO [train.py:715] (3/8) Epoch 9, batch 6500, loss[loss=0.158, simple_loss=0.2256, pruned_loss=0.0452, over 4690.00 frames.], tot_loss[loss=0.1416, simple_loss=0.214, pruned_loss=0.03454, over 972738.57 frames.], batch size: 15, lr: 2.39e-04
+2022-05-06 10:28:04,256 INFO [train.py:715] (3/8) Epoch 9, batch 6550, loss[loss=0.1429, simple_loss=0.2129, pruned_loss=0.03642, over 4972.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03437, over 974167.70 frames.], batch size: 14, lr: 2.39e-04
+2022-05-06 10:28:44,038 INFO [train.py:715] (3/8) Epoch 9, batch 6600, loss[loss=0.1602, simple_loss=0.2234, pruned_loss=0.0485, over 4719.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.0346, over 972831.11 frames.], batch size: 12, lr: 2.39e-04
+2022-05-06 10:29:23,596 INFO [train.py:715] (3/8) Epoch 9, batch 6650, loss[loss=0.1296, simple_loss=0.2076, pruned_loss=0.02578, over 4846.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03444, over 972953.50 frames.], batch size: 20, lr: 2.39e-04
+2022-05-06 10:30:02,747 INFO [train.py:715] (3/8) Epoch 9, batch 6700, loss[loss=0.1716, simple_loss=0.2371, pruned_loss=0.05303, over 4974.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03446, over 973147.65 frames.], batch size: 15, lr: 2.39e-04
+2022-05-06 10:30:44,170 INFO [train.py:715] (3/8) Epoch 9, batch 6750, loss[loss=0.1457, simple_loss=0.2194, pruned_loss=0.03602, over 4813.00 frames.], tot_loss[loss=0.142, simple_loss=0.2144, pruned_loss=0.0348, over 973649.38 frames.], batch size: 27, lr: 2.39e-04
+2022-05-06 10:31:23,603 INFO [train.py:715] (3/8) Epoch 9, batch 6800, loss[loss=0.1426, simple_loss=0.2286, pruned_loss=0.02837, over 4791.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2147, pruned_loss=0.03457, over 973542.02 frames.], batch size: 17, lr: 2.39e-04
+2022-05-06 10:32:02,558 INFO [train.py:715] (3/8) Epoch 9, batch 6850, loss[loss=0.1425, simple_loss=0.214, pruned_loss=0.03554, over 4954.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03409, over 974108.00 frames.], batch size: 24, lr: 2.39e-04
+2022-05-06 10:32:40,753 INFO [train.py:715] (3/8) Epoch 9, batch 6900, loss[loss=0.1344, simple_loss=0.215, pruned_loss=0.02686, over 4906.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03361, over 974232.30 frames.], batch size: 18, lr: 2.39e-04
+2022-05-06 10:33:20,058 INFO [train.py:715] (3/8) Epoch 9, batch 6950, loss[loss=0.138, simple_loss=0.2096, pruned_loss=0.03316, over 4927.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2145, pruned_loss=0.03415, over 974137.29 frames.], batch size: 23, lr: 2.39e-04
+2022-05-06 10:33:59,865 INFO [train.py:715] (3/8) Epoch 9, batch 7000, loss[loss=0.159, simple_loss=0.2382, pruned_loss=0.0399, over 4961.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.03373, over 973546.01 frames.], batch size: 15, lr: 2.39e-04
+2022-05-06 10:34:38,726 INFO [train.py:715] (3/8) Epoch 9, batch 7050, loss[loss=0.1456, simple_loss=0.2098, pruned_loss=0.04069, over 4689.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03387, over 973406.43 frames.], batch size: 15, lr: 2.39e-04
+2022-05-06 10:35:17,350 INFO [train.py:715] (3/8) Epoch 9, batch 7100, loss[loss=0.1292, simple_loss=0.2007, pruned_loss=0.02883, over 4952.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.03419, over 973132.43 frames.], batch size: 21, lr: 2.39e-04
+2022-05-06 10:35:56,811 INFO [train.py:715] (3/8) Epoch 9, batch 7150, loss[loss=0.1381, simple_loss=0.2154, pruned_loss=0.03042, over 4888.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2126, pruned_loss=0.03401, over 973458.78 frames.], batch size: 22, lr: 2.39e-04
+2022-05-06 10:36:35,505 INFO [train.py:715] (3/8) Epoch 9, batch 7200, loss[loss=0.13, simple_loss=0.2037, pruned_loss=0.02816, over 4793.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03458, over 973233.35 frames.], batch size: 18, lr: 2.39e-04
+2022-05-06 10:37:14,247 INFO [train.py:715] (3/8) Epoch 9, batch 7250, loss[loss=0.1586, simple_loss=0.2416, pruned_loss=0.03775, over 4699.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03428, over 972810.37 frames.], batch size: 15, lr: 2.39e-04
+2022-05-06 10:37:53,496 INFO [train.py:715] (3/8) Epoch 9, batch 7300, loss[loss=0.1695, simple_loss=0.2381, pruned_loss=0.05039, over 4845.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.03477, over 973056.14 frames.], batch size: 32, lr: 2.39e-04
+2022-05-06 10:38:32,800 INFO [train.py:715] (3/8) Epoch 9, batch 7350, loss[loss=0.1452, simple_loss=0.2201, pruned_loss=0.03511, over 4963.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03511, over 973330.04 frames.], batch size: 39, lr: 2.39e-04
+2022-05-06 10:39:11,301 INFO [train.py:715] (3/8) Epoch 9, batch 7400, loss[loss=0.1787, simple_loss=0.2397, pruned_loss=0.05884, over 4962.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03478, over 973321.34 frames.], batch size: 35, lr: 2.39e-04
+2022-05-06 10:39:50,261 INFO [train.py:715] (3/8) Epoch 9, batch 7450, loss[loss=0.1642, simple_loss=0.2191, pruned_loss=0.05469, over 4887.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03517, over 974380.67 frames.], batch size: 22, lr: 2.39e-04
+2022-05-06 10:40:30,202 INFO [train.py:715] (3/8) Epoch 9, batch 7500, loss[loss=0.1442, simple_loss=0.2141, pruned_loss=0.03717, over 4789.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03551, over 975201.65 frames.], batch size: 18, lr: 2.39e-04
+2022-05-06 10:41:09,251 INFO [train.py:715] (3/8) Epoch 9, batch 7550, loss[loss=0.1435, simple_loss=0.2321, pruned_loss=0.02744, over 4764.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03504, over 974342.68 frames.], batch size: 17, lr: 2.39e-04
+2022-05-06 10:41:48,090 INFO [train.py:715] (3/8) Epoch 9, batch 7600, loss[loss=0.1493, simple_loss=0.2278, pruned_loss=0.03545, over 4779.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03528, over 973486.09 frames.], batch size: 18, lr: 2.39e-04
+2022-05-06 10:42:27,545 INFO [train.py:715] (3/8) Epoch 9, batch 7650, loss[loss=0.1311, simple_loss=0.1998, pruned_loss=0.03117, over 4731.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03518, over 973312.68 frames.], batch size: 16, lr: 2.39e-04
+2022-05-06 10:43:06,740 INFO [train.py:715] (3/8) Epoch 9, batch 7700, loss[loss=0.1444, simple_loss=0.2146, pruned_loss=0.0371, over 4973.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03501, over 972800.46 frames.], batch size: 39, lr: 2.39e-04
+2022-05-06 10:43:45,572 INFO [train.py:715] (3/8) Epoch 9, batch 7750, loss[loss=0.1335, simple_loss=0.2205, pruned_loss=0.02329, over 4876.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.03497, over 972459.01 frames.], batch size: 16, lr: 2.39e-04
+2022-05-06 10:44:24,378 INFO [train.py:715] (3/8) Epoch 9, batch 7800, loss[loss=0.1386, simple_loss=0.2248, pruned_loss=0.02619, over 4818.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2148, pruned_loss=0.03482, over 972472.87 frames.], batch size: 25, lr: 2.39e-04
+2022-05-06 10:45:04,417 INFO [train.py:715] (3/8) Epoch 9, batch 7850, loss[loss=0.149, simple_loss=0.2099, pruned_loss=0.044, over 4849.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03444, over 971852.85 frames.], batch size: 32, lr: 2.39e-04
+2022-05-06 10:45:43,395 INFO [train.py:715] (3/8) Epoch 9, batch 7900, loss[loss=0.1268, simple_loss=0.1956, pruned_loss=0.029, over 4845.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03499, over 971473.24 frames.], batch size: 15, lr: 2.39e-04
+2022-05-06 10:46:21,529 INFO [train.py:715] (3/8) Epoch 9, batch 7950, loss[loss=0.1741, simple_loss=0.2429, pruned_loss=0.05269, over 4899.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03496, over 971866.96 frames.], batch size: 17, lr: 2.39e-04
+2022-05-06 10:47:00,914 INFO [train.py:715] (3/8) Epoch 9, batch 8000, loss[loss=0.1459, simple_loss=0.2277, pruned_loss=0.03203, over 4912.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03475, over 972625.21 frames.], batch size: 18, lr: 2.38e-04
+2022-05-06 10:47:39,934 INFO [train.py:715] (3/8) Epoch 9, batch 8050, loss[loss=0.1296, simple_loss=0.2143, pruned_loss=0.02251, over 4823.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2146, pruned_loss=0.03454, over 972344.20 frames.], batch size: 15, lr: 2.38e-04
+2022-05-06 10:48:18,556 INFO [train.py:715] (3/8) Epoch 9, batch 8100, loss[loss=0.1073, simple_loss=0.1844, pruned_loss=0.01512, over 4941.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2153, pruned_loss=0.03465, over 973377.61 frames.], batch size: 29, lr: 2.38e-04
+2022-05-06 10:48:57,106 INFO [train.py:715] (3/8) Epoch 9, batch 8150, loss[loss=0.1394, simple_loss=0.2187, pruned_loss=0.03011, over 4965.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03463, over 973184.49 frames.], batch size: 39, lr: 2.38e-04
+2022-05-06 10:49:36,458 INFO [train.py:715] (3/8) Epoch 9, batch 8200, loss[loss=0.1342, simple_loss=0.2039, pruned_loss=0.03226, over 4880.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03516, over 972978.74 frames.], batch size: 22, lr: 2.38e-04
+2022-05-06 10:50:15,123 INFO [train.py:715] (3/8) Epoch 9, batch 8250, loss[loss=0.1106, simple_loss=0.1828, pruned_loss=0.01921, over 4793.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03503, over 973412.22 frames.], batch size: 21, lr: 2.38e-04
+2022-05-06 10:50:53,695 INFO [train.py:715] (3/8) Epoch 9, batch 8300, loss[loss=0.1437, simple_loss=0.2189, pruned_loss=0.03427, over 4993.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03462, over 973842.80 frames.], batch size: 16, lr: 2.38e-04
+2022-05-06 10:51:32,739 INFO [train.py:715] (3/8) Epoch 9, batch 8350, loss[loss=0.1552, simple_loss=0.2195, pruned_loss=0.04546, over 4941.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03507, over 974161.38 frames.], batch size: 39, lr: 2.38e-04
+2022-05-06 10:52:12,415 INFO [train.py:715] (3/8) Epoch 9, batch 8400, loss[loss=0.1323, simple_loss=0.2093, pruned_loss=0.0277, over 4821.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03491, over 973179.64 frames.], batch size: 13, lr: 2.38e-04
+2022-05-06 10:52:50,772 INFO [train.py:715] (3/8) Epoch 9, batch 8450, loss[loss=0.1213, simple_loss=0.1975, pruned_loss=0.02254, over 4990.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03507, over 973457.30 frames.], batch size: 20, lr: 2.38e-04
+2022-05-06 10:53:29,412 INFO [train.py:715] (3/8) Epoch 9, batch 8500, loss[loss=0.1531, simple_loss=0.2259, pruned_loss=0.04014, over 4832.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2145, pruned_loss=0.03531, over 972844.01 frames.], batch size: 13, lr: 2.38e-04
+2022-05-06 10:54:08,958 INFO [train.py:715] (3/8) Epoch 9, batch 8550, loss[loss=0.1213, simple_loss=0.1987, pruned_loss=0.02194, over 4770.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2149, pruned_loss=0.03529, over 972068.82 frames.], batch size: 12, lr: 2.38e-04
+2022-05-06 10:54:48,127 INFO [train.py:715] (3/8) Epoch 9, batch 8600, loss[loss=0.1664, simple_loss=0.2351, pruned_loss=0.04891, over 4835.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03509, over 972277.85 frames.], batch size: 15, lr: 2.38e-04
+2022-05-06 10:55:26,985 INFO [train.py:715] (3/8) Epoch 9, batch 8650, loss[loss=0.1435, simple_loss=0.2286, pruned_loss=0.02917, over 4963.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03518, over 971399.65 frames.], batch size: 24, lr: 2.38e-04
+2022-05-06 10:56:06,798 INFO [train.py:715] (3/8) Epoch 9, batch 8700, loss[loss=0.1385, simple_loss=0.2139, pruned_loss=0.03156, over 4788.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.03521, over 972246.98 frames.], batch size: 14, lr: 2.38e-04
+2022-05-06 10:56:46,700 INFO [train.py:715] (3/8) Epoch 9, batch 8750, loss[loss=0.173, simple_loss=0.2468, pruned_loss=0.04964, over 4743.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.03493, over 972872.57 frames.], batch size: 16, lr: 2.38e-04
+2022-05-06 10:57:25,010 INFO [train.py:715] (3/8) Epoch 9, batch 8800, loss[loss=0.1436, simple_loss=0.216, pruned_loss=0.03561, over 4840.00 frames.], tot_loss[loss=0.1419, simple_loss=0.214, pruned_loss=0.03489, over 973629.82 frames.], batch size: 26, lr: 2.38e-04
+2022-05-06 10:58:04,391 INFO [train.py:715] (3/8) Epoch 9, batch 8850, loss[loss=0.1664, simple_loss=0.2324, pruned_loss=0.05022, over 4773.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.03425, over 972392.49 frames.], batch size: 14, lr: 2.38e-04
+2022-05-06 10:58:43,839 INFO [train.py:715] (3/8) Epoch 9, batch 8900, loss[loss=0.1159, simple_loss=0.1876, pruned_loss=0.02207, over 4816.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03455, over 973084.49 frames.], batch size: 13, lr: 2.38e-04
+2022-05-06 10:59:22,968 INFO [train.py:715] (3/8) Epoch 9, batch 8950, loss[loss=0.114, simple_loss=0.1914, pruned_loss=0.01829, over 4940.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03466, over 972684.28 frames.], batch size: 23, lr: 2.38e-04
+2022-05-06 11:00:01,615 INFO [train.py:715] (3/8) Epoch 9, batch 9000, loss[loss=0.1334, simple_loss=0.2136, pruned_loss=0.02665, over 4928.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03483, over 973227.07 frames.], batch size: 29, lr: 2.38e-04
+2022-05-06 11:00:01,616 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 11:00:11,231 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.107, simple_loss=0.1914, pruned_loss=0.0113, over 914524.00 frames.
+2022-05-06 11:00:49,915 INFO [train.py:715] (3/8) Epoch 9, batch 9050, loss[loss=0.1626, simple_loss=0.2326, pruned_loss=0.04635, over 4902.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2133, pruned_loss=0.0343, over 973435.57 frames.], batch size: 39, lr: 2.38e-04
+2022-05-06 11:01:30,083 INFO [train.py:715] (3/8) Epoch 9, batch 9100, loss[loss=0.1341, simple_loss=0.2036, pruned_loss=0.03225, over 4823.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2139, pruned_loss=0.03485, over 972781.44 frames.], batch size: 26, lr: 2.38e-04
+2022-05-06 11:02:09,670 INFO [train.py:715] (3/8) Epoch 9, batch 9150, loss[loss=0.157, simple_loss=0.2142, pruned_loss=0.0499, over 4785.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03513, over 973105.83 frames.], batch size: 12, lr: 2.38e-04
+2022-05-06 11:02:48,632 INFO [train.py:715] (3/8) Epoch 9, batch 9200, loss[loss=0.1489, simple_loss=0.2228, pruned_loss=0.03754, over 4967.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2149, pruned_loss=0.03562, over 972281.08 frames.], batch size: 24, lr: 2.38e-04
+2022-05-06 11:03:28,185 INFO [train.py:715] (3/8) Epoch 9, batch 9250, loss[loss=0.1241, simple_loss=0.1962, pruned_loss=0.02597, over 4828.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2159, pruned_loss=0.03632, over 972057.50 frames.], batch size: 27, lr: 2.38e-04
+2022-05-06 11:04:07,600 INFO [train.py:715] (3/8) Epoch 9, batch 9300, loss[loss=0.1131, simple_loss=0.1852, pruned_loss=0.02046, over 4959.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2153, pruned_loss=0.03584, over 971714.61 frames.], batch size: 24, lr: 2.38e-04
+2022-05-06 11:04:46,767 INFO [train.py:715] (3/8) Epoch 9, batch 9350, loss[loss=0.1591, simple_loss=0.2318, pruned_loss=0.04324, over 4828.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2154, pruned_loss=0.03555, over 971344.93 frames.], batch size: 30, lr: 2.38e-04
+2022-05-06 11:05:25,229 INFO [train.py:715] (3/8) Epoch 9, batch 9400, loss[loss=0.1361, simple_loss=0.2105, pruned_loss=0.03082, over 4858.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2144, pruned_loss=0.03504, over 971233.77 frames.], batch size: 20, lr: 2.38e-04
+2022-05-06 11:06:05,137 INFO [train.py:715] (3/8) Epoch 9, batch 9450, loss[loss=0.1332, simple_loss=0.216, pruned_loss=0.02518, over 4812.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2141, pruned_loss=0.03476, over 971850.68 frames.], batch size: 21, lr: 2.38e-04
+2022-05-06 11:06:44,277 INFO [train.py:715] (3/8) Epoch 9, batch 9500, loss[loss=0.1238, simple_loss=0.1978, pruned_loss=0.02491, over 4711.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03476, over 972317.28 frames.], batch size: 15, lr: 2.38e-04
+2022-05-06 11:07:22,930 INFO [train.py:715] (3/8) Epoch 9, batch 9550, loss[loss=0.1457, simple_loss=0.2217, pruned_loss=0.03487, over 4946.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2135, pruned_loss=0.03459, over 972554.48 frames.], batch size: 21, lr: 2.38e-04
+2022-05-06 11:08:02,127 INFO [train.py:715] (3/8) Epoch 9, batch 9600, loss[loss=0.1504, simple_loss=0.2192, pruned_loss=0.04081, over 4951.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2137, pruned_loss=0.03492, over 972316.73 frames.], batch size: 18, lr: 2.38e-04
+2022-05-06 11:08:41,397 INFO [train.py:715] (3/8) Epoch 9, batch 9650, loss[loss=0.1451, simple_loss=0.2122, pruned_loss=0.03905, over 4852.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2139, pruned_loss=0.03489, over 971920.93 frames.], batch size: 34, lr: 2.38e-04
+2022-05-06 11:09:20,428 INFO [train.py:715] (3/8) Epoch 9, batch 9700, loss[loss=0.1454, simple_loss=0.2059, pruned_loss=0.04241, over 4826.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03467, over 972368.23 frames.], batch size: 13, lr: 2.38e-04
+2022-05-06 11:09:58,455 INFO [train.py:715] (3/8) Epoch 9, batch 9750, loss[loss=0.155, simple_loss=0.2199, pruned_loss=0.04504, over 4696.00 frames.], tot_loss[loss=0.1408, simple_loss=0.213, pruned_loss=0.03436, over 972711.27 frames.], batch size: 15, lr: 2.38e-04
+2022-05-06 11:10:38,590 INFO [train.py:715] (3/8) Epoch 9, batch 9800, loss[loss=0.1406, simple_loss=0.2204, pruned_loss=0.03044, over 4951.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03466, over 972431.47 frames.], batch size: 21, lr: 2.38e-04
+2022-05-06 11:11:18,276 INFO [train.py:715] (3/8) Epoch 9, batch 9850, loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03608, over 4740.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03512, over 971875.09 frames.], batch size: 16, lr: 2.38e-04
+2022-05-06 11:11:56,609 INFO [train.py:715] (3/8) Epoch 9, batch 9900, loss[loss=0.1422, simple_loss=0.2076, pruned_loss=0.03836, over 4902.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2145, pruned_loss=0.03542, over 972123.72 frames.], batch size: 17, lr: 2.38e-04
+2022-05-06 11:12:35,818 INFO [train.py:715] (3/8) Epoch 9, batch 9950, loss[loss=0.1634, simple_loss=0.2389, pruned_loss=0.04392, over 4879.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2142, pruned_loss=0.03516, over 971365.61 frames.], batch size: 22, lr: 2.38e-04
+2022-05-06 11:13:15,756 INFO [train.py:715] (3/8) Epoch 9, batch 10000, loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03032, over 4823.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2146, pruned_loss=0.03557, over 971701.28 frames.], batch size: 27, lr: 2.38e-04
+2022-05-06 11:13:55,090 INFO [train.py:715] (3/8) Epoch 9, batch 10050, loss[loss=0.1508, simple_loss=0.2178, pruned_loss=0.04193, over 4911.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03526, over 972143.37 frames.], batch size: 39, lr: 2.38e-04
+2022-05-06 11:14:33,374 INFO [train.py:715] (3/8) Epoch 9, batch 10100, loss[loss=0.1311, simple_loss=0.2043, pruned_loss=0.02892, over 4771.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03526, over 971845.24 frames.], batch size: 14, lr: 2.38e-04
+2022-05-06 11:15:12,912 INFO [train.py:715] (3/8) Epoch 9, batch 10150, loss[loss=0.169, simple_loss=0.2534, pruned_loss=0.04224, over 4779.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03554, over 971412.73 frames.], batch size: 18, lr: 2.38e-04
+2022-05-06 11:15:52,571 INFO [train.py:715] (3/8) Epoch 9, batch 10200, loss[loss=0.1658, simple_loss=0.249, pruned_loss=0.0413, over 4750.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03465, over 971325.62 frames.], batch size: 16, lr: 2.38e-04
+2022-05-06 11:16:31,361 INFO [train.py:715] (3/8) Epoch 9, batch 10250, loss[loss=0.1591, simple_loss=0.23, pruned_loss=0.04409, over 4939.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03472, over 971813.79 frames.], batch size: 23, lr: 2.38e-04
+2022-05-06 11:17:10,102 INFO [train.py:715] (3/8) Epoch 9, batch 10300, loss[loss=0.1426, simple_loss=0.2227, pruned_loss=0.03122, over 4743.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03465, over 972768.59 frames.], batch size: 16, lr: 2.38e-04
+2022-05-06 11:17:49,726 INFO [train.py:715] (3/8) Epoch 9, batch 10350, loss[loss=0.115, simple_loss=0.1891, pruned_loss=0.02043, over 4749.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2144, pruned_loss=0.03449, over 972461.66 frames.], batch size: 16, lr: 2.38e-04
+2022-05-06 11:18:28,422 INFO [train.py:715] (3/8) Epoch 9, batch 10400, loss[loss=0.1572, simple_loss=0.2336, pruned_loss=0.04037, over 4811.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03439, over 972048.82 frames.], batch size: 25, lr: 2.38e-04
+2022-05-06 11:19:06,741 INFO [train.py:715] (3/8) Epoch 9, batch 10450, loss[loss=0.1504, simple_loss=0.2258, pruned_loss=0.03752, over 4741.00 frames.], tot_loss[loss=0.1424, simple_loss=0.215, pruned_loss=0.03492, over 972317.36 frames.], batch size: 19, lr: 2.38e-04
+2022-05-06 11:19:45,851 INFO [train.py:715] (3/8) Epoch 9, batch 10500, loss[loss=0.1446, simple_loss=0.2224, pruned_loss=0.03337, over 4907.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03475, over 972508.97 frames.], batch size: 17, lr: 2.38e-04
+2022-05-06 11:20:25,285 INFO [train.py:715] (3/8) Epoch 9, batch 10550, loss[loss=0.1443, simple_loss=0.2172, pruned_loss=0.03574, over 4902.00 frames.], tot_loss[loss=0.142, simple_loss=0.2149, pruned_loss=0.03462, over 972788.00 frames.], batch size: 39, lr: 2.38e-04
+2022-05-06 11:21:04,104 INFO [train.py:715] (3/8) Epoch 9, batch 10600, loss[loss=0.1243, simple_loss=0.1947, pruned_loss=0.027, over 4953.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03458, over 972989.24 frames.], batch size: 21, lr: 2.38e-04
+2022-05-06 11:21:42,614 INFO [train.py:715] (3/8) Epoch 9, batch 10650, loss[loss=0.1489, simple_loss=0.2307, pruned_loss=0.03355, over 4866.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03494, over 973031.33 frames.], batch size: 20, lr: 2.38e-04
+2022-05-06 11:22:21,917 INFO [train.py:715] (3/8) Epoch 9, batch 10700, loss[loss=0.1918, simple_loss=0.255, pruned_loss=0.06425, over 4872.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03527, over 972966.75 frames.], batch size: 16, lr: 2.37e-04
+2022-05-06 11:23:01,946 INFO [train.py:715] (3/8) Epoch 9, batch 10750, loss[loss=0.137, simple_loss=0.2066, pruned_loss=0.03371, over 4952.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.035, over 972946.85 frames.], batch size: 21, lr: 2.37e-04
+2022-05-06 11:23:40,541 INFO [train.py:715] (3/8) Epoch 9, batch 10800, loss[loss=0.1501, simple_loss=0.2241, pruned_loss=0.03802, over 4748.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03484, over 972579.18 frames.], batch size: 19, lr: 2.37e-04
+2022-05-06 11:24:20,016 INFO [train.py:715] (3/8) Epoch 9, batch 10850, loss[loss=0.1369, simple_loss=0.2044, pruned_loss=0.03472, over 4773.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03488, over 972946.32 frames.], batch size: 14, lr: 2.37e-04
+2022-05-06 11:24:59,848 INFO [train.py:715] (3/8) Epoch 9, batch 10900, loss[loss=0.1497, simple_loss=0.2071, pruned_loss=0.04613, over 4983.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03488, over 972859.83 frames.], batch size: 26, lr: 2.37e-04
+2022-05-06 11:25:40,142 INFO [train.py:715] (3/8) Epoch 9, batch 10950, loss[loss=0.1626, simple_loss=0.2355, pruned_loss=0.0448, over 4747.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03462, over 972658.08 frames.], batch size: 16, lr: 2.37e-04
+2022-05-06 11:26:20,015 INFO [train.py:715] (3/8) Epoch 9, batch 11000, loss[loss=0.1639, simple_loss=0.2203, pruned_loss=0.0538, over 4975.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03504, over 972964.64 frames.], batch size: 14, lr: 2.37e-04
+2022-05-06 11:27:00,852 INFO [train.py:715] (3/8) Epoch 9, batch 11050, loss[loss=0.1536, simple_loss=0.2235, pruned_loss=0.04191, over 4913.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03483, over 974128.55 frames.], batch size: 17, lr: 2.37e-04
+2022-05-06 11:27:42,120 INFO [train.py:715] (3/8) Epoch 9, batch 11100, loss[loss=0.1504, simple_loss=0.2176, pruned_loss=0.0416, over 4889.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03438, over 973958.70 frames.], batch size: 22, lr: 2.37e-04
+2022-05-06 11:28:22,784 INFO [train.py:715] (3/8) Epoch 9, batch 11150, loss[loss=0.1335, simple_loss=0.2053, pruned_loss=0.03089, over 4872.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.0344, over 973916.75 frames.], batch size: 30, lr: 2.37e-04
+2022-05-06 11:29:03,600 INFO [train.py:715] (3/8) Epoch 9, batch 11200, loss[loss=0.145, simple_loss=0.2198, pruned_loss=0.0351, over 4826.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03489, over 973341.03 frames.], batch size: 15, lr: 2.37e-04
+2022-05-06 11:29:45,084 INFO [train.py:715] (3/8) Epoch 9, batch 11250, loss[loss=0.1308, simple_loss=0.2102, pruned_loss=0.02569, over 4768.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.0348, over 972263.48 frames.], batch size: 19, lr: 2.37e-04
+2022-05-06 11:30:26,203 INFO [train.py:715] (3/8) Epoch 9, batch 11300, loss[loss=0.1289, simple_loss=0.2019, pruned_loss=0.02794, over 4763.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2149, pruned_loss=0.03539, over 972436.97 frames.], batch size: 18, lr: 2.37e-04
+2022-05-06 11:31:06,651 INFO [train.py:715] (3/8) Epoch 9, batch 11350, loss[loss=0.1235, simple_loss=0.1991, pruned_loss=0.02394, over 4907.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2155, pruned_loss=0.03535, over 973243.71 frames.], batch size: 17, lr: 2.37e-04
+2022-05-06 11:31:47,929 INFO [train.py:715] (3/8) Epoch 9, batch 11400, loss[loss=0.1359, simple_loss=0.2082, pruned_loss=0.03177, over 4800.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03513, over 972867.10 frames.], batch size: 21, lr: 2.37e-04
+2022-05-06 11:32:29,497 INFO [train.py:715] (3/8) Epoch 9, batch 11450, loss[loss=0.1472, simple_loss=0.2195, pruned_loss=0.03742, over 4907.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.0353, over 973592.25 frames.], batch size: 19, lr: 2.37e-04
+2022-05-06 11:33:10,078 INFO [train.py:715] (3/8) Epoch 9, batch 11500, loss[loss=0.1151, simple_loss=0.2015, pruned_loss=0.01436, over 4690.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03451, over 972791.59 frames.], batch size: 15, lr: 2.37e-04
+2022-05-06 11:33:50,773 INFO [train.py:715] (3/8) Epoch 9, batch 11550, loss[loss=0.1376, simple_loss=0.209, pruned_loss=0.03313, over 4933.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2137, pruned_loss=0.03454, over 973373.37 frames.], batch size: 29, lr: 2.37e-04
+2022-05-06 11:34:32,090 INFO [train.py:715] (3/8) Epoch 9, batch 11600, loss[loss=0.1387, simple_loss=0.2053, pruned_loss=0.03609, over 4798.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.03359, over 973759.45 frames.], batch size: 17, lr: 2.37e-04
+2022-05-06 11:35:13,601 INFO [train.py:715] (3/8) Epoch 9, batch 11650, loss[loss=0.1579, simple_loss=0.2376, pruned_loss=0.03907, over 4707.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.03353, over 972820.33 frames.], batch size: 15, lr: 2.37e-04
+2022-05-06 11:35:53,522 INFO [train.py:715] (3/8) Epoch 9, batch 11700, loss[loss=0.1361, simple_loss=0.2047, pruned_loss=0.0337, over 4921.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.03413, over 973197.09 frames.], batch size: 29, lr: 2.37e-04
+2022-05-06 11:36:34,967 INFO [train.py:715] (3/8) Epoch 9, batch 11750, loss[loss=0.1441, simple_loss=0.2149, pruned_loss=0.03668, over 4765.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03431, over 972979.77 frames.], batch size: 19, lr: 2.37e-04
+2022-05-06 11:37:16,470 INFO [train.py:715] (3/8) Epoch 9, batch 11800, loss[loss=0.1172, simple_loss=0.1861, pruned_loss=0.02419, over 4828.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.03475, over 972348.12 frames.], batch size: 25, lr: 2.37e-04
+2022-05-06 11:37:56,813 INFO [train.py:715] (3/8) Epoch 9, batch 11850, loss[loss=0.1756, simple_loss=0.229, pruned_loss=0.06112, over 4908.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03439, over 972597.26 frames.], batch size: 17, lr: 2.37e-04
+2022-05-06 11:38:37,234 INFO [train.py:715] (3/8) Epoch 9, batch 11900, loss[loss=0.1153, simple_loss=0.1863, pruned_loss=0.0221, over 4825.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2131, pruned_loss=0.0346, over 972578.99 frames.], batch size: 12, lr: 2.37e-04
+2022-05-06 11:39:18,263 INFO [train.py:715] (3/8) Epoch 9, batch 11950, loss[loss=0.1432, simple_loss=0.2174, pruned_loss=0.03451, over 4980.00 frames.], tot_loss[loss=0.142, simple_loss=0.2141, pruned_loss=0.03493, over 973306.80 frames.], batch size: 26, lr: 2.37e-04
+2022-05-06 11:39:59,369 INFO [train.py:715] (3/8) Epoch 9, batch 12000, loss[loss=0.1352, simple_loss=0.2106, pruned_loss=0.02993, over 4691.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2132, pruned_loss=0.03459, over 972306.32 frames.], batch size: 15, lr: 2.37e-04
+2022-05-06 11:39:59,370 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 11:40:09,081 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.107, simple_loss=0.1913, pruned_loss=0.01136, over 914524.00 frames.
+2022-05-06 11:40:50,126 INFO [train.py:715] (3/8) Epoch 9, batch 12050, loss[loss=0.1226, simple_loss=0.1973, pruned_loss=0.02395, over 4784.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03442, over 972068.19 frames.], batch size: 21, lr: 2.37e-04
+2022-05-06 11:41:29,626 INFO [train.py:715] (3/8) Epoch 9, batch 12100, loss[loss=0.1589, simple_loss=0.2252, pruned_loss=0.04632, over 4870.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2141, pruned_loss=0.03435, over 972634.73 frames.], batch size: 34, lr: 2.37e-04
+2022-05-06 11:42:10,009 INFO [train.py:715] (3/8) Epoch 9, batch 12150, loss[loss=0.1539, simple_loss=0.2243, pruned_loss=0.04173, over 4927.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03437, over 972401.51 frames.], batch size: 18, lr: 2.37e-04
+2022-05-06 11:42:50,011 INFO [train.py:715] (3/8) Epoch 9, batch 12200, loss[loss=0.1105, simple_loss=0.1834, pruned_loss=0.01873, over 4771.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03406, over 971798.81 frames.], batch size: 14, lr: 2.37e-04
+2022-05-06 11:43:29,260 INFO [train.py:715] (3/8) Epoch 9, batch 12250, loss[loss=0.1386, simple_loss=0.2181, pruned_loss=0.02954, over 4906.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03441, over 971578.19 frames.], batch size: 17, lr: 2.37e-04
+2022-05-06 11:44:08,226 INFO [train.py:715] (3/8) Epoch 9, batch 12300, loss[loss=0.1516, simple_loss=0.2225, pruned_loss=0.04035, over 4935.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2137, pruned_loss=0.0349, over 971382.31 frames.], batch size: 18, lr: 2.37e-04
+2022-05-06 11:44:47,991 INFO [train.py:715] (3/8) Epoch 9, batch 12350, loss[loss=0.1298, simple_loss=0.1928, pruned_loss=0.03345, over 4802.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03478, over 971280.35 frames.], batch size: 13, lr: 2.37e-04
+2022-05-06 11:45:28,032 INFO [train.py:715] (3/8) Epoch 9, batch 12400, loss[loss=0.1561, simple_loss=0.2395, pruned_loss=0.03637, over 4937.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03411, over 971238.46 frames.], batch size: 29, lr: 2.37e-04
+2022-05-06 11:46:07,546 INFO [train.py:715] (3/8) Epoch 9, batch 12450, loss[loss=0.1403, simple_loss=0.215, pruned_loss=0.03285, over 4959.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03445, over 972076.91 frames.], batch size: 24, lr: 2.37e-04
+2022-05-06 11:46:47,600 INFO [train.py:715] (3/8) Epoch 9, batch 12500, loss[loss=0.1713, simple_loss=0.2394, pruned_loss=0.05158, over 4929.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.03485, over 971677.76 frames.], batch size: 29, lr: 2.37e-04
+2022-05-06 11:47:27,729 INFO [train.py:715] (3/8) Epoch 9, batch 12550, loss[loss=0.131, simple_loss=0.2063, pruned_loss=0.02783, over 4800.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2154, pruned_loss=0.03468, over 971027.44 frames.], batch size: 14, lr: 2.37e-04
+2022-05-06 11:48:07,690 INFO [train.py:715] (3/8) Epoch 9, batch 12600, loss[loss=0.1414, simple_loss=0.2134, pruned_loss=0.0347, over 4652.00 frames.], tot_loss[loss=0.142, simple_loss=0.215, pruned_loss=0.03444, over 971317.99 frames.], batch size: 13, lr: 2.37e-04
+2022-05-06 11:48:46,462 INFO [train.py:715] (3/8) Epoch 9, batch 12650, loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03459, over 4928.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2156, pruned_loss=0.03481, over 971354.58 frames.], batch size: 23, lr: 2.37e-04
+2022-05-06 11:49:26,598 INFO [train.py:715] (3/8) Epoch 9, batch 12700, loss[loss=0.1598, simple_loss=0.2335, pruned_loss=0.04307, over 4755.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2152, pruned_loss=0.03487, over 971335.68 frames.], batch size: 19, lr: 2.37e-04
+2022-05-06 11:50:06,591 INFO [train.py:715] (3/8) Epoch 9, batch 12750, loss[loss=0.1552, simple_loss=0.2256, pruned_loss=0.04242, over 4898.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03491, over 971933.20 frames.], batch size: 39, lr: 2.37e-04
+2022-05-06 11:50:45,760 INFO [train.py:715] (3/8) Epoch 9, batch 12800, loss[loss=0.1254, simple_loss=0.2066, pruned_loss=0.02208, over 4936.00 frames.], tot_loss[loss=0.142, simple_loss=0.2146, pruned_loss=0.03468, over 972242.06 frames.], batch size: 21, lr: 2.37e-04
+2022-05-06 11:51:25,603 INFO [train.py:715] (3/8) Epoch 9, batch 12850, loss[loss=0.1389, simple_loss=0.2143, pruned_loss=0.03173, over 4971.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.03502, over 972059.60 frames.], batch size: 15, lr: 2.37e-04
+2022-05-06 11:52:05,498 INFO [train.py:715] (3/8) Epoch 9, batch 12900, loss[loss=0.1287, simple_loss=0.1997, pruned_loss=0.02884, over 4964.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.035, over 972097.95 frames.], batch size: 15, lr: 2.37e-04
+2022-05-06 11:52:45,475 INFO [train.py:715] (3/8) Epoch 9, batch 12950, loss[loss=0.1466, simple_loss=0.2219, pruned_loss=0.03569, over 4756.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03439, over 972536.14 frames.], batch size: 16, lr: 2.37e-04
+2022-05-06 11:53:24,502 INFO [train.py:715] (3/8) Epoch 9, batch 13000, loss[loss=0.1105, simple_loss=0.1869, pruned_loss=0.01704, over 4993.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03423, over 972719.30 frames.], batch size: 26, lr: 2.37e-04
+2022-05-06 11:54:04,858 INFO [train.py:715] (3/8) Epoch 9, batch 13050, loss[loss=0.1075, simple_loss=0.1816, pruned_loss=0.01671, over 4952.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03435, over 972476.11 frames.], batch size: 24, lr: 2.37e-04
+2022-05-06 11:54:44,621 INFO [train.py:715] (3/8) Epoch 9, batch 13100, loss[loss=0.1407, simple_loss=0.213, pruned_loss=0.03417, over 4873.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.03412, over 971740.76 frames.], batch size: 39, lr: 2.37e-04
+2022-05-06 11:55:23,866 INFO [train.py:715] (3/8) Epoch 9, batch 13150, loss[loss=0.156, simple_loss=0.2213, pruned_loss=0.04537, over 4847.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.0343, over 972360.47 frames.], batch size: 15, lr: 2.37e-04
+2022-05-06 11:56:03,854 INFO [train.py:715] (3/8) Epoch 9, batch 13200, loss[loss=0.1467, simple_loss=0.2141, pruned_loss=0.03964, over 4786.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03477, over 972641.28 frames.], batch size: 17, lr: 2.37e-04
+2022-05-06 11:56:44,164 INFO [train.py:715] (3/8) Epoch 9, batch 13250, loss[loss=0.1252, simple_loss=0.1962, pruned_loss=0.02708, over 4866.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.0348, over 971998.45 frames.], batch size: 20, lr: 2.37e-04
+2022-05-06 11:57:23,741 INFO [train.py:715] (3/8) Epoch 9, batch 13300, loss[loss=0.1298, simple_loss=0.2034, pruned_loss=0.02811, over 4895.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2141, pruned_loss=0.03501, over 972611.68 frames.], batch size: 32, lr: 2.37e-04
+2022-05-06 11:58:03,444 INFO [train.py:715] (3/8) Epoch 9, batch 13350, loss[loss=0.1585, simple_loss=0.2402, pruned_loss=0.03836, over 4779.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03497, over 972578.39 frames.], batch size: 14, lr: 2.37e-04
+2022-05-06 11:58:43,525 INFO [train.py:715] (3/8) Epoch 9, batch 13400, loss[loss=0.1384, simple_loss=0.2104, pruned_loss=0.03326, over 4928.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.0347, over 973018.84 frames.], batch size: 29, lr: 2.37e-04
+2022-05-06 11:59:23,794 INFO [train.py:715] (3/8) Epoch 9, batch 13450, loss[loss=0.1483, simple_loss=0.2289, pruned_loss=0.03384, over 4864.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2146, pruned_loss=0.03502, over 973107.65 frames.], batch size: 20, lr: 2.36e-04
+2022-05-06 12:00:02,967 INFO [train.py:715] (3/8) Epoch 9, batch 13500, loss[loss=0.1318, simple_loss=0.1999, pruned_loss=0.0318, over 4843.00 frames.], tot_loss[loss=0.1416, simple_loss=0.214, pruned_loss=0.03459, over 973113.77 frames.], batch size: 30, lr: 2.36e-04
+2022-05-06 12:00:42,984 INFO [train.py:715] (3/8) Epoch 9, batch 13550, loss[loss=0.1406, simple_loss=0.2044, pruned_loss=0.03845, over 4904.00 frames.], tot_loss[loss=0.1424, simple_loss=0.215, pruned_loss=0.0349, over 972246.69 frames.], batch size: 22, lr: 2.36e-04
+2022-05-06 12:01:22,497 INFO [train.py:715] (3/8) Epoch 9, batch 13600, loss[loss=0.1396, simple_loss=0.2205, pruned_loss=0.02934, over 4813.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2143, pruned_loss=0.03424, over 971709.08 frames.], batch size: 25, lr: 2.36e-04
+2022-05-06 12:02:01,622 INFO [train.py:715] (3/8) Epoch 9, batch 13650, loss[loss=0.1096, simple_loss=0.1834, pruned_loss=0.01785, over 4758.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2139, pruned_loss=0.03397, over 970779.53 frames.], batch size: 12, lr: 2.36e-04
+2022-05-06 12:02:40,853 INFO [train.py:715] (3/8) Epoch 9, batch 13700, loss[loss=0.1402, simple_loss=0.2156, pruned_loss=0.03241, over 4794.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2148, pruned_loss=0.03431, over 971609.35 frames.], batch size: 17, lr: 2.36e-04
+2022-05-06 12:03:20,735 INFO [train.py:715] (3/8) Epoch 9, batch 13750, loss[loss=0.1284, simple_loss=0.1979, pruned_loss=0.02945, over 4876.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03488, over 970870.63 frames.], batch size: 16, lr: 2.36e-04
+2022-05-06 12:03:59,888 INFO [train.py:715] (3/8) Epoch 9, batch 13800, loss[loss=0.1259, simple_loss=0.1935, pruned_loss=0.02912, over 4839.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2159, pruned_loss=0.03524, over 970626.19 frames.], batch size: 27, lr: 2.36e-04
+2022-05-06 12:04:38,388 INFO [train.py:715] (3/8) Epoch 9, batch 13850, loss[loss=0.129, simple_loss=0.2053, pruned_loss=0.0264, over 4796.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2168, pruned_loss=0.03602, over 970884.69 frames.], batch size: 24, lr: 2.36e-04
+2022-05-06 12:05:17,813 INFO [train.py:715] (3/8) Epoch 9, batch 13900, loss[loss=0.1339, simple_loss=0.2075, pruned_loss=0.03013, over 4953.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2159, pruned_loss=0.03526, over 971785.20 frames.], batch size: 39, lr: 2.36e-04
+2022-05-06 12:05:57,958 INFO [train.py:715] (3/8) Epoch 9, batch 13950, loss[loss=0.1551, simple_loss=0.2288, pruned_loss=0.04073, over 4853.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2161, pruned_loss=0.03507, over 971907.55 frames.], batch size: 39, lr: 2.36e-04
+2022-05-06 12:06:36,916 INFO [train.py:715] (3/8) Epoch 9, batch 14000, loss[loss=0.1401, simple_loss=0.212, pruned_loss=0.03412, over 4786.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2165, pruned_loss=0.03515, over 972800.95 frames.], batch size: 17, lr: 2.36e-04
+2022-05-06 12:07:16,027 INFO [train.py:715] (3/8) Epoch 9, batch 14050, loss[loss=0.1747, simple_loss=0.2402, pruned_loss=0.05461, over 4961.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2164, pruned_loss=0.03523, over 973081.98 frames.], batch size: 15, lr: 2.36e-04
+2022-05-06 12:07:55,564 INFO [train.py:715] (3/8) Epoch 9, batch 14100, loss[loss=0.1469, simple_loss=0.2009, pruned_loss=0.04645, over 4797.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2161, pruned_loss=0.03533, over 973274.90 frames.], batch size: 17, lr: 2.36e-04
+2022-05-06 12:08:35,132 INFO [train.py:715] (3/8) Epoch 9, batch 14150, loss[loss=0.1393, simple_loss=0.2175, pruned_loss=0.03059, over 4939.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2159, pruned_loss=0.03568, over 973050.04 frames.], batch size: 29, lr: 2.36e-04
+2022-05-06 12:09:14,476 INFO [train.py:715] (3/8) Epoch 9, batch 14200, loss[loss=0.1768, simple_loss=0.251, pruned_loss=0.05126, over 4915.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2166, pruned_loss=0.03558, over 973010.67 frames.], batch size: 17, lr: 2.36e-04
+2022-05-06 12:09:53,802 INFO [train.py:715] (3/8) Epoch 9, batch 14250, loss[loss=0.1205, simple_loss=0.2024, pruned_loss=0.01929, over 4739.00 frames.], tot_loss[loss=0.1433, simple_loss=0.216, pruned_loss=0.03528, over 973463.38 frames.], batch size: 12, lr: 2.36e-04
+2022-05-06 12:10:33,297 INFO [train.py:715] (3/8) Epoch 9, batch 14300, loss[loss=0.1512, simple_loss=0.2176, pruned_loss=0.04246, over 4988.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03552, over 973144.31 frames.], batch size: 33, lr: 2.36e-04
+2022-05-06 12:11:11,975 INFO [train.py:715] (3/8) Epoch 9, batch 14350, loss[loss=0.1391, simple_loss=0.2175, pruned_loss=0.03033, over 4977.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.03518, over 972513.55 frames.], batch size: 25, lr: 2.36e-04
+2022-05-06 12:11:50,598 INFO [train.py:715] (3/8) Epoch 9, batch 14400, loss[loss=0.1517, simple_loss=0.2339, pruned_loss=0.03473, over 4933.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03534, over 973510.48 frames.], batch size: 29, lr: 2.36e-04
+2022-05-06 12:12:30,354 INFO [train.py:715] (3/8) Epoch 9, batch 14450, loss[loss=0.1313, simple_loss=0.2011, pruned_loss=0.03072, over 4829.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2162, pruned_loss=0.03525, over 973037.15 frames.], batch size: 30, lr: 2.36e-04
+2022-05-06 12:13:09,689 INFO [train.py:715] (3/8) Epoch 9, batch 14500, loss[loss=0.1562, simple_loss=0.226, pruned_loss=0.04315, over 4885.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2161, pruned_loss=0.03532, over 973126.03 frames.], batch size: 22, lr: 2.36e-04
+2022-05-06 12:13:48,636 INFO [train.py:715] (3/8) Epoch 9, batch 14550, loss[loss=0.1405, simple_loss=0.2054, pruned_loss=0.03777, over 4856.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2162, pruned_loss=0.03544, over 972668.60 frames.], batch size: 20, lr: 2.36e-04
+2022-05-06 12:14:27,683 INFO [train.py:715] (3/8) Epoch 9, batch 14600, loss[loss=0.1618, simple_loss=0.2332, pruned_loss=0.04518, over 4927.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03575, over 972467.49 frames.], batch size: 23, lr: 2.36e-04
+2022-05-06 12:15:07,387 INFO [train.py:715] (3/8) Epoch 9, batch 14650, loss[loss=0.1372, simple_loss=0.2023, pruned_loss=0.03601, over 4951.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2153, pruned_loss=0.03521, over 971871.44 frames.], batch size: 14, lr: 2.36e-04
+2022-05-06 12:15:45,916 INFO [train.py:715] (3/8) Epoch 9, batch 14700, loss[loss=0.1526, simple_loss=0.2226, pruned_loss=0.04129, over 4831.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.0351, over 971358.77 frames.], batch size: 30, lr: 2.36e-04
+2022-05-06 12:16:27,519 INFO [train.py:715] (3/8) Epoch 9, batch 14750, loss[loss=0.1262, simple_loss=0.2073, pruned_loss=0.02256, over 4821.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2146, pruned_loss=0.03521, over 971380.02 frames.], batch size: 25, lr: 2.36e-04
+2022-05-06 12:17:06,569 INFO [train.py:715] (3/8) Epoch 9, batch 14800, loss[loss=0.135, simple_loss=0.2099, pruned_loss=0.03006, over 4927.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2154, pruned_loss=0.03556, over 971137.25 frames.], batch size: 23, lr: 2.36e-04
+2022-05-06 12:17:45,497 INFO [train.py:715] (3/8) Epoch 9, batch 14850, loss[loss=0.1488, simple_loss=0.2226, pruned_loss=0.03749, over 4880.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.0355, over 971533.60 frames.], batch size: 22, lr: 2.36e-04
+2022-05-06 12:18:24,548 INFO [train.py:715] (3/8) Epoch 9, batch 14900, loss[loss=0.1252, simple_loss=0.2055, pruned_loss=0.02247, over 4975.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2162, pruned_loss=0.03561, over 971913.29 frames.], batch size: 28, lr: 2.36e-04
+2022-05-06 12:19:03,081 INFO [train.py:715] (3/8) Epoch 9, batch 14950, loss[loss=0.1267, simple_loss=0.1961, pruned_loss=0.02867, over 4862.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03593, over 971683.74 frames.], batch size: 20, lr: 2.36e-04
+2022-05-06 12:19:42,681 INFO [train.py:715] (3/8) Epoch 9, batch 15000, loss[loss=0.199, simple_loss=0.2604, pruned_loss=0.06879, over 4825.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2158, pruned_loss=0.03573, over 971829.58 frames.], batch size: 13, lr: 2.36e-04
+2022-05-06 12:19:42,682 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 12:19:52,344 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.1071, simple_loss=0.1915, pruned_loss=0.01139, over 914524.00 frames.
+2022-05-06 12:20:32,095 INFO [train.py:715] (3/8) Epoch 9, batch 15050, loss[loss=0.1289, simple_loss=0.2081, pruned_loss=0.02488, over 4792.00 frames.], tot_loss[loss=0.1427, simple_loss=0.215, pruned_loss=0.03518, over 972212.42 frames.], batch size: 14, lr: 2.36e-04
+2022-05-06 12:21:11,097 INFO [train.py:715] (3/8) Epoch 9, batch 15100, loss[loss=0.185, simple_loss=0.2659, pruned_loss=0.05209, over 4792.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.03502, over 971812.57 frames.], batch size: 18, lr: 2.36e-04
+2022-05-06 12:21:50,198 INFO [train.py:715] (3/8) Epoch 9, batch 15150, loss[loss=0.129, simple_loss=0.2044, pruned_loss=0.02679, over 4840.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03461, over 971260.01 frames.], batch size: 15, lr: 2.36e-04
+2022-05-06 12:22:30,011 INFO [train.py:715] (3/8) Epoch 9, batch 15200, loss[loss=0.1526, simple_loss=0.2281, pruned_loss=0.0385, over 4892.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03444, over 971230.15 frames.], batch size: 17, lr: 2.36e-04
+2022-05-06 12:23:09,319 INFO [train.py:715] (3/8) Epoch 9, batch 15250, loss[loss=0.1595, simple_loss=0.2209, pruned_loss=0.049, over 4930.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03557, over 971611.94 frames.], batch size: 35, lr: 2.36e-04
+2022-05-06 12:23:48,031 INFO [train.py:715] (3/8) Epoch 9, batch 15300, loss[loss=0.1359, simple_loss=0.2073, pruned_loss=0.03224, over 4846.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03525, over 970474.92 frames.], batch size: 32, lr: 2.36e-04
+2022-05-06 12:24:27,150 INFO [train.py:715] (3/8) Epoch 9, batch 15350, loss[loss=0.1487, simple_loss=0.216, pruned_loss=0.04072, over 4959.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2158, pruned_loss=0.03575, over 971264.87 frames.], batch size: 35, lr: 2.36e-04
+2022-05-06 12:25:06,183 INFO [train.py:715] (3/8) Epoch 9, batch 15400, loss[loss=0.1257, simple_loss=0.195, pruned_loss=0.02818, over 4663.00 frames.], tot_loss[loss=0.144, simple_loss=0.2158, pruned_loss=0.03612, over 971113.34 frames.], batch size: 14, lr: 2.36e-04
+2022-05-06 12:25:44,958 INFO [train.py:715] (3/8) Epoch 9, batch 15450, loss[loss=0.1949, simple_loss=0.2539, pruned_loss=0.06793, over 4799.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2163, pruned_loss=0.03627, over 971735.40 frames.], batch size: 17, lr: 2.36e-04
+2022-05-06 12:26:23,388 INFO [train.py:715] (3/8) Epoch 9, batch 15500, loss[loss=0.1126, simple_loss=0.1924, pruned_loss=0.01646, over 4905.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.03658, over 972852.73 frames.], batch size: 18, lr: 2.36e-04
+2022-05-06 12:27:03,113 INFO [train.py:715] (3/8) Epoch 9, batch 15550, loss[loss=0.1533, simple_loss=0.2179, pruned_loss=0.04436, over 4771.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2163, pruned_loss=0.03626, over 973161.88 frames.], batch size: 18, lr: 2.36e-04
+2022-05-06 12:27:41,874 INFO [train.py:715] (3/8) Epoch 9, batch 15600, loss[loss=0.1628, simple_loss=0.2289, pruned_loss=0.04838, over 4951.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2157, pruned_loss=0.03607, over 972783.61 frames.], batch size: 21, lr: 2.36e-04
+2022-05-06 12:28:20,223 INFO [train.py:715] (3/8) Epoch 9, batch 15650, loss[loss=0.1255, simple_loss=0.21, pruned_loss=0.02046, over 4814.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2142, pruned_loss=0.03508, over 972618.38 frames.], batch size: 27, lr: 2.36e-04
+2022-05-06 12:28:59,316 INFO [train.py:715] (3/8) Epoch 9, batch 15700, loss[loss=0.1206, simple_loss=0.2004, pruned_loss=0.02038, over 4754.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2147, pruned_loss=0.03551, over 972232.29 frames.], batch size: 16, lr: 2.36e-04
+2022-05-06 12:29:39,074 INFO [train.py:715] (3/8) Epoch 9, batch 15750, loss[loss=0.143, simple_loss=0.2157, pruned_loss=0.03513, over 4966.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2143, pruned_loss=0.0355, over 973486.40 frames.], batch size: 21, lr: 2.36e-04
+2022-05-06 12:30:17,865 INFO [train.py:715] (3/8) Epoch 9, batch 15800, loss[loss=0.1405, simple_loss=0.2076, pruned_loss=0.03676, over 4828.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2153, pruned_loss=0.03555, over 972455.81 frames.], batch size: 13, lr: 2.36e-04
+2022-05-06 12:30:56,797 INFO [train.py:715] (3/8) Epoch 9, batch 15850, loss[loss=0.1504, simple_loss=0.2135, pruned_loss=0.04368, over 4836.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2152, pruned_loss=0.03565, over 972424.14 frames.], batch size: 30, lr: 2.36e-04
+2022-05-06 12:31:36,399 INFO [train.py:715] (3/8) Epoch 9, batch 15900, loss[loss=0.2525, simple_loss=0.3012, pruned_loss=0.1019, over 4867.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03553, over 971756.92 frames.], batch size: 16, lr: 2.36e-04
+2022-05-06 12:32:15,974 INFO [train.py:715] (3/8) Epoch 9, batch 15950, loss[loss=0.1651, simple_loss=0.2267, pruned_loss=0.05173, over 4943.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03559, over 971279.16 frames.], batch size: 35, lr: 2.36e-04
+2022-05-06 12:32:54,619 INFO [train.py:715] (3/8) Epoch 9, batch 16000, loss[loss=0.1453, simple_loss=0.2244, pruned_loss=0.03308, over 4844.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.03532, over 971261.91 frames.], batch size: 15, lr: 2.36e-04
+2022-05-06 12:33:33,297 INFO [train.py:715] (3/8) Epoch 9, batch 16050, loss[loss=0.1571, simple_loss=0.2244, pruned_loss=0.04491, over 4926.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03573, over 971634.99 frames.], batch size: 21, lr: 2.36e-04
+2022-05-06 12:34:12,506 INFO [train.py:715] (3/8) Epoch 9, batch 16100, loss[loss=0.1195, simple_loss=0.1935, pruned_loss=0.02274, over 4962.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2162, pruned_loss=0.03602, over 971831.65 frames.], batch size: 15, lr: 2.36e-04
+2022-05-06 12:34:51,594 INFO [train.py:715] (3/8) Epoch 9, batch 16150, loss[loss=0.1593, simple_loss=0.224, pruned_loss=0.04732, over 4975.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03603, over 971907.09 frames.], batch size: 24, lr: 2.36e-04
+2022-05-06 12:35:30,772 INFO [train.py:715] (3/8) Epoch 9, batch 16200, loss[loss=0.1611, simple_loss=0.2364, pruned_loss=0.04289, over 4832.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2155, pruned_loss=0.03539, over 971538.94 frames.], batch size: 30, lr: 2.36e-04
+2022-05-06 12:36:10,111 INFO [train.py:715] (3/8) Epoch 9, batch 16250, loss[loss=0.1791, simple_loss=0.2433, pruned_loss=0.05739, over 4862.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2163, pruned_loss=0.03549, over 971246.49 frames.], batch size: 20, lr: 2.35e-04
+2022-05-06 12:36:49,785 INFO [train.py:715] (3/8) Epoch 9, batch 16300, loss[loss=0.1389, simple_loss=0.2029, pruned_loss=0.03751, over 4988.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03554, over 972167.18 frames.], batch size: 14, lr: 2.35e-04
+2022-05-06 12:37:27,730 INFO [train.py:715] (3/8) Epoch 9, batch 16350, loss[loss=0.17, simple_loss=0.2511, pruned_loss=0.04447, over 4914.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2152, pruned_loss=0.03474, over 972066.54 frames.], batch size: 18, lr: 2.35e-04
+2022-05-06 12:38:07,161 INFO [train.py:715] (3/8) Epoch 9, batch 16400, loss[loss=0.1301, simple_loss=0.2135, pruned_loss=0.02336, over 4823.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2148, pruned_loss=0.03449, over 971162.83 frames.], batch size: 26, lr: 2.35e-04
+2022-05-06 12:38:47,057 INFO [train.py:715] (3/8) Epoch 9, batch 16450, loss[loss=0.1423, simple_loss=0.2213, pruned_loss=0.0317, over 4978.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2148, pruned_loss=0.03407, over 972380.50 frames.], batch size: 35, lr: 2.35e-04
+2022-05-06 12:39:25,806 INFO [train.py:715] (3/8) Epoch 9, batch 16500, loss[loss=0.1277, simple_loss=0.1997, pruned_loss=0.02783, over 4849.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2145, pruned_loss=0.0341, over 971925.66 frames.], batch size: 13, lr: 2.35e-04
+2022-05-06 12:40:04,404 INFO [train.py:715] (3/8) Epoch 9, batch 16550, loss[loss=0.1352, simple_loss=0.2019, pruned_loss=0.03427, over 4906.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03413, over 972242.31 frames.], batch size: 17, lr: 2.35e-04
+2022-05-06 12:40:43,848 INFO [train.py:715] (3/8) Epoch 9, batch 16600, loss[loss=0.1439, simple_loss=0.2265, pruned_loss=0.03058, over 4905.00 frames.], tot_loss[loss=0.141, simple_loss=0.2143, pruned_loss=0.03386, over 972476.07 frames.], batch size: 19, lr: 2.35e-04
+2022-05-06 12:41:23,435 INFO [train.py:715] (3/8) Epoch 9, batch 16650, loss[loss=0.1496, simple_loss=0.2164, pruned_loss=0.0414, over 4923.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2139, pruned_loss=0.03374, over 973264.18 frames.], batch size: 18, lr: 2.35e-04
+2022-05-06 12:42:02,350 INFO [train.py:715] (3/8) Epoch 9, batch 16700, loss[loss=0.1523, simple_loss=0.2185, pruned_loss=0.04312, over 4911.00 frames.], tot_loss[loss=0.1421, simple_loss=0.215, pruned_loss=0.03457, over 973747.93 frames.], batch size: 19, lr: 2.35e-04
+2022-05-06 12:42:41,615 INFO [train.py:715] (3/8) Epoch 9, batch 16750, loss[loss=0.1048, simple_loss=0.1863, pruned_loss=0.01158, over 4792.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.03469, over 972765.24 frames.], batch size: 12, lr: 2.35e-04
+2022-05-06 12:43:21,409 INFO [train.py:715] (3/8) Epoch 9, batch 16800, loss[loss=0.1408, simple_loss=0.2147, pruned_loss=0.03343, over 4749.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03445, over 972024.97 frames.], batch size: 16, lr: 2.35e-04
+2022-05-06 12:44:01,037 INFO [train.py:715] (3/8) Epoch 9, batch 16850, loss[loss=0.1868, simple_loss=0.2477, pruned_loss=0.06292, over 4812.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2134, pruned_loss=0.03436, over 972432.46 frames.], batch size: 15, lr: 2.35e-04
+2022-05-06 12:44:40,454 INFO [train.py:715] (3/8) Epoch 9, batch 16900, loss[loss=0.1588, simple_loss=0.2158, pruned_loss=0.05088, over 4826.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.03504, over 972374.90 frames.], batch size: 15, lr: 2.35e-04
+2022-05-06 12:45:20,534 INFO [train.py:715] (3/8) Epoch 9, batch 16950, loss[loss=0.1144, simple_loss=0.1843, pruned_loss=0.02229, over 4784.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03513, over 972645.80 frames.], batch size: 12, lr: 2.35e-04
+2022-05-06 12:46:00,236 INFO [train.py:715] (3/8) Epoch 9, batch 17000, loss[loss=0.1311, simple_loss=0.2132, pruned_loss=0.02447, over 4956.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03518, over 972909.45 frames.], batch size: 24, lr: 2.35e-04
+2022-05-06 12:46:38,807 INFO [train.py:715] (3/8) Epoch 9, batch 17050, loss[loss=0.1343, simple_loss=0.1995, pruned_loss=0.0345, over 4770.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03482, over 972585.59 frames.], batch size: 14, lr: 2.35e-04
+2022-05-06 12:47:18,390 INFO [train.py:715] (3/8) Epoch 9, batch 17100, loss[loss=0.1501, simple_loss=0.2151, pruned_loss=0.04251, over 4781.00 frames.], tot_loss[loss=0.1416, simple_loss=0.214, pruned_loss=0.03463, over 972246.14 frames.], batch size: 18, lr: 2.35e-04
+2022-05-06 12:47:58,063 INFO [train.py:715] (3/8) Epoch 9, batch 17150, loss[loss=0.171, simple_loss=0.2404, pruned_loss=0.05082, over 4785.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.0347, over 972813.51 frames.], batch size: 17, lr: 2.35e-04
+2022-05-06 12:48:37,322 INFO [train.py:715] (3/8) Epoch 9, batch 17200, loss[loss=0.1425, simple_loss=0.2238, pruned_loss=0.03062, over 4887.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2141, pruned_loss=0.03472, over 972816.72 frames.], batch size: 19, lr: 2.35e-04
+2022-05-06 12:49:15,992 INFO [train.py:715] (3/8) Epoch 9, batch 17250, loss[loss=0.1372, simple_loss=0.2222, pruned_loss=0.02606, over 4929.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03461, over 972394.31 frames.], batch size: 29, lr: 2.35e-04
+2022-05-06 12:49:54,886 INFO [train.py:715] (3/8) Epoch 9, batch 17300, loss[loss=0.1386, simple_loss=0.2078, pruned_loss=0.03469, over 4771.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03472, over 972263.48 frames.], batch size: 14, lr: 2.35e-04
+2022-05-06 12:50:33,971 INFO [train.py:715] (3/8) Epoch 9, batch 17350, loss[loss=0.172, simple_loss=0.2385, pruned_loss=0.05269, over 4862.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03512, over 971989.44 frames.], batch size: 32, lr: 2.35e-04
+2022-05-06 12:51:13,080 INFO [train.py:715] (3/8) Epoch 9, batch 17400, loss[loss=0.1499, simple_loss=0.2275, pruned_loss=0.03612, over 4805.00 frames.], tot_loss[loss=0.142, simple_loss=0.2144, pruned_loss=0.03487, over 971848.94 frames.], batch size: 21, lr: 2.35e-04
+2022-05-06 12:51:52,390 INFO [train.py:715] (3/8) Epoch 9, batch 17450, loss[loss=0.1381, simple_loss=0.2024, pruned_loss=0.03685, over 4898.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03438, over 972232.46 frames.], batch size: 19, lr: 2.35e-04
+2022-05-06 12:52:31,602 INFO [train.py:715] (3/8) Epoch 9, batch 17500, loss[loss=0.1327, simple_loss=0.2115, pruned_loss=0.02698, over 4973.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2133, pruned_loss=0.03448, over 972796.23 frames.], batch size: 24, lr: 2.35e-04
+2022-05-06 12:53:10,814 INFO [train.py:715] (3/8) Epoch 9, batch 17550, loss[loss=0.1506, simple_loss=0.2156, pruned_loss=0.0428, over 4821.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2134, pruned_loss=0.03439, over 972894.54 frames.], batch size: 26, lr: 2.35e-04
+2022-05-06 12:53:49,891 INFO [train.py:715] (3/8) Epoch 9, batch 17600, loss[loss=0.1378, simple_loss=0.2127, pruned_loss=0.03142, over 4846.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2131, pruned_loss=0.0342, over 972915.44 frames.], batch size: 30, lr: 2.35e-04
+2022-05-06 12:54:29,583 INFO [train.py:715] (3/8) Epoch 9, batch 17650, loss[loss=0.1313, simple_loss=0.1955, pruned_loss=0.03359, over 4988.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03406, over 972891.01 frames.], batch size: 14, lr: 2.35e-04
+2022-05-06 12:55:08,478 INFO [train.py:715] (3/8) Epoch 9, batch 17700, loss[loss=0.1315, simple_loss=0.2123, pruned_loss=0.02535, over 4786.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.03371, over 972532.00 frames.], batch size: 17, lr: 2.35e-04
+2022-05-06 12:55:47,744 INFO [train.py:715] (3/8) Epoch 9, batch 17750, loss[loss=0.1576, simple_loss=0.2272, pruned_loss=0.04405, over 4794.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2126, pruned_loss=0.03381, over 972743.88 frames.], batch size: 17, lr: 2.35e-04
+2022-05-06 12:56:27,546 INFO [train.py:715] (3/8) Epoch 9, batch 17800, loss[loss=0.1128, simple_loss=0.1789, pruned_loss=0.02333, over 4889.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2127, pruned_loss=0.03374, over 973538.69 frames.], batch size: 19, lr: 2.35e-04
+2022-05-06 12:57:06,526 INFO [train.py:715] (3/8) Epoch 9, batch 17850, loss[loss=0.1648, simple_loss=0.2249, pruned_loss=0.0523, over 4696.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03396, over 973573.49 frames.], batch size: 15, lr: 2.35e-04
+2022-05-06 12:57:45,750 INFO [train.py:715] (3/8) Epoch 9, batch 17900, loss[loss=0.1567, simple_loss=0.2345, pruned_loss=0.03946, over 4924.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03461, over 974106.38 frames.], batch size: 23, lr: 2.35e-04
+2022-05-06 12:58:25,609 INFO [train.py:715] (3/8) Epoch 9, batch 17950, loss[loss=0.1195, simple_loss=0.1992, pruned_loss=0.01993, over 4770.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03465, over 973427.49 frames.], batch size: 17, lr: 2.35e-04
+2022-05-06 12:59:04,972 INFO [train.py:715] (3/8) Epoch 9, batch 18000, loss[loss=0.1171, simple_loss=0.2, pruned_loss=0.01713, over 4898.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2135, pruned_loss=0.03451, over 974063.20 frames.], batch size: 17, lr: 2.35e-04
+2022-05-06 12:59:04,973 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 12:59:14,501 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1912, pruned_loss=0.01121, over 914524.00 frames.
+2022-05-06 12:59:53,955 INFO [train.py:715] (3/8) Epoch 9, batch 18050, loss[loss=0.1453, simple_loss=0.2214, pruned_loss=0.0346, over 4923.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.03438, over 973603.31 frames.], batch size: 18, lr: 2.35e-04
+2022-05-06 13:00:33,773 INFO [train.py:715] (3/8) Epoch 9, batch 18100, loss[loss=0.1413, simple_loss=0.2162, pruned_loss=0.03314, over 4857.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03408, over 973783.24 frames.], batch size: 13, lr: 2.35e-04
+2022-05-06 13:01:13,064 INFO [train.py:715] (3/8) Epoch 9, batch 18150, loss[loss=0.1301, simple_loss=0.2041, pruned_loss=0.02803, over 4805.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2132, pruned_loss=0.03428, over 973813.94 frames.], batch size: 25, lr: 2.35e-04
+2022-05-06 13:01:52,673 INFO [train.py:715] (3/8) Epoch 9, batch 18200, loss[loss=0.1453, simple_loss=0.2294, pruned_loss=0.0306, over 4778.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2132, pruned_loss=0.03414, over 973705.35 frames.], batch size: 18, lr: 2.35e-04
+2022-05-06 13:02:31,901 INFO [train.py:715] (3/8) Epoch 9, batch 18250, loss[loss=0.1549, simple_loss=0.2267, pruned_loss=0.04159, over 4984.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03423, over 972206.02 frames.], batch size: 14, lr: 2.35e-04
+2022-05-06 13:03:11,075 INFO [train.py:715] (3/8) Epoch 9, batch 18300, loss[loss=0.1323, simple_loss=0.2099, pruned_loss=0.02729, over 4901.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03377, over 972469.16 frames.], batch size: 19, lr: 2.35e-04
+2022-05-06 13:03:50,428 INFO [train.py:715] (3/8) Epoch 9, batch 18350, loss[loss=0.1344, simple_loss=0.216, pruned_loss=0.02642, over 4824.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2122, pruned_loss=0.03348, over 971374.80 frames.], batch size: 13, lr: 2.35e-04
+2022-05-06 13:04:29,595 INFO [train.py:715] (3/8) Epoch 9, batch 18400, loss[loss=0.1409, simple_loss=0.199, pruned_loss=0.04134, over 4789.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03416, over 973072.68 frames.], batch size: 14, lr: 2.35e-04
+2022-05-06 13:05:08,638 INFO [train.py:715] (3/8) Epoch 9, batch 18450, loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.0351, over 4784.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03411, over 972552.76 frames.], batch size: 18, lr: 2.35e-04
+2022-05-06 13:05:47,601 INFO [train.py:715] (3/8) Epoch 9, batch 18500, loss[loss=0.1315, simple_loss=0.2094, pruned_loss=0.0268, over 4883.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2136, pruned_loss=0.03401, over 972698.47 frames.], batch size: 39, lr: 2.35e-04
+2022-05-06 13:06:26,996 INFO [train.py:715] (3/8) Epoch 9, batch 18550, loss[loss=0.1278, simple_loss=0.1919, pruned_loss=0.03182, over 4864.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03363, over 973073.05 frames.], batch size: 20, lr: 2.35e-04
+2022-05-06 13:07:06,066 INFO [train.py:715] (3/8) Epoch 9, batch 18600, loss[loss=0.1277, simple_loss=0.2045, pruned_loss=0.02548, over 4743.00 frames.], tot_loss[loss=0.14, simple_loss=0.2132, pruned_loss=0.03346, over 972586.91 frames.], batch size: 19, lr: 2.35e-04
+2022-05-06 13:07:44,917 INFO [train.py:715] (3/8) Epoch 9, batch 18650, loss[loss=0.1465, simple_loss=0.2183, pruned_loss=0.03733, over 4913.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03348, over 972676.22 frames.], batch size: 17, lr: 2.35e-04
+2022-05-06 13:08:24,472 INFO [train.py:715] (3/8) Epoch 9, batch 18700, loss[loss=0.1459, simple_loss=0.2235, pruned_loss=0.03411, over 4955.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2146, pruned_loss=0.03405, over 972607.30 frames.], batch size: 24, lr: 2.35e-04
+2022-05-06 13:09:03,185 INFO [train.py:715] (3/8) Epoch 9, batch 18750, loss[loss=0.1255, simple_loss=0.1913, pruned_loss=0.02989, over 4865.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.03367, over 972791.39 frames.], batch size: 30, lr: 2.35e-04
+2022-05-06 13:09:42,756 INFO [train.py:715] (3/8) Epoch 9, batch 18800, loss[loss=0.1277, simple_loss=0.1966, pruned_loss=0.02938, over 4807.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03321, over 973277.98 frames.], batch size: 26, lr: 2.35e-04
+2022-05-06 13:10:21,586 INFO [train.py:715] (3/8) Epoch 9, batch 18850, loss[loss=0.1356, simple_loss=0.1978, pruned_loss=0.03669, over 4767.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.03347, over 974117.75 frames.], batch size: 14, lr: 2.35e-04
+2022-05-06 13:11:00,817 INFO [train.py:715] (3/8) Epoch 9, batch 18900, loss[loss=0.1454, simple_loss=0.2142, pruned_loss=0.0383, over 4795.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2141, pruned_loss=0.03385, over 973596.73 frames.], batch size: 17, lr: 2.35e-04
+2022-05-06 13:11:40,160 INFO [train.py:715] (3/8) Epoch 9, batch 18950, loss[loss=0.1316, simple_loss=0.2047, pruned_loss=0.02923, over 4849.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2144, pruned_loss=0.03373, over 973067.69 frames.], batch size: 13, lr: 2.35e-04
+2022-05-06 13:12:18,867 INFO [train.py:715] (3/8) Epoch 9, batch 19000, loss[loss=0.1359, simple_loss=0.2071, pruned_loss=0.03237, over 4976.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2144, pruned_loss=0.03393, over 972662.41 frames.], batch size: 15, lr: 2.35e-04
+2022-05-06 13:12:58,959 INFO [train.py:715] (3/8) Epoch 9, batch 19050, loss[loss=0.1357, simple_loss=0.2118, pruned_loss=0.02981, over 4986.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03423, over 972474.13 frames.], batch size: 26, lr: 2.34e-04
+2022-05-06 13:13:38,428 INFO [train.py:715] (3/8) Epoch 9, batch 19100, loss[loss=0.1354, simple_loss=0.2009, pruned_loss=0.03499, over 4773.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03414, over 973527.08 frames.], batch size: 12, lr: 2.34e-04
+2022-05-06 13:14:17,257 INFO [train.py:715] (3/8) Epoch 9, batch 19150, loss[loss=0.131, simple_loss=0.1967, pruned_loss=0.03261, over 4978.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03408, over 973090.12 frames.], batch size: 14, lr: 2.34e-04
+2022-05-06 13:14:57,088 INFO [train.py:715] (3/8) Epoch 9, batch 19200, loss[loss=0.1211, simple_loss=0.1953, pruned_loss=0.02347, over 4691.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03409, over 972669.24 frames.], batch size: 15, lr: 2.34e-04
+2022-05-06 13:15:36,591 INFO [train.py:715] (3/8) Epoch 9, batch 19250, loss[loss=0.1635, simple_loss=0.2281, pruned_loss=0.04943, over 4818.00 frames.], tot_loss[loss=0.141, simple_loss=0.2131, pruned_loss=0.03439, over 972775.31 frames.], batch size: 13, lr: 2.34e-04
+2022-05-06 13:16:15,484 INFO [train.py:715] (3/8) Epoch 9, batch 19300, loss[loss=0.112, simple_loss=0.1866, pruned_loss=0.01868, over 4758.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2142, pruned_loss=0.03508, over 972015.91 frames.], batch size: 18, lr: 2.34e-04
+2022-05-06 13:16:54,062 INFO [train.py:715] (3/8) Epoch 9, batch 19350, loss[loss=0.1541, simple_loss=0.2297, pruned_loss=0.03929, over 4770.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03484, over 971569.91 frames.], batch size: 14, lr: 2.34e-04
+2022-05-06 13:17:34,089 INFO [train.py:715] (3/8) Epoch 9, batch 19400, loss[loss=0.1565, simple_loss=0.2237, pruned_loss=0.04461, over 4889.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03505, over 971976.74 frames.], batch size: 16, lr: 2.34e-04
+2022-05-06 13:18:13,120 INFO [train.py:715] (3/8) Epoch 9, batch 19450, loss[loss=0.1621, simple_loss=0.2336, pruned_loss=0.04525, over 4885.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.03515, over 972403.55 frames.], batch size: 22, lr: 2.34e-04
+2022-05-06 13:18:51,812 INFO [train.py:715] (3/8) Epoch 9, batch 19500, loss[loss=0.1424, simple_loss=0.2193, pruned_loss=0.03269, over 4935.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2154, pruned_loss=0.0349, over 972667.42 frames.], batch size: 23, lr: 2.34e-04
+2022-05-06 13:19:30,940 INFO [train.py:715] (3/8) Epoch 9, batch 19550, loss[loss=0.1357, simple_loss=0.2117, pruned_loss=0.02987, over 4874.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.03523, over 972693.96 frames.], batch size: 16, lr: 2.34e-04
+2022-05-06 13:20:10,203 INFO [train.py:715] (3/8) Epoch 9, batch 19600, loss[loss=0.1219, simple_loss=0.1992, pruned_loss=0.02235, over 4807.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.0355, over 973477.91 frames.], batch size: 21, lr: 2.34e-04
+2022-05-06 13:20:48,782 INFO [train.py:715] (3/8) Epoch 9, batch 19650, loss[loss=0.151, simple_loss=0.21, pruned_loss=0.04599, over 4966.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2163, pruned_loss=0.0356, over 973714.93 frames.], batch size: 35, lr: 2.34e-04
+2022-05-06 13:21:27,270 INFO [train.py:715] (3/8) Epoch 9, batch 19700, loss[loss=0.1493, simple_loss=0.22, pruned_loss=0.0393, over 4770.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03505, over 972954.48 frames.], batch size: 14, lr: 2.34e-04
+2022-05-06 13:22:07,184 INFO [train.py:715] (3/8) Epoch 9, batch 19750, loss[loss=0.1282, simple_loss=0.2024, pruned_loss=0.02695, over 4693.00 frames.], tot_loss[loss=0.142, simple_loss=0.2149, pruned_loss=0.0346, over 973270.31 frames.], batch size: 15, lr: 2.34e-04
+2022-05-06 13:22:46,851 INFO [train.py:715] (3/8) Epoch 9, batch 19800, loss[loss=0.1421, simple_loss=0.2129, pruned_loss=0.03567, over 4845.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03468, over 973000.09 frames.], batch size: 15, lr: 2.34e-04
+2022-05-06 13:23:26,647 INFO [train.py:715] (3/8) Epoch 9, batch 19850, loss[loss=0.1384, simple_loss=0.2082, pruned_loss=0.03434, over 4979.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2148, pruned_loss=0.03453, over 972674.88 frames.], batch size: 35, lr: 2.34e-04
+2022-05-06 13:24:06,289 INFO [train.py:715] (3/8) Epoch 9, batch 19900, loss[loss=0.1611, simple_loss=0.2376, pruned_loss=0.04226, over 4872.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2142, pruned_loss=0.03424, over 972628.33 frames.], batch size: 16, lr: 2.34e-04
+2022-05-06 13:24:45,454 INFO [train.py:715] (3/8) Epoch 9, batch 19950, loss[loss=0.1547, simple_loss=0.2172, pruned_loss=0.04614, over 4840.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03409, over 971939.11 frames.], batch size: 30, lr: 2.34e-04
+2022-05-06 13:25:24,505 INFO [train.py:715] (3/8) Epoch 9, batch 20000, loss[loss=0.1257, simple_loss=0.1974, pruned_loss=0.02705, over 4982.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03381, over 972834.94 frames.], batch size: 27, lr: 2.34e-04
+2022-05-06 13:26:02,952 INFO [train.py:715] (3/8) Epoch 9, batch 20050, loss[loss=0.1389, simple_loss=0.2181, pruned_loss=0.02986, over 4892.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03409, over 972132.94 frames.], batch size: 19, lr: 2.34e-04
+2022-05-06 13:26:42,425 INFO [train.py:715] (3/8) Epoch 9, batch 20100, loss[loss=0.1426, simple_loss=0.2243, pruned_loss=0.03042, over 4915.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03397, over 972253.74 frames.], batch size: 18, lr: 2.34e-04
+2022-05-06 13:27:21,485 INFO [train.py:715] (3/8) Epoch 9, batch 20150, loss[loss=0.1262, simple_loss=0.2064, pruned_loss=0.02299, over 4782.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2136, pruned_loss=0.03404, over 971520.87 frames.], batch size: 14, lr: 2.34e-04
+2022-05-06 13:27:59,968 INFO [train.py:715] (3/8) Epoch 9, batch 20200, loss[loss=0.1355, simple_loss=0.203, pruned_loss=0.03399, over 4760.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2131, pruned_loss=0.03415, over 970954.80 frames.], batch size: 16, lr: 2.34e-04
+2022-05-06 13:28:39,477 INFO [train.py:715] (3/8) Epoch 9, batch 20250, loss[loss=0.1627, simple_loss=0.2301, pruned_loss=0.04762, over 4918.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03457, over 971088.75 frames.], batch size: 18, lr: 2.34e-04
+2022-05-06 13:29:18,328 INFO [train.py:715] (3/8) Epoch 9, batch 20300, loss[loss=0.1516, simple_loss=0.2266, pruned_loss=0.03826, over 4763.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2151, pruned_loss=0.03477, over 970898.32 frames.], batch size: 19, lr: 2.34e-04
+2022-05-06 13:29:57,719 INFO [train.py:715] (3/8) Epoch 9, batch 20350, loss[loss=0.148, simple_loss=0.21, pruned_loss=0.04298, over 4840.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2146, pruned_loss=0.03451, over 971313.34 frames.], batch size: 30, lr: 2.34e-04
+2022-05-06 13:30:37,199 INFO [train.py:715] (3/8) Epoch 9, batch 20400, loss[loss=0.1356, simple_loss=0.2153, pruned_loss=0.02791, over 4748.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03437, over 971799.92 frames.], batch size: 16, lr: 2.34e-04
+2022-05-06 13:31:17,092 INFO [train.py:715] (3/8) Epoch 9, batch 20450, loss[loss=0.1317, simple_loss=0.2026, pruned_loss=0.03037, over 4973.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.03459, over 971326.97 frames.], batch size: 28, lr: 2.34e-04
+2022-05-06 13:31:56,597 INFO [train.py:715] (3/8) Epoch 9, batch 20500, loss[loss=0.1404, simple_loss=0.2082, pruned_loss=0.03631, over 4934.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2138, pruned_loss=0.03477, over 972286.00 frames.], batch size: 29, lr: 2.34e-04
+2022-05-06 13:32:35,667 INFO [train.py:715] (3/8) Epoch 9, batch 20550, loss[loss=0.1414, simple_loss=0.2063, pruned_loss=0.03825, over 4805.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2136, pruned_loss=0.03473, over 972154.78 frames.], batch size: 21, lr: 2.34e-04
+2022-05-06 13:33:14,861 INFO [train.py:715] (3/8) Epoch 9, batch 20600, loss[loss=0.1693, simple_loss=0.2468, pruned_loss=0.04592, over 4783.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03497, over 971807.65 frames.], batch size: 19, lr: 2.34e-04
+2022-05-06 13:33:53,311 INFO [train.py:715] (3/8) Epoch 9, batch 20650, loss[loss=0.1413, simple_loss=0.2153, pruned_loss=0.03363, over 4956.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.03475, over 971679.01 frames.], batch size: 24, lr: 2.34e-04
+2022-05-06 13:34:32,413 INFO [train.py:715] (3/8) Epoch 9, batch 20700, loss[loss=0.1379, simple_loss=0.2049, pruned_loss=0.03549, over 4858.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2132, pruned_loss=0.0343, over 972728.86 frames.], batch size: 32, lr: 2.34e-04
+2022-05-06 13:35:11,247 INFO [train.py:715] (3/8) Epoch 9, batch 20750, loss[loss=0.1496, simple_loss=0.2406, pruned_loss=0.02928, over 4974.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2134, pruned_loss=0.03451, over 972975.72 frames.], batch size: 28, lr: 2.34e-04
+2022-05-06 13:35:50,838 INFO [train.py:715] (3/8) Epoch 9, batch 20800, loss[loss=0.1334, simple_loss=0.203, pruned_loss=0.03194, over 4841.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2133, pruned_loss=0.03447, over 972655.48 frames.], batch size: 32, lr: 2.34e-04
+2022-05-06 13:36:30,210 INFO [train.py:715] (3/8) Epoch 9, batch 20850, loss[loss=0.1398, simple_loss=0.2032, pruned_loss=0.03822, over 4873.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.03433, over 972724.68 frames.], batch size: 32, lr: 2.34e-04
+2022-05-06 13:37:09,647 INFO [train.py:715] (3/8) Epoch 9, batch 20900, loss[loss=0.1626, simple_loss=0.2318, pruned_loss=0.04671, over 4763.00 frames.], tot_loss[loss=0.141, simple_loss=0.2131, pruned_loss=0.03445, over 972642.74 frames.], batch size: 16, lr: 2.34e-04
+2022-05-06 13:37:49,145 INFO [train.py:715] (3/8) Epoch 9, batch 20950, loss[loss=0.1238, simple_loss=0.1955, pruned_loss=0.02605, over 4847.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2132, pruned_loss=0.03416, over 972600.59 frames.], batch size: 13, lr: 2.34e-04
+2022-05-06 13:38:28,445 INFO [train.py:715] (3/8) Epoch 9, batch 21000, loss[loss=0.159, simple_loss=0.234, pruned_loss=0.04203, over 4927.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03437, over 971737.84 frames.], batch size: 29, lr: 2.34e-04
+2022-05-06 13:38:28,446 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 13:38:38,082 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.1069, simple_loss=0.1912, pruned_loss=0.01129, over 914524.00 frames.
+2022-05-06 13:39:17,241 INFO [train.py:715] (3/8) Epoch 9, batch 21050, loss[loss=0.1394, simple_loss=0.2174, pruned_loss=0.03067, over 4813.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2142, pruned_loss=0.03418, over 972143.22 frames.], batch size: 27, lr: 2.34e-04
+2022-05-06 13:39:56,157 INFO [train.py:715] (3/8) Epoch 9, batch 21100, loss[loss=0.1736, simple_loss=0.2409, pruned_loss=0.05309, over 4796.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2142, pruned_loss=0.03422, over 972753.37 frames.], batch size: 14, lr: 2.34e-04
+2022-05-06 13:40:35,519 INFO [train.py:715] (3/8) Epoch 9, batch 21150, loss[loss=0.1779, simple_loss=0.2367, pruned_loss=0.0595, over 4954.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2144, pruned_loss=0.03429, over 973102.60 frames.], batch size: 24, lr: 2.34e-04
+2022-05-06 13:41:14,527 INFO [train.py:715] (3/8) Epoch 9, batch 21200, loss[loss=0.1531, simple_loss=0.2358, pruned_loss=0.0352, over 4781.00 frames.], tot_loss[loss=0.142, simple_loss=0.215, pruned_loss=0.03453, over 973023.49 frames.], batch size: 18, lr: 2.34e-04
+2022-05-06 13:41:54,098 INFO [train.py:715] (3/8) Epoch 9, batch 21250, loss[loss=0.1517, simple_loss=0.2193, pruned_loss=0.0421, over 4915.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2146, pruned_loss=0.03424, over 973350.55 frames.], batch size: 39, lr: 2.34e-04
+2022-05-06 13:42:32,486 INFO [train.py:715] (3/8) Epoch 9, batch 21300, loss[loss=0.1465, simple_loss=0.2286, pruned_loss=0.03223, over 4809.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2146, pruned_loss=0.03403, over 972384.15 frames.], batch size: 21, lr: 2.34e-04
+2022-05-06 13:43:11,098 INFO [train.py:715] (3/8) Epoch 9, batch 21350, loss[loss=0.1088, simple_loss=0.1713, pruned_loss=0.02316, over 4802.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03397, over 972482.36 frames.], batch size: 13, lr: 2.34e-04
+2022-05-06 13:43:50,029 INFO [train.py:715] (3/8) Epoch 9, batch 21400, loss[loss=0.1413, simple_loss=0.2201, pruned_loss=0.03126, over 4968.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2136, pruned_loss=0.03398, over 973413.76 frames.], batch size: 15, lr: 2.34e-04
+2022-05-06 13:44:28,771 INFO [train.py:715] (3/8) Epoch 9, batch 21450, loss[loss=0.1311, simple_loss=0.2121, pruned_loss=0.02504, over 4869.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.034, over 972851.29 frames.], batch size: 20, lr: 2.34e-04
+2022-05-06 13:45:07,166 INFO [train.py:715] (3/8) Epoch 9, batch 21500, loss[loss=0.1863, simple_loss=0.2446, pruned_loss=0.06398, over 4897.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03439, over 972673.85 frames.], batch size: 39, lr: 2.34e-04
+2022-05-06 13:45:46,282 INFO [train.py:715] (3/8) Epoch 9, batch 21550, loss[loss=0.1328, simple_loss=0.2013, pruned_loss=0.03215, over 4903.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03402, over 972104.09 frames.], batch size: 18, lr: 2.34e-04
+2022-05-06 13:46:24,998 INFO [train.py:715] (3/8) Epoch 9, batch 21600, loss[loss=0.1485, simple_loss=0.23, pruned_loss=0.03345, over 4970.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03432, over 971923.90 frames.], batch size: 24, lr: 2.34e-04
+2022-05-06 13:47:04,089 INFO [train.py:715] (3/8) Epoch 9, batch 21650, loss[loss=0.2383, simple_loss=0.2982, pruned_loss=0.08918, over 4902.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03419, over 971795.52 frames.], batch size: 22, lr: 2.34e-04
+2022-05-06 13:47:43,365 INFO [train.py:715] (3/8) Epoch 9, batch 21700, loss[loss=0.1514, simple_loss=0.2188, pruned_loss=0.04202, over 4952.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03469, over 972497.64 frames.], batch size: 14, lr: 2.34e-04
+2022-05-06 13:48:22,454 INFO [train.py:715] (3/8) Epoch 9, batch 21750, loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.0308, over 4765.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.0348, over 973031.44 frames.], batch size: 14, lr: 2.34e-04
+2022-05-06 13:49:01,563 INFO [train.py:715] (3/8) Epoch 9, batch 21800, loss[loss=0.1276, simple_loss=0.206, pruned_loss=0.02464, over 4893.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03471, over 973222.76 frames.], batch size: 22, lr: 2.34e-04
+2022-05-06 13:49:41,088 INFO [train.py:715] (3/8) Epoch 9, batch 21850, loss[loss=0.1452, simple_loss=0.2101, pruned_loss=0.04021, over 4841.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03522, over 973117.62 frames.], batch size: 15, lr: 2.34e-04
+2022-05-06 13:50:20,437 INFO [train.py:715] (3/8) Epoch 9, batch 21900, loss[loss=0.1239, simple_loss=0.1934, pruned_loss=0.02721, over 4901.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03492, over 973935.34 frames.], batch size: 19, lr: 2.33e-04
+2022-05-06 13:50:59,007 INFO [train.py:715] (3/8) Epoch 9, batch 21950, loss[loss=0.1172, simple_loss=0.1871, pruned_loss=0.02365, over 4833.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03409, over 974149.94 frames.], batch size: 30, lr: 2.33e-04
+2022-05-06 13:51:37,911 INFO [train.py:715] (3/8) Epoch 9, batch 22000, loss[loss=0.1449, simple_loss=0.2119, pruned_loss=0.03893, over 4706.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.03414, over 973556.51 frames.], batch size: 15, lr: 2.33e-04
+2022-05-06 13:52:16,810 INFO [train.py:715] (3/8) Epoch 9, batch 22050, loss[loss=0.13, simple_loss=0.2074, pruned_loss=0.02629, over 4897.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03438, over 973374.98 frames.], batch size: 17, lr: 2.33e-04
+2022-05-06 13:52:56,517 INFO [train.py:715] (3/8) Epoch 9, batch 22100, loss[loss=0.1545, simple_loss=0.212, pruned_loss=0.04855, over 4791.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2147, pruned_loss=0.03452, over 972692.15 frames.], batch size: 14, lr: 2.33e-04
+2022-05-06 13:53:35,797 INFO [train.py:715] (3/8) Epoch 9, batch 22150, loss[loss=0.1253, simple_loss=0.1995, pruned_loss=0.02559, over 4916.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2148, pruned_loss=0.03456, over 972489.01 frames.], batch size: 17, lr: 2.33e-04
+2022-05-06 13:54:14,966 INFO [train.py:715] (3/8) Epoch 9, batch 22200, loss[loss=0.1731, simple_loss=0.2343, pruned_loss=0.05596, over 4813.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.0348, over 972464.88 frames.], batch size: 13, lr: 2.33e-04
+2022-05-06 13:54:54,449 INFO [train.py:715] (3/8) Epoch 9, batch 22250, loss[loss=0.1809, simple_loss=0.2515, pruned_loss=0.05512, over 4758.00 frames.], tot_loss[loss=0.142, simple_loss=0.2144, pruned_loss=0.03478, over 972165.92 frames.], batch size: 16, lr: 2.33e-04
+2022-05-06 13:55:33,232 INFO [train.py:715] (3/8) Epoch 9, batch 22300, loss[loss=0.1128, simple_loss=0.1943, pruned_loss=0.01569, over 4874.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2142, pruned_loss=0.0351, over 971978.79 frames.], batch size: 20, lr: 2.33e-04
+2022-05-06 13:56:11,833 INFO [train.py:715] (3/8) Epoch 9, batch 22350, loss[loss=0.1455, simple_loss=0.2126, pruned_loss=0.03923, over 4969.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03496, over 971983.69 frames.], batch size: 15, lr: 2.33e-04
+2022-05-06 13:56:50,722 INFO [train.py:715] (3/8) Epoch 9, batch 22400, loss[loss=0.1021, simple_loss=0.1774, pruned_loss=0.01341, over 4848.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03499, over 971656.71 frames.], batch size: 13, lr: 2.33e-04
+2022-05-06 13:57:29,424 INFO [train.py:715] (3/8) Epoch 9, batch 22450, loss[loss=0.1566, simple_loss=0.2215, pruned_loss=0.04586, over 4783.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03481, over 972288.11 frames.], batch size: 17, lr: 2.33e-04
+2022-05-06 13:58:08,129 INFO [train.py:715] (3/8) Epoch 9, batch 22500, loss[loss=0.1458, simple_loss=0.2178, pruned_loss=0.03689, over 4806.00 frames.], tot_loss[loss=0.1416, simple_loss=0.214, pruned_loss=0.03463, over 971572.86 frames.], batch size: 21, lr: 2.33e-04
+2022-05-06 13:58:47,017 INFO [train.py:715] (3/8) Epoch 9, batch 22550, loss[loss=0.132, simple_loss=0.2, pruned_loss=0.03205, over 4827.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2149, pruned_loss=0.03523, over 972213.78 frames.], batch size: 13, lr: 2.33e-04
+2022-05-06 13:59:26,037 INFO [train.py:715] (3/8) Epoch 9, batch 22600, loss[loss=0.1393, simple_loss=0.2165, pruned_loss=0.03103, over 4924.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2134, pruned_loss=0.0344, over 972066.24 frames.], batch size: 18, lr: 2.33e-04
+2022-05-06 14:00:05,202 INFO [train.py:715] (3/8) Epoch 9, batch 22650, loss[loss=0.1583, simple_loss=0.2301, pruned_loss=0.04321, over 4771.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03439, over 971732.17 frames.], batch size: 14, lr: 2.33e-04
+2022-05-06 14:00:44,244 INFO [train.py:715] (3/8) Epoch 9, batch 22700, loss[loss=0.1382, simple_loss=0.2169, pruned_loss=0.02976, over 4884.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03416, over 971393.53 frames.], batch size: 22, lr: 2.33e-04
+2022-05-06 14:01:26,075 INFO [train.py:715] (3/8) Epoch 9, batch 22750, loss[loss=0.139, simple_loss=0.2015, pruned_loss=0.03829, over 4973.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03475, over 972486.69 frames.], batch size: 14, lr: 2.33e-04
+2022-05-06 14:02:04,865 INFO [train.py:715] (3/8) Epoch 9, batch 22800, loss[loss=0.1187, simple_loss=0.1979, pruned_loss=0.01978, over 4941.00 frames.], tot_loss[loss=0.142, simple_loss=0.2146, pruned_loss=0.03474, over 973218.44 frames.], batch size: 21, lr: 2.33e-04
+2022-05-06 14:02:44,149 INFO [train.py:715] (3/8) Epoch 9, batch 22850, loss[loss=0.1477, simple_loss=0.2197, pruned_loss=0.03782, over 4890.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2153, pruned_loss=0.0346, over 973964.93 frames.], batch size: 19, lr: 2.33e-04
+2022-05-06 14:03:22,720 INFO [train.py:715] (3/8) Epoch 9, batch 22900, loss[loss=0.1708, simple_loss=0.252, pruned_loss=0.04483, over 4919.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2142, pruned_loss=0.03417, over 973676.73 frames.], batch size: 18, lr: 2.33e-04
+2022-05-06 14:04:01,802 INFO [train.py:715] (3/8) Epoch 9, batch 22950, loss[loss=0.122, simple_loss=0.2038, pruned_loss=0.02014, over 4693.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2146, pruned_loss=0.0343, over 973248.66 frames.], batch size: 15, lr: 2.33e-04
+2022-05-06 14:04:40,857 INFO [train.py:715] (3/8) Epoch 9, batch 23000, loss[loss=0.128, simple_loss=0.1982, pruned_loss=0.02891, over 4951.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03429, over 973048.58 frames.], batch size: 21, lr: 2.33e-04
+2022-05-06 14:05:20,249 INFO [train.py:715] (3/8) Epoch 9, batch 23050, loss[loss=0.1348, simple_loss=0.2158, pruned_loss=0.02687, over 4976.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2144, pruned_loss=0.03421, over 972394.64 frames.], batch size: 15, lr: 2.33e-04
+2022-05-06 14:05:59,520 INFO [train.py:715] (3/8) Epoch 9, batch 23100, loss[loss=0.1357, simple_loss=0.2192, pruned_loss=0.0261, over 4916.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03468, over 972124.38 frames.], batch size: 23, lr: 2.33e-04
+2022-05-06 14:06:38,546 INFO [train.py:715] (3/8) Epoch 9, batch 23150, loss[loss=0.1471, simple_loss=0.2175, pruned_loss=0.03831, over 4867.00 frames.], tot_loss[loss=0.142, simple_loss=0.214, pruned_loss=0.03495, over 972841.82 frames.], batch size: 32, lr: 2.33e-04
+2022-05-06 14:07:18,157 INFO [train.py:715] (3/8) Epoch 9, batch 23200, loss[loss=0.1337, simple_loss=0.2026, pruned_loss=0.03236, over 4767.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.03516, over 973571.11 frames.], batch size: 18, lr: 2.33e-04
+2022-05-06 14:07:57,915 INFO [train.py:715] (3/8) Epoch 9, batch 23250, loss[loss=0.127, simple_loss=0.2063, pruned_loss=0.02392, over 4925.00 frames.], tot_loss[loss=0.142, simple_loss=0.2141, pruned_loss=0.03492, over 973695.14 frames.], batch size: 18, lr: 2.33e-04
+2022-05-06 14:08:37,683 INFO [train.py:715] (3/8) Epoch 9, batch 23300, loss[loss=0.1687, simple_loss=0.2488, pruned_loss=0.04435, over 4903.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03454, over 973839.37 frames.], batch size: 19, lr: 2.33e-04
+2022-05-06 14:09:17,440 INFO [train.py:715] (3/8) Epoch 9, batch 23350, loss[loss=0.1461, simple_loss=0.2007, pruned_loss=0.04572, over 4970.00 frames.], tot_loss[loss=0.142, simple_loss=0.2143, pruned_loss=0.03481, over 973658.55 frames.], batch size: 14, lr: 2.33e-04
+2022-05-06 14:09:56,734 INFO [train.py:715] (3/8) Epoch 9, batch 23400, loss[loss=0.1614, simple_loss=0.2364, pruned_loss=0.04319, over 4856.00 frames.], tot_loss[loss=0.142, simple_loss=0.2141, pruned_loss=0.0349, over 973733.45 frames.], batch size: 20, lr: 2.33e-04
+2022-05-06 14:10:35,595 INFO [train.py:715] (3/8) Epoch 9, batch 23450, loss[loss=0.1369, simple_loss=0.2161, pruned_loss=0.02882, over 4951.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03483, over 974649.35 frames.], batch size: 21, lr: 2.33e-04
+2022-05-06 14:11:14,355 INFO [train.py:715] (3/8) Epoch 9, batch 23500, loss[loss=0.1232, simple_loss=0.1964, pruned_loss=0.02493, over 4736.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03447, over 974080.08 frames.], batch size: 16, lr: 2.33e-04
+2022-05-06 14:11:52,882 INFO [train.py:715] (3/8) Epoch 9, batch 23550, loss[loss=0.1201, simple_loss=0.1962, pruned_loss=0.02207, over 4700.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.03429, over 973854.26 frames.], batch size: 15, lr: 2.33e-04
+2022-05-06 14:12:32,347 INFO [train.py:715] (3/8) Epoch 9, batch 23600, loss[loss=0.1606, simple_loss=0.2273, pruned_loss=0.04689, over 4878.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2149, pruned_loss=0.03459, over 972919.57 frames.], batch size: 32, lr: 2.33e-04
+2022-05-06 14:13:11,498 INFO [train.py:715] (3/8) Epoch 9, batch 23650, loss[loss=0.1204, simple_loss=0.1877, pruned_loss=0.02657, over 4775.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03435, over 972857.51 frames.], batch size: 12, lr: 2.33e-04
+2022-05-06 14:13:50,879 INFO [train.py:715] (3/8) Epoch 9, batch 23700, loss[loss=0.1435, simple_loss=0.2134, pruned_loss=0.03684, over 4850.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03464, over 973325.32 frames.], batch size: 30, lr: 2.33e-04
+2022-05-06 14:14:30,049 INFO [train.py:715] (3/8) Epoch 9, batch 23750, loss[loss=0.1623, simple_loss=0.214, pruned_loss=0.05536, over 4907.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.0348, over 973048.20 frames.], batch size: 17, lr: 2.33e-04
+2022-05-06 14:15:09,283 INFO [train.py:715] (3/8) Epoch 9, batch 23800, loss[loss=0.1296, simple_loss=0.2037, pruned_loss=0.02777, over 4685.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2141, pruned_loss=0.03435, over 973049.64 frames.], batch size: 15, lr: 2.33e-04
+2022-05-06 14:15:48,391 INFO [train.py:715] (3/8) Epoch 9, batch 23850, loss[loss=0.1372, simple_loss=0.2124, pruned_loss=0.031, over 4872.00 frames.], tot_loss[loss=0.142, simple_loss=0.2149, pruned_loss=0.03451, over 972954.90 frames.], batch size: 22, lr: 2.33e-04
+2022-05-06 14:16:27,643 INFO [train.py:715] (3/8) Epoch 9, batch 23900, loss[loss=0.1104, simple_loss=0.183, pruned_loss=0.0189, over 4852.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03412, over 972917.87 frames.], batch size: 12, lr: 2.33e-04
+2022-05-06 14:17:06,536 INFO [train.py:715] (3/8) Epoch 9, batch 23950, loss[loss=0.1531, simple_loss=0.2284, pruned_loss=0.03892, over 4909.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03418, over 972110.64 frames.], batch size: 17, lr: 2.33e-04
+2022-05-06 14:17:45,502 INFO [train.py:715] (3/8) Epoch 9, batch 24000, loss[loss=0.1373, simple_loss=0.2131, pruned_loss=0.03078, over 4941.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03439, over 972173.84 frames.], batch size: 39, lr: 2.33e-04
+2022-05-06 14:17:45,502 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 14:17:55,356 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.1069, simple_loss=0.1913, pruned_loss=0.01128, over 914524.00 frames.
+2022-05-06 14:18:34,692 INFO [train.py:715] (3/8) Epoch 9, batch 24050, loss[loss=0.1384, simple_loss=0.2009, pruned_loss=0.03795, over 4810.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2134, pruned_loss=0.03461, over 972194.22 frames.], batch size: 14, lr: 2.33e-04
+2022-05-06 14:19:14,962 INFO [train.py:715] (3/8) Epoch 9, batch 24100, loss[loss=0.1395, simple_loss=0.2117, pruned_loss=0.03361, over 4804.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2139, pruned_loss=0.03488, over 972329.07 frames.], batch size: 21, lr: 2.33e-04
+2022-05-06 14:19:54,474 INFO [train.py:715] (3/8) Epoch 9, batch 24150, loss[loss=0.1477, simple_loss=0.2264, pruned_loss=0.03451, over 4745.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03529, over 972099.41 frames.], batch size: 16, lr: 2.33e-04
+2022-05-06 14:20:33,560 INFO [train.py:715] (3/8) Epoch 9, batch 24200, loss[loss=0.1394, simple_loss=0.2143, pruned_loss=0.03226, over 4784.00 frames.], tot_loss[loss=0.1429, simple_loss=0.215, pruned_loss=0.03542, over 972444.84 frames.], batch size: 17, lr: 2.33e-04
+2022-05-06 14:21:12,481 INFO [train.py:715] (3/8) Epoch 9, batch 24250, loss[loss=0.1661, simple_loss=0.2337, pruned_loss=0.0492, over 4968.00 frames.], tot_loss[loss=0.1429, simple_loss=0.215, pruned_loss=0.03538, over 972486.15 frames.], batch size: 39, lr: 2.33e-04
+2022-05-06 14:21:52,134 INFO [train.py:715] (3/8) Epoch 9, batch 24300, loss[loss=0.1485, simple_loss=0.2349, pruned_loss=0.03105, over 4835.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03541, over 972673.28 frames.], batch size: 25, lr: 2.33e-04
+2022-05-06 14:22:31,315 INFO [train.py:715] (3/8) Epoch 9, batch 24350, loss[loss=0.1522, simple_loss=0.2234, pruned_loss=0.04047, over 4940.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.03539, over 972721.82 frames.], batch size: 21, lr: 2.33e-04
+2022-05-06 14:23:10,730 INFO [train.py:715] (3/8) Epoch 9, batch 24400, loss[loss=0.1472, simple_loss=0.2173, pruned_loss=0.03852, over 4808.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2153, pruned_loss=0.03471, over 973080.07 frames.], batch size: 26, lr: 2.33e-04
+2022-05-06 14:23:50,614 INFO [train.py:715] (3/8) Epoch 9, batch 24450, loss[loss=0.1463, simple_loss=0.2116, pruned_loss=0.04048, over 4943.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2147, pruned_loss=0.03458, over 973175.08 frames.], batch size: 35, lr: 2.33e-04
+2022-05-06 14:24:30,640 INFO [train.py:715] (3/8) Epoch 9, batch 24500, loss[loss=0.1468, simple_loss=0.2275, pruned_loss=0.03306, over 4825.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03407, over 973977.85 frames.], batch size: 15, lr: 2.33e-04
+2022-05-06 14:25:10,999 INFO [train.py:715] (3/8) Epoch 9, batch 24550, loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.03062, over 4760.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.0338, over 973609.86 frames.], batch size: 18, lr: 2.33e-04
+2022-05-06 14:25:50,744 INFO [train.py:715] (3/8) Epoch 9, batch 24600, loss[loss=0.1407, simple_loss=0.2109, pruned_loss=0.03522, over 4759.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03425, over 973490.27 frames.], batch size: 16, lr: 2.33e-04
+2022-05-06 14:26:30,719 INFO [train.py:715] (3/8) Epoch 9, batch 24650, loss[loss=0.1671, simple_loss=0.2262, pruned_loss=0.05403, over 4849.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03437, over 973505.98 frames.], batch size: 32, lr: 2.33e-04
+2022-05-06 14:27:09,793 INFO [train.py:715] (3/8) Epoch 9, batch 24700, loss[loss=0.1691, simple_loss=0.2352, pruned_loss=0.05149, over 4984.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03457, over 973359.31 frames.], batch size: 28, lr: 2.33e-04
+2022-05-06 14:27:48,505 INFO [train.py:715] (3/8) Epoch 9, batch 24750, loss[loss=0.1414, simple_loss=0.2217, pruned_loss=0.03061, over 4988.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03473, over 972575.44 frames.], batch size: 25, lr: 2.33e-04
+2022-05-06 14:28:28,025 INFO [train.py:715] (3/8) Epoch 9, batch 24800, loss[loss=0.1217, simple_loss=0.2021, pruned_loss=0.0207, over 4961.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.03415, over 972073.38 frames.], batch size: 24, lr: 2.32e-04
+2022-05-06 14:29:07,571 INFO [train.py:715] (3/8) Epoch 9, batch 24850, loss[loss=0.1252, simple_loss=0.2023, pruned_loss=0.02404, over 4816.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03436, over 972662.50 frames.], batch size: 25, lr: 2.32e-04
+2022-05-06 14:29:46,969 INFO [train.py:715] (3/8) Epoch 9, batch 24900, loss[loss=0.1075, simple_loss=0.1733, pruned_loss=0.02082, over 4989.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03389, over 973336.89 frames.], batch size: 14, lr: 2.32e-04
+2022-05-06 14:30:26,386 INFO [train.py:715] (3/8) Epoch 9, batch 24950, loss[loss=0.1749, simple_loss=0.2498, pruned_loss=0.04998, over 4925.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03437, over 973428.47 frames.], batch size: 39, lr: 2.32e-04
+2022-05-06 14:31:06,086 INFO [train.py:715] (3/8) Epoch 9, batch 25000, loss[loss=0.1449, simple_loss=0.2185, pruned_loss=0.03558, over 4833.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2141, pruned_loss=0.03443, over 973316.71 frames.], batch size: 30, lr: 2.32e-04
+2022-05-06 14:31:44,920 INFO [train.py:715] (3/8) Epoch 9, batch 25050, loss[loss=0.154, simple_loss=0.2197, pruned_loss=0.04409, over 4773.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.0343, over 972589.79 frames.], batch size: 19, lr: 2.32e-04
+2022-05-06 14:32:24,414 INFO [train.py:715] (3/8) Epoch 9, batch 25100, loss[loss=0.1298, simple_loss=0.2066, pruned_loss=0.02652, over 4871.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2143, pruned_loss=0.03416, over 972365.51 frames.], batch size: 16, lr: 2.32e-04
+2022-05-06 14:33:03,522 INFO [train.py:715] (3/8) Epoch 9, batch 25150, loss[loss=0.1352, simple_loss=0.2021, pruned_loss=0.03411, over 4898.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2147, pruned_loss=0.03425, over 973233.81 frames.], batch size: 19, lr: 2.32e-04
+2022-05-06 14:33:42,579 INFO [train.py:715] (3/8) Epoch 9, batch 25200, loss[loss=0.1508, simple_loss=0.2233, pruned_loss=0.03917, over 4686.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03426, over 973308.98 frames.], batch size: 15, lr: 2.32e-04
+2022-05-06 14:34:21,840 INFO [train.py:715] (3/8) Epoch 9, batch 25250, loss[loss=0.1451, simple_loss=0.2103, pruned_loss=0.03992, over 4935.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03376, over 972320.20 frames.], batch size: 35, lr: 2.32e-04
+2022-05-06 14:35:00,584 INFO [train.py:715] (3/8) Epoch 9, batch 25300, loss[loss=0.1299, simple_loss=0.2057, pruned_loss=0.02707, over 4758.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2127, pruned_loss=0.03417, over 971855.45 frames.], batch size: 19, lr: 2.32e-04
+2022-05-06 14:35:40,270 INFO [train.py:715] (3/8) Epoch 9, batch 25350, loss[loss=0.1552, simple_loss=0.2211, pruned_loss=0.04462, over 4858.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2131, pruned_loss=0.03431, over 972537.38 frames.], batch size: 13, lr: 2.32e-04
+2022-05-06 14:36:20,107 INFO [train.py:715] (3/8) Epoch 9, batch 25400, loss[loss=0.1314, simple_loss=0.1996, pruned_loss=0.03158, over 4886.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03407, over 972889.25 frames.], batch size: 16, lr: 2.32e-04
+2022-05-06 14:37:00,344 INFO [train.py:715] (3/8) Epoch 9, batch 25450, loss[loss=0.1323, simple_loss=0.203, pruned_loss=0.03075, over 4992.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03374, over 973342.07 frames.], batch size: 14, lr: 2.32e-04
+2022-05-06 14:37:38,911 INFO [train.py:715] (3/8) Epoch 9, batch 25500, loss[loss=0.1489, simple_loss=0.2295, pruned_loss=0.0341, over 4885.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03384, over 972991.01 frames.], batch size: 22, lr: 2.32e-04
+2022-05-06 14:38:18,074 INFO [train.py:715] (3/8) Epoch 9, batch 25550, loss[loss=0.1582, simple_loss=0.2305, pruned_loss=0.04295, over 4897.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03402, over 973484.16 frames.], batch size: 19, lr: 2.32e-04
+2022-05-06 14:38:57,229 INFO [train.py:715] (3/8) Epoch 9, batch 25600, loss[loss=0.1713, simple_loss=0.2298, pruned_loss=0.05636, over 4818.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2141, pruned_loss=0.0343, over 972999.57 frames.], batch size: 25, lr: 2.32e-04
+2022-05-06 14:39:36,161 INFO [train.py:715] (3/8) Epoch 9, batch 25650, loss[loss=0.152, simple_loss=0.2211, pruned_loss=0.04145, over 4790.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03381, over 972876.74 frames.], batch size: 17, lr: 2.32e-04
+2022-05-06 14:40:15,295 INFO [train.py:715] (3/8) Epoch 9, batch 25700, loss[loss=0.1479, simple_loss=0.2275, pruned_loss=0.03418, over 4760.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.03334, over 972782.40 frames.], batch size: 19, lr: 2.32e-04
+2022-05-06 14:40:54,416 INFO [train.py:715] (3/8) Epoch 9, batch 25750, loss[loss=0.1368, simple_loss=0.2033, pruned_loss=0.03514, over 4901.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03351, over 972136.37 frames.], batch size: 22, lr: 2.32e-04
+2022-05-06 14:41:33,410 INFO [train.py:715] (3/8) Epoch 9, batch 25800, loss[loss=0.1572, simple_loss=0.2284, pruned_loss=0.04303, over 4807.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03393, over 972090.70 frames.], batch size: 25, lr: 2.32e-04
+2022-05-06 14:42:13,628 INFO [train.py:715] (3/8) Epoch 9, batch 25850, loss[loss=0.1544, simple_loss=0.2264, pruned_loss=0.04123, over 4879.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03437, over 972538.97 frames.], batch size: 16, lr: 2.32e-04
+2022-05-06 14:42:53,071 INFO [train.py:715] (3/8) Epoch 9, batch 25900, loss[loss=0.1517, simple_loss=0.2228, pruned_loss=0.04033, over 4892.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2141, pruned_loss=0.03435, over 973307.44 frames.], batch size: 39, lr: 2.32e-04
+2022-05-06 14:43:32,745 INFO [train.py:715] (3/8) Epoch 9, batch 25950, loss[loss=0.155, simple_loss=0.2169, pruned_loss=0.04648, over 4842.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03482, over 973642.32 frames.], batch size: 32, lr: 2.32e-04
+2022-05-06 14:44:11,978 INFO [train.py:715] (3/8) Epoch 9, batch 26000, loss[loss=0.1554, simple_loss=0.2288, pruned_loss=0.04104, over 4708.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03482, over 972159.38 frames.], batch size: 15, lr: 2.32e-04
+2022-05-06 14:44:51,308 INFO [train.py:715] (3/8) Epoch 9, batch 26050, loss[loss=0.1339, simple_loss=0.2162, pruned_loss=0.02579, over 4986.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2147, pruned_loss=0.03456, over 972254.51 frames.], batch size: 25, lr: 2.32e-04
+2022-05-06 14:45:30,099 INFO [train.py:715] (3/8) Epoch 9, batch 26100, loss[loss=0.1356, simple_loss=0.2097, pruned_loss=0.03076, over 4802.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03408, over 971637.65 frames.], batch size: 21, lr: 2.32e-04
+2022-05-06 14:46:09,804 INFO [train.py:715] (3/8) Epoch 9, batch 26150, loss[loss=0.1685, simple_loss=0.2232, pruned_loss=0.05692, over 4736.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03422, over 972583.68 frames.], batch size: 16, lr: 2.32e-04
+2022-05-06 14:46:50,054 INFO [train.py:715] (3/8) Epoch 9, batch 26200, loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03898, over 4967.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03409, over 973206.97 frames.], batch size: 24, lr: 2.32e-04
+2022-05-06 14:47:29,915 INFO [train.py:715] (3/8) Epoch 9, batch 26250, loss[loss=0.1176, simple_loss=0.18, pruned_loss=0.02758, over 4885.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2123, pruned_loss=0.0336, over 973672.11 frames.], batch size: 13, lr: 2.32e-04
+2022-05-06 14:48:09,838 INFO [train.py:715] (3/8) Epoch 9, batch 26300, loss[loss=0.1441, simple_loss=0.2065, pruned_loss=0.04078, over 4967.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2119, pruned_loss=0.03342, over 973818.63 frames.], batch size: 15, lr: 2.32e-04
+2022-05-06 14:48:49,365 INFO [train.py:715] (3/8) Epoch 9, batch 26350, loss[loss=0.1284, simple_loss=0.2013, pruned_loss=0.02776, over 4846.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03383, over 973230.90 frames.], batch size: 20, lr: 2.32e-04
+2022-05-06 14:49:28,725 INFO [train.py:715] (3/8) Epoch 9, batch 26400, loss[loss=0.1541, simple_loss=0.2171, pruned_loss=0.04555, over 4985.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03424, over 972935.88 frames.], batch size: 14, lr: 2.32e-04
+2022-05-06 14:50:07,641 INFO [train.py:715] (3/8) Epoch 9, batch 26450, loss[loss=0.1398, simple_loss=0.2065, pruned_loss=0.03649, over 4949.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03394, over 972427.12 frames.], batch size: 23, lr: 2.32e-04
+2022-05-06 14:50:46,956 INFO [train.py:715] (3/8) Epoch 9, batch 26500, loss[loss=0.1462, simple_loss=0.2247, pruned_loss=0.03381, over 4860.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03349, over 972655.28 frames.], batch size: 20, lr: 2.32e-04
+2022-05-06 14:51:26,797 INFO [train.py:715] (3/8) Epoch 9, batch 26550, loss[loss=0.1187, simple_loss=0.1898, pruned_loss=0.02377, over 4795.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03353, over 972801.90 frames.], batch size: 17, lr: 2.32e-04
+2022-05-06 14:52:06,134 INFO [train.py:715] (3/8) Epoch 9, batch 26600, loss[loss=0.1311, simple_loss=0.2209, pruned_loss=0.02066, over 4926.00 frames.], tot_loss[loss=0.14, simple_loss=0.2135, pruned_loss=0.03329, over 972314.32 frames.], batch size: 21, lr: 2.32e-04
+2022-05-06 14:52:46,086 INFO [train.py:715] (3/8) Epoch 9, batch 26650, loss[loss=0.1152, simple_loss=0.1899, pruned_loss=0.02029, over 4939.00 frames.], tot_loss[loss=0.14, simple_loss=0.2136, pruned_loss=0.03315, over 971551.89 frames.], batch size: 23, lr: 2.32e-04
+2022-05-06 14:53:25,378 INFO [train.py:715] (3/8) Epoch 9, batch 26700, loss[loss=0.1935, simple_loss=0.2651, pruned_loss=0.06094, over 4838.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2147, pruned_loss=0.03402, over 971332.50 frames.], batch size: 15, lr: 2.32e-04
+2022-05-06 14:54:04,745 INFO [train.py:715] (3/8) Epoch 9, batch 26750, loss[loss=0.1368, simple_loss=0.2002, pruned_loss=0.03672, over 4983.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2143, pruned_loss=0.03413, over 971621.48 frames.], batch size: 28, lr: 2.32e-04
+2022-05-06 14:54:43,923 INFO [train.py:715] (3/8) Epoch 9, batch 26800, loss[loss=0.1447, simple_loss=0.2242, pruned_loss=0.03257, over 4941.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.03443, over 971828.05 frames.], batch size: 21, lr: 2.32e-04
+2022-05-06 14:55:22,922 INFO [train.py:715] (3/8) Epoch 9, batch 26850, loss[loss=0.129, simple_loss=0.1953, pruned_loss=0.03134, over 4854.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03388, over 972172.58 frames.], batch size: 12, lr: 2.32e-04
+2022-05-06 14:56:02,400 INFO [train.py:715] (3/8) Epoch 9, batch 26900, loss[loss=0.1276, simple_loss=0.2043, pruned_loss=0.02548, over 4950.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03377, over 972503.92 frames.], batch size: 24, lr: 2.32e-04
+2022-05-06 14:56:42,228 INFO [train.py:715] (3/8) Epoch 9, batch 26950, loss[loss=0.1088, simple_loss=0.1872, pruned_loss=0.0152, over 4813.00 frames.], tot_loss[loss=0.141, simple_loss=0.2143, pruned_loss=0.03385, over 972623.72 frames.], batch size: 13, lr: 2.32e-04
+2022-05-06 14:57:21,397 INFO [train.py:715] (3/8) Epoch 9, batch 27000, loss[loss=0.1095, simple_loss=0.1837, pruned_loss=0.01761, over 4822.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03408, over 972381.88 frames.], batch size: 21, lr: 2.32e-04
+2022-05-06 14:57:21,398 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 14:57:30,963 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1912, pruned_loss=0.01121, over 914524.00 frames.
+2022-05-06 14:58:10,507 INFO [train.py:715] (3/8) Epoch 9, batch 27050, loss[loss=0.1327, simple_loss=0.2079, pruned_loss=0.0288, over 4989.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.03417, over 972820.31 frames.], batch size: 28, lr: 2.32e-04
+2022-05-06 14:58:50,066 INFO [train.py:715] (3/8) Epoch 9, batch 27100, loss[loss=0.1402, simple_loss=0.2086, pruned_loss=0.03588, over 4827.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03358, over 971916.37 frames.], batch size: 27, lr: 2.32e-04
+2022-05-06 14:59:30,122 INFO [train.py:715] (3/8) Epoch 9, batch 27150, loss[loss=0.1221, simple_loss=0.2014, pruned_loss=0.02141, over 4799.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03376, over 972947.52 frames.], batch size: 18, lr: 2.32e-04
+2022-05-06 15:00:09,247 INFO [train.py:715] (3/8) Epoch 9, batch 27200, loss[loss=0.1117, simple_loss=0.1885, pruned_loss=0.01749, over 4910.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03394, over 973070.06 frames.], batch size: 19, lr: 2.32e-04
+2022-05-06 15:00:48,165 INFO [train.py:715] (3/8) Epoch 9, batch 27250, loss[loss=0.1225, simple_loss=0.1926, pruned_loss=0.02623, over 4962.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.03342, over 972566.41 frames.], batch size: 14, lr: 2.32e-04
+2022-05-06 15:01:27,383 INFO [train.py:715] (3/8) Epoch 9, batch 27300, loss[loss=0.1301, simple_loss=0.1965, pruned_loss=0.03183, over 4880.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03345, over 973064.56 frames.], batch size: 32, lr: 2.32e-04
+2022-05-06 15:02:06,269 INFO [train.py:715] (3/8) Epoch 9, batch 27350, loss[loss=0.1241, simple_loss=0.1929, pruned_loss=0.02767, over 4828.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03337, over 972790.41 frames.], batch size: 13, lr: 2.32e-04
+2022-05-06 15:02:45,300 INFO [train.py:715] (3/8) Epoch 9, batch 27400, loss[loss=0.1336, simple_loss=0.2045, pruned_loss=0.03135, over 4859.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03375, over 972235.18 frames.], batch size: 32, lr: 2.32e-04
+2022-05-06 15:03:24,467 INFO [train.py:715] (3/8) Epoch 9, batch 27450, loss[loss=0.1473, simple_loss=0.2052, pruned_loss=0.0447, over 4994.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03374, over 971519.10 frames.], batch size: 14, lr: 2.32e-04
+2022-05-06 15:04:03,436 INFO [train.py:715] (3/8) Epoch 9, batch 27500, loss[loss=0.1195, simple_loss=0.1946, pruned_loss=0.02222, over 4762.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03312, over 972004.81 frames.], batch size: 16, lr: 2.32e-04
+2022-05-06 15:04:42,460 INFO [train.py:715] (3/8) Epoch 9, batch 27550, loss[loss=0.1891, simple_loss=0.2708, pruned_loss=0.05365, over 4836.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03381, over 971499.12 frames.], batch size: 15, lr: 2.32e-04
+2022-05-06 15:05:21,389 INFO [train.py:715] (3/8) Epoch 9, batch 27600, loss[loss=0.145, simple_loss=0.2243, pruned_loss=0.03283, over 4900.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.0335, over 972101.28 frames.], batch size: 19, lr: 2.32e-04
+2022-05-06 15:06:00,165 INFO [train.py:715] (3/8) Epoch 9, batch 27650, loss[loss=0.1421, simple_loss=0.2097, pruned_loss=0.03731, over 4972.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03313, over 972098.76 frames.], batch size: 28, lr: 2.32e-04
+2022-05-06 15:06:39,018 INFO [train.py:715] (3/8) Epoch 9, batch 27700, loss[loss=0.1251, simple_loss=0.1973, pruned_loss=0.0264, over 4968.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03332, over 971809.47 frames.], batch size: 25, lr: 2.32e-04
+2022-05-06 15:07:18,263 INFO [train.py:715] (3/8) Epoch 9, batch 27750, loss[loss=0.1808, simple_loss=0.2542, pruned_loss=0.05366, over 4859.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03347, over 972325.93 frames.], batch size: 15, lr: 2.31e-04
+2022-05-06 15:07:57,615 INFO [train.py:715] (3/8) Epoch 9, batch 27800, loss[loss=0.1473, simple_loss=0.2216, pruned_loss=0.03657, over 4802.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03371, over 971998.72 frames.], batch size: 14, lr: 2.31e-04
+2022-05-06 15:08:36,547 INFO [train.py:715] (3/8) Epoch 9, batch 27850, loss[loss=0.1296, simple_loss=0.1949, pruned_loss=0.03218, over 4781.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03384, over 972439.59 frames.], batch size: 14, lr: 2.31e-04
+2022-05-06 15:09:16,413 INFO [train.py:715] (3/8) Epoch 9, batch 27900, loss[loss=0.181, simple_loss=0.2563, pruned_loss=0.05286, over 4685.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03384, over 971742.44 frames.], batch size: 15, lr: 2.31e-04
+2022-05-06 15:09:54,912 INFO [train.py:715] (3/8) Epoch 9, batch 27950, loss[loss=0.1267, simple_loss=0.1965, pruned_loss=0.02849, over 4814.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03398, over 971189.41 frames.], batch size: 13, lr: 2.31e-04
+2022-05-06 15:10:34,266 INFO [train.py:715] (3/8) Epoch 9, batch 28000, loss[loss=0.1602, simple_loss=0.2198, pruned_loss=0.05026, over 4876.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.0341, over 971927.75 frames.], batch size: 30, lr: 2.31e-04
+2022-05-06 15:11:13,571 INFO [train.py:715] (3/8) Epoch 9, batch 28050, loss[loss=0.1396, simple_loss=0.203, pruned_loss=0.03813, over 4643.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03456, over 971945.34 frames.], batch size: 13, lr: 2.31e-04
+2022-05-06 15:11:52,642 INFO [train.py:715] (3/8) Epoch 9, batch 28100, loss[loss=0.1265, simple_loss=0.1979, pruned_loss=0.02761, over 4775.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03464, over 972525.16 frames.], batch size: 18, lr: 2.31e-04
+2022-05-06 15:12:31,905 INFO [train.py:715] (3/8) Epoch 9, batch 28150, loss[loss=0.1503, simple_loss=0.2227, pruned_loss=0.03889, over 4971.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.035, over 973405.94 frames.], batch size: 24, lr: 2.31e-04
+2022-05-06 15:13:10,817 INFO [train.py:715] (3/8) Epoch 9, batch 28200, loss[loss=0.1295, simple_loss=0.206, pruned_loss=0.02647, over 4968.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2154, pruned_loss=0.03476, over 973097.69 frames.], batch size: 24, lr: 2.31e-04
+2022-05-06 15:13:50,249 INFO [train.py:715] (3/8) Epoch 9, batch 28250, loss[loss=0.1318, simple_loss=0.1912, pruned_loss=0.03616, over 4767.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03468, over 973068.56 frames.], batch size: 14, lr: 2.31e-04
+2022-05-06 15:14:28,525 INFO [train.py:715] (3/8) Epoch 9, batch 28300, loss[loss=0.1424, simple_loss=0.2181, pruned_loss=0.03332, over 4805.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2149, pruned_loss=0.03466, over 972799.84 frames.], batch size: 26, lr: 2.31e-04
+2022-05-06 15:15:07,475 INFO [train.py:715] (3/8) Epoch 9, batch 28350, loss[loss=0.1337, simple_loss=0.2026, pruned_loss=0.03243, over 4823.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2147, pruned_loss=0.03427, over 973182.62 frames.], batch size: 15, lr: 2.31e-04
+2022-05-06 15:15:46,871 INFO [train.py:715] (3/8) Epoch 9, batch 28400, loss[loss=0.1398, simple_loss=0.2103, pruned_loss=0.03461, over 4919.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2145, pruned_loss=0.03441, over 973380.77 frames.], batch size: 17, lr: 2.31e-04
+2022-05-06 15:16:25,949 INFO [train.py:715] (3/8) Epoch 9, batch 28450, loss[loss=0.1455, simple_loss=0.2125, pruned_loss=0.0393, over 4911.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03443, over 973744.14 frames.], batch size: 23, lr: 2.31e-04
+2022-05-06 15:17:04,387 INFO [train.py:715] (3/8) Epoch 9, batch 28500, loss[loss=0.1444, simple_loss=0.2151, pruned_loss=0.03688, over 4905.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2144, pruned_loss=0.03448, over 973318.49 frames.], batch size: 22, lr: 2.31e-04
+2022-05-06 15:17:43,522 INFO [train.py:715] (3/8) Epoch 9, batch 28550, loss[loss=0.1702, simple_loss=0.2392, pruned_loss=0.05058, over 4869.00 frames.], tot_loss[loss=0.1424, simple_loss=0.215, pruned_loss=0.03485, over 973593.97 frames.], batch size: 16, lr: 2.31e-04
+2022-05-06 15:18:22,911 INFO [train.py:715] (3/8) Epoch 9, batch 28600, loss[loss=0.1651, simple_loss=0.2355, pruned_loss=0.04729, over 4694.00 frames.], tot_loss[loss=0.1421, simple_loss=0.215, pruned_loss=0.03462, over 973875.31 frames.], batch size: 15, lr: 2.31e-04
+2022-05-06 15:19:01,328 INFO [train.py:715] (3/8) Epoch 9, batch 28650, loss[loss=0.1231, simple_loss=0.2012, pruned_loss=0.02243, over 4817.00 frames.], tot_loss[loss=0.1417, simple_loss=0.215, pruned_loss=0.03424, over 973639.42 frames.], batch size: 26, lr: 2.31e-04
+2022-05-06 15:19:40,172 INFO [train.py:715] (3/8) Epoch 9, batch 28700, loss[loss=0.1785, simple_loss=0.2356, pruned_loss=0.06073, over 4982.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2143, pruned_loss=0.03397, over 972543.66 frames.], batch size: 39, lr: 2.31e-04
+2022-05-06 15:20:19,621 INFO [train.py:715] (3/8) Epoch 9, batch 28750, loss[loss=0.156, simple_loss=0.2279, pruned_loss=0.04211, over 4868.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2136, pruned_loss=0.03349, over 973019.17 frames.], batch size: 22, lr: 2.31e-04
+2022-05-06 15:20:58,321 INFO [train.py:715] (3/8) Epoch 9, batch 28800, loss[loss=0.1348, simple_loss=0.205, pruned_loss=0.03235, over 4845.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2142, pruned_loss=0.03402, over 973156.99 frames.], batch size: 30, lr: 2.31e-04
+2022-05-06 15:21:36,720 INFO [train.py:715] (3/8) Epoch 9, batch 28850, loss[loss=0.1548, simple_loss=0.2195, pruned_loss=0.04505, over 4711.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2141, pruned_loss=0.03376, over 973131.13 frames.], batch size: 15, lr: 2.31e-04
+2022-05-06 15:22:16,104 INFO [train.py:715] (3/8) Epoch 9, batch 28900, loss[loss=0.1547, simple_loss=0.2231, pruned_loss=0.04317, over 4936.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2141, pruned_loss=0.03372, over 973296.49 frames.], batch size: 21, lr: 2.31e-04
+2022-05-06 15:22:55,368 INFO [train.py:715] (3/8) Epoch 9, batch 28950, loss[loss=0.1427, simple_loss=0.2217, pruned_loss=0.03178, over 4935.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2142, pruned_loss=0.0341, over 973448.69 frames.], batch size: 21, lr: 2.31e-04
+2022-05-06 15:23:33,684 INFO [train.py:715] (3/8) Epoch 9, batch 29000, loss[loss=0.1178, simple_loss=0.1921, pruned_loss=0.02177, over 4916.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03412, over 973769.58 frames.], batch size: 18, lr: 2.31e-04
+2022-05-06 15:24:12,156 INFO [train.py:715] (3/8) Epoch 9, batch 29050, loss[loss=0.1252, simple_loss=0.1945, pruned_loss=0.02797, over 4830.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03417, over 972842.05 frames.], batch size: 26, lr: 2.31e-04
+2022-05-06 15:24:51,100 INFO [train.py:715] (3/8) Epoch 9, batch 29100, loss[loss=0.1382, simple_loss=0.208, pruned_loss=0.03426, over 4644.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2143, pruned_loss=0.03418, over 972128.96 frames.], batch size: 13, lr: 2.31e-04
+2022-05-06 15:25:30,247 INFO [train.py:715] (3/8) Epoch 9, batch 29150, loss[loss=0.1629, simple_loss=0.2368, pruned_loss=0.04453, over 4936.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03379, over 972662.55 frames.], batch size: 39, lr: 2.31e-04
+2022-05-06 15:26:09,094 INFO [train.py:715] (3/8) Epoch 9, batch 29200, loss[loss=0.1615, simple_loss=0.2562, pruned_loss=0.03336, over 4803.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2139, pruned_loss=0.03371, over 972631.63 frames.], batch size: 25, lr: 2.31e-04
+2022-05-06 15:26:48,459 INFO [train.py:715] (3/8) Epoch 9, batch 29250, loss[loss=0.1517, simple_loss=0.2238, pruned_loss=0.03984, over 4964.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.03406, over 972523.66 frames.], batch size: 15, lr: 2.31e-04
+2022-05-06 15:27:27,197 INFO [train.py:715] (3/8) Epoch 9, batch 29300, loss[loss=0.1641, simple_loss=0.2309, pruned_loss=0.0487, over 4886.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03342, over 972386.14 frames.], batch size: 22, lr: 2.31e-04
+2022-05-06 15:28:06,267 INFO [train.py:715] (3/8) Epoch 9, batch 29350, loss[loss=0.1302, simple_loss=0.205, pruned_loss=0.02767, over 4787.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2138, pruned_loss=0.0337, over 971657.29 frames.], batch size: 21, lr: 2.31e-04
+2022-05-06 15:28:45,213 INFO [train.py:715] (3/8) Epoch 9, batch 29400, loss[loss=0.1419, simple_loss=0.2119, pruned_loss=0.03591, over 4796.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03391, over 971872.06 frames.], batch size: 21, lr: 2.31e-04
+2022-05-06 15:29:23,946 INFO [train.py:715] (3/8) Epoch 9, batch 29450, loss[loss=0.149, simple_loss=0.2246, pruned_loss=0.03673, over 4938.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2136, pruned_loss=0.03364, over 972289.47 frames.], batch size: 23, lr: 2.31e-04
+2022-05-06 15:30:02,407 INFO [train.py:715] (3/8) Epoch 9, batch 29500, loss[loss=0.1441, simple_loss=0.2215, pruned_loss=0.03337, over 4897.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03387, over 973211.30 frames.], batch size: 39, lr: 2.31e-04
+2022-05-06 15:30:41,339 INFO [train.py:715] (3/8) Epoch 9, batch 29550, loss[loss=0.1526, simple_loss=0.2362, pruned_loss=0.03452, over 4844.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2136, pruned_loss=0.03364, over 973842.72 frames.], batch size: 34, lr: 2.31e-04
+2022-05-06 15:31:20,278 INFO [train.py:715] (3/8) Epoch 9, batch 29600, loss[loss=0.114, simple_loss=0.1841, pruned_loss=0.02198, over 4937.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03381, over 973530.41 frames.], batch size: 23, lr: 2.31e-04
+2022-05-06 15:31:59,539 INFO [train.py:715] (3/8) Epoch 9, batch 29650, loss[loss=0.1281, simple_loss=0.2011, pruned_loss=0.0276, over 4760.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2145, pruned_loss=0.03443, over 973282.30 frames.], batch size: 19, lr: 2.31e-04
+2022-05-06 15:32:39,147 INFO [train.py:715] (3/8) Epoch 9, batch 29700, loss[loss=0.1721, simple_loss=0.2232, pruned_loss=0.06053, over 4824.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03455, over 973120.88 frames.], batch size: 15, lr: 2.31e-04
+2022-05-06 15:33:17,092 INFO [train.py:715] (3/8) Epoch 9, batch 29750, loss[loss=0.161, simple_loss=0.2298, pruned_loss=0.04605, over 4869.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03403, over 972631.81 frames.], batch size: 20, lr: 2.31e-04
+2022-05-06 15:33:55,773 INFO [train.py:715] (3/8) Epoch 9, batch 29800, loss[loss=0.1485, simple_loss=0.2203, pruned_loss=0.03837, over 4758.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03454, over 972723.58 frames.], batch size: 16, lr: 2.31e-04
+2022-05-06 15:34:34,892 INFO [train.py:715] (3/8) Epoch 9, batch 29850, loss[loss=0.128, simple_loss=0.2089, pruned_loss=0.02362, over 4955.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2131, pruned_loss=0.03393, over 973513.92 frames.], batch size: 24, lr: 2.31e-04
+2022-05-06 15:35:13,058 INFO [train.py:715] (3/8) Epoch 9, batch 29900, loss[loss=0.1748, simple_loss=0.2217, pruned_loss=0.06396, over 4849.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03448, over 973601.30 frames.], batch size: 15, lr: 2.31e-04
+2022-05-06 15:35:52,534 INFO [train.py:715] (3/8) Epoch 9, batch 29950, loss[loss=0.1617, simple_loss=0.2261, pruned_loss=0.04865, over 4763.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.0346, over 972913.58 frames.], batch size: 14, lr: 2.31e-04
+2022-05-06 15:36:31,406 INFO [train.py:715] (3/8) Epoch 9, batch 30000, loss[loss=0.1239, simple_loss=0.2087, pruned_loss=0.01958, over 4880.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03453, over 973139.17 frames.], batch size: 22, lr: 2.31e-04
+2022-05-06 15:36:31,406 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 15:36:40,918 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1911, pruned_loss=0.01124, over 914524.00 frames.
+2022-05-06 15:37:20,161 INFO [train.py:715] (3/8) Epoch 9, batch 30050, loss[loss=0.1367, simple_loss=0.199, pruned_loss=0.03723, over 4847.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.03498, over 974851.98 frames.], batch size: 12, lr: 2.31e-04
+2022-05-06 15:37:58,807 INFO [train.py:715] (3/8) Epoch 9, batch 30100, loss[loss=0.1495, simple_loss=0.2156, pruned_loss=0.04172, over 4823.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2146, pruned_loss=0.03502, over 974668.12 frames.], batch size: 13, lr: 2.31e-04
+2022-05-06 15:38:38,128 INFO [train.py:715] (3/8) Epoch 9, batch 30150, loss[loss=0.1661, simple_loss=0.2307, pruned_loss=0.05072, over 4775.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2142, pruned_loss=0.03508, over 973954.44 frames.], batch size: 12, lr: 2.31e-04
+2022-05-06 15:39:17,504 INFO [train.py:715] (3/8) Epoch 9, batch 30200, loss[loss=0.1396, simple_loss=0.2258, pruned_loss=0.02673, over 4971.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03471, over 974189.81 frames.], batch size: 23, lr: 2.31e-04
+2022-05-06 15:39:56,690 INFO [train.py:715] (3/8) Epoch 9, batch 30250, loss[loss=0.1417, simple_loss=0.2283, pruned_loss=0.02752, over 4760.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03461, over 974058.79 frames.], batch size: 19, lr: 2.31e-04
+2022-05-06 15:40:35,247 INFO [train.py:715] (3/8) Epoch 9, batch 30300, loss[loss=0.1261, simple_loss=0.2054, pruned_loss=0.02342, over 4970.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2148, pruned_loss=0.0349, over 973926.35 frames.], batch size: 24, lr: 2.31e-04
+2022-05-06 15:41:14,057 INFO [train.py:715] (3/8) Epoch 9, batch 30350, loss[loss=0.1418, simple_loss=0.2111, pruned_loss=0.03622, over 4831.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03469, over 973694.00 frames.], batch size: 15, lr: 2.31e-04
+2022-05-06 15:41:53,486 INFO [train.py:715] (3/8) Epoch 9, batch 30400, loss[loss=0.1263, simple_loss=0.1888, pruned_loss=0.03185, over 4845.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03454, over 973314.20 frames.], batch size: 13, lr: 2.31e-04
+2022-05-06 15:42:32,293 INFO [train.py:715] (3/8) Epoch 9, batch 30450, loss[loss=0.1248, simple_loss=0.2046, pruned_loss=0.02251, over 4874.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.03478, over 973505.65 frames.], batch size: 22, lr: 2.31e-04
+2022-05-06 15:43:10,918 INFO [train.py:715] (3/8) Epoch 9, batch 30500, loss[loss=0.1194, simple_loss=0.1988, pruned_loss=0.02004, over 4873.00 frames.], tot_loss[loss=0.141, simple_loss=0.2134, pruned_loss=0.03426, over 973303.95 frames.], batch size: 22, lr: 2.31e-04
+2022-05-06 15:43:49,987 INFO [train.py:715] (3/8) Epoch 9, batch 30550, loss[loss=0.1113, simple_loss=0.1847, pruned_loss=0.01896, over 4814.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.03433, over 973461.00 frames.], batch size: 21, lr: 2.31e-04
+2022-05-06 15:44:28,846 INFO [train.py:715] (3/8) Epoch 9, batch 30600, loss[loss=0.1463, simple_loss=0.2236, pruned_loss=0.0345, over 4825.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2128, pruned_loss=0.03399, over 973456.57 frames.], batch size: 15, lr: 2.31e-04
+2022-05-06 15:45:06,882 INFO [train.py:715] (3/8) Epoch 9, batch 30650, loss[loss=0.1784, simple_loss=0.239, pruned_loss=0.05893, over 4788.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2138, pruned_loss=0.03465, over 972928.16 frames.], batch size: 14, lr: 2.31e-04
+2022-05-06 15:45:45,882 INFO [train.py:715] (3/8) Epoch 9, batch 30700, loss[loss=0.1485, simple_loss=0.2307, pruned_loss=0.03308, over 4958.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2137, pruned_loss=0.03478, over 972555.03 frames.], batch size: 24, lr: 2.30e-04
+2022-05-06 15:46:27,570 INFO [train.py:715] (3/8) Epoch 9, batch 30750, loss[loss=0.1693, simple_loss=0.2425, pruned_loss=0.04809, over 4966.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03456, over 973131.46 frames.], batch size: 14, lr: 2.30e-04
+2022-05-06 15:47:06,258 INFO [train.py:715] (3/8) Epoch 9, batch 30800, loss[loss=0.1432, simple_loss=0.222, pruned_loss=0.03215, over 4785.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03485, over 972634.29 frames.], batch size: 17, lr: 2.30e-04
+2022-05-06 15:47:44,603 INFO [train.py:715] (3/8) Epoch 9, batch 30850, loss[loss=0.1282, simple_loss=0.211, pruned_loss=0.02271, over 4860.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03485, over 972318.92 frames.], batch size: 32, lr: 2.30e-04
+2022-05-06 15:48:23,858 INFO [train.py:715] (3/8) Epoch 9, batch 30900, loss[loss=0.1286, simple_loss=0.1996, pruned_loss=0.02876, over 4759.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.03488, over 972017.55 frames.], batch size: 19, lr: 2.30e-04
+2022-05-06 15:49:03,047 INFO [train.py:715] (3/8) Epoch 9, batch 30950, loss[loss=0.1236, simple_loss=0.193, pruned_loss=0.0271, over 4873.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03495, over 971482.49 frames.], batch size: 16, lr: 2.30e-04
+2022-05-06 15:49:41,535 INFO [train.py:715] (3/8) Epoch 9, batch 31000, loss[loss=0.151, simple_loss=0.2241, pruned_loss=0.03892, over 4854.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03498, over 972722.13 frames.], batch size: 30, lr: 2.30e-04
+2022-05-06 15:50:20,509 INFO [train.py:715] (3/8) Epoch 9, batch 31050, loss[loss=0.1463, simple_loss=0.222, pruned_loss=0.03529, over 4983.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.03492, over 973236.65 frames.], batch size: 14, lr: 2.30e-04
+2022-05-06 15:50:59,767 INFO [train.py:715] (3/8) Epoch 9, batch 31100, loss[loss=0.1475, simple_loss=0.2252, pruned_loss=0.03495, over 4957.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03468, over 972638.53 frames.], batch size: 15, lr: 2.30e-04
+2022-05-06 15:51:38,436 INFO [train.py:715] (3/8) Epoch 9, batch 31150, loss[loss=0.147, simple_loss=0.208, pruned_loss=0.043, over 4769.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03485, over 971568.51 frames.], batch size: 14, lr: 2.30e-04
+2022-05-06 15:52:17,019 INFO [train.py:715] (3/8) Epoch 9, batch 31200, loss[loss=0.129, simple_loss=0.2058, pruned_loss=0.02605, over 4943.00 frames.], tot_loss[loss=0.142, simple_loss=0.2148, pruned_loss=0.03466, over 971777.33 frames.], batch size: 21, lr: 2.30e-04
+2022-05-06 15:52:56,548 INFO [train.py:715] (3/8) Epoch 9, batch 31250, loss[loss=0.1289, simple_loss=0.1992, pruned_loss=0.02931, over 4826.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03439, over 971433.84 frames.], batch size: 26, lr: 2.30e-04
+2022-05-06 15:53:36,000 INFO [train.py:715] (3/8) Epoch 9, batch 31300, loss[loss=0.1886, simple_loss=0.2445, pruned_loss=0.06641, over 4760.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2152, pruned_loss=0.03454, over 972258.50 frames.], batch size: 18, lr: 2.30e-04
+2022-05-06 15:54:14,967 INFO [train.py:715] (3/8) Epoch 9, batch 31350, loss[loss=0.1139, simple_loss=0.1916, pruned_loss=0.01814, over 4804.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2149, pruned_loss=0.03445, over 972474.17 frames.], batch size: 25, lr: 2.30e-04
+2022-05-06 15:54:53,758 INFO [train.py:715] (3/8) Epoch 9, batch 31400, loss[loss=0.1546, simple_loss=0.2307, pruned_loss=0.03929, over 4869.00 frames.], tot_loss[loss=0.1417, simple_loss=0.215, pruned_loss=0.03417, over 972904.68 frames.], batch size: 20, lr: 2.30e-04
+2022-05-06 15:55:32,701 INFO [train.py:715] (3/8) Epoch 9, batch 31450, loss[loss=0.1198, simple_loss=0.1931, pruned_loss=0.02327, over 4783.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2151, pruned_loss=0.0341, over 973619.48 frames.], batch size: 18, lr: 2.30e-04
+2022-05-06 15:56:11,771 INFO [train.py:715] (3/8) Epoch 9, batch 31500, loss[loss=0.1398, simple_loss=0.2133, pruned_loss=0.03318, over 4853.00 frames.], tot_loss[loss=0.141, simple_loss=0.2146, pruned_loss=0.03365, over 973911.24 frames.], batch size: 13, lr: 2.30e-04
+2022-05-06 15:56:50,181 INFO [train.py:715] (3/8) Epoch 9, batch 31550, loss[loss=0.1451, simple_loss=0.2157, pruned_loss=0.03723, over 4912.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2143, pruned_loss=0.03379, over 973043.36 frames.], batch size: 18, lr: 2.30e-04
+2022-05-06 15:57:29,719 INFO [train.py:715] (3/8) Epoch 9, batch 31600, loss[loss=0.1688, simple_loss=0.2469, pruned_loss=0.04533, over 4921.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2142, pruned_loss=0.03378, over 973856.28 frames.], batch size: 29, lr: 2.30e-04
+2022-05-06 15:58:09,723 INFO [train.py:715] (3/8) Epoch 9, batch 31650, loss[loss=0.1309, simple_loss=0.2048, pruned_loss=0.02845, over 4991.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03363, over 973914.62 frames.], batch size: 20, lr: 2.30e-04
+2022-05-06 15:58:48,439 INFO [train.py:715] (3/8) Epoch 9, batch 31700, loss[loss=0.1394, simple_loss=0.2237, pruned_loss=0.0275, over 4922.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2147, pruned_loss=0.03404, over 973956.61 frames.], batch size: 19, lr: 2.30e-04
+2022-05-06 15:59:27,453 INFO [train.py:715] (3/8) Epoch 9, batch 31750, loss[loss=0.1236, simple_loss=0.1968, pruned_loss=0.02521, over 4771.00 frames.], tot_loss[loss=0.142, simple_loss=0.2152, pruned_loss=0.03439, over 974662.62 frames.], batch size: 12, lr: 2.30e-04
+2022-05-06 16:00:06,077 INFO [train.py:715] (3/8) Epoch 9, batch 31800, loss[loss=0.104, simple_loss=0.1905, pruned_loss=0.008783, over 4883.00 frames.], tot_loss[loss=0.1409, simple_loss=0.214, pruned_loss=0.03387, over 973998.46 frames.], batch size: 16, lr: 2.30e-04
+2022-05-06 16:00:45,144 INFO [train.py:715] (3/8) Epoch 9, batch 31850, loss[loss=0.1382, simple_loss=0.2121, pruned_loss=0.03213, over 4855.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03379, over 973247.39 frames.], batch size: 20, lr: 2.30e-04
+2022-05-06 16:01:23,638 INFO [train.py:715] (3/8) Epoch 9, batch 31900, loss[loss=0.1358, simple_loss=0.1989, pruned_loss=0.03635, over 4966.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03419, over 973699.61 frames.], batch size: 15, lr: 2.30e-04
+2022-05-06 16:02:02,943 INFO [train.py:715] (3/8) Epoch 9, batch 31950, loss[loss=0.1663, simple_loss=0.2458, pruned_loss=0.04343, over 4909.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03436, over 973393.51 frames.], batch size: 17, lr: 2.30e-04
+2022-05-06 16:02:42,216 INFO [train.py:715] (3/8) Epoch 9, batch 32000, loss[loss=0.1335, simple_loss=0.1976, pruned_loss=0.03465, over 4815.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03404, over 972969.10 frames.], batch size: 13, lr: 2.30e-04
+2022-05-06 16:03:20,779 INFO [train.py:715] (3/8) Epoch 9, batch 32050, loss[loss=0.1619, simple_loss=0.2261, pruned_loss=0.0488, over 4854.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03391, over 972705.29 frames.], batch size: 30, lr: 2.30e-04
+2022-05-06 16:03:59,265 INFO [train.py:715] (3/8) Epoch 9, batch 32100, loss[loss=0.1224, simple_loss=0.1976, pruned_loss=0.02355, over 4740.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03385, over 973058.93 frames.], batch size: 16, lr: 2.30e-04
+2022-05-06 16:04:38,260 INFO [train.py:715] (3/8) Epoch 9, batch 32150, loss[loss=0.1613, simple_loss=0.2315, pruned_loss=0.04552, over 4780.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03397, over 973281.14 frames.], batch size: 17, lr: 2.30e-04
+2022-05-06 16:05:17,702 INFO [train.py:715] (3/8) Epoch 9, batch 32200, loss[loss=0.1386, simple_loss=0.21, pruned_loss=0.03355, over 4846.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.0338, over 973044.12 frames.], batch size: 15, lr: 2.30e-04
+2022-05-06 16:05:55,461 INFO [train.py:715] (3/8) Epoch 9, batch 32250, loss[loss=0.1188, simple_loss=0.1916, pruned_loss=0.02298, over 4992.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03422, over 973376.72 frames.], batch size: 14, lr: 2.30e-04
+2022-05-06 16:06:34,666 INFO [train.py:715] (3/8) Epoch 9, batch 32300, loss[loss=0.1459, simple_loss=0.2074, pruned_loss=0.04217, over 4945.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03451, over 972681.81 frames.], batch size: 35, lr: 2.30e-04
+2022-05-06 16:07:13,842 INFO [train.py:715] (3/8) Epoch 9, batch 32350, loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03143, over 4914.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.03428, over 971961.85 frames.], batch size: 23, lr: 2.30e-04
+2022-05-06 16:07:52,332 INFO [train.py:715] (3/8) Epoch 9, batch 32400, loss[loss=0.1467, simple_loss=0.2186, pruned_loss=0.03746, over 4976.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03466, over 972016.17 frames.], batch size: 35, lr: 2.30e-04
+2022-05-06 16:08:31,415 INFO [train.py:715] (3/8) Epoch 9, batch 32450, loss[loss=0.1199, simple_loss=0.1945, pruned_loss=0.02269, over 4953.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03437, over 972552.95 frames.], batch size: 24, lr: 2.30e-04
+2022-05-06 16:09:10,515 INFO [train.py:715] (3/8) Epoch 9, batch 32500, loss[loss=0.1135, simple_loss=0.1748, pruned_loss=0.02612, over 4738.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2129, pruned_loss=0.03426, over 972062.54 frames.], batch size: 16, lr: 2.30e-04
+2022-05-06 16:09:49,359 INFO [train.py:715] (3/8) Epoch 9, batch 32550, loss[loss=0.1353, simple_loss=0.2119, pruned_loss=0.02935, over 4870.00 frames.], tot_loss[loss=0.14, simple_loss=0.2124, pruned_loss=0.03375, over 971754.97 frames.], batch size: 16, lr: 2.30e-04
+2022-05-06 16:10:27,861 INFO [train.py:715] (3/8) Epoch 9, batch 32600, loss[loss=0.1551, simple_loss=0.2296, pruned_loss=0.04031, over 4834.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2135, pruned_loss=0.03435, over 971753.21 frames.], batch size: 15, lr: 2.30e-04
+2022-05-06 16:11:06,892 INFO [train.py:715] (3/8) Epoch 9, batch 32650, loss[loss=0.1307, simple_loss=0.2061, pruned_loss=0.02771, over 4967.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03463, over 971224.38 frames.], batch size: 35, lr: 2.30e-04
+2022-05-06 16:11:45,873 INFO [train.py:715] (3/8) Epoch 9, batch 32700, loss[loss=0.1268, simple_loss=0.2029, pruned_loss=0.02538, over 4896.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03435, over 971433.29 frames.], batch size: 17, lr: 2.30e-04
+2022-05-06 16:12:24,794 INFO [train.py:715] (3/8) Epoch 9, batch 32750, loss[loss=0.1377, simple_loss=0.2135, pruned_loss=0.03088, over 4792.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03421, over 972614.62 frames.], batch size: 24, lr: 2.30e-04
+2022-05-06 16:13:03,521 INFO [train.py:715] (3/8) Epoch 9, batch 32800, loss[loss=0.1393, simple_loss=0.2099, pruned_loss=0.03433, over 4803.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03433, over 972366.85 frames.], batch size: 21, lr: 2.30e-04
+2022-05-06 16:13:42,563 INFO [train.py:715] (3/8) Epoch 9, batch 32850, loss[loss=0.1358, simple_loss=0.2035, pruned_loss=0.0341, over 4789.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03417, over 971230.95 frames.], batch size: 17, lr: 2.30e-04
+2022-05-06 16:14:21,301 INFO [train.py:715] (3/8) Epoch 9, batch 32900, loss[loss=0.1462, simple_loss=0.22, pruned_loss=0.03626, over 4943.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03455, over 971680.94 frames.], batch size: 21, lr: 2.30e-04
+2022-05-06 16:14:59,681 INFO [train.py:715] (3/8) Epoch 9, batch 32950, loss[loss=0.1581, simple_loss=0.2294, pruned_loss=0.04339, over 4973.00 frames.], tot_loss[loss=0.142, simple_loss=0.2151, pruned_loss=0.03445, over 971578.87 frames.], batch size: 35, lr: 2.30e-04
+2022-05-06 16:15:38,639 INFO [train.py:715] (3/8) Epoch 9, batch 33000, loss[loss=0.1051, simple_loss=0.1732, pruned_loss=0.0185, over 4811.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.0351, over 972176.19 frames.], batch size: 12, lr: 2.30e-04
+2022-05-06 16:15:38,640 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 16:15:48,000 INFO [train.py:742] (3/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1913, pruned_loss=0.01119, over 914524.00 frames.
+2022-05-06 16:16:27,265 INFO [train.py:715] (3/8) Epoch 9, batch 33050, loss[loss=0.1754, simple_loss=0.2422, pruned_loss=0.05429, over 4838.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03504, over 972346.31 frames.], batch size: 15, lr: 2.30e-04
+2022-05-06 16:17:06,454 INFO [train.py:715] (3/8) Epoch 9, batch 33100, loss[loss=0.1532, simple_loss=0.2301, pruned_loss=0.03816, over 4938.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03448, over 972735.49 frames.], batch size: 29, lr: 2.30e-04
+2022-05-06 16:17:45,626 INFO [train.py:715] (3/8) Epoch 9, batch 33150, loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03612, over 4823.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03414, over 972782.15 frames.], batch size: 13, lr: 2.30e-04
+2022-05-06 16:18:25,451 INFO [train.py:715] (3/8) Epoch 9, batch 33200, loss[loss=0.1262, simple_loss=0.2068, pruned_loss=0.02283, over 4774.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03383, over 972050.68 frames.], batch size: 14, lr: 2.30e-04
+2022-05-06 16:19:04,995 INFO [train.py:715] (3/8) Epoch 9, batch 33250, loss[loss=0.1295, simple_loss=0.2004, pruned_loss=0.02926, over 4918.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03356, over 972297.77 frames.], batch size: 18, lr: 2.30e-04
+2022-05-06 16:19:44,054 INFO [train.py:715] (3/8) Epoch 9, batch 33300, loss[loss=0.1269, simple_loss=0.2102, pruned_loss=0.02181, over 4942.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03381, over 972502.93 frames.], batch size: 29, lr: 2.30e-04
+2022-05-06 16:20:23,550 INFO [train.py:715] (3/8) Epoch 9, batch 33350, loss[loss=0.1515, simple_loss=0.2225, pruned_loss=0.04024, over 4833.00 frames.], tot_loss[loss=0.141, simple_loss=0.2145, pruned_loss=0.03373, over 971976.22 frames.], batch size: 30, lr: 2.30e-04
+2022-05-06 16:21:03,298 INFO [train.py:715] (3/8) Epoch 9, batch 33400, loss[loss=0.1541, simple_loss=0.2286, pruned_loss=0.03979, over 4828.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2144, pruned_loss=0.03418, over 972321.20 frames.], batch size: 25, lr: 2.30e-04
+2022-05-06 16:21:43,052 INFO [train.py:715] (3/8) Epoch 9, batch 33450, loss[loss=0.1468, simple_loss=0.2221, pruned_loss=0.03574, over 4735.00 frames.], tot_loss[loss=0.1418, simple_loss=0.215, pruned_loss=0.03428, over 972934.13 frames.], batch size: 16, lr: 2.30e-04
+2022-05-06 16:22:22,075 INFO [train.py:715] (3/8) Epoch 9, batch 33500, loss[loss=0.1505, simple_loss=0.2207, pruned_loss=0.04015, over 4897.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2142, pruned_loss=0.03373, over 972570.86 frames.], batch size: 22, lr: 2.30e-04
+2022-05-06 16:23:00,825 INFO [train.py:715] (3/8) Epoch 9, batch 33550, loss[loss=0.1465, simple_loss=0.2244, pruned_loss=0.03425, over 4789.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2141, pruned_loss=0.0337, over 973085.48 frames.], batch size: 17, lr: 2.30e-04
+2022-05-06 16:23:40,548 INFO [train.py:715] (3/8) Epoch 9, batch 33600, loss[loss=0.1321, simple_loss=0.2058, pruned_loss=0.02918, over 4741.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03353, over 972967.43 frames.], batch size: 16, lr: 2.30e-04
+2022-05-06 16:24:19,324 INFO [train.py:715] (3/8) Epoch 9, batch 33650, loss[loss=0.132, simple_loss=0.2093, pruned_loss=0.0274, over 4911.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03369, over 972867.68 frames.], batch size: 19, lr: 2.30e-04
+2022-05-06 16:24:58,232 INFO [train.py:715] (3/8) Epoch 9, batch 33700, loss[loss=0.1363, simple_loss=0.2087, pruned_loss=0.03196, over 4895.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2124, pruned_loss=0.03345, over 972979.44 frames.], batch size: 38, lr: 2.29e-04
+2022-05-06 16:25:37,408 INFO [train.py:715] (3/8) Epoch 9, batch 33750, loss[loss=0.1323, simple_loss=0.2102, pruned_loss=0.0272, over 4875.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2126, pruned_loss=0.03402, over 972117.62 frames.], batch size: 22, lr: 2.29e-04
+2022-05-06 16:26:16,198 INFO [train.py:715] (3/8) Epoch 9, batch 33800, loss[loss=0.1722, simple_loss=0.2387, pruned_loss=0.05288, over 4898.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2133, pruned_loss=0.03463, over 972687.55 frames.], batch size: 19, lr: 2.29e-04
+2022-05-06 16:26:54,913 INFO [train.py:715] (3/8) Epoch 9, batch 33850, loss[loss=0.1309, simple_loss=0.2008, pruned_loss=0.03049, over 4914.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03462, over 972539.97 frames.], batch size: 17, lr: 2.29e-04
+2022-05-06 16:27:33,756 INFO [train.py:715] (3/8) Epoch 9, batch 33900, loss[loss=0.1137, simple_loss=0.193, pruned_loss=0.01719, over 4965.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03467, over 972687.50 frames.], batch size: 24, lr: 2.29e-04
+2022-05-06 16:28:13,482 INFO [train.py:715] (3/8) Epoch 9, batch 33950, loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03108, over 4970.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03437, over 972059.77 frames.], batch size: 24, lr: 2.29e-04
+2022-05-06 16:28:52,282 INFO [train.py:715] (3/8) Epoch 9, batch 34000, loss[loss=0.1149, simple_loss=0.1969, pruned_loss=0.01648, over 4814.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2136, pruned_loss=0.03456, over 971168.57 frames.], batch size: 25, lr: 2.29e-04
+2022-05-06 16:29:31,512 INFO [train.py:715] (3/8) Epoch 9, batch 34050, loss[loss=0.1426, simple_loss=0.2095, pruned_loss=0.03783, over 4894.00 frames.], tot_loss[loss=0.1408, simple_loss=0.213, pruned_loss=0.03428, over 971369.34 frames.], batch size: 19, lr: 2.29e-04
+2022-05-06 16:30:09,974 INFO [train.py:715] (3/8) Epoch 9, batch 34100, loss[loss=0.1426, simple_loss=0.2205, pruned_loss=0.03231, over 4774.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2133, pruned_loss=0.03424, over 971436.13 frames.], batch size: 18, lr: 2.29e-04
+2022-05-06 16:30:49,071 INFO [train.py:715] (3/8) Epoch 9, batch 34150, loss[loss=0.1493, simple_loss=0.2329, pruned_loss=0.03285, over 4965.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03413, over 971922.90 frames.], batch size: 35, lr: 2.29e-04
+2022-05-06 16:31:27,540 INFO [train.py:715] (3/8) Epoch 9, batch 34200, loss[loss=0.1358, simple_loss=0.2147, pruned_loss=0.02849, over 4973.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2127, pruned_loss=0.03373, over 971637.05 frames.], batch size: 24, lr: 2.29e-04
+2022-05-06 16:32:05,776 INFO [train.py:715] (3/8) Epoch 9, batch 34250, loss[loss=0.1241, simple_loss=0.2077, pruned_loss=0.02028, over 4774.00 frames.], tot_loss[loss=0.1405, simple_loss=0.213, pruned_loss=0.03403, over 972676.64 frames.], batch size: 14, lr: 2.29e-04
+2022-05-06 16:32:45,093 INFO [train.py:715] (3/8) Epoch 9, batch 34300, loss[loss=0.145, simple_loss=0.2223, pruned_loss=0.03381, over 4987.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03465, over 971882.23 frames.], batch size: 28, lr: 2.29e-04
+2022-05-06 16:33:23,849 INFO [train.py:715] (3/8) Epoch 9, batch 34350, loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03317, over 4813.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03413, over 972085.36 frames.], batch size: 13, lr: 2.29e-04
+2022-05-06 16:34:02,524 INFO [train.py:715] (3/8) Epoch 9, batch 34400, loss[loss=0.1442, simple_loss=0.2171, pruned_loss=0.03569, over 4875.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03401, over 972179.01 frames.], batch size: 19, lr: 2.29e-04
+2022-05-06 16:34:41,409 INFO [train.py:715] (3/8) Epoch 9, batch 34450, loss[loss=0.1095, simple_loss=0.1858, pruned_loss=0.01655, over 4794.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2141, pruned_loss=0.0344, over 972431.00 frames.], batch size: 24, lr: 2.29e-04
+2022-05-06 16:35:20,339 INFO [train.py:715] (3/8) Epoch 9, batch 34500, loss[loss=0.1376, simple_loss=0.2256, pruned_loss=0.0248, over 4917.00 frames.], tot_loss[loss=0.141, simple_loss=0.2141, pruned_loss=0.03396, over 972548.73 frames.], batch size: 17, lr: 2.29e-04
+2022-05-06 16:35:59,375 INFO [train.py:715] (3/8) Epoch 9, batch 34550, loss[loss=0.125, simple_loss=0.2029, pruned_loss=0.0235, over 4943.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2149, pruned_loss=0.03396, over 972324.70 frames.], batch size: 21, lr: 2.29e-04
+2022-05-06 16:36:38,005 INFO [train.py:715] (3/8) Epoch 9, batch 34600, loss[loss=0.1192, simple_loss=0.1934, pruned_loss=0.02249, over 4744.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2144, pruned_loss=0.03374, over 971654.42 frames.], batch size: 16, lr: 2.29e-04
+2022-05-06 16:37:17,108 INFO [train.py:715] (3/8) Epoch 9, batch 34650, loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.04078, over 4829.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03387, over 972404.88 frames.], batch size: 13, lr: 2.29e-04
+2022-05-06 16:37:56,492 INFO [train.py:715] (3/8) Epoch 9, batch 34700, loss[loss=0.1491, simple_loss=0.2273, pruned_loss=0.03548, over 4987.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.0339, over 972311.82 frames.], batch size: 14, lr: 2.29e-04
+2022-05-06 16:38:34,790 INFO [train.py:715] (3/8) Epoch 9, batch 34750, loss[loss=0.1182, simple_loss=0.1919, pruned_loss=0.02226, over 4819.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03363, over 972612.97 frames.], batch size: 12, lr: 2.29e-04
+2022-05-06 16:39:12,243 INFO [train.py:715] (3/8) Epoch 9, batch 34800, loss[loss=0.09412, simple_loss=0.168, pruned_loss=0.01013, over 4780.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2119, pruned_loss=0.03381, over 972613.69 frames.], batch size: 12, lr: 2.29e-04
+2022-05-06 16:40:01,154 INFO [train.py:715] (3/8) Epoch 10, batch 0, loss[loss=0.1583, simple_loss=0.2438, pruned_loss=0.0364, over 4761.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2438, pruned_loss=0.0364, over 4761.00 frames.], batch size: 19, lr: 2.19e-04
+2022-05-06 16:40:41,026 INFO [train.py:715] (3/8) Epoch 10, batch 50, loss[loss=0.133, simple_loss=0.2092, pruned_loss=0.02839, over 4975.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2145, pruned_loss=0.03354, over 218997.82 frames.], batch size: 15, lr: 2.19e-04
+2022-05-06 16:41:20,752 INFO [train.py:715] (3/8) Epoch 10, batch 100, loss[loss=0.1481, simple_loss=0.2126, pruned_loss=0.04179, over 4970.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03293, over 386769.53 frames.], batch size: 35, lr: 2.19e-04
+2022-05-06 16:42:00,747 INFO [train.py:715] (3/8) Epoch 10, batch 150, loss[loss=0.1508, simple_loss=0.2277, pruned_loss=0.03693, over 4973.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03335, over 516755.36 frames.], batch size: 14, lr: 2.19e-04
+2022-05-06 16:42:41,342 INFO [train.py:715] (3/8) Epoch 10, batch 200, loss[loss=0.1456, simple_loss=0.2233, pruned_loss=0.03395, over 4830.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03332, over 618885.28 frames.], batch size: 15, lr: 2.19e-04
+2022-05-06 16:43:22,397 INFO [train.py:715] (3/8) Epoch 10, batch 250, loss[loss=0.1244, simple_loss=0.1953, pruned_loss=0.02677, over 4772.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.0335, over 697639.97 frames.], batch size: 18, lr: 2.19e-04
+2022-05-06 16:44:03,221 INFO [train.py:715] (3/8) Epoch 10, batch 300, loss[loss=0.1192, simple_loss=0.2035, pruned_loss=0.01747, over 4866.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03369, over 758279.61 frames.], batch size: 16, lr: 2.19e-04
+2022-05-06 16:44:43,669 INFO [train.py:715] (3/8) Epoch 10, batch 350, loss[loss=0.1429, simple_loss=0.2149, pruned_loss=0.03548, over 4874.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.0339, over 805058.58 frames.], batch size: 32, lr: 2.19e-04
+2022-05-06 16:45:25,023 INFO [train.py:715] (3/8) Epoch 10, batch 400, loss[loss=0.1431, simple_loss=0.2205, pruned_loss=0.03282, over 4799.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03446, over 842579.37 frames.], batch size: 21, lr: 2.19e-04
+2022-05-06 16:46:06,713 INFO [train.py:715] (3/8) Epoch 10, batch 450, loss[loss=0.1197, simple_loss=0.1937, pruned_loss=0.02285, over 4804.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03444, over 871094.67 frames.], batch size: 14, lr: 2.19e-04
+2022-05-06 16:46:47,445 INFO [train.py:715] (3/8) Epoch 10, batch 500, loss[loss=0.128, simple_loss=0.2021, pruned_loss=0.02695, over 4967.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.0341, over 892837.88 frames.], batch size: 14, lr: 2.19e-04
+2022-05-06 16:47:28,879 INFO [train.py:715] (3/8) Epoch 10, batch 550, loss[loss=0.1458, simple_loss=0.2164, pruned_loss=0.03757, over 4871.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.0341, over 910738.02 frames.], batch size: 16, lr: 2.19e-04
+2022-05-06 16:48:10,021 INFO [train.py:715] (3/8) Epoch 10, batch 600, loss[loss=0.1118, simple_loss=0.186, pruned_loss=0.01883, over 4822.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03434, over 924602.19 frames.], batch size: 12, lr: 2.19e-04
+2022-05-06 16:48:50,532 INFO [train.py:715] (3/8) Epoch 10, batch 650, loss[loss=0.1152, simple_loss=0.1885, pruned_loss=0.0209, over 4747.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03462, over 935700.45 frames.], batch size: 16, lr: 2.19e-04
+2022-05-06 16:49:31,189 INFO [train.py:715] (3/8) Epoch 10, batch 700, loss[loss=0.1553, simple_loss=0.2306, pruned_loss=0.04003, over 4954.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03411, over 943944.88 frames.], batch size: 24, lr: 2.19e-04
+2022-05-06 16:50:12,725 INFO [train.py:715] (3/8) Epoch 10, batch 750, loss[loss=0.1643, simple_loss=0.2369, pruned_loss=0.04584, over 4692.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03424, over 950403.28 frames.], batch size: 15, lr: 2.19e-04
+2022-05-06 16:50:54,001 INFO [train.py:715] (3/8) Epoch 10, batch 800, loss[loss=0.1183, simple_loss=0.1974, pruned_loss=0.01957, over 4934.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2136, pruned_loss=0.03404, over 955468.32 frames.], batch size: 23, lr: 2.19e-04
+2022-05-06 16:51:34,424 INFO [train.py:715] (3/8) Epoch 10, batch 850, loss[loss=0.1421, simple_loss=0.2306, pruned_loss=0.0268, over 4960.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03382, over 958702.41 frames.], batch size: 21, lr: 2.19e-04
+2022-05-06 16:52:15,219 INFO [train.py:715] (3/8) Epoch 10, batch 900, loss[loss=0.1328, simple_loss=0.2035, pruned_loss=0.03109, over 4985.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03324, over 962002.63 frames.], batch size: 25, lr: 2.19e-04
+2022-05-06 16:52:55,739 INFO [train.py:715] (3/8) Epoch 10, batch 950, loss[loss=0.1283, simple_loss=0.2053, pruned_loss=0.0256, over 4829.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03364, over 964459.57 frames.], batch size: 26, lr: 2.19e-04
+2022-05-06 16:53:35,735 INFO [train.py:715] (3/8) Epoch 10, batch 1000, loss[loss=0.1504, simple_loss=0.225, pruned_loss=0.03795, over 4843.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03387, over 966755.66 frames.], batch size: 30, lr: 2.19e-04
+2022-05-06 16:54:14,958 INFO [train.py:715] (3/8) Epoch 10, batch 1050, loss[loss=0.1636, simple_loss=0.2376, pruned_loss=0.04483, over 4790.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2132, pruned_loss=0.03417, over 967071.37 frames.], batch size: 17, lr: 2.19e-04
+2022-05-06 16:54:55,332 INFO [train.py:715] (3/8) Epoch 10, batch 1100, loss[loss=0.2035, simple_loss=0.2623, pruned_loss=0.07235, over 4787.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03444, over 968221.64 frames.], batch size: 18, lr: 2.19e-04
+2022-05-06 16:55:34,626 INFO [train.py:715] (3/8) Epoch 10, batch 1150, loss[loss=0.1421, simple_loss=0.2174, pruned_loss=0.03338, over 4958.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.0344, over 969308.38 frames.], batch size: 24, lr: 2.19e-04
+2022-05-06 16:56:13,831 INFO [train.py:715] (3/8) Epoch 10, batch 1200, loss[loss=0.133, simple_loss=0.2039, pruned_loss=0.03105, over 4841.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.03467, over 970196.09 frames.], batch size: 25, lr: 2.19e-04
+2022-05-06 16:56:53,600 INFO [train.py:715] (3/8) Epoch 10, batch 1250, loss[loss=0.1471, simple_loss=0.2178, pruned_loss=0.03823, over 4983.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.03507, over 970606.68 frames.], batch size: 31, lr: 2.19e-04
+2022-05-06 16:57:32,225 INFO [train.py:715] (3/8) Epoch 10, batch 1300, loss[loss=0.1275, simple_loss=0.1955, pruned_loss=0.0297, over 4937.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2146, pruned_loss=0.03454, over 971065.09 frames.], batch size: 18, lr: 2.19e-04
+2022-05-06 16:58:11,021 INFO [train.py:715] (3/8) Epoch 10, batch 1350, loss[loss=0.1583, simple_loss=0.2222, pruned_loss=0.0472, over 4888.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.0351, over 971156.90 frames.], batch size: 39, lr: 2.19e-04
+2022-05-06 16:58:49,194 INFO [train.py:715] (3/8) Epoch 10, batch 1400, loss[loss=0.1483, simple_loss=0.2263, pruned_loss=0.03517, over 4891.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03462, over 971482.42 frames.], batch size: 22, lr: 2.19e-04
+2022-05-06 16:59:28,743 INFO [train.py:715] (3/8) Epoch 10, batch 1450, loss[loss=0.1533, simple_loss=0.2152, pruned_loss=0.04571, over 4765.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.0348, over 972577.22 frames.], batch size: 19, lr: 2.19e-04
+2022-05-06 17:00:07,718 INFO [train.py:715] (3/8) Epoch 10, batch 1500, loss[loss=0.1573, simple_loss=0.2188, pruned_loss=0.04792, over 4860.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.0343, over 972872.24 frames.], batch size: 32, lr: 2.19e-04
+2022-05-06 17:00:46,474 INFO [train.py:715] (3/8) Epoch 10, batch 1550, loss[loss=0.1172, simple_loss=0.1896, pruned_loss=0.02238, over 4981.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03371, over 972454.44 frames.], batch size: 28, lr: 2.19e-04
+2022-05-06 17:01:25,570 INFO [train.py:715] (3/8) Epoch 10, batch 1600, loss[loss=0.1414, simple_loss=0.2272, pruned_loss=0.02786, over 4957.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.0342, over 972659.41 frames.], batch size: 24, lr: 2.19e-04
+2022-05-06 17:02:04,987 INFO [train.py:715] (3/8) Epoch 10, batch 1650, loss[loss=0.1423, simple_loss=0.2101, pruned_loss=0.03729, over 4923.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03472, over 973098.73 frames.], batch size: 23, lr: 2.19e-04
+2022-05-06 17:02:43,710 INFO [train.py:715] (3/8) Epoch 10, batch 1700, loss[loss=0.171, simple_loss=0.2542, pruned_loss=0.0439, over 4952.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03423, over 973600.47 frames.], batch size: 15, lr: 2.19e-04
+2022-05-06 17:03:22,054 INFO [train.py:715] (3/8) Epoch 10, batch 1750, loss[loss=0.1357, simple_loss=0.2061, pruned_loss=0.03271, over 4983.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03454, over 973889.48 frames.], batch size: 15, lr: 2.19e-04
+2022-05-06 17:04:02,177 INFO [train.py:715] (3/8) Epoch 10, batch 1800, loss[loss=0.1434, simple_loss=0.2194, pruned_loss=0.03373, over 4873.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03414, over 973302.10 frames.], batch size: 38, lr: 2.19e-04
+2022-05-06 17:04:41,814 INFO [train.py:715] (3/8) Epoch 10, batch 1850, loss[loss=0.1173, simple_loss=0.1909, pruned_loss=0.02188, over 4841.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03413, over 973915.52 frames.], batch size: 13, lr: 2.19e-04
+2022-05-06 17:05:20,555 INFO [train.py:715] (3/8) Epoch 10, batch 1900, loss[loss=0.1582, simple_loss=0.2187, pruned_loss=0.04888, over 4961.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2138, pruned_loss=0.03469, over 973353.52 frames.], batch size: 35, lr: 2.19e-04
+2022-05-06 17:05:59,511 INFO [train.py:715] (3/8) Epoch 10, batch 1950, loss[loss=0.1558, simple_loss=0.2202, pruned_loss=0.04572, over 4792.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2135, pruned_loss=0.03455, over 973551.74 frames.], batch size: 17, lr: 2.18e-04
+2022-05-06 17:06:39,837 INFO [train.py:715] (3/8) Epoch 10, batch 2000, loss[loss=0.1311, simple_loss=0.2113, pruned_loss=0.02545, over 4763.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03458, over 973230.15 frames.], batch size: 19, lr: 2.18e-04
+2022-05-06 17:07:19,134 INFO [train.py:715] (3/8) Epoch 10, batch 2050, loss[loss=0.1635, simple_loss=0.2409, pruned_loss=0.043, over 4775.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2162, pruned_loss=0.03552, over 972305.71 frames.], batch size: 16, lr: 2.18e-04
+2022-05-06 17:07:57,715 INFO [train.py:715] (3/8) Epoch 10, batch 2100, loss[loss=0.1376, simple_loss=0.2052, pruned_loss=0.03495, over 4700.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.0351, over 972304.40 frames.], batch size: 15, lr: 2.18e-04
+2022-05-06 17:08:37,351 INFO [train.py:715] (3/8) Epoch 10, batch 2150, loss[loss=0.1458, simple_loss=0.2285, pruned_loss=0.03157, over 4804.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03499, over 971363.84 frames.], batch size: 25, lr: 2.18e-04
+2022-05-06 17:09:16,489 INFO [train.py:715] (3/8) Epoch 10, batch 2200, loss[loss=0.1204, simple_loss=0.2005, pruned_loss=0.02018, over 4826.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03484, over 972544.37 frames.], batch size: 26, lr: 2.18e-04
+2022-05-06 17:09:55,196 INFO [train.py:715] (3/8) Epoch 10, batch 2250, loss[loss=0.1221, simple_loss=0.1934, pruned_loss=0.02541, over 4751.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03418, over 972681.00 frames.], batch size: 19, lr: 2.18e-04
+2022-05-06 17:10:33,967 INFO [train.py:715] (3/8) Epoch 10, batch 2300, loss[loss=0.1282, simple_loss=0.2059, pruned_loss=0.02524, over 4817.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.034, over 973080.54 frames.], batch size: 15, lr: 2.18e-04
+2022-05-06 17:11:13,698 INFO [train.py:715] (3/8) Epoch 10, batch 2350, loss[loss=0.1528, simple_loss=0.2239, pruned_loss=0.04092, over 4924.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03431, over 972973.25 frames.], batch size: 18, lr: 2.18e-04
+2022-05-06 17:11:52,499 INFO [train.py:715] (3/8) Epoch 10, batch 2400, loss[loss=0.1287, simple_loss=0.2102, pruned_loss=0.02361, over 4951.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.0338, over 972650.00 frames.], batch size: 39, lr: 2.18e-04
+2022-05-06 17:12:31,235 INFO [train.py:715] (3/8) Epoch 10, batch 2450, loss[loss=0.1708, simple_loss=0.2338, pruned_loss=0.05386, over 4780.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2132, pruned_loss=0.03409, over 971838.64 frames.], batch size: 17, lr: 2.18e-04
+2022-05-06 17:13:10,537 INFO [train.py:715] (3/8) Epoch 10, batch 2500, loss[loss=0.1319, simple_loss=0.2096, pruned_loss=0.02709, over 4755.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03414, over 971470.22 frames.], batch size: 19, lr: 2.18e-04
+2022-05-06 17:13:49,922 INFO [train.py:715] (3/8) Epoch 10, batch 2550, loss[loss=0.126, simple_loss=0.1969, pruned_loss=0.02754, over 4916.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03441, over 971780.05 frames.], batch size: 18, lr: 2.18e-04
+2022-05-06 17:14:29,342 INFO [train.py:715] (3/8) Epoch 10, batch 2600, loss[loss=0.1248, simple_loss=0.1965, pruned_loss=0.02661, over 4978.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03494, over 971904.61 frames.], batch size: 15, lr: 2.18e-04
+2022-05-06 17:15:08,460 INFO [train.py:715] (3/8) Epoch 10, batch 2650, loss[loss=0.1344, simple_loss=0.209, pruned_loss=0.02988, over 4924.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2138, pruned_loss=0.03461, over 972648.80 frames.], batch size: 21, lr: 2.18e-04
+2022-05-06 17:15:47,657 INFO [train.py:715] (3/8) Epoch 10, batch 2700, loss[loss=0.1653, simple_loss=0.2281, pruned_loss=0.0512, over 4773.00 frames.], tot_loss[loss=0.142, simple_loss=0.2145, pruned_loss=0.03475, over 973338.29 frames.], batch size: 14, lr: 2.18e-04
+2022-05-06 17:16:26,375 INFO [train.py:715] (3/8) Epoch 10, batch 2750, loss[loss=0.1396, simple_loss=0.208, pruned_loss=0.03562, over 4807.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03416, over 973629.16 frames.], batch size: 25, lr: 2.18e-04
+2022-05-06 17:17:05,077 INFO [train.py:715] (3/8) Epoch 10, batch 2800, loss[loss=0.1347, simple_loss=0.2114, pruned_loss=0.02898, over 4738.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03422, over 972980.39 frames.], batch size: 16, lr: 2.18e-04
+2022-05-06 17:17:43,821 INFO [train.py:715] (3/8) Epoch 10, batch 2850, loss[loss=0.1458, simple_loss=0.2034, pruned_loss=0.0441, over 4774.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.0343, over 972602.59 frames.], batch size: 14, lr: 2.18e-04
+2022-05-06 17:18:23,065 INFO [train.py:715] (3/8) Epoch 10, batch 2900, loss[loss=0.116, simple_loss=0.1975, pruned_loss=0.01728, over 4797.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03392, over 972886.50 frames.], batch size: 24, lr: 2.18e-04
+2022-05-06 17:19:02,253 INFO [train.py:715] (3/8) Epoch 10, batch 2950, loss[loss=0.1904, simple_loss=0.2538, pruned_loss=0.06347, over 4857.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.03406, over 972758.98 frames.], batch size: 20, lr: 2.18e-04
+2022-05-06 17:19:40,632 INFO [train.py:715] (3/8) Epoch 10, batch 3000, loss[loss=0.1489, simple_loss=0.2199, pruned_loss=0.03895, over 4984.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2136, pruned_loss=0.03398, over 971970.05 frames.], batch size: 31, lr: 2.18e-04
+2022-05-06 17:19:40,633 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 17:19:50,100 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1908, pruned_loss=0.01113, over 914524.00 frames.
+2022-05-06 17:20:28,628 INFO [train.py:715] (3/8) Epoch 10, batch 3050, loss[loss=0.1437, simple_loss=0.2134, pruned_loss=0.03697, over 4836.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03365, over 971603.57 frames.], batch size: 30, lr: 2.18e-04
+2022-05-06 17:21:07,569 INFO [train.py:715] (3/8) Epoch 10, batch 3100, loss[loss=0.1169, simple_loss=0.1912, pruned_loss=0.02137, over 4931.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03391, over 972192.31 frames.], batch size: 29, lr: 2.18e-04
+2022-05-06 17:21:46,720 INFO [train.py:715] (3/8) Epoch 10, batch 3150, loss[loss=0.1362, simple_loss=0.2141, pruned_loss=0.02913, over 4852.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03343, over 972458.19 frames.], batch size: 34, lr: 2.18e-04
+2022-05-06 17:22:25,533 INFO [train.py:715] (3/8) Epoch 10, batch 3200, loss[loss=0.1258, simple_loss=0.194, pruned_loss=0.02885, over 4985.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.0333, over 973423.80 frames.], batch size: 25, lr: 2.18e-04
+2022-05-06 17:23:03,968 INFO [train.py:715] (3/8) Epoch 10, batch 3250, loss[loss=0.1417, simple_loss=0.2122, pruned_loss=0.03564, over 4962.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.03373, over 973505.34 frames.], batch size: 35, lr: 2.18e-04
+2022-05-06 17:23:44,489 INFO [train.py:715] (3/8) Epoch 10, batch 3300, loss[loss=0.1436, simple_loss=0.2195, pruned_loss=0.03385, over 4802.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2139, pruned_loss=0.0341, over 973526.72 frames.], batch size: 25, lr: 2.18e-04
+2022-05-06 17:24:24,207 INFO [train.py:715] (3/8) Epoch 10, batch 3350, loss[loss=0.1396, simple_loss=0.2222, pruned_loss=0.02846, over 4799.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2144, pruned_loss=0.03398, over 973707.94 frames.], batch size: 18, lr: 2.18e-04
+2022-05-06 17:25:04,066 INFO [train.py:715] (3/8) Epoch 10, batch 3400, loss[loss=0.1265, simple_loss=0.1964, pruned_loss=0.02834, over 4820.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2142, pruned_loss=0.03401, over 973137.20 frames.], batch size: 21, lr: 2.18e-04
+2022-05-06 17:25:44,885 INFO [train.py:715] (3/8) Epoch 10, batch 3450, loss[loss=0.1311, simple_loss=0.2075, pruned_loss=0.02731, over 4980.00 frames.], tot_loss[loss=0.141, simple_loss=0.2143, pruned_loss=0.03379, over 972841.31 frames.], batch size: 28, lr: 2.18e-04
+2022-05-06 17:26:26,601 INFO [train.py:715] (3/8) Epoch 10, batch 3500, loss[loss=0.1486, simple_loss=0.2188, pruned_loss=0.03924, over 4767.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03369, over 972083.62 frames.], batch size: 18, lr: 2.18e-04
+2022-05-06 17:27:07,261 INFO [train.py:715] (3/8) Epoch 10, batch 3550, loss[loss=0.1637, simple_loss=0.2569, pruned_loss=0.03521, over 4766.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03347, over 971917.20 frames.], batch size: 19, lr: 2.18e-04
+2022-05-06 17:27:48,540 INFO [train.py:715] (3/8) Epoch 10, batch 3600, loss[loss=0.156, simple_loss=0.229, pruned_loss=0.04149, over 4906.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03361, over 972413.32 frames.], batch size: 19, lr: 2.18e-04
+2022-05-06 17:28:29,179 INFO [train.py:715] (3/8) Epoch 10, batch 3650, loss[loss=0.1516, simple_loss=0.2263, pruned_loss=0.03845, over 4944.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03362, over 972050.92 frames.], batch size: 29, lr: 2.18e-04
+2022-05-06 17:29:10,565 INFO [train.py:715] (3/8) Epoch 10, batch 3700, loss[loss=0.1196, simple_loss=0.2041, pruned_loss=0.01753, over 4772.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03355, over 971760.65 frames.], batch size: 14, lr: 2.18e-04
+2022-05-06 17:29:51,154 INFO [train.py:715] (3/8) Epoch 10, batch 3750, loss[loss=0.1667, simple_loss=0.2366, pruned_loss=0.04837, over 4694.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2128, pruned_loss=0.034, over 971398.05 frames.], batch size: 15, lr: 2.18e-04
+2022-05-06 17:30:32,379 INFO [train.py:715] (3/8) Epoch 10, batch 3800, loss[loss=0.1374, simple_loss=0.2078, pruned_loss=0.03354, over 4909.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03362, over 971683.05 frames.], batch size: 29, lr: 2.18e-04
+2022-05-06 17:31:13,749 INFO [train.py:715] (3/8) Epoch 10, batch 3850, loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02892, over 4860.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03402, over 972459.23 frames.], batch size: 20, lr: 2.18e-04
+2022-05-06 17:31:54,697 INFO [train.py:715] (3/8) Epoch 10, batch 3900, loss[loss=0.1434, simple_loss=0.208, pruned_loss=0.03936, over 4845.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2135, pruned_loss=0.03433, over 971655.52 frames.], batch size: 30, lr: 2.18e-04
+2022-05-06 17:32:36,894 INFO [train.py:715] (3/8) Epoch 10, batch 3950, loss[loss=0.128, simple_loss=0.2064, pruned_loss=0.0248, over 4873.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03449, over 971940.93 frames.], batch size: 32, lr: 2.18e-04
+2022-05-06 17:33:16,172 INFO [train.py:715] (3/8) Epoch 10, batch 4000, loss[loss=0.1241, simple_loss=0.1932, pruned_loss=0.02751, over 4780.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2126, pruned_loss=0.03395, over 972281.88 frames.], batch size: 18, lr: 2.18e-04
+2022-05-06 17:33:55,834 INFO [train.py:715] (3/8) Epoch 10, batch 4050, loss[loss=0.1171, simple_loss=0.1853, pruned_loss=0.02448, over 4781.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2123, pruned_loss=0.03367, over 972287.71 frames.], batch size: 18, lr: 2.18e-04
+2022-05-06 17:34:34,556 INFO [train.py:715] (3/8) Epoch 10, batch 4100, loss[loss=0.1158, simple_loss=0.1889, pruned_loss=0.02131, over 4701.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03369, over 972394.11 frames.], batch size: 15, lr: 2.18e-04
+2022-05-06 17:35:13,432 INFO [train.py:715] (3/8) Epoch 10, batch 4150, loss[loss=0.1235, simple_loss=0.1862, pruned_loss=0.03033, over 4857.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03368, over 971754.88 frames.], batch size: 16, lr: 2.18e-04
+2022-05-06 17:35:52,989 INFO [train.py:715] (3/8) Epoch 10, batch 4200, loss[loss=0.1444, simple_loss=0.2156, pruned_loss=0.03667, over 4898.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2125, pruned_loss=0.0338, over 970962.18 frames.], batch size: 19, lr: 2.18e-04
+2022-05-06 17:36:31,674 INFO [train.py:715] (3/8) Epoch 10, batch 4250, loss[loss=0.1317, simple_loss=0.2044, pruned_loss=0.02947, over 4905.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03352, over 970556.79 frames.], batch size: 19, lr: 2.18e-04
+2022-05-06 17:37:10,487 INFO [train.py:715] (3/8) Epoch 10, batch 4300, loss[loss=0.1223, simple_loss=0.1922, pruned_loss=0.0262, over 4827.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03329, over 971174.23 frames.], batch size: 13, lr: 2.18e-04
+2022-05-06 17:37:49,693 INFO [train.py:715] (3/8) Epoch 10, batch 4350, loss[loss=0.171, simple_loss=0.2423, pruned_loss=0.0498, over 4927.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.0338, over 971658.31 frames.], batch size: 23, lr: 2.18e-04
+2022-05-06 17:38:28,652 INFO [train.py:715] (3/8) Epoch 10, batch 4400, loss[loss=0.1469, simple_loss=0.2135, pruned_loss=0.04021, over 4857.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03388, over 972158.30 frames.], batch size: 32, lr: 2.18e-04
+2022-05-06 17:39:07,612 INFO [train.py:715] (3/8) Epoch 10, batch 4450, loss[loss=0.1571, simple_loss=0.2414, pruned_loss=0.03643, over 4850.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2142, pruned_loss=0.03396, over 971825.13 frames.], batch size: 20, lr: 2.18e-04
+2022-05-06 17:39:46,322 INFO [train.py:715] (3/8) Epoch 10, batch 4500, loss[loss=0.1508, simple_loss=0.2206, pruned_loss=0.04047, over 4854.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2141, pruned_loss=0.03378, over 971942.16 frames.], batch size: 15, lr: 2.18e-04
+2022-05-06 17:40:25,796 INFO [train.py:715] (3/8) Epoch 10, batch 4550, loss[loss=0.1347, simple_loss=0.2038, pruned_loss=0.03286, over 4988.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.0335, over 972779.76 frames.], batch size: 25, lr: 2.18e-04
+2022-05-06 17:41:04,678 INFO [train.py:715] (3/8) Epoch 10, batch 4600, loss[loss=0.1616, simple_loss=0.2475, pruned_loss=0.03788, over 4702.00 frames.], tot_loss[loss=0.1409, simple_loss=0.214, pruned_loss=0.03386, over 973037.45 frames.], batch size: 15, lr: 2.18e-04
+2022-05-06 17:41:43,576 INFO [train.py:715] (3/8) Epoch 10, batch 4650, loss[loss=0.1468, simple_loss=0.229, pruned_loss=0.03225, over 4936.00 frames.], tot_loss[loss=0.142, simple_loss=0.2152, pruned_loss=0.0344, over 973237.05 frames.], batch size: 21, lr: 2.18e-04
+2022-05-06 17:42:23,828 INFO [train.py:715] (3/8) Epoch 10, batch 4700, loss[loss=0.1253, simple_loss=0.2039, pruned_loss=0.02336, over 4844.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03385, over 973068.98 frames.], batch size: 15, lr: 2.18e-04
+2022-05-06 17:43:03,974 INFO [train.py:715] (3/8) Epoch 10, batch 4750, loss[loss=0.1254, simple_loss=0.2036, pruned_loss=0.02355, over 4767.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03345, over 972978.57 frames.], batch size: 12, lr: 2.18e-04
+2022-05-06 17:43:43,164 INFO [train.py:715] (3/8) Epoch 10, batch 4800, loss[loss=0.1584, simple_loss=0.2247, pruned_loss=0.04608, over 4982.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03366, over 972431.03 frames.], batch size: 31, lr: 2.18e-04
+2022-05-06 17:44:22,998 INFO [train.py:715] (3/8) Epoch 10, batch 4850, loss[loss=0.1142, simple_loss=0.1913, pruned_loss=0.01855, over 4786.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03383, over 972871.33 frames.], batch size: 18, lr: 2.18e-04
+2022-05-06 17:45:02,945 INFO [train.py:715] (3/8) Epoch 10, batch 4900, loss[loss=0.1526, simple_loss=0.2279, pruned_loss=0.03868, over 4903.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2142, pruned_loss=0.03407, over 972191.81 frames.], batch size: 17, lr: 2.18e-04
+2022-05-06 17:45:42,396 INFO [train.py:715] (3/8) Epoch 10, batch 4950, loss[loss=0.1516, simple_loss=0.2145, pruned_loss=0.04437, over 4865.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2141, pruned_loss=0.03432, over 971730.15 frames.], batch size: 32, lr: 2.18e-04
+2022-05-06 17:46:21,436 INFO [train.py:715] (3/8) Epoch 10, batch 5000, loss[loss=0.1514, simple_loss=0.225, pruned_loss=0.03889, over 4794.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2143, pruned_loss=0.03408, over 972137.19 frames.], batch size: 24, lr: 2.18e-04
+2022-05-06 17:47:00,598 INFO [train.py:715] (3/8) Epoch 10, batch 5050, loss[loss=0.1701, simple_loss=0.2338, pruned_loss=0.05321, over 4847.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2145, pruned_loss=0.03432, over 973155.23 frames.], batch size: 30, lr: 2.18e-04
+2022-05-06 17:47:39,529 INFO [train.py:715] (3/8) Epoch 10, batch 5100, loss[loss=0.1795, simple_loss=0.22, pruned_loss=0.06943, over 4979.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.03418, over 972512.41 frames.], batch size: 15, lr: 2.18e-04
+2022-05-06 17:48:18,799 INFO [train.py:715] (3/8) Epoch 10, batch 5150, loss[loss=0.1464, simple_loss=0.2133, pruned_loss=0.03976, over 4831.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.03407, over 972295.25 frames.], batch size: 15, lr: 2.18e-04
+2022-05-06 17:48:58,634 INFO [train.py:715] (3/8) Epoch 10, batch 5200, loss[loss=0.1606, simple_loss=0.2361, pruned_loss=0.04259, over 4820.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03349, over 971904.16 frames.], batch size: 15, lr: 2.17e-04
+2022-05-06 17:49:38,476 INFO [train.py:715] (3/8) Epoch 10, batch 5250, loss[loss=0.1762, simple_loss=0.2512, pruned_loss=0.05064, over 4821.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.0343, over 971625.52 frames.], batch size: 15, lr: 2.17e-04
+2022-05-06 17:50:17,852 INFO [train.py:715] (3/8) Epoch 10, batch 5300, loss[loss=0.1187, simple_loss=0.192, pruned_loss=0.02271, over 4876.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03393, over 971696.25 frames.], batch size: 22, lr: 2.17e-04
+2022-05-06 17:50:57,191 INFO [train.py:715] (3/8) Epoch 10, batch 5350, loss[loss=0.1414, simple_loss=0.2221, pruned_loss=0.03032, over 4773.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2136, pruned_loss=0.03364, over 971205.30 frames.], batch size: 18, lr: 2.17e-04
+2022-05-06 17:51:37,022 INFO [train.py:715] (3/8) Epoch 10, batch 5400, loss[loss=0.1306, simple_loss=0.2132, pruned_loss=0.02403, over 4785.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03405, over 971111.19 frames.], batch size: 17, lr: 2.17e-04
+2022-05-06 17:52:16,939 INFO [train.py:715] (3/8) Epoch 10, batch 5450, loss[loss=0.1801, simple_loss=0.243, pruned_loss=0.05858, over 4840.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03411, over 972685.66 frames.], batch size: 30, lr: 2.17e-04
+2022-05-06 17:52:56,345 INFO [train.py:715] (3/8) Epoch 10, batch 5500, loss[loss=0.1148, simple_loss=0.1861, pruned_loss=0.02173, over 4783.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03406, over 972133.02 frames.], batch size: 18, lr: 2.17e-04
+2022-05-06 17:53:36,102 INFO [train.py:715] (3/8) Epoch 10, batch 5550, loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03285, over 4962.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03425, over 971918.46 frames.], batch size: 35, lr: 2.17e-04
+2022-05-06 17:54:16,053 INFO [train.py:715] (3/8) Epoch 10, batch 5600, loss[loss=0.1537, simple_loss=0.2261, pruned_loss=0.04063, over 4765.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03343, over 971761.13 frames.], batch size: 17, lr: 2.17e-04
+2022-05-06 17:54:55,811 INFO [train.py:715] (3/8) Epoch 10, batch 5650, loss[loss=0.1216, simple_loss=0.1977, pruned_loss=0.02273, over 4779.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2131, pruned_loss=0.03324, over 971081.97 frames.], batch size: 14, lr: 2.17e-04
+2022-05-06 17:55:34,978 INFO [train.py:715] (3/8) Epoch 10, batch 5700, loss[loss=0.1392, simple_loss=0.2129, pruned_loss=0.03271, over 4910.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03335, over 971711.84 frames.], batch size: 17, lr: 2.17e-04
+2022-05-06 17:56:15,023 INFO [train.py:715] (3/8) Epoch 10, batch 5750, loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03466, over 4926.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03304, over 972134.72 frames.], batch size: 29, lr: 2.17e-04
+2022-05-06 17:56:54,685 INFO [train.py:715] (3/8) Epoch 10, batch 5800, loss[loss=0.1421, simple_loss=0.2123, pruned_loss=0.03593, over 4897.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03294, over 972432.65 frames.], batch size: 19, lr: 2.17e-04
+2022-05-06 17:57:34,209 INFO [train.py:715] (3/8) Epoch 10, batch 5850, loss[loss=0.1046, simple_loss=0.1747, pruned_loss=0.01727, over 4659.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03277, over 971861.13 frames.], batch size: 13, lr: 2.17e-04
+2022-05-06 17:58:14,027 INFO [train.py:715] (3/8) Epoch 10, batch 5900, loss[loss=0.1098, simple_loss=0.1904, pruned_loss=0.01462, over 4774.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03298, over 971527.90 frames.], batch size: 17, lr: 2.17e-04
+2022-05-06 17:58:53,764 INFO [train.py:715] (3/8) Epoch 10, batch 5950, loss[loss=0.171, simple_loss=0.2472, pruned_loss=0.04742, over 4833.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03306, over 971259.48 frames.], batch size: 30, lr: 2.17e-04
+2022-05-06 17:59:33,427 INFO [train.py:715] (3/8) Epoch 10, batch 6000, loss[loss=0.1199, simple_loss=0.19, pruned_loss=0.02495, over 4761.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.0333, over 969917.89 frames.], batch size: 12, lr: 2.17e-04
+2022-05-06 17:59:33,428 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 17:59:42,752 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1067, simple_loss=0.1909, pruned_loss=0.01126, over 914524.00 frames.
+2022-05-06 18:00:22,327 INFO [train.py:715] (3/8) Epoch 10, batch 6050, loss[loss=0.1558, simple_loss=0.2312, pruned_loss=0.04017, over 4822.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03409, over 969635.35 frames.], batch size: 15, lr: 2.17e-04
+2022-05-06 18:01:00,749 INFO [train.py:715] (3/8) Epoch 10, batch 6100, loss[loss=0.1634, simple_loss=0.2372, pruned_loss=0.04475, over 4827.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03429, over 969393.35 frames.], batch size: 26, lr: 2.17e-04
+2022-05-06 18:01:40,208 INFO [train.py:715] (3/8) Epoch 10, batch 6150, loss[loss=0.1408, simple_loss=0.2144, pruned_loss=0.0336, over 4903.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2131, pruned_loss=0.03418, over 969966.39 frames.], batch size: 17, lr: 2.17e-04
+2022-05-06 18:02:20,067 INFO [train.py:715] (3/8) Epoch 10, batch 6200, loss[loss=0.1377, simple_loss=0.1983, pruned_loss=0.03858, over 4757.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03396, over 970563.25 frames.], batch size: 19, lr: 2.17e-04
+2022-05-06 18:02:59,937 INFO [train.py:715] (3/8) Epoch 10, batch 6250, loss[loss=0.1439, simple_loss=0.2178, pruned_loss=0.03499, over 4885.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2133, pruned_loss=0.0344, over 970785.22 frames.], batch size: 32, lr: 2.17e-04
+2022-05-06 18:03:39,468 INFO [train.py:715] (3/8) Epoch 10, batch 6300, loss[loss=0.1226, simple_loss=0.1992, pruned_loss=0.02301, over 4754.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2123, pruned_loss=0.03403, over 971574.05 frames.], batch size: 19, lr: 2.17e-04
+2022-05-06 18:04:19,279 INFO [train.py:715] (3/8) Epoch 10, batch 6350, loss[loss=0.1442, simple_loss=0.215, pruned_loss=0.03667, over 4796.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2122, pruned_loss=0.03381, over 972443.11 frames.], batch size: 21, lr: 2.17e-04
+2022-05-06 18:04:58,326 INFO [train.py:715] (3/8) Epoch 10, batch 6400, loss[loss=0.1772, simple_loss=0.2498, pruned_loss=0.05232, over 4699.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2126, pruned_loss=0.03389, over 972786.82 frames.], batch size: 15, lr: 2.17e-04
+2022-05-06 18:05:36,735 INFO [train.py:715] (3/8) Epoch 10, batch 6450, loss[loss=0.1402, simple_loss=0.2253, pruned_loss=0.02759, over 4823.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.0341, over 973209.09 frames.], batch size: 26, lr: 2.17e-04
+2022-05-06 18:06:15,661 INFO [train.py:715] (3/8) Epoch 10, batch 6500, loss[loss=0.1425, simple_loss=0.2078, pruned_loss=0.03863, over 4962.00 frames.], tot_loss[loss=0.1409, simple_loss=0.213, pruned_loss=0.03435, over 972977.44 frames.], batch size: 35, lr: 2.17e-04
+2022-05-06 18:06:54,773 INFO [train.py:715] (3/8) Epoch 10, batch 6550, loss[loss=0.1485, simple_loss=0.2311, pruned_loss=0.03294, over 4905.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2134, pruned_loss=0.03445, over 972862.85 frames.], batch size: 18, lr: 2.17e-04
+2022-05-06 18:07:33,916 INFO [train.py:715] (3/8) Epoch 10, batch 6600, loss[loss=0.1368, simple_loss=0.2148, pruned_loss=0.02935, over 4961.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03434, over 972794.69 frames.], batch size: 24, lr: 2.17e-04
+2022-05-06 18:08:12,469 INFO [train.py:715] (3/8) Epoch 10, batch 6650, loss[loss=0.1596, simple_loss=0.2225, pruned_loss=0.04837, over 4644.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.03417, over 972356.61 frames.], batch size: 13, lr: 2.17e-04
+2022-05-06 18:08:52,601 INFO [train.py:715] (3/8) Epoch 10, batch 6700, loss[loss=0.1635, simple_loss=0.2279, pruned_loss=0.04955, over 4751.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03421, over 972621.74 frames.], batch size: 19, lr: 2.17e-04
+2022-05-06 18:09:31,855 INFO [train.py:715] (3/8) Epoch 10, batch 6750, loss[loss=0.1564, simple_loss=0.2361, pruned_loss=0.03836, over 4943.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03396, over 973109.29 frames.], batch size: 29, lr: 2.17e-04
+2022-05-06 18:10:10,544 INFO [train.py:715] (3/8) Epoch 10, batch 6800, loss[loss=0.1472, simple_loss=0.2194, pruned_loss=0.0375, over 4768.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2131, pruned_loss=0.03431, over 971639.32 frames.], batch size: 16, lr: 2.17e-04
+2022-05-06 18:10:50,411 INFO [train.py:715] (3/8) Epoch 10, batch 6850, loss[loss=0.1359, simple_loss=0.2115, pruned_loss=0.03019, over 4949.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2126, pruned_loss=0.03381, over 971887.18 frames.], batch size: 21, lr: 2.17e-04
+2022-05-06 18:11:29,655 INFO [train.py:715] (3/8) Epoch 10, batch 6900, loss[loss=0.1476, simple_loss=0.2232, pruned_loss=0.036, over 4769.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2115, pruned_loss=0.03287, over 971645.47 frames.], batch size: 17, lr: 2.17e-04
+2022-05-06 18:12:08,733 INFO [train.py:715] (3/8) Epoch 10, batch 6950, loss[loss=0.1306, simple_loss=0.2067, pruned_loss=0.02728, over 4876.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03314, over 971443.73 frames.], batch size: 16, lr: 2.17e-04
+2022-05-06 18:12:48,642 INFO [train.py:715] (3/8) Epoch 10, batch 7000, loss[loss=0.1221, simple_loss=0.2053, pruned_loss=0.01945, over 4939.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2122, pruned_loss=0.03376, over 971095.23 frames.], batch size: 21, lr: 2.17e-04
+2022-05-06 18:13:28,548 INFO [train.py:715] (3/8) Epoch 10, batch 7050, loss[loss=0.1519, simple_loss=0.2194, pruned_loss=0.04218, over 4695.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2117, pruned_loss=0.03362, over 971028.07 frames.], batch size: 15, lr: 2.17e-04
+2022-05-06 18:14:07,744 INFO [train.py:715] (3/8) Epoch 10, batch 7100, loss[loss=0.1148, simple_loss=0.1928, pruned_loss=0.01837, over 4757.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2127, pruned_loss=0.03409, over 971072.32 frames.], batch size: 12, lr: 2.17e-04
+2022-05-06 18:14:46,904 INFO [train.py:715] (3/8) Epoch 10, batch 7150, loss[loss=0.1256, simple_loss=0.2031, pruned_loss=0.0241, over 4782.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2127, pruned_loss=0.03416, over 970708.50 frames.], batch size: 18, lr: 2.17e-04
+2022-05-06 18:15:26,295 INFO [train.py:715] (3/8) Epoch 10, batch 7200, loss[loss=0.1196, simple_loss=0.1935, pruned_loss=0.02291, over 4820.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03419, over 971091.25 frames.], batch size: 12, lr: 2.17e-04
+2022-05-06 18:16:05,421 INFO [train.py:715] (3/8) Epoch 10, batch 7250, loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03481, over 4748.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03403, over 972127.31 frames.], batch size: 12, lr: 2.17e-04
+2022-05-06 18:16:44,410 INFO [train.py:715] (3/8) Epoch 10, batch 7300, loss[loss=0.1279, simple_loss=0.2022, pruned_loss=0.02675, over 4923.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.03405, over 972757.60 frames.], batch size: 18, lr: 2.17e-04
+2022-05-06 18:17:23,330 INFO [train.py:715] (3/8) Epoch 10, batch 7350, loss[loss=0.1344, simple_loss=0.2193, pruned_loss=0.02479, over 4950.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03406, over 971914.96 frames.], batch size: 21, lr: 2.17e-04
+2022-05-06 18:18:02,744 INFO [train.py:715] (3/8) Epoch 10, batch 7400, loss[loss=0.1337, simple_loss=0.212, pruned_loss=0.02774, over 4843.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03412, over 972034.46 frames.], batch size: 20, lr: 2.17e-04
+2022-05-06 18:18:41,888 INFO [train.py:715] (3/8) Epoch 10, batch 7450, loss[loss=0.105, simple_loss=0.1745, pruned_loss=0.0177, over 4849.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03354, over 972266.25 frames.], batch size: 20, lr: 2.17e-04
+2022-05-06 18:19:20,014 INFO [train.py:715] (3/8) Epoch 10, batch 7500, loss[loss=0.116, simple_loss=0.1858, pruned_loss=0.02307, over 4914.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2115, pruned_loss=0.03318, over 971756.70 frames.], batch size: 17, lr: 2.17e-04
+2022-05-06 18:19:59,644 INFO [train.py:715] (3/8) Epoch 10, batch 7550, loss[loss=0.143, simple_loss=0.2216, pruned_loss=0.03223, over 4939.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.03344, over 972326.86 frames.], batch size: 21, lr: 2.17e-04
+2022-05-06 18:20:38,459 INFO [train.py:715] (3/8) Epoch 10, batch 7600, loss[loss=0.151, simple_loss=0.2108, pruned_loss=0.04557, over 4694.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2126, pruned_loss=0.03405, over 971789.51 frames.], batch size: 15, lr: 2.17e-04
+2022-05-06 18:21:17,038 INFO [train.py:715] (3/8) Epoch 10, batch 7650, loss[loss=0.1418, simple_loss=0.2175, pruned_loss=0.03304, over 4796.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.03417, over 972318.66 frames.], batch size: 18, lr: 2.17e-04
+2022-05-06 18:21:56,435 INFO [train.py:715] (3/8) Epoch 10, batch 7700, loss[loss=0.1336, simple_loss=0.2097, pruned_loss=0.0287, over 4690.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03443, over 971752.09 frames.], batch size: 15, lr: 2.17e-04
+2022-05-06 18:22:35,791 INFO [train.py:715] (3/8) Epoch 10, batch 7750, loss[loss=0.1601, simple_loss=0.2262, pruned_loss=0.04702, over 4940.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03447, over 972020.91 frames.], batch size: 39, lr: 2.17e-04
+2022-05-06 18:23:15,174 INFO [train.py:715] (3/8) Epoch 10, batch 7800, loss[loss=0.1369, simple_loss=0.2045, pruned_loss=0.03462, over 4904.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2135, pruned_loss=0.03456, over 972102.70 frames.], batch size: 19, lr: 2.17e-04
+2022-05-06 18:23:53,545 INFO [train.py:715] (3/8) Epoch 10, batch 7850, loss[loss=0.1493, simple_loss=0.2206, pruned_loss=0.03895, over 4855.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2127, pruned_loss=0.03408, over 971732.51 frames.], batch size: 20, lr: 2.17e-04
+2022-05-06 18:24:33,022 INFO [train.py:715] (3/8) Epoch 10, batch 7900, loss[loss=0.1213, simple_loss=0.2071, pruned_loss=0.01777, over 4852.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.03373, over 971302.48 frames.], batch size: 20, lr: 2.17e-04
+2022-05-06 18:25:12,544 INFO [train.py:715] (3/8) Epoch 10, batch 7950, loss[loss=0.1321, simple_loss=0.2058, pruned_loss=0.02922, over 4798.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2131, pruned_loss=0.03436, over 971219.25 frames.], batch size: 24, lr: 2.17e-04
+2022-05-06 18:25:51,360 INFO [train.py:715] (3/8) Epoch 10, batch 8000, loss[loss=0.1272, simple_loss=0.2151, pruned_loss=0.01967, over 4807.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03411, over 971669.69 frames.], batch size: 24, lr: 2.17e-04
+2022-05-06 18:26:30,786 INFO [train.py:715] (3/8) Epoch 10, batch 8050, loss[loss=0.1211, simple_loss=0.1956, pruned_loss=0.02327, over 4820.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03404, over 971435.93 frames.], batch size: 13, lr: 2.17e-04
+2022-05-06 18:27:10,411 INFO [train.py:715] (3/8) Epoch 10, batch 8100, loss[loss=0.1871, simple_loss=0.2501, pruned_loss=0.06202, over 4783.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.0342, over 971153.52 frames.], batch size: 17, lr: 2.17e-04
+2022-05-06 18:27:49,302 INFO [train.py:715] (3/8) Epoch 10, batch 8150, loss[loss=0.1606, simple_loss=0.2354, pruned_loss=0.04288, over 4776.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03418, over 971258.52 frames.], batch size: 14, lr: 2.17e-04
+2022-05-06 18:28:27,918 INFO [train.py:715] (3/8) Epoch 10, batch 8200, loss[loss=0.144, simple_loss=0.2196, pruned_loss=0.03423, over 4800.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03454, over 971972.20 frames.], batch size: 24, lr: 2.17e-04
+2022-05-06 18:29:07,589 INFO [train.py:715] (3/8) Epoch 10, batch 8250, loss[loss=0.1841, simple_loss=0.2418, pruned_loss=0.06326, over 4863.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03434, over 971198.21 frames.], batch size: 13, lr: 2.17e-04
+2022-05-06 18:29:46,989 INFO [train.py:715] (3/8) Epoch 10, batch 8300, loss[loss=0.1702, simple_loss=0.2325, pruned_loss=0.05392, over 4851.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03423, over 972174.52 frames.], batch size: 32, lr: 2.17e-04
+2022-05-06 18:30:25,735 INFO [train.py:715] (3/8) Epoch 10, batch 8350, loss[loss=0.1389, simple_loss=0.2109, pruned_loss=0.03343, over 4843.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03359, over 971334.39 frames.], batch size: 15, lr: 2.17e-04
+2022-05-06 18:31:05,470 INFO [train.py:715] (3/8) Epoch 10, batch 8400, loss[loss=0.1293, simple_loss=0.2029, pruned_loss=0.02781, over 4763.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2127, pruned_loss=0.03385, over 971913.50 frames.], batch size: 18, lr: 2.17e-04
+2022-05-06 18:31:44,983 INFO [train.py:715] (3/8) Epoch 10, batch 8450, loss[loss=0.1202, simple_loss=0.1986, pruned_loss=0.02091, over 4924.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03396, over 972372.61 frames.], batch size: 23, lr: 2.16e-04
+2022-05-06 18:32:23,259 INFO [train.py:715] (3/8) Epoch 10, batch 8500, loss[loss=0.137, simple_loss=0.2066, pruned_loss=0.03375, over 4831.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.0337, over 972078.62 frames.], batch size: 26, lr: 2.16e-04
+2022-05-06 18:33:02,053 INFO [train.py:715] (3/8) Epoch 10, batch 8550, loss[loss=0.1402, simple_loss=0.2071, pruned_loss=0.03666, over 4893.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03358, over 971802.80 frames.], batch size: 22, lr: 2.16e-04
+2022-05-06 18:33:41,305 INFO [train.py:715] (3/8) Epoch 10, batch 8600, loss[loss=0.1289, simple_loss=0.1992, pruned_loss=0.02936, over 4967.00 frames.], tot_loss[loss=0.14, simple_loss=0.2121, pruned_loss=0.0339, over 971765.67 frames.], batch size: 24, lr: 2.16e-04
+2022-05-06 18:34:19,985 INFO [train.py:715] (3/8) Epoch 10, batch 8650, loss[loss=0.1374, simple_loss=0.2077, pruned_loss=0.03355, over 4852.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.0336, over 972335.09 frames.], batch size: 30, lr: 2.16e-04
+2022-05-06 18:34:58,635 INFO [train.py:715] (3/8) Epoch 10, batch 8700, loss[loss=0.1275, simple_loss=0.1886, pruned_loss=0.03317, over 4760.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2118, pruned_loss=0.03342, over 972577.80 frames.], batch size: 14, lr: 2.16e-04
+2022-05-06 18:35:37,460 INFO [train.py:715] (3/8) Epoch 10, batch 8750, loss[loss=0.1542, simple_loss=0.2301, pruned_loss=0.03916, over 4850.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.0343, over 972837.45 frames.], batch size: 13, lr: 2.16e-04
+2022-05-06 18:36:15,827 INFO [train.py:715] (3/8) Epoch 10, batch 8800, loss[loss=0.1368, simple_loss=0.2178, pruned_loss=0.02793, over 4704.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2125, pruned_loss=0.03388, over 971436.20 frames.], batch size: 15, lr: 2.16e-04
+2022-05-06 18:36:54,707 INFO [train.py:715] (3/8) Epoch 10, batch 8850, loss[loss=0.1219, simple_loss=0.1953, pruned_loss=0.0243, over 4732.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2128, pruned_loss=0.03382, over 972078.55 frames.], batch size: 16, lr: 2.16e-04
+2022-05-06 18:37:34,275 INFO [train.py:715] (3/8) Epoch 10, batch 8900, loss[loss=0.1373, simple_loss=0.2168, pruned_loss=0.02893, over 4972.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03405, over 971779.04 frames.], batch size: 24, lr: 2.16e-04
+2022-05-06 18:38:13,790 INFO [train.py:715] (3/8) Epoch 10, batch 8950, loss[loss=0.1791, simple_loss=0.2511, pruned_loss=0.0536, over 4935.00 frames.], tot_loss[loss=0.1416, simple_loss=0.214, pruned_loss=0.03461, over 972609.03 frames.], batch size: 23, lr: 2.16e-04
+2022-05-06 18:38:53,305 INFO [train.py:715] (3/8) Epoch 10, batch 9000, loss[loss=0.1339, simple_loss=0.2089, pruned_loss=0.02946, over 4902.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2144, pruned_loss=0.03525, over 971913.52 frames.], batch size: 19, lr: 2.16e-04
+2022-05-06 18:38:53,305 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 18:39:02,857 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1064, simple_loss=0.1907, pruned_loss=0.01106, over 914524.00 frames.
+2022-05-06 18:39:42,085 INFO [train.py:715] (3/8) Epoch 10, batch 9050, loss[loss=0.1862, simple_loss=0.2506, pruned_loss=0.0609, over 4795.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2142, pruned_loss=0.03518, over 972493.25 frames.], batch size: 17, lr: 2.16e-04
+2022-05-06 18:40:21,152 INFO [train.py:715] (3/8) Epoch 10, batch 9100, loss[loss=0.1241, simple_loss=0.199, pruned_loss=0.02458, over 4936.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2142, pruned_loss=0.03497, over 972464.51 frames.], batch size: 21, lr: 2.16e-04
+2022-05-06 18:41:01,480 INFO [train.py:715] (3/8) Epoch 10, batch 9150, loss[loss=0.1491, simple_loss=0.2215, pruned_loss=0.0384, over 4856.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2138, pruned_loss=0.03492, over 972498.00 frames.], batch size: 20, lr: 2.16e-04
+2022-05-06 18:41:40,998 INFO [train.py:715] (3/8) Epoch 10, batch 9200, loss[loss=0.1115, simple_loss=0.1848, pruned_loss=0.01906, over 4972.00 frames.], tot_loss[loss=0.1409, simple_loss=0.213, pruned_loss=0.03437, over 972252.43 frames.], batch size: 25, lr: 2.16e-04
+2022-05-06 18:42:20,444 INFO [train.py:715] (3/8) Epoch 10, batch 9250, loss[loss=0.1332, simple_loss=0.202, pruned_loss=0.03225, over 4955.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03443, over 972653.60 frames.], batch size: 35, lr: 2.16e-04
+2022-05-06 18:43:00,265 INFO [train.py:715] (3/8) Epoch 10, batch 9300, loss[loss=0.1546, simple_loss=0.2247, pruned_loss=0.04223, over 4885.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.03456, over 972721.73 frames.], batch size: 16, lr: 2.16e-04
+2022-05-06 18:43:39,884 INFO [train.py:715] (3/8) Epoch 10, batch 9350, loss[loss=0.1373, simple_loss=0.2221, pruned_loss=0.02631, over 4903.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2126, pruned_loss=0.03422, over 972982.21 frames.], batch size: 18, lr: 2.16e-04
+2022-05-06 18:44:19,394 INFO [train.py:715] (3/8) Epoch 10, batch 9400, loss[loss=0.1669, simple_loss=0.2323, pruned_loss=0.05075, over 4945.00 frames.], tot_loss[loss=0.141, simple_loss=0.2134, pruned_loss=0.03433, over 973432.84 frames.], batch size: 21, lr: 2.16e-04
+2022-05-06 18:44:58,982 INFO [train.py:715] (3/8) Epoch 10, batch 9450, loss[loss=0.1509, simple_loss=0.2261, pruned_loss=0.03788, over 4880.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03459, over 973582.87 frames.], batch size: 39, lr: 2.16e-04
+2022-05-06 18:45:38,378 INFO [train.py:715] (3/8) Epoch 10, batch 9500, loss[loss=0.145, simple_loss=0.2289, pruned_loss=0.0306, over 4820.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03396, over 973399.13 frames.], batch size: 26, lr: 2.16e-04
+2022-05-06 18:46:17,356 INFO [train.py:715] (3/8) Epoch 10, batch 9550, loss[loss=0.1463, simple_loss=0.2173, pruned_loss=0.03766, over 4878.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.03411, over 973655.22 frames.], batch size: 22, lr: 2.16e-04
+2022-05-06 18:46:55,766 INFO [train.py:715] (3/8) Epoch 10, batch 9600, loss[loss=0.1616, simple_loss=0.2389, pruned_loss=0.0421, over 4920.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03363, over 974369.69 frames.], batch size: 39, lr: 2.16e-04
+2022-05-06 18:47:34,905 INFO [train.py:715] (3/8) Epoch 10, batch 9650, loss[loss=0.1553, simple_loss=0.2264, pruned_loss=0.04211, over 4787.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03347, over 973912.05 frames.], batch size: 17, lr: 2.16e-04
+2022-05-06 18:48:14,562 INFO [train.py:715] (3/8) Epoch 10, batch 9700, loss[loss=0.1806, simple_loss=0.2471, pruned_loss=0.05702, over 4940.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03376, over 973792.61 frames.], batch size: 21, lr: 2.16e-04
+2022-05-06 18:48:52,977 INFO [train.py:715] (3/8) Epoch 10, batch 9750, loss[loss=0.1385, simple_loss=0.2083, pruned_loss=0.03432, over 4756.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.03366, over 972988.75 frames.], batch size: 19, lr: 2.16e-04
+2022-05-06 18:49:32,213 INFO [train.py:715] (3/8) Epoch 10, batch 9800, loss[loss=0.1551, simple_loss=0.2344, pruned_loss=0.03792, over 4995.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03365, over 971677.54 frames.], batch size: 16, lr: 2.16e-04
+2022-05-06 18:50:11,747 INFO [train.py:715] (3/8) Epoch 10, batch 9850, loss[loss=0.1362, simple_loss=0.1985, pruned_loss=0.03697, over 4978.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.03376, over 972584.91 frames.], batch size: 14, lr: 2.16e-04
+2022-05-06 18:50:51,058 INFO [train.py:715] (3/8) Epoch 10, batch 9900, loss[loss=0.1318, simple_loss=0.1965, pruned_loss=0.03356, over 4991.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.0337, over 973670.07 frames.], batch size: 14, lr: 2.16e-04
+2022-05-06 18:51:30,049 INFO [train.py:715] (3/8) Epoch 10, batch 9950, loss[loss=0.145, simple_loss=0.2273, pruned_loss=0.03138, over 4832.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03356, over 973743.68 frames.], batch size: 25, lr: 2.16e-04
+2022-05-06 18:52:10,242 INFO [train.py:715] (3/8) Epoch 10, batch 10000, loss[loss=0.1462, simple_loss=0.2221, pruned_loss=0.0352, over 4834.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.03348, over 973093.85 frames.], batch size: 26, lr: 2.16e-04
+2022-05-06 18:52:49,845 INFO [train.py:715] (3/8) Epoch 10, batch 10050, loss[loss=0.1268, simple_loss=0.1997, pruned_loss=0.02698, over 4965.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03309, over 972822.37 frames.], batch size: 24, lr: 2.16e-04
+2022-05-06 18:53:27,870 INFO [train.py:715] (3/8) Epoch 10, batch 10100, loss[loss=0.1714, simple_loss=0.2294, pruned_loss=0.05671, over 4852.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.0338, over 973020.78 frames.], batch size: 13, lr: 2.16e-04
+2022-05-06 18:54:06,608 INFO [train.py:715] (3/8) Epoch 10, batch 10150, loss[loss=0.145, simple_loss=0.2263, pruned_loss=0.03181, over 4886.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.0338, over 973376.96 frames.], batch size: 22, lr: 2.16e-04
+2022-05-06 18:54:46,539 INFO [train.py:715] (3/8) Epoch 10, batch 10200, loss[loss=0.1655, simple_loss=0.2288, pruned_loss=0.05109, over 4978.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03372, over 973303.12 frames.], batch size: 14, lr: 2.16e-04
+2022-05-06 18:55:25,657 INFO [train.py:715] (3/8) Epoch 10, batch 10250, loss[loss=0.1308, simple_loss=0.2058, pruned_loss=0.02793, over 4802.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03381, over 973511.11 frames.], batch size: 21, lr: 2.16e-04
+2022-05-06 18:56:04,510 INFO [train.py:715] (3/8) Epoch 10, batch 10300, loss[loss=0.126, simple_loss=0.2016, pruned_loss=0.02524, over 4819.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03341, over 973294.18 frames.], batch size: 25, lr: 2.16e-04
+2022-05-06 18:56:44,440 INFO [train.py:715] (3/8) Epoch 10, batch 10350, loss[loss=0.1284, simple_loss=0.2105, pruned_loss=0.02312, over 4758.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03356, over 972802.33 frames.], batch size: 19, lr: 2.16e-04
+2022-05-06 18:57:24,436 INFO [train.py:715] (3/8) Epoch 10, batch 10400, loss[loss=0.1287, simple_loss=0.2061, pruned_loss=0.02565, over 4875.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03344, over 973872.53 frames.], batch size: 20, lr: 2.16e-04
+2022-05-06 18:58:02,842 INFO [train.py:715] (3/8) Epoch 10, batch 10450, loss[loss=0.1265, simple_loss=0.2114, pruned_loss=0.0208, over 4878.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2129, pruned_loss=0.03386, over 973448.71 frames.], batch size: 22, lr: 2.16e-04
+2022-05-06 18:58:41,112 INFO [train.py:715] (3/8) Epoch 10, batch 10500, loss[loss=0.1393, simple_loss=0.2139, pruned_loss=0.03239, over 4821.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03394, over 973245.79 frames.], batch size: 25, lr: 2.16e-04
+2022-05-06 18:59:20,246 INFO [train.py:715] (3/8) Epoch 10, batch 10550, loss[loss=0.1315, simple_loss=0.1966, pruned_loss=0.03323, over 4798.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03349, over 972695.40 frames.], batch size: 14, lr: 2.16e-04
+2022-05-06 18:59:59,206 INFO [train.py:715] (3/8) Epoch 10, batch 10600, loss[loss=0.1221, simple_loss=0.1897, pruned_loss=0.02728, over 4976.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03342, over 972241.19 frames.], batch size: 28, lr: 2.16e-04
+2022-05-06 19:00:37,418 INFO [train.py:715] (3/8) Epoch 10, batch 10650, loss[loss=0.1379, simple_loss=0.2175, pruned_loss=0.02916, over 4915.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03318, over 972762.90 frames.], batch size: 18, lr: 2.16e-04
+2022-05-06 19:01:16,839 INFO [train.py:715] (3/8) Epoch 10, batch 10700, loss[loss=0.1839, simple_loss=0.2475, pruned_loss=0.06015, over 4866.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03326, over 972767.69 frames.], batch size: 20, lr: 2.16e-04
+2022-05-06 19:01:56,164 INFO [train.py:715] (3/8) Epoch 10, batch 10750, loss[loss=0.1162, simple_loss=0.187, pruned_loss=0.02271, over 4854.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03276, over 973244.89 frames.], batch size: 13, lr: 2.16e-04
+2022-05-06 19:02:34,991 INFO [train.py:715] (3/8) Epoch 10, batch 10800, loss[loss=0.1336, simple_loss=0.2005, pruned_loss=0.03333, over 4882.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.03302, over 973519.10 frames.], batch size: 17, lr: 2.16e-04
+2022-05-06 19:03:13,437 INFO [train.py:715] (3/8) Epoch 10, batch 10850, loss[loss=0.158, simple_loss=0.2297, pruned_loss=0.04315, over 4756.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2121, pruned_loss=0.03346, over 973201.51 frames.], batch size: 19, lr: 2.16e-04
+2022-05-06 19:03:52,880 INFO [train.py:715] (3/8) Epoch 10, batch 10900, loss[loss=0.1718, simple_loss=0.2451, pruned_loss=0.04927, over 4909.00 frames.], tot_loss[loss=0.1407, simple_loss=0.213, pruned_loss=0.03413, over 973125.34 frames.], batch size: 19, lr: 2.16e-04
+2022-05-06 19:04:31,791 INFO [train.py:715] (3/8) Epoch 10, batch 10950, loss[loss=0.11, simple_loss=0.1853, pruned_loss=0.01729, over 4776.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03357, over 972820.48 frames.], batch size: 12, lr: 2.16e-04
+2022-05-06 19:05:10,346 INFO [train.py:715] (3/8) Epoch 10, batch 11000, loss[loss=0.123, simple_loss=0.1991, pruned_loss=0.02343, over 4816.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03339, over 972789.87 frames.], batch size: 26, lr: 2.16e-04
+2022-05-06 19:05:49,499 INFO [train.py:715] (3/8) Epoch 10, batch 11050, loss[loss=0.1456, simple_loss=0.2179, pruned_loss=0.03665, over 4882.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03359, over 972456.97 frames.], batch size: 22, lr: 2.16e-04
+2022-05-06 19:06:29,282 INFO [train.py:715] (3/8) Epoch 10, batch 11100, loss[loss=0.1438, simple_loss=0.2141, pruned_loss=0.03674, over 4818.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03375, over 972237.35 frames.], batch size: 15, lr: 2.16e-04
+2022-05-06 19:07:07,081 INFO [train.py:715] (3/8) Epoch 10, batch 11150, loss[loss=0.1433, simple_loss=0.2223, pruned_loss=0.03216, over 4915.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2126, pruned_loss=0.03311, over 972485.10 frames.], batch size: 29, lr: 2.16e-04
+2022-05-06 19:07:46,336 INFO [train.py:715] (3/8) Epoch 10, batch 11200, loss[loss=0.1147, simple_loss=0.1908, pruned_loss=0.0193, over 4931.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.03348, over 971810.55 frames.], batch size: 18, lr: 2.16e-04
+2022-05-06 19:08:25,401 INFO [train.py:715] (3/8) Epoch 10, batch 11250, loss[loss=0.1427, simple_loss=0.1999, pruned_loss=0.04274, over 4850.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03331, over 971705.68 frames.], batch size: 34, lr: 2.16e-04
+2022-05-06 19:09:03,755 INFO [train.py:715] (3/8) Epoch 10, batch 11300, loss[loss=0.1434, simple_loss=0.2301, pruned_loss=0.0283, over 4837.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03326, over 972577.02 frames.], batch size: 20, lr: 2.16e-04
+2022-05-06 19:09:42,489 INFO [train.py:715] (3/8) Epoch 10, batch 11350, loss[loss=0.1487, simple_loss=0.2263, pruned_loss=0.03557, over 4755.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2131, pruned_loss=0.03333, over 972686.34 frames.], batch size: 16, lr: 2.16e-04
+2022-05-06 19:10:21,472 INFO [train.py:715] (3/8) Epoch 10, batch 11400, loss[loss=0.1704, simple_loss=0.2407, pruned_loss=0.05007, over 4898.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03339, over 972855.94 frames.], batch size: 17, lr: 2.16e-04
+2022-05-06 19:11:00,936 INFO [train.py:715] (3/8) Epoch 10, batch 11450, loss[loss=0.1496, simple_loss=0.2297, pruned_loss=0.03475, over 4832.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03331, over 972359.03 frames.], batch size: 26, lr: 2.16e-04
+2022-05-06 19:11:38,821 INFO [train.py:715] (3/8) Epoch 10, batch 11500, loss[loss=0.1244, simple_loss=0.1891, pruned_loss=0.02984, over 4838.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03335, over 972355.91 frames.], batch size: 13, lr: 2.16e-04
+2022-05-06 19:12:17,874 INFO [train.py:715] (3/8) Epoch 10, batch 11550, loss[loss=0.1218, simple_loss=0.193, pruned_loss=0.02526, over 4878.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03339, over 972842.81 frames.], batch size: 16, lr: 2.16e-04
+2022-05-06 19:12:57,424 INFO [train.py:715] (3/8) Epoch 10, batch 11600, loss[loss=0.142, simple_loss=0.2065, pruned_loss=0.03877, over 4852.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03331, over 972604.65 frames.], batch size: 30, lr: 2.16e-04
+2022-05-06 19:13:35,825 INFO [train.py:715] (3/8) Epoch 10, batch 11650, loss[loss=0.1105, simple_loss=0.1945, pruned_loss=0.01325, over 4819.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2111, pruned_loss=0.03274, over 972587.88 frames.], batch size: 21, lr: 2.16e-04
+2022-05-06 19:14:14,881 INFO [train.py:715] (3/8) Epoch 10, batch 11700, loss[loss=0.17, simple_loss=0.2311, pruned_loss=0.0545, over 4866.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2113, pruned_loss=0.03273, over 972592.87 frames.], batch size: 20, lr: 2.16e-04
+2022-05-06 19:14:53,450 INFO [train.py:715] (3/8) Epoch 10, batch 11750, loss[loss=0.1508, simple_loss=0.2172, pruned_loss=0.0422, over 4682.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03267, over 972569.86 frames.], batch size: 15, lr: 2.15e-04
+2022-05-06 19:15:32,371 INFO [train.py:715] (3/8) Epoch 10, batch 11800, loss[loss=0.1619, simple_loss=0.2269, pruned_loss=0.04846, over 4916.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2118, pruned_loss=0.03341, over 972664.64 frames.], batch size: 17, lr: 2.15e-04
+2022-05-06 19:16:10,394 INFO [train.py:715] (3/8) Epoch 10, batch 11850, loss[loss=0.1104, simple_loss=0.1782, pruned_loss=0.02129, over 4806.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2115, pruned_loss=0.03285, over 972626.34 frames.], batch size: 12, lr: 2.15e-04
+2022-05-06 19:16:49,165 INFO [train.py:715] (3/8) Epoch 10, batch 11900, loss[loss=0.1477, simple_loss=0.2226, pruned_loss=0.0364, over 4844.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03403, over 972713.02 frames.], batch size: 15, lr: 2.15e-04
+2022-05-06 19:17:30,483 INFO [train.py:715] (3/8) Epoch 10, batch 11950, loss[loss=0.1413, simple_loss=0.2121, pruned_loss=0.03531, over 4946.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03367, over 971988.48 frames.], batch size: 29, lr: 2.15e-04
+2022-05-06 19:18:09,370 INFO [train.py:715] (3/8) Epoch 10, batch 12000, loss[loss=0.1297, simple_loss=0.2067, pruned_loss=0.02633, over 4957.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.03336, over 972754.15 frames.], batch size: 39, lr: 2.15e-04
+2022-05-06 19:18:09,370 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 19:18:19,015 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1908, pruned_loss=0.01105, over 914524.00 frames.
+2022-05-06 19:18:57,896 INFO [train.py:715] (3/8) Epoch 10, batch 12050, loss[loss=0.1293, simple_loss=0.2021, pruned_loss=0.02819, over 4964.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03348, over 972299.11 frames.], batch size: 21, lr: 2.15e-04
+2022-05-06 19:19:37,117 INFO [train.py:715] (3/8) Epoch 10, batch 12100, loss[loss=0.1576, simple_loss=0.2397, pruned_loss=0.03777, over 4972.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03358, over 973193.39 frames.], batch size: 25, lr: 2.15e-04
+2022-05-06 19:20:16,377 INFO [train.py:715] (3/8) Epoch 10, batch 12150, loss[loss=0.1322, simple_loss=0.2191, pruned_loss=0.02267, over 4933.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03411, over 973210.61 frames.], batch size: 23, lr: 2.15e-04
+2022-05-06 19:20:55,542 INFO [train.py:715] (3/8) Epoch 10, batch 12200, loss[loss=0.1642, simple_loss=0.2305, pruned_loss=0.04901, over 4934.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03383, over 973759.02 frames.], batch size: 39, lr: 2.15e-04
+2022-05-06 19:21:34,084 INFO [train.py:715] (3/8) Epoch 10, batch 12250, loss[loss=0.1402, simple_loss=0.2135, pruned_loss=0.03344, over 4929.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03365, over 973032.06 frames.], batch size: 21, lr: 2.15e-04
+2022-05-06 19:22:13,030 INFO [train.py:715] (3/8) Epoch 10, batch 12300, loss[loss=0.1263, simple_loss=0.1956, pruned_loss=0.02847, over 4860.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03377, over 973520.84 frames.], batch size: 32, lr: 2.15e-04
+2022-05-06 19:22:51,958 INFO [train.py:715] (3/8) Epoch 10, batch 12350, loss[loss=0.1052, simple_loss=0.1761, pruned_loss=0.0171, over 4852.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2126, pruned_loss=0.03385, over 971987.51 frames.], batch size: 13, lr: 2.15e-04
+2022-05-06 19:23:30,787 INFO [train.py:715] (3/8) Epoch 10, batch 12400, loss[loss=0.1752, simple_loss=0.2551, pruned_loss=0.04762, over 4880.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03392, over 972331.41 frames.], batch size: 22, lr: 2.15e-04
+2022-05-06 19:24:09,217 INFO [train.py:715] (3/8) Epoch 10, batch 12450, loss[loss=0.1438, simple_loss=0.2197, pruned_loss=0.03393, over 4953.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03375, over 972503.52 frames.], batch size: 39, lr: 2.15e-04
+2022-05-06 19:24:48,250 INFO [train.py:715] (3/8) Epoch 10, batch 12500, loss[loss=0.1362, simple_loss=0.2109, pruned_loss=0.0308, over 4753.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03407, over 971794.53 frames.], batch size: 16, lr: 2.15e-04
+2022-05-06 19:25:27,026 INFO [train.py:715] (3/8) Epoch 10, batch 12550, loss[loss=0.1277, simple_loss=0.2081, pruned_loss=0.02371, over 4843.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03406, over 971989.45 frames.], batch size: 15, lr: 2.15e-04
+2022-05-06 19:26:05,181 INFO [train.py:715] (3/8) Epoch 10, batch 12600, loss[loss=0.1594, simple_loss=0.2371, pruned_loss=0.04083, over 4884.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03448, over 972290.62 frames.], batch size: 19, lr: 2.15e-04
+2022-05-06 19:26:43,471 INFO [train.py:715] (3/8) Epoch 10, batch 12650, loss[loss=0.1494, simple_loss=0.2089, pruned_loss=0.04494, over 4967.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2135, pruned_loss=0.03466, over 971683.39 frames.], batch size: 15, lr: 2.15e-04
+2022-05-06 19:27:22,407 INFO [train.py:715] (3/8) Epoch 10, batch 12700, loss[loss=0.1387, simple_loss=0.2063, pruned_loss=0.03553, over 4882.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2132, pruned_loss=0.03419, over 972387.01 frames.], batch size: 16, lr: 2.15e-04
+2022-05-06 19:28:00,752 INFO [train.py:715] (3/8) Epoch 10, batch 12750, loss[loss=0.1057, simple_loss=0.1829, pruned_loss=0.01431, over 4946.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03424, over 972024.60 frames.], batch size: 21, lr: 2.15e-04
+2022-05-06 19:28:39,214 INFO [train.py:715] (3/8) Epoch 10, batch 12800, loss[loss=0.1385, simple_loss=0.2283, pruned_loss=0.02433, over 4813.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.0338, over 972978.72 frames.], batch size: 27, lr: 2.15e-04
+2022-05-06 19:29:18,645 INFO [train.py:715] (3/8) Epoch 10, batch 12850, loss[loss=0.1164, simple_loss=0.1925, pruned_loss=0.0202, over 4730.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03372, over 972253.70 frames.], batch size: 16, lr: 2.15e-04
+2022-05-06 19:29:57,809 INFO [train.py:715] (3/8) Epoch 10, batch 12900, loss[loss=0.1298, simple_loss=0.2007, pruned_loss=0.02941, over 4802.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03361, over 972227.22 frames.], batch size: 25, lr: 2.15e-04
+2022-05-06 19:30:36,227 INFO [train.py:715] (3/8) Epoch 10, batch 12950, loss[loss=0.1551, simple_loss=0.2254, pruned_loss=0.04239, over 4756.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03372, over 972112.61 frames.], batch size: 16, lr: 2.15e-04
+2022-05-06 19:31:14,797 INFO [train.py:715] (3/8) Epoch 10, batch 13000, loss[loss=0.1639, simple_loss=0.2497, pruned_loss=0.03908, over 4956.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03383, over 971779.44 frames.], batch size: 39, lr: 2.15e-04
+2022-05-06 19:31:54,374 INFO [train.py:715] (3/8) Epoch 10, batch 13050, loss[loss=0.1485, simple_loss=0.2119, pruned_loss=0.04255, over 4766.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2137, pruned_loss=0.03359, over 972193.00 frames.], batch size: 19, lr: 2.15e-04
+2022-05-06 19:32:32,859 INFO [train.py:715] (3/8) Epoch 10, batch 13100, loss[loss=0.1726, simple_loss=0.2355, pruned_loss=0.05486, over 4842.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03348, over 972208.48 frames.], batch size: 30, lr: 2.15e-04
+2022-05-06 19:33:11,983 INFO [train.py:715] (3/8) Epoch 10, batch 13150, loss[loss=0.12, simple_loss=0.1922, pruned_loss=0.0239, over 4975.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03345, over 971649.93 frames.], batch size: 28, lr: 2.15e-04
+2022-05-06 19:33:51,011 INFO [train.py:715] (3/8) Epoch 10, batch 13200, loss[loss=0.1378, simple_loss=0.2244, pruned_loss=0.02561, over 4894.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03416, over 971728.81 frames.], batch size: 22, lr: 2.15e-04
+2022-05-06 19:34:30,051 INFO [train.py:715] (3/8) Epoch 10, batch 13250, loss[loss=0.1477, simple_loss=0.2173, pruned_loss=0.03904, over 4961.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03388, over 972528.94 frames.], batch size: 35, lr: 2.15e-04
+2022-05-06 19:35:08,701 INFO [train.py:715] (3/8) Epoch 10, batch 13300, loss[loss=0.1272, simple_loss=0.1882, pruned_loss=0.03307, over 4932.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2126, pruned_loss=0.03386, over 972278.79 frames.], batch size: 18, lr: 2.15e-04
+2022-05-06 19:35:47,103 INFO [train.py:715] (3/8) Epoch 10, batch 13350, loss[loss=0.1487, simple_loss=0.2216, pruned_loss=0.03795, over 4754.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.03351, over 972450.65 frames.], batch size: 16, lr: 2.15e-04
+2022-05-06 19:36:26,375 INFO [train.py:715] (3/8) Epoch 10, batch 13400, loss[loss=0.1297, simple_loss=0.2061, pruned_loss=0.02662, over 4843.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.0329, over 972366.29 frames.], batch size: 15, lr: 2.15e-04
+2022-05-06 19:37:04,722 INFO [train.py:715] (3/8) Epoch 10, batch 13450, loss[loss=0.1334, simple_loss=0.197, pruned_loss=0.0349, over 4990.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03324, over 972067.70 frames.], batch size: 35, lr: 2.15e-04
+2022-05-06 19:37:42,964 INFO [train.py:715] (3/8) Epoch 10, batch 13500, loss[loss=0.1273, simple_loss=0.1966, pruned_loss=0.02897, over 4771.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03394, over 971609.27 frames.], batch size: 17, lr: 2.15e-04
+2022-05-06 19:38:22,035 INFO [train.py:715] (3/8) Epoch 10, batch 13550, loss[loss=0.1533, simple_loss=0.2219, pruned_loss=0.04233, over 4846.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2139, pruned_loss=0.03417, over 971847.00 frames.], batch size: 30, lr: 2.15e-04
+2022-05-06 19:39:00,609 INFO [train.py:715] (3/8) Epoch 10, batch 13600, loss[loss=0.1575, simple_loss=0.2276, pruned_loss=0.04369, over 4751.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.03404, over 972348.46 frames.], batch size: 14, lr: 2.15e-04
+2022-05-06 19:39:39,007 INFO [train.py:715] (3/8) Epoch 10, batch 13650, loss[loss=0.1363, simple_loss=0.212, pruned_loss=0.03029, over 4811.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03373, over 972834.44 frames.], batch size: 21, lr: 2.15e-04
+2022-05-06 19:40:17,581 INFO [train.py:715] (3/8) Epoch 10, batch 13700, loss[loss=0.1583, simple_loss=0.2167, pruned_loss=0.04994, over 4833.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03396, over 972441.66 frames.], batch size: 30, lr: 2.15e-04
+2022-05-06 19:40:57,641 INFO [train.py:715] (3/8) Epoch 10, batch 13750, loss[loss=0.1786, simple_loss=0.2574, pruned_loss=0.04985, over 4978.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.03427, over 972488.39 frames.], batch size: 39, lr: 2.15e-04
+2022-05-06 19:41:37,004 INFO [train.py:715] (3/8) Epoch 10, batch 13800, loss[loss=0.1587, simple_loss=0.2331, pruned_loss=0.04217, over 4948.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2145, pruned_loss=0.03448, over 971804.14 frames.], batch size: 21, lr: 2.15e-04
+2022-05-06 19:42:15,510 INFO [train.py:715] (3/8) Epoch 10, batch 13850, loss[loss=0.1499, simple_loss=0.2134, pruned_loss=0.04315, over 4967.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03463, over 972001.36 frames.], batch size: 14, lr: 2.15e-04
+2022-05-06 19:42:55,147 INFO [train.py:715] (3/8) Epoch 10, batch 13900, loss[loss=0.1194, simple_loss=0.1972, pruned_loss=0.02076, over 4839.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03433, over 971647.95 frames.], batch size: 13, lr: 2.15e-04
+2022-05-06 19:43:33,822 INFO [train.py:715] (3/8) Epoch 10, batch 13950, loss[loss=0.128, simple_loss=0.2067, pruned_loss=0.02462, over 4931.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03393, over 971775.51 frames.], batch size: 29, lr: 2.15e-04
+2022-05-06 19:44:12,830 INFO [train.py:715] (3/8) Epoch 10, batch 14000, loss[loss=0.1451, simple_loss=0.2203, pruned_loss=0.03494, over 4688.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03412, over 971290.53 frames.], batch size: 15, lr: 2.15e-04
+2022-05-06 19:44:51,236 INFO [train.py:715] (3/8) Epoch 10, batch 14050, loss[loss=0.2059, simple_loss=0.2592, pruned_loss=0.07632, over 4841.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.0341, over 971175.47 frames.], batch size: 32, lr: 2.15e-04
+2022-05-06 19:45:30,770 INFO [train.py:715] (3/8) Epoch 10, batch 14100, loss[loss=0.145, simple_loss=0.2149, pruned_loss=0.03756, over 4777.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.03429, over 970857.21 frames.], batch size: 18, lr: 2.15e-04
+2022-05-06 19:46:09,126 INFO [train.py:715] (3/8) Epoch 10, batch 14150, loss[loss=0.1616, simple_loss=0.2204, pruned_loss=0.05143, over 4981.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2142, pruned_loss=0.03423, over 972388.00 frames.], batch size: 31, lr: 2.15e-04
+2022-05-06 19:46:47,032 INFO [train.py:715] (3/8) Epoch 10, batch 14200, loss[loss=0.1434, simple_loss=0.2202, pruned_loss=0.03328, over 4900.00 frames.], tot_loss[loss=0.1424, simple_loss=0.215, pruned_loss=0.03493, over 972225.78 frames.], batch size: 17, lr: 2.15e-04
+2022-05-06 19:47:26,632 INFO [train.py:715] (3/8) Epoch 10, batch 14250, loss[loss=0.1384, simple_loss=0.1998, pruned_loss=0.03848, over 4847.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03484, over 971979.94 frames.], batch size: 30, lr: 2.15e-04
+2022-05-06 19:48:05,008 INFO [train.py:715] (3/8) Epoch 10, batch 14300, loss[loss=0.1705, simple_loss=0.2335, pruned_loss=0.05376, over 4918.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03465, over 971959.08 frames.], batch size: 39, lr: 2.15e-04
+2022-05-06 19:48:43,127 INFO [train.py:715] (3/8) Epoch 10, batch 14350, loss[loss=0.1606, simple_loss=0.2278, pruned_loss=0.04673, over 4932.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03454, over 972901.02 frames.], batch size: 29, lr: 2.15e-04
+2022-05-06 19:49:21,567 INFO [train.py:715] (3/8) Epoch 10, batch 14400, loss[loss=0.119, simple_loss=0.1971, pruned_loss=0.02042, over 4863.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03437, over 972753.07 frames.], batch size: 20, lr: 2.15e-04
+2022-05-06 19:50:01,195 INFO [train.py:715] (3/8) Epoch 10, batch 14450, loss[loss=0.1257, simple_loss=0.2015, pruned_loss=0.02494, over 4935.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.03427, over 972690.80 frames.], batch size: 29, lr: 2.15e-04
+2022-05-06 19:50:39,563 INFO [train.py:715] (3/8) Epoch 10, batch 14500, loss[loss=0.1374, simple_loss=0.2135, pruned_loss=0.03059, over 4774.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03434, over 972067.13 frames.], batch size: 19, lr: 2.15e-04
+2022-05-06 19:51:17,697 INFO [train.py:715] (3/8) Epoch 10, batch 14550, loss[loss=0.1264, simple_loss=0.1965, pruned_loss=0.02809, over 4889.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03399, over 972923.47 frames.], batch size: 19, lr: 2.15e-04
+2022-05-06 19:51:57,348 INFO [train.py:715] (3/8) Epoch 10, batch 14600, loss[loss=0.1539, simple_loss=0.2355, pruned_loss=0.03611, over 4825.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.03371, over 972857.38 frames.], batch size: 13, lr: 2.15e-04
+2022-05-06 19:52:35,982 INFO [train.py:715] (3/8) Epoch 10, batch 14650, loss[loss=0.1357, simple_loss=0.2109, pruned_loss=0.03029, over 4815.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03323, over 972501.72 frames.], batch size: 26, lr: 2.15e-04
+2022-05-06 19:53:14,373 INFO [train.py:715] (3/8) Epoch 10, batch 14700, loss[loss=0.1772, simple_loss=0.246, pruned_loss=0.0542, over 4826.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03314, over 971732.55 frames.], batch size: 26, lr: 2.15e-04
+2022-05-06 19:53:53,328 INFO [train.py:715] (3/8) Epoch 10, batch 14750, loss[loss=0.1348, simple_loss=0.2098, pruned_loss=0.02989, over 4849.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2108, pruned_loss=0.03276, over 971694.34 frames.], batch size: 20, lr: 2.15e-04
+2022-05-06 19:54:33,135 INFO [train.py:715] (3/8) Epoch 10, batch 14800, loss[loss=0.1531, simple_loss=0.2206, pruned_loss=0.0428, over 4899.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.03256, over 971759.30 frames.], batch size: 22, lr: 2.15e-04
+2022-05-06 19:55:12,162 INFO [train.py:715] (3/8) Epoch 10, batch 14850, loss[loss=0.1506, simple_loss=0.2319, pruned_loss=0.03465, over 4729.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03218, over 971496.36 frames.], batch size: 16, lr: 2.15e-04
+2022-05-06 19:55:50,177 INFO [train.py:715] (3/8) Epoch 10, batch 14900, loss[loss=0.1555, simple_loss=0.2216, pruned_loss=0.04468, over 4906.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03267, over 971934.70 frames.], batch size: 39, lr: 2.15e-04
+2022-05-06 19:56:30,296 INFO [train.py:715] (3/8) Epoch 10, batch 14950, loss[loss=0.1752, simple_loss=0.2475, pruned_loss=0.05141, over 4870.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03275, over 972359.32 frames.], batch size: 39, lr: 2.15e-04
+2022-05-06 19:57:09,818 INFO [train.py:715] (3/8) Epoch 10, batch 15000, loss[loss=0.1584, simple_loss=0.2372, pruned_loss=0.03976, over 4955.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03235, over 972331.61 frames.], batch size: 21, lr: 2.15e-04
+2022-05-06 19:57:09,818 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 19:57:19,462 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1909, pruned_loss=0.01111, over 914524.00 frames.
+2022-05-06 19:57:59,086 INFO [train.py:715] (3/8) Epoch 10, batch 15050, loss[loss=0.1246, simple_loss=0.2029, pruned_loss=0.02314, over 4773.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03306, over 971850.99 frames.], batch size: 18, lr: 2.15e-04
+2022-05-06 19:58:38,147 INFO [train.py:715] (3/8) Epoch 10, batch 15100, loss[loss=0.1269, simple_loss=0.2091, pruned_loss=0.0224, over 4920.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2114, pruned_loss=0.03317, over 971287.08 frames.], batch size: 29, lr: 2.15e-04
+2022-05-06 19:59:17,366 INFO [train.py:715] (3/8) Epoch 10, batch 15150, loss[loss=0.1422, simple_loss=0.2153, pruned_loss=0.03451, over 4892.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2113, pruned_loss=0.03298, over 971770.71 frames.], batch size: 19, lr: 2.14e-04
+2022-05-06 19:59:56,361 INFO [train.py:715] (3/8) Epoch 10, batch 15200, loss[loss=0.1366, simple_loss=0.208, pruned_loss=0.03261, over 4904.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2117, pruned_loss=0.03339, over 972252.69 frames.], batch size: 17, lr: 2.14e-04
+2022-05-06 20:00:35,745 INFO [train.py:715] (3/8) Epoch 10, batch 15250, loss[loss=0.1151, simple_loss=0.1955, pruned_loss=0.01735, over 4927.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03303, over 972513.10 frames.], batch size: 23, lr: 2.14e-04
+2022-05-06 20:01:14,789 INFO [train.py:715] (3/8) Epoch 10, batch 15300, loss[loss=0.114, simple_loss=0.1923, pruned_loss=0.01783, over 4811.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03272, over 972126.61 frames.], batch size: 26, lr: 2.14e-04
+2022-05-06 20:01:54,058 INFO [train.py:715] (3/8) Epoch 10, batch 15350, loss[loss=0.1401, simple_loss=0.2036, pruned_loss=0.03834, over 4737.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03283, over 971990.55 frames.], batch size: 16, lr: 2.14e-04
+2022-05-06 20:02:34,124 INFO [train.py:715] (3/8) Epoch 10, batch 15400, loss[loss=0.1511, simple_loss=0.2207, pruned_loss=0.04076, over 4930.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03293, over 971689.62 frames.], batch size: 23, lr: 2.14e-04
+2022-05-06 20:03:13,393 INFO [train.py:715] (3/8) Epoch 10, batch 15450, loss[loss=0.1274, simple_loss=0.1987, pruned_loss=0.02808, over 4969.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03291, over 972135.89 frames.], batch size: 24, lr: 2.14e-04
+2022-05-06 20:03:53,466 INFO [train.py:715] (3/8) Epoch 10, batch 15500, loss[loss=0.1715, simple_loss=0.2358, pruned_loss=0.05363, over 4978.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03325, over 972089.95 frames.], batch size: 39, lr: 2.14e-04
+2022-05-06 20:04:32,471 INFO [train.py:715] (3/8) Epoch 10, batch 15550, loss[loss=0.1254, simple_loss=0.1924, pruned_loss=0.02919, over 4794.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03338, over 972859.32 frames.], batch size: 12, lr: 2.14e-04
+2022-05-06 20:05:11,888 INFO [train.py:715] (3/8) Epoch 10, batch 15600, loss[loss=0.1197, simple_loss=0.1948, pruned_loss=0.02235, over 4971.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03352, over 972893.06 frames.], batch size: 15, lr: 2.14e-04
+2022-05-06 20:05:50,244 INFO [train.py:715] (3/8) Epoch 10, batch 15650, loss[loss=0.1276, simple_loss=0.2006, pruned_loss=0.02734, over 4803.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03355, over 972604.37 frames.], batch size: 24, lr: 2.14e-04
+2022-05-06 20:06:28,933 INFO [train.py:715] (3/8) Epoch 10, batch 15700, loss[loss=0.125, simple_loss=0.1902, pruned_loss=0.02995, over 4897.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03335, over 973863.73 frames.], batch size: 19, lr: 2.14e-04
+2022-05-06 20:07:08,406 INFO [train.py:715] (3/8) Epoch 10, batch 15750, loss[loss=0.1593, simple_loss=0.2304, pruned_loss=0.04416, over 4819.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.03432, over 973946.45 frames.], batch size: 26, lr: 2.14e-04
+2022-05-06 20:07:46,970 INFO [train.py:715] (3/8) Epoch 10, batch 15800, loss[loss=0.1309, simple_loss=0.2064, pruned_loss=0.02772, over 4760.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03384, over 973800.06 frames.], batch size: 19, lr: 2.14e-04
+2022-05-06 20:08:26,771 INFO [train.py:715] (3/8) Epoch 10, batch 15850, loss[loss=0.1311, simple_loss=0.1981, pruned_loss=0.03199, over 4949.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.0344, over 973818.67 frames.], batch size: 24, lr: 2.14e-04
+2022-05-06 20:09:05,639 INFO [train.py:715] (3/8) Epoch 10, batch 15900, loss[loss=0.1276, simple_loss=0.1994, pruned_loss=0.02787, over 4969.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2144, pruned_loss=0.03431, over 973727.96 frames.], batch size: 15, lr: 2.14e-04
+2022-05-06 20:09:44,839 INFO [train.py:715] (3/8) Epoch 10, batch 15950, loss[loss=0.1503, simple_loss=0.2169, pruned_loss=0.04181, over 4756.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2146, pruned_loss=0.03437, over 973064.18 frames.], batch size: 16, lr: 2.14e-04
+2022-05-06 20:10:23,753 INFO [train.py:715] (3/8) Epoch 10, batch 16000, loss[loss=0.1424, simple_loss=0.214, pruned_loss=0.03544, over 4788.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03389, over 972943.43 frames.], batch size: 17, lr: 2.14e-04
+2022-05-06 20:11:02,643 INFO [train.py:715] (3/8) Epoch 10, batch 16050, loss[loss=0.128, simple_loss=0.2067, pruned_loss=0.02467, over 4790.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.0338, over 972909.92 frames.], batch size: 24, lr: 2.14e-04
+2022-05-06 20:11:41,916 INFO [train.py:715] (3/8) Epoch 10, batch 16100, loss[loss=0.1467, simple_loss=0.2237, pruned_loss=0.0348, over 4900.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03375, over 973040.13 frames.], batch size: 17, lr: 2.14e-04
+2022-05-06 20:12:21,129 INFO [train.py:715] (3/8) Epoch 10, batch 16150, loss[loss=0.1147, simple_loss=0.1864, pruned_loss=0.02156, over 4961.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.0333, over 972987.75 frames.], batch size: 15, lr: 2.14e-04
+2022-05-06 20:13:01,096 INFO [train.py:715] (3/8) Epoch 10, batch 16200, loss[loss=0.1677, simple_loss=0.2347, pruned_loss=0.0503, over 4757.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.0337, over 972442.39 frames.], batch size: 19, lr: 2.14e-04
+2022-05-06 20:13:40,633 INFO [train.py:715] (3/8) Epoch 10, batch 16250, loss[loss=0.1232, simple_loss=0.1972, pruned_loss=0.02459, over 4764.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2137, pruned_loss=0.03347, over 971756.84 frames.], batch size: 19, lr: 2.14e-04
+2022-05-06 20:14:19,846 INFO [train.py:715] (3/8) Epoch 10, batch 16300, loss[loss=0.1445, simple_loss=0.2152, pruned_loss=0.03686, over 4905.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.0335, over 972564.68 frames.], batch size: 19, lr: 2.14e-04
+2022-05-06 20:14:59,851 INFO [train.py:715] (3/8) Epoch 10, batch 16350, loss[loss=0.1362, simple_loss=0.2144, pruned_loss=0.02898, over 4807.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03287, over 973029.63 frames.], batch size: 21, lr: 2.14e-04
+2022-05-06 20:15:39,244 INFO [train.py:715] (3/8) Epoch 10, batch 16400, loss[loss=0.1517, simple_loss=0.2164, pruned_loss=0.04346, over 4975.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.03367, over 972676.07 frames.], batch size: 15, lr: 2.14e-04
+2022-05-06 20:16:18,979 INFO [train.py:715] (3/8) Epoch 10, batch 16450, loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.03474, over 4877.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03395, over 971922.60 frames.], batch size: 22, lr: 2.14e-04
+2022-05-06 20:16:57,470 INFO [train.py:715] (3/8) Epoch 10, batch 16500, loss[loss=0.1259, simple_loss=0.1926, pruned_loss=0.02954, over 4887.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03393, over 972158.39 frames.], batch size: 16, lr: 2.14e-04
+2022-05-06 20:17:36,175 INFO [train.py:715] (3/8) Epoch 10, batch 16550, loss[loss=0.1465, simple_loss=0.2146, pruned_loss=0.0392, over 4945.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03404, over 972016.96 frames.], batch size: 39, lr: 2.14e-04
+2022-05-06 20:18:15,834 INFO [train.py:715] (3/8) Epoch 10, batch 16600, loss[loss=0.1305, simple_loss=0.1986, pruned_loss=0.03122, over 4920.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03388, over 971703.73 frames.], batch size: 18, lr: 2.14e-04
+2022-05-06 20:18:54,014 INFO [train.py:715] (3/8) Epoch 10, batch 16650, loss[loss=0.1517, simple_loss=0.2225, pruned_loss=0.04046, over 4875.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.03359, over 971941.82 frames.], batch size: 32, lr: 2.14e-04
+2022-05-06 20:19:33,369 INFO [train.py:715] (3/8) Epoch 10, batch 16700, loss[loss=0.1604, simple_loss=0.2299, pruned_loss=0.04544, over 4802.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.03399, over 971845.79 frames.], batch size: 21, lr: 2.14e-04
+2022-05-06 20:20:12,357 INFO [train.py:715] (3/8) Epoch 10, batch 16750, loss[loss=0.1728, simple_loss=0.2498, pruned_loss=0.04791, over 4943.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03322, over 971976.03 frames.], batch size: 21, lr: 2.14e-04
+2022-05-06 20:20:52,512 INFO [train.py:715] (3/8) Epoch 10, batch 16800, loss[loss=0.1107, simple_loss=0.1806, pruned_loss=0.02038, over 4956.00 frames.], tot_loss[loss=0.1385, simple_loss=0.211, pruned_loss=0.03298, over 972144.98 frames.], batch size: 15, lr: 2.14e-04
+2022-05-06 20:21:31,831 INFO [train.py:715] (3/8) Epoch 10, batch 16850, loss[loss=0.1405, simple_loss=0.212, pruned_loss=0.03452, over 4880.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2114, pruned_loss=0.03296, over 972845.41 frames.], batch size: 22, lr: 2.14e-04
+2022-05-06 20:22:11,632 INFO [train.py:715] (3/8) Epoch 10, batch 16900, loss[loss=0.1476, simple_loss=0.2174, pruned_loss=0.03892, over 4752.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03325, over 972337.46 frames.], batch size: 19, lr: 2.14e-04
+2022-05-06 20:22:51,672 INFO [train.py:715] (3/8) Epoch 10, batch 16950, loss[loss=0.1775, simple_loss=0.2583, pruned_loss=0.04829, over 4745.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03364, over 972892.52 frames.], batch size: 19, lr: 2.14e-04
+2022-05-06 20:23:29,923 INFO [train.py:715] (3/8) Epoch 10, batch 17000, loss[loss=0.1118, simple_loss=0.1823, pruned_loss=0.02068, over 4783.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03324, over 972041.95 frames.], batch size: 17, lr: 2.14e-04
+2022-05-06 20:24:09,513 INFO [train.py:715] (3/8) Epoch 10, batch 17050, loss[loss=0.1682, simple_loss=0.2367, pruned_loss=0.04979, over 4908.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03327, over 972041.36 frames.], batch size: 17, lr: 2.14e-04
+2022-05-06 20:24:48,211 INFO [train.py:715] (3/8) Epoch 10, batch 17100, loss[loss=0.1393, simple_loss=0.2135, pruned_loss=0.03254, over 4828.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03288, over 971796.81 frames.], batch size: 25, lr: 2.14e-04
+2022-05-06 20:25:27,434 INFO [train.py:715] (3/8) Epoch 10, batch 17150, loss[loss=0.1222, simple_loss=0.1994, pruned_loss=0.02249, over 4790.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03276, over 972060.09 frames.], batch size: 24, lr: 2.14e-04
+2022-05-06 20:26:07,398 INFO [train.py:715] (3/8) Epoch 10, batch 17200, loss[loss=0.1196, simple_loss=0.1924, pruned_loss=0.02336, over 4905.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03304, over 972289.49 frames.], batch size: 17, lr: 2.14e-04
+2022-05-06 20:26:47,006 INFO [train.py:715] (3/8) Epoch 10, batch 17250, loss[loss=0.1333, simple_loss=0.2086, pruned_loss=0.029, over 4852.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03332, over 971587.27 frames.], batch size: 15, lr: 2.14e-04
+2022-05-06 20:27:26,663 INFO [train.py:715] (3/8) Epoch 10, batch 17300, loss[loss=0.1603, simple_loss=0.24, pruned_loss=0.04024, over 4686.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03381, over 971760.38 frames.], batch size: 15, lr: 2.14e-04
+2022-05-06 20:28:05,425 INFO [train.py:715] (3/8) Epoch 10, batch 17350, loss[loss=0.1597, simple_loss=0.2297, pruned_loss=0.04481, over 4925.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03354, over 971621.72 frames.], batch size: 23, lr: 2.14e-04
+2022-05-06 20:28:44,828 INFO [train.py:715] (3/8) Epoch 10, batch 17400, loss[loss=0.132, simple_loss=0.2194, pruned_loss=0.02231, over 4837.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03334, over 971505.92 frames.], batch size: 15, lr: 2.14e-04
+2022-05-06 20:29:24,008 INFO [train.py:715] (3/8) Epoch 10, batch 17450, loss[loss=0.1317, simple_loss=0.2075, pruned_loss=0.02792, over 4874.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03324, over 971692.93 frames.], batch size: 20, lr: 2.14e-04
+2022-05-06 20:30:02,982 INFO [train.py:715] (3/8) Epoch 10, batch 17500, loss[loss=0.1421, simple_loss=0.2212, pruned_loss=0.0315, over 4971.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03351, over 971659.37 frames.], batch size: 35, lr: 2.14e-04
+2022-05-06 20:30:42,977 INFO [train.py:715] (3/8) Epoch 10, batch 17550, loss[loss=0.1353, simple_loss=0.2064, pruned_loss=0.0321, over 4799.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03405, over 972667.78 frames.], batch size: 17, lr: 2.14e-04
+2022-05-06 20:31:21,945 INFO [train.py:715] (3/8) Epoch 10, batch 17600, loss[loss=0.1326, simple_loss=0.2008, pruned_loss=0.03224, over 4971.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03392, over 972324.78 frames.], batch size: 15, lr: 2.14e-04
+2022-05-06 20:32:01,507 INFO [train.py:715] (3/8) Epoch 10, batch 17650, loss[loss=0.1372, simple_loss=0.2022, pruned_loss=0.03611, over 4745.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03394, over 971391.20 frames.], batch size: 12, lr: 2.14e-04
+2022-05-06 20:32:40,266 INFO [train.py:715] (3/8) Epoch 10, batch 17700, loss[loss=0.1297, simple_loss=0.2106, pruned_loss=0.02438, over 4804.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03402, over 971759.68 frames.], batch size: 21, lr: 2.14e-04
+2022-05-06 20:33:20,044 INFO [train.py:715] (3/8) Epoch 10, batch 17750, loss[loss=0.1213, simple_loss=0.1993, pruned_loss=0.02168, over 4824.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2137, pruned_loss=0.03323, over 971849.23 frames.], batch size: 26, lr: 2.14e-04
+2022-05-06 20:33:59,770 INFO [train.py:715] (3/8) Epoch 10, batch 17800, loss[loss=0.1243, simple_loss=0.2035, pruned_loss=0.02252, over 4912.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2131, pruned_loss=0.03315, over 972260.48 frames.], batch size: 18, lr: 2.14e-04
+2022-05-06 20:34:38,715 INFO [train.py:715] (3/8) Epoch 10, batch 17850, loss[loss=0.129, simple_loss=0.2045, pruned_loss=0.02678, over 4778.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03349, over 972090.29 frames.], batch size: 17, lr: 2.14e-04
+2022-05-06 20:35:18,469 INFO [train.py:715] (3/8) Epoch 10, batch 17900, loss[loss=0.1427, simple_loss=0.2087, pruned_loss=0.03835, over 4826.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03359, over 971553.69 frames.], batch size: 30, lr: 2.14e-04
+2022-05-06 20:35:57,402 INFO [train.py:715] (3/8) Epoch 10, batch 17950, loss[loss=0.1338, simple_loss=0.2049, pruned_loss=0.03142, over 4914.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03336, over 971945.78 frames.], batch size: 17, lr: 2.14e-04
+2022-05-06 20:36:36,022 INFO [train.py:715] (3/8) Epoch 10, batch 18000, loss[loss=0.1322, simple_loss=0.2094, pruned_loss=0.0275, over 4841.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03376, over 972406.31 frames.], batch size: 30, lr: 2.14e-04
+2022-05-06 20:36:36,023 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 20:36:45,529 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1064, simple_loss=0.1906, pruned_loss=0.01104, over 914524.00 frames.
+2022-05-06 20:37:24,889 INFO [train.py:715] (3/8) Epoch 10, batch 18050, loss[loss=0.1069, simple_loss=0.1724, pruned_loss=0.02067, over 4984.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03384, over 972817.34 frames.], batch size: 14, lr: 2.14e-04
+2022-05-06 20:38:03,981 INFO [train.py:715] (3/8) Epoch 10, batch 18100, loss[loss=0.1452, simple_loss=0.2146, pruned_loss=0.03788, over 4969.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03397, over 973082.47 frames.], batch size: 35, lr: 2.14e-04
+2022-05-06 20:38:43,263 INFO [train.py:715] (3/8) Epoch 10, batch 18150, loss[loss=0.1573, simple_loss=0.2249, pruned_loss=0.04488, over 4881.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2137, pruned_loss=0.03373, over 972857.07 frames.], batch size: 16, lr: 2.14e-04
+2022-05-06 20:39:21,942 INFO [train.py:715] (3/8) Epoch 10, batch 18200, loss[loss=0.1394, simple_loss=0.2085, pruned_loss=0.03521, over 4931.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.03383, over 973427.98 frames.], batch size: 21, lr: 2.14e-04
+2022-05-06 20:40:00,620 INFO [train.py:715] (3/8) Epoch 10, batch 18250, loss[loss=0.1163, simple_loss=0.1977, pruned_loss=0.01746, over 4918.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03354, over 973381.42 frames.], batch size: 18, lr: 2.14e-04
+2022-05-06 20:40:40,112 INFO [train.py:715] (3/8) Epoch 10, batch 18300, loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03476, over 4787.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03389, over 973040.94 frames.], batch size: 17, lr: 2.14e-04
+2022-05-06 20:41:19,473 INFO [train.py:715] (3/8) Epoch 10, batch 18350, loss[loss=0.1354, simple_loss=0.21, pruned_loss=0.03041, over 4864.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03368, over 972887.45 frames.], batch size: 16, lr: 2.14e-04
+2022-05-06 20:41:57,961 INFO [train.py:715] (3/8) Epoch 10, batch 18400, loss[loss=0.1461, simple_loss=0.233, pruned_loss=0.02963, over 4928.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2138, pruned_loss=0.03374, over 973645.96 frames.], batch size: 29, lr: 2.14e-04
+2022-05-06 20:42:37,149 INFO [train.py:715] (3/8) Epoch 10, batch 18450, loss[loss=0.1422, simple_loss=0.2114, pruned_loss=0.03645, over 4866.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03313, over 973600.25 frames.], batch size: 16, lr: 2.14e-04
+2022-05-06 20:43:16,006 INFO [train.py:715] (3/8) Epoch 10, batch 18500, loss[loss=0.122, simple_loss=0.1911, pruned_loss=0.0264, over 4649.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03309, over 972231.29 frames.], batch size: 13, lr: 2.14e-04
+2022-05-06 20:43:55,529 INFO [train.py:715] (3/8) Epoch 10, batch 18550, loss[loss=0.1439, simple_loss=0.2199, pruned_loss=0.03393, over 4817.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2135, pruned_loss=0.03334, over 972245.63 frames.], batch size: 27, lr: 2.13e-04
+2022-05-06 20:44:33,843 INFO [train.py:715] (3/8) Epoch 10, batch 18600, loss[loss=0.1458, simple_loss=0.206, pruned_loss=0.04282, over 4848.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03361, over 971914.55 frames.], batch size: 30, lr: 2.13e-04
+2022-05-06 20:45:13,254 INFO [train.py:715] (3/8) Epoch 10, batch 18650, loss[loss=0.1321, simple_loss=0.2129, pruned_loss=0.02562, over 4942.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.0336, over 971741.87 frames.], batch size: 21, lr: 2.13e-04
+2022-05-06 20:45:52,992 INFO [train.py:715] (3/8) Epoch 10, batch 18700, loss[loss=0.1325, simple_loss=0.2087, pruned_loss=0.02817, over 4745.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.03409, over 971110.41 frames.], batch size: 16, lr: 2.13e-04
+2022-05-06 20:46:31,253 INFO [train.py:715] (3/8) Epoch 10, batch 18750, loss[loss=0.1463, simple_loss=0.2192, pruned_loss=0.03669, over 4750.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.03383, over 971251.24 frames.], batch size: 16, lr: 2.13e-04
+2022-05-06 20:47:10,633 INFO [train.py:715] (3/8) Epoch 10, batch 18800, loss[loss=0.1554, simple_loss=0.2292, pruned_loss=0.04078, over 4778.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2136, pruned_loss=0.03335, over 970665.52 frames.], batch size: 14, lr: 2.13e-04
+2022-05-06 20:47:50,112 INFO [train.py:715] (3/8) Epoch 10, batch 18850, loss[loss=0.1506, simple_loss=0.2135, pruned_loss=0.04388, over 4890.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03331, over 970947.42 frames.], batch size: 22, lr: 2.13e-04
+2022-05-06 20:48:29,013 INFO [train.py:715] (3/8) Epoch 10, batch 18900, loss[loss=0.1246, simple_loss=0.208, pruned_loss=0.02061, over 4940.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03332, over 971672.13 frames.], batch size: 23, lr: 2.13e-04
+2022-05-06 20:49:08,063 INFO [train.py:715] (3/8) Epoch 10, batch 18950, loss[loss=0.1539, simple_loss=0.221, pruned_loss=0.04341, over 4853.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03325, over 972453.73 frames.], batch size: 20, lr: 2.13e-04
+2022-05-06 20:49:48,336 INFO [train.py:715] (3/8) Epoch 10, batch 19000, loss[loss=0.1616, simple_loss=0.2339, pruned_loss=0.04463, over 4787.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03311, over 971632.89 frames.], batch size: 17, lr: 2.13e-04
+2022-05-06 20:50:27,642 INFO [train.py:715] (3/8) Epoch 10, batch 19050, loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03601, over 4872.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03352, over 971873.12 frames.], batch size: 16, lr: 2.13e-04
+2022-05-06 20:51:06,453 INFO [train.py:715] (3/8) Epoch 10, batch 19100, loss[loss=0.2534, simple_loss=0.3068, pruned_loss=0.1001, over 4792.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03422, over 973552.59 frames.], batch size: 17, lr: 2.13e-04
+2022-05-06 20:51:46,324 INFO [train.py:715] (3/8) Epoch 10, batch 19150, loss[loss=0.1642, simple_loss=0.233, pruned_loss=0.04766, over 4857.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03407, over 973262.06 frames.], batch size: 32, lr: 2.13e-04
+2022-05-06 20:52:26,494 INFO [train.py:715] (3/8) Epoch 10, batch 19200, loss[loss=0.1207, simple_loss=0.1952, pruned_loss=0.02308, over 4897.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03394, over 972973.39 frames.], batch size: 19, lr: 2.13e-04
+2022-05-06 20:53:06,170 INFO [train.py:715] (3/8) Epoch 10, batch 19250, loss[loss=0.1416, simple_loss=0.2183, pruned_loss=0.03246, over 4842.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2137, pruned_loss=0.03375, over 973381.50 frames.], batch size: 26, lr: 2.13e-04
+2022-05-06 20:53:46,066 INFO [train.py:715] (3/8) Epoch 10, batch 19300, loss[loss=0.1492, simple_loss=0.2155, pruned_loss=0.04143, over 4995.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03449, over 973241.21 frames.], batch size: 16, lr: 2.13e-04
+2022-05-06 20:54:26,474 INFO [train.py:715] (3/8) Epoch 10, batch 19350, loss[loss=0.1074, simple_loss=0.1842, pruned_loss=0.01531, over 4802.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03421, over 972777.80 frames.], batch size: 14, lr: 2.13e-04
+2022-05-06 20:55:06,649 INFO [train.py:715] (3/8) Epoch 10, batch 19400, loss[loss=0.1325, simple_loss=0.1978, pruned_loss=0.03365, over 4763.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03396, over 971760.16 frames.], batch size: 12, lr: 2.13e-04
+2022-05-06 20:55:45,796 INFO [train.py:715] (3/8) Epoch 10, batch 19450, loss[loss=0.1442, simple_loss=0.2106, pruned_loss=0.03887, over 4809.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03401, over 971681.11 frames.], batch size: 15, lr: 2.13e-04
+2022-05-06 20:56:25,406 INFO [train.py:715] (3/8) Epoch 10, batch 19500, loss[loss=0.1387, simple_loss=0.2142, pruned_loss=0.0316, over 4980.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03407, over 972300.42 frames.], batch size: 24, lr: 2.13e-04
+2022-05-06 20:57:04,610 INFO [train.py:715] (3/8) Epoch 10, batch 19550, loss[loss=0.1371, simple_loss=0.2171, pruned_loss=0.02857, over 4923.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03383, over 972015.63 frames.], batch size: 23, lr: 2.13e-04
+2022-05-06 20:57:43,332 INFO [train.py:715] (3/8) Epoch 10, batch 19600, loss[loss=0.1366, simple_loss=0.211, pruned_loss=0.03115, over 4852.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03356, over 972072.09 frames.], batch size: 15, lr: 2.13e-04
+2022-05-06 20:58:22,307 INFO [train.py:715] (3/8) Epoch 10, batch 19650, loss[loss=0.1117, simple_loss=0.1826, pruned_loss=0.02044, over 4797.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2118, pruned_loss=0.03335, over 972187.36 frames.], batch size: 12, lr: 2.13e-04
+2022-05-06 20:59:01,941 INFO [train.py:715] (3/8) Epoch 10, batch 19700, loss[loss=0.1918, simple_loss=0.2607, pruned_loss=0.06145, over 4785.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.03295, over 972081.87 frames.], batch size: 18, lr: 2.13e-04
+2022-05-06 20:59:41,296 INFO [train.py:715] (3/8) Epoch 10, batch 19750, loss[loss=0.1469, simple_loss=0.2324, pruned_loss=0.03073, over 4867.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.03334, over 971895.52 frames.], batch size: 20, lr: 2.13e-04
+2022-05-06 21:00:19,603 INFO [train.py:715] (3/8) Epoch 10, batch 19800, loss[loss=0.1663, simple_loss=0.236, pruned_loss=0.04836, over 4822.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03322, over 972898.24 frames.], batch size: 26, lr: 2.13e-04
+2022-05-06 21:00:59,242 INFO [train.py:715] (3/8) Epoch 10, batch 19850, loss[loss=0.1518, simple_loss=0.2259, pruned_loss=0.03881, over 4782.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03329, over 972781.29 frames.], batch size: 17, lr: 2.13e-04
+2022-05-06 21:01:38,757 INFO [train.py:715] (3/8) Epoch 10, batch 19900, loss[loss=0.1465, simple_loss=0.2159, pruned_loss=0.03851, over 4969.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2121, pruned_loss=0.03356, over 973753.76 frames.], batch size: 35, lr: 2.13e-04
+2022-05-06 21:02:19,875 INFO [train.py:715] (3/8) Epoch 10, batch 19950, loss[loss=0.1413, simple_loss=0.2203, pruned_loss=0.03114, over 4974.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2122, pruned_loss=0.03368, over 974143.18 frames.], batch size: 14, lr: 2.13e-04
+2022-05-06 21:02:58,930 INFO [train.py:715] (3/8) Epoch 10, batch 20000, loss[loss=0.1523, simple_loss=0.2176, pruned_loss=0.04353, over 4774.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2119, pruned_loss=0.03336, over 975318.46 frames.], batch size: 17, lr: 2.13e-04
+2022-05-06 21:03:37,944 INFO [train.py:715] (3/8) Epoch 10, batch 20050, loss[loss=0.1154, simple_loss=0.1831, pruned_loss=0.02388, over 4904.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03313, over 975303.61 frames.], batch size: 17, lr: 2.13e-04
+2022-05-06 21:04:17,427 INFO [train.py:715] (3/8) Epoch 10, batch 20100, loss[loss=0.1572, simple_loss=0.2289, pruned_loss=0.04272, over 4928.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03329, over 974398.30 frames.], batch size: 18, lr: 2.13e-04
+2022-05-06 21:04:55,529 INFO [train.py:715] (3/8) Epoch 10, batch 20150, loss[loss=0.1283, simple_loss=0.211, pruned_loss=0.02278, over 4988.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03294, over 973870.11 frames.], batch size: 24, lr: 2.13e-04
+2022-05-06 21:05:34,942 INFO [train.py:715] (3/8) Epoch 10, batch 20200, loss[loss=0.1358, simple_loss=0.2195, pruned_loss=0.02603, over 4921.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03333, over 974242.72 frames.], batch size: 18, lr: 2.13e-04
+2022-05-06 21:06:13,961 INFO [train.py:715] (3/8) Epoch 10, batch 20250, loss[loss=0.1512, simple_loss=0.2216, pruned_loss=0.04042, over 4849.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2134, pruned_loss=0.03339, over 973425.29 frames.], batch size: 30, lr: 2.13e-04
+2022-05-06 21:06:52,617 INFO [train.py:715] (3/8) Epoch 10, batch 20300, loss[loss=0.1409, simple_loss=0.216, pruned_loss=0.03289, over 4897.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2134, pruned_loss=0.03338, over 972615.75 frames.], batch size: 17, lr: 2.13e-04
+2022-05-06 21:07:31,400 INFO [train.py:715] (3/8) Epoch 10, batch 20350, loss[loss=0.1281, simple_loss=0.1999, pruned_loss=0.02813, over 4954.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03341, over 971878.46 frames.], batch size: 24, lr: 2.13e-04
+2022-05-06 21:08:10,513 INFO [train.py:715] (3/8) Epoch 10, batch 20400, loss[loss=0.1405, simple_loss=0.2197, pruned_loss=0.03068, over 4812.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2141, pruned_loss=0.03355, over 972340.26 frames.], batch size: 27, lr: 2.13e-04
+2022-05-06 21:08:49,432 INFO [train.py:715] (3/8) Epoch 10, batch 20450, loss[loss=0.163, simple_loss=0.2432, pruned_loss=0.04144, over 4984.00 frames.], tot_loss[loss=0.1409, simple_loss=0.214, pruned_loss=0.03387, over 971641.14 frames.], batch size: 20, lr: 2.13e-04
+2022-05-06 21:09:27,881 INFO [train.py:715] (3/8) Epoch 10, batch 20500, loss[loss=0.1464, simple_loss=0.2179, pruned_loss=0.0375, over 4851.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03438, over 972481.30 frames.], batch size: 32, lr: 2.13e-04
+2022-05-06 21:10:06,953 INFO [train.py:715] (3/8) Epoch 10, batch 20550, loss[loss=0.1303, simple_loss=0.2051, pruned_loss=0.02775, over 4951.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03503, over 972474.51 frames.], batch size: 15, lr: 2.13e-04
+2022-05-06 21:10:46,034 INFO [train.py:715] (3/8) Epoch 10, batch 20600, loss[loss=0.1175, simple_loss=0.1929, pruned_loss=0.021, over 4852.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.03437, over 971578.57 frames.], batch size: 20, lr: 2.13e-04
+2022-05-06 21:11:25,464 INFO [train.py:715] (3/8) Epoch 10, batch 20650, loss[loss=0.1348, simple_loss=0.1977, pruned_loss=0.03597, over 4831.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2142, pruned_loss=0.03411, over 971749.94 frames.], batch size: 15, lr: 2.13e-04
+2022-05-06 21:12:04,255 INFO [train.py:715] (3/8) Epoch 10, batch 20700, loss[loss=0.1369, simple_loss=0.2153, pruned_loss=0.02923, over 4861.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03366, over 971918.24 frames.], batch size: 20, lr: 2.13e-04
+2022-05-06 21:12:44,596 INFO [train.py:715] (3/8) Epoch 10, batch 20750, loss[loss=0.1538, simple_loss=0.2285, pruned_loss=0.03955, over 4985.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.0338, over 971548.34 frames.], batch size: 24, lr: 2.13e-04
+2022-05-06 21:13:24,575 INFO [train.py:715] (3/8) Epoch 10, batch 20800, loss[loss=0.1366, simple_loss=0.2062, pruned_loss=0.03349, over 4972.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03431, over 970770.19 frames.], batch size: 28, lr: 2.13e-04
+2022-05-06 21:14:03,352 INFO [train.py:715] (3/8) Epoch 10, batch 20850, loss[loss=0.1379, simple_loss=0.2157, pruned_loss=0.03009, over 4959.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03407, over 970470.19 frames.], batch size: 15, lr: 2.13e-04
+2022-05-06 21:14:43,293 INFO [train.py:715] (3/8) Epoch 10, batch 20900, loss[loss=0.1209, simple_loss=0.2002, pruned_loss=0.02078, over 4820.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.0335, over 970543.27 frames.], batch size: 26, lr: 2.13e-04
+2022-05-06 21:15:23,756 INFO [train.py:715] (3/8) Epoch 10, batch 20950, loss[loss=0.1471, simple_loss=0.2095, pruned_loss=0.04237, over 4815.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.03377, over 970528.73 frames.], batch size: 15, lr: 2.13e-04
+2022-05-06 21:16:02,698 INFO [train.py:715] (3/8) Epoch 10, batch 21000, loss[loss=0.1505, simple_loss=0.2219, pruned_loss=0.03953, over 4852.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.03374, over 971006.22 frames.], batch size: 20, lr: 2.13e-04
+2022-05-06 21:16:02,699 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 21:16:12,202 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1909, pruned_loss=0.01111, over 914524.00 frames.
+2022-05-06 21:16:51,725 INFO [train.py:715] (3/8) Epoch 10, batch 21050, loss[loss=0.1201, simple_loss=0.1976, pruned_loss=0.02133, over 4974.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03386, over 972057.46 frames.], batch size: 24, lr: 2.13e-04
+2022-05-06 21:17:32,530 INFO [train.py:715] (3/8) Epoch 10, batch 21100, loss[loss=0.1678, simple_loss=0.2314, pruned_loss=0.05208, over 4937.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03393, over 971646.50 frames.], batch size: 23, lr: 2.13e-04
+2022-05-06 21:18:14,010 INFO [train.py:715] (3/8) Epoch 10, batch 21150, loss[loss=0.1702, simple_loss=0.2436, pruned_loss=0.04843, over 4849.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03395, over 971021.20 frames.], batch size: 15, lr: 2.13e-04
+2022-05-06 21:18:55,100 INFO [train.py:715] (3/8) Epoch 10, batch 21200, loss[loss=0.1293, simple_loss=0.22, pruned_loss=0.01934, over 4899.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2127, pruned_loss=0.03375, over 971248.66 frames.], batch size: 17, lr: 2.13e-04
+2022-05-06 21:19:35,765 INFO [train.py:715] (3/8) Epoch 10, batch 21250, loss[loss=0.1975, simple_loss=0.2762, pruned_loss=0.05938, over 4706.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03386, over 971072.38 frames.], batch size: 15, lr: 2.13e-04
+2022-05-06 21:20:17,429 INFO [train.py:715] (3/8) Epoch 10, batch 21300, loss[loss=0.169, simple_loss=0.2468, pruned_loss=0.04561, over 4888.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2128, pruned_loss=0.03387, over 971089.12 frames.], batch size: 16, lr: 2.13e-04
+2022-05-06 21:20:58,695 INFO [train.py:715] (3/8) Epoch 10, batch 21350, loss[loss=0.1362, simple_loss=0.205, pruned_loss=0.03367, over 4832.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03381, over 970319.03 frames.], batch size: 13, lr: 2.13e-04
+2022-05-06 21:21:39,122 INFO [train.py:715] (3/8) Epoch 10, batch 21400, loss[loss=0.1178, simple_loss=0.1962, pruned_loss=0.01971, over 4975.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.03356, over 970880.68 frames.], batch size: 28, lr: 2.13e-04
+2022-05-06 21:22:20,538 INFO [train.py:715] (3/8) Epoch 10, batch 21450, loss[loss=0.1625, simple_loss=0.2281, pruned_loss=0.04848, over 4986.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03402, over 971419.15 frames.], batch size: 15, lr: 2.13e-04
+2022-05-06 21:23:02,357 INFO [train.py:715] (3/8) Epoch 10, batch 21500, loss[loss=0.1476, simple_loss=0.2143, pruned_loss=0.04044, over 4867.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2121, pruned_loss=0.03367, over 970872.37 frames.], batch size: 38, lr: 2.13e-04
+2022-05-06 21:23:43,372 INFO [train.py:715] (3/8) Epoch 10, batch 21550, loss[loss=0.1567, simple_loss=0.2263, pruned_loss=0.04355, over 4961.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.034, over 971090.80 frames.], batch size: 35, lr: 2.13e-04
+2022-05-06 21:24:24,261 INFO [train.py:715] (3/8) Epoch 10, batch 21600, loss[loss=0.1281, simple_loss=0.2046, pruned_loss=0.02577, over 4858.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2122, pruned_loss=0.03368, over 971585.55 frames.], batch size: 20, lr: 2.13e-04
+2022-05-06 21:25:06,207 INFO [train.py:715] (3/8) Epoch 10, batch 21650, loss[loss=0.1249, simple_loss=0.1956, pruned_loss=0.0271, over 4845.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03332, over 971609.57 frames.], batch size: 12, lr: 2.13e-04
+2022-05-06 21:25:47,750 INFO [train.py:715] (3/8) Epoch 10, batch 21700, loss[loss=0.1685, simple_loss=0.2354, pruned_loss=0.05074, over 4983.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.03318, over 971810.33 frames.], batch size: 25, lr: 2.13e-04
+2022-05-06 21:26:28,008 INFO [train.py:715] (3/8) Epoch 10, batch 21750, loss[loss=0.1513, simple_loss=0.2304, pruned_loss=0.03613, over 4937.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03266, over 972658.29 frames.], batch size: 29, lr: 2.13e-04
+2022-05-06 21:27:08,993 INFO [train.py:715] (3/8) Epoch 10, batch 21800, loss[loss=0.1356, simple_loss=0.2031, pruned_loss=0.03401, over 4817.00 frames.], tot_loss[loss=0.1389, simple_loss=0.212, pruned_loss=0.03296, over 972943.13 frames.], batch size: 26, lr: 2.13e-04
+2022-05-06 21:27:50,697 INFO [train.py:715] (3/8) Epoch 10, batch 21850, loss[loss=0.1466, simple_loss=0.2248, pruned_loss=0.03422, over 4867.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.03331, over 973207.01 frames.], batch size: 22, lr: 2.13e-04
+2022-05-06 21:28:31,162 INFO [train.py:715] (3/8) Epoch 10, batch 21900, loss[loss=0.1452, simple_loss=0.2063, pruned_loss=0.04202, over 4810.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03324, over 972944.15 frames.], batch size: 13, lr: 2.13e-04
+2022-05-06 21:29:11,915 INFO [train.py:715] (3/8) Epoch 10, batch 21950, loss[loss=0.1325, simple_loss=0.2099, pruned_loss=0.02754, over 4872.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03328, over 972756.66 frames.], batch size: 16, lr: 2.13e-04
+2022-05-06 21:29:53,133 INFO [train.py:715] (3/8) Epoch 10, batch 22000, loss[loss=0.1387, simple_loss=0.2145, pruned_loss=0.03149, over 4853.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03302, over 972476.53 frames.], batch size: 30, lr: 2.12e-04
+2022-05-06 21:30:33,466 INFO [train.py:715] (3/8) Epoch 10, batch 22050, loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03368, over 4847.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.0334, over 971984.18 frames.], batch size: 20, lr: 2.12e-04
+2022-05-06 21:31:14,079 INFO [train.py:715] (3/8) Epoch 10, batch 22100, loss[loss=0.1312, simple_loss=0.2102, pruned_loss=0.0261, over 4922.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.03378, over 971627.79 frames.], batch size: 19, lr: 2.12e-04
+2022-05-06 21:31:54,935 INFO [train.py:715] (3/8) Epoch 10, batch 22150, loss[loss=0.1294, simple_loss=0.203, pruned_loss=0.02794, over 4967.00 frames.], tot_loss[loss=0.141, simple_loss=0.2141, pruned_loss=0.03392, over 971819.55 frames.], batch size: 35, lr: 2.12e-04
+2022-05-06 21:32:35,994 INFO [train.py:715] (3/8) Epoch 10, batch 22200, loss[loss=0.1376, simple_loss=0.2007, pruned_loss=0.03724, over 4795.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2136, pruned_loss=0.0336, over 971220.33 frames.], batch size: 12, lr: 2.12e-04
+2022-05-06 21:33:16,086 INFO [train.py:715] (3/8) Epoch 10, batch 22250, loss[loss=0.122, simple_loss=0.1942, pruned_loss=0.02488, over 4818.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03319, over 970713.81 frames.], batch size: 26, lr: 2.12e-04
+2022-05-06 21:33:56,739 INFO [train.py:715] (3/8) Epoch 10, batch 22300, loss[loss=0.1275, simple_loss=0.2017, pruned_loss=0.02665, over 4810.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03327, over 971050.22 frames.], batch size: 12, lr: 2.12e-04
+2022-05-06 21:34:37,775 INFO [train.py:715] (3/8) Epoch 10, batch 22350, loss[loss=0.1547, simple_loss=0.2309, pruned_loss=0.03923, over 4927.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2113, pruned_loss=0.03308, over 971139.80 frames.], batch size: 18, lr: 2.12e-04
+2022-05-06 21:35:17,623 INFO [train.py:715] (3/8) Epoch 10, batch 22400, loss[loss=0.1236, simple_loss=0.2003, pruned_loss=0.02343, over 4965.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2119, pruned_loss=0.03331, over 971914.63 frames.], batch size: 24, lr: 2.12e-04
+2022-05-06 21:35:56,791 INFO [train.py:715] (3/8) Epoch 10, batch 22450, loss[loss=0.1702, simple_loss=0.2463, pruned_loss=0.04706, over 4916.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03424, over 971778.51 frames.], batch size: 29, lr: 2.12e-04
+2022-05-06 21:36:36,728 INFO [train.py:715] (3/8) Epoch 10, batch 22500, loss[loss=0.1302, simple_loss=0.2086, pruned_loss=0.02591, over 4932.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.0337, over 971076.72 frames.], batch size: 29, lr: 2.12e-04
+2022-05-06 21:37:17,614 INFO [train.py:715] (3/8) Epoch 10, batch 22550, loss[loss=0.1226, simple_loss=0.204, pruned_loss=0.02059, over 4789.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03294, over 971719.69 frames.], batch size: 18, lr: 2.12e-04
+2022-05-06 21:37:56,429 INFO [train.py:715] (3/8) Epoch 10, batch 22600, loss[loss=0.1415, simple_loss=0.2164, pruned_loss=0.03328, over 4943.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03262, over 971999.52 frames.], batch size: 29, lr: 2.12e-04
+2022-05-06 21:38:37,510 INFO [train.py:715] (3/8) Epoch 10, batch 22650, loss[loss=0.1259, simple_loss=0.2069, pruned_loss=0.02244, over 4983.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2122, pruned_loss=0.03274, over 972534.45 frames.], batch size: 25, lr: 2.12e-04
+2022-05-06 21:39:19,367 INFO [train.py:715] (3/8) Epoch 10, batch 22700, loss[loss=0.1263, simple_loss=0.2036, pruned_loss=0.02449, over 4817.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2131, pruned_loss=0.03331, over 972081.34 frames.], batch size: 26, lr: 2.12e-04
+2022-05-06 21:40:00,109 INFO [train.py:715] (3/8) Epoch 10, batch 22750, loss[loss=0.1419, simple_loss=0.2103, pruned_loss=0.03676, over 4879.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2134, pruned_loss=0.03339, over 971779.30 frames.], batch size: 22, lr: 2.12e-04
+2022-05-06 21:40:41,326 INFO [train.py:715] (3/8) Epoch 10, batch 22800, loss[loss=0.129, simple_loss=0.2028, pruned_loss=0.0276, over 4931.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2142, pruned_loss=0.03351, over 971554.23 frames.], batch size: 29, lr: 2.12e-04
+2022-05-06 21:41:22,878 INFO [train.py:715] (3/8) Epoch 10, batch 22850, loss[loss=0.1398, simple_loss=0.2108, pruned_loss=0.03443, over 4975.00 frames.], tot_loss[loss=0.1404, simple_loss=0.214, pruned_loss=0.0334, over 971856.35 frames.], batch size: 14, lr: 2.12e-04
+2022-05-06 21:42:04,582 INFO [train.py:715] (3/8) Epoch 10, batch 22900, loss[loss=0.147, simple_loss=0.2216, pruned_loss=0.03618, over 4807.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2136, pruned_loss=0.03312, over 972358.51 frames.], batch size: 21, lr: 2.12e-04
+2022-05-06 21:42:45,054 INFO [train.py:715] (3/8) Epoch 10, batch 22950, loss[loss=0.1561, simple_loss=0.234, pruned_loss=0.03909, over 4926.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2137, pruned_loss=0.03341, over 973061.62 frames.], batch size: 21, lr: 2.12e-04
+2022-05-06 21:43:27,077 INFO [train.py:715] (3/8) Epoch 10, batch 23000, loss[loss=0.1288, simple_loss=0.1935, pruned_loss=0.03207, over 4793.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2137, pruned_loss=0.03345, over 972928.66 frames.], batch size: 14, lr: 2.12e-04
+2022-05-06 21:44:09,146 INFO [train.py:715] (3/8) Epoch 10, batch 23050, loss[loss=0.1534, simple_loss=0.2163, pruned_loss=0.04524, over 4862.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03343, over 972661.57 frames.], batch size: 32, lr: 2.12e-04
+2022-05-06 21:44:49,681 INFO [train.py:715] (3/8) Epoch 10, batch 23100, loss[loss=0.1298, simple_loss=0.2081, pruned_loss=0.0258, over 4920.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.03258, over 973043.45 frames.], batch size: 29, lr: 2.12e-04
+2022-05-06 21:45:30,868 INFO [train.py:715] (3/8) Epoch 10, batch 23150, loss[loss=0.1111, simple_loss=0.1825, pruned_loss=0.01987, over 4755.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03248, over 972557.32 frames.], batch size: 19, lr: 2.12e-04
+2022-05-06 21:46:12,872 INFO [train.py:715] (3/8) Epoch 10, batch 23200, loss[loss=0.1685, simple_loss=0.2393, pruned_loss=0.04883, over 4893.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.03261, over 972962.42 frames.], batch size: 22, lr: 2.12e-04
+2022-05-06 21:46:54,161 INFO [train.py:715] (3/8) Epoch 10, batch 23250, loss[loss=0.1599, simple_loss=0.2276, pruned_loss=0.04605, over 4943.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03282, over 973777.96 frames.], batch size: 21, lr: 2.12e-04
+2022-05-06 21:47:34,830 INFO [train.py:715] (3/8) Epoch 10, batch 23300, loss[loss=0.1395, simple_loss=0.2144, pruned_loss=0.03225, over 4848.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2118, pruned_loss=0.03245, over 973478.57 frames.], batch size: 30, lr: 2.12e-04
+2022-05-06 21:48:16,727 INFO [train.py:715] (3/8) Epoch 10, batch 23350, loss[loss=0.1622, simple_loss=0.229, pruned_loss=0.04768, over 4816.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03256, over 973515.61 frames.], batch size: 26, lr: 2.12e-04
+2022-05-06 21:48:58,865 INFO [train.py:715] (3/8) Epoch 10, batch 23400, loss[loss=0.1639, simple_loss=0.2297, pruned_loss=0.04907, over 4780.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03263, over 973419.53 frames.], batch size: 18, lr: 2.12e-04
+2022-05-06 21:49:39,773 INFO [train.py:715] (3/8) Epoch 10, batch 23450, loss[loss=0.1171, simple_loss=0.1935, pruned_loss=0.02036, over 4783.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2116, pruned_loss=0.03286, over 972540.66 frames.], batch size: 17, lr: 2.12e-04
+2022-05-06 21:50:20,145 INFO [train.py:715] (3/8) Epoch 10, batch 23500, loss[loss=0.1553, simple_loss=0.2364, pruned_loss=0.03713, over 4922.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03331, over 971907.89 frames.], batch size: 17, lr: 2.12e-04
+2022-05-06 21:51:02,212 INFO [train.py:715] (3/8) Epoch 10, batch 23550, loss[loss=0.1362, simple_loss=0.205, pruned_loss=0.03369, over 4971.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03329, over 971540.06 frames.], batch size: 15, lr: 2.12e-04
+2022-05-06 21:51:43,365 INFO [train.py:715] (3/8) Epoch 10, batch 23600, loss[loss=0.1325, simple_loss=0.2081, pruned_loss=0.02848, over 4877.00 frames.], tot_loss[loss=0.1385, simple_loss=0.211, pruned_loss=0.033, over 972232.18 frames.], batch size: 16, lr: 2.12e-04
+2022-05-06 21:52:23,128 INFO [train.py:715] (3/8) Epoch 10, batch 23650, loss[loss=0.1429, simple_loss=0.2106, pruned_loss=0.03759, over 4907.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2108, pruned_loss=0.03301, over 972254.70 frames.], batch size: 19, lr: 2.12e-04
+2022-05-06 21:53:03,649 INFO [train.py:715] (3/8) Epoch 10, batch 23700, loss[loss=0.1514, simple_loss=0.2293, pruned_loss=0.03674, over 4791.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2119, pruned_loss=0.03319, over 973004.68 frames.], batch size: 21, lr: 2.12e-04
+2022-05-06 21:53:44,220 INFO [train.py:715] (3/8) Epoch 10, batch 23750, loss[loss=0.1771, simple_loss=0.2424, pruned_loss=0.0559, over 4978.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03333, over 973393.36 frames.], batch size: 39, lr: 2.12e-04
+2022-05-06 21:54:24,358 INFO [train.py:715] (3/8) Epoch 10, batch 23800, loss[loss=0.1356, simple_loss=0.2077, pruned_loss=0.03171, over 4943.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03374, over 972572.51 frames.], batch size: 39, lr: 2.12e-04
+2022-05-06 21:55:04,949 INFO [train.py:715] (3/8) Epoch 10, batch 23850, loss[loss=0.1473, simple_loss=0.2224, pruned_loss=0.03611, over 4922.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03369, over 972993.31 frames.], batch size: 18, lr: 2.12e-04
+2022-05-06 21:55:46,220 INFO [train.py:715] (3/8) Epoch 10, batch 23900, loss[loss=0.145, simple_loss=0.2139, pruned_loss=0.038, over 4865.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2139, pruned_loss=0.03396, over 972621.42 frames.], batch size: 16, lr: 2.12e-04
+2022-05-06 21:56:25,837 INFO [train.py:715] (3/8) Epoch 10, batch 23950, loss[loss=0.1764, simple_loss=0.258, pruned_loss=0.04738, over 4866.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2142, pruned_loss=0.0337, over 972774.99 frames.], batch size: 20, lr: 2.12e-04
+2022-05-06 21:57:06,219 INFO [train.py:715] (3/8) Epoch 10, batch 24000, loss[loss=0.1581, simple_loss=0.2347, pruned_loss=0.04073, over 4990.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.0337, over 973030.08 frames.], batch size: 28, lr: 2.12e-04
+2022-05-06 21:57:06,220 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 21:57:15,893 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1061, simple_loss=0.1905, pruned_loss=0.01087, over 914524.00 frames.
+2022-05-06 21:57:55,804 INFO [train.py:715] (3/8) Epoch 10, batch 24050, loss[loss=0.1151, simple_loss=0.1873, pruned_loss=0.02149, over 4773.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03298, over 972587.95 frames.], batch size: 12, lr: 2.12e-04
+2022-05-06 21:58:36,846 INFO [train.py:715] (3/8) Epoch 10, batch 24100, loss[loss=0.1195, simple_loss=0.195, pruned_loss=0.02194, over 4965.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2109, pruned_loss=0.03274, over 972522.13 frames.], batch size: 25, lr: 2.12e-04
+2022-05-06 21:59:18,108 INFO [train.py:715] (3/8) Epoch 10, batch 24150, loss[loss=0.1413, simple_loss=0.219, pruned_loss=0.03183, over 4936.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03303, over 972407.47 frames.], batch size: 21, lr: 2.12e-04
+2022-05-06 21:59:57,441 INFO [train.py:715] (3/8) Epoch 10, batch 24200, loss[loss=0.1224, simple_loss=0.1942, pruned_loss=0.02534, over 4832.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03302, over 972405.67 frames.], batch size: 15, lr: 2.12e-04
+2022-05-06 22:00:38,183 INFO [train.py:715] (3/8) Epoch 10, batch 24250, loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.0297, over 4985.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03325, over 972504.49 frames.], batch size: 24, lr: 2.12e-04
+2022-05-06 22:01:19,296 INFO [train.py:715] (3/8) Epoch 10, batch 24300, loss[loss=0.1722, simple_loss=0.234, pruned_loss=0.05513, over 4853.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.0331, over 973026.74 frames.], batch size: 20, lr: 2.12e-04
+2022-05-06 22:01:59,416 INFO [train.py:715] (3/8) Epoch 10, batch 24350, loss[loss=0.1295, simple_loss=0.2047, pruned_loss=0.02713, over 4787.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03275, over 973018.60 frames.], batch size: 17, lr: 2.12e-04
+2022-05-06 22:02:39,458 INFO [train.py:715] (3/8) Epoch 10, batch 24400, loss[loss=0.1446, simple_loss=0.2054, pruned_loss=0.04189, over 4956.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03311, over 972943.98 frames.], batch size: 35, lr: 2.12e-04
+2022-05-06 22:03:20,173 INFO [train.py:715] (3/8) Epoch 10, batch 24450, loss[loss=0.1361, simple_loss=0.2112, pruned_loss=0.03051, over 4925.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03311, over 972519.75 frames.], batch size: 18, lr: 2.12e-04
+2022-05-06 22:04:01,138 INFO [train.py:715] (3/8) Epoch 10, batch 24500, loss[loss=0.1516, simple_loss=0.2252, pruned_loss=0.039, over 4802.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03351, over 972293.06 frames.], batch size: 21, lr: 2.12e-04
+2022-05-06 22:04:40,220 INFO [train.py:715] (3/8) Epoch 10, batch 24550, loss[loss=0.1246, simple_loss=0.1965, pruned_loss=0.02636, over 4758.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03392, over 972617.86 frames.], batch size: 19, lr: 2.12e-04
+2022-05-06 22:05:20,207 INFO [train.py:715] (3/8) Epoch 10, batch 24600, loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.03525, over 4917.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03361, over 972893.78 frames.], batch size: 39, lr: 2.12e-04
+2022-05-06 22:06:00,576 INFO [train.py:715] (3/8) Epoch 10, batch 24650, loss[loss=0.1677, simple_loss=0.247, pruned_loss=0.04419, over 4962.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2129, pruned_loss=0.03367, over 972633.03 frames.], batch size: 24, lr: 2.12e-04
+2022-05-06 22:06:39,587 INFO [train.py:715] (3/8) Epoch 10, batch 24700, loss[loss=0.1219, simple_loss=0.198, pruned_loss=0.02294, over 4976.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03426, over 973007.59 frames.], batch size: 24, lr: 2.12e-04
+2022-05-06 22:07:18,188 INFO [train.py:715] (3/8) Epoch 10, batch 24750, loss[loss=0.1313, simple_loss=0.204, pruned_loss=0.02928, over 4828.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03463, over 972906.21 frames.], batch size: 26, lr: 2.12e-04
+2022-05-06 22:07:57,675 INFO [train.py:715] (3/8) Epoch 10, batch 24800, loss[loss=0.1127, simple_loss=0.1886, pruned_loss=0.01842, over 4833.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03417, over 972672.17 frames.], batch size: 27, lr: 2.12e-04
+2022-05-06 22:08:36,821 INFO [train.py:715] (3/8) Epoch 10, batch 24850, loss[loss=0.1537, simple_loss=0.2195, pruned_loss=0.04397, over 4863.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.0341, over 973328.06 frames.], batch size: 30, lr: 2.12e-04
+2022-05-06 22:09:14,896 INFO [train.py:715] (3/8) Epoch 10, batch 24900, loss[loss=0.1532, simple_loss=0.2137, pruned_loss=0.0463, over 4809.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03396, over 973898.05 frames.], batch size: 12, lr: 2.12e-04
+2022-05-06 22:09:54,524 INFO [train.py:715] (3/8) Epoch 10, batch 24950, loss[loss=0.1211, simple_loss=0.2029, pruned_loss=0.01965, over 4987.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2142, pruned_loss=0.03416, over 974241.70 frames.], batch size: 28, lr: 2.12e-04
+2022-05-06 22:10:34,374 INFO [train.py:715] (3/8) Epoch 10, batch 25000, loss[loss=0.1256, simple_loss=0.1976, pruned_loss=0.02676, over 4889.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.03355, over 973971.35 frames.], batch size: 22, lr: 2.12e-04
+2022-05-06 22:11:13,225 INFO [train.py:715] (3/8) Epoch 10, batch 25050, loss[loss=0.1451, simple_loss=0.218, pruned_loss=0.03608, over 4839.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03417, over 973754.84 frames.], batch size: 32, lr: 2.12e-04
+2022-05-06 22:11:52,696 INFO [train.py:715] (3/8) Epoch 10, batch 25100, loss[loss=0.1444, simple_loss=0.2145, pruned_loss=0.03713, over 4790.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2124, pruned_loss=0.03346, over 973587.79 frames.], batch size: 17, lr: 2.12e-04
+2022-05-06 22:12:32,718 INFO [train.py:715] (3/8) Epoch 10, batch 25150, loss[loss=0.1602, simple_loss=0.2385, pruned_loss=0.04099, over 4784.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2129, pruned_loss=0.03381, over 973066.48 frames.], batch size: 14, lr: 2.12e-04
+2022-05-06 22:13:12,209 INFO [train.py:715] (3/8) Epoch 10, batch 25200, loss[loss=0.146, simple_loss=0.2157, pruned_loss=0.03819, over 4920.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03378, over 973541.04 frames.], batch size: 17, lr: 2.12e-04
+2022-05-06 22:13:50,343 INFO [train.py:715] (3/8) Epoch 10, batch 25250, loss[loss=0.1363, simple_loss=0.211, pruned_loss=0.03076, over 4901.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03367, over 973461.62 frames.], batch size: 19, lr: 2.12e-04
+2022-05-06 22:14:29,218 INFO [train.py:715] (3/8) Epoch 10, batch 25300, loss[loss=0.1581, simple_loss=0.2289, pruned_loss=0.04368, over 4692.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03324, over 973346.90 frames.], batch size: 15, lr: 2.12e-04
+2022-05-06 22:15:08,862 INFO [train.py:715] (3/8) Epoch 10, batch 25350, loss[loss=0.1551, simple_loss=0.2318, pruned_loss=0.03917, over 4967.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03358, over 973060.07 frames.], batch size: 35, lr: 2.12e-04
+2022-05-06 22:15:47,380 INFO [train.py:715] (3/8) Epoch 10, batch 25400, loss[loss=0.12, simple_loss=0.1977, pruned_loss=0.02109, over 4921.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03353, over 973482.37 frames.], batch size: 29, lr: 2.12e-04
+2022-05-06 22:16:26,238 INFO [train.py:715] (3/8) Epoch 10, batch 25450, loss[loss=0.1204, simple_loss=0.1939, pruned_loss=0.02349, over 4879.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2123, pruned_loss=0.03368, over 973857.23 frames.], batch size: 20, lr: 2.12e-04
+2022-05-06 22:17:06,160 INFO [train.py:715] (3/8) Epoch 10, batch 25500, loss[loss=0.1258, simple_loss=0.2036, pruned_loss=0.02397, over 4818.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03358, over 974039.43 frames.], batch size: 27, lr: 2.11e-04
+2022-05-06 22:17:45,980 INFO [train.py:715] (3/8) Epoch 10, batch 25550, loss[loss=0.1081, simple_loss=0.1785, pruned_loss=0.0189, over 4825.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03333, over 973772.94 frames.], batch size: 26, lr: 2.11e-04
+2022-05-06 22:18:24,960 INFO [train.py:715] (3/8) Epoch 10, batch 25600, loss[loss=0.1473, simple_loss=0.2293, pruned_loss=0.03266, over 4804.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2117, pruned_loss=0.03304, over 973559.57 frames.], batch size: 21, lr: 2.11e-04
+2022-05-06 22:19:05,111 INFO [train.py:715] (3/8) Epoch 10, batch 25650, loss[loss=0.1443, simple_loss=0.2168, pruned_loss=0.03587, over 4703.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.0332, over 973171.98 frames.], batch size: 15, lr: 2.11e-04
+2022-05-06 22:19:45,487 INFO [train.py:715] (3/8) Epoch 10, batch 25700, loss[loss=0.1408, simple_loss=0.2228, pruned_loss=0.02939, over 4973.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03333, over 973483.81 frames.], batch size: 25, lr: 2.11e-04
+2022-05-06 22:20:25,349 INFO [train.py:715] (3/8) Epoch 10, batch 25750, loss[loss=0.1489, simple_loss=0.2075, pruned_loss=0.0451, over 4897.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03403, over 972808.21 frames.], batch size: 22, lr: 2.11e-04
+2022-05-06 22:21:04,757 INFO [train.py:715] (3/8) Epoch 10, batch 25800, loss[loss=0.1467, simple_loss=0.2217, pruned_loss=0.03581, over 4826.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.03403, over 974210.28 frames.], batch size: 27, lr: 2.11e-04
+2022-05-06 22:21:45,292 INFO [train.py:715] (3/8) Epoch 10, batch 25850, loss[loss=0.1255, simple_loss=0.1957, pruned_loss=0.02761, over 4803.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03403, over 974363.95 frames.], batch size: 14, lr: 2.11e-04
+2022-05-06 22:22:25,222 INFO [train.py:715] (3/8) Epoch 10, batch 25900, loss[loss=0.1193, simple_loss=0.2022, pruned_loss=0.01817, over 4746.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03336, over 973305.11 frames.], batch size: 19, lr: 2.11e-04
+2022-05-06 22:23:03,942 INFO [train.py:715] (3/8) Epoch 10, batch 25950, loss[loss=0.1508, simple_loss=0.2219, pruned_loss=0.0398, over 4935.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03379, over 973371.21 frames.], batch size: 23, lr: 2.11e-04
+2022-05-06 22:23:42,718 INFO [train.py:715] (3/8) Epoch 10, batch 26000, loss[loss=0.1531, simple_loss=0.2361, pruned_loss=0.03499, over 4872.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03428, over 973028.57 frames.], batch size: 38, lr: 2.11e-04
+2022-05-06 22:24:21,988 INFO [train.py:715] (3/8) Epoch 10, batch 26050, loss[loss=0.1295, simple_loss=0.2023, pruned_loss=0.02832, over 4662.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03399, over 972277.86 frames.], batch size: 13, lr: 2.11e-04
+2022-05-06 22:25:00,975 INFO [train.py:715] (3/8) Epoch 10, batch 26100, loss[loss=0.1099, simple_loss=0.1837, pruned_loss=0.01809, over 4777.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2122, pruned_loss=0.03378, over 972394.00 frames.], batch size: 17, lr: 2.11e-04
+2022-05-06 22:25:40,337 INFO [train.py:715] (3/8) Epoch 10, batch 26150, loss[loss=0.1594, simple_loss=0.2249, pruned_loss=0.04693, over 4767.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2116, pruned_loss=0.03381, over 972455.15 frames.], batch size: 19, lr: 2.11e-04
+2022-05-06 22:26:21,097 INFO [train.py:715] (3/8) Epoch 10, batch 26200, loss[loss=0.1509, simple_loss=0.2126, pruned_loss=0.04466, over 4844.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2124, pruned_loss=0.03393, over 972731.49 frames.], batch size: 32, lr: 2.11e-04
+2022-05-06 22:27:00,350 INFO [train.py:715] (3/8) Epoch 10, batch 26250, loss[loss=0.1467, simple_loss=0.2104, pruned_loss=0.04148, over 4921.00 frames.], tot_loss[loss=0.14, simple_loss=0.2123, pruned_loss=0.03384, over 972978.48 frames.], batch size: 18, lr: 2.11e-04
+2022-05-06 22:27:39,999 INFO [train.py:715] (3/8) Epoch 10, batch 26300, loss[loss=0.1158, simple_loss=0.1905, pruned_loss=0.02055, over 4931.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2116, pruned_loss=0.03337, over 972254.57 frames.], batch size: 29, lr: 2.11e-04
+2022-05-06 22:28:19,567 INFO [train.py:715] (3/8) Epoch 10, batch 26350, loss[loss=0.1368, simple_loss=0.2114, pruned_loss=0.03111, over 4759.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2114, pruned_loss=0.03338, over 972226.44 frames.], batch size: 12, lr: 2.11e-04
+2022-05-06 22:28:59,166 INFO [train.py:715] (3/8) Epoch 10, batch 26400, loss[loss=0.1294, simple_loss=0.2068, pruned_loss=0.026, over 4891.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2112, pruned_loss=0.03358, over 972493.43 frames.], batch size: 19, lr: 2.11e-04
+2022-05-06 22:29:38,870 INFO [train.py:715] (3/8) Epoch 10, batch 26450, loss[loss=0.1161, simple_loss=0.192, pruned_loss=0.02009, over 4816.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2114, pruned_loss=0.03305, over 971717.97 frames.], batch size: 25, lr: 2.11e-04
+2022-05-06 22:30:18,684 INFO [train.py:715] (3/8) Epoch 10, batch 26500, loss[loss=0.1385, simple_loss=0.2129, pruned_loss=0.03205, over 4875.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2118, pruned_loss=0.03333, over 971823.57 frames.], batch size: 16, lr: 2.11e-04
+2022-05-06 22:30:59,097 INFO [train.py:715] (3/8) Epoch 10, batch 26550, loss[loss=0.1344, simple_loss=0.2154, pruned_loss=0.02672, over 4982.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2117, pruned_loss=0.03304, over 971610.10 frames.], batch size: 24, lr: 2.11e-04
+2022-05-06 22:31:37,640 INFO [train.py:715] (3/8) Epoch 10, batch 26600, loss[loss=0.1893, simple_loss=0.2466, pruned_loss=0.06601, over 4787.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2121, pruned_loss=0.0338, over 971262.46 frames.], batch size: 14, lr: 2.11e-04
+2022-05-06 22:32:17,161 INFO [train.py:715] (3/8) Epoch 10, batch 26650, loss[loss=0.108, simple_loss=0.1809, pruned_loss=0.01754, over 4809.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2119, pruned_loss=0.03363, over 970814.14 frames.], batch size: 21, lr: 2.11e-04
+2022-05-06 22:32:56,672 INFO [train.py:715] (3/8) Epoch 10, batch 26700, loss[loss=0.1296, simple_loss=0.2119, pruned_loss=0.02364, over 4907.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2109, pruned_loss=0.0329, over 971604.34 frames.], batch size: 19, lr: 2.11e-04
+2022-05-06 22:33:36,179 INFO [train.py:715] (3/8) Epoch 10, batch 26750, loss[loss=0.1324, simple_loss=0.2046, pruned_loss=0.03012, over 4758.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2111, pruned_loss=0.03311, over 972229.02 frames.], batch size: 16, lr: 2.11e-04
+2022-05-06 22:34:14,863 INFO [train.py:715] (3/8) Epoch 10, batch 26800, loss[loss=0.1243, simple_loss=0.1937, pruned_loss=0.02749, over 4766.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2112, pruned_loss=0.03311, over 972092.86 frames.], batch size: 14, lr: 2.11e-04
+2022-05-06 22:34:54,619 INFO [train.py:715] (3/8) Epoch 10, batch 26850, loss[loss=0.1168, simple_loss=0.1963, pruned_loss=0.01869, over 4858.00 frames.], tot_loss[loss=0.1386, simple_loss=0.211, pruned_loss=0.03305, over 971695.96 frames.], batch size: 20, lr: 2.11e-04
+2022-05-06 22:35:34,126 INFO [train.py:715] (3/8) Epoch 10, batch 26900, loss[loss=0.1192, simple_loss=0.1919, pruned_loss=0.02326, over 4930.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2112, pruned_loss=0.03299, over 972772.89 frames.], batch size: 29, lr: 2.11e-04
+2022-05-06 22:36:12,942 INFO [train.py:715] (3/8) Epoch 10, batch 26950, loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02815, over 4990.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2127, pruned_loss=0.03379, over 972170.37 frames.], batch size: 25, lr: 2.11e-04
+2022-05-06 22:36:51,895 INFO [train.py:715] (3/8) Epoch 10, batch 27000, loss[loss=0.1478, simple_loss=0.2229, pruned_loss=0.03631, over 4982.00 frames.], tot_loss[loss=0.14, simple_loss=0.2123, pruned_loss=0.03389, over 971577.82 frames.], batch size: 28, lr: 2.11e-04
+2022-05-06 22:36:51,895 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 22:37:01,643 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1063, simple_loss=0.1906, pruned_loss=0.01104, over 914524.00 frames.
+2022-05-06 22:37:41,041 INFO [train.py:715] (3/8) Epoch 10, batch 27050, loss[loss=0.1601, simple_loss=0.2291, pruned_loss=0.04553, over 4869.00 frames.], tot_loss[loss=0.1407, simple_loss=0.213, pruned_loss=0.03415, over 972081.22 frames.], batch size: 20, lr: 2.11e-04
+2022-05-06 22:38:21,003 INFO [train.py:715] (3/8) Epoch 10, batch 27100, loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03254, over 4954.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2125, pruned_loss=0.03395, over 971597.49 frames.], batch size: 24, lr: 2.11e-04
+2022-05-06 22:38:59,618 INFO [train.py:715] (3/8) Epoch 10, batch 27150, loss[loss=0.133, simple_loss=0.199, pruned_loss=0.03356, over 4880.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03368, over 971220.69 frames.], batch size: 13, lr: 2.11e-04
+2022-05-06 22:39:38,786 INFO [train.py:715] (3/8) Epoch 10, batch 27200, loss[loss=0.1276, simple_loss=0.2074, pruned_loss=0.02389, over 4959.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03359, over 971987.50 frames.], batch size: 21, lr: 2.11e-04
+2022-05-06 22:40:18,822 INFO [train.py:715] (3/8) Epoch 10, batch 27250, loss[loss=0.1517, simple_loss=0.2231, pruned_loss=0.04012, over 4777.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2135, pruned_loss=0.03337, over 972020.87 frames.], batch size: 17, lr: 2.11e-04
+2022-05-06 22:40:58,234 INFO [train.py:715] (3/8) Epoch 10, batch 27300, loss[loss=0.1321, simple_loss=0.2011, pruned_loss=0.03153, over 4958.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2131, pruned_loss=0.03326, over 971550.51 frames.], batch size: 29, lr: 2.11e-04
+2022-05-06 22:41:36,435 INFO [train.py:715] (3/8) Epoch 10, batch 27350, loss[loss=0.1335, simple_loss=0.1926, pruned_loss=0.03718, over 4772.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.0335, over 971536.86 frames.], batch size: 12, lr: 2.11e-04
+2022-05-06 22:42:15,731 INFO [train.py:715] (3/8) Epoch 10, batch 27400, loss[loss=0.1318, simple_loss=0.2032, pruned_loss=0.03024, over 4857.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03418, over 972671.81 frames.], batch size: 20, lr: 2.11e-04
+2022-05-06 22:42:55,899 INFO [train.py:715] (3/8) Epoch 10, batch 27450, loss[loss=0.1457, simple_loss=0.2179, pruned_loss=0.03679, over 4829.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2129, pruned_loss=0.03391, over 972850.68 frames.], batch size: 15, lr: 2.11e-04
+2022-05-06 22:43:34,162 INFO [train.py:715] (3/8) Epoch 10, batch 27500, loss[loss=0.1393, simple_loss=0.2193, pruned_loss=0.02966, over 4949.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2124, pruned_loss=0.0337, over 972835.27 frames.], batch size: 15, lr: 2.11e-04
+2022-05-06 22:44:13,414 INFO [train.py:715] (3/8) Epoch 10, batch 27550, loss[loss=0.1472, simple_loss=0.2105, pruned_loss=0.04194, over 4842.00 frames.], tot_loss[loss=0.1396, simple_loss=0.212, pruned_loss=0.03363, over 972349.49 frames.], batch size: 20, lr: 2.11e-04
+2022-05-06 22:44:52,782 INFO [train.py:715] (3/8) Epoch 10, batch 27600, loss[loss=0.1522, simple_loss=0.2228, pruned_loss=0.0408, over 4700.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2118, pruned_loss=0.03384, over 971640.43 frames.], batch size: 15, lr: 2.11e-04
+2022-05-06 22:45:32,113 INFO [train.py:715] (3/8) Epoch 10, batch 27650, loss[loss=0.1524, simple_loss=0.2121, pruned_loss=0.04638, over 4970.00 frames.], tot_loss[loss=0.1387, simple_loss=0.211, pruned_loss=0.03322, over 971561.20 frames.], batch size: 15, lr: 2.11e-04
+2022-05-06 22:46:11,032 INFO [train.py:715] (3/8) Epoch 10, batch 27700, loss[loss=0.1333, simple_loss=0.1973, pruned_loss=0.03465, over 4844.00 frames.], tot_loss[loss=0.139, simple_loss=0.2111, pruned_loss=0.03344, over 972052.15 frames.], batch size: 15, lr: 2.11e-04
+2022-05-06 22:46:51,027 INFO [train.py:715] (3/8) Epoch 10, batch 27750, loss[loss=0.1778, simple_loss=0.2536, pruned_loss=0.05099, over 4885.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2118, pruned_loss=0.03332, over 972429.98 frames.], batch size: 16, lr: 2.11e-04
+2022-05-06 22:47:31,100 INFO [train.py:715] (3/8) Epoch 10, batch 27800, loss[loss=0.128, simple_loss=0.2081, pruned_loss=0.02391, over 4953.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.0336, over 972430.78 frames.], batch size: 21, lr: 2.11e-04
+2022-05-06 22:48:10,306 INFO [train.py:715] (3/8) Epoch 10, batch 27850, loss[loss=0.1519, simple_loss=0.2253, pruned_loss=0.03926, over 4925.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03372, over 973126.41 frames.], batch size: 39, lr: 2.11e-04
+2022-05-06 22:48:50,678 INFO [train.py:715] (3/8) Epoch 10, batch 27900, loss[loss=0.1297, simple_loss=0.2072, pruned_loss=0.02607, over 4843.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2127, pruned_loss=0.03382, over 973113.07 frames.], batch size: 20, lr: 2.11e-04
+2022-05-06 22:49:34,038 INFO [train.py:715] (3/8) Epoch 10, batch 27950, loss[loss=0.1279, simple_loss=0.2077, pruned_loss=0.02405, over 4883.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03388, over 973096.15 frames.], batch size: 20, lr: 2.11e-04
+2022-05-06 22:50:13,531 INFO [train.py:715] (3/8) Epoch 10, batch 28000, loss[loss=0.1217, simple_loss=0.1851, pruned_loss=0.02919, over 4769.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2119, pruned_loss=0.03343, over 973091.33 frames.], batch size: 12, lr: 2.11e-04
+2022-05-06 22:50:53,593 INFO [train.py:715] (3/8) Epoch 10, batch 28050, loss[loss=0.1571, simple_loss=0.2319, pruned_loss=0.0412, over 4746.00 frames.], tot_loss[loss=0.1392, simple_loss=0.212, pruned_loss=0.03322, over 972080.93 frames.], batch size: 16, lr: 2.11e-04
+2022-05-06 22:51:34,465 INFO [train.py:715] (3/8) Epoch 10, batch 28100, loss[loss=0.1303, simple_loss=0.2038, pruned_loss=0.02845, over 4783.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2113, pruned_loss=0.03278, over 971950.66 frames.], batch size: 18, lr: 2.11e-04
+2022-05-06 22:52:15,139 INFO [train.py:715] (3/8) Epoch 10, batch 28150, loss[loss=0.1065, simple_loss=0.1659, pruned_loss=0.02355, over 4776.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.03258, over 972001.51 frames.], batch size: 12, lr: 2.11e-04
+2022-05-06 22:52:54,868 INFO [train.py:715] (3/8) Epoch 10, batch 28200, loss[loss=0.1312, simple_loss=0.2081, pruned_loss=0.02714, over 4920.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2111, pruned_loss=0.03305, over 972352.30 frames.], batch size: 17, lr: 2.11e-04
+2022-05-06 22:53:35,216 INFO [train.py:715] (3/8) Epoch 10, batch 28250, loss[loss=0.1252, simple_loss=0.2021, pruned_loss=0.02413, over 4827.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2114, pruned_loss=0.03303, over 972393.64 frames.], batch size: 27, lr: 2.11e-04
+2022-05-06 22:54:16,802 INFO [train.py:715] (3/8) Epoch 10, batch 28300, loss[loss=0.15, simple_loss=0.2227, pruned_loss=0.03867, over 4924.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03303, over 973401.92 frames.], batch size: 23, lr: 2.11e-04
+2022-05-06 22:54:56,895 INFO [train.py:715] (3/8) Epoch 10, batch 28350, loss[loss=0.1306, simple_loss=0.2148, pruned_loss=0.02325, over 4814.00 frames.], tot_loss[loss=0.139, simple_loss=0.2116, pruned_loss=0.03316, over 974006.50 frames.], batch size: 21, lr: 2.11e-04
+2022-05-06 22:55:37,453 INFO [train.py:715] (3/8) Epoch 10, batch 28400, loss[loss=0.1285, simple_loss=0.2058, pruned_loss=0.02565, over 4971.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03308, over 974026.44 frames.], batch size: 24, lr: 2.11e-04
+2022-05-06 22:56:19,122 INFO [train.py:715] (3/8) Epoch 10, batch 28450, loss[loss=0.1475, simple_loss=0.2222, pruned_loss=0.03642, over 4890.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03328, over 973839.54 frames.], batch size: 39, lr: 2.11e-04
+2022-05-06 22:57:00,137 INFO [train.py:715] (3/8) Epoch 10, batch 28500, loss[loss=0.1554, simple_loss=0.2347, pruned_loss=0.03805, over 4805.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2119, pruned_loss=0.03315, over 973377.24 frames.], batch size: 26, lr: 2.11e-04
+2022-05-06 22:57:40,545 INFO [train.py:715] (3/8) Epoch 10, batch 28550, loss[loss=0.1484, simple_loss=0.226, pruned_loss=0.03536, over 4805.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2113, pruned_loss=0.0329, over 973360.59 frames.], batch size: 21, lr: 2.11e-04
+2022-05-06 22:58:21,443 INFO [train.py:715] (3/8) Epoch 10, batch 28600, loss[loss=0.1279, simple_loss=0.2024, pruned_loss=0.02669, over 4951.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03249, over 974422.60 frames.], batch size: 24, lr: 2.11e-04
+2022-05-06 22:59:03,591 INFO [train.py:715] (3/8) Epoch 10, batch 28650, loss[loss=0.1319, simple_loss=0.2146, pruned_loss=0.02464, over 4988.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03255, over 973396.30 frames.], batch size: 25, lr: 2.11e-04
+2022-05-06 22:59:43,742 INFO [train.py:715] (3/8) Epoch 10, batch 28700, loss[loss=0.1204, simple_loss=0.1961, pruned_loss=0.02237, over 4907.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.0323, over 973482.21 frames.], batch size: 19, lr: 2.11e-04
+2022-05-06 23:00:24,815 INFO [train.py:715] (3/8) Epoch 10, batch 28750, loss[loss=0.1311, simple_loss=0.2116, pruned_loss=0.02529, over 4912.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03222, over 973250.07 frames.], batch size: 17, lr: 2.11e-04
+2022-05-06 23:01:05,929 INFO [train.py:715] (3/8) Epoch 10, batch 28800, loss[loss=0.129, simple_loss=0.2066, pruned_loss=0.02574, over 4771.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03257, over 973755.63 frames.], batch size: 19, lr: 2.11e-04
+2022-05-06 23:01:46,833 INFO [train.py:715] (3/8) Epoch 10, batch 28850, loss[loss=0.1332, simple_loss=0.2028, pruned_loss=0.03184, over 4906.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2128, pruned_loss=0.03321, over 972588.75 frames.], batch size: 23, lr: 2.11e-04
+2022-05-06 23:02:27,343 INFO [train.py:715] (3/8) Epoch 10, batch 28900, loss[loss=0.119, simple_loss=0.197, pruned_loss=0.02048, over 4897.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03323, over 973129.04 frames.], batch size: 19, lr: 2.11e-04
+2022-05-06 23:03:08,209 INFO [train.py:715] (3/8) Epoch 10, batch 28950, loss[loss=0.1275, simple_loss=0.201, pruned_loss=0.02706, over 4934.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03304, over 972814.82 frames.], batch size: 29, lr: 2.11e-04
+2022-05-06 23:03:49,284 INFO [train.py:715] (3/8) Epoch 10, batch 29000, loss[loss=0.1413, simple_loss=0.2123, pruned_loss=0.03511, over 4945.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03322, over 972849.82 frames.], batch size: 21, lr: 2.11e-04
+2022-05-06 23:04:28,431 INFO [train.py:715] (3/8) Epoch 10, batch 29050, loss[loss=0.1372, simple_loss=0.1996, pruned_loss=0.03742, over 4862.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.03312, over 972283.27 frames.], batch size: 16, lr: 2.10e-04
+2022-05-06 23:05:07,300 INFO [train.py:715] (3/8) Epoch 10, batch 29100, loss[loss=0.1389, simple_loss=0.2185, pruned_loss=0.02961, over 4751.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03324, over 972959.81 frames.], batch size: 19, lr: 2.10e-04
+2022-05-06 23:05:47,481 INFO [train.py:715] (3/8) Epoch 10, batch 29150, loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03429, over 4766.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03311, over 971943.83 frames.], batch size: 18, lr: 2.10e-04
+2022-05-06 23:06:27,775 INFO [train.py:715] (3/8) Epoch 10, batch 29200, loss[loss=0.1477, simple_loss=0.2204, pruned_loss=0.03748, over 4846.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03334, over 971918.30 frames.], batch size: 32, lr: 2.10e-04
+2022-05-06 23:07:06,674 INFO [train.py:715] (3/8) Epoch 10, batch 29250, loss[loss=0.1298, simple_loss=0.2085, pruned_loss=0.02555, over 4933.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03264, over 971976.80 frames.], batch size: 21, lr: 2.10e-04
+2022-05-06 23:07:46,922 INFO [train.py:715] (3/8) Epoch 10, batch 29300, loss[loss=0.1913, simple_loss=0.2664, pruned_loss=0.05809, over 4980.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03269, over 971265.84 frames.], batch size: 25, lr: 2.10e-04
+2022-05-06 23:08:27,018 INFO [train.py:715] (3/8) Epoch 10, batch 29350, loss[loss=0.114, simple_loss=0.1761, pruned_loss=0.02591, over 4654.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.0324, over 971410.50 frames.], batch size: 13, lr: 2.10e-04
+2022-05-06 23:09:06,022 INFO [train.py:715] (3/8) Epoch 10, batch 29400, loss[loss=0.1454, simple_loss=0.2254, pruned_loss=0.03275, over 4842.00 frames.], tot_loss[loss=0.1389, simple_loss=0.212, pruned_loss=0.03289, over 971703.42 frames.], batch size: 15, lr: 2.10e-04
+2022-05-06 23:09:45,804 INFO [train.py:715] (3/8) Epoch 10, batch 29450, loss[loss=0.1314, simple_loss=0.209, pruned_loss=0.02697, over 4890.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03263, over 971996.06 frames.], batch size: 16, lr: 2.10e-04
+2022-05-06 23:10:26,002 INFO [train.py:715] (3/8) Epoch 10, batch 29500, loss[loss=0.1442, simple_loss=0.2196, pruned_loss=0.03441, over 4787.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03276, over 972232.09 frames.], batch size: 17, lr: 2.10e-04
+2022-05-06 23:11:05,705 INFO [train.py:715] (3/8) Epoch 10, batch 29550, loss[loss=0.1274, simple_loss=0.1944, pruned_loss=0.03022, over 4984.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03327, over 971718.91 frames.], batch size: 15, lr: 2.10e-04
+2022-05-06 23:11:44,342 INFO [train.py:715] (3/8) Epoch 10, batch 29600, loss[loss=0.1437, simple_loss=0.206, pruned_loss=0.04073, over 4863.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03384, over 971221.52 frames.], batch size: 32, lr: 2.10e-04
+2022-05-06 23:12:24,001 INFO [train.py:715] (3/8) Epoch 10, batch 29650, loss[loss=0.1158, simple_loss=0.1826, pruned_loss=0.02445, over 4821.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.03347, over 972271.07 frames.], batch size: 25, lr: 2.10e-04
+2022-05-06 23:13:03,436 INFO [train.py:715] (3/8) Epoch 10, batch 29700, loss[loss=0.1125, simple_loss=0.1815, pruned_loss=0.02174, over 4789.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.03331, over 973394.37 frames.], batch size: 13, lr: 2.10e-04
+2022-05-06 23:13:42,105 INFO [train.py:715] (3/8) Epoch 10, batch 29750, loss[loss=0.1083, simple_loss=0.1892, pruned_loss=0.01372, over 4973.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03328, over 973103.63 frames.], batch size: 24, lr: 2.10e-04
+2022-05-06 23:14:21,082 INFO [train.py:715] (3/8) Epoch 10, batch 29800, loss[loss=0.1334, simple_loss=0.2082, pruned_loss=0.02936, over 4947.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2137, pruned_loss=0.03325, over 972554.82 frames.], batch size: 21, lr: 2.10e-04
+2022-05-06 23:15:00,555 INFO [train.py:715] (3/8) Epoch 10, batch 29850, loss[loss=0.1392, simple_loss=0.2085, pruned_loss=0.03495, over 4752.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2134, pruned_loss=0.03301, over 972371.15 frames.], batch size: 19, lr: 2.10e-04
+2022-05-06 23:15:39,440 INFO [train.py:715] (3/8) Epoch 10, batch 29900, loss[loss=0.132, simple_loss=0.2205, pruned_loss=0.02178, over 4941.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2144, pruned_loss=0.03331, over 972867.89 frames.], batch size: 23, lr: 2.10e-04
+2022-05-06 23:16:17,895 INFO [train.py:715] (3/8) Epoch 10, batch 29950, loss[loss=0.1025, simple_loss=0.1824, pruned_loss=0.01134, over 4979.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2135, pruned_loss=0.03301, over 972492.83 frames.], batch size: 35, lr: 2.10e-04
+2022-05-06 23:16:57,115 INFO [train.py:715] (3/8) Epoch 10, batch 30000, loss[loss=0.1702, simple_loss=0.2296, pruned_loss=0.05539, over 4957.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2127, pruned_loss=0.03275, over 972479.88 frames.], batch size: 24, lr: 2.10e-04
+2022-05-06 23:16:57,116 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 23:17:06,541 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1063, simple_loss=0.1906, pruned_loss=0.01106, over 914524.00 frames.
+2022-05-06 23:17:46,310 INFO [train.py:715] (3/8) Epoch 10, batch 30050, loss[loss=0.1507, simple_loss=0.2206, pruned_loss=0.04036, over 4847.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03283, over 972455.30 frames.], batch size: 20, lr: 2.10e-04
+2022-05-06 23:18:25,803 INFO [train.py:715] (3/8) Epoch 10, batch 30100, loss[loss=0.1535, simple_loss=0.2244, pruned_loss=0.04126, over 4649.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03319, over 971741.83 frames.], batch size: 13, lr: 2.10e-04
+2022-05-06 23:19:04,199 INFO [train.py:715] (3/8) Epoch 10, batch 30150, loss[loss=0.111, simple_loss=0.1835, pruned_loss=0.01923, over 4764.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03351, over 971966.64 frames.], batch size: 19, lr: 2.10e-04
+2022-05-06 23:19:44,549 INFO [train.py:715] (3/8) Epoch 10, batch 30200, loss[loss=0.1569, simple_loss=0.2283, pruned_loss=0.04281, over 4804.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03314, over 971671.82 frames.], batch size: 21, lr: 2.10e-04
+2022-05-06 23:20:24,571 INFO [train.py:715] (3/8) Epoch 10, batch 30250, loss[loss=0.1335, simple_loss=0.2067, pruned_loss=0.03011, over 4839.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03328, over 972207.02 frames.], batch size: 12, lr: 2.10e-04
+2022-05-06 23:21:02,962 INFO [train.py:715] (3/8) Epoch 10, batch 30300, loss[loss=0.1414, simple_loss=0.2103, pruned_loss=0.03626, over 4965.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2125, pruned_loss=0.03399, over 972429.21 frames.], batch size: 14, lr: 2.10e-04
+2022-05-06 23:21:41,377 INFO [train.py:715] (3/8) Epoch 10, batch 30350, loss[loss=0.1126, simple_loss=0.1951, pruned_loss=0.01508, over 4860.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2118, pruned_loss=0.0334, over 971813.11 frames.], batch size: 20, lr: 2.10e-04
+2022-05-06 23:22:21,182 INFO [train.py:715] (3/8) Epoch 10, batch 30400, loss[loss=0.1201, simple_loss=0.1942, pruned_loss=0.02296, over 4806.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2112, pruned_loss=0.03292, over 971936.47 frames.], batch size: 21, lr: 2.10e-04
+2022-05-06 23:23:00,549 INFO [train.py:715] (3/8) Epoch 10, batch 30450, loss[loss=0.1644, simple_loss=0.2285, pruned_loss=0.05009, over 4966.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2117, pruned_loss=0.0331, over 972754.34 frames.], batch size: 35, lr: 2.10e-04
+2022-05-06 23:23:38,706 INFO [train.py:715] (3/8) Epoch 10, batch 30500, loss[loss=0.1058, simple_loss=0.1862, pruned_loss=0.01273, over 4976.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03294, over 973353.77 frames.], batch size: 28, lr: 2.10e-04
+2022-05-06 23:24:18,303 INFO [train.py:715] (3/8) Epoch 10, batch 30550, loss[loss=0.143, simple_loss=0.2134, pruned_loss=0.03633, over 4936.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.03301, over 972967.57 frames.], batch size: 39, lr: 2.10e-04
+2022-05-06 23:24:57,943 INFO [train.py:715] (3/8) Epoch 10, batch 30600, loss[loss=0.1584, simple_loss=0.2376, pruned_loss=0.03961, over 4839.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03275, over 972836.31 frames.], batch size: 15, lr: 2.10e-04
+2022-05-06 23:25:36,406 INFO [train.py:715] (3/8) Epoch 10, batch 30650, loss[loss=0.1193, simple_loss=0.1891, pruned_loss=0.02471, over 4772.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2128, pruned_loss=0.03271, over 972771.39 frames.], batch size: 12, lr: 2.10e-04
+2022-05-06 23:26:15,888 INFO [train.py:715] (3/8) Epoch 10, batch 30700, loss[loss=0.1237, simple_loss=0.2041, pruned_loss=0.02166, over 4988.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03251, over 972626.04 frames.], batch size: 25, lr: 2.10e-04
+2022-05-06 23:26:55,009 INFO [train.py:715] (3/8) Epoch 10, batch 30750, loss[loss=0.1344, simple_loss=0.2178, pruned_loss=0.02554, over 4960.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03299, over 972806.89 frames.], batch size: 15, lr: 2.10e-04
+2022-05-06 23:27:33,902 INFO [train.py:715] (3/8) Epoch 10, batch 30800, loss[loss=0.1457, simple_loss=0.2253, pruned_loss=0.03302, over 4754.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03264, over 971931.19 frames.], batch size: 19, lr: 2.10e-04
+2022-05-06 23:28:12,409 INFO [train.py:715] (3/8) Epoch 10, batch 30850, loss[loss=0.1495, simple_loss=0.2303, pruned_loss=0.03432, over 4806.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.0321, over 972828.86 frames.], batch size: 25, lr: 2.10e-04
+2022-05-06 23:28:52,164 INFO [train.py:715] (3/8) Epoch 10, batch 30900, loss[loss=0.1081, simple_loss=0.1807, pruned_loss=0.0178, over 4779.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.03239, over 972076.22 frames.], batch size: 18, lr: 2.10e-04
+2022-05-06 23:29:32,113 INFO [train.py:715] (3/8) Epoch 10, batch 30950, loss[loss=0.1295, simple_loss=0.2008, pruned_loss=0.02905, over 4802.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2105, pruned_loss=0.03231, over 972235.34 frames.], batch size: 13, lr: 2.10e-04
+2022-05-06 23:30:11,649 INFO [train.py:715] (3/8) Epoch 10, batch 31000, loss[loss=0.1358, simple_loss=0.2045, pruned_loss=0.03358, over 4751.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2111, pruned_loss=0.03263, over 972130.42 frames.], batch size: 16, lr: 2.10e-04
+2022-05-06 23:30:50,321 INFO [train.py:715] (3/8) Epoch 10, batch 31050, loss[loss=0.1143, simple_loss=0.1873, pruned_loss=0.02068, over 4927.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03305, over 971871.11 frames.], batch size: 29, lr: 2.10e-04
+2022-05-06 23:31:29,593 INFO [train.py:715] (3/8) Epoch 10, batch 31100, loss[loss=0.1137, simple_loss=0.1856, pruned_loss=0.02095, over 4769.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03273, over 972138.68 frames.], batch size: 12, lr: 2.10e-04
+2022-05-06 23:32:09,327 INFO [train.py:715] (3/8) Epoch 10, batch 31150, loss[loss=0.1727, simple_loss=0.2389, pruned_loss=0.05329, over 4777.00 frames.], tot_loss[loss=0.1394, simple_loss=0.213, pruned_loss=0.03291, over 971664.79 frames.], batch size: 17, lr: 2.10e-04
+2022-05-06 23:32:47,337 INFO [train.py:715] (3/8) Epoch 10, batch 31200, loss[loss=0.1928, simple_loss=0.2637, pruned_loss=0.06092, over 4689.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2132, pruned_loss=0.033, over 971186.34 frames.], batch size: 15, lr: 2.10e-04
+2022-05-06 23:33:26,827 INFO [train.py:715] (3/8) Epoch 10, batch 31250, loss[loss=0.1528, simple_loss=0.2302, pruned_loss=0.03769, over 4869.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2132, pruned_loss=0.0332, over 971547.32 frames.], batch size: 22, lr: 2.10e-04
+2022-05-06 23:34:06,251 INFO [train.py:715] (3/8) Epoch 10, batch 31300, loss[loss=0.1368, simple_loss=0.2208, pruned_loss=0.02639, over 4867.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03325, over 971636.53 frames.], batch size: 22, lr: 2.10e-04
+2022-05-06 23:34:45,238 INFO [train.py:715] (3/8) Epoch 10, batch 31350, loss[loss=0.1542, simple_loss=0.2211, pruned_loss=0.04367, over 4876.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2128, pruned_loss=0.03285, over 972270.33 frames.], batch size: 16, lr: 2.10e-04
+2022-05-06 23:35:23,742 INFO [train.py:715] (3/8) Epoch 10, batch 31400, loss[loss=0.1277, simple_loss=0.1886, pruned_loss=0.03337, over 4779.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03307, over 972661.18 frames.], batch size: 17, lr: 2.10e-04
+2022-05-06 23:36:02,749 INFO [train.py:715] (3/8) Epoch 10, batch 31450, loss[loss=0.168, simple_loss=0.238, pruned_loss=0.04904, over 4941.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03345, over 972618.16 frames.], batch size: 23, lr: 2.10e-04
+2022-05-06 23:36:42,174 INFO [train.py:715] (3/8) Epoch 10, batch 31500, loss[loss=0.1334, simple_loss=0.2097, pruned_loss=0.02859, over 4711.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03382, over 972602.45 frames.], batch size: 15, lr: 2.10e-04
+2022-05-06 23:37:19,852 INFO [train.py:715] (3/8) Epoch 10, batch 31550, loss[loss=0.1184, simple_loss=0.1899, pruned_loss=0.02344, over 4821.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03421, over 972187.24 frames.], batch size: 27, lr: 2.10e-04
+2022-05-06 23:37:58,956 INFO [train.py:715] (3/8) Epoch 10, batch 31600, loss[loss=0.13, simple_loss=0.2096, pruned_loss=0.02526, over 4951.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03397, over 972045.44 frames.], batch size: 35, lr: 2.10e-04
+2022-05-06 23:38:38,095 INFO [train.py:715] (3/8) Epoch 10, batch 31650, loss[loss=0.1289, simple_loss=0.198, pruned_loss=0.02994, over 4975.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.0338, over 972123.95 frames.], batch size: 35, lr: 2.10e-04
+2022-05-06 23:39:17,242 INFO [train.py:715] (3/8) Epoch 10, batch 31700, loss[loss=0.1353, simple_loss=0.2162, pruned_loss=0.02723, over 4750.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03363, over 972292.83 frames.], batch size: 19, lr: 2.10e-04
+2022-05-06 23:39:55,909 INFO [train.py:715] (3/8) Epoch 10, batch 31750, loss[loss=0.1806, simple_loss=0.2524, pruned_loss=0.0544, over 4754.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03381, over 972493.94 frames.], batch size: 16, lr: 2.10e-04
+2022-05-06 23:40:34,952 INFO [train.py:715] (3/8) Epoch 10, batch 31800, loss[loss=0.1541, simple_loss=0.2291, pruned_loss=0.03956, over 4911.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03347, over 972373.90 frames.], batch size: 18, lr: 2.10e-04
+2022-05-06 23:41:14,308 INFO [train.py:715] (3/8) Epoch 10, batch 31850, loss[loss=0.1753, simple_loss=0.2407, pruned_loss=0.05489, over 4876.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03392, over 973496.19 frames.], batch size: 22, lr: 2.10e-04
+2022-05-06 23:41:52,372 INFO [train.py:715] (3/8) Epoch 10, batch 31900, loss[loss=0.1483, simple_loss=0.2209, pruned_loss=0.03786, over 4899.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03402, over 973374.01 frames.], batch size: 39, lr: 2.10e-04
+2022-05-06 23:42:31,525 INFO [train.py:715] (3/8) Epoch 10, batch 31950, loss[loss=0.1193, simple_loss=0.2007, pruned_loss=0.01893, over 4963.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03369, over 972872.37 frames.], batch size: 24, lr: 2.10e-04
+2022-05-06 23:43:10,930 INFO [train.py:715] (3/8) Epoch 10, batch 32000, loss[loss=0.1246, simple_loss=0.2046, pruned_loss=0.02226, over 4683.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03371, over 972135.70 frames.], batch size: 15, lr: 2.10e-04
+2022-05-06 23:43:49,600 INFO [train.py:715] (3/8) Epoch 10, batch 32050, loss[loss=0.137, simple_loss=0.206, pruned_loss=0.03395, over 4973.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03378, over 972282.78 frames.], batch size: 35, lr: 2.10e-04
+2022-05-06 23:44:27,917 INFO [train.py:715] (3/8) Epoch 10, batch 32100, loss[loss=0.1278, simple_loss=0.1986, pruned_loss=0.02851, over 4937.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03365, over 972738.49 frames.], batch size: 23, lr: 2.10e-04
+2022-05-06 23:45:06,916 INFO [train.py:715] (3/8) Epoch 10, batch 32150, loss[loss=0.1414, simple_loss=0.2192, pruned_loss=0.03175, over 4684.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03365, over 972817.27 frames.], batch size: 15, lr: 2.10e-04
+2022-05-06 23:45:45,855 INFO [train.py:715] (3/8) Epoch 10, batch 32200, loss[loss=0.1509, simple_loss=0.226, pruned_loss=0.03789, over 4965.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03424, over 972368.00 frames.], batch size: 15, lr: 2.10e-04
+2022-05-06 23:46:23,728 INFO [train.py:715] (3/8) Epoch 10, batch 32250, loss[loss=0.1504, simple_loss=0.2204, pruned_loss=0.0402, over 4868.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2149, pruned_loss=0.03418, over 972294.45 frames.], batch size: 22, lr: 2.10e-04
+2022-05-06 23:47:02,887 INFO [train.py:715] (3/8) Epoch 10, batch 32300, loss[loss=0.1397, simple_loss=0.2163, pruned_loss=0.03158, over 4829.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2142, pruned_loss=0.03363, over 972577.27 frames.], batch size: 15, lr: 2.10e-04
+2022-05-06 23:47:42,099 INFO [train.py:715] (3/8) Epoch 10, batch 32350, loss[loss=0.1205, simple_loss=0.1968, pruned_loss=0.02209, over 4914.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2142, pruned_loss=0.03354, over 973119.04 frames.], batch size: 19, lr: 2.10e-04
+2022-05-06 23:48:20,902 INFO [train.py:715] (3/8) Epoch 10, batch 32400, loss[loss=0.1388, simple_loss=0.2198, pruned_loss=0.02891, over 4982.00 frames.], tot_loss[loss=0.141, simple_loss=0.2146, pruned_loss=0.03375, over 973776.95 frames.], batch size: 25, lr: 2.10e-04
+2022-05-06 23:48:59,312 INFO [train.py:715] (3/8) Epoch 10, batch 32450, loss[loss=0.1222, simple_loss=0.1923, pruned_loss=0.02606, over 4879.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2143, pruned_loss=0.03399, over 974431.23 frames.], batch size: 13, lr: 2.10e-04
+2022-05-06 23:49:38,631 INFO [train.py:715] (3/8) Epoch 10, batch 32500, loss[loss=0.136, simple_loss=0.2053, pruned_loss=0.03332, over 4860.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2137, pruned_loss=0.03365, over 974606.40 frames.], batch size: 32, lr: 2.10e-04
+2022-05-06 23:50:18,346 INFO [train.py:715] (3/8) Epoch 10, batch 32550, loss[loss=0.1209, simple_loss=0.1993, pruned_loss=0.02127, over 4990.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2131, pruned_loss=0.0332, over 974331.69 frames.], batch size: 14, lr: 2.10e-04
+2022-05-06 23:50:56,264 INFO [train.py:715] (3/8) Epoch 10, batch 32600, loss[loss=0.1442, simple_loss=0.2141, pruned_loss=0.03709, over 4778.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03333, over 973807.88 frames.], batch size: 17, lr: 2.10e-04
+2022-05-06 23:51:35,797 INFO [train.py:715] (3/8) Epoch 10, batch 32650, loss[loss=0.1436, simple_loss=0.2147, pruned_loss=0.03619, over 4976.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03344, over 973229.57 frames.], batch size: 14, lr: 2.10e-04
+2022-05-06 23:52:15,565 INFO [train.py:715] (3/8) Epoch 10, batch 32700, loss[loss=0.1633, simple_loss=0.2366, pruned_loss=0.04502, over 4814.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03367, over 972669.08 frames.], batch size: 26, lr: 2.09e-04
+2022-05-06 23:52:53,820 INFO [train.py:715] (3/8) Epoch 10, batch 32750, loss[loss=0.1543, simple_loss=0.2312, pruned_loss=0.03868, over 4761.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.03331, over 971990.63 frames.], batch size: 17, lr: 2.09e-04
+2022-05-06 23:53:34,508 INFO [train.py:715] (3/8) Epoch 10, batch 32800, loss[loss=0.1375, simple_loss=0.2073, pruned_loss=0.03384, over 4879.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.03369, over 971847.38 frames.], batch size: 32, lr: 2.09e-04
+2022-05-06 23:54:14,773 INFO [train.py:715] (3/8) Epoch 10, batch 32850, loss[loss=0.1309, simple_loss=0.1938, pruned_loss=0.03398, over 4773.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03356, over 972379.72 frames.], batch size: 18, lr: 2.09e-04
+2022-05-06 23:54:54,888 INFO [train.py:715] (3/8) Epoch 10, batch 32900, loss[loss=0.1417, simple_loss=0.2069, pruned_loss=0.0383, over 4894.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03363, over 972716.30 frames.], batch size: 22, lr: 2.09e-04
+2022-05-06 23:55:34,227 INFO [train.py:715] (3/8) Epoch 10, batch 32950, loss[loss=0.163, simple_loss=0.2249, pruned_loss=0.05054, over 4870.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03336, over 972587.83 frames.], batch size: 16, lr: 2.09e-04
+2022-05-06 23:56:14,908 INFO [train.py:715] (3/8) Epoch 10, batch 33000, loss[loss=0.1303, simple_loss=0.1911, pruned_loss=0.0347, over 4840.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.03363, over 972490.26 frames.], batch size: 32, lr: 2.09e-04
+2022-05-06 23:56:14,909 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-06 23:56:24,575 INFO [train.py:742] (3/8) Epoch 10, validation: loss=0.1063, simple_loss=0.1905, pruned_loss=0.01103, over 914524.00 frames.
+2022-05-06 23:57:03,964 INFO [train.py:715] (3/8) Epoch 10, batch 33050, loss[loss=0.1311, simple_loss=0.2008, pruned_loss=0.03068, over 4830.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.0333, over 972782.85 frames.], batch size: 13, lr: 2.09e-04
+2022-05-06 23:57:43,742 INFO [train.py:715] (3/8) Epoch 10, batch 33100, loss[loss=0.1401, simple_loss=0.223, pruned_loss=0.02857, over 4972.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2136, pruned_loss=0.03337, over 973777.04 frames.], batch size: 24, lr: 2.09e-04
+2022-05-06 23:58:21,689 INFO [train.py:715] (3/8) Epoch 10, batch 33150, loss[loss=0.1294, simple_loss=0.1962, pruned_loss=0.03127, over 4985.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2141, pruned_loss=0.03366, over 974262.41 frames.], batch size: 14, lr: 2.09e-04
+2022-05-06 23:59:00,822 INFO [train.py:715] (3/8) Epoch 10, batch 33200, loss[loss=0.123, simple_loss=0.1963, pruned_loss=0.02491, over 4759.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03341, over 973751.34 frames.], batch size: 14, lr: 2.09e-04
+2022-05-06 23:59:40,448 INFO [train.py:715] (3/8) Epoch 10, batch 33250, loss[loss=0.1282, simple_loss=0.2082, pruned_loss=0.02408, over 4936.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03342, over 973514.03 frames.], batch size: 18, lr: 2.09e-04
+2022-05-07 00:00:18,361 INFO [train.py:715] (3/8) Epoch 10, batch 33300, loss[loss=0.1477, simple_loss=0.2242, pruned_loss=0.03561, over 4928.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03331, over 973778.56 frames.], batch size: 29, lr: 2.09e-04
+2022-05-07 00:00:57,772 INFO [train.py:715] (3/8) Epoch 10, batch 33350, loss[loss=0.1439, simple_loss=0.2195, pruned_loss=0.03414, over 4824.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03305, over 973202.60 frames.], batch size: 27, lr: 2.09e-04
+2022-05-07 00:01:37,017 INFO [train.py:715] (3/8) Epoch 10, batch 33400, loss[loss=0.1513, simple_loss=0.2244, pruned_loss=0.03906, over 4912.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03277, over 973567.16 frames.], batch size: 19, lr: 2.09e-04
+2022-05-07 00:02:16,544 INFO [train.py:715] (3/8) Epoch 10, batch 33450, loss[loss=0.1552, simple_loss=0.2323, pruned_loss=0.03902, over 4896.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03303, over 973452.92 frames.], batch size: 19, lr: 2.09e-04
+2022-05-07 00:02:54,366 INFO [train.py:715] (3/8) Epoch 10, batch 33500, loss[loss=0.1269, simple_loss=0.195, pruned_loss=0.02945, over 4987.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03285, over 972650.42 frames.], batch size: 14, lr: 2.09e-04
+2022-05-07 00:03:33,959 INFO [train.py:715] (3/8) Epoch 10, batch 33550, loss[loss=0.1221, simple_loss=0.1863, pruned_loss=0.02898, over 4883.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03318, over 972873.79 frames.], batch size: 16, lr: 2.09e-04
+2022-05-07 00:04:13,563 INFO [train.py:715] (3/8) Epoch 10, batch 33600, loss[loss=0.1491, simple_loss=0.2165, pruned_loss=0.04081, over 4945.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03309, over 972728.73 frames.], batch size: 39, lr: 2.09e-04
+2022-05-07 00:04:52,114 INFO [train.py:715] (3/8) Epoch 10, batch 33650, loss[loss=0.1221, simple_loss=0.2004, pruned_loss=0.02192, over 4856.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03268, over 972503.53 frames.], batch size: 20, lr: 2.09e-04
+2022-05-07 00:05:30,843 INFO [train.py:715] (3/8) Epoch 10, batch 33700, loss[loss=0.1175, simple_loss=0.1913, pruned_loss=0.02183, over 4899.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03245, over 972373.82 frames.], batch size: 17, lr: 2.09e-04
+2022-05-07 00:06:10,498 INFO [train.py:715] (3/8) Epoch 10, batch 33750, loss[loss=0.1495, simple_loss=0.2238, pruned_loss=0.0376, over 4986.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03216, over 972868.35 frames.], batch size: 14, lr: 2.09e-04
+2022-05-07 00:06:50,168 INFO [train.py:715] (3/8) Epoch 10, batch 33800, loss[loss=0.1612, simple_loss=0.2489, pruned_loss=0.03676, over 4899.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03223, over 973596.25 frames.], batch size: 17, lr: 2.09e-04
+2022-05-07 00:07:29,179 INFO [train.py:715] (3/8) Epoch 10, batch 33850, loss[loss=0.1522, simple_loss=0.2159, pruned_loss=0.04429, over 4874.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03199, over 974160.93 frames.], batch size: 32, lr: 2.09e-04
+2022-05-07 00:08:08,838 INFO [train.py:715] (3/8) Epoch 10, batch 33900, loss[loss=0.1497, simple_loss=0.2259, pruned_loss=0.03672, over 4983.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03279, over 974403.43 frames.], batch size: 25, lr: 2.09e-04
+2022-05-07 00:08:48,748 INFO [train.py:715] (3/8) Epoch 10, batch 33950, loss[loss=0.1299, simple_loss=0.2046, pruned_loss=0.02763, over 4972.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03287, over 974854.90 frames.], batch size: 14, lr: 2.09e-04
+2022-05-07 00:09:27,304 INFO [train.py:715] (3/8) Epoch 10, batch 34000, loss[loss=0.1263, simple_loss=0.2045, pruned_loss=0.02405, over 4768.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03287, over 974117.45 frames.], batch size: 18, lr: 2.09e-04
+2022-05-07 00:10:06,613 INFO [train.py:715] (3/8) Epoch 10, batch 34050, loss[loss=0.1434, simple_loss=0.2165, pruned_loss=0.03513, over 4955.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03268, over 973501.54 frames.], batch size: 24, lr: 2.09e-04
+2022-05-07 00:10:45,876 INFO [train.py:715] (3/8) Epoch 10, batch 34100, loss[loss=0.1631, simple_loss=0.225, pruned_loss=0.05058, over 4688.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03234, over 973563.48 frames.], batch size: 15, lr: 2.09e-04
+2022-05-07 00:11:25,359 INFO [train.py:715] (3/8) Epoch 10, batch 34150, loss[loss=0.1579, simple_loss=0.2357, pruned_loss=0.04003, over 4826.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03308, over 972454.85 frames.], batch size: 15, lr: 2.09e-04
+2022-05-07 00:12:04,924 INFO [train.py:715] (3/8) Epoch 10, batch 34200, loss[loss=0.1625, simple_loss=0.2295, pruned_loss=0.04777, over 4888.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.033, over 972749.62 frames.], batch size: 22, lr: 2.09e-04
+2022-05-07 00:12:44,143 INFO [train.py:715] (3/8) Epoch 10, batch 34250, loss[loss=0.1092, simple_loss=0.1943, pruned_loss=0.01207, over 4821.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.0332, over 972273.12 frames.], batch size: 27, lr: 2.09e-04
+2022-05-07 00:13:23,646 INFO [train.py:715] (3/8) Epoch 10, batch 34300, loss[loss=0.1467, simple_loss=0.2124, pruned_loss=0.04053, over 4992.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03273, over 973077.44 frames.], batch size: 14, lr: 2.09e-04
+2022-05-07 00:14:03,553 INFO [train.py:715] (3/8) Epoch 10, batch 34350, loss[loss=0.1376, simple_loss=0.2019, pruned_loss=0.03662, over 4851.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2105, pruned_loss=0.03239, over 972830.85 frames.], batch size: 30, lr: 2.09e-04
+2022-05-07 00:14:43,432 INFO [train.py:715] (3/8) Epoch 10, batch 34400, loss[loss=0.1438, simple_loss=0.2104, pruned_loss=0.03858, over 4755.00 frames.], tot_loss[loss=0.1373, simple_loss=0.21, pruned_loss=0.03229, over 972882.12 frames.], batch size: 19, lr: 2.09e-04
+2022-05-07 00:15:23,583 INFO [train.py:715] (3/8) Epoch 10, batch 34450, loss[loss=0.1147, simple_loss=0.1999, pruned_loss=0.0147, over 4909.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2102, pruned_loss=0.03225, over 972433.04 frames.], batch size: 17, lr: 2.09e-04
+2022-05-07 00:16:03,653 INFO [train.py:715] (3/8) Epoch 10, batch 34500, loss[loss=0.1183, simple_loss=0.1962, pruned_loss=0.02018, over 4981.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03274, over 973003.77 frames.], batch size: 28, lr: 2.09e-04
+2022-05-07 00:16:42,850 INFO [train.py:715] (3/8) Epoch 10, batch 34550, loss[loss=0.1554, simple_loss=0.2309, pruned_loss=0.03991, over 4784.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03318, over 972537.87 frames.], batch size: 17, lr: 2.09e-04
+2022-05-07 00:17:23,151 INFO [train.py:715] (3/8) Epoch 10, batch 34600, loss[loss=0.1308, simple_loss=0.2161, pruned_loss=0.0228, over 4926.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03291, over 972897.92 frames.], batch size: 23, lr: 2.09e-04
+2022-05-07 00:18:03,612 INFO [train.py:715] (3/8) Epoch 10, batch 34650, loss[loss=0.1185, simple_loss=0.1982, pruned_loss=0.01937, over 4981.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03332, over 973114.69 frames.], batch size: 28, lr: 2.09e-04
+2022-05-07 00:18:42,653 INFO [train.py:715] (3/8) Epoch 10, batch 34700, loss[loss=0.1289, simple_loss=0.2067, pruned_loss=0.02561, over 4794.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03327, over 973061.14 frames.], batch size: 13, lr: 2.09e-04
+2022-05-07 00:19:21,231 INFO [train.py:715] (3/8) Epoch 10, batch 34750, loss[loss=0.1404, simple_loss=0.2038, pruned_loss=0.03846, over 4825.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03263, over 972384.42 frames.], batch size: 15, lr: 2.09e-04
+2022-05-07 00:19:57,689 INFO [train.py:715] (3/8) Epoch 10, batch 34800, loss[loss=0.1226, simple_loss=0.1803, pruned_loss=0.03248, over 4768.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.03234, over 971633.99 frames.], batch size: 12, lr: 2.09e-04
+2022-05-07 00:20:47,594 INFO [train.py:715] (3/8) Epoch 11, batch 0, loss[loss=0.1555, simple_loss=0.2234, pruned_loss=0.04381, over 4650.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2234, pruned_loss=0.04381, over 4650.00 frames.], batch size: 13, lr: 2.00e-04
+2022-05-07 00:21:26,500 INFO [train.py:715] (3/8) Epoch 11, batch 50, loss[loss=0.1814, simple_loss=0.2586, pruned_loss=0.05213, over 4819.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.03483, over 218461.00 frames.], batch size: 26, lr: 2.00e-04
+2022-05-07 00:22:06,397 INFO [train.py:715] (3/8) Epoch 11, batch 100, loss[loss=0.1347, simple_loss=0.2014, pruned_loss=0.03403, over 4850.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03305, over 385913.46 frames.], batch size: 30, lr: 2.00e-04
+2022-05-07 00:22:46,273 INFO [train.py:715] (3/8) Epoch 11, batch 150, loss[loss=0.1061, simple_loss=0.1762, pruned_loss=0.01797, over 4918.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03324, over 516592.79 frames.], batch size: 17, lr: 2.00e-04
+2022-05-07 00:23:26,829 INFO [train.py:715] (3/8) Epoch 11, batch 200, loss[loss=0.1307, simple_loss=0.2067, pruned_loss=0.02736, over 4818.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2137, pruned_loss=0.0333, over 617560.86 frames.], batch size: 25, lr: 2.00e-04
+2022-05-07 00:24:06,702 INFO [train.py:715] (3/8) Epoch 11, batch 250, loss[loss=0.1327, simple_loss=0.2083, pruned_loss=0.02862, over 4789.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2134, pruned_loss=0.03335, over 695865.66 frames.], batch size: 14, lr: 2.00e-04
+2022-05-07 00:24:45,522 INFO [train.py:715] (3/8) Epoch 11, batch 300, loss[loss=0.1549, simple_loss=0.2292, pruned_loss=0.04029, over 4956.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.03351, over 757771.58 frames.], batch size: 24, lr: 2.00e-04
+2022-05-07 00:25:26,105 INFO [train.py:715] (3/8) Epoch 11, batch 350, loss[loss=0.1386, simple_loss=0.2142, pruned_loss=0.03146, over 4971.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03383, over 805329.72 frames.], batch size: 24, lr: 2.00e-04
+2022-05-07 00:26:05,773 INFO [train.py:715] (3/8) Epoch 11, batch 400, loss[loss=0.1442, simple_loss=0.2259, pruned_loss=0.03121, over 4783.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03428, over 842597.58 frames.], batch size: 17, lr: 2.00e-04
+2022-05-07 00:26:46,460 INFO [train.py:715] (3/8) Epoch 11, batch 450, loss[loss=0.1463, simple_loss=0.2079, pruned_loss=0.04235, over 4959.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03437, over 871351.43 frames.], batch size: 24, lr: 2.00e-04
+2022-05-07 00:27:27,785 INFO [train.py:715] (3/8) Epoch 11, batch 500, loss[loss=0.1167, simple_loss=0.1924, pruned_loss=0.02047, over 4895.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.0336, over 894713.93 frames.], batch size: 17, lr: 2.00e-04
+2022-05-07 00:28:09,385 INFO [train.py:715] (3/8) Epoch 11, batch 550, loss[loss=0.14, simple_loss=0.213, pruned_loss=0.0335, over 4874.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.03415, over 912027.48 frames.], batch size: 16, lr: 2.00e-04
+2022-05-07 00:28:50,701 INFO [train.py:715] (3/8) Epoch 11, batch 600, loss[loss=0.1123, simple_loss=0.1906, pruned_loss=0.01703, over 4917.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03424, over 925207.49 frames.], batch size: 18, lr: 2.00e-04
+2022-05-07 00:29:32,039 INFO [train.py:715] (3/8) Epoch 11, batch 650, loss[loss=0.1524, simple_loss=0.2276, pruned_loss=0.03855, over 4858.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03422, over 935787.31 frames.], batch size: 39, lr: 2.00e-04
+2022-05-07 00:30:13,300 INFO [train.py:715] (3/8) Epoch 11, batch 700, loss[loss=0.1268, simple_loss=0.2019, pruned_loss=0.02583, over 4981.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03442, over 944086.57 frames.], batch size: 24, lr: 2.00e-04
+2022-05-07 00:30:54,880 INFO [train.py:715] (3/8) Epoch 11, batch 750, loss[loss=0.1432, simple_loss=0.2273, pruned_loss=0.0295, over 4863.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2137, pruned_loss=0.03478, over 950765.44 frames.], batch size: 20, lr: 2.00e-04
+2022-05-07 00:31:36,032 INFO [train.py:715] (3/8) Epoch 11, batch 800, loss[loss=0.153, simple_loss=0.2366, pruned_loss=0.03469, over 4987.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2133, pruned_loss=0.03427, over 955778.55 frames.], batch size: 25, lr: 2.00e-04
+2022-05-07 00:32:16,760 INFO [train.py:715] (3/8) Epoch 11, batch 850, loss[loss=0.127, simple_loss=0.2078, pruned_loss=0.02308, over 4852.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03426, over 958827.43 frames.], batch size: 20, lr: 2.00e-04
+2022-05-07 00:32:58,360 INFO [train.py:715] (3/8) Epoch 11, batch 900, loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03081, over 4984.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2128, pruned_loss=0.03414, over 961787.03 frames.], batch size: 28, lr: 2.00e-04
+2022-05-07 00:33:38,988 INFO [train.py:715] (3/8) Epoch 11, batch 950, loss[loss=0.1359, simple_loss=0.197, pruned_loss=0.03739, over 4891.00 frames.], tot_loss[loss=0.14, simple_loss=0.212, pruned_loss=0.03395, over 964322.17 frames.], batch size: 16, lr: 2.00e-04
+2022-05-07 00:34:19,481 INFO [train.py:715] (3/8) Epoch 11, batch 1000, loss[loss=0.1345, simple_loss=0.2121, pruned_loss=0.0284, over 4875.00 frames.], tot_loss[loss=0.1395, simple_loss=0.212, pruned_loss=0.03355, over 967397.61 frames.], batch size: 22, lr: 2.00e-04
+2022-05-07 00:34:58,893 INFO [train.py:715] (3/8) Epoch 11, batch 1050, loss[loss=0.1414, simple_loss=0.2129, pruned_loss=0.03495, over 4787.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.03418, over 968842.99 frames.], batch size: 17, lr: 2.00e-04
+2022-05-07 00:35:41,048 INFO [train.py:715] (3/8) Epoch 11, batch 1100, loss[loss=0.1243, simple_loss=0.1937, pruned_loss=0.02743, over 4870.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03387, over 969577.06 frames.], batch size: 32, lr: 2.00e-04
+2022-05-07 00:36:20,719 INFO [train.py:715] (3/8) Epoch 11, batch 1150, loss[loss=0.1426, simple_loss=0.2072, pruned_loss=0.03896, over 4977.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03369, over 969816.33 frames.], batch size: 24, lr: 2.00e-04
+2022-05-07 00:37:00,329 INFO [train.py:715] (3/8) Epoch 11, batch 1200, loss[loss=0.1402, simple_loss=0.2068, pruned_loss=0.03676, over 4895.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.03408, over 970277.63 frames.], batch size: 22, lr: 2.00e-04
+2022-05-07 00:37:39,163 INFO [train.py:715] (3/8) Epoch 11, batch 1250, loss[loss=0.1499, simple_loss=0.2241, pruned_loss=0.03789, over 4949.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03378, over 970539.94 frames.], batch size: 40, lr: 2.00e-04
+2022-05-07 00:38:18,008 INFO [train.py:715] (3/8) Epoch 11, batch 1300, loss[loss=0.1333, simple_loss=0.2124, pruned_loss=0.02709, over 4796.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.03371, over 971485.06 frames.], batch size: 24, lr: 2.00e-04
+2022-05-07 00:38:56,861 INFO [train.py:715] (3/8) Epoch 11, batch 1350, loss[loss=0.1277, simple_loss=0.2041, pruned_loss=0.02567, over 4946.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03382, over 971357.54 frames.], batch size: 21, lr: 2.00e-04
+2022-05-07 00:39:35,880 INFO [train.py:715] (3/8) Epoch 11, batch 1400, loss[loss=0.1238, simple_loss=0.1907, pruned_loss=0.02843, over 4913.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2128, pruned_loss=0.03323, over 971544.32 frames.], batch size: 18, lr: 2.00e-04
+2022-05-07 00:40:14,714 INFO [train.py:715] (3/8) Epoch 11, batch 1450, loss[loss=0.1322, simple_loss=0.2149, pruned_loss=0.02479, over 4758.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2126, pruned_loss=0.03306, over 971987.87 frames.], batch size: 19, lr: 2.00e-04
+2022-05-07 00:40:53,351 INFO [train.py:715] (3/8) Epoch 11, batch 1500, loss[loss=0.1377, simple_loss=0.215, pruned_loss=0.03016, over 4979.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2129, pruned_loss=0.033, over 971978.61 frames.], batch size: 25, lr: 2.00e-04
+2022-05-07 00:41:31,714 INFO [train.py:715] (3/8) Epoch 11, batch 1550, loss[loss=0.1355, simple_loss=0.2028, pruned_loss=0.03405, over 4944.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2138, pruned_loss=0.03353, over 971916.89 frames.], batch size: 35, lr: 2.00e-04
+2022-05-07 00:42:10,772 INFO [train.py:715] (3/8) Epoch 11, batch 1600, loss[loss=0.1419, simple_loss=0.2014, pruned_loss=0.04115, over 4845.00 frames.], tot_loss[loss=0.14, simple_loss=0.2132, pruned_loss=0.0334, over 972124.80 frames.], batch size: 15, lr: 2.00e-04
+2022-05-07 00:42:49,744 INFO [train.py:715] (3/8) Epoch 11, batch 1650, loss[loss=0.1314, simple_loss=0.188, pruned_loss=0.03738, over 4984.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03359, over 972329.27 frames.], batch size: 14, lr: 2.00e-04
+2022-05-07 00:43:28,109 INFO [train.py:715] (3/8) Epoch 11, batch 1700, loss[loss=0.1136, simple_loss=0.174, pruned_loss=0.02662, over 4828.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.0335, over 972723.09 frames.], batch size: 12, lr: 2.00e-04
+2022-05-07 00:44:07,381 INFO [train.py:715] (3/8) Epoch 11, batch 1750, loss[loss=0.1175, simple_loss=0.196, pruned_loss=0.01946, over 4647.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.0333, over 973167.98 frames.], batch size: 13, lr: 2.00e-04
+2022-05-07 00:44:46,269 INFO [train.py:715] (3/8) Epoch 11, batch 1800, loss[loss=0.1333, simple_loss=0.2003, pruned_loss=0.03311, over 4840.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03324, over 972533.06 frames.], batch size: 30, lr: 2.00e-04
+2022-05-07 00:45:25,304 INFO [train.py:715] (3/8) Epoch 11, batch 1850, loss[loss=0.1368, simple_loss=0.2137, pruned_loss=0.02999, over 4776.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03265, over 972236.59 frames.], batch size: 14, lr: 2.00e-04
+2022-05-07 00:46:04,485 INFO [train.py:715] (3/8) Epoch 11, batch 1900, loss[loss=0.1915, simple_loss=0.2579, pruned_loss=0.06257, over 4944.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03307, over 972668.94 frames.], batch size: 39, lr: 2.00e-04
+2022-05-07 00:46:43,764 INFO [train.py:715] (3/8) Epoch 11, batch 1950, loss[loss=0.126, simple_loss=0.2016, pruned_loss=0.02524, over 4860.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03287, over 973054.65 frames.], batch size: 20, lr: 2.00e-04
+2022-05-07 00:47:23,300 INFO [train.py:715] (3/8) Epoch 11, batch 2000, loss[loss=0.1658, simple_loss=0.224, pruned_loss=0.05376, over 4757.00 frames.], tot_loss[loss=0.1397, simple_loss=0.213, pruned_loss=0.03316, over 972208.80 frames.], batch size: 16, lr: 2.00e-04
+2022-05-07 00:48:01,929 INFO [train.py:715] (3/8) Epoch 11, batch 2050, loss[loss=0.1299, simple_loss=0.2028, pruned_loss=0.02845, over 4761.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03301, over 972743.68 frames.], batch size: 19, lr: 2.00e-04
+2022-05-07 00:48:41,075 INFO [train.py:715] (3/8) Epoch 11, batch 2100, loss[loss=0.1261, simple_loss=0.199, pruned_loss=0.02666, over 4925.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2123, pruned_loss=0.03251, over 972724.91 frames.], batch size: 18, lr: 2.00e-04
+2022-05-07 00:49:20,362 INFO [train.py:715] (3/8) Epoch 11, batch 2150, loss[loss=0.1165, simple_loss=0.1977, pruned_loss=0.01768, over 4928.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03242, over 972353.63 frames.], batch size: 29, lr: 2.00e-04
+2022-05-07 00:49:59,563 INFO [train.py:715] (3/8) Epoch 11, batch 2200, loss[loss=0.1192, simple_loss=0.1898, pruned_loss=0.02431, over 4952.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03294, over 973112.12 frames.], batch size: 14, lr: 2.00e-04
+2022-05-07 00:50:38,223 INFO [train.py:715] (3/8) Epoch 11, batch 2250, loss[loss=0.1328, simple_loss=0.1951, pruned_loss=0.03521, over 4952.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.0333, over 972502.71 frames.], batch size: 24, lr: 2.00e-04
+2022-05-07 00:51:17,280 INFO [train.py:715] (3/8) Epoch 11, batch 2300, loss[loss=0.1408, simple_loss=0.207, pruned_loss=0.0373, over 4840.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03324, over 972097.79 frames.], batch size: 15, lr: 2.00e-04
+2022-05-07 00:51:56,681 INFO [train.py:715] (3/8) Epoch 11, batch 2350, loss[loss=0.1661, simple_loss=0.2364, pruned_loss=0.04788, over 4761.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03313, over 972626.50 frames.], batch size: 16, lr: 2.00e-04
+2022-05-07 00:52:35,083 INFO [train.py:715] (3/8) Epoch 11, batch 2400, loss[loss=0.12, simple_loss=0.1998, pruned_loss=0.02012, over 4988.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.03355, over 972355.74 frames.], batch size: 14, lr: 2.00e-04
+2022-05-07 00:53:14,458 INFO [train.py:715] (3/8) Epoch 11, batch 2450, loss[loss=0.1812, simple_loss=0.2368, pruned_loss=0.0628, over 4851.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03362, over 971904.41 frames.], batch size: 34, lr: 2.00e-04
+2022-05-07 00:53:54,033 INFO [train.py:715] (3/8) Epoch 11, batch 2500, loss[loss=0.1574, simple_loss=0.2248, pruned_loss=0.04503, over 4993.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03344, over 972479.22 frames.], batch size: 14, lr: 2.00e-04
+2022-05-07 00:54:33,181 INFO [train.py:715] (3/8) Epoch 11, batch 2550, loss[loss=0.1288, simple_loss=0.2032, pruned_loss=0.02718, over 4705.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03297, over 971935.08 frames.], batch size: 15, lr: 2.00e-04
+2022-05-07 00:55:12,420 INFO [train.py:715] (3/8) Epoch 11, batch 2600, loss[loss=0.152, simple_loss=0.2316, pruned_loss=0.03622, over 4735.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03303, over 971751.25 frames.], batch size: 16, lr: 2.00e-04
+2022-05-07 00:55:51,261 INFO [train.py:715] (3/8) Epoch 11, batch 2650, loss[loss=0.1221, simple_loss=0.1966, pruned_loss=0.02381, over 4972.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.0333, over 970982.37 frames.], batch size: 28, lr: 2.00e-04
+2022-05-07 00:56:30,346 INFO [train.py:715] (3/8) Epoch 11, batch 2700, loss[loss=0.1351, simple_loss=0.2185, pruned_loss=0.02582, over 4785.00 frames.], tot_loss[loss=0.1392, simple_loss=0.212, pruned_loss=0.03322, over 970918.53 frames.], batch size: 18, lr: 2.00e-04
+2022-05-07 00:57:09,097 INFO [train.py:715] (3/8) Epoch 11, batch 2750, loss[loss=0.124, simple_loss=0.1965, pruned_loss=0.02578, over 4901.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03242, over 971702.27 frames.], batch size: 19, lr: 2.00e-04
+2022-05-07 00:57:48,077 INFO [train.py:715] (3/8) Epoch 11, batch 2800, loss[loss=0.1355, simple_loss=0.2115, pruned_loss=0.02973, over 4994.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03305, over 972740.73 frames.], batch size: 24, lr: 2.00e-04
+2022-05-07 00:58:27,252 INFO [train.py:715] (3/8) Epoch 11, batch 2850, loss[loss=0.1477, simple_loss=0.2235, pruned_loss=0.03588, over 4974.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03293, over 972318.42 frames.], batch size: 15, lr: 2.00e-04
+2022-05-07 00:59:05,707 INFO [train.py:715] (3/8) Epoch 11, batch 2900, loss[loss=0.1551, simple_loss=0.2271, pruned_loss=0.04159, over 4699.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03296, over 972088.37 frames.], batch size: 15, lr: 2.00e-04
+2022-05-07 00:59:45,166 INFO [train.py:715] (3/8) Epoch 11, batch 2950, loss[loss=0.1413, simple_loss=0.2122, pruned_loss=0.03515, over 4840.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03299, over 972479.72 frames.], batch size: 15, lr: 2.00e-04
+2022-05-07 01:00:25,029 INFO [train.py:715] (3/8) Epoch 11, batch 3000, loss[loss=0.1531, simple_loss=0.2241, pruned_loss=0.04101, over 4754.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03299, over 971930.94 frames.], batch size: 19, lr: 2.00e-04
+2022-05-07 01:00:25,029 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 01:00:34,771 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1902, pruned_loss=0.01097, over 914524.00 frames.
+2022-05-07 01:01:14,748 INFO [train.py:715] (3/8) Epoch 11, batch 3050, loss[loss=0.1718, simple_loss=0.2347, pruned_loss=0.05443, over 4937.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03283, over 972118.09 frames.], batch size: 39, lr: 2.00e-04
+2022-05-07 01:01:54,019 INFO [train.py:715] (3/8) Epoch 11, batch 3100, loss[loss=0.1509, simple_loss=0.231, pruned_loss=0.03539, over 4927.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03257, over 972786.57 frames.], batch size: 18, lr: 2.00e-04
+2022-05-07 01:02:34,091 INFO [train.py:715] (3/8) Epoch 11, batch 3150, loss[loss=0.1254, simple_loss=0.2024, pruned_loss=0.02423, over 4910.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2127, pruned_loss=0.0329, over 972621.88 frames.], batch size: 18, lr: 2.00e-04
+2022-05-07 01:03:13,127 INFO [train.py:715] (3/8) Epoch 11, batch 3200, loss[loss=0.1811, simple_loss=0.2638, pruned_loss=0.04915, over 4866.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03271, over 972986.90 frames.], batch size: 16, lr: 2.00e-04
+2022-05-07 01:03:52,801 INFO [train.py:715] (3/8) Epoch 11, batch 3250, loss[loss=0.131, simple_loss=0.223, pruned_loss=0.01954, over 4982.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2128, pruned_loss=0.03274, over 973775.45 frames.], batch size: 24, lr: 2.00e-04
+2022-05-07 01:04:31,534 INFO [train.py:715] (3/8) Epoch 11, batch 3300, loss[loss=0.1563, simple_loss=0.2325, pruned_loss=0.04007, over 4838.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2124, pruned_loss=0.03233, over 973681.42 frames.], batch size: 13, lr: 2.00e-04
+2022-05-07 01:05:10,792 INFO [train.py:715] (3/8) Epoch 11, batch 3350, loss[loss=0.1355, simple_loss=0.2124, pruned_loss=0.02928, over 4895.00 frames.], tot_loss[loss=0.139, simple_loss=0.2128, pruned_loss=0.0326, over 973892.06 frames.], batch size: 22, lr: 2.00e-04
+2022-05-07 01:05:50,445 INFO [train.py:715] (3/8) Epoch 11, batch 3400, loss[loss=0.1603, simple_loss=0.2333, pruned_loss=0.04359, over 4939.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03277, over 973783.92 frames.], batch size: 29, lr: 2.00e-04
+2022-05-07 01:06:29,435 INFO [train.py:715] (3/8) Epoch 11, batch 3450, loss[loss=0.1178, simple_loss=0.1899, pruned_loss=0.02288, over 4801.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.03311, over 973039.16 frames.], batch size: 14, lr: 2.00e-04
+2022-05-07 01:07:08,299 INFO [train.py:715] (3/8) Epoch 11, batch 3500, loss[loss=0.1489, simple_loss=0.2214, pruned_loss=0.03822, over 4988.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2128, pruned_loss=0.03289, over 972991.71 frames.], batch size: 25, lr: 1.99e-04
+2022-05-07 01:07:47,578 INFO [train.py:715] (3/8) Epoch 11, batch 3550, loss[loss=0.1186, simple_loss=0.1943, pruned_loss=0.02139, over 4913.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2125, pruned_loss=0.0326, over 973073.06 frames.], batch size: 17, lr: 1.99e-04
+2022-05-07 01:08:27,195 INFO [train.py:715] (3/8) Epoch 11, batch 3600, loss[loss=0.1603, simple_loss=0.2358, pruned_loss=0.04241, over 4927.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03246, over 972341.24 frames.], batch size: 18, lr: 1.99e-04
+2022-05-07 01:09:05,513 INFO [train.py:715] (3/8) Epoch 11, batch 3650, loss[loss=0.138, simple_loss=0.2158, pruned_loss=0.03015, over 4863.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03221, over 972296.95 frames.], batch size: 16, lr: 1.99e-04
+2022-05-07 01:09:45,169 INFO [train.py:715] (3/8) Epoch 11, batch 3700, loss[loss=0.1202, simple_loss=0.1884, pruned_loss=0.02596, over 4810.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03253, over 972160.34 frames.], batch size: 26, lr: 1.99e-04
+2022-05-07 01:10:24,603 INFO [train.py:715] (3/8) Epoch 11, batch 3750, loss[loss=0.1571, simple_loss=0.2181, pruned_loss=0.04811, over 4937.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03251, over 972391.01 frames.], batch size: 21, lr: 1.99e-04
+2022-05-07 01:11:03,049 INFO [train.py:715] (3/8) Epoch 11, batch 3800, loss[loss=0.1115, simple_loss=0.1856, pruned_loss=0.01875, over 4821.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2109, pruned_loss=0.03265, over 972528.57 frames.], batch size: 12, lr: 1.99e-04
+2022-05-07 01:11:42,113 INFO [train.py:715] (3/8) Epoch 11, batch 3850, loss[loss=0.1515, simple_loss=0.2304, pruned_loss=0.0363, over 4952.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03303, over 972998.50 frames.], batch size: 24, lr: 1.99e-04
+2022-05-07 01:12:21,422 INFO [train.py:715] (3/8) Epoch 11, batch 3900, loss[loss=0.1483, simple_loss=0.222, pruned_loss=0.03732, over 4935.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03298, over 972930.51 frames.], batch size: 35, lr: 1.99e-04
+2022-05-07 01:13:01,147 INFO [train.py:715] (3/8) Epoch 11, batch 3950, loss[loss=0.1418, simple_loss=0.2217, pruned_loss=0.03092, over 4687.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03371, over 972244.31 frames.], batch size: 15, lr: 1.99e-04
+2022-05-07 01:13:39,997 INFO [train.py:715] (3/8) Epoch 11, batch 4000, loss[loss=0.1566, simple_loss=0.2289, pruned_loss=0.04214, over 4789.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2143, pruned_loss=0.03397, over 973030.28 frames.], batch size: 18, lr: 1.99e-04
+2022-05-07 01:14:19,835 INFO [train.py:715] (3/8) Epoch 11, batch 4050, loss[loss=0.1322, simple_loss=0.2046, pruned_loss=0.02991, over 4930.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03393, over 972980.33 frames.], batch size: 35, lr: 1.99e-04
+2022-05-07 01:14:59,481 INFO [train.py:715] (3/8) Epoch 11, batch 4100, loss[loss=0.115, simple_loss=0.1802, pruned_loss=0.02487, over 4759.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2144, pruned_loss=0.03431, over 973344.35 frames.], batch size: 12, lr: 1.99e-04
+2022-05-07 01:15:38,034 INFO [train.py:715] (3/8) Epoch 11, batch 4150, loss[loss=0.1303, simple_loss=0.1931, pruned_loss=0.03376, over 4923.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.0339, over 972668.34 frames.], batch size: 18, lr: 1.99e-04
+2022-05-07 01:16:16,418 INFO [train.py:715] (3/8) Epoch 11, batch 4200, loss[loss=0.1263, simple_loss=0.1901, pruned_loss=0.03125, over 4799.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.03359, over 972308.29 frames.], batch size: 12, lr: 1.99e-04
+2022-05-07 01:16:56,660 INFO [train.py:715] (3/8) Epoch 11, batch 4250, loss[loss=0.1637, simple_loss=0.2355, pruned_loss=0.04595, over 4819.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03381, over 972434.11 frames.], batch size: 26, lr: 1.99e-04
+2022-05-07 01:17:36,660 INFO [train.py:715] (3/8) Epoch 11, batch 4300, loss[loss=0.14, simple_loss=0.2214, pruned_loss=0.0293, over 4810.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03345, over 972280.40 frames.], batch size: 26, lr: 1.99e-04
+2022-05-07 01:18:15,822 INFO [train.py:715] (3/8) Epoch 11, batch 4350, loss[loss=0.1522, simple_loss=0.229, pruned_loss=0.03769, over 4984.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03279, over 972900.51 frames.], batch size: 31, lr: 1.99e-04
+2022-05-07 01:18:56,182 INFO [train.py:715] (3/8) Epoch 11, batch 4400, loss[loss=0.1458, simple_loss=0.2196, pruned_loss=0.03596, over 4915.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2126, pruned_loss=0.03264, over 972065.75 frames.], batch size: 19, lr: 1.99e-04
+2022-05-07 01:19:36,294 INFO [train.py:715] (3/8) Epoch 11, batch 4450, loss[loss=0.1488, simple_loss=0.233, pruned_loss=0.03228, over 4868.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2124, pruned_loss=0.03262, over 971621.13 frames.], batch size: 22, lr: 1.99e-04
+2022-05-07 01:20:15,927 INFO [train.py:715] (3/8) Epoch 11, batch 4500, loss[loss=0.1285, simple_loss=0.2076, pruned_loss=0.02467, over 4942.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03253, over 971636.55 frames.], batch size: 29, lr: 1.99e-04
+2022-05-07 01:20:55,940 INFO [train.py:715] (3/8) Epoch 11, batch 4550, loss[loss=0.1659, simple_loss=0.2294, pruned_loss=0.05121, over 4964.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03317, over 972408.95 frames.], batch size: 15, lr: 1.99e-04
+2022-05-07 01:21:35,995 INFO [train.py:715] (3/8) Epoch 11, batch 4600, loss[loss=0.1356, simple_loss=0.2111, pruned_loss=0.03005, over 4745.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03303, over 971435.10 frames.], batch size: 16, lr: 1.99e-04
+2022-05-07 01:22:15,463 INFO [train.py:715] (3/8) Epoch 11, batch 4650, loss[loss=0.1251, simple_loss=0.2081, pruned_loss=0.02109, over 4765.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03239, over 971358.16 frames.], batch size: 19, lr: 1.99e-04
+2022-05-07 01:22:55,178 INFO [train.py:715] (3/8) Epoch 11, batch 4700, loss[loss=0.1228, simple_loss=0.1904, pruned_loss=0.02764, over 4915.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03303, over 970849.01 frames.], batch size: 18, lr: 1.99e-04
+2022-05-07 01:23:35,353 INFO [train.py:715] (3/8) Epoch 11, batch 4750, loss[loss=0.1437, simple_loss=0.2224, pruned_loss=0.03254, over 4988.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03287, over 971298.70 frames.], batch size: 26, lr: 1.99e-04
+2022-05-07 01:24:15,522 INFO [train.py:715] (3/8) Epoch 11, batch 4800, loss[loss=0.1649, simple_loss=0.2334, pruned_loss=0.04825, over 4984.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03293, over 971605.80 frames.], batch size: 31, lr: 1.99e-04
+2022-05-07 01:24:55,134 INFO [train.py:715] (3/8) Epoch 11, batch 4850, loss[loss=0.1477, simple_loss=0.2239, pruned_loss=0.03575, over 4755.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03273, over 971177.96 frames.], batch size: 16, lr: 1.99e-04
+2022-05-07 01:25:34,922 INFO [train.py:715] (3/8) Epoch 11, batch 4900, loss[loss=0.1326, simple_loss=0.2032, pruned_loss=0.03095, over 4880.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03292, over 971808.25 frames.], batch size: 32, lr: 1.99e-04
+2022-05-07 01:26:14,639 INFO [train.py:715] (3/8) Epoch 11, batch 4950, loss[loss=0.1374, simple_loss=0.2049, pruned_loss=0.0349, over 4757.00 frames.], tot_loss[loss=0.139, simple_loss=0.2123, pruned_loss=0.03282, over 972233.72 frames.], batch size: 12, lr: 1.99e-04
+2022-05-07 01:26:53,443 INFO [train.py:715] (3/8) Epoch 11, batch 5000, loss[loss=0.1546, simple_loss=0.2204, pruned_loss=0.04435, over 4690.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03284, over 972318.55 frames.], batch size: 15, lr: 1.99e-04
+2022-05-07 01:27:31,885 INFO [train.py:715] (3/8) Epoch 11, batch 5050, loss[loss=0.149, simple_loss=0.2341, pruned_loss=0.03201, over 4950.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.0327, over 972278.69 frames.], batch size: 29, lr: 1.99e-04
+2022-05-07 01:28:11,143 INFO [train.py:715] (3/8) Epoch 11, batch 5100, loss[loss=0.1363, simple_loss=0.2166, pruned_loss=0.028, over 4769.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.03285, over 972998.59 frames.], batch size: 19, lr: 1.99e-04
+2022-05-07 01:28:50,278 INFO [train.py:715] (3/8) Epoch 11, batch 5150, loss[loss=0.1582, simple_loss=0.2146, pruned_loss=0.05095, over 4963.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03333, over 972972.43 frames.], batch size: 14, lr: 1.99e-04
+2022-05-07 01:29:29,204 INFO [train.py:715] (3/8) Epoch 11, batch 5200, loss[loss=0.1325, simple_loss=0.2059, pruned_loss=0.02955, over 4989.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03305, over 972835.63 frames.], batch size: 25, lr: 1.99e-04
+2022-05-07 01:30:08,610 INFO [train.py:715] (3/8) Epoch 11, batch 5250, loss[loss=0.1214, simple_loss=0.1999, pruned_loss=0.02142, over 4877.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03255, over 972671.23 frames.], batch size: 16, lr: 1.99e-04
+2022-05-07 01:30:48,293 INFO [train.py:715] (3/8) Epoch 11, batch 5300, loss[loss=0.1113, simple_loss=0.1781, pruned_loss=0.02222, over 4837.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03217, over 972806.58 frames.], batch size: 15, lr: 1.99e-04
+2022-05-07 01:31:27,445 INFO [train.py:715] (3/8) Epoch 11, batch 5350, loss[loss=0.1718, simple_loss=0.2382, pruned_loss=0.05268, over 4881.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.03233, over 972445.90 frames.], batch size: 16, lr: 1.99e-04
+2022-05-07 01:32:06,513 INFO [train.py:715] (3/8) Epoch 11, batch 5400, loss[loss=0.1537, simple_loss=0.2247, pruned_loss=0.04137, over 4778.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03262, over 971892.18 frames.], batch size: 17, lr: 1.99e-04
+2022-05-07 01:32:45,902 INFO [train.py:715] (3/8) Epoch 11, batch 5450, loss[loss=0.1402, simple_loss=0.2175, pruned_loss=0.03146, over 4827.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03255, over 971920.68 frames.], batch size: 15, lr: 1.99e-04
+2022-05-07 01:33:25,400 INFO [train.py:715] (3/8) Epoch 11, batch 5500, loss[loss=0.1386, simple_loss=0.207, pruned_loss=0.03511, over 4770.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03276, over 972333.65 frames.], batch size: 18, lr: 1.99e-04
+2022-05-07 01:34:04,254 INFO [train.py:715] (3/8) Epoch 11, batch 5550, loss[loss=0.1288, simple_loss=0.1991, pruned_loss=0.02929, over 4875.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03266, over 971825.19 frames.], batch size: 32, lr: 1.99e-04
+2022-05-07 01:34:42,709 INFO [train.py:715] (3/8) Epoch 11, batch 5600, loss[loss=0.1212, simple_loss=0.1922, pruned_loss=0.02507, over 4811.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03306, over 970797.11 frames.], batch size: 13, lr: 1.99e-04
+2022-05-07 01:35:22,174 INFO [train.py:715] (3/8) Epoch 11, batch 5650, loss[loss=0.1302, simple_loss=0.1985, pruned_loss=0.03089, over 4882.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03315, over 971287.98 frames.], batch size: 22, lr: 1.99e-04
+2022-05-07 01:36:01,615 INFO [train.py:715] (3/8) Epoch 11, batch 5700, loss[loss=0.1612, simple_loss=0.228, pruned_loss=0.0472, over 4891.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03296, over 971760.69 frames.], batch size: 19, lr: 1.99e-04
+2022-05-07 01:36:40,400 INFO [train.py:715] (3/8) Epoch 11, batch 5750, loss[loss=0.1186, simple_loss=0.1935, pruned_loss=0.02191, over 4872.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03336, over 971985.49 frames.], batch size: 16, lr: 1.99e-04
+2022-05-07 01:37:19,377 INFO [train.py:715] (3/8) Epoch 11, batch 5800, loss[loss=0.164, simple_loss=0.2447, pruned_loss=0.04164, over 4722.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.03348, over 972433.29 frames.], batch size: 15, lr: 1.99e-04
+2022-05-07 01:37:58,487 INFO [train.py:715] (3/8) Epoch 11, batch 5850, loss[loss=0.1378, simple_loss=0.2118, pruned_loss=0.03192, over 4982.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03364, over 972310.67 frames.], batch size: 25, lr: 1.99e-04
+2022-05-07 01:38:37,497 INFO [train.py:715] (3/8) Epoch 11, batch 5900, loss[loss=0.1559, simple_loss=0.2309, pruned_loss=0.04043, over 4812.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03338, over 972157.22 frames.], batch size: 15, lr: 1.99e-04
+2022-05-07 01:39:16,658 INFO [train.py:715] (3/8) Epoch 11, batch 5950, loss[loss=0.1213, simple_loss=0.2045, pruned_loss=0.01902, over 4855.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03275, over 972291.95 frames.], batch size: 20, lr: 1.99e-04
+2022-05-07 01:39:56,445 INFO [train.py:715] (3/8) Epoch 11, batch 6000, loss[loss=0.1726, simple_loss=0.2519, pruned_loss=0.04664, over 4921.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.033, over 971281.41 frames.], batch size: 39, lr: 1.99e-04
+2022-05-07 01:39:56,446 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 01:40:06,014 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.1059, simple_loss=0.1901, pruned_loss=0.01082, over 914524.00 frames.
+2022-05-07 01:40:45,575 INFO [train.py:715] (3/8) Epoch 11, batch 6050, loss[loss=0.1193, simple_loss=0.1941, pruned_loss=0.02224, over 4760.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.0331, over 971045.64 frames.], batch size: 19, lr: 1.99e-04
+2022-05-07 01:41:24,987 INFO [train.py:715] (3/8) Epoch 11, batch 6100, loss[loss=0.1604, simple_loss=0.2378, pruned_loss=0.04147, over 4803.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.0334, over 970813.12 frames.], batch size: 26, lr: 1.99e-04
+2022-05-07 01:42:03,737 INFO [train.py:715] (3/8) Epoch 11, batch 6150, loss[loss=0.1216, simple_loss=0.1978, pruned_loss=0.02268, over 4790.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03331, over 970342.09 frames.], batch size: 14, lr: 1.99e-04
+2022-05-07 01:42:43,201 INFO [train.py:715] (3/8) Epoch 11, batch 6200, loss[loss=0.1495, simple_loss=0.2141, pruned_loss=0.04248, over 4965.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2131, pruned_loss=0.03413, over 970791.93 frames.], batch size: 14, lr: 1.99e-04
+2022-05-07 01:43:22,230 INFO [train.py:715] (3/8) Epoch 11, batch 6250, loss[loss=0.1548, simple_loss=0.2336, pruned_loss=0.03801, over 4860.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2121, pruned_loss=0.03353, over 971399.01 frames.], batch size: 15, lr: 1.99e-04
+2022-05-07 01:44:01,022 INFO [train.py:715] (3/8) Epoch 11, batch 6300, loss[loss=0.1299, simple_loss=0.2071, pruned_loss=0.02632, over 4803.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03308, over 972546.39 frames.], batch size: 21, lr: 1.99e-04
+2022-05-07 01:44:39,692 INFO [train.py:715] (3/8) Epoch 11, batch 6350, loss[loss=0.1585, simple_loss=0.222, pruned_loss=0.04755, over 4748.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03331, over 971999.21 frames.], batch size: 16, lr: 1.99e-04
+2022-05-07 01:45:20,272 INFO [train.py:715] (3/8) Epoch 11, batch 6400, loss[loss=0.1393, simple_loss=0.2244, pruned_loss=0.02713, over 4791.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03324, over 971776.81 frames.], batch size: 17, lr: 1.99e-04
+2022-05-07 01:45:59,616 INFO [train.py:715] (3/8) Epoch 11, batch 6450, loss[loss=0.1259, simple_loss=0.2053, pruned_loss=0.02322, over 4889.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03291, over 971719.91 frames.], batch size: 39, lr: 1.99e-04
+2022-05-07 01:46:38,691 INFO [train.py:715] (3/8) Epoch 11, batch 6500, loss[loss=0.1252, simple_loss=0.2039, pruned_loss=0.02324, over 4966.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03247, over 971931.18 frames.], batch size: 24, lr: 1.99e-04
+2022-05-07 01:47:18,037 INFO [train.py:715] (3/8) Epoch 11, batch 6550, loss[loss=0.1483, simple_loss=0.2257, pruned_loss=0.03547, over 4939.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.0332, over 972277.62 frames.], batch size: 21, lr: 1.99e-04
+2022-05-07 01:47:58,218 INFO [train.py:715] (3/8) Epoch 11, batch 6600, loss[loss=0.1411, simple_loss=0.2031, pruned_loss=0.03955, over 4812.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03327, over 972574.20 frames.], batch size: 13, lr: 1.99e-04
+2022-05-07 01:48:38,343 INFO [train.py:715] (3/8) Epoch 11, batch 6650, loss[loss=0.1271, simple_loss=0.1985, pruned_loss=0.02787, over 4855.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.03303, over 973034.59 frames.], batch size: 20, lr: 1.99e-04
+2022-05-07 01:49:17,553 INFO [train.py:715] (3/8) Epoch 11, batch 6700, loss[loss=0.143, simple_loss=0.2086, pruned_loss=0.03868, over 4773.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03322, over 972060.07 frames.], batch size: 18, lr: 1.99e-04
+2022-05-07 01:49:57,813 INFO [train.py:715] (3/8) Epoch 11, batch 6750, loss[loss=0.1517, simple_loss=0.2108, pruned_loss=0.04627, over 4784.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2113, pruned_loss=0.03282, over 971792.44 frames.], batch size: 14, lr: 1.99e-04
+2022-05-07 01:50:37,609 INFO [train.py:715] (3/8) Epoch 11, batch 6800, loss[loss=0.1268, simple_loss=0.2052, pruned_loss=0.02413, over 4917.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03316, over 971765.72 frames.], batch size: 29, lr: 1.99e-04
+2022-05-07 01:51:16,477 INFO [train.py:715] (3/8) Epoch 11, batch 6850, loss[loss=0.1288, simple_loss=0.2173, pruned_loss=0.02016, over 4747.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03288, over 971486.04 frames.], batch size: 16, lr: 1.99e-04
+2022-05-07 01:51:55,544 INFO [train.py:715] (3/8) Epoch 11, batch 6900, loss[loss=0.1058, simple_loss=0.1812, pruned_loss=0.01513, over 4965.00 frames.], tot_loss[loss=0.139, simple_loss=0.2126, pruned_loss=0.03272, over 971669.45 frames.], batch size: 28, lr: 1.99e-04
+2022-05-07 01:52:34,233 INFO [train.py:715] (3/8) Epoch 11, batch 6950, loss[loss=0.1297, simple_loss=0.2041, pruned_loss=0.02763, over 4943.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03229, over 972211.63 frames.], batch size: 21, lr: 1.99e-04
+2022-05-07 01:53:13,693 INFO [train.py:715] (3/8) Epoch 11, batch 7000, loss[loss=0.1419, simple_loss=0.215, pruned_loss=0.03439, over 4876.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2125, pruned_loss=0.03244, over 972515.69 frames.], batch size: 32, lr: 1.99e-04
+2022-05-07 01:53:52,254 INFO [train.py:715] (3/8) Epoch 11, batch 7050, loss[loss=0.1253, simple_loss=0.2009, pruned_loss=0.02488, over 4893.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2121, pruned_loss=0.03248, over 971807.91 frames.], batch size: 22, lr: 1.99e-04
+2022-05-07 01:54:31,696 INFO [train.py:715] (3/8) Epoch 11, batch 7100, loss[loss=0.1553, simple_loss=0.2343, pruned_loss=0.03809, over 4750.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03208, over 971542.98 frames.], batch size: 19, lr: 1.99e-04
+2022-05-07 01:55:10,749 INFO [train.py:715] (3/8) Epoch 11, batch 7150, loss[loss=0.1433, simple_loss=0.2186, pruned_loss=0.03397, over 4863.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03215, over 971580.28 frames.], batch size: 20, lr: 1.99e-04
+2022-05-07 01:55:49,510 INFO [train.py:715] (3/8) Epoch 11, batch 7200, loss[loss=0.1187, simple_loss=0.191, pruned_loss=0.02318, over 4764.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03193, over 972709.30 frames.], batch size: 16, lr: 1.99e-04
+2022-05-07 01:56:28,452 INFO [train.py:715] (3/8) Epoch 11, batch 7250, loss[loss=0.1318, simple_loss=0.2095, pruned_loss=0.02704, over 4955.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03172, over 973030.14 frames.], batch size: 21, lr: 1.99e-04
+2022-05-07 01:57:07,430 INFO [train.py:715] (3/8) Epoch 11, batch 7300, loss[loss=0.1493, simple_loss=0.2168, pruned_loss=0.04089, over 4853.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2115, pruned_loss=0.03215, over 973474.15 frames.], batch size: 20, lr: 1.99e-04
+2022-05-07 01:57:46,540 INFO [train.py:715] (3/8) Epoch 11, batch 7350, loss[loss=0.1674, simple_loss=0.2536, pruned_loss=0.04062, over 4739.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2126, pruned_loss=0.03226, over 973135.62 frames.], batch size: 16, lr: 1.99e-04
+2022-05-07 01:58:25,307 INFO [train.py:715] (3/8) Epoch 11, batch 7400, loss[loss=0.1273, simple_loss=0.2093, pruned_loss=0.02265, over 4857.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2122, pruned_loss=0.03214, over 972813.49 frames.], batch size: 22, lr: 1.98e-04
+2022-05-07 01:59:04,703 INFO [train.py:715] (3/8) Epoch 11, batch 7450, loss[loss=0.1275, simple_loss=0.2094, pruned_loss=0.02281, over 4944.00 frames.], tot_loss[loss=0.1379, simple_loss=0.212, pruned_loss=0.03195, over 974784.15 frames.], batch size: 35, lr: 1.98e-04
+2022-05-07 01:59:43,842 INFO [train.py:715] (3/8) Epoch 11, batch 7500, loss[loss=0.1506, simple_loss=0.2241, pruned_loss=0.03855, over 4801.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2125, pruned_loss=0.0325, over 974425.21 frames.], batch size: 17, lr: 1.98e-04
+2022-05-07 02:00:23,090 INFO [train.py:715] (3/8) Epoch 11, batch 7550, loss[loss=0.1135, simple_loss=0.1919, pruned_loss=0.01757, over 4936.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2124, pruned_loss=0.03247, over 973776.61 frames.], batch size: 29, lr: 1.98e-04
+2022-05-07 02:01:02,846 INFO [train.py:715] (3/8) Epoch 11, batch 7600, loss[loss=0.1273, simple_loss=0.1985, pruned_loss=0.02807, over 4826.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2123, pruned_loss=0.03246, over 973830.04 frames.], batch size: 25, lr: 1.98e-04
+2022-05-07 02:01:42,512 INFO [train.py:715] (3/8) Epoch 11, batch 7650, loss[loss=0.1503, simple_loss=0.2181, pruned_loss=0.04122, over 4858.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2127, pruned_loss=0.03296, over 973055.39 frames.], batch size: 20, lr: 1.98e-04
+2022-05-07 02:02:22,053 INFO [train.py:715] (3/8) Epoch 11, batch 7700, loss[loss=0.1369, simple_loss=0.2099, pruned_loss=0.03201, over 4765.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03284, over 972652.85 frames.], batch size: 17, lr: 1.98e-04
+2022-05-07 02:03:01,233 INFO [train.py:715] (3/8) Epoch 11, batch 7750, loss[loss=0.1596, simple_loss=0.2177, pruned_loss=0.05072, over 4815.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03247, over 972191.45 frames.], batch size: 13, lr: 1.98e-04
+2022-05-07 02:03:40,567 INFO [train.py:715] (3/8) Epoch 11, batch 7800, loss[loss=0.1339, simple_loss=0.2151, pruned_loss=0.02635, over 4939.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03261, over 972240.89 frames.], batch size: 29, lr: 1.98e-04
+2022-05-07 02:04:19,853 INFO [train.py:715] (3/8) Epoch 11, batch 7850, loss[loss=0.1615, simple_loss=0.2356, pruned_loss=0.0437, over 4769.00 frames.], tot_loss[loss=0.139, simple_loss=0.2123, pruned_loss=0.03289, over 972489.85 frames.], batch size: 18, lr: 1.98e-04
+2022-05-07 02:04:58,993 INFO [train.py:715] (3/8) Epoch 11, batch 7900, loss[loss=0.1212, simple_loss=0.1964, pruned_loss=0.02301, over 4747.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03322, over 972461.75 frames.], batch size: 16, lr: 1.98e-04
+2022-05-07 02:05:37,730 INFO [train.py:715] (3/8) Epoch 11, batch 7950, loss[loss=0.1697, simple_loss=0.2302, pruned_loss=0.05459, over 4940.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03318, over 972634.17 frames.], batch size: 21, lr: 1.98e-04
+2022-05-07 02:06:18,360 INFO [train.py:715] (3/8) Epoch 11, batch 8000, loss[loss=0.1033, simple_loss=0.1718, pruned_loss=0.01739, over 4754.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2117, pruned_loss=0.03305, over 972746.51 frames.], batch size: 12, lr: 1.98e-04
+2022-05-07 02:06:57,624 INFO [train.py:715] (3/8) Epoch 11, batch 8050, loss[loss=0.1253, simple_loss=0.1958, pruned_loss=0.02742, over 4837.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.03343, over 972983.94 frames.], batch size: 32, lr: 1.98e-04
+2022-05-07 02:07:37,876 INFO [train.py:715] (3/8) Epoch 11, batch 8100, loss[loss=0.1532, simple_loss=0.2321, pruned_loss=0.03711, over 4977.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03326, over 973468.57 frames.], batch size: 24, lr: 1.98e-04
+2022-05-07 02:08:17,870 INFO [train.py:715] (3/8) Epoch 11, batch 8150, loss[loss=0.1037, simple_loss=0.1699, pruned_loss=0.01873, over 4822.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03319, over 972640.74 frames.], batch size: 13, lr: 1.98e-04
+2022-05-07 02:08:57,396 INFO [train.py:715] (3/8) Epoch 11, batch 8200, loss[loss=0.1354, simple_loss=0.2126, pruned_loss=0.0291, over 4845.00 frames.], tot_loss[loss=0.14, simple_loss=0.2132, pruned_loss=0.03343, over 973113.37 frames.], batch size: 15, lr: 1.98e-04
+2022-05-07 02:09:36,728 INFO [train.py:715] (3/8) Epoch 11, batch 8250, loss[loss=0.1416, simple_loss=0.2138, pruned_loss=0.03469, over 4774.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03323, over 973233.82 frames.], batch size: 18, lr: 1.98e-04
+2022-05-07 02:10:15,060 INFO [train.py:715] (3/8) Epoch 11, batch 8300, loss[loss=0.1382, simple_loss=0.215, pruned_loss=0.03076, over 4786.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03364, over 973517.93 frames.], batch size: 21, lr: 1.98e-04
+2022-05-07 02:10:54,959 INFO [train.py:715] (3/8) Epoch 11, batch 8350, loss[loss=0.1419, simple_loss=0.222, pruned_loss=0.03093, over 4932.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03373, over 973294.82 frames.], batch size: 23, lr: 1.98e-04
+2022-05-07 02:11:34,527 INFO [train.py:715] (3/8) Epoch 11, batch 8400, loss[loss=0.1194, simple_loss=0.1935, pruned_loss=0.02264, over 4991.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.03351, over 973424.43 frames.], batch size: 20, lr: 1.98e-04
+2022-05-07 02:12:13,501 INFO [train.py:715] (3/8) Epoch 11, batch 8450, loss[loss=0.1162, simple_loss=0.1922, pruned_loss=0.02004, over 4824.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03351, over 973233.63 frames.], batch size: 25, lr: 1.98e-04
+2022-05-07 02:12:52,200 INFO [train.py:715] (3/8) Epoch 11, batch 8500, loss[loss=0.1451, simple_loss=0.2198, pruned_loss=0.03522, over 4933.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.0337, over 973128.57 frames.], batch size: 21, lr: 1.98e-04
+2022-05-07 02:13:32,005 INFO [train.py:715] (3/8) Epoch 11, batch 8550, loss[loss=0.1565, simple_loss=0.228, pruned_loss=0.04247, over 4838.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.0335, over 972972.57 frames.], batch size: 25, lr: 1.98e-04
+2022-05-07 02:14:11,213 INFO [train.py:715] (3/8) Epoch 11, batch 8600, loss[loss=0.115, simple_loss=0.1817, pruned_loss=0.02417, over 4927.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03351, over 972434.89 frames.], batch size: 29, lr: 1.98e-04
+2022-05-07 02:14:49,545 INFO [train.py:715] (3/8) Epoch 11, batch 8650, loss[loss=0.117, simple_loss=0.1868, pruned_loss=0.0236, over 4821.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03414, over 971910.17 frames.], batch size: 13, lr: 1.98e-04
+2022-05-07 02:15:29,403 INFO [train.py:715] (3/8) Epoch 11, batch 8700, loss[loss=0.1409, simple_loss=0.2155, pruned_loss=0.03318, over 4874.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2129, pruned_loss=0.0339, over 971827.52 frames.], batch size: 16, lr: 1.98e-04
+2022-05-07 02:16:08,720 INFO [train.py:715] (3/8) Epoch 11, batch 8750, loss[loss=0.1293, simple_loss=0.2068, pruned_loss=0.02595, over 4877.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2119, pruned_loss=0.03362, over 972169.18 frames.], batch size: 20, lr: 1.98e-04
+2022-05-07 02:16:47,705 INFO [train.py:715] (3/8) Epoch 11, batch 8800, loss[loss=0.158, simple_loss=0.2311, pruned_loss=0.04247, over 4756.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2116, pruned_loss=0.0337, over 971496.35 frames.], batch size: 16, lr: 1.98e-04
+2022-05-07 02:17:26,836 INFO [train.py:715] (3/8) Epoch 11, batch 8850, loss[loss=0.1466, simple_loss=0.2207, pruned_loss=0.03623, over 4787.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2126, pruned_loss=0.03399, over 971346.18 frames.], batch size: 17, lr: 1.98e-04
+2022-05-07 02:18:06,537 INFO [train.py:715] (3/8) Epoch 11, batch 8900, loss[loss=0.138, simple_loss=0.2117, pruned_loss=0.0321, over 4899.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.03345, over 971379.43 frames.], batch size: 19, lr: 1.98e-04
+2022-05-07 02:18:46,168 INFO [train.py:715] (3/8) Epoch 11, batch 8950, loss[loss=0.1302, simple_loss=0.2045, pruned_loss=0.02793, over 4914.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.03355, over 970505.22 frames.], batch size: 18, lr: 1.98e-04
+2022-05-07 02:19:25,277 INFO [train.py:715] (3/8) Epoch 11, batch 9000, loss[loss=0.1737, simple_loss=0.2491, pruned_loss=0.04914, over 4937.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03334, over 972028.80 frames.], batch size: 39, lr: 1.98e-04
+2022-05-07 02:19:25,278 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 02:19:34,856 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1903, pruned_loss=0.011, over 914524.00 frames.
+2022-05-07 02:20:13,750 INFO [train.py:715] (3/8) Epoch 11, batch 9050, loss[loss=0.1884, simple_loss=0.2479, pruned_loss=0.06449, over 4892.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03296, over 971917.80 frames.], batch size: 32, lr: 1.98e-04
+2022-05-07 02:20:55,922 INFO [train.py:715] (3/8) Epoch 11, batch 9100, loss[loss=0.1795, simple_loss=0.2495, pruned_loss=0.05478, over 4846.00 frames.], tot_loss[loss=0.1404, simple_loss=0.214, pruned_loss=0.03341, over 972374.12 frames.], batch size: 30, lr: 1.98e-04
+2022-05-07 02:21:35,544 INFO [train.py:715] (3/8) Epoch 11, batch 9150, loss[loss=0.1299, simple_loss=0.205, pruned_loss=0.02742, over 4754.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2141, pruned_loss=0.03327, over 973389.92 frames.], batch size: 19, lr: 1.98e-04
+2022-05-07 02:22:15,054 INFO [train.py:715] (3/8) Epoch 11, batch 9200, loss[loss=0.1279, simple_loss=0.1882, pruned_loss=0.03378, over 4906.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2129, pruned_loss=0.03285, over 972983.61 frames.], batch size: 29, lr: 1.98e-04
+2022-05-07 02:22:54,636 INFO [train.py:715] (3/8) Epoch 11, batch 9250, loss[loss=0.1686, simple_loss=0.2525, pruned_loss=0.04233, over 4791.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2139, pruned_loss=0.03328, over 972916.11 frames.], batch size: 17, lr: 1.98e-04
+2022-05-07 02:23:33,872 INFO [train.py:715] (3/8) Epoch 11, batch 9300, loss[loss=0.1243, simple_loss=0.1948, pruned_loss=0.02684, over 4810.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2141, pruned_loss=0.03373, over 972324.45 frames.], batch size: 27, lr: 1.98e-04
+2022-05-07 02:24:12,708 INFO [train.py:715] (3/8) Epoch 11, batch 9350, loss[loss=0.1745, simple_loss=0.2317, pruned_loss=0.0587, over 4871.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2145, pruned_loss=0.03386, over 972192.21 frames.], batch size: 39, lr: 1.98e-04
+2022-05-07 02:24:51,487 INFO [train.py:715] (3/8) Epoch 11, batch 9400, loss[loss=0.1299, simple_loss=0.2058, pruned_loss=0.02695, over 4807.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2147, pruned_loss=0.03402, over 972656.53 frames.], batch size: 21, lr: 1.98e-04
+2022-05-07 02:25:31,001 INFO [train.py:715] (3/8) Epoch 11, batch 9450, loss[loss=0.1547, simple_loss=0.2358, pruned_loss=0.03678, over 4878.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2142, pruned_loss=0.03363, over 973345.63 frames.], batch size: 22, lr: 1.98e-04
+2022-05-07 02:26:10,042 INFO [train.py:715] (3/8) Epoch 11, batch 9500, loss[loss=0.1586, simple_loss=0.2262, pruned_loss=0.04547, over 4927.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03357, over 973856.07 frames.], batch size: 18, lr: 1.98e-04
+2022-05-07 02:26:48,572 INFO [train.py:715] (3/8) Epoch 11, batch 9550, loss[loss=0.1396, simple_loss=0.2071, pruned_loss=0.03606, over 4987.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03334, over 974061.41 frames.], batch size: 28, lr: 1.98e-04
+2022-05-07 02:27:28,234 INFO [train.py:715] (3/8) Epoch 11, batch 9600, loss[loss=0.1228, simple_loss=0.1988, pruned_loss=0.02341, over 4940.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03281, over 973676.54 frames.], batch size: 23, lr: 1.98e-04
+2022-05-07 02:28:07,061 INFO [train.py:715] (3/8) Epoch 11, batch 9650, loss[loss=0.1418, simple_loss=0.2272, pruned_loss=0.02816, over 4919.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03274, over 973409.26 frames.], batch size: 18, lr: 1.98e-04
+2022-05-07 02:28:45,587 INFO [train.py:715] (3/8) Epoch 11, batch 9700, loss[loss=0.1215, simple_loss=0.1994, pruned_loss=0.02177, over 4746.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03325, over 971911.08 frames.], batch size: 16, lr: 1.98e-04
+2022-05-07 02:29:24,590 INFO [train.py:715] (3/8) Epoch 11, batch 9750, loss[loss=0.1425, simple_loss=0.2123, pruned_loss=0.03636, over 4966.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03283, over 972070.81 frames.], batch size: 21, lr: 1.98e-04
+2022-05-07 02:30:03,698 INFO [train.py:715] (3/8) Epoch 11, batch 9800, loss[loss=0.1526, simple_loss=0.2304, pruned_loss=0.03734, over 4790.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03324, over 971639.56 frames.], batch size: 18, lr: 1.98e-04
+2022-05-07 02:30:43,327 INFO [train.py:715] (3/8) Epoch 11, batch 9850, loss[loss=0.1458, simple_loss=0.2079, pruned_loss=0.0419, over 4906.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2115, pruned_loss=0.03334, over 971232.96 frames.], batch size: 19, lr: 1.98e-04
+2022-05-07 02:31:22,285 INFO [train.py:715] (3/8) Epoch 11, batch 9900, loss[loss=0.1222, simple_loss=0.2001, pruned_loss=0.02221, over 4952.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2111, pruned_loss=0.03301, over 972033.95 frames.], batch size: 24, lr: 1.98e-04
+2022-05-07 02:32:02,527 INFO [train.py:715] (3/8) Epoch 11, batch 9950, loss[loss=0.1654, simple_loss=0.2341, pruned_loss=0.04832, over 4846.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2118, pruned_loss=0.03335, over 972554.33 frames.], batch size: 15, lr: 1.98e-04
+2022-05-07 02:32:41,853 INFO [train.py:715] (3/8) Epoch 11, batch 10000, loss[loss=0.1394, simple_loss=0.2055, pruned_loss=0.03659, over 4917.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.0333, over 972706.03 frames.], batch size: 17, lr: 1.98e-04
+2022-05-07 02:33:21,582 INFO [train.py:715] (3/8) Epoch 11, batch 10050, loss[loss=0.1223, simple_loss=0.1946, pruned_loss=0.02498, over 4985.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2117, pruned_loss=0.03329, over 972261.69 frames.], batch size: 28, lr: 1.98e-04
+2022-05-07 02:33:59,721 INFO [train.py:715] (3/8) Epoch 11, batch 10100, loss[loss=0.1134, simple_loss=0.1844, pruned_loss=0.02117, over 4737.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03287, over 973335.08 frames.], batch size: 16, lr: 1.98e-04
+2022-05-07 02:34:38,756 INFO [train.py:715] (3/8) Epoch 11, batch 10150, loss[loss=0.1527, simple_loss=0.2304, pruned_loss=0.03747, over 4770.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03327, over 973624.77 frames.], batch size: 18, lr: 1.98e-04
+2022-05-07 02:35:17,189 INFO [train.py:715] (3/8) Epoch 11, batch 10200, loss[loss=0.1229, simple_loss=0.189, pruned_loss=0.02836, over 4802.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2121, pruned_loss=0.03356, over 973151.59 frames.], batch size: 12, lr: 1.98e-04
+2022-05-07 02:35:55,358 INFO [train.py:715] (3/8) Epoch 11, batch 10250, loss[loss=0.143, simple_loss=0.2266, pruned_loss=0.02975, over 4967.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03306, over 972831.81 frames.], batch size: 24, lr: 1.98e-04
+2022-05-07 02:36:34,758 INFO [train.py:715] (3/8) Epoch 11, batch 10300, loss[loss=0.1511, simple_loss=0.2257, pruned_loss=0.03832, over 4771.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2134, pruned_loss=0.03312, over 972257.68 frames.], batch size: 17, lr: 1.98e-04
+2022-05-07 02:37:13,485 INFO [train.py:715] (3/8) Epoch 11, batch 10350, loss[loss=0.1903, simple_loss=0.2616, pruned_loss=0.05952, over 4770.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2142, pruned_loss=0.03381, over 972136.61 frames.], batch size: 16, lr: 1.98e-04
+2022-05-07 02:37:52,307 INFO [train.py:715] (3/8) Epoch 11, batch 10400, loss[loss=0.1377, simple_loss=0.2151, pruned_loss=0.03013, over 4978.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2134, pruned_loss=0.03312, over 972632.21 frames.], batch size: 24, lr: 1.98e-04
+2022-05-07 02:38:30,786 INFO [train.py:715] (3/8) Epoch 11, batch 10450, loss[loss=0.121, simple_loss=0.1965, pruned_loss=0.02276, over 4872.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03328, over 972051.97 frames.], batch size: 16, lr: 1.98e-04
+2022-05-07 02:39:09,428 INFO [train.py:715] (3/8) Epoch 11, batch 10500, loss[loss=0.1331, simple_loss=0.2034, pruned_loss=0.03142, over 4921.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03336, over 971504.27 frames.], batch size: 23, lr: 1.98e-04
+2022-05-07 02:39:48,486 INFO [train.py:715] (3/8) Epoch 11, batch 10550, loss[loss=0.1483, simple_loss=0.2188, pruned_loss=0.03888, over 4923.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03277, over 971292.52 frames.], batch size: 23, lr: 1.98e-04
+2022-05-07 02:40:27,834 INFO [train.py:715] (3/8) Epoch 11, batch 10600, loss[loss=0.126, simple_loss=0.2028, pruned_loss=0.0246, over 4818.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2121, pruned_loss=0.03259, over 971023.82 frames.], batch size: 27, lr: 1.98e-04
+2022-05-07 02:41:06,622 INFO [train.py:715] (3/8) Epoch 11, batch 10650, loss[loss=0.1417, simple_loss=0.2223, pruned_loss=0.03057, over 4979.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03213, over 971354.26 frames.], batch size: 39, lr: 1.98e-04
+2022-05-07 02:41:45,852 INFO [train.py:715] (3/8) Epoch 11, batch 10700, loss[loss=0.1631, simple_loss=0.2457, pruned_loss=0.04032, over 4981.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03211, over 971881.64 frames.], batch size: 39, lr: 1.98e-04
+2022-05-07 02:42:25,053 INFO [train.py:715] (3/8) Epoch 11, batch 10750, loss[loss=0.1365, simple_loss=0.2156, pruned_loss=0.02865, over 4741.00 frames.], tot_loss[loss=0.138, simple_loss=0.212, pruned_loss=0.03203, over 970889.88 frames.], batch size: 16, lr: 1.98e-04
+2022-05-07 02:43:03,975 INFO [train.py:715] (3/8) Epoch 11, batch 10800, loss[loss=0.1399, simple_loss=0.2205, pruned_loss=0.02967, over 4939.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.03204, over 971895.47 frames.], batch size: 21, lr: 1.98e-04
+2022-05-07 02:43:43,681 INFO [train.py:715] (3/8) Epoch 11, batch 10850, loss[loss=0.1605, simple_loss=0.2322, pruned_loss=0.04442, over 4753.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03244, over 971677.61 frames.], batch size: 19, lr: 1.98e-04
+2022-05-07 02:44:23,475 INFO [train.py:715] (3/8) Epoch 11, batch 10900, loss[loss=0.1483, simple_loss=0.2193, pruned_loss=0.03869, over 4968.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2122, pruned_loss=0.03269, over 972746.87 frames.], batch size: 15, lr: 1.98e-04
+2022-05-07 02:45:02,833 INFO [train.py:715] (3/8) Epoch 11, batch 10950, loss[loss=0.1428, simple_loss=0.2052, pruned_loss=0.04021, over 4939.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03266, over 972309.08 frames.], batch size: 18, lr: 1.98e-04
+2022-05-07 02:45:42,048 INFO [train.py:715] (3/8) Epoch 11, batch 11000, loss[loss=0.1472, simple_loss=0.2172, pruned_loss=0.03862, over 4973.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2112, pruned_loss=0.03224, over 972566.67 frames.], batch size: 28, lr: 1.98e-04
+2022-05-07 02:46:21,451 INFO [train.py:715] (3/8) Epoch 11, batch 11050, loss[loss=0.1351, simple_loss=0.2117, pruned_loss=0.0293, over 4932.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03227, over 972650.54 frames.], batch size: 39, lr: 1.98e-04
+2022-05-07 02:47:00,458 INFO [train.py:715] (3/8) Epoch 11, batch 11100, loss[loss=0.1209, simple_loss=0.1965, pruned_loss=0.02267, over 4819.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03238, over 973203.06 frames.], batch size: 25, lr: 1.98e-04
+2022-05-07 02:47:39,069 INFO [train.py:715] (3/8) Epoch 11, batch 11150, loss[loss=0.1446, simple_loss=0.2285, pruned_loss=0.03036, over 4904.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03215, over 972781.97 frames.], batch size: 19, lr: 1.98e-04
+2022-05-07 02:48:18,474 INFO [train.py:715] (3/8) Epoch 11, batch 11200, loss[loss=0.1212, simple_loss=0.2078, pruned_loss=0.01728, over 4882.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03207, over 972605.44 frames.], batch size: 22, lr: 1.98e-04
+2022-05-07 02:48:57,591 INFO [train.py:715] (3/8) Epoch 11, batch 11250, loss[loss=0.1443, simple_loss=0.2172, pruned_loss=0.03566, over 4861.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03196, over 973457.03 frames.], batch size: 16, lr: 1.98e-04
+2022-05-07 02:49:35,932 INFO [train.py:715] (3/8) Epoch 11, batch 11300, loss[loss=0.1335, simple_loss=0.2067, pruned_loss=0.03012, over 4771.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.0315, over 972868.91 frames.], batch size: 17, lr: 1.98e-04
+2022-05-07 02:50:14,829 INFO [train.py:715] (3/8) Epoch 11, batch 11350, loss[loss=0.1226, simple_loss=0.2013, pruned_loss=0.02196, over 4827.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03128, over 972225.94 frames.], batch size: 27, lr: 1.97e-04
+2022-05-07 02:50:54,372 INFO [train.py:715] (3/8) Epoch 11, batch 11400, loss[loss=0.1365, simple_loss=0.2072, pruned_loss=0.0329, over 4854.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03139, over 971652.67 frames.], batch size: 30, lr: 1.97e-04
+2022-05-07 02:51:32,956 INFO [train.py:715] (3/8) Epoch 11, batch 11450, loss[loss=0.1035, simple_loss=0.1785, pruned_loss=0.01424, over 4817.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.0311, over 972383.96 frames.], batch size: 12, lr: 1.97e-04
+2022-05-07 02:52:11,285 INFO [train.py:715] (3/8) Epoch 11, batch 11500, loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02889, over 4914.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03136, over 972914.65 frames.], batch size: 23, lr: 1.97e-04
+2022-05-07 02:52:50,110 INFO [train.py:715] (3/8) Epoch 11, batch 11550, loss[loss=0.1564, simple_loss=0.2246, pruned_loss=0.04413, over 4775.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03123, over 973737.45 frames.], batch size: 14, lr: 1.97e-04
+2022-05-07 02:53:29,303 INFO [train.py:715] (3/8) Epoch 11, batch 11600, loss[loss=0.1358, simple_loss=0.2085, pruned_loss=0.0315, over 4970.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03168, over 974254.65 frames.], batch size: 14, lr: 1.97e-04
+2022-05-07 02:54:08,232 INFO [train.py:715] (3/8) Epoch 11, batch 11650, loss[loss=0.1375, simple_loss=0.2058, pruned_loss=0.03457, over 4840.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03193, over 972580.74 frames.], batch size: 13, lr: 1.97e-04
+2022-05-07 02:54:46,493 INFO [train.py:715] (3/8) Epoch 11, batch 11700, loss[loss=0.1425, simple_loss=0.2254, pruned_loss=0.02983, over 4877.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.0323, over 972782.83 frames.], batch size: 16, lr: 1.97e-04
+2022-05-07 02:55:25,411 INFO [train.py:715] (3/8) Epoch 11, batch 11750, loss[loss=0.1497, simple_loss=0.2228, pruned_loss=0.03829, over 4850.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03233, over 972433.47 frames.], batch size: 30, lr: 1.97e-04
+2022-05-07 02:56:04,627 INFO [train.py:715] (3/8) Epoch 11, batch 11800, loss[loss=0.12, simple_loss=0.1919, pruned_loss=0.02403, over 4992.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03231, over 972671.09 frames.], batch size: 15, lr: 1.97e-04
+2022-05-07 02:56:43,716 INFO [train.py:715] (3/8) Epoch 11, batch 11850, loss[loss=0.1677, simple_loss=0.2322, pruned_loss=0.05158, over 4982.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03217, over 971940.05 frames.], batch size: 39, lr: 1.97e-04
+2022-05-07 02:57:23,412 INFO [train.py:715] (3/8) Epoch 11, batch 11900, loss[loss=0.1763, simple_loss=0.2496, pruned_loss=0.05153, over 4989.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2115, pruned_loss=0.03286, over 971871.35 frames.], batch size: 14, lr: 1.97e-04
+2022-05-07 02:58:03,754 INFO [train.py:715] (3/8) Epoch 11, batch 11950, loss[loss=0.1206, simple_loss=0.193, pruned_loss=0.02409, over 4846.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03269, over 971397.40 frames.], batch size: 12, lr: 1.97e-04
+2022-05-07 02:58:43,548 INFO [train.py:715] (3/8) Epoch 11, batch 12000, loss[loss=0.1481, simple_loss=0.2134, pruned_loss=0.04137, over 4801.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03273, over 972334.42 frames.], batch size: 13, lr: 1.97e-04
+2022-05-07 02:58:43,549 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 02:58:53,274 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1902, pruned_loss=0.01096, over 914524.00 frames.
+2022-05-07 02:59:33,213 INFO [train.py:715] (3/8) Epoch 11, batch 12050, loss[loss=0.1402, simple_loss=0.2082, pruned_loss=0.03609, over 4902.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03292, over 972317.54 frames.], batch size: 17, lr: 1.97e-04
+2022-05-07 03:00:12,649 INFO [train.py:715] (3/8) Epoch 11, batch 12100, loss[loss=0.1354, simple_loss=0.2116, pruned_loss=0.02964, over 4875.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03322, over 973242.24 frames.], batch size: 20, lr: 1.97e-04
+2022-05-07 03:00:51,872 INFO [train.py:715] (3/8) Epoch 11, batch 12150, loss[loss=0.1497, simple_loss=0.2263, pruned_loss=0.03652, over 4764.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.03303, over 972913.00 frames.], batch size: 17, lr: 1.97e-04
+2022-05-07 03:01:31,401 INFO [train.py:715] (3/8) Epoch 11, batch 12200, loss[loss=0.1386, simple_loss=0.2092, pruned_loss=0.03396, over 4982.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.03282, over 973971.20 frames.], batch size: 25, lr: 1.97e-04
+2022-05-07 03:02:09,902 INFO [train.py:715] (3/8) Epoch 11, batch 12250, loss[loss=0.1516, simple_loss=0.2246, pruned_loss=0.03931, over 4797.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03293, over 972997.73 frames.], batch size: 13, lr: 1.97e-04
+2022-05-07 03:02:49,518 INFO [train.py:715] (3/8) Epoch 11, batch 12300, loss[loss=0.1454, simple_loss=0.2166, pruned_loss=0.03709, over 4958.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03313, over 973169.27 frames.], batch size: 35, lr: 1.97e-04
+2022-05-07 03:03:29,335 INFO [train.py:715] (3/8) Epoch 11, batch 12350, loss[loss=0.1235, simple_loss=0.2016, pruned_loss=0.02268, over 4931.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03334, over 973231.19 frames.], batch size: 18, lr: 1.97e-04
+2022-05-07 03:04:08,693 INFO [train.py:715] (3/8) Epoch 11, batch 12400, loss[loss=0.1348, simple_loss=0.2148, pruned_loss=0.02737, over 4958.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2119, pruned_loss=0.03316, over 973696.98 frames.], batch size: 21, lr: 1.97e-04
+2022-05-07 03:04:46,933 INFO [train.py:715] (3/8) Epoch 11, batch 12450, loss[loss=0.1186, simple_loss=0.1843, pruned_loss=0.02651, over 4927.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03301, over 972992.16 frames.], batch size: 23, lr: 1.97e-04
+2022-05-07 03:05:26,164 INFO [train.py:715] (3/8) Epoch 11, batch 12500, loss[loss=0.1137, simple_loss=0.1966, pruned_loss=0.0154, over 4785.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03265, over 973678.35 frames.], batch size: 12, lr: 1.97e-04
+2022-05-07 03:06:05,433 INFO [train.py:715] (3/8) Epoch 11, batch 12550, loss[loss=0.1332, simple_loss=0.2109, pruned_loss=0.0278, over 4703.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03255, over 972987.14 frames.], batch size: 15, lr: 1.97e-04
+2022-05-07 03:06:44,092 INFO [train.py:715] (3/8) Epoch 11, batch 12600, loss[loss=0.1195, simple_loss=0.189, pruned_loss=0.02503, over 4975.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2107, pruned_loss=0.03257, over 971796.80 frames.], batch size: 25, lr: 1.97e-04
+2022-05-07 03:07:23,080 INFO [train.py:715] (3/8) Epoch 11, batch 12650, loss[loss=0.1335, simple_loss=0.1978, pruned_loss=0.03461, over 4815.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2103, pruned_loss=0.03223, over 970806.19 frames.], batch size: 25, lr: 1.97e-04
+2022-05-07 03:08:02,195 INFO [train.py:715] (3/8) Epoch 11, batch 12700, loss[loss=0.1472, simple_loss=0.2202, pruned_loss=0.03714, over 4740.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.03291, over 970908.43 frames.], batch size: 16, lr: 1.97e-04
+2022-05-07 03:08:40,888 INFO [train.py:715] (3/8) Epoch 11, batch 12750, loss[loss=0.1388, simple_loss=0.2126, pruned_loss=0.03253, over 4945.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03249, over 970506.19 frames.], batch size: 21, lr: 1.97e-04
+2022-05-07 03:09:19,302 INFO [train.py:715] (3/8) Epoch 11, batch 12800, loss[loss=0.1688, simple_loss=0.2419, pruned_loss=0.04786, over 4693.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03292, over 971175.36 frames.], batch size: 15, lr: 1.97e-04
+2022-05-07 03:09:58,877 INFO [train.py:715] (3/8) Epoch 11, batch 12850, loss[loss=0.1171, simple_loss=0.1919, pruned_loss=0.02113, over 4879.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03285, over 971783.21 frames.], batch size: 16, lr: 1.97e-04
+2022-05-07 03:10:38,290 INFO [train.py:715] (3/8) Epoch 11, batch 12900, loss[loss=0.1326, simple_loss=0.2078, pruned_loss=0.02864, over 4771.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03312, over 972243.80 frames.], batch size: 18, lr: 1.97e-04
+2022-05-07 03:11:17,931 INFO [train.py:715] (3/8) Epoch 11, batch 12950, loss[loss=0.1189, simple_loss=0.1821, pruned_loss=0.02786, over 4895.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03294, over 971814.22 frames.], batch size: 19, lr: 1.97e-04
+2022-05-07 03:11:56,710 INFO [train.py:715] (3/8) Epoch 11, batch 13000, loss[loss=0.1217, simple_loss=0.194, pruned_loss=0.02464, over 4910.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03286, over 971667.92 frames.], batch size: 19, lr: 1.97e-04
+2022-05-07 03:12:36,382 INFO [train.py:715] (3/8) Epoch 11, batch 13050, loss[loss=0.1447, simple_loss=0.2164, pruned_loss=0.03646, over 4756.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03278, over 971397.48 frames.], batch size: 16, lr: 1.97e-04
+2022-05-07 03:13:15,472 INFO [train.py:715] (3/8) Epoch 11, batch 13100, loss[loss=0.1387, simple_loss=0.2171, pruned_loss=0.03015, over 4755.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03262, over 971434.69 frames.], batch size: 19, lr: 1.97e-04
+2022-05-07 03:13:53,585 INFO [train.py:715] (3/8) Epoch 11, batch 13150, loss[loss=0.1345, simple_loss=0.2056, pruned_loss=0.03171, over 4844.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03291, over 972345.61 frames.], batch size: 13, lr: 1.97e-04
+2022-05-07 03:14:32,701 INFO [train.py:715] (3/8) Epoch 11, batch 13200, loss[loss=0.1301, simple_loss=0.2127, pruned_loss=0.02381, over 4919.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03205, over 971748.77 frames.], batch size: 17, lr: 1.97e-04
+2022-05-07 03:15:11,058 INFO [train.py:715] (3/8) Epoch 11, batch 13250, loss[loss=0.1356, simple_loss=0.2012, pruned_loss=0.03503, over 4751.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03241, over 971697.77 frames.], batch size: 12, lr: 1.97e-04
+2022-05-07 03:15:50,453 INFO [train.py:715] (3/8) Epoch 11, batch 13300, loss[loss=0.1362, simple_loss=0.2111, pruned_loss=0.03061, over 4800.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03235, over 972208.19 frames.], batch size: 24, lr: 1.97e-04
+2022-05-07 03:16:29,353 INFO [train.py:715] (3/8) Epoch 11, batch 13350, loss[loss=0.1726, simple_loss=0.245, pruned_loss=0.05003, over 4849.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03291, over 972228.88 frames.], batch size: 30, lr: 1.97e-04
+2022-05-07 03:17:08,598 INFO [train.py:715] (3/8) Epoch 11, batch 13400, loss[loss=0.1165, simple_loss=0.2047, pruned_loss=0.01413, over 4988.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03248, over 971935.16 frames.], batch size: 28, lr: 1.97e-04
+2022-05-07 03:17:47,310 INFO [train.py:715] (3/8) Epoch 11, batch 13450, loss[loss=0.1458, simple_loss=0.2213, pruned_loss=0.03515, over 4864.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03247, over 971772.55 frames.], batch size: 20, lr: 1.97e-04
+2022-05-07 03:18:26,311 INFO [train.py:715] (3/8) Epoch 11, batch 13500, loss[loss=0.1543, simple_loss=0.2384, pruned_loss=0.0351, over 4987.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2123, pruned_loss=0.03257, over 972376.64 frames.], batch size: 25, lr: 1.97e-04
+2022-05-07 03:19:05,026 INFO [train.py:715] (3/8) Epoch 11, batch 13550, loss[loss=0.1281, simple_loss=0.1977, pruned_loss=0.02922, over 4967.00 frames.], tot_loss[loss=0.139, simple_loss=0.2123, pruned_loss=0.03278, over 972727.82 frames.], batch size: 15, lr: 1.97e-04
+2022-05-07 03:19:44,149 INFO [train.py:715] (3/8) Epoch 11, batch 13600, loss[loss=0.1242, simple_loss=0.1931, pruned_loss=0.02763, over 4769.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03203, over 972564.68 frames.], batch size: 12, lr: 1.97e-04
+2022-05-07 03:20:22,538 INFO [train.py:715] (3/8) Epoch 11, batch 13650, loss[loss=0.1375, simple_loss=0.2058, pruned_loss=0.03457, over 4806.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03197, over 972410.07 frames.], batch size: 25, lr: 1.97e-04
+2022-05-07 03:21:00,719 INFO [train.py:715] (3/8) Epoch 11, batch 13700, loss[loss=0.1352, simple_loss=0.2114, pruned_loss=0.02947, over 4836.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03229, over 972556.99 frames.], batch size: 15, lr: 1.97e-04
+2022-05-07 03:21:39,795 INFO [train.py:715] (3/8) Epoch 11, batch 13750, loss[loss=0.1302, simple_loss=0.1925, pruned_loss=0.03398, over 4857.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2102, pruned_loss=0.03237, over 972314.34 frames.], batch size: 32, lr: 1.97e-04
+2022-05-07 03:22:19,175 INFO [train.py:715] (3/8) Epoch 11, batch 13800, loss[loss=0.1304, simple_loss=0.212, pruned_loss=0.02435, over 4781.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03168, over 972294.10 frames.], batch size: 17, lr: 1.97e-04
+2022-05-07 03:22:57,645 INFO [train.py:715] (3/8) Epoch 11, batch 13850, loss[loss=0.1654, simple_loss=0.2448, pruned_loss=0.04306, over 4900.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03242, over 972638.60 frames.], batch size: 19, lr: 1.97e-04
+2022-05-07 03:23:37,055 INFO [train.py:715] (3/8) Epoch 11, batch 13900, loss[loss=0.1331, simple_loss=0.1985, pruned_loss=0.0338, over 4929.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2104, pruned_loss=0.03244, over 972702.20 frames.], batch size: 18, lr: 1.97e-04
+2022-05-07 03:24:15,994 INFO [train.py:715] (3/8) Epoch 11, batch 13950, loss[loss=0.139, simple_loss=0.2093, pruned_loss=0.03433, over 4856.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2111, pruned_loss=0.03253, over 972600.53 frames.], batch size: 20, lr: 1.97e-04
+2022-05-07 03:24:55,160 INFO [train.py:715] (3/8) Epoch 11, batch 14000, loss[loss=0.1478, simple_loss=0.2256, pruned_loss=0.03499, over 4873.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03262, over 972182.06 frames.], batch size: 20, lr: 1.97e-04
+2022-05-07 03:25:34,610 INFO [train.py:715] (3/8) Epoch 11, batch 14050, loss[loss=0.1466, simple_loss=0.2266, pruned_loss=0.03335, over 4864.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03237, over 971192.14 frames.], batch size: 22, lr: 1.97e-04
+2022-05-07 03:26:14,334 INFO [train.py:715] (3/8) Epoch 11, batch 14100, loss[loss=0.1527, simple_loss=0.2301, pruned_loss=0.03769, over 4749.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03238, over 971725.40 frames.], batch size: 19, lr: 1.97e-04
+2022-05-07 03:26:53,603 INFO [train.py:715] (3/8) Epoch 11, batch 14150, loss[loss=0.115, simple_loss=0.1934, pruned_loss=0.01828, over 4861.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.03182, over 971903.15 frames.], batch size: 20, lr: 1.97e-04
+2022-05-07 03:27:32,868 INFO [train.py:715] (3/8) Epoch 11, batch 14200, loss[loss=0.1234, simple_loss=0.196, pruned_loss=0.02539, over 4762.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2117, pruned_loss=0.03197, over 971665.03 frames.], batch size: 18, lr: 1.97e-04
+2022-05-07 03:28:13,018 INFO [train.py:715] (3/8) Epoch 11, batch 14250, loss[loss=0.1165, simple_loss=0.1812, pruned_loss=0.02593, over 4754.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03189, over 971115.42 frames.], batch size: 12, lr: 1.97e-04
+2022-05-07 03:28:53,021 INFO [train.py:715] (3/8) Epoch 11, batch 14300, loss[loss=0.1655, simple_loss=0.2344, pruned_loss=0.04829, over 4959.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03214, over 971073.01 frames.], batch size: 15, lr: 1.97e-04
+2022-05-07 03:29:32,292 INFO [train.py:715] (3/8) Epoch 11, batch 14350, loss[loss=0.1608, simple_loss=0.2299, pruned_loss=0.04578, over 4939.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2123, pruned_loss=0.03249, over 971471.41 frames.], batch size: 23, lr: 1.97e-04
+2022-05-07 03:30:12,238 INFO [train.py:715] (3/8) Epoch 11, batch 14400, loss[loss=0.1551, simple_loss=0.2287, pruned_loss=0.04072, over 4746.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2124, pruned_loss=0.03259, over 972030.32 frames.], batch size: 16, lr: 1.97e-04
+2022-05-07 03:30:52,514 INFO [train.py:715] (3/8) Epoch 11, batch 14450, loss[loss=0.1593, simple_loss=0.2318, pruned_loss=0.04342, over 4780.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03273, over 971162.97 frames.], batch size: 14, lr: 1.97e-04
+2022-05-07 03:31:31,924 INFO [train.py:715] (3/8) Epoch 11, batch 14500, loss[loss=0.1428, simple_loss=0.2069, pruned_loss=0.03931, over 4689.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03285, over 969401.89 frames.], batch size: 15, lr: 1.97e-04
+2022-05-07 03:32:11,423 INFO [train.py:715] (3/8) Epoch 11, batch 14550, loss[loss=0.1434, simple_loss=0.2172, pruned_loss=0.03479, over 4985.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03234, over 970506.51 frames.], batch size: 28, lr: 1.97e-04
+2022-05-07 03:32:51,266 INFO [train.py:715] (3/8) Epoch 11, batch 14600, loss[loss=0.12, simple_loss=0.2061, pruned_loss=0.01701, over 4960.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2128, pruned_loss=0.03301, over 971102.30 frames.], batch size: 24, lr: 1.97e-04
+2022-05-07 03:33:30,641 INFO [train.py:715] (3/8) Epoch 11, batch 14650, loss[loss=0.1665, simple_loss=0.2369, pruned_loss=0.04806, over 4759.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2126, pruned_loss=0.03265, over 971388.30 frames.], batch size: 19, lr: 1.97e-04
+2022-05-07 03:34:09,053 INFO [train.py:715] (3/8) Epoch 11, batch 14700, loss[loss=0.1528, simple_loss=0.2337, pruned_loss=0.03599, over 4938.00 frames.], tot_loss[loss=0.1384, simple_loss=0.212, pruned_loss=0.03239, over 971356.29 frames.], batch size: 21, lr: 1.97e-04
+2022-05-07 03:34:48,549 INFO [train.py:715] (3/8) Epoch 11, batch 14750, loss[loss=0.1524, simple_loss=0.2252, pruned_loss=0.03982, over 4878.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03252, over 970289.99 frames.], batch size: 20, lr: 1.97e-04
+2022-05-07 03:35:27,679 INFO [train.py:715] (3/8) Epoch 11, batch 14800, loss[loss=0.1245, simple_loss=0.2027, pruned_loss=0.0232, over 4775.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03259, over 970511.12 frames.], batch size: 14, lr: 1.97e-04
+2022-05-07 03:36:06,361 INFO [train.py:715] (3/8) Epoch 11, batch 14850, loss[loss=0.1303, simple_loss=0.2096, pruned_loss=0.02551, over 4880.00 frames.], tot_loss[loss=0.1384, simple_loss=0.212, pruned_loss=0.03239, over 970361.13 frames.], batch size: 13, lr: 1.97e-04
+2022-05-07 03:36:45,863 INFO [train.py:715] (3/8) Epoch 11, batch 14900, loss[loss=0.1214, simple_loss=0.2005, pruned_loss=0.02113, over 4946.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2128, pruned_loss=0.03273, over 971286.02 frames.], batch size: 35, lr: 1.97e-04
+2022-05-07 03:37:25,091 INFO [train.py:715] (3/8) Epoch 11, batch 14950, loss[loss=0.1434, simple_loss=0.2117, pruned_loss=0.03757, over 4801.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2131, pruned_loss=0.03274, over 971775.45 frames.], batch size: 21, lr: 1.97e-04
+2022-05-07 03:38:03,588 INFO [train.py:715] (3/8) Epoch 11, batch 15000, loss[loss=0.1305, simple_loss=0.2018, pruned_loss=0.02962, over 4863.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2125, pruned_loss=0.03249, over 972184.32 frames.], batch size: 20, lr: 1.97e-04
+2022-05-07 03:38:03,589 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 03:38:13,229 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.106, simple_loss=0.1901, pruned_loss=0.01091, over 914524.00 frames.
+2022-05-07 03:38:52,000 INFO [train.py:715] (3/8) Epoch 11, batch 15050, loss[loss=0.1445, simple_loss=0.2236, pruned_loss=0.03268, over 4969.00 frames.], tot_loss[loss=0.139, simple_loss=0.2128, pruned_loss=0.03258, over 971791.03 frames.], batch size: 24, lr: 1.97e-04
+2022-05-07 03:39:30,961 INFO [train.py:715] (3/8) Epoch 11, batch 15100, loss[loss=0.1419, simple_loss=0.2251, pruned_loss=0.02934, over 4789.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2123, pruned_loss=0.0324, over 971966.97 frames.], batch size: 17, lr: 1.97e-04
+2022-05-07 03:40:10,672 INFO [train.py:715] (3/8) Epoch 11, batch 15150, loss[loss=0.1684, simple_loss=0.246, pruned_loss=0.04538, over 4882.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03294, over 972087.50 frames.], batch size: 16, lr: 1.97e-04
+2022-05-07 03:40:49,841 INFO [train.py:715] (3/8) Epoch 11, batch 15200, loss[loss=0.1274, simple_loss=0.2069, pruned_loss=0.02394, over 4984.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.03279, over 973014.33 frames.], batch size: 28, lr: 1.97e-04
+2022-05-07 03:41:28,409 INFO [train.py:715] (3/8) Epoch 11, batch 15250, loss[loss=0.1311, simple_loss=0.204, pruned_loss=0.02909, over 4883.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2128, pruned_loss=0.03321, over 973196.62 frames.], batch size: 32, lr: 1.97e-04
+2022-05-07 03:42:07,671 INFO [train.py:715] (3/8) Epoch 11, batch 15300, loss[loss=0.1383, simple_loss=0.2029, pruned_loss=0.03682, over 4823.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03339, over 973657.29 frames.], batch size: 12, lr: 1.97e-04
+2022-05-07 03:42:46,994 INFO [train.py:715] (3/8) Epoch 11, batch 15350, loss[loss=0.1565, simple_loss=0.2212, pruned_loss=0.04589, over 4811.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03366, over 973202.29 frames.], batch size: 13, lr: 1.96e-04
+2022-05-07 03:43:25,864 INFO [train.py:715] (3/8) Epoch 11, batch 15400, loss[loss=0.1374, simple_loss=0.2092, pruned_loss=0.03279, over 4963.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03361, over 973601.70 frames.], batch size: 24, lr: 1.96e-04
+2022-05-07 03:44:04,607 INFO [train.py:715] (3/8) Epoch 11, batch 15450, loss[loss=0.1075, simple_loss=0.1798, pruned_loss=0.01758, over 4853.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2118, pruned_loss=0.03327, over 972527.80 frames.], batch size: 20, lr: 1.96e-04
+2022-05-07 03:44:44,028 INFO [train.py:715] (3/8) Epoch 11, batch 15500, loss[loss=0.1844, simple_loss=0.2544, pruned_loss=0.05714, over 4894.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03344, over 972289.60 frames.], batch size: 39, lr: 1.96e-04
+2022-05-07 03:45:23,172 INFO [train.py:715] (3/8) Epoch 11, batch 15550, loss[loss=0.1315, simple_loss=0.2012, pruned_loss=0.03086, over 4960.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03338, over 972014.93 frames.], batch size: 24, lr: 1.96e-04
+2022-05-07 03:46:01,708 INFO [train.py:715] (3/8) Epoch 11, batch 15600, loss[loss=0.1799, simple_loss=0.2364, pruned_loss=0.06169, over 4961.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03353, over 972218.04 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 03:46:40,880 INFO [train.py:715] (3/8) Epoch 11, batch 15650, loss[loss=0.1279, simple_loss=0.2053, pruned_loss=0.02522, over 4703.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03294, over 971342.38 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 03:47:19,841 INFO [train.py:715] (3/8) Epoch 11, batch 15700, loss[loss=0.1155, simple_loss=0.1979, pruned_loss=0.0165, over 4849.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03277, over 972076.60 frames.], batch size: 20, lr: 1.96e-04
+2022-05-07 03:47:58,648 INFO [train.py:715] (3/8) Epoch 11, batch 15750, loss[loss=0.1219, simple_loss=0.2001, pruned_loss=0.02185, over 4826.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03257, over 972138.76 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 03:48:37,393 INFO [train.py:715] (3/8) Epoch 11, batch 15800, loss[loss=0.1488, simple_loss=0.2289, pruned_loss=0.03436, over 4870.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03257, over 971891.66 frames.], batch size: 20, lr: 1.96e-04
+2022-05-07 03:49:16,754 INFO [train.py:715] (3/8) Epoch 11, batch 15850, loss[loss=0.1412, simple_loss=0.2155, pruned_loss=0.03341, over 4933.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03245, over 971391.93 frames.], batch size: 23, lr: 1.96e-04
+2022-05-07 03:49:55,696 INFO [train.py:715] (3/8) Epoch 11, batch 15900, loss[loss=0.1135, simple_loss=0.1873, pruned_loss=0.01984, over 4855.00 frames.], tot_loss[loss=0.139, simple_loss=0.2123, pruned_loss=0.03287, over 971886.57 frames.], batch size: 20, lr: 1.96e-04
+2022-05-07 03:50:34,611 INFO [train.py:715] (3/8) Epoch 11, batch 15950, loss[loss=0.1131, simple_loss=0.1833, pruned_loss=0.02139, over 4957.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03306, over 971963.36 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 03:51:13,825 INFO [train.py:715] (3/8) Epoch 11, batch 16000, loss[loss=0.1466, simple_loss=0.2247, pruned_loss=0.03428, over 4779.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03307, over 971582.11 frames.], batch size: 17, lr: 1.96e-04
+2022-05-07 03:51:53,248 INFO [train.py:715] (3/8) Epoch 11, batch 16050, loss[loss=0.1308, simple_loss=0.2144, pruned_loss=0.0236, over 4979.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03267, over 971886.23 frames.], batch size: 24, lr: 1.96e-04
+2022-05-07 03:52:31,938 INFO [train.py:715] (3/8) Epoch 11, batch 16100, loss[loss=0.1253, simple_loss=0.1961, pruned_loss=0.02721, over 4947.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.0322, over 972464.87 frames.], batch size: 21, lr: 1.96e-04
+2022-05-07 03:53:10,815 INFO [train.py:715] (3/8) Epoch 11, batch 16150, loss[loss=0.1427, simple_loss=0.206, pruned_loss=0.0397, over 4829.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03258, over 972122.84 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 03:53:50,405 INFO [train.py:715] (3/8) Epoch 11, batch 16200, loss[loss=0.1419, simple_loss=0.2099, pruned_loss=0.03698, over 4813.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03249, over 971881.07 frames.], batch size: 25, lr: 1.96e-04
+2022-05-07 03:54:29,885 INFO [train.py:715] (3/8) Epoch 11, batch 16250, loss[loss=0.1206, simple_loss=0.1925, pruned_loss=0.02437, over 4812.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03296, over 972583.52 frames.], batch size: 27, lr: 1.96e-04
+2022-05-07 03:55:08,234 INFO [train.py:715] (3/8) Epoch 11, batch 16300, loss[loss=0.1439, simple_loss=0.2148, pruned_loss=0.03649, over 4793.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03256, over 973159.83 frames.], batch size: 14, lr: 1.96e-04
+2022-05-07 03:55:47,432 INFO [train.py:715] (3/8) Epoch 11, batch 16350, loss[loss=0.157, simple_loss=0.238, pruned_loss=0.03797, over 4933.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03212, over 972911.38 frames.], batch size: 23, lr: 1.96e-04
+2022-05-07 03:56:26,682 INFO [train.py:715] (3/8) Epoch 11, batch 16400, loss[loss=0.1379, simple_loss=0.2194, pruned_loss=0.02824, over 4805.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.0323, over 973382.62 frames.], batch size: 25, lr: 1.96e-04
+2022-05-07 03:57:05,178 INFO [train.py:715] (3/8) Epoch 11, batch 16450, loss[loss=0.1353, simple_loss=0.2139, pruned_loss=0.02835, over 4952.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03269, over 973458.72 frames.], batch size: 24, lr: 1.96e-04
+2022-05-07 03:57:44,150 INFO [train.py:715] (3/8) Epoch 11, batch 16500, loss[loss=0.1387, simple_loss=0.2148, pruned_loss=0.03123, over 4978.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03249, over 972464.31 frames.], batch size: 25, lr: 1.96e-04
+2022-05-07 03:58:23,676 INFO [train.py:715] (3/8) Epoch 11, batch 16550, loss[loss=0.1473, simple_loss=0.2118, pruned_loss=0.04139, over 4874.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03266, over 972089.79 frames.], batch size: 16, lr: 1.96e-04
+2022-05-07 03:59:02,827 INFO [train.py:715] (3/8) Epoch 11, batch 16600, loss[loss=0.1475, simple_loss=0.2192, pruned_loss=0.03788, over 4746.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.0331, over 971385.92 frames.], batch size: 16, lr: 1.96e-04
+2022-05-07 03:59:41,210 INFO [train.py:715] (3/8) Epoch 11, batch 16650, loss[loss=0.1607, simple_loss=0.2469, pruned_loss=0.03723, over 4935.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2109, pruned_loss=0.03259, over 971210.39 frames.], batch size: 23, lr: 1.96e-04
+2022-05-07 04:00:20,432 INFO [train.py:715] (3/8) Epoch 11, batch 16700, loss[loss=0.1154, simple_loss=0.1895, pruned_loss=0.02063, over 4975.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2105, pruned_loss=0.03245, over 970758.33 frames.], batch size: 35, lr: 1.96e-04
+2022-05-07 04:00:59,408 INFO [train.py:715] (3/8) Epoch 11, batch 16750, loss[loss=0.1039, simple_loss=0.1749, pruned_loss=0.01644, over 4822.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2111, pruned_loss=0.03251, over 971771.81 frames.], batch size: 12, lr: 1.96e-04
+2022-05-07 04:01:38,342 INFO [train.py:715] (3/8) Epoch 11, batch 16800, loss[loss=0.1044, simple_loss=0.1734, pruned_loss=0.01774, over 4793.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03285, over 972181.91 frames.], batch size: 12, lr: 1.96e-04
+2022-05-07 04:02:17,996 INFO [train.py:715] (3/8) Epoch 11, batch 16850, loss[loss=0.1088, simple_loss=0.1789, pruned_loss=0.01934, over 4792.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03298, over 972759.82 frames.], batch size: 14, lr: 1.96e-04
+2022-05-07 04:02:57,559 INFO [train.py:715] (3/8) Epoch 11, batch 16900, loss[loss=0.1324, simple_loss=0.1982, pruned_loss=0.03327, over 4836.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.0328, over 972997.58 frames.], batch size: 30, lr: 1.96e-04
+2022-05-07 04:03:37,028 INFO [train.py:715] (3/8) Epoch 11, batch 16950, loss[loss=0.1401, simple_loss=0.2145, pruned_loss=0.0328, over 4811.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03246, over 972440.33 frames.], batch size: 25, lr: 1.96e-04
+2022-05-07 04:04:15,766 INFO [train.py:715] (3/8) Epoch 11, batch 17000, loss[loss=0.1295, simple_loss=0.207, pruned_loss=0.02598, over 4963.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03278, over 972181.32 frames.], batch size: 24, lr: 1.96e-04
+2022-05-07 04:04:55,494 INFO [train.py:715] (3/8) Epoch 11, batch 17050, loss[loss=0.2, simple_loss=0.2682, pruned_loss=0.06591, over 4977.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03306, over 971518.21 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 04:05:38,133 INFO [train.py:715] (3/8) Epoch 11, batch 17100, loss[loss=0.1701, simple_loss=0.2489, pruned_loss=0.04566, over 4973.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2123, pruned_loss=0.03254, over 971831.54 frames.], batch size: 14, lr: 1.96e-04
+2022-05-07 04:06:17,134 INFO [train.py:715] (3/8) Epoch 11, batch 17150, loss[loss=0.1283, simple_loss=0.2022, pruned_loss=0.02718, over 4773.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2128, pruned_loss=0.03273, over 971681.89 frames.], batch size: 14, lr: 1.96e-04
+2022-05-07 04:06:56,396 INFO [train.py:715] (3/8) Epoch 11, batch 17200, loss[loss=0.1399, simple_loss=0.2189, pruned_loss=0.03048, over 4959.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2123, pruned_loss=0.03257, over 971817.64 frames.], batch size: 24, lr: 1.96e-04
+2022-05-07 04:07:35,863 INFO [train.py:715] (3/8) Epoch 11, batch 17250, loss[loss=0.139, simple_loss=0.2165, pruned_loss=0.03075, over 4781.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2114, pruned_loss=0.03202, over 971901.19 frames.], batch size: 17, lr: 1.96e-04
+2022-05-07 04:08:14,914 INFO [train.py:715] (3/8) Epoch 11, batch 17300, loss[loss=0.1461, simple_loss=0.2176, pruned_loss=0.03731, over 4779.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03219, over 971563.29 frames.], batch size: 14, lr: 1.96e-04
+2022-05-07 04:08:53,648 INFO [train.py:715] (3/8) Epoch 11, batch 17350, loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.0321, over 4796.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03243, over 971537.79 frames.], batch size: 21, lr: 1.96e-04
+2022-05-07 04:09:33,977 INFO [train.py:715] (3/8) Epoch 11, batch 17400, loss[loss=0.1169, simple_loss=0.1906, pruned_loss=0.02155, over 4941.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2128, pruned_loss=0.0328, over 972252.40 frames.], batch size: 29, lr: 1.96e-04
+2022-05-07 04:10:14,470 INFO [train.py:715] (3/8) Epoch 11, batch 17450, loss[loss=0.1309, simple_loss=0.1885, pruned_loss=0.03664, over 4851.00 frames.], tot_loss[loss=0.1396, simple_loss=0.213, pruned_loss=0.03308, over 972655.79 frames.], batch size: 13, lr: 1.96e-04
+2022-05-07 04:10:53,784 INFO [train.py:715] (3/8) Epoch 11, batch 17500, loss[loss=0.1522, simple_loss=0.237, pruned_loss=0.03365, over 4790.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2131, pruned_loss=0.03299, over 972831.61 frames.], batch size: 21, lr: 1.96e-04
+2022-05-07 04:11:33,221 INFO [train.py:715] (3/8) Epoch 11, batch 17550, loss[loss=0.1213, simple_loss=0.1989, pruned_loss=0.02187, over 4748.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.0329, over 972719.08 frames.], batch size: 16, lr: 1.96e-04
+2022-05-07 04:12:12,578 INFO [train.py:715] (3/8) Epoch 11, batch 17600, loss[loss=0.1441, simple_loss=0.2109, pruned_loss=0.03863, over 4856.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03271, over 972109.13 frames.], batch size: 34, lr: 1.96e-04
+2022-05-07 04:12:51,732 INFO [train.py:715] (3/8) Epoch 11, batch 17650, loss[loss=0.1379, simple_loss=0.2102, pruned_loss=0.03284, over 4835.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03246, over 972428.07 frames.], batch size: 13, lr: 1.96e-04
+2022-05-07 04:13:29,968 INFO [train.py:715] (3/8) Epoch 11, batch 17700, loss[loss=0.1743, simple_loss=0.2242, pruned_loss=0.06225, over 4851.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03245, over 972186.15 frames.], batch size: 32, lr: 1.96e-04
+2022-05-07 04:14:09,453 INFO [train.py:715] (3/8) Epoch 11, batch 17750, loss[loss=0.1495, simple_loss=0.2127, pruned_loss=0.04318, over 4979.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03248, over 972729.23 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 04:14:49,015 INFO [train.py:715] (3/8) Epoch 11, batch 17800, loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03404, over 4895.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03236, over 973423.44 frames.], batch size: 17, lr: 1.96e-04
+2022-05-07 04:15:27,265 INFO [train.py:715] (3/8) Epoch 11, batch 17850, loss[loss=0.1534, simple_loss=0.2199, pruned_loss=0.04339, over 4989.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.0325, over 972691.70 frames.], batch size: 25, lr: 1.96e-04
+2022-05-07 04:16:06,256 INFO [train.py:715] (3/8) Epoch 11, batch 17900, loss[loss=0.1437, simple_loss=0.215, pruned_loss=0.03618, over 4656.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03218, over 973174.72 frames.], batch size: 13, lr: 1.96e-04
+2022-05-07 04:16:45,880 INFO [train.py:715] (3/8) Epoch 11, batch 17950, loss[loss=0.1222, simple_loss=0.1879, pruned_loss=0.02819, over 4955.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03174, over 973413.47 frames.], batch size: 35, lr: 1.96e-04
+2022-05-07 04:17:24,870 INFO [train.py:715] (3/8) Epoch 11, batch 18000, loss[loss=0.1539, simple_loss=0.2385, pruned_loss=0.03461, over 4907.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03169, over 973214.26 frames.], batch size: 18, lr: 1.96e-04
+2022-05-07 04:17:24,871 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 04:17:34,461 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1903, pruned_loss=0.01092, over 914524.00 frames.
+2022-05-07 04:18:14,137 INFO [train.py:715] (3/8) Epoch 11, batch 18050, loss[loss=0.118, simple_loss=0.1914, pruned_loss=0.02229, over 4825.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03202, over 973811.39 frames.], batch size: 25, lr: 1.96e-04
+2022-05-07 04:18:53,409 INFO [train.py:715] (3/8) Epoch 11, batch 18100, loss[loss=0.1303, simple_loss=0.1974, pruned_loss=0.03157, over 4844.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03249, over 973934.18 frames.], batch size: 30, lr: 1.96e-04
+2022-05-07 04:19:32,617 INFO [train.py:715] (3/8) Epoch 11, batch 18150, loss[loss=0.1097, simple_loss=0.182, pruned_loss=0.01876, over 4932.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2116, pruned_loss=0.03286, over 973682.31 frames.], batch size: 21, lr: 1.96e-04
+2022-05-07 04:20:12,192 INFO [train.py:715] (3/8) Epoch 11, batch 18200, loss[loss=0.1545, simple_loss=0.2292, pruned_loss=0.03987, over 4842.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03288, over 972963.99 frames.], batch size: 30, lr: 1.96e-04
+2022-05-07 04:20:50,626 INFO [train.py:715] (3/8) Epoch 11, batch 18250, loss[loss=0.09847, simple_loss=0.1763, pruned_loss=0.01031, over 4984.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03262, over 973321.61 frames.], batch size: 14, lr: 1.96e-04
+2022-05-07 04:21:29,929 INFO [train.py:715] (3/8) Epoch 11, batch 18300, loss[loss=0.1262, simple_loss=0.1916, pruned_loss=0.03039, over 4885.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.03259, over 972737.24 frames.], batch size: 17, lr: 1.96e-04
+2022-05-07 04:22:09,172 INFO [train.py:715] (3/8) Epoch 11, batch 18350, loss[loss=0.1137, simple_loss=0.1865, pruned_loss=0.02041, over 4986.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03208, over 972056.83 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 04:22:47,572 INFO [train.py:715] (3/8) Epoch 11, batch 18400, loss[loss=0.1362, simple_loss=0.2077, pruned_loss=0.03232, over 4787.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03228, over 971301.45 frames.], batch size: 14, lr: 1.96e-04
+2022-05-07 04:23:25,986 INFO [train.py:715] (3/8) Epoch 11, batch 18450, loss[loss=0.1502, simple_loss=0.2276, pruned_loss=0.03636, over 4847.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2121, pruned_loss=0.03224, over 971006.30 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 04:24:05,022 INFO [train.py:715] (3/8) Epoch 11, batch 18500, loss[loss=0.1575, simple_loss=0.2327, pruned_loss=0.0412, over 4712.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2124, pruned_loss=0.03226, over 971778.85 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 04:24:44,460 INFO [train.py:715] (3/8) Epoch 11, batch 18550, loss[loss=0.126, simple_loss=0.1929, pruned_loss=0.02958, over 4823.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2128, pruned_loss=0.03249, over 972916.50 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 04:25:22,563 INFO [train.py:715] (3/8) Epoch 11, batch 18600, loss[loss=0.136, simple_loss=0.216, pruned_loss=0.02798, over 4932.00 frames.], tot_loss[loss=0.139, simple_loss=0.2127, pruned_loss=0.03262, over 972496.53 frames.], batch size: 21, lr: 1.96e-04
+2022-05-07 04:26:01,409 INFO [train.py:715] (3/8) Epoch 11, batch 18650, loss[loss=0.1396, simple_loss=0.215, pruned_loss=0.03212, over 4737.00 frames.], tot_loss[loss=0.139, simple_loss=0.2125, pruned_loss=0.03277, over 973059.73 frames.], batch size: 16, lr: 1.96e-04
+2022-05-07 04:26:40,666 INFO [train.py:715] (3/8) Epoch 11, batch 18700, loss[loss=0.1473, simple_loss=0.2266, pruned_loss=0.03401, over 4852.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2124, pruned_loss=0.03241, over 972856.46 frames.], batch size: 20, lr: 1.96e-04
+2022-05-07 04:27:18,909 INFO [train.py:715] (3/8) Epoch 11, batch 18750, loss[loss=0.1928, simple_loss=0.2608, pruned_loss=0.06242, over 4845.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03285, over 973089.19 frames.], batch size: 13, lr: 1.96e-04
+2022-05-07 04:27:57,976 INFO [train.py:715] (3/8) Epoch 11, batch 18800, loss[loss=0.1367, simple_loss=0.2156, pruned_loss=0.02888, over 4749.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03282, over 973253.97 frames.], batch size: 16, lr: 1.96e-04
+2022-05-07 04:28:36,590 INFO [train.py:715] (3/8) Epoch 11, batch 18850, loss[loss=0.1259, simple_loss=0.1996, pruned_loss=0.02607, over 4903.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2114, pruned_loss=0.03293, over 972922.86 frames.], batch size: 19, lr: 1.96e-04
+2022-05-07 04:29:16,483 INFO [train.py:715] (3/8) Epoch 11, batch 18900, loss[loss=0.1311, simple_loss=0.2092, pruned_loss=0.02651, over 4814.00 frames.], tot_loss[loss=0.1389, simple_loss=0.212, pruned_loss=0.03292, over 973340.39 frames.], batch size: 25, lr: 1.96e-04
+2022-05-07 04:29:55,265 INFO [train.py:715] (3/8) Epoch 11, batch 18950, loss[loss=0.1138, simple_loss=0.1887, pruned_loss=0.01948, over 4771.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03292, over 972762.70 frames.], batch size: 12, lr: 1.96e-04
+2022-05-07 04:30:34,363 INFO [train.py:715] (3/8) Epoch 11, batch 19000, loss[loss=0.1474, simple_loss=0.2271, pruned_loss=0.03385, over 4957.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.033, over 972483.65 frames.], batch size: 21, lr: 1.96e-04
+2022-05-07 04:31:13,457 INFO [train.py:715] (3/8) Epoch 11, batch 19050, loss[loss=0.1205, simple_loss=0.2008, pruned_loss=0.02008, over 4902.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03285, over 972562.84 frames.], batch size: 17, lr: 1.96e-04
+2022-05-07 04:31:52,053 INFO [train.py:715] (3/8) Epoch 11, batch 19100, loss[loss=0.1581, simple_loss=0.2234, pruned_loss=0.04645, over 4862.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.03315, over 973034.90 frames.], batch size: 30, lr: 1.96e-04
+2022-05-07 04:32:31,178 INFO [train.py:715] (3/8) Epoch 11, batch 19150, loss[loss=0.1317, simple_loss=0.2158, pruned_loss=0.02378, over 4759.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2112, pruned_loss=0.03301, over 971893.71 frames.], batch size: 19, lr: 1.96e-04
+2022-05-07 04:33:10,078 INFO [train.py:715] (3/8) Epoch 11, batch 19200, loss[loss=0.1325, simple_loss=0.2149, pruned_loss=0.02499, over 4892.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2104, pruned_loss=0.03303, over 971434.87 frames.], batch size: 19, lr: 1.96e-04
+2022-05-07 04:33:49,484 INFO [train.py:715] (3/8) Epoch 11, batch 19250, loss[loss=0.1304, simple_loss=0.2145, pruned_loss=0.0231, over 4698.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2108, pruned_loss=0.03314, over 971140.96 frames.], batch size: 15, lr: 1.96e-04
+2022-05-07 04:34:27,830 INFO [train.py:715] (3/8) Epoch 11, batch 19300, loss[loss=0.1456, simple_loss=0.2212, pruned_loss=0.03497, over 4942.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2114, pruned_loss=0.03315, over 970650.40 frames.], batch size: 23, lr: 1.96e-04
+2022-05-07 04:35:06,980 INFO [train.py:715] (3/8) Epoch 11, batch 19350, loss[loss=0.1319, simple_loss=0.2028, pruned_loss=0.03053, over 4959.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03287, over 970715.91 frames.], batch size: 14, lr: 1.96e-04
+2022-05-07 04:35:46,159 INFO [train.py:715] (3/8) Epoch 11, batch 19400, loss[loss=0.1451, simple_loss=0.2169, pruned_loss=0.03661, over 4845.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03299, over 971008.30 frames.], batch size: 34, lr: 1.96e-04
+2022-05-07 04:36:24,107 INFO [train.py:715] (3/8) Epoch 11, batch 19450, loss[loss=0.1451, simple_loss=0.2057, pruned_loss=0.04228, over 4784.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.0329, over 971329.71 frames.], batch size: 12, lr: 1.95e-04
+2022-05-07 04:37:03,252 INFO [train.py:715] (3/8) Epoch 11, batch 19500, loss[loss=0.1411, simple_loss=0.2174, pruned_loss=0.03237, over 4833.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.03288, over 971363.80 frames.], batch size: 26, lr: 1.95e-04
+2022-05-07 04:37:42,219 INFO [train.py:715] (3/8) Epoch 11, batch 19550, loss[loss=0.1658, simple_loss=0.2328, pruned_loss=0.04939, over 4888.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03335, over 971380.64 frames.], batch size: 19, lr: 1.95e-04
+2022-05-07 04:38:20,965 INFO [train.py:715] (3/8) Epoch 11, batch 19600, loss[loss=0.1685, simple_loss=0.2391, pruned_loss=0.04891, over 4826.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.03313, over 971435.98 frames.], batch size: 26, lr: 1.95e-04
+2022-05-07 04:38:59,545 INFO [train.py:715] (3/8) Epoch 11, batch 19650, loss[loss=0.1417, simple_loss=0.21, pruned_loss=0.03665, over 4986.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03292, over 971290.51 frames.], batch size: 15, lr: 1.95e-04
+2022-05-07 04:39:38,340 INFO [train.py:715] (3/8) Epoch 11, batch 19700, loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02912, over 4813.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03305, over 971221.24 frames.], batch size: 21, lr: 1.95e-04
+2022-05-07 04:40:17,420 INFO [train.py:715] (3/8) Epoch 11, batch 19750, loss[loss=0.1437, simple_loss=0.2184, pruned_loss=0.03457, over 4807.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2128, pruned_loss=0.03279, over 971243.50 frames.], batch size: 21, lr: 1.95e-04
+2022-05-07 04:40:55,508 INFO [train.py:715] (3/8) Epoch 11, batch 19800, loss[loss=0.1585, simple_loss=0.2289, pruned_loss=0.04406, over 4774.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2136, pruned_loss=0.03348, over 971790.33 frames.], batch size: 18, lr: 1.95e-04
+2022-05-07 04:41:35,007 INFO [train.py:715] (3/8) Epoch 11, batch 19850, loss[loss=0.1201, simple_loss=0.1968, pruned_loss=0.02169, over 4945.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03285, over 972590.47 frames.], batch size: 21, lr: 1.95e-04
+2022-05-07 04:42:14,373 INFO [train.py:715] (3/8) Epoch 11, batch 19900, loss[loss=0.1415, simple_loss=0.2104, pruned_loss=0.03631, over 4770.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2133, pruned_loss=0.03288, over 972159.85 frames.], batch size: 14, lr: 1.95e-04
+2022-05-07 04:42:53,604 INFO [train.py:715] (3/8) Epoch 11, batch 19950, loss[loss=0.1466, simple_loss=0.1969, pruned_loss=0.0482, over 4822.00 frames.], tot_loss[loss=0.1393, simple_loss=0.213, pruned_loss=0.03277, over 971970.16 frames.], batch size: 13, lr: 1.95e-04
+2022-05-07 04:43:32,802 INFO [train.py:715] (3/8) Epoch 11, batch 20000, loss[loss=0.118, simple_loss=0.1812, pruned_loss=0.02736, over 4987.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2123, pruned_loss=0.03268, over 972729.68 frames.], batch size: 28, lr: 1.95e-04
+2022-05-07 04:44:11,788 INFO [train.py:715] (3/8) Epoch 11, batch 20050, loss[loss=0.1443, simple_loss=0.2174, pruned_loss=0.03556, over 4690.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03269, over 972191.85 frames.], batch size: 15, lr: 1.95e-04
+2022-05-07 04:44:51,036 INFO [train.py:715] (3/8) Epoch 11, batch 20100, loss[loss=0.1649, simple_loss=0.2376, pruned_loss=0.04615, over 4903.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03244, over 972120.34 frames.], batch size: 22, lr: 1.95e-04
+2022-05-07 04:45:29,366 INFO [train.py:715] (3/8) Epoch 11, batch 20150, loss[loss=0.1416, simple_loss=0.2232, pruned_loss=0.03001, over 4927.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03198, over 971683.26 frames.], batch size: 23, lr: 1.95e-04
+2022-05-07 04:46:08,145 INFO [train.py:715] (3/8) Epoch 11, batch 20200, loss[loss=0.1374, simple_loss=0.2065, pruned_loss=0.03416, over 4967.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03255, over 972373.18 frames.], batch size: 15, lr: 1.95e-04
+2022-05-07 04:46:46,987 INFO [train.py:715] (3/8) Epoch 11, batch 20250, loss[loss=0.1301, simple_loss=0.2013, pruned_loss=0.02944, over 4839.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03264, over 973457.71 frames.], batch size: 30, lr: 1.95e-04
+2022-05-07 04:47:25,728 INFO [train.py:715] (3/8) Epoch 11, batch 20300, loss[loss=0.1413, simple_loss=0.2131, pruned_loss=0.03477, over 4850.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03241, over 972801.49 frames.], batch size: 32, lr: 1.95e-04
+2022-05-07 04:48:04,828 INFO [train.py:715] (3/8) Epoch 11, batch 20350, loss[loss=0.1171, simple_loss=0.1945, pruned_loss=0.01989, over 4832.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03296, over 972285.14 frames.], batch size: 13, lr: 1.95e-04
+2022-05-07 04:48:43,797 INFO [train.py:715] (3/8) Epoch 11, batch 20400, loss[loss=0.1676, simple_loss=0.2359, pruned_loss=0.0497, over 4983.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03307, over 972829.26 frames.], batch size: 31, lr: 1.95e-04
+2022-05-07 04:49:23,229 INFO [train.py:715] (3/8) Epoch 11, batch 20450, loss[loss=0.1516, simple_loss=0.2181, pruned_loss=0.04258, over 4689.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03277, over 972065.37 frames.], batch size: 15, lr: 1.95e-04
+2022-05-07 04:50:01,759 INFO [train.py:715] (3/8) Epoch 11, batch 20500, loss[loss=0.1462, simple_loss=0.2207, pruned_loss=0.03588, over 4920.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03348, over 972900.91 frames.], batch size: 23, lr: 1.95e-04
+2022-05-07 04:50:41,083 INFO [train.py:715] (3/8) Epoch 11, batch 20550, loss[loss=0.1265, simple_loss=0.2006, pruned_loss=0.02615, over 4940.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03372, over 972954.34 frames.], batch size: 21, lr: 1.95e-04
+2022-05-07 04:51:19,713 INFO [train.py:715] (3/8) Epoch 11, batch 20600, loss[loss=0.126, simple_loss=0.1976, pruned_loss=0.02719, over 4791.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.0336, over 973127.67 frames.], batch size: 18, lr: 1.95e-04
+2022-05-07 04:51:57,489 INFO [train.py:715] (3/8) Epoch 11, batch 20650, loss[loss=0.1861, simple_loss=0.2412, pruned_loss=0.06554, over 4906.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2138, pruned_loss=0.03386, over 972485.29 frames.], batch size: 19, lr: 1.95e-04
+2022-05-07 04:52:36,868 INFO [train.py:715] (3/8) Epoch 11, batch 20700, loss[loss=0.1417, simple_loss=0.2077, pruned_loss=0.03787, over 4820.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.0327, over 972047.95 frames.], batch size: 27, lr: 1.95e-04
+2022-05-07 04:53:16,101 INFO [train.py:715] (3/8) Epoch 11, batch 20750, loss[loss=0.1521, simple_loss=0.2239, pruned_loss=0.04015, over 4929.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03226, over 972701.76 frames.], batch size: 18, lr: 1.95e-04
+2022-05-07 04:53:54,803 INFO [train.py:715] (3/8) Epoch 11, batch 20800, loss[loss=0.1349, simple_loss=0.2119, pruned_loss=0.029, over 4752.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03187, over 972775.12 frames.], batch size: 19, lr: 1.95e-04
+2022-05-07 04:54:33,170 INFO [train.py:715] (3/8) Epoch 11, batch 20850, loss[loss=0.1248, simple_loss=0.203, pruned_loss=0.02333, over 4935.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03183, over 973387.54 frames.], batch size: 23, lr: 1.95e-04
+2022-05-07 04:55:12,420 INFO [train.py:715] (3/8) Epoch 11, batch 20900, loss[loss=0.1448, simple_loss=0.2247, pruned_loss=0.03248, over 4788.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03179, over 973205.40 frames.], batch size: 18, lr: 1.95e-04
+2022-05-07 04:55:52,029 INFO [train.py:715] (3/8) Epoch 11, batch 20950, loss[loss=0.1828, simple_loss=0.2361, pruned_loss=0.06477, over 4858.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03191, over 973147.15 frames.], batch size: 32, lr: 1.95e-04
+2022-05-07 04:56:30,996 INFO [train.py:715] (3/8) Epoch 11, batch 21000, loss[loss=0.1311, simple_loss=0.2114, pruned_loss=0.02535, over 4938.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03171, over 973486.19 frames.], batch size: 18, lr: 1.95e-04
+2022-05-07 04:56:30,996 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 04:56:40,630 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.106, simple_loss=0.19, pruned_loss=0.01097, over 914524.00 frames.
+2022-05-07 04:57:20,095 INFO [train.py:715] (3/8) Epoch 11, batch 21050, loss[loss=0.1574, simple_loss=0.2321, pruned_loss=0.04133, over 4837.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.03148, over 974293.89 frames.], batch size: 13, lr: 1.95e-04
+2022-05-07 04:57:59,831 INFO [train.py:715] (3/8) Epoch 11, batch 21100, loss[loss=0.1064, simple_loss=0.1837, pruned_loss=0.01456, over 4816.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03151, over 974127.53 frames.], batch size: 26, lr: 1.95e-04
+2022-05-07 04:58:38,863 INFO [train.py:715] (3/8) Epoch 11, batch 21150, loss[loss=0.1308, simple_loss=0.2174, pruned_loss=0.02212, over 4921.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03156, over 972404.93 frames.], batch size: 23, lr: 1.95e-04
+2022-05-07 04:59:18,202 INFO [train.py:715] (3/8) Epoch 11, batch 21200, loss[loss=0.1346, simple_loss=0.2055, pruned_loss=0.03183, over 4844.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03161, over 973353.52 frames.], batch size: 34, lr: 1.95e-04
+2022-05-07 04:59:56,327 INFO [train.py:715] (3/8) Epoch 11, batch 21250, loss[loss=0.1182, simple_loss=0.1986, pruned_loss=0.01889, over 4895.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03189, over 973149.53 frames.], batch size: 22, lr: 1.95e-04
+2022-05-07 05:00:35,639 INFO [train.py:715] (3/8) Epoch 11, batch 21300, loss[loss=0.143, simple_loss=0.2122, pruned_loss=0.03691, over 4800.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03184, over 972594.84 frames.], batch size: 21, lr: 1.95e-04
+2022-05-07 05:01:15,027 INFO [train.py:715] (3/8) Epoch 11, batch 21350, loss[loss=0.1332, simple_loss=0.2159, pruned_loss=0.02522, over 4882.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.03205, over 973294.58 frames.], batch size: 16, lr: 1.95e-04
+2022-05-07 05:01:53,537 INFO [train.py:715] (3/8) Epoch 11, batch 21400, loss[loss=0.1293, simple_loss=0.2077, pruned_loss=0.02541, over 4860.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.03172, over 973178.32 frames.], batch size: 20, lr: 1.95e-04
+2022-05-07 05:02:32,178 INFO [train.py:715] (3/8) Epoch 11, batch 21450, loss[loss=0.1226, simple_loss=0.1984, pruned_loss=0.02338, over 4792.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03212, over 972537.56 frames.], batch size: 21, lr: 1.95e-04
+2022-05-07 05:03:11,028 INFO [train.py:715] (3/8) Epoch 11, batch 21500, loss[loss=0.1372, simple_loss=0.2056, pruned_loss=0.03441, over 4851.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03249, over 971685.61 frames.], batch size: 32, lr: 1.95e-04
+2022-05-07 05:03:50,386 INFO [train.py:715] (3/8) Epoch 11, batch 21550, loss[loss=0.1246, simple_loss=0.1902, pruned_loss=0.02948, over 4834.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.03189, over 970976.32 frames.], batch size: 13, lr: 1.95e-04
+2022-05-07 05:04:28,680 INFO [train.py:715] (3/8) Epoch 11, batch 21600, loss[loss=0.1538, simple_loss=0.2293, pruned_loss=0.03912, over 4835.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03243, over 971793.59 frames.], batch size: 15, lr: 1.95e-04
+2022-05-07 05:05:07,529 INFO [train.py:715] (3/8) Epoch 11, batch 21650, loss[loss=0.1276, simple_loss=0.2151, pruned_loss=0.02005, over 4812.00 frames.], tot_loss[loss=0.1382, simple_loss=0.211, pruned_loss=0.03267, over 972100.05 frames.], batch size: 25, lr: 1.95e-04
+2022-05-07 05:05:47,578 INFO [train.py:715] (3/8) Epoch 11, batch 21700, loss[loss=0.1197, simple_loss=0.1947, pruned_loss=0.02236, over 4859.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.0324, over 972179.91 frames.], batch size: 38, lr: 1.95e-04
+2022-05-07 05:06:26,871 INFO [train.py:715] (3/8) Epoch 11, batch 21750, loss[loss=0.1344, simple_loss=0.2228, pruned_loss=0.02294, over 4936.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03262, over 971801.84 frames.], batch size: 29, lr: 1.95e-04
+2022-05-07 05:07:07,061 INFO [train.py:715] (3/8) Epoch 11, batch 21800, loss[loss=0.1185, simple_loss=0.2018, pruned_loss=0.01762, over 4916.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03213, over 972193.93 frames.], batch size: 18, lr: 1.95e-04
+2022-05-07 05:07:46,734 INFO [train.py:715] (3/8) Epoch 11, batch 21850, loss[loss=0.1988, simple_loss=0.2537, pruned_loss=0.0719, over 4871.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03211, over 972341.28 frames.], batch size: 16, lr: 1.95e-04
+2022-05-07 05:08:27,225 INFO [train.py:715] (3/8) Epoch 11, batch 21900, loss[loss=0.1751, simple_loss=0.243, pruned_loss=0.05358, over 4918.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03239, over 972545.11 frames.], batch size: 18, lr: 1.95e-04
+2022-05-07 05:09:06,442 INFO [train.py:715] (3/8) Epoch 11, batch 21950, loss[loss=0.1394, simple_loss=0.2073, pruned_loss=0.03571, over 4799.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03208, over 971866.70 frames.], batch size: 14, lr: 1.95e-04
+2022-05-07 05:09:46,763 INFO [train.py:715] (3/8) Epoch 11, batch 22000, loss[loss=0.1662, simple_loss=0.2281, pruned_loss=0.05217, over 4852.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03229, over 972296.73 frames.], batch size: 30, lr: 1.95e-04
+2022-05-07 05:10:27,231 INFO [train.py:715] (3/8) Epoch 11, batch 22050, loss[loss=0.1806, simple_loss=0.2392, pruned_loss=0.06099, over 4779.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03243, over 971730.86 frames.], batch size: 12, lr: 1.95e-04
+2022-05-07 05:11:05,501 INFO [train.py:715] (3/8) Epoch 11, batch 22100, loss[loss=0.1164, simple_loss=0.1987, pruned_loss=0.01701, over 4804.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2121, pruned_loss=0.03222, over 971090.76 frames.], batch size: 21, lr: 1.95e-04
+2022-05-07 05:11:45,099 INFO [train.py:715] (3/8) Epoch 11, batch 22150, loss[loss=0.1609, simple_loss=0.2346, pruned_loss=0.04362, over 4756.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2129, pruned_loss=0.03248, over 971014.34 frames.], batch size: 16, lr: 1.95e-04
+2022-05-07 05:12:24,690 INFO [train.py:715] (3/8) Epoch 11, batch 22200, loss[loss=0.151, simple_loss=0.2206, pruned_loss=0.04065, over 4768.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2134, pruned_loss=0.03289, over 970941.20 frames.], batch size: 14, lr: 1.95e-04
+2022-05-07 05:13:03,456 INFO [train.py:715] (3/8) Epoch 11, batch 22250, loss[loss=0.1413, simple_loss=0.2271, pruned_loss=0.02779, over 4847.00 frames.], tot_loss[loss=0.1392, simple_loss=0.213, pruned_loss=0.03265, over 970064.12 frames.], batch size: 25, lr: 1.95e-04
+2022-05-07 05:13:41,887 INFO [train.py:715] (3/8) Epoch 11, batch 22300, loss[loss=0.1256, simple_loss=0.197, pruned_loss=0.02713, over 4929.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2131, pruned_loss=0.03269, over 970249.89 frames.], batch size: 24, lr: 1.95e-04
+2022-05-07 05:14:21,104 INFO [train.py:715] (3/8) Epoch 11, batch 22350, loss[loss=0.1493, simple_loss=0.2225, pruned_loss=0.03808, over 4691.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2123, pruned_loss=0.03249, over 970550.34 frames.], batch size: 15, lr: 1.95e-04
+2022-05-07 05:15:00,558 INFO [train.py:715] (3/8) Epoch 11, batch 22400, loss[loss=0.171, simple_loss=0.2363, pruned_loss=0.05287, over 4653.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03235, over 970454.27 frames.], batch size: 13, lr: 1.95e-04
+2022-05-07 05:15:38,491 INFO [train.py:715] (3/8) Epoch 11, batch 22450, loss[loss=0.1104, simple_loss=0.1859, pruned_loss=0.01743, over 4932.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03216, over 971176.44 frames.], batch size: 23, lr: 1.95e-04
+2022-05-07 05:16:18,415 INFO [train.py:715] (3/8) Epoch 11, batch 22500, loss[loss=0.1653, simple_loss=0.2287, pruned_loss=0.0509, over 4851.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03287, over 970989.15 frames.], batch size: 30, lr: 1.95e-04
+2022-05-07 05:16:57,487 INFO [train.py:715] (3/8) Epoch 11, batch 22550, loss[loss=0.1457, simple_loss=0.214, pruned_loss=0.03867, over 4824.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.0325, over 971164.03 frames.], batch size: 15, lr: 1.95e-04
+2022-05-07 05:17:36,657 INFO [train.py:715] (3/8) Epoch 11, batch 22600, loss[loss=0.1342, simple_loss=0.2007, pruned_loss=0.03386, over 4817.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2115, pruned_loss=0.03281, over 971429.07 frames.], batch size: 12, lr: 1.95e-04
+2022-05-07 05:18:15,029 INFO [train.py:715] (3/8) Epoch 11, batch 22650, loss[loss=0.14, simple_loss=0.2287, pruned_loss=0.02563, over 4962.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.0331, over 971142.43 frames.], batch size: 23, lr: 1.95e-04
+2022-05-07 05:18:54,214 INFO [train.py:715] (3/8) Epoch 11, batch 22700, loss[loss=0.1394, simple_loss=0.2093, pruned_loss=0.0348, over 4787.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03268, over 972430.18 frames.], batch size: 24, lr: 1.95e-04
+2022-05-07 05:19:34,077 INFO [train.py:715] (3/8) Epoch 11, batch 22750, loss[loss=0.1254, simple_loss=0.2033, pruned_loss=0.02376, over 4990.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03334, over 972306.76 frames.], batch size: 25, lr: 1.95e-04
+2022-05-07 05:20:12,497 INFO [train.py:715] (3/8) Epoch 11, batch 22800, loss[loss=0.1428, simple_loss=0.2244, pruned_loss=0.03056, over 4843.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2135, pruned_loss=0.03344, over 971549.54 frames.], batch size: 15, lr: 1.95e-04
+2022-05-07 05:20:52,295 INFO [train.py:715] (3/8) Epoch 11, batch 22850, loss[loss=0.1412, simple_loss=0.2083, pruned_loss=0.03704, over 4785.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03344, over 972062.56 frames.], batch size: 17, lr: 1.95e-04
+2022-05-07 05:21:31,221 INFO [train.py:715] (3/8) Epoch 11, batch 22900, loss[loss=0.1359, simple_loss=0.2171, pruned_loss=0.02738, over 4918.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2135, pruned_loss=0.03335, over 972196.36 frames.], batch size: 23, lr: 1.95e-04
+2022-05-07 05:22:10,211 INFO [train.py:715] (3/8) Epoch 11, batch 22950, loss[loss=0.1441, simple_loss=0.2109, pruned_loss=0.03866, over 4893.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03281, over 970779.81 frames.], batch size: 19, lr: 1.95e-04
+2022-05-07 05:22:48,360 INFO [train.py:715] (3/8) Epoch 11, batch 23000, loss[loss=0.1357, simple_loss=0.2135, pruned_loss=0.02891, over 4874.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2126, pruned_loss=0.03311, over 971898.25 frames.], batch size: 16, lr: 1.95e-04
+2022-05-07 05:23:27,329 INFO [train.py:715] (3/8) Epoch 11, batch 23050, loss[loss=0.137, simple_loss=0.2221, pruned_loss=0.02594, over 4923.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03298, over 972057.22 frames.], batch size: 17, lr: 1.95e-04
+2022-05-07 05:24:06,662 INFO [train.py:715] (3/8) Epoch 11, batch 23100, loss[loss=0.1342, simple_loss=0.2048, pruned_loss=0.03179, over 4845.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.03331, over 972588.51 frames.], batch size: 15, lr: 1.95e-04
+2022-05-07 05:24:44,409 INFO [train.py:715] (3/8) Epoch 11, batch 23150, loss[loss=0.1863, simple_loss=0.2445, pruned_loss=0.06407, over 4840.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.0335, over 972444.31 frames.], batch size: 32, lr: 1.95e-04
+2022-05-07 05:25:23,977 INFO [train.py:715] (3/8) Epoch 11, batch 23200, loss[loss=0.1276, simple_loss=0.1977, pruned_loss=0.02874, over 4708.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2121, pruned_loss=0.0336, over 971531.25 frames.], batch size: 15, lr: 1.95e-04
+2022-05-07 05:26:02,908 INFO [train.py:715] (3/8) Epoch 11, batch 23250, loss[loss=0.1399, simple_loss=0.2093, pruned_loss=0.03532, over 4867.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.03262, over 971038.59 frames.], batch size: 22, lr: 1.95e-04
+2022-05-07 05:26:41,984 INFO [train.py:715] (3/8) Epoch 11, batch 23300, loss[loss=0.1413, simple_loss=0.2098, pruned_loss=0.03641, over 4824.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2106, pruned_loss=0.03233, over 971061.34 frames.], batch size: 13, lr: 1.95e-04
+2022-05-07 05:27:20,072 INFO [train.py:715] (3/8) Epoch 11, batch 23350, loss[loss=0.138, simple_loss=0.2067, pruned_loss=0.03467, over 4982.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2113, pruned_loss=0.03282, over 971387.87 frames.], batch size: 31, lr: 1.95e-04
+2022-05-07 05:27:59,122 INFO [train.py:715] (3/8) Epoch 11, batch 23400, loss[loss=0.1611, simple_loss=0.2254, pruned_loss=0.04841, over 4885.00 frames.], tot_loss[loss=0.139, simple_loss=0.2114, pruned_loss=0.03327, over 972246.23 frames.], batch size: 39, lr: 1.95e-04
+2022-05-07 05:28:38,745 INFO [train.py:715] (3/8) Epoch 11, batch 23450, loss[loss=0.1359, simple_loss=0.207, pruned_loss=0.03235, over 4976.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03351, over 972247.84 frames.], batch size: 25, lr: 1.95e-04
+2022-05-07 05:29:16,868 INFO [train.py:715] (3/8) Epoch 11, batch 23500, loss[loss=0.1305, simple_loss=0.1978, pruned_loss=0.03156, over 4807.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.03342, over 971959.58 frames.], batch size: 21, lr: 1.95e-04
+2022-05-07 05:29:55,785 INFO [train.py:715] (3/8) Epoch 11, batch 23550, loss[loss=0.1336, simple_loss=0.2082, pruned_loss=0.02947, over 4801.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03271, over 971435.60 frames.], batch size: 25, lr: 1.95e-04
+2022-05-07 05:30:34,766 INFO [train.py:715] (3/8) Epoch 11, batch 23600, loss[loss=0.1212, simple_loss=0.1959, pruned_loss=0.02323, over 4901.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03272, over 971580.67 frames.], batch size: 19, lr: 1.94e-04
+2022-05-07 05:31:14,124 INFO [train.py:715] (3/8) Epoch 11, batch 23650, loss[loss=0.1283, simple_loss=0.2007, pruned_loss=0.02797, over 4987.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03285, over 971603.43 frames.], batch size: 15, lr: 1.94e-04
+2022-05-07 05:31:51,831 INFO [train.py:715] (3/8) Epoch 11, batch 23700, loss[loss=0.1408, simple_loss=0.2141, pruned_loss=0.03378, over 4831.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03273, over 972222.11 frames.], batch size: 15, lr: 1.94e-04
+2022-05-07 05:32:30,819 INFO [train.py:715] (3/8) Epoch 11, batch 23750, loss[loss=0.1537, simple_loss=0.2298, pruned_loss=0.03879, over 4854.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2122, pruned_loss=0.03258, over 972291.87 frames.], batch size: 15, lr: 1.94e-04
+2022-05-07 05:33:09,310 INFO [train.py:715] (3/8) Epoch 11, batch 23800, loss[loss=0.1619, simple_loss=0.2347, pruned_loss=0.04452, over 4690.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03241, over 972480.63 frames.], batch size: 15, lr: 1.94e-04
+2022-05-07 05:33:46,739 INFO [train.py:715] (3/8) Epoch 11, batch 23850, loss[loss=0.1411, simple_loss=0.2164, pruned_loss=0.03289, over 4894.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03233, over 971714.96 frames.], batch size: 17, lr: 1.94e-04
+2022-05-07 05:34:24,312 INFO [train.py:715] (3/8) Epoch 11, batch 23900, loss[loss=0.1641, simple_loss=0.2265, pruned_loss=0.05083, over 4920.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03239, over 972361.58 frames.], batch size: 17, lr: 1.94e-04
+2022-05-07 05:35:01,656 INFO [train.py:715] (3/8) Epoch 11, batch 23950, loss[loss=0.1359, simple_loss=0.2067, pruned_loss=0.03257, over 4839.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03248, over 972203.32 frames.], batch size: 15, lr: 1.94e-04
+2022-05-07 05:35:39,343 INFO [train.py:715] (3/8) Epoch 11, batch 24000, loss[loss=0.143, simple_loss=0.2173, pruned_loss=0.03438, over 4847.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03257, over 971448.33 frames.], batch size: 32, lr: 1.94e-04
+2022-05-07 05:35:39,344 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 05:35:48,812 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.1059, simple_loss=0.19, pruned_loss=0.01092, over 914524.00 frames.
+2022-05-07 05:36:27,136 INFO [train.py:715] (3/8) Epoch 11, batch 24050, loss[loss=0.1541, simple_loss=0.224, pruned_loss=0.04205, over 4898.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03236, over 970987.56 frames.], batch size: 19, lr: 1.94e-04
+2022-05-07 05:37:04,267 INFO [train.py:715] (3/8) Epoch 11, batch 24100, loss[loss=0.13, simple_loss=0.2036, pruned_loss=0.02827, over 4847.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.0318, over 971498.16 frames.], batch size: 30, lr: 1.94e-04
+2022-05-07 05:37:42,096 INFO [train.py:715] (3/8) Epoch 11, batch 24150, loss[loss=0.1416, simple_loss=0.2129, pruned_loss=0.03517, over 4779.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03197, over 972076.19 frames.], batch size: 18, lr: 1.94e-04
+2022-05-07 05:38:20,368 INFO [train.py:715] (3/8) Epoch 11, batch 24200, loss[loss=0.1451, simple_loss=0.224, pruned_loss=0.03309, over 4873.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.03183, over 971589.83 frames.], batch size: 22, lr: 1.94e-04
+2022-05-07 05:38:57,453 INFO [train.py:715] (3/8) Epoch 11, batch 24250, loss[loss=0.1527, simple_loss=0.2285, pruned_loss=0.03848, over 4982.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.03152, over 971731.23 frames.], batch size: 28, lr: 1.94e-04
+2022-05-07 05:39:35,484 INFO [train.py:715] (3/8) Epoch 11, batch 24300, loss[loss=0.1489, simple_loss=0.2245, pruned_loss=0.03669, over 4828.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03161, over 971749.73 frames.], batch size: 15, lr: 1.94e-04
+2022-05-07 05:40:13,073 INFO [train.py:715] (3/8) Epoch 11, batch 24350, loss[loss=0.1605, simple_loss=0.2366, pruned_loss=0.04223, over 4944.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2116, pruned_loss=0.03184, over 972239.26 frames.], batch size: 21, lr: 1.94e-04
+2022-05-07 05:40:50,678 INFO [train.py:715] (3/8) Epoch 11, batch 24400, loss[loss=0.1269, simple_loss=0.201, pruned_loss=0.02638, over 4928.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2109, pruned_loss=0.0314, over 972380.87 frames.], batch size: 23, lr: 1.94e-04
+2022-05-07 05:41:28,273 INFO [train.py:715] (3/8) Epoch 11, batch 24450, loss[loss=0.1481, simple_loss=0.2358, pruned_loss=0.03022, over 4807.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2108, pruned_loss=0.03126, over 971332.20 frames.], batch size: 25, lr: 1.94e-04
+2022-05-07 05:42:06,387 INFO [train.py:715] (3/8) Epoch 11, batch 24500, loss[loss=0.1326, simple_loss=0.1934, pruned_loss=0.03594, over 4831.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03141, over 971243.16 frames.], batch size: 13, lr: 1.94e-04
+2022-05-07 05:42:45,028 INFO [train.py:715] (3/8) Epoch 11, batch 24550, loss[loss=0.1703, simple_loss=0.2474, pruned_loss=0.04662, over 4972.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03164, over 971937.39 frames.], batch size: 15, lr: 1.94e-04
+2022-05-07 05:43:23,052 INFO [train.py:715] (3/8) Epoch 11, batch 24600, loss[loss=0.1399, simple_loss=0.2038, pruned_loss=0.03805, over 4765.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03194, over 971663.55 frames.], batch size: 16, lr: 1.94e-04
+2022-05-07 05:44:01,528 INFO [train.py:715] (3/8) Epoch 11, batch 24650, loss[loss=0.1428, simple_loss=0.2239, pruned_loss=0.03087, over 4978.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.0319, over 971276.23 frames.], batch size: 14, lr: 1.94e-04
+2022-05-07 05:44:39,863 INFO [train.py:715] (3/8) Epoch 11, batch 24700, loss[loss=0.126, simple_loss=0.2067, pruned_loss=0.02264, over 4938.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2118, pruned_loss=0.03218, over 971909.25 frames.], batch size: 29, lr: 1.94e-04
+2022-05-07 05:45:18,488 INFO [train.py:715] (3/8) Epoch 11, batch 24750, loss[loss=0.1177, simple_loss=0.2008, pruned_loss=0.0173, over 4791.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2118, pruned_loss=0.03221, over 971460.53 frames.], batch size: 17, lr: 1.94e-04
+2022-05-07 05:45:56,383 INFO [train.py:715] (3/8) Epoch 11, batch 24800, loss[loss=0.1301, simple_loss=0.1914, pruned_loss=0.03434, over 4861.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.032, over 971384.95 frames.], batch size: 13, lr: 1.94e-04
+2022-05-07 05:46:34,704 INFO [train.py:715] (3/8) Epoch 11, batch 24850, loss[loss=0.1376, simple_loss=0.214, pruned_loss=0.03066, over 4775.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03213, over 971895.20 frames.], batch size: 17, lr: 1.94e-04
+2022-05-07 05:47:13,630 INFO [train.py:715] (3/8) Epoch 11, batch 24900, loss[loss=0.1225, simple_loss=0.1953, pruned_loss=0.02484, over 4980.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03211, over 972032.74 frames.], batch size: 14, lr: 1.94e-04
+2022-05-07 05:47:51,694 INFO [train.py:715] (3/8) Epoch 11, batch 24950, loss[loss=0.1731, simple_loss=0.2489, pruned_loss=0.04861, over 4969.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03228, over 971885.25 frames.], batch size: 15, lr: 1.94e-04
+2022-05-07 05:48:30,023 INFO [train.py:715] (3/8) Epoch 11, batch 25000, loss[loss=0.157, simple_loss=0.2278, pruned_loss=0.04307, over 4950.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03244, over 972477.51 frames.], batch size: 39, lr: 1.94e-04
+2022-05-07 05:49:08,319 INFO [train.py:715] (3/8) Epoch 11, batch 25050, loss[loss=0.134, simple_loss=0.2106, pruned_loss=0.02873, over 4835.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03211, over 971451.31 frames.], batch size: 20, lr: 1.94e-04
+2022-05-07 05:49:49,679 INFO [train.py:715] (3/8) Epoch 11, batch 25100, loss[loss=0.1358, simple_loss=0.2116, pruned_loss=0.02997, over 4785.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03187, over 971900.29 frames.], batch size: 18, lr: 1.94e-04
+2022-05-07 05:50:27,839 INFO [train.py:715] (3/8) Epoch 11, batch 25150, loss[loss=0.1493, simple_loss=0.2182, pruned_loss=0.0402, over 4988.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03174, over 972101.00 frames.], batch size: 25, lr: 1.94e-04
+2022-05-07 05:51:06,432 INFO [train.py:715] (3/8) Epoch 11, batch 25200, loss[loss=0.133, simple_loss=0.2094, pruned_loss=0.02832, over 4800.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03197, over 972163.08 frames.], batch size: 21, lr: 1.94e-04
+2022-05-07 05:51:45,285 INFO [train.py:715] (3/8) Epoch 11, batch 25250, loss[loss=0.1391, simple_loss=0.2178, pruned_loss=0.03019, over 4875.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03231, over 973024.52 frames.], batch size: 22, lr: 1.94e-04
+2022-05-07 05:52:23,561 INFO [train.py:715] (3/8) Epoch 11, batch 25300, loss[loss=0.1099, simple_loss=0.1861, pruned_loss=0.01684, over 4801.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03195, over 972696.31 frames.], batch size: 24, lr: 1.94e-04
+2022-05-07 05:53:01,962 INFO [train.py:715] (3/8) Epoch 11, batch 25350, loss[loss=0.1486, simple_loss=0.2254, pruned_loss=0.03586, over 4775.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2119, pruned_loss=0.03219, over 972509.93 frames.], batch size: 14, lr: 1.94e-04
+2022-05-07 05:53:40,601 INFO [train.py:715] (3/8) Epoch 11, batch 25400, loss[loss=0.124, simple_loss=0.1879, pruned_loss=0.03007, over 4862.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03252, over 973457.53 frames.], batch size: 13, lr: 1.94e-04
+2022-05-07 05:54:19,418 INFO [train.py:715] (3/8) Epoch 11, batch 25450, loss[loss=0.1597, simple_loss=0.2198, pruned_loss=0.04979, over 4856.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03273, over 972636.33 frames.], batch size: 30, lr: 1.94e-04
+2022-05-07 05:54:57,470 INFO [train.py:715] (3/8) Epoch 11, batch 25500, loss[loss=0.1523, simple_loss=0.2237, pruned_loss=0.04044, over 4941.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03291, over 972195.30 frames.], batch size: 21, lr: 1.94e-04
+2022-05-07 05:55:36,080 INFO [train.py:715] (3/8) Epoch 11, batch 25550, loss[loss=0.1342, simple_loss=0.2123, pruned_loss=0.02805, over 4809.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03281, over 972061.77 frames.], batch size: 21, lr: 1.94e-04
+2022-05-07 05:56:15,316 INFO [train.py:715] (3/8) Epoch 11, batch 25600, loss[loss=0.1079, simple_loss=0.1884, pruned_loss=0.0137, over 4866.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03246, over 971589.14 frames.], batch size: 20, lr: 1.94e-04
+2022-05-07 05:56:53,595 INFO [train.py:715] (3/8) Epoch 11, batch 25650, loss[loss=0.1424, simple_loss=0.205, pruned_loss=0.03989, over 4905.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2097, pruned_loss=0.03198, over 972448.97 frames.], batch size: 17, lr: 1.94e-04
+2022-05-07 05:57:31,750 INFO [train.py:715] (3/8) Epoch 11, batch 25700, loss[loss=0.1585, simple_loss=0.2211, pruned_loss=0.04798, over 4908.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.03261, over 972283.93 frames.], batch size: 39, lr: 1.94e-04
+2022-05-07 05:58:10,580 INFO [train.py:715] (3/8) Epoch 11, batch 25750, loss[loss=0.1229, simple_loss=0.1978, pruned_loss=0.02399, over 4808.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03244, over 973290.38 frames.], batch size: 25, lr: 1.94e-04
+2022-05-07 05:58:48,901 INFO [train.py:715] (3/8) Epoch 11, batch 25800, loss[loss=0.1515, simple_loss=0.2139, pruned_loss=0.04459, over 4957.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03249, over 973330.23 frames.], batch size: 14, lr: 1.94e-04
+2022-05-07 05:59:26,904 INFO [train.py:715] (3/8) Epoch 11, batch 25850, loss[loss=0.1263, simple_loss=0.1942, pruned_loss=0.02915, over 4879.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.0319, over 972997.28 frames.], batch size: 16, lr: 1.94e-04
+2022-05-07 06:00:05,562 INFO [train.py:715] (3/8) Epoch 11, batch 25900, loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04134, over 4783.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03208, over 972796.47 frames.], batch size: 18, lr: 1.94e-04
+2022-05-07 06:00:44,269 INFO [train.py:715] (3/8) Epoch 11, batch 25950, loss[loss=0.1127, simple_loss=0.1852, pruned_loss=0.02011, over 4813.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03196, over 972765.19 frames.], batch size: 27, lr: 1.94e-04
+2022-05-07 06:01:22,319 INFO [train.py:715] (3/8) Epoch 11, batch 26000, loss[loss=0.1142, simple_loss=0.1851, pruned_loss=0.02162, over 4799.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.033, over 971376.09 frames.], batch size: 24, lr: 1.94e-04
+2022-05-07 06:02:00,401 INFO [train.py:715] (3/8) Epoch 11, batch 26050, loss[loss=0.1278, simple_loss=0.1969, pruned_loss=0.02937, over 4827.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2116, pruned_loss=0.03335, over 971346.79 frames.], batch size: 13, lr: 1.94e-04
+2022-05-07 06:02:38,954 INFO [train.py:715] (3/8) Epoch 11, batch 26100, loss[loss=0.1344, simple_loss=0.2099, pruned_loss=0.02947, over 4773.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03329, over 971242.22 frames.], batch size: 19, lr: 1.94e-04
+2022-05-07 06:03:17,344 INFO [train.py:715] (3/8) Epoch 11, batch 26150, loss[loss=0.09402, simple_loss=0.1663, pruned_loss=0.01085, over 4814.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03282, over 972250.97 frames.], batch size: 12, lr: 1.94e-04
+2022-05-07 06:03:55,313 INFO [train.py:715] (3/8) Epoch 11, batch 26200, loss[loss=0.1421, simple_loss=0.2108, pruned_loss=0.03674, over 4898.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2108, pruned_loss=0.03263, over 972244.08 frames.], batch size: 19, lr: 1.94e-04
+2022-05-07 06:04:32,930 INFO [train.py:715] (3/8) Epoch 11, batch 26250, loss[loss=0.1363, simple_loss=0.2, pruned_loss=0.03629, over 4924.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2117, pruned_loss=0.03354, over 972429.97 frames.], batch size: 29, lr: 1.94e-04
+2022-05-07 06:05:10,977 INFO [train.py:715] (3/8) Epoch 11, batch 26300, loss[loss=0.1629, simple_loss=0.2409, pruned_loss=0.04243, over 4925.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.03301, over 972024.01 frames.], batch size: 18, lr: 1.94e-04
+2022-05-07 06:05:48,410 INFO [train.py:715] (3/8) Epoch 11, batch 26350, loss[loss=0.1872, simple_loss=0.2532, pruned_loss=0.06057, over 4902.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2112, pruned_loss=0.03292, over 971983.31 frames.], batch size: 17, lr: 1.94e-04
+2022-05-07 06:06:25,428 INFO [train.py:715] (3/8) Epoch 11, batch 26400, loss[loss=0.1577, simple_loss=0.2246, pruned_loss=0.04537, over 4774.00 frames.], tot_loss[loss=0.1394, simple_loss=0.212, pruned_loss=0.03341, over 972086.13 frames.], batch size: 18, lr: 1.94e-04
+2022-05-07 06:07:03,858 INFO [train.py:715] (3/8) Epoch 11, batch 26450, loss[loss=0.1537, simple_loss=0.2324, pruned_loss=0.03747, over 4970.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03367, over 972720.27 frames.], batch size: 24, lr: 1.94e-04
+2022-05-07 06:07:41,341 INFO [train.py:715] (3/8) Epoch 11, batch 26500, loss[loss=0.1427, simple_loss=0.2248, pruned_loss=0.03036, over 4885.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03338, over 972564.34 frames.], batch size: 19, lr: 1.94e-04
+2022-05-07 06:08:19,084 INFO [train.py:715] (3/8) Epoch 11, batch 26550, loss[loss=0.1351, simple_loss=0.2143, pruned_loss=0.02794, over 4778.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2129, pruned_loss=0.03311, over 971521.22 frames.], batch size: 14, lr: 1.94e-04
+2022-05-07 06:08:56,821 INFO [train.py:715] (3/8) Epoch 11, batch 26600, loss[loss=0.1624, simple_loss=0.2337, pruned_loss=0.04555, over 4961.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2136, pruned_loss=0.03331, over 972374.91 frames.], batch size: 21, lr: 1.94e-04
+2022-05-07 06:09:34,845 INFO [train.py:715] (3/8) Epoch 11, batch 26650, loss[loss=0.1567, simple_loss=0.2154, pruned_loss=0.04904, over 4822.00 frames.], tot_loss[loss=0.1396, simple_loss=0.213, pruned_loss=0.03304, over 972274.48 frames.], batch size: 15, lr: 1.94e-04
+2022-05-07 06:10:12,910 INFO [train.py:715] (3/8) Epoch 11, batch 26700, loss[loss=0.1327, simple_loss=0.2107, pruned_loss=0.02733, over 4919.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2121, pruned_loss=0.03233, over 972474.32 frames.], batch size: 39, lr: 1.94e-04
+2022-05-07 06:10:49,897 INFO [train.py:715] (3/8) Epoch 11, batch 26750, loss[loss=0.1261, simple_loss=0.2009, pruned_loss=0.02562, over 4934.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2122, pruned_loss=0.0323, over 972486.45 frames.], batch size: 29, lr: 1.94e-04
+2022-05-07 06:11:28,541 INFO [train.py:715] (3/8) Epoch 11, batch 26800, loss[loss=0.1129, simple_loss=0.1872, pruned_loss=0.01926, over 4795.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03244, over 972472.73 frames.], batch size: 18, lr: 1.94e-04
+2022-05-07 06:12:06,143 INFO [train.py:715] (3/8) Epoch 11, batch 26850, loss[loss=0.134, simple_loss=0.2263, pruned_loss=0.02086, over 4768.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2115, pruned_loss=0.03187, over 972657.76 frames.], batch size: 18, lr: 1.94e-04
+2022-05-07 06:12:43,631 INFO [train.py:715] (3/8) Epoch 11, batch 26900, loss[loss=0.1426, simple_loss=0.217, pruned_loss=0.03407, over 4982.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03206, over 974024.48 frames.], batch size: 31, lr: 1.94e-04
+2022-05-07 06:13:21,272 INFO [train.py:715] (3/8) Epoch 11, batch 26950, loss[loss=0.1413, simple_loss=0.2111, pruned_loss=0.03571, over 4839.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03194, over 973341.73 frames.], batch size: 30, lr: 1.94e-04
+2022-05-07 06:13:59,655 INFO [train.py:715] (3/8) Epoch 11, batch 27000, loss[loss=0.1264, simple_loss=0.1945, pruned_loss=0.02915, over 4952.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03263, over 973277.37 frames.], batch size: 21, lr: 1.94e-04
+2022-05-07 06:13:59,656 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 06:14:09,117 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.1059, simple_loss=0.19, pruned_loss=0.01084, over 914524.00 frames.
+2022-05-07 06:14:47,549 INFO [train.py:715] (3/8) Epoch 11, batch 27050, loss[loss=0.1149, simple_loss=0.1974, pruned_loss=0.01624, over 4955.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2107, pruned_loss=0.03222, over 973205.72 frames.], batch size: 21, lr: 1.94e-04
+2022-05-07 06:15:25,150 INFO [train.py:715] (3/8) Epoch 11, batch 27100, loss[loss=0.1507, simple_loss=0.2147, pruned_loss=0.04337, over 4879.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.0326, over 972848.12 frames.], batch size: 16, lr: 1.94e-04
+2022-05-07 06:16:02,383 INFO [train.py:715] (3/8) Epoch 11, batch 27150, loss[loss=0.1294, simple_loss=0.2019, pruned_loss=0.02845, over 4644.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2106, pruned_loss=0.03288, over 973043.03 frames.], batch size: 13, lr: 1.94e-04
+2022-05-07 06:16:41,020 INFO [train.py:715] (3/8) Epoch 11, batch 27200, loss[loss=0.1436, simple_loss=0.2141, pruned_loss=0.03656, over 4871.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2104, pruned_loss=0.03261, over 972694.07 frames.], batch size: 16, lr: 1.94e-04
+2022-05-07 06:17:18,730 INFO [train.py:715] (3/8) Epoch 11, batch 27250, loss[loss=0.1268, simple_loss=0.2088, pruned_loss=0.02239, over 4942.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.03193, over 972379.25 frames.], batch size: 21, lr: 1.94e-04
+2022-05-07 06:17:56,617 INFO [train.py:715] (3/8) Epoch 11, batch 27300, loss[loss=0.1496, simple_loss=0.2274, pruned_loss=0.03587, over 4801.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03211, over 972084.89 frames.], batch size: 25, lr: 1.94e-04
+2022-05-07 06:18:34,290 INFO [train.py:715] (3/8) Epoch 11, batch 27350, loss[loss=0.1226, simple_loss=0.2029, pruned_loss=0.02111, over 4988.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03193, over 972026.83 frames.], batch size: 20, lr: 1.94e-04
+2022-05-07 06:19:13,064 INFO [train.py:715] (3/8) Epoch 11, batch 27400, loss[loss=0.1462, simple_loss=0.2191, pruned_loss=0.03667, over 4856.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03228, over 973459.07 frames.], batch size: 20, lr: 1.94e-04
+2022-05-07 06:19:50,857 INFO [train.py:715] (3/8) Epoch 11, batch 27450, loss[loss=0.118, simple_loss=0.1922, pruned_loss=0.02191, over 4957.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2099, pruned_loss=0.03197, over 973390.43 frames.], batch size: 35, lr: 1.94e-04
+2022-05-07 06:20:28,121 INFO [train.py:715] (3/8) Epoch 11, batch 27500, loss[loss=0.1386, simple_loss=0.2086, pruned_loss=0.0343, over 4825.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03201, over 973893.44 frames.], batch size: 15, lr: 1.94e-04
+2022-05-07 06:21:07,286 INFO [train.py:715] (3/8) Epoch 11, batch 27550, loss[loss=0.1382, simple_loss=0.2104, pruned_loss=0.03303, over 4827.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03204, over 973634.22 frames.], batch size: 27, lr: 1.94e-04
+2022-05-07 06:21:45,753 INFO [train.py:715] (3/8) Epoch 11, batch 27600, loss[loss=0.1372, simple_loss=0.208, pruned_loss=0.03315, over 4909.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03278, over 973608.50 frames.], batch size: 18, lr: 1.94e-04
+2022-05-07 06:22:23,477 INFO [train.py:715] (3/8) Epoch 11, batch 27650, loss[loss=0.1058, simple_loss=0.1828, pruned_loss=0.01441, over 4853.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03268, over 972781.82 frames.], batch size: 20, lr: 1.94e-04
+2022-05-07 06:23:01,301 INFO [train.py:715] (3/8) Epoch 11, batch 27700, loss[loss=0.1189, simple_loss=0.1907, pruned_loss=0.02357, over 4893.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03219, over 972695.58 frames.], batch size: 17, lr: 1.94e-04
+2022-05-07 06:23:39,627 INFO [train.py:715] (3/8) Epoch 11, batch 27750, loss[loss=0.1572, simple_loss=0.2238, pruned_loss=0.04529, over 4786.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2107, pruned_loss=0.03225, over 972408.21 frames.], batch size: 17, lr: 1.94e-04
+2022-05-07 06:24:17,575 INFO [train.py:715] (3/8) Epoch 11, batch 27800, loss[loss=0.1275, simple_loss=0.2024, pruned_loss=0.02634, over 4989.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03216, over 972890.50 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 06:24:54,560 INFO [train.py:715] (3/8) Epoch 11, batch 27850, loss[loss=0.1751, simple_loss=0.23, pruned_loss=0.06014, over 4981.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03242, over 973083.84 frames.], batch size: 35, lr: 1.93e-04
+2022-05-07 06:25:32,919 INFO [train.py:715] (3/8) Epoch 11, batch 27900, loss[loss=0.1148, simple_loss=0.1879, pruned_loss=0.02083, over 4802.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2113, pruned_loss=0.03286, over 973443.37 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 06:26:10,975 INFO [train.py:715] (3/8) Epoch 11, batch 27950, loss[loss=0.1583, simple_loss=0.2312, pruned_loss=0.04274, over 4688.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2102, pruned_loss=0.03225, over 972999.86 frames.], batch size: 15, lr: 1.93e-04
+2022-05-07 06:26:48,584 INFO [train.py:715] (3/8) Epoch 11, batch 28000, loss[loss=0.1121, simple_loss=0.1879, pruned_loss=0.01813, over 4873.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2103, pruned_loss=0.03228, over 972883.85 frames.], batch size: 22, lr: 1.93e-04
+2022-05-07 06:27:26,141 INFO [train.py:715] (3/8) Epoch 11, batch 28050, loss[loss=0.1319, simple_loss=0.2096, pruned_loss=0.02709, over 4779.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03229, over 973539.67 frames.], batch size: 18, lr: 1.93e-04
+2022-05-07 06:28:04,143 INFO [train.py:715] (3/8) Epoch 11, batch 28100, loss[loss=0.1314, simple_loss=0.2052, pruned_loss=0.02885, over 4809.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.0324, over 973078.46 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 06:28:41,422 INFO [train.py:715] (3/8) Epoch 11, batch 28150, loss[loss=0.1466, simple_loss=0.2235, pruned_loss=0.03488, over 4946.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03223, over 972982.04 frames.], batch size: 21, lr: 1.93e-04
+2022-05-07 06:29:18,869 INFO [train.py:715] (3/8) Epoch 11, batch 28200, loss[loss=0.1363, simple_loss=0.2106, pruned_loss=0.03098, over 4784.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03211, over 972958.28 frames.], batch size: 17, lr: 1.93e-04
+2022-05-07 06:29:57,424 INFO [train.py:715] (3/8) Epoch 11, batch 28250, loss[loss=0.1306, simple_loss=0.2029, pruned_loss=0.02909, over 4844.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03234, over 973637.51 frames.], batch size: 15, lr: 1.93e-04
+2022-05-07 06:30:34,927 INFO [train.py:715] (3/8) Epoch 11, batch 28300, loss[loss=0.1381, simple_loss=0.2092, pruned_loss=0.03353, over 4893.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03228, over 973439.80 frames.], batch size: 22, lr: 1.93e-04
+2022-05-07 06:31:12,832 INFO [train.py:715] (3/8) Epoch 11, batch 28350, loss[loss=0.1558, simple_loss=0.2264, pruned_loss=0.04262, over 4800.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03271, over 973078.76 frames.], batch size: 24, lr: 1.93e-04
+2022-05-07 06:31:50,526 INFO [train.py:715] (3/8) Epoch 11, batch 28400, loss[loss=0.1434, simple_loss=0.2146, pruned_loss=0.0361, over 4853.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03277, over 972826.00 frames.], batch size: 32, lr: 1.93e-04
+2022-05-07 06:32:28,900 INFO [train.py:715] (3/8) Epoch 11, batch 28450, loss[loss=0.1281, simple_loss=0.2045, pruned_loss=0.02587, over 4910.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.03302, over 971383.38 frames.], batch size: 17, lr: 1.93e-04
+2022-05-07 06:33:06,938 INFO [train.py:715] (3/8) Epoch 11, batch 28500, loss[loss=0.1471, simple_loss=0.2226, pruned_loss=0.03579, over 4814.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.03356, over 971583.63 frames.], batch size: 21, lr: 1.93e-04
+2022-05-07 06:33:44,629 INFO [train.py:715] (3/8) Epoch 11, batch 28550, loss[loss=0.1248, simple_loss=0.1942, pruned_loss=0.02772, over 4951.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.0333, over 971781.84 frames.], batch size: 21, lr: 1.93e-04
+2022-05-07 06:34:23,469 INFO [train.py:715] (3/8) Epoch 11, batch 28600, loss[loss=0.174, simple_loss=0.2444, pruned_loss=0.0518, over 4898.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2134, pruned_loss=0.0334, over 971961.97 frames.], batch size: 19, lr: 1.93e-04
+2022-05-07 06:35:01,436 INFO [train.py:715] (3/8) Epoch 11, batch 28650, loss[loss=0.1284, simple_loss=0.1975, pruned_loss=0.02966, over 4974.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2133, pruned_loss=0.03309, over 972845.78 frames.], batch size: 31, lr: 1.93e-04
+2022-05-07 06:35:39,422 INFO [train.py:715] (3/8) Epoch 11, batch 28700, loss[loss=0.1433, simple_loss=0.2124, pruned_loss=0.03714, over 4751.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03288, over 972266.53 frames.], batch size: 16, lr: 1.93e-04
+2022-05-07 06:36:17,176 INFO [train.py:715] (3/8) Epoch 11, batch 28750, loss[loss=0.125, simple_loss=0.2069, pruned_loss=0.02153, over 4814.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03293, over 972663.85 frames.], batch size: 27, lr: 1.93e-04
+2022-05-07 06:36:55,925 INFO [train.py:715] (3/8) Epoch 11, batch 28800, loss[loss=0.1127, simple_loss=0.1894, pruned_loss=0.01804, over 4818.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03208, over 972110.04 frames.], batch size: 26, lr: 1.93e-04
+2022-05-07 06:37:33,392 INFO [train.py:715] (3/8) Epoch 11, batch 28850, loss[loss=0.1518, simple_loss=0.2339, pruned_loss=0.03485, over 4835.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03224, over 972142.33 frames.], batch size: 15, lr: 1.93e-04
+2022-05-07 06:38:10,807 INFO [train.py:715] (3/8) Epoch 11, batch 28900, loss[loss=0.1282, simple_loss=0.2014, pruned_loss=0.02748, over 4986.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03188, over 972478.91 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 06:38:49,569 INFO [train.py:715] (3/8) Epoch 11, batch 28950, loss[loss=0.1299, simple_loss=0.1989, pruned_loss=0.03045, over 4978.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03218, over 971853.02 frames.], batch size: 14, lr: 1.93e-04
+2022-05-07 06:39:27,039 INFO [train.py:715] (3/8) Epoch 11, batch 29000, loss[loss=0.1214, simple_loss=0.199, pruned_loss=0.02189, over 4987.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03193, over 973079.39 frames.], batch size: 28, lr: 1.93e-04
+2022-05-07 06:40:04,958 INFO [train.py:715] (3/8) Epoch 11, batch 29050, loss[loss=0.153, simple_loss=0.2311, pruned_loss=0.03746, over 4920.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03189, over 973822.38 frames.], batch size: 23, lr: 1.93e-04
+2022-05-07 06:40:42,751 INFO [train.py:715] (3/8) Epoch 11, batch 29100, loss[loss=0.1636, simple_loss=0.226, pruned_loss=0.05061, over 4984.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03224, over 973629.35 frames.], batch size: 35, lr: 1.93e-04
+2022-05-07 06:41:21,084 INFO [train.py:715] (3/8) Epoch 11, batch 29150, loss[loss=0.1347, simple_loss=0.216, pruned_loss=0.0267, over 4897.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03206, over 972052.23 frames.], batch size: 18, lr: 1.93e-04
+2022-05-07 06:41:58,820 INFO [train.py:715] (3/8) Epoch 11, batch 29200, loss[loss=0.1701, simple_loss=0.2473, pruned_loss=0.0465, over 4856.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03228, over 971936.27 frames.], batch size: 32, lr: 1.93e-04
+2022-05-07 06:42:36,370 INFO [train.py:715] (3/8) Epoch 11, batch 29250, loss[loss=0.133, simple_loss=0.2024, pruned_loss=0.03176, over 4817.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03222, over 972618.57 frames.], batch size: 13, lr: 1.93e-04
+2022-05-07 06:43:15,063 INFO [train.py:715] (3/8) Epoch 11, batch 29300, loss[loss=0.1119, simple_loss=0.1817, pruned_loss=0.021, over 4903.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03214, over 972624.06 frames.], batch size: 19, lr: 1.93e-04
+2022-05-07 06:43:53,137 INFO [train.py:715] (3/8) Epoch 11, batch 29350, loss[loss=0.1331, simple_loss=0.2149, pruned_loss=0.02565, over 4879.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03211, over 972979.73 frames.], batch size: 19, lr: 1.93e-04
+2022-05-07 06:44:30,901 INFO [train.py:715] (3/8) Epoch 11, batch 29400, loss[loss=0.1134, simple_loss=0.1939, pruned_loss=0.01641, over 4949.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03201, over 972332.07 frames.], batch size: 29, lr: 1.93e-04
+2022-05-07 06:45:08,812 INFO [train.py:715] (3/8) Epoch 11, batch 29450, loss[loss=0.189, simple_loss=0.2611, pruned_loss=0.05843, over 4991.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03223, over 973068.99 frames.], batch size: 16, lr: 1.93e-04
+2022-05-07 06:45:46,710 INFO [train.py:715] (3/8) Epoch 11, batch 29500, loss[loss=0.1282, simple_loss=0.2066, pruned_loss=0.02491, over 4945.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2115, pruned_loss=0.03218, over 972758.30 frames.], batch size: 24, lr: 1.93e-04
+2022-05-07 06:46:25,303 INFO [train.py:715] (3/8) Epoch 11, batch 29550, loss[loss=0.1307, simple_loss=0.204, pruned_loss=0.02871, over 4974.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03187, over 972280.37 frames.], batch size: 15, lr: 1.93e-04
+2022-05-07 06:47:02,904 INFO [train.py:715] (3/8) Epoch 11, batch 29600, loss[loss=0.1587, simple_loss=0.2161, pruned_loss=0.05062, over 4641.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03211, over 972317.86 frames.], batch size: 13, lr: 1.93e-04
+2022-05-07 06:47:41,474 INFO [train.py:715] (3/8) Epoch 11, batch 29650, loss[loss=0.1582, simple_loss=0.2216, pruned_loss=0.04738, over 4775.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03203, over 972405.48 frames.], batch size: 14, lr: 1.93e-04
+2022-05-07 06:48:19,465 INFO [train.py:715] (3/8) Epoch 11, batch 29700, loss[loss=0.1042, simple_loss=0.1708, pruned_loss=0.01875, over 4765.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03156, over 972731.90 frames.], batch size: 18, lr: 1.93e-04
+2022-05-07 06:48:57,625 INFO [train.py:715] (3/8) Epoch 11, batch 29750, loss[loss=0.1304, simple_loss=0.205, pruned_loss=0.02788, over 4741.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2105, pruned_loss=0.03232, over 972739.90 frames.], batch size: 16, lr: 1.93e-04
+2022-05-07 06:49:35,436 INFO [train.py:715] (3/8) Epoch 11, batch 29800, loss[loss=0.1464, simple_loss=0.24, pruned_loss=0.02637, over 4933.00 frames.], tot_loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03256, over 972882.55 frames.], batch size: 23, lr: 1.93e-04
+2022-05-07 06:50:13,827 INFO [train.py:715] (3/8) Epoch 11, batch 29850, loss[loss=0.1152, simple_loss=0.1949, pruned_loss=0.01776, over 4822.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2113, pruned_loss=0.03299, over 972696.56 frames.], batch size: 26, lr: 1.93e-04
+2022-05-07 06:50:52,363 INFO [train.py:715] (3/8) Epoch 11, batch 29900, loss[loss=0.1158, simple_loss=0.1979, pruned_loss=0.01685, over 4772.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03275, over 972782.46 frames.], batch size: 18, lr: 1.93e-04
+2022-05-07 06:51:29,992 INFO [train.py:715] (3/8) Epoch 11, batch 29950, loss[loss=0.1455, simple_loss=0.2128, pruned_loss=0.03906, over 4838.00 frames.], tot_loss[loss=0.1383, simple_loss=0.211, pruned_loss=0.03279, over 972496.99 frames.], batch size: 13, lr: 1.93e-04
+2022-05-07 06:52:08,179 INFO [train.py:715] (3/8) Epoch 11, batch 30000, loss[loss=0.1522, simple_loss=0.2218, pruned_loss=0.04134, over 4968.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2108, pruned_loss=0.03269, over 972967.21 frames.], batch size: 31, lr: 1.93e-04
+2022-05-07 06:52:08,180 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 06:52:17,626 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.106, simple_loss=0.19, pruned_loss=0.01095, over 914524.00 frames.
+2022-05-07 06:52:56,515 INFO [train.py:715] (3/8) Epoch 11, batch 30050, loss[loss=0.1556, simple_loss=0.2288, pruned_loss=0.04116, over 4869.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03229, over 973247.72 frames.], batch size: 22, lr: 1.93e-04
+2022-05-07 06:53:34,388 INFO [train.py:715] (3/8) Epoch 11, batch 30100, loss[loss=0.1466, simple_loss=0.2096, pruned_loss=0.04185, over 4784.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2106, pruned_loss=0.03235, over 972701.35 frames.], batch size: 14, lr: 1.93e-04
+2022-05-07 06:54:13,053 INFO [train.py:715] (3/8) Epoch 11, batch 30150, loss[loss=0.1217, simple_loss=0.2012, pruned_loss=0.02107, over 4978.00 frames.], tot_loss[loss=0.138, simple_loss=0.2107, pruned_loss=0.03261, over 971864.55 frames.], batch size: 24, lr: 1.93e-04
+2022-05-07 06:54:50,401 INFO [train.py:715] (3/8) Epoch 11, batch 30200, loss[loss=0.1281, simple_loss=0.2034, pruned_loss=0.02637, over 4807.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2103, pruned_loss=0.03228, over 971682.72 frames.], batch size: 21, lr: 1.93e-04
+2022-05-07 06:55:29,244 INFO [train.py:715] (3/8) Epoch 11, batch 30250, loss[loss=0.136, simple_loss=0.2107, pruned_loss=0.03064, over 4804.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03256, over 972458.47 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 06:56:07,230 INFO [train.py:715] (3/8) Epoch 11, batch 30300, loss[loss=0.1432, simple_loss=0.2164, pruned_loss=0.035, over 4952.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03268, over 972689.68 frames.], batch size: 21, lr: 1.93e-04
+2022-05-07 06:56:45,178 INFO [train.py:715] (3/8) Epoch 11, batch 30350, loss[loss=0.1357, simple_loss=0.2125, pruned_loss=0.0295, over 4990.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2111, pruned_loss=0.03291, over 972591.60 frames.], batch size: 20, lr: 1.93e-04
+2022-05-07 06:57:23,262 INFO [train.py:715] (3/8) Epoch 11, batch 30400, loss[loss=0.1419, simple_loss=0.2181, pruned_loss=0.03285, over 4960.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2106, pruned_loss=0.0326, over 971668.71 frames.], batch size: 35, lr: 1.93e-04
+2022-05-07 06:58:01,501 INFO [train.py:715] (3/8) Epoch 11, batch 30450, loss[loss=0.1206, simple_loss=0.1996, pruned_loss=0.02077, over 4968.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2101, pruned_loss=0.03227, over 972609.56 frames.], batch size: 24, lr: 1.93e-04
+2022-05-07 06:58:39,332 INFO [train.py:715] (3/8) Epoch 11, batch 30500, loss[loss=0.1358, simple_loss=0.2135, pruned_loss=0.02898, over 4815.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03242, over 973600.03 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 06:59:17,144 INFO [train.py:715] (3/8) Epoch 11, batch 30550, loss[loss=0.1349, simple_loss=0.2154, pruned_loss=0.02719, over 4794.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.033, over 973068.59 frames.], batch size: 14, lr: 1.93e-04
+2022-05-07 06:59:56,406 INFO [train.py:715] (3/8) Epoch 11, batch 30600, loss[loss=0.1648, simple_loss=0.2225, pruned_loss=0.05353, over 4905.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03269, over 973167.89 frames.], batch size: 17, lr: 1.93e-04
+2022-05-07 07:00:35,035 INFO [train.py:715] (3/8) Epoch 11, batch 30650, loss[loss=0.1121, simple_loss=0.1943, pruned_loss=0.01492, over 4982.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03198, over 972037.94 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 07:01:13,830 INFO [train.py:715] (3/8) Epoch 11, batch 30700, loss[loss=0.151, simple_loss=0.2199, pruned_loss=0.04102, over 4965.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2097, pruned_loss=0.03183, over 972675.00 frames.], batch size: 24, lr: 1.93e-04
+2022-05-07 07:01:52,336 INFO [train.py:715] (3/8) Epoch 11, batch 30750, loss[loss=0.1678, simple_loss=0.2389, pruned_loss=0.04832, over 4857.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.03238, over 973508.46 frames.], batch size: 20, lr: 1.93e-04
+2022-05-07 07:02:30,948 INFO [train.py:715] (3/8) Epoch 11, batch 30800, loss[loss=0.1172, simple_loss=0.1914, pruned_loss=0.02144, over 4850.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03196, over 973177.97 frames.], batch size: 20, lr: 1.93e-04
+2022-05-07 07:03:09,709 INFO [train.py:715] (3/8) Epoch 11, batch 30850, loss[loss=0.1188, simple_loss=0.1941, pruned_loss=0.02178, over 4883.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03204, over 973716.33 frames.], batch size: 19, lr: 1.93e-04
+2022-05-07 07:03:48,267 INFO [train.py:715] (3/8) Epoch 11, batch 30900, loss[loss=0.119, simple_loss=0.2049, pruned_loss=0.01657, over 4972.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2111, pruned_loss=0.03255, over 973191.05 frames.], batch size: 15, lr: 1.93e-04
+2022-05-07 07:04:27,074 INFO [train.py:715] (3/8) Epoch 11, batch 30950, loss[loss=0.1235, simple_loss=0.1967, pruned_loss=0.02511, over 4748.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03307, over 973248.51 frames.], batch size: 19, lr: 1.93e-04
+2022-05-07 07:05:06,007 INFO [train.py:715] (3/8) Epoch 11, batch 31000, loss[loss=0.1236, simple_loss=0.197, pruned_loss=0.02512, over 4986.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03257, over 974100.74 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 07:05:44,523 INFO [train.py:715] (3/8) Epoch 11, batch 31050, loss[loss=0.166, simple_loss=0.224, pruned_loss=0.054, over 4933.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03232, over 973045.22 frames.], batch size: 29, lr: 1.93e-04
+2022-05-07 07:06:23,343 INFO [train.py:715] (3/8) Epoch 11, batch 31100, loss[loss=0.1576, simple_loss=0.2282, pruned_loss=0.0435, over 4987.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03243, over 973032.00 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 07:07:01,741 INFO [train.py:715] (3/8) Epoch 11, batch 31150, loss[loss=0.1334, simple_loss=0.2136, pruned_loss=0.02665, over 4823.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03232, over 973116.36 frames.], batch size: 26, lr: 1.93e-04
+2022-05-07 07:07:39,379 INFO [train.py:715] (3/8) Epoch 11, batch 31200, loss[loss=0.1095, simple_loss=0.1816, pruned_loss=0.01871, over 4865.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2114, pruned_loss=0.03195, over 972495.18 frames.], batch size: 32, lr: 1.93e-04
+2022-05-07 07:08:17,483 INFO [train.py:715] (3/8) Epoch 11, batch 31250, loss[loss=0.1307, simple_loss=0.2081, pruned_loss=0.02663, over 4807.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.0315, over 972214.42 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 07:08:55,766 INFO [train.py:715] (3/8) Epoch 11, batch 31300, loss[loss=0.1413, simple_loss=0.2222, pruned_loss=0.03014, over 4795.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03171, over 972175.46 frames.], batch size: 14, lr: 1.93e-04
+2022-05-07 07:09:33,563 INFO [train.py:715] (3/8) Epoch 11, batch 31350, loss[loss=0.1351, simple_loss=0.2148, pruned_loss=0.02776, over 4820.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2116, pruned_loss=0.03186, over 972709.47 frames.], batch size: 25, lr: 1.93e-04
+2022-05-07 07:10:10,910 INFO [train.py:715] (3/8) Epoch 11, batch 31400, loss[loss=0.1348, simple_loss=0.2167, pruned_loss=0.02641, over 4907.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03261, over 972511.25 frames.], batch size: 23, lr: 1.93e-04
+2022-05-07 07:10:48,407 INFO [train.py:715] (3/8) Epoch 11, batch 31450, loss[loss=0.1279, simple_loss=0.202, pruned_loss=0.02689, over 4843.00 frames.], tot_loss[loss=0.1383, simple_loss=0.212, pruned_loss=0.03229, over 972301.20 frames.], batch size: 20, lr: 1.93e-04
+2022-05-07 07:11:26,020 INFO [train.py:715] (3/8) Epoch 11, batch 31500, loss[loss=0.156, simple_loss=0.2395, pruned_loss=0.03622, over 4862.00 frames.], tot_loss[loss=0.139, simple_loss=0.2128, pruned_loss=0.03264, over 971411.04 frames.], batch size: 16, lr: 1.93e-04
+2022-05-07 07:12:03,666 INFO [train.py:715] (3/8) Epoch 11, batch 31550, loss[loss=0.1618, simple_loss=0.2405, pruned_loss=0.04158, over 4903.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2116, pruned_loss=0.03183, over 971231.75 frames.], batch size: 22, lr: 1.93e-04
+2022-05-07 07:12:41,669 INFO [train.py:715] (3/8) Epoch 11, batch 31600, loss[loss=0.1251, simple_loss=0.193, pruned_loss=0.02861, over 4936.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2109, pruned_loss=0.03129, over 971266.10 frames.], batch size: 29, lr: 1.93e-04
+2022-05-07 07:13:19,758 INFO [train.py:715] (3/8) Epoch 11, batch 31650, loss[loss=0.1566, simple_loss=0.219, pruned_loss=0.04715, over 4955.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2113, pruned_loss=0.03175, over 973084.27 frames.], batch size: 35, lr: 1.93e-04
+2022-05-07 07:13:57,690 INFO [train.py:715] (3/8) Epoch 11, batch 31700, loss[loss=0.1291, simple_loss=0.2004, pruned_loss=0.02888, over 4953.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2115, pruned_loss=0.03212, over 972646.41 frames.], batch size: 21, lr: 1.93e-04
+2022-05-07 07:14:35,213 INFO [train.py:715] (3/8) Epoch 11, batch 31750, loss[loss=0.1269, simple_loss=0.207, pruned_loss=0.02341, over 4917.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03198, over 972699.62 frames.], batch size: 23, lr: 1.93e-04
+2022-05-07 07:15:14,061 INFO [train.py:715] (3/8) Epoch 11, batch 31800, loss[loss=0.1396, simple_loss=0.2154, pruned_loss=0.03189, over 4902.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.0319, over 971947.89 frames.], batch size: 19, lr: 1.93e-04
+2022-05-07 07:15:52,639 INFO [train.py:715] (3/8) Epoch 11, batch 31850, loss[loss=0.1347, simple_loss=0.2189, pruned_loss=0.02521, over 4974.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03224, over 972661.79 frames.], batch size: 28, lr: 1.93e-04
+2022-05-07 07:16:30,871 INFO [train.py:715] (3/8) Epoch 11, batch 31900, loss[loss=0.1712, simple_loss=0.245, pruned_loss=0.0487, over 4788.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03263, over 972720.01 frames.], batch size: 14, lr: 1.93e-04
+2022-05-07 07:17:09,162 INFO [train.py:715] (3/8) Epoch 11, batch 31950, loss[loss=0.1338, simple_loss=0.2191, pruned_loss=0.02427, over 4739.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03274, over 973036.17 frames.], batch size: 16, lr: 1.93e-04
+2022-05-07 07:17:47,944 INFO [train.py:715] (3/8) Epoch 11, batch 32000, loss[loss=0.192, simple_loss=0.2798, pruned_loss=0.0521, over 4806.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03301, over 972568.65 frames.], batch size: 21, lr: 1.93e-04
+2022-05-07 07:18:26,170 INFO [train.py:715] (3/8) Epoch 11, batch 32050, loss[loss=0.1367, simple_loss=0.2037, pruned_loss=0.03485, over 4920.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03251, over 972217.31 frames.], batch size: 29, lr: 1.93e-04
+2022-05-07 07:19:04,554 INFO [train.py:715] (3/8) Epoch 11, batch 32100, loss[loss=0.1235, simple_loss=0.2045, pruned_loss=0.02129, over 4924.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03249, over 971256.50 frames.], batch size: 29, lr: 1.92e-04
+2022-05-07 07:19:42,572 INFO [train.py:715] (3/8) Epoch 11, batch 32150, loss[loss=0.1334, simple_loss=0.1908, pruned_loss=0.03801, over 4837.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03226, over 970911.31 frames.], batch size: 30, lr: 1.92e-04
+2022-05-07 07:20:19,991 INFO [train.py:715] (3/8) Epoch 11, batch 32200, loss[loss=0.1364, simple_loss=0.2088, pruned_loss=0.03195, over 4912.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03217, over 971560.77 frames.], batch size: 23, lr: 1.92e-04
+2022-05-07 07:20:57,516 INFO [train.py:715] (3/8) Epoch 11, batch 32250, loss[loss=0.1314, simple_loss=0.2006, pruned_loss=0.03112, over 4828.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03195, over 971347.50 frames.], batch size: 15, lr: 1.92e-04
+2022-05-07 07:21:35,348 INFO [train.py:715] (3/8) Epoch 11, batch 32300, loss[loss=0.1379, simple_loss=0.2006, pruned_loss=0.03757, over 4834.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03241, over 971961.09 frames.], batch size: 15, lr: 1.92e-04
+2022-05-07 07:22:13,997 INFO [train.py:715] (3/8) Epoch 11, batch 32350, loss[loss=0.1231, simple_loss=0.1864, pruned_loss=0.02992, over 4763.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03233, over 971733.80 frames.], batch size: 12, lr: 1.92e-04
+2022-05-07 07:22:51,417 INFO [train.py:715] (3/8) Epoch 11, batch 32400, loss[loss=0.1565, simple_loss=0.2271, pruned_loss=0.04294, over 4861.00 frames.], tot_loss[loss=0.138, simple_loss=0.2118, pruned_loss=0.03212, over 972547.61 frames.], batch size: 20, lr: 1.92e-04
+2022-05-07 07:23:29,419 INFO [train.py:715] (3/8) Epoch 11, batch 32450, loss[loss=0.1316, simple_loss=0.2148, pruned_loss=0.02423, over 4825.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.03261, over 971928.24 frames.], batch size: 26, lr: 1.92e-04
+2022-05-07 07:24:07,459 INFO [train.py:715] (3/8) Epoch 11, batch 32500, loss[loss=0.1303, simple_loss=0.2035, pruned_loss=0.02855, over 4893.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03262, over 972824.58 frames.], batch size: 22, lr: 1.92e-04
+2022-05-07 07:24:45,518 INFO [train.py:715] (3/8) Epoch 11, batch 32550, loss[loss=0.158, simple_loss=0.2294, pruned_loss=0.04332, over 4985.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03201, over 972443.05 frames.], batch size: 24, lr: 1.92e-04
+2022-05-07 07:25:23,172 INFO [train.py:715] (3/8) Epoch 11, batch 32600, loss[loss=0.1411, simple_loss=0.2133, pruned_loss=0.03444, over 4779.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03183, over 972605.77 frames.], batch size: 18, lr: 1.92e-04
+2022-05-07 07:26:01,258 INFO [train.py:715] (3/8) Epoch 11, batch 32650, loss[loss=0.1603, simple_loss=0.2369, pruned_loss=0.04185, over 4918.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03162, over 971943.63 frames.], batch size: 18, lr: 1.92e-04
+2022-05-07 07:26:39,443 INFO [train.py:715] (3/8) Epoch 11, batch 32700, loss[loss=0.1347, simple_loss=0.2108, pruned_loss=0.0293, over 4742.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03166, over 972393.94 frames.], batch size: 16, lr: 1.92e-04
+2022-05-07 07:27:16,892 INFO [train.py:715] (3/8) Epoch 11, batch 32750, loss[loss=0.1235, simple_loss=0.1913, pruned_loss=0.0278, over 4795.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2098, pruned_loss=0.0315, over 972136.98 frames.], batch size: 14, lr: 1.92e-04
+2022-05-07 07:27:55,658 INFO [train.py:715] (3/8) Epoch 11, batch 32800, loss[loss=0.1471, simple_loss=0.2131, pruned_loss=0.04057, over 4874.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2099, pruned_loss=0.03173, over 972272.53 frames.], batch size: 22, lr: 1.92e-04
+2022-05-07 07:28:35,369 INFO [train.py:715] (3/8) Epoch 11, batch 32850, loss[loss=0.1309, simple_loss=0.209, pruned_loss=0.02635, over 4833.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03198, over 971234.40 frames.], batch size: 15, lr: 1.92e-04
+2022-05-07 07:29:13,923 INFO [train.py:715] (3/8) Epoch 11, batch 32900, loss[loss=0.1229, simple_loss=0.1983, pruned_loss=0.02377, over 4759.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03212, over 971705.39 frames.], batch size: 19, lr: 1.92e-04
+2022-05-07 07:29:52,134 INFO [train.py:715] (3/8) Epoch 11, batch 32950, loss[loss=0.1333, simple_loss=0.208, pruned_loss=0.02929, over 4936.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03242, over 971201.77 frames.], batch size: 29, lr: 1.92e-04
+2022-05-07 07:30:31,049 INFO [train.py:715] (3/8) Epoch 11, batch 33000, loss[loss=0.1113, simple_loss=0.1905, pruned_loss=0.01603, over 4812.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.03238, over 971368.03 frames.], batch size: 21, lr: 1.92e-04
+2022-05-07 07:30:31,049 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 07:30:40,493 INFO [train.py:742] (3/8) Epoch 11, validation: loss=0.1059, simple_loss=0.1899, pruned_loss=0.0109, over 914524.00 frames.
+2022-05-07 07:31:19,416 INFO [train.py:715] (3/8) Epoch 11, batch 33050, loss[loss=0.1325, simple_loss=0.2103, pruned_loss=0.02739, over 4913.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.0323, over 971955.98 frames.], batch size: 18, lr: 1.92e-04
+2022-05-07 07:32:00,920 INFO [train.py:715] (3/8) Epoch 11, batch 33100, loss[loss=0.1356, simple_loss=0.2021, pruned_loss=0.03453, over 4769.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03264, over 972566.70 frames.], batch size: 14, lr: 1.92e-04
+2022-05-07 07:32:38,878 INFO [train.py:715] (3/8) Epoch 11, batch 33150, loss[loss=0.149, simple_loss=0.2174, pruned_loss=0.04028, over 4967.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03234, over 973306.34 frames.], batch size: 21, lr: 1.92e-04
+2022-05-07 07:33:17,492 INFO [train.py:715] (3/8) Epoch 11, batch 33200, loss[loss=0.1183, simple_loss=0.1931, pruned_loss=0.02173, over 4988.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03212, over 972898.25 frames.], batch size: 28, lr: 1.92e-04
+2022-05-07 07:33:56,618 INFO [train.py:715] (3/8) Epoch 11, batch 33250, loss[loss=0.1226, simple_loss=0.1957, pruned_loss=0.02472, over 4903.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2128, pruned_loss=0.03265, over 972981.19 frames.], batch size: 19, lr: 1.92e-04
+2022-05-07 07:34:35,410 INFO [train.py:715] (3/8) Epoch 11, batch 33300, loss[loss=0.1356, simple_loss=0.2144, pruned_loss=0.0284, over 4846.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.0328, over 972440.89 frames.], batch size: 30, lr: 1.92e-04
+2022-05-07 07:35:13,284 INFO [train.py:715] (3/8) Epoch 11, batch 33350, loss[loss=0.1353, simple_loss=0.2149, pruned_loss=0.02789, over 4767.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03286, over 971500.02 frames.], batch size: 14, lr: 1.92e-04
+2022-05-07 07:35:51,703 INFO [train.py:715] (3/8) Epoch 11, batch 33400, loss[loss=0.1426, simple_loss=0.2173, pruned_loss=0.03395, over 4823.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03226, over 971397.05 frames.], batch size: 15, lr: 1.92e-04
+2022-05-07 07:36:30,392 INFO [train.py:715] (3/8) Epoch 11, batch 33450, loss[loss=0.1649, simple_loss=0.2401, pruned_loss=0.04482, over 4989.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03205, over 971481.91 frames.], batch size: 28, lr: 1.92e-04
+2022-05-07 07:37:08,731 INFO [train.py:715] (3/8) Epoch 11, batch 33500, loss[loss=0.1456, simple_loss=0.2249, pruned_loss=0.03312, over 4908.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03246, over 971628.84 frames.], batch size: 29, lr: 1.92e-04
+2022-05-07 07:37:47,176 INFO [train.py:715] (3/8) Epoch 11, batch 33550, loss[loss=0.1483, simple_loss=0.2223, pruned_loss=0.0372, over 4976.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2123, pruned_loss=0.03258, over 971771.18 frames.], batch size: 35, lr: 1.92e-04
+2022-05-07 07:38:25,762 INFO [train.py:715] (3/8) Epoch 11, batch 33600, loss[loss=0.153, simple_loss=0.2183, pruned_loss=0.04385, over 4901.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2127, pruned_loss=0.03258, over 971645.62 frames.], batch size: 17, lr: 1.92e-04
+2022-05-07 07:39:04,165 INFO [train.py:715] (3/8) Epoch 11, batch 33650, loss[loss=0.1336, simple_loss=0.2046, pruned_loss=0.03133, over 4808.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2123, pruned_loss=0.03221, over 971334.66 frames.], batch size: 25, lr: 1.92e-04
+2022-05-07 07:39:42,292 INFO [train.py:715] (3/8) Epoch 11, batch 33700, loss[loss=0.1546, simple_loss=0.2229, pruned_loss=0.04313, over 4919.00 frames.], tot_loss[loss=0.1393, simple_loss=0.213, pruned_loss=0.03284, over 971969.58 frames.], batch size: 18, lr: 1.92e-04
+2022-05-07 07:40:20,579 INFO [train.py:715] (3/8) Epoch 11, batch 33750, loss[loss=0.1314, simple_loss=0.2029, pruned_loss=0.02993, over 4870.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2121, pruned_loss=0.03252, over 971796.83 frames.], batch size: 16, lr: 1.92e-04
+2022-05-07 07:40:59,160 INFO [train.py:715] (3/8) Epoch 11, batch 33800, loss[loss=0.1901, simple_loss=0.2694, pruned_loss=0.0554, over 4767.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03318, over 971740.53 frames.], batch size: 19, lr: 1.92e-04
+2022-05-07 07:41:37,148 INFO [train.py:715] (3/8) Epoch 11, batch 33850, loss[loss=0.1322, simple_loss=0.2044, pruned_loss=0.03001, over 4988.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03272, over 971746.01 frames.], batch size: 25, lr: 1.92e-04
+2022-05-07 07:42:15,181 INFO [train.py:715] (3/8) Epoch 11, batch 33900, loss[loss=0.124, simple_loss=0.1828, pruned_loss=0.03259, over 4819.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03263, over 972280.32 frames.], batch size: 13, lr: 1.92e-04
+2022-05-07 07:42:53,934 INFO [train.py:715] (3/8) Epoch 11, batch 33950, loss[loss=0.1274, simple_loss=0.2076, pruned_loss=0.02362, over 4735.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03225, over 972367.19 frames.], batch size: 16, lr: 1.92e-04
+2022-05-07 07:43:32,251 INFO [train.py:715] (3/8) Epoch 11, batch 34000, loss[loss=0.1441, simple_loss=0.225, pruned_loss=0.03166, over 4759.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03234, over 972647.96 frames.], batch size: 19, lr: 1.92e-04
+2022-05-07 07:44:10,352 INFO [train.py:715] (3/8) Epoch 11, batch 34050, loss[loss=0.1687, simple_loss=0.2325, pruned_loss=0.05242, over 4856.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03285, over 973256.04 frames.], batch size: 15, lr: 1.92e-04
+2022-05-07 07:44:48,874 INFO [train.py:715] (3/8) Epoch 11, batch 34100, loss[loss=0.116, simple_loss=0.1944, pruned_loss=0.01879, over 4849.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03292, over 973098.40 frames.], batch size: 20, lr: 1.92e-04
+2022-05-07 07:45:27,613 INFO [train.py:715] (3/8) Epoch 11, batch 34150, loss[loss=0.1559, simple_loss=0.2274, pruned_loss=0.04217, over 4813.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03306, over 972579.84 frames.], batch size: 13, lr: 1.92e-04
+2022-05-07 07:46:05,701 INFO [train.py:715] (3/8) Epoch 11, batch 34200, loss[loss=0.1371, simple_loss=0.2079, pruned_loss=0.03318, over 4797.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03272, over 973558.45 frames.], batch size: 24, lr: 1.92e-04
+2022-05-07 07:46:44,126 INFO [train.py:715] (3/8) Epoch 11, batch 34250, loss[loss=0.1293, simple_loss=0.1994, pruned_loss=0.02959, over 4843.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03272, over 972816.85 frames.], batch size: 30, lr: 1.92e-04
+2022-05-07 07:47:23,288 INFO [train.py:715] (3/8) Epoch 11, batch 34300, loss[loss=0.1193, simple_loss=0.1939, pruned_loss=0.02237, over 4841.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03247, over 972669.32 frames.], batch size: 15, lr: 1.92e-04
+2022-05-07 07:48:01,581 INFO [train.py:715] (3/8) Epoch 11, batch 34350, loss[loss=0.1571, simple_loss=0.236, pruned_loss=0.03909, over 4903.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03254, over 972979.33 frames.], batch size: 17, lr: 1.92e-04
+2022-05-07 07:48:40,023 INFO [train.py:715] (3/8) Epoch 11, batch 34400, loss[loss=0.119, simple_loss=0.1937, pruned_loss=0.02217, over 4651.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03257, over 973181.25 frames.], batch size: 13, lr: 1.92e-04
+2022-05-07 07:49:18,674 INFO [train.py:715] (3/8) Epoch 11, batch 34450, loss[loss=0.123, simple_loss=0.1791, pruned_loss=0.03343, over 4799.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03301, over 973629.26 frames.], batch size: 12, lr: 1.92e-04
+2022-05-07 07:49:57,853 INFO [train.py:715] (3/8) Epoch 11, batch 34500, loss[loss=0.1276, simple_loss=0.2043, pruned_loss=0.0254, over 4814.00 frames.], tot_loss[loss=0.1389, simple_loss=0.212, pruned_loss=0.03286, over 973548.98 frames.], batch size: 15, lr: 1.92e-04
+2022-05-07 07:50:35,959 INFO [train.py:715] (3/8) Epoch 11, batch 34550, loss[loss=0.1747, simple_loss=0.237, pruned_loss=0.05623, over 4877.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.0326, over 973651.71 frames.], batch size: 22, lr: 1.92e-04
+2022-05-07 07:51:12,743 INFO [train.py:715] (3/8) Epoch 11, batch 34600, loss[loss=0.1484, simple_loss=0.2226, pruned_loss=0.0371, over 4880.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03214, over 973105.84 frames.], batch size: 16, lr: 1.92e-04
+2022-05-07 07:51:50,532 INFO [train.py:715] (3/8) Epoch 11, batch 34650, loss[loss=0.1352, simple_loss=0.2121, pruned_loss=0.02916, over 4816.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03254, over 972526.35 frames.], batch size: 26, lr: 1.92e-04
+2022-05-07 07:52:27,798 INFO [train.py:715] (3/8) Epoch 11, batch 34700, loss[loss=0.1434, simple_loss=0.2197, pruned_loss=0.03358, over 4911.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03239, over 972591.86 frames.], batch size: 19, lr: 1.92e-04
+2022-05-07 07:53:04,319 INFO [train.py:715] (3/8) Epoch 11, batch 34750, loss[loss=0.1731, simple_loss=0.2372, pruned_loss=0.05449, over 4973.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03265, over 972107.71 frames.], batch size: 35, lr: 1.92e-04
+2022-05-07 07:53:39,314 INFO [train.py:715] (3/8) Epoch 11, batch 34800, loss[loss=0.1448, simple_loss=0.23, pruned_loss=0.02977, over 4918.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.03294, over 971971.24 frames.], batch size: 18, lr: 1.92e-04
+2022-05-07 07:54:26,267 INFO [train.py:715] (3/8) Epoch 12, batch 0, loss[loss=0.1285, simple_loss=0.1968, pruned_loss=0.03014, over 4901.00 frames.], tot_loss[loss=0.1285, simple_loss=0.1968, pruned_loss=0.03014, over 4901.00 frames.], batch size: 19, lr: 1.85e-04
+2022-05-07 07:55:04,629 INFO [train.py:715] (3/8) Epoch 12, batch 50, loss[loss=0.1267, simple_loss=0.2007, pruned_loss=0.02637, over 4835.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2133, pruned_loss=0.03278, over 219203.45 frames.], batch size: 15, lr: 1.85e-04
+2022-05-07 07:55:42,695 INFO [train.py:715] (3/8) Epoch 12, batch 100, loss[loss=0.1146, simple_loss=0.1942, pruned_loss=0.01749, over 4986.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03294, over 386496.61 frames.], batch size: 24, lr: 1.85e-04
+2022-05-07 07:56:21,321 INFO [train.py:715] (3/8) Epoch 12, batch 150, loss[loss=0.1427, simple_loss=0.2173, pruned_loss=0.03405, over 4968.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03211, over 515595.24 frames.], batch size: 24, lr: 1.85e-04
+2022-05-07 07:56:59,065 INFO [train.py:715] (3/8) Epoch 12, batch 200, loss[loss=0.123, simple_loss=0.1908, pruned_loss=0.02764, over 4982.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2094, pruned_loss=0.03173, over 617339.27 frames.], batch size: 14, lr: 1.85e-04
+2022-05-07 07:57:38,281 INFO [train.py:715] (3/8) Epoch 12, batch 250, loss[loss=0.1035, simple_loss=0.1795, pruned_loss=0.01377, over 4685.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03114, over 696331.38 frames.], batch size: 13, lr: 1.85e-04
+2022-05-07 07:58:16,542 INFO [train.py:715] (3/8) Epoch 12, batch 300, loss[loss=0.1271, simple_loss=0.2017, pruned_loss=0.02624, over 4923.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03183, over 757522.26 frames.], batch size: 18, lr: 1.84e-04
+2022-05-07 07:58:54,472 INFO [train.py:715] (3/8) Epoch 12, batch 350, loss[loss=0.1789, simple_loss=0.2582, pruned_loss=0.0498, over 4923.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03176, over 805940.54 frames.], batch size: 18, lr: 1.84e-04
+2022-05-07 07:59:32,946 INFO [train.py:715] (3/8) Epoch 12, batch 400, loss[loss=0.1302, simple_loss=0.1974, pruned_loss=0.03155, over 4836.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.0317, over 843286.15 frames.], batch size: 32, lr: 1.84e-04
+2022-05-07 08:00:10,578 INFO [train.py:715] (3/8) Epoch 12, batch 450, loss[loss=0.1321, simple_loss=0.2005, pruned_loss=0.03182, over 4911.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.03139, over 872198.55 frames.], batch size: 17, lr: 1.84e-04
+2022-05-07 08:00:48,789 INFO [train.py:715] (3/8) Epoch 12, batch 500, loss[loss=0.1102, simple_loss=0.1831, pruned_loss=0.0187, over 4872.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03161, over 894020.81 frames.], batch size: 16, lr: 1.84e-04
+2022-05-07 08:01:26,233 INFO [train.py:715] (3/8) Epoch 12, batch 550, loss[loss=0.1426, simple_loss=0.2132, pruned_loss=0.036, over 4792.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03161, over 911333.44 frames.], batch size: 14, lr: 1.84e-04
+2022-05-07 08:02:04,575 INFO [train.py:715] (3/8) Epoch 12, batch 600, loss[loss=0.1462, simple_loss=0.2166, pruned_loss=0.03789, over 4950.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03147, over 924921.23 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:02:41,619 INFO [train.py:715] (3/8) Epoch 12, batch 650, loss[loss=0.1161, simple_loss=0.1955, pruned_loss=0.01834, over 4816.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03146, over 935700.36 frames.], batch size: 26, lr: 1.84e-04
+2022-05-07 08:03:20,188 INFO [train.py:715] (3/8) Epoch 12, batch 700, loss[loss=0.1315, simple_loss=0.2001, pruned_loss=0.03146, over 4866.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03152, over 944016.88 frames.], batch size: 34, lr: 1.84e-04
+2022-05-07 08:03:58,808 INFO [train.py:715] (3/8) Epoch 12, batch 750, loss[loss=0.1356, simple_loss=0.2114, pruned_loss=0.02984, over 4838.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03169, over 950308.71 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:04:37,574 INFO [train.py:715] (3/8) Epoch 12, batch 800, loss[loss=0.1068, simple_loss=0.1665, pruned_loss=0.02355, over 4806.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.0321, over 953988.57 frames.], batch size: 13, lr: 1.84e-04
+2022-05-07 08:05:16,050 INFO [train.py:715] (3/8) Epoch 12, batch 850, loss[loss=0.1241, simple_loss=0.1939, pruned_loss=0.02716, over 4921.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03203, over 957638.86 frames.], batch size: 18, lr: 1.84e-04
+2022-05-07 08:05:54,153 INFO [train.py:715] (3/8) Epoch 12, batch 900, loss[loss=0.1365, simple_loss=0.2158, pruned_loss=0.0286, over 4917.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2096, pruned_loss=0.03171, over 960006.82 frames.], batch size: 17, lr: 1.84e-04
+2022-05-07 08:06:32,490 INFO [train.py:715] (3/8) Epoch 12, batch 950, loss[loss=0.1193, simple_loss=0.1864, pruned_loss=0.02615, over 4634.00 frames.], tot_loss[loss=0.1359, simple_loss=0.209, pruned_loss=0.03138, over 962609.94 frames.], batch size: 13, lr: 1.84e-04
+2022-05-07 08:07:09,850 INFO [train.py:715] (3/8) Epoch 12, batch 1000, loss[loss=0.1211, simple_loss=0.1907, pruned_loss=0.02577, over 4822.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2093, pruned_loss=0.03166, over 964516.45 frames.], batch size: 13, lr: 1.84e-04
+2022-05-07 08:07:47,344 INFO [train.py:715] (3/8) Epoch 12, batch 1050, loss[loss=0.122, simple_loss=0.1923, pruned_loss=0.02582, over 4815.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03158, over 966343.76 frames.], batch size: 25, lr: 1.84e-04
+2022-05-07 08:08:25,195 INFO [train.py:715] (3/8) Epoch 12, batch 1100, loss[loss=0.1435, simple_loss=0.2255, pruned_loss=0.03073, over 4964.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2096, pruned_loss=0.03173, over 967302.17 frames.], batch size: 24, lr: 1.84e-04
+2022-05-07 08:09:03,090 INFO [train.py:715] (3/8) Epoch 12, batch 1150, loss[loss=0.1382, simple_loss=0.205, pruned_loss=0.03575, over 4710.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03171, over 968343.04 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:09:41,431 INFO [train.py:715] (3/8) Epoch 12, batch 1200, loss[loss=0.1457, simple_loss=0.2124, pruned_loss=0.03946, over 4930.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03165, over 969692.51 frames.], batch size: 18, lr: 1.84e-04
+2022-05-07 08:10:18,740 INFO [train.py:715] (3/8) Epoch 12, batch 1250, loss[loss=0.1554, simple_loss=0.2261, pruned_loss=0.04234, over 4983.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.0317, over 970237.39 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:10:56,845 INFO [train.py:715] (3/8) Epoch 12, batch 1300, loss[loss=0.1447, simple_loss=0.2225, pruned_loss=0.03348, over 4856.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03183, over 970320.68 frames.], batch size: 20, lr: 1.84e-04
+2022-05-07 08:11:33,987 INFO [train.py:715] (3/8) Epoch 12, batch 1350, loss[loss=0.1562, simple_loss=0.2226, pruned_loss=0.04491, over 4869.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03178, over 970613.47 frames.], batch size: 30, lr: 1.84e-04
+2022-05-07 08:12:12,112 INFO [train.py:715] (3/8) Epoch 12, batch 1400, loss[loss=0.1398, simple_loss=0.2198, pruned_loss=0.02991, over 4804.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03171, over 971759.68 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:12:49,763 INFO [train.py:715] (3/8) Epoch 12, batch 1450, loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03669, over 4994.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03145, over 972696.10 frames.], batch size: 14, lr: 1.84e-04
+2022-05-07 08:13:27,681 INFO [train.py:715] (3/8) Epoch 12, batch 1500, loss[loss=0.1103, simple_loss=0.1874, pruned_loss=0.01661, over 4776.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03108, over 972564.55 frames.], batch size: 12, lr: 1.84e-04
+2022-05-07 08:14:05,278 INFO [train.py:715] (3/8) Epoch 12, batch 1550, loss[loss=0.1084, simple_loss=0.176, pruned_loss=0.02037, over 4802.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03137, over 972432.00 frames.], batch size: 12, lr: 1.84e-04
+2022-05-07 08:14:42,472 INFO [train.py:715] (3/8) Epoch 12, batch 1600, loss[loss=0.1326, simple_loss=0.2124, pruned_loss=0.0264, over 4810.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03216, over 972259.84 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:15:20,492 INFO [train.py:715] (3/8) Epoch 12, batch 1650, loss[loss=0.1472, simple_loss=0.218, pruned_loss=0.03824, over 4863.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03164, over 971041.96 frames.], batch size: 32, lr: 1.84e-04
+2022-05-07 08:15:57,869 INFO [train.py:715] (3/8) Epoch 12, batch 1700, loss[loss=0.1618, simple_loss=0.2417, pruned_loss=0.04098, over 4806.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2112, pruned_loss=0.03233, over 971701.08 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:16:35,315 INFO [train.py:715] (3/8) Epoch 12, batch 1750, loss[loss=0.1334, simple_loss=0.2002, pruned_loss=0.0333, over 4977.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.0324, over 971586.45 frames.], batch size: 33, lr: 1.84e-04
+2022-05-07 08:17:12,473 INFO [train.py:715] (3/8) Epoch 12, batch 1800, loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02958, over 4763.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03287, over 972167.06 frames.], batch size: 16, lr: 1.84e-04
+2022-05-07 08:17:50,169 INFO [train.py:715] (3/8) Epoch 12, batch 1850, loss[loss=0.1547, simple_loss=0.2157, pruned_loss=0.04691, over 4988.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2126, pruned_loss=0.03309, over 971588.47 frames.], batch size: 14, lr: 1.84e-04
+2022-05-07 08:18:27,659 INFO [train.py:715] (3/8) Epoch 12, batch 1900, loss[loss=0.14, simple_loss=0.206, pruned_loss=0.03699, over 4780.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03248, over 972145.61 frames.], batch size: 17, lr: 1.84e-04
+2022-05-07 08:19:05,285 INFO [train.py:715] (3/8) Epoch 12, batch 1950, loss[loss=0.1319, simple_loss=0.2055, pruned_loss=0.0292, over 4931.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.03213, over 972154.60 frames.], batch size: 29, lr: 1.84e-04
+2022-05-07 08:19:43,103 INFO [train.py:715] (3/8) Epoch 12, batch 2000, loss[loss=0.1848, simple_loss=0.2567, pruned_loss=0.05647, over 4819.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.03288, over 972265.79 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:20:21,265 INFO [train.py:715] (3/8) Epoch 12, batch 2050, loss[loss=0.1189, simple_loss=0.1948, pruned_loss=0.02152, over 4944.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03278, over 972543.84 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:20:59,322 INFO [train.py:715] (3/8) Epoch 12, batch 2100, loss[loss=0.1584, simple_loss=0.2353, pruned_loss=0.04068, over 4832.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03306, over 972476.06 frames.], batch size: 30, lr: 1.84e-04
+2022-05-07 08:21:36,626 INFO [train.py:715] (3/8) Epoch 12, batch 2150, loss[loss=0.1086, simple_loss=0.1873, pruned_loss=0.01497, over 4925.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.0332, over 972741.59 frames.], batch size: 29, lr: 1.84e-04
+2022-05-07 08:22:14,598 INFO [train.py:715] (3/8) Epoch 12, batch 2200, loss[loss=0.1207, simple_loss=0.1995, pruned_loss=0.02095, over 4773.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2112, pruned_loss=0.03291, over 972379.05 frames.], batch size: 17, lr: 1.84e-04
+2022-05-07 08:22:52,523 INFO [train.py:715] (3/8) Epoch 12, batch 2250, loss[loss=0.1183, simple_loss=0.1931, pruned_loss=0.02172, over 4824.00 frames.], tot_loss[loss=0.1382, simple_loss=0.211, pruned_loss=0.03277, over 971936.19 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:23:30,601 INFO [train.py:715] (3/8) Epoch 12, batch 2300, loss[loss=0.1163, simple_loss=0.2006, pruned_loss=0.01601, over 4980.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2097, pruned_loss=0.03269, over 971789.91 frames.], batch size: 28, lr: 1.84e-04
+2022-05-07 08:24:07,789 INFO [train.py:715] (3/8) Epoch 12, batch 2350, loss[loss=0.1265, simple_loss=0.2141, pruned_loss=0.01945, over 4812.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2097, pruned_loss=0.03249, over 971742.68 frames.], batch size: 25, lr: 1.84e-04
+2022-05-07 08:24:45,331 INFO [train.py:715] (3/8) Epoch 12, batch 2400, loss[loss=0.1411, simple_loss=0.2099, pruned_loss=0.03615, over 4830.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2097, pruned_loss=0.03278, over 970986.05 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:25:23,252 INFO [train.py:715] (3/8) Epoch 12, batch 2450, loss[loss=0.1243, simple_loss=0.1947, pruned_loss=0.02698, over 4774.00 frames.], tot_loss[loss=0.1367, simple_loss=0.209, pruned_loss=0.03217, over 970457.29 frames.], batch size: 17, lr: 1.84e-04
+2022-05-07 08:26:00,045 INFO [train.py:715] (3/8) Epoch 12, batch 2500, loss[loss=0.1581, simple_loss=0.2336, pruned_loss=0.04129, over 4943.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2105, pruned_loss=0.033, over 970504.26 frames.], batch size: 40, lr: 1.84e-04
+2022-05-07 08:26:38,144 INFO [train.py:715] (3/8) Epoch 12, batch 2550, loss[loss=0.1447, simple_loss=0.2107, pruned_loss=0.03934, over 4840.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2112, pruned_loss=0.0333, over 970657.23 frames.], batch size: 30, lr: 1.84e-04
+2022-05-07 08:27:15,555 INFO [train.py:715] (3/8) Epoch 12, batch 2600, loss[loss=0.1437, simple_loss=0.2057, pruned_loss=0.04084, over 4932.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2116, pruned_loss=0.03346, over 972131.11 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:27:54,373 INFO [train.py:715] (3/8) Epoch 12, batch 2650, loss[loss=0.1407, simple_loss=0.2154, pruned_loss=0.03299, over 4912.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2122, pruned_loss=0.03358, over 972483.81 frames.], batch size: 17, lr: 1.84e-04
+2022-05-07 08:28:32,745 INFO [train.py:715] (3/8) Epoch 12, batch 2700, loss[loss=0.1129, simple_loss=0.192, pruned_loss=0.0169, over 4866.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.0333, over 972615.57 frames.], batch size: 16, lr: 1.84e-04
+2022-05-07 08:29:11,535 INFO [train.py:715] (3/8) Epoch 12, batch 2750, loss[loss=0.1217, simple_loss=0.1931, pruned_loss=0.02516, over 4804.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03295, over 972757.53 frames.], batch size: 25, lr: 1.84e-04
+2022-05-07 08:29:50,413 INFO [train.py:715] (3/8) Epoch 12, batch 2800, loss[loss=0.155, simple_loss=0.2231, pruned_loss=0.04344, over 4970.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.0332, over 973682.43 frames.], batch size: 14, lr: 1.84e-04
+2022-05-07 08:30:28,422 INFO [train.py:715] (3/8) Epoch 12, batch 2850, loss[loss=0.132, simple_loss=0.2113, pruned_loss=0.0263, over 4950.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03291, over 973951.82 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:31:07,089 INFO [train.py:715] (3/8) Epoch 12, batch 2900, loss[loss=0.1123, simple_loss=0.1896, pruned_loss=0.01747, over 4899.00 frames.], tot_loss[loss=0.1397, simple_loss=0.213, pruned_loss=0.03323, over 973749.45 frames.], batch size: 19, lr: 1.84e-04
+2022-05-07 08:31:45,562 INFO [train.py:715] (3/8) Epoch 12, batch 2950, loss[loss=0.1492, simple_loss=0.2275, pruned_loss=0.03542, over 4901.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03309, over 972851.53 frames.], batch size: 17, lr: 1.84e-04
+2022-05-07 08:32:24,277 INFO [train.py:715] (3/8) Epoch 12, batch 3000, loss[loss=0.134, simple_loss=0.2101, pruned_loss=0.02899, over 4742.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.0325, over 973696.02 frames.], batch size: 19, lr: 1.84e-04
+2022-05-07 08:32:24,278 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 08:32:33,756 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.1056, simple_loss=0.1896, pruned_loss=0.01082, over 914524.00 frames.
+2022-05-07 08:33:11,808 INFO [train.py:715] (3/8) Epoch 12, batch 3050, loss[loss=0.1364, simple_loss=0.2049, pruned_loss=0.03395, over 4814.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.03284, over 972657.55 frames.], batch size: 13, lr: 1.84e-04
+2022-05-07 08:33:49,493 INFO [train.py:715] (3/8) Epoch 12, batch 3100, loss[loss=0.1279, simple_loss=0.2097, pruned_loss=0.02304, over 4784.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03273, over 972954.09 frames.], batch size: 18, lr: 1.84e-04
+2022-05-07 08:34:27,408 INFO [train.py:715] (3/8) Epoch 12, batch 3150, loss[loss=0.1626, simple_loss=0.2499, pruned_loss=0.0376, over 4814.00 frames.], tot_loss[loss=0.14, simple_loss=0.2132, pruned_loss=0.0334, over 972286.86 frames.], batch size: 25, lr: 1.84e-04
+2022-05-07 08:35:05,546 INFO [train.py:715] (3/8) Epoch 12, batch 3200, loss[loss=0.1479, simple_loss=0.2338, pruned_loss=0.03095, over 4903.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2133, pruned_loss=0.03301, over 972761.72 frames.], batch size: 19, lr: 1.84e-04
+2022-05-07 08:35:43,250 INFO [train.py:715] (3/8) Epoch 12, batch 3250, loss[loss=0.1103, simple_loss=0.1877, pruned_loss=0.01647, over 4851.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2127, pruned_loss=0.03297, over 973512.75 frames.], batch size: 13, lr: 1.84e-04
+2022-05-07 08:36:21,486 INFO [train.py:715] (3/8) Epoch 12, batch 3300, loss[loss=0.1273, simple_loss=0.2032, pruned_loss=0.02571, over 4985.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03313, over 974327.03 frames.], batch size: 28, lr: 1.84e-04
+2022-05-07 08:36:59,238 INFO [train.py:715] (3/8) Epoch 12, batch 3350, loss[loss=0.1215, simple_loss=0.1985, pruned_loss=0.02229, over 4741.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.03275, over 973490.70 frames.], batch size: 16, lr: 1.84e-04
+2022-05-07 08:37:37,377 INFO [train.py:715] (3/8) Epoch 12, batch 3400, loss[loss=0.1435, simple_loss=0.2124, pruned_loss=0.03732, over 4963.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03295, over 973149.08 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:38:14,961 INFO [train.py:715] (3/8) Epoch 12, batch 3450, loss[loss=0.1511, simple_loss=0.2332, pruned_loss=0.03447, over 4889.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.0328, over 972551.25 frames.], batch size: 19, lr: 1.84e-04
+2022-05-07 08:38:52,885 INFO [train.py:715] (3/8) Epoch 12, batch 3500, loss[loss=0.1227, simple_loss=0.2002, pruned_loss=0.02259, over 4783.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2114, pruned_loss=0.03287, over 971992.79 frames.], batch size: 17, lr: 1.84e-04
+2022-05-07 08:39:31,086 INFO [train.py:715] (3/8) Epoch 12, batch 3550, loss[loss=0.1461, simple_loss=0.2164, pruned_loss=0.03793, over 4978.00 frames.], tot_loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03254, over 971212.55 frames.], batch size: 39, lr: 1.84e-04
+2022-05-07 08:40:08,796 INFO [train.py:715] (3/8) Epoch 12, batch 3600, loss[loss=0.131, simple_loss=0.2067, pruned_loss=0.02766, over 4936.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03207, over 971626.85 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:40:46,534 INFO [train.py:715] (3/8) Epoch 12, batch 3650, loss[loss=0.1377, simple_loss=0.207, pruned_loss=0.03422, over 4878.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03139, over 971529.83 frames.], batch size: 22, lr: 1.84e-04
+2022-05-07 08:41:24,468 INFO [train.py:715] (3/8) Epoch 12, batch 3700, loss[loss=0.17, simple_loss=0.2348, pruned_loss=0.05257, over 4759.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03136, over 972179.67 frames.], batch size: 16, lr: 1.84e-04
+2022-05-07 08:42:02,374 INFO [train.py:715] (3/8) Epoch 12, batch 3750, loss[loss=0.124, simple_loss=0.2027, pruned_loss=0.0226, over 4826.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03091, over 972541.96 frames.], batch size: 26, lr: 1.84e-04
+2022-05-07 08:42:40,470 INFO [train.py:715] (3/8) Epoch 12, batch 3800, loss[loss=0.1259, simple_loss=0.2024, pruned_loss=0.02472, over 4852.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.0307, over 972224.37 frames.], batch size: 20, lr: 1.84e-04
+2022-05-07 08:43:18,089 INFO [train.py:715] (3/8) Epoch 12, batch 3850, loss[loss=0.147, simple_loss=0.2176, pruned_loss=0.03813, over 4859.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2088, pruned_loss=0.03137, over 972122.86 frames.], batch size: 20, lr: 1.84e-04
+2022-05-07 08:43:55,566 INFO [train.py:715] (3/8) Epoch 12, batch 3900, loss[loss=0.1479, simple_loss=0.2267, pruned_loss=0.03462, over 4923.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2091, pruned_loss=0.03132, over 972236.84 frames.], batch size: 29, lr: 1.84e-04
+2022-05-07 08:44:33,442 INFO [train.py:715] (3/8) Epoch 12, batch 3950, loss[loss=0.1518, simple_loss=0.2348, pruned_loss=0.03438, over 4834.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03146, over 972576.15 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:45:11,212 INFO [train.py:715] (3/8) Epoch 12, batch 4000, loss[loss=0.1231, simple_loss=0.2048, pruned_loss=0.02063, over 4961.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.032, over 972021.09 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:45:49,154 INFO [train.py:715] (3/8) Epoch 12, batch 4050, loss[loss=0.1135, simple_loss=0.1871, pruned_loss=0.01989, over 4934.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03154, over 971673.09 frames.], batch size: 29, lr: 1.84e-04
+2022-05-07 08:46:27,046 INFO [train.py:715] (3/8) Epoch 12, batch 4100, loss[loss=0.1188, simple_loss=0.1963, pruned_loss=0.02062, over 4977.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03134, over 972236.60 frames.], batch size: 25, lr: 1.84e-04
+2022-05-07 08:47:05,072 INFO [train.py:715] (3/8) Epoch 12, batch 4150, loss[loss=0.1484, simple_loss=0.2225, pruned_loss=0.0371, over 4895.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03131, over 971933.65 frames.], batch size: 19, lr: 1.84e-04
+2022-05-07 08:47:43,033 INFO [train.py:715] (3/8) Epoch 12, batch 4200, loss[loss=0.1436, simple_loss=0.2195, pruned_loss=0.03382, over 4824.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03156, over 971947.53 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:48:20,659 INFO [train.py:715] (3/8) Epoch 12, batch 4250, loss[loss=0.1414, simple_loss=0.2037, pruned_loss=0.03958, over 4792.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03232, over 972232.75 frames.], batch size: 14, lr: 1.84e-04
+2022-05-07 08:48:58,348 INFO [train.py:715] (3/8) Epoch 12, batch 4300, loss[loss=0.1618, simple_loss=0.2313, pruned_loss=0.04615, over 4943.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03246, over 972884.78 frames.], batch size: 39, lr: 1.84e-04
+2022-05-07 08:49:37,515 INFO [train.py:715] (3/8) Epoch 12, batch 4350, loss[loss=0.1368, simple_loss=0.2074, pruned_loss=0.03307, over 4948.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03232, over 973456.09 frames.], batch size: 35, lr: 1.84e-04
+2022-05-07 08:50:16,265 INFO [train.py:715] (3/8) Epoch 12, batch 4400, loss[loss=0.1183, simple_loss=0.1955, pruned_loss=0.02061, over 4978.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03155, over 974652.37 frames.], batch size: 20, lr: 1.84e-04
+2022-05-07 08:50:54,765 INFO [train.py:715] (3/8) Epoch 12, batch 4450, loss[loss=0.1423, simple_loss=0.226, pruned_loss=0.02928, over 4920.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.03149, over 974686.90 frames.], batch size: 18, lr: 1.84e-04
+2022-05-07 08:51:33,202 INFO [train.py:715] (3/8) Epoch 12, batch 4500, loss[loss=0.1532, simple_loss=0.2258, pruned_loss=0.04026, over 4844.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.03181, over 974197.68 frames.], batch size: 32, lr: 1.84e-04
+2022-05-07 08:52:12,281 INFO [train.py:715] (3/8) Epoch 12, batch 4550, loss[loss=0.124, simple_loss=0.2017, pruned_loss=0.02313, over 4811.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2121, pruned_loss=0.03206, over 974628.03 frames.], batch size: 15, lr: 1.84e-04
+2022-05-07 08:52:50,490 INFO [train.py:715] (3/8) Epoch 12, batch 4600, loss[loss=0.1702, simple_loss=0.255, pruned_loss=0.04273, over 4818.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2121, pruned_loss=0.03211, over 974099.76 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:53:29,040 INFO [train.py:715] (3/8) Epoch 12, batch 4650, loss[loss=0.113, simple_loss=0.1853, pruned_loss=0.02036, over 4825.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.03181, over 973160.44 frames.], batch size: 26, lr: 1.84e-04
+2022-05-07 08:54:07,730 INFO [train.py:715] (3/8) Epoch 12, batch 4700, loss[loss=0.124, simple_loss=0.198, pruned_loss=0.02504, over 4881.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2115, pruned_loss=0.03197, over 973260.64 frames.], batch size: 32, lr: 1.84e-04
+2022-05-07 08:54:46,299 INFO [train.py:715] (3/8) Epoch 12, batch 4750, loss[loss=0.1248, simple_loss=0.2035, pruned_loss=0.02298, over 4802.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03216, over 973184.88 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:55:25,000 INFO [train.py:715] (3/8) Epoch 12, batch 4800, loss[loss=0.1119, simple_loss=0.1856, pruned_loss=0.01908, over 4824.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.03182, over 973423.87 frames.], batch size: 26, lr: 1.84e-04
+2022-05-07 08:56:03,562 INFO [train.py:715] (3/8) Epoch 12, batch 4850, loss[loss=0.1166, simple_loss=0.2015, pruned_loss=0.01584, over 4800.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03199, over 973213.44 frames.], batch size: 21, lr: 1.84e-04
+2022-05-07 08:56:42,593 INFO [train.py:715] (3/8) Epoch 12, batch 4900, loss[loss=0.1416, simple_loss=0.2223, pruned_loss=0.03043, over 4882.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03181, over 973315.08 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 08:57:20,603 INFO [train.py:715] (3/8) Epoch 12, batch 4950, loss[loss=0.1614, simple_loss=0.2299, pruned_loss=0.04647, over 4820.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03159, over 973194.11 frames.], batch size: 27, lr: 1.83e-04
+2022-05-07 08:57:58,207 INFO [train.py:715] (3/8) Epoch 12, batch 5000, loss[loss=0.1394, simple_loss=0.2224, pruned_loss=0.02817, over 4813.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.03176, over 974239.83 frames.], batch size: 26, lr: 1.83e-04
+2022-05-07 08:58:36,394 INFO [train.py:715] (3/8) Epoch 12, batch 5050, loss[loss=0.1462, simple_loss=0.2194, pruned_loss=0.03646, over 4781.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03191, over 972805.04 frames.], batch size: 18, lr: 1.83e-04
+2022-05-07 08:59:13,985 INFO [train.py:715] (3/8) Epoch 12, batch 5100, loss[loss=0.1239, simple_loss=0.1915, pruned_loss=0.02815, over 4978.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2119, pruned_loss=0.03229, over 973317.79 frames.], batch size: 14, lr: 1.83e-04
+2022-05-07 08:59:52,112 INFO [train.py:715] (3/8) Epoch 12, batch 5150, loss[loss=0.1478, simple_loss=0.2236, pruned_loss=0.036, over 4957.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03195, over 973190.41 frames.], batch size: 24, lr: 1.83e-04
+2022-05-07 09:00:30,013 INFO [train.py:715] (3/8) Epoch 12, batch 5200, loss[loss=0.1437, simple_loss=0.2085, pruned_loss=0.03942, over 4912.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2112, pruned_loss=0.0318, over 972906.77 frames.], batch size: 23, lr: 1.83e-04
+2022-05-07 09:01:08,127 INFO [train.py:715] (3/8) Epoch 12, batch 5250, loss[loss=0.1429, simple_loss=0.2185, pruned_loss=0.03366, over 4940.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2113, pruned_loss=0.0317, over 973492.35 frames.], batch size: 35, lr: 1.83e-04
+2022-05-07 09:01:45,993 INFO [train.py:715] (3/8) Epoch 12, batch 5300, loss[loss=0.1395, simple_loss=0.2101, pruned_loss=0.0345, over 4966.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2116, pruned_loss=0.03199, over 973582.93 frames.], batch size: 35, lr: 1.83e-04
+2022-05-07 09:02:24,111 INFO [train.py:715] (3/8) Epoch 12, batch 5350, loss[loss=0.1537, simple_loss=0.2262, pruned_loss=0.04061, over 4910.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03187, over 973988.78 frames.], batch size: 17, lr: 1.83e-04
+2022-05-07 09:03:02,672 INFO [train.py:715] (3/8) Epoch 12, batch 5400, loss[loss=0.1337, simple_loss=0.2049, pruned_loss=0.03123, over 4749.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03152, over 973228.90 frames.], batch size: 19, lr: 1.83e-04
+2022-05-07 09:03:40,515 INFO [train.py:715] (3/8) Epoch 12, batch 5450, loss[loss=0.1559, simple_loss=0.226, pruned_loss=0.04293, over 4792.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2114, pruned_loss=0.03174, over 972629.36 frames.], batch size: 24, lr: 1.83e-04
+2022-05-07 09:04:18,719 INFO [train.py:715] (3/8) Epoch 12, batch 5500, loss[loss=0.1329, simple_loss=0.2136, pruned_loss=0.02608, over 4984.00 frames.], tot_loss[loss=0.1379, simple_loss=0.212, pruned_loss=0.03195, over 973422.77 frames.], batch size: 25, lr: 1.83e-04
+2022-05-07 09:04:56,508 INFO [train.py:715] (3/8) Epoch 12, batch 5550, loss[loss=0.1436, simple_loss=0.2156, pruned_loss=0.03578, over 4767.00 frames.], tot_loss[loss=0.138, simple_loss=0.2119, pruned_loss=0.03206, over 973422.55 frames.], batch size: 18, lr: 1.83e-04
+2022-05-07 09:05:35,155 INFO [train.py:715] (3/8) Epoch 12, batch 5600, loss[loss=0.1139, simple_loss=0.1907, pruned_loss=0.0186, over 4899.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03182, over 973691.69 frames.], batch size: 19, lr: 1.83e-04
+2022-05-07 09:06:12,949 INFO [train.py:715] (3/8) Epoch 12, batch 5650, loss[loss=0.1291, simple_loss=0.1878, pruned_loss=0.03516, over 4853.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03199, over 973655.75 frames.], batch size: 32, lr: 1.83e-04
+2022-05-07 09:06:50,902 INFO [train.py:715] (3/8) Epoch 12, batch 5700, loss[loss=0.1421, simple_loss=0.2325, pruned_loss=0.02581, over 4784.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.03181, over 973781.96 frames.], batch size: 18, lr: 1.83e-04
+2022-05-07 09:07:29,808 INFO [train.py:715] (3/8) Epoch 12, batch 5750, loss[loss=0.13, simple_loss=0.2101, pruned_loss=0.02498, over 4928.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03172, over 973826.08 frames.], batch size: 23, lr: 1.83e-04
+2022-05-07 09:08:07,981 INFO [train.py:715] (3/8) Epoch 12, batch 5800, loss[loss=0.1339, simple_loss=0.2097, pruned_loss=0.02906, over 4881.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03155, over 973345.39 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:08:46,181 INFO [train.py:715] (3/8) Epoch 12, batch 5850, loss[loss=0.1128, simple_loss=0.1846, pruned_loss=0.02045, over 4835.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03174, over 973463.28 frames.], batch size: 13, lr: 1.83e-04
+2022-05-07 09:09:24,397 INFO [train.py:715] (3/8) Epoch 12, batch 5900, loss[loss=0.1591, simple_loss=0.2399, pruned_loss=0.03918, over 4902.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.0317, over 974024.08 frames.], batch size: 17, lr: 1.83e-04
+2022-05-07 09:10:02,495 INFO [train.py:715] (3/8) Epoch 12, batch 5950, loss[loss=0.1181, simple_loss=0.1844, pruned_loss=0.02595, over 4810.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03155, over 973230.75 frames.], batch size: 21, lr: 1.83e-04
+2022-05-07 09:10:40,375 INFO [train.py:715] (3/8) Epoch 12, batch 6000, loss[loss=0.1421, simple_loss=0.2079, pruned_loss=0.0382, over 4867.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.032, over 972569.03 frames.], batch size: 32, lr: 1.83e-04
+2022-05-07 09:10:40,375 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 09:10:49,852 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1897, pruned_loss=0.01086, over 914524.00 frames.
+2022-05-07 09:11:28,466 INFO [train.py:715] (3/8) Epoch 12, batch 6050, loss[loss=0.1473, simple_loss=0.2165, pruned_loss=0.03908, over 4886.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.03189, over 973409.09 frames.], batch size: 39, lr: 1.83e-04
+2022-05-07 09:12:07,171 INFO [train.py:715] (3/8) Epoch 12, batch 6100, loss[loss=0.1277, simple_loss=0.2015, pruned_loss=0.02697, over 4927.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.03197, over 972925.62 frames.], batch size: 18, lr: 1.83e-04
+2022-05-07 09:12:46,249 INFO [train.py:715] (3/8) Epoch 12, batch 6150, loss[loss=0.1572, simple_loss=0.2262, pruned_loss=0.04404, over 4913.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.0325, over 973549.76 frames.], batch size: 17, lr: 1.83e-04
+2022-05-07 09:13:24,045 INFO [train.py:715] (3/8) Epoch 12, batch 6200, loss[loss=0.1217, simple_loss=0.2042, pruned_loss=0.01955, over 4847.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03204, over 973442.72 frames.], batch size: 20, lr: 1.83e-04
+2022-05-07 09:14:02,109 INFO [train.py:715] (3/8) Epoch 12, batch 6250, loss[loss=0.1565, simple_loss=0.2222, pruned_loss=0.04535, over 4738.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2099, pruned_loss=0.03193, over 972385.56 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:14:42,632 INFO [train.py:715] (3/8) Epoch 12, batch 6300, loss[loss=0.1518, simple_loss=0.2152, pruned_loss=0.04419, over 4758.00 frames.], tot_loss[loss=0.1372, simple_loss=0.21, pruned_loss=0.03225, over 972975.25 frames.], batch size: 14, lr: 1.83e-04
+2022-05-07 09:15:20,411 INFO [train.py:715] (3/8) Epoch 12, batch 6350, loss[loss=0.1277, simple_loss=0.2032, pruned_loss=0.02612, over 4867.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2102, pruned_loss=0.03231, over 973504.86 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:15:58,260 INFO [train.py:715] (3/8) Epoch 12, batch 6400, loss[loss=0.1289, simple_loss=0.2075, pruned_loss=0.02514, over 4765.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.0321, over 972858.19 frames.], batch size: 19, lr: 1.83e-04
+2022-05-07 09:16:36,188 INFO [train.py:715] (3/8) Epoch 12, batch 6450, loss[loss=0.1849, simple_loss=0.2587, pruned_loss=0.05561, over 4909.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03281, over 973019.33 frames.], batch size: 19, lr: 1.83e-04
+2022-05-07 09:17:14,182 INFO [train.py:715] (3/8) Epoch 12, batch 6500, loss[loss=0.1381, simple_loss=0.2107, pruned_loss=0.03268, over 4990.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03265, over 973133.88 frames.], batch size: 25, lr: 1.83e-04
+2022-05-07 09:17:51,826 INFO [train.py:715] (3/8) Epoch 12, batch 6550, loss[loss=0.1071, simple_loss=0.1766, pruned_loss=0.01886, over 4946.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03246, over 972178.32 frames.], batch size: 29, lr: 1.83e-04
+2022-05-07 09:18:29,931 INFO [train.py:715] (3/8) Epoch 12, batch 6600, loss[loss=0.1451, simple_loss=0.2147, pruned_loss=0.03777, over 4831.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03245, over 971840.33 frames.], batch size: 15, lr: 1.83e-04
+2022-05-07 09:19:08,079 INFO [train.py:715] (3/8) Epoch 12, batch 6650, loss[loss=0.1127, simple_loss=0.1809, pruned_loss=0.02226, over 4870.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03225, over 972289.49 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:19:46,572 INFO [train.py:715] (3/8) Epoch 12, batch 6700, loss[loss=0.1128, simple_loss=0.1822, pruned_loss=0.02176, over 4962.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.03187, over 972912.08 frames.], batch size: 15, lr: 1.83e-04
+2022-05-07 09:20:24,047 INFO [train.py:715] (3/8) Epoch 12, batch 6750, loss[loss=0.1279, simple_loss=0.2088, pruned_loss=0.02348, over 4791.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.0313, over 973825.30 frames.], batch size: 14, lr: 1.83e-04
+2022-05-07 09:21:02,176 INFO [train.py:715] (3/8) Epoch 12, batch 6800, loss[loss=0.1414, simple_loss=0.2212, pruned_loss=0.03079, over 4927.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03184, over 973041.71 frames.], batch size: 17, lr: 1.83e-04
+2022-05-07 09:21:40,239 INFO [train.py:715] (3/8) Epoch 12, batch 6850, loss[loss=0.1107, simple_loss=0.1869, pruned_loss=0.01719, over 4924.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03194, over 972750.22 frames.], batch size: 23, lr: 1.83e-04
+2022-05-07 09:22:18,035 INFO [train.py:715] (3/8) Epoch 12, batch 6900, loss[loss=0.1183, simple_loss=0.1985, pruned_loss=0.01907, over 4857.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03204, over 973549.63 frames.], batch size: 20, lr: 1.83e-04
+2022-05-07 09:22:56,144 INFO [train.py:715] (3/8) Epoch 12, batch 6950, loss[loss=0.1174, simple_loss=0.1772, pruned_loss=0.02879, over 4647.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03192, over 972739.93 frames.], batch size: 13, lr: 1.83e-04
+2022-05-07 09:23:34,139 INFO [train.py:715] (3/8) Epoch 12, batch 7000, loss[loss=0.1579, simple_loss=0.2274, pruned_loss=0.04415, over 4919.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03191, over 972859.83 frames.], batch size: 18, lr: 1.83e-04
+2022-05-07 09:24:12,557 INFO [train.py:715] (3/8) Epoch 12, batch 7050, loss[loss=0.1415, simple_loss=0.2022, pruned_loss=0.04035, over 4915.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03242, over 972476.42 frames.], batch size: 17, lr: 1.83e-04
+2022-05-07 09:24:50,040 INFO [train.py:715] (3/8) Epoch 12, batch 7100, loss[loss=0.1372, simple_loss=0.215, pruned_loss=0.02966, over 4880.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03209, over 972033.57 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:25:28,613 INFO [train.py:715] (3/8) Epoch 12, batch 7150, loss[loss=0.1166, simple_loss=0.1903, pruned_loss=0.02144, over 4969.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03241, over 972729.78 frames.], batch size: 24, lr: 1.83e-04
+2022-05-07 09:26:06,442 INFO [train.py:715] (3/8) Epoch 12, batch 7200, loss[loss=0.1382, simple_loss=0.2123, pruned_loss=0.03209, over 4738.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03195, over 972094.83 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:26:44,290 INFO [train.py:715] (3/8) Epoch 12, batch 7250, loss[loss=0.1405, simple_loss=0.2251, pruned_loss=0.028, over 4909.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03245, over 972402.81 frames.], batch size: 19, lr: 1.83e-04
+2022-05-07 09:27:22,552 INFO [train.py:715] (3/8) Epoch 12, batch 7300, loss[loss=0.1278, simple_loss=0.2162, pruned_loss=0.0197, over 4810.00 frames.], tot_loss[loss=0.1382, simple_loss=0.212, pruned_loss=0.03222, over 972349.09 frames.], batch size: 26, lr: 1.83e-04
+2022-05-07 09:28:00,296 INFO [train.py:715] (3/8) Epoch 12, batch 7350, loss[loss=0.1475, simple_loss=0.218, pruned_loss=0.03852, over 4777.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2116, pruned_loss=0.03189, over 971880.54 frames.], batch size: 14, lr: 1.83e-04
+2022-05-07 09:28:38,318 INFO [train.py:715] (3/8) Epoch 12, batch 7400, loss[loss=0.1072, simple_loss=0.1855, pruned_loss=0.01444, over 4797.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2113, pruned_loss=0.03187, over 972820.58 frames.], batch size: 24, lr: 1.83e-04
+2022-05-07 09:29:16,071 INFO [train.py:715] (3/8) Epoch 12, batch 7450, loss[loss=0.1059, simple_loss=0.1705, pruned_loss=0.02067, over 4980.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03198, over 971815.40 frames.], batch size: 14, lr: 1.83e-04
+2022-05-07 09:29:54,163 INFO [train.py:715] (3/8) Epoch 12, batch 7500, loss[loss=0.1604, simple_loss=0.2256, pruned_loss=0.04758, over 4766.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03279, over 972283.52 frames.], batch size: 19, lr: 1.83e-04
+2022-05-07 09:30:32,183 INFO [train.py:715] (3/8) Epoch 12, batch 7550, loss[loss=0.1442, simple_loss=0.2258, pruned_loss=0.03128, over 4697.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03272, over 971939.17 frames.], batch size: 15, lr: 1.83e-04
+2022-05-07 09:31:10,033 INFO [train.py:715] (3/8) Epoch 12, batch 7600, loss[loss=0.1451, simple_loss=0.2151, pruned_loss=0.03758, over 4880.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03271, over 971892.29 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:31:48,261 INFO [train.py:715] (3/8) Epoch 12, batch 7650, loss[loss=0.1253, simple_loss=0.1952, pruned_loss=0.02774, over 4787.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03305, over 972210.74 frames.], batch size: 18, lr: 1.83e-04
+2022-05-07 09:32:26,439 INFO [train.py:715] (3/8) Epoch 12, batch 7700, loss[loss=0.1113, simple_loss=0.1829, pruned_loss=0.01986, over 4809.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03264, over 972756.11 frames.], batch size: 21, lr: 1.83e-04
+2022-05-07 09:33:04,638 INFO [train.py:715] (3/8) Epoch 12, batch 7750, loss[loss=0.1169, simple_loss=0.2004, pruned_loss=0.01673, over 4973.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03171, over 972306.33 frames.], batch size: 24, lr: 1.83e-04
+2022-05-07 09:33:42,405 INFO [train.py:715] (3/8) Epoch 12, batch 7800, loss[loss=0.1221, simple_loss=0.2013, pruned_loss=0.02146, over 4953.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03177, over 972431.70 frames.], batch size: 23, lr: 1.83e-04
+2022-05-07 09:34:20,596 INFO [train.py:715] (3/8) Epoch 12, batch 7850, loss[loss=0.1177, simple_loss=0.1974, pruned_loss=0.01902, over 4874.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03153, over 971352.29 frames.], batch size: 32, lr: 1.83e-04
+2022-05-07 09:34:58,403 INFO [train.py:715] (3/8) Epoch 12, batch 7900, loss[loss=0.1286, simple_loss=0.1992, pruned_loss=0.02904, over 4833.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03185, over 971664.38 frames.], batch size: 20, lr: 1.83e-04
+2022-05-07 09:35:36,649 INFO [train.py:715] (3/8) Epoch 12, batch 7950, loss[loss=0.1578, simple_loss=0.2296, pruned_loss=0.04297, over 4907.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03209, over 971726.93 frames.], batch size: 17, lr: 1.83e-04
+2022-05-07 09:36:14,623 INFO [train.py:715] (3/8) Epoch 12, batch 8000, loss[loss=0.157, simple_loss=0.2194, pruned_loss=0.0473, over 4936.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03297, over 971931.34 frames.], batch size: 35, lr: 1.83e-04
+2022-05-07 09:36:53,082 INFO [train.py:715] (3/8) Epoch 12, batch 8050, loss[loss=0.1503, simple_loss=0.2284, pruned_loss=0.03613, over 4932.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03293, over 972166.61 frames.], batch size: 18, lr: 1.83e-04
+2022-05-07 09:37:31,433 INFO [train.py:715] (3/8) Epoch 12, batch 8100, loss[loss=0.1476, simple_loss=0.2191, pruned_loss=0.03801, over 4770.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.03283, over 972038.16 frames.], batch size: 14, lr: 1.83e-04
+2022-05-07 09:38:09,022 INFO [train.py:715] (3/8) Epoch 12, batch 8150, loss[loss=0.1455, simple_loss=0.2148, pruned_loss=0.0381, over 4829.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03299, over 972332.30 frames.], batch size: 15, lr: 1.83e-04
+2022-05-07 09:38:47,285 INFO [train.py:715] (3/8) Epoch 12, batch 8200, loss[loss=0.1544, simple_loss=0.2242, pruned_loss=0.04226, over 4951.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03267, over 973437.45 frames.], batch size: 35, lr: 1.83e-04
+2022-05-07 09:39:25,281 INFO [train.py:715] (3/8) Epoch 12, batch 8250, loss[loss=0.1305, simple_loss=0.202, pruned_loss=0.02951, over 4754.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03255, over 973394.75 frames.], batch size: 17, lr: 1.83e-04
+2022-05-07 09:40:03,014 INFO [train.py:715] (3/8) Epoch 12, batch 8300, loss[loss=0.1472, simple_loss=0.2069, pruned_loss=0.04373, over 4854.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2107, pruned_loss=0.03222, over 972897.69 frames.], batch size: 34, lr: 1.83e-04
+2022-05-07 09:40:41,113 INFO [train.py:715] (3/8) Epoch 12, batch 8350, loss[loss=0.1393, simple_loss=0.2167, pruned_loss=0.031, over 4938.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03228, over 972151.17 frames.], batch size: 29, lr: 1.83e-04
+2022-05-07 09:41:19,301 INFO [train.py:715] (3/8) Epoch 12, batch 8400, loss[loss=0.145, simple_loss=0.2315, pruned_loss=0.02923, over 4778.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2107, pruned_loss=0.03223, over 971458.28 frames.], batch size: 19, lr: 1.83e-04
+2022-05-07 09:41:57,374 INFO [train.py:715] (3/8) Epoch 12, batch 8450, loss[loss=0.1181, simple_loss=0.188, pruned_loss=0.02409, over 4740.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03167, over 971439.52 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:42:34,904 INFO [train.py:715] (3/8) Epoch 12, batch 8500, loss[loss=0.1389, simple_loss=0.2157, pruned_loss=0.03104, over 4869.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03152, over 971681.59 frames.], batch size: 22, lr: 1.83e-04
+2022-05-07 09:43:13,190 INFO [train.py:715] (3/8) Epoch 12, batch 8550, loss[loss=0.1441, simple_loss=0.2088, pruned_loss=0.03966, over 4746.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03169, over 972146.85 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:43:51,189 INFO [train.py:715] (3/8) Epoch 12, batch 8600, loss[loss=0.1192, simple_loss=0.1952, pruned_loss=0.02165, over 4860.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03192, over 972333.01 frames.], batch size: 20, lr: 1.83e-04
+2022-05-07 09:44:28,882 INFO [train.py:715] (3/8) Epoch 12, batch 8650, loss[loss=0.1541, simple_loss=0.2389, pruned_loss=0.03463, over 4747.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.0318, over 972534.92 frames.], batch size: 19, lr: 1.83e-04
+2022-05-07 09:45:07,103 INFO [train.py:715] (3/8) Epoch 12, batch 8700, loss[loss=0.1537, simple_loss=0.2196, pruned_loss=0.04386, over 4698.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03186, over 972764.81 frames.], batch size: 15, lr: 1.83e-04
+2022-05-07 09:45:45,270 INFO [train.py:715] (3/8) Epoch 12, batch 8750, loss[loss=0.1316, simple_loss=0.213, pruned_loss=0.02509, over 4933.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2095, pruned_loss=0.03198, over 972748.75 frames.], batch size: 29, lr: 1.83e-04
+2022-05-07 09:46:23,701 INFO [train.py:715] (3/8) Epoch 12, batch 8800, loss[loss=0.1342, simple_loss=0.2088, pruned_loss=0.02975, over 4880.00 frames.], tot_loss[loss=0.1372, simple_loss=0.21, pruned_loss=0.03223, over 973190.36 frames.], batch size: 22, lr: 1.83e-04
+2022-05-07 09:47:01,614 INFO [train.py:715] (3/8) Epoch 12, batch 8850, loss[loss=0.1241, simple_loss=0.2002, pruned_loss=0.02399, over 4813.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03203, over 972207.59 frames.], batch size: 26, lr: 1.83e-04
+2022-05-07 09:47:40,606 INFO [train.py:715] (3/8) Epoch 12, batch 8900, loss[loss=0.1433, simple_loss=0.2066, pruned_loss=0.04002, over 4968.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2097, pruned_loss=0.03168, over 971787.56 frames.], batch size: 14, lr: 1.83e-04
+2022-05-07 09:48:20,144 INFO [train.py:715] (3/8) Epoch 12, batch 8950, loss[loss=0.1613, simple_loss=0.2317, pruned_loss=0.04549, over 4757.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03226, over 972441.48 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:48:58,104 INFO [train.py:715] (3/8) Epoch 12, batch 9000, loss[loss=0.1392, simple_loss=0.1998, pruned_loss=0.03927, over 4768.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03251, over 972508.87 frames.], batch size: 12, lr: 1.83e-04
+2022-05-07 09:48:58,105 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 09:49:07,570 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1898, pruned_loss=0.01084, over 914524.00 frames.
+2022-05-07 09:49:45,346 INFO [train.py:715] (3/8) Epoch 12, batch 9050, loss[loss=0.1404, simple_loss=0.2041, pruned_loss=0.03832, over 4971.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.03215, over 972128.97 frames.], batch size: 15, lr: 1.83e-04
+2022-05-07 09:50:23,566 INFO [train.py:715] (3/8) Epoch 12, batch 9100, loss[loss=0.153, simple_loss=0.2338, pruned_loss=0.03607, over 4981.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2112, pruned_loss=0.03231, over 971830.66 frames.], batch size: 15, lr: 1.83e-04
+2022-05-07 09:51:01,824 INFO [train.py:715] (3/8) Epoch 12, batch 9150, loss[loss=0.1423, simple_loss=0.2168, pruned_loss=0.03386, over 4745.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03221, over 970980.68 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:51:39,542 INFO [train.py:715] (3/8) Epoch 12, batch 9200, loss[loss=0.1551, simple_loss=0.2149, pruned_loss=0.04761, over 4736.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03253, over 970831.14 frames.], batch size: 16, lr: 1.83e-04
+2022-05-07 09:52:17,395 INFO [train.py:715] (3/8) Epoch 12, batch 9250, loss[loss=0.1377, simple_loss=0.2136, pruned_loss=0.03088, over 4843.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03303, over 971144.20 frames.], batch size: 30, lr: 1.83e-04
+2022-05-07 09:52:55,473 INFO [train.py:715] (3/8) Epoch 12, batch 9300, loss[loss=0.1202, simple_loss=0.1787, pruned_loss=0.03085, over 4762.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03329, over 970982.61 frames.], batch size: 12, lr: 1.83e-04
+2022-05-07 09:53:33,066 INFO [train.py:715] (3/8) Epoch 12, batch 9350, loss[loss=0.1464, simple_loss=0.2072, pruned_loss=0.04277, over 4988.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03306, over 971534.91 frames.], batch size: 20, lr: 1.83e-04
+2022-05-07 09:54:10,844 INFO [train.py:715] (3/8) Epoch 12, batch 9400, loss[loss=0.1165, simple_loss=0.1858, pruned_loss=0.02362, over 4937.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.0328, over 971763.97 frames.], batch size: 29, lr: 1.83e-04
+2022-05-07 09:54:48,556 INFO [train.py:715] (3/8) Epoch 12, batch 9450, loss[loss=0.1523, simple_loss=0.2259, pruned_loss=0.03939, over 4990.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03215, over 972333.92 frames.], batch size: 25, lr: 1.83e-04
+2022-05-07 09:55:26,596 INFO [train.py:715] (3/8) Epoch 12, batch 9500, loss[loss=0.1259, simple_loss=0.205, pruned_loss=0.02341, over 4884.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03241, over 972693.68 frames.], batch size: 22, lr: 1.83e-04
+2022-05-07 09:56:04,149 INFO [train.py:715] (3/8) Epoch 12, batch 9550, loss[loss=0.141, simple_loss=0.2116, pruned_loss=0.03525, over 4811.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2107, pruned_loss=0.03274, over 972491.64 frames.], batch size: 13, lr: 1.82e-04
+2022-05-07 09:56:41,642 INFO [train.py:715] (3/8) Epoch 12, batch 9600, loss[loss=0.1539, simple_loss=0.2253, pruned_loss=0.04123, over 4910.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03296, over 972016.09 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 09:57:19,886 INFO [train.py:715] (3/8) Epoch 12, batch 9650, loss[loss=0.1365, simple_loss=0.2156, pruned_loss=0.02874, over 4959.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03246, over 972402.66 frames.], batch size: 29, lr: 1.82e-04
+2022-05-07 09:57:57,756 INFO [train.py:715] (3/8) Epoch 12, batch 9700, loss[loss=0.146, simple_loss=0.2109, pruned_loss=0.04053, over 4698.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03249, over 972164.76 frames.], batch size: 15, lr: 1.82e-04
+2022-05-07 09:58:35,537 INFO [train.py:715] (3/8) Epoch 12, batch 9750, loss[loss=0.1422, simple_loss=0.2143, pruned_loss=0.03508, over 4736.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03255, over 972316.60 frames.], batch size: 16, lr: 1.82e-04
+2022-05-07 09:59:13,484 INFO [train.py:715] (3/8) Epoch 12, batch 9800, loss[loss=0.1486, simple_loss=0.2233, pruned_loss=0.03701, over 4829.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03272, over 972032.44 frames.], batch size: 15, lr: 1.82e-04
+2022-05-07 09:59:52,005 INFO [train.py:715] (3/8) Epoch 12, batch 9850, loss[loss=0.1685, simple_loss=0.2443, pruned_loss=0.04635, over 4660.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03277, over 971863.77 frames.], batch size: 13, lr: 1.82e-04
+2022-05-07 10:00:29,633 INFO [train.py:715] (3/8) Epoch 12, batch 9900, loss[loss=0.1522, simple_loss=0.2289, pruned_loss=0.03778, over 4900.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03252, over 971703.99 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:01:07,864 INFO [train.py:715] (3/8) Epoch 12, batch 9950, loss[loss=0.1423, simple_loss=0.2298, pruned_loss=0.02743, over 4856.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2125, pruned_loss=0.03244, over 972100.30 frames.], batch size: 20, lr: 1.82e-04
+2022-05-07 10:01:46,618 INFO [train.py:715] (3/8) Epoch 12, batch 10000, loss[loss=0.1241, simple_loss=0.2035, pruned_loss=0.02239, over 4950.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2122, pruned_loss=0.03231, over 972378.39 frames.], batch size: 21, lr: 1.82e-04
+2022-05-07 10:02:25,150 INFO [train.py:715] (3/8) Epoch 12, batch 10050, loss[loss=0.1953, simple_loss=0.2663, pruned_loss=0.06216, over 4951.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.0322, over 972283.21 frames.], batch size: 21, lr: 1.82e-04
+2022-05-07 10:03:03,488 INFO [train.py:715] (3/8) Epoch 12, batch 10100, loss[loss=0.1268, simple_loss=0.199, pruned_loss=0.02731, over 4761.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2123, pruned_loss=0.03259, over 972021.87 frames.], batch size: 19, lr: 1.82e-04
+2022-05-07 10:03:41,896 INFO [train.py:715] (3/8) Epoch 12, batch 10150, loss[loss=0.1572, simple_loss=0.2363, pruned_loss=0.03902, over 4836.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03248, over 972425.03 frames.], batch size: 27, lr: 1.82e-04
+2022-05-07 10:04:20,550 INFO [train.py:715] (3/8) Epoch 12, batch 10200, loss[loss=0.1247, simple_loss=0.194, pruned_loss=0.02769, over 4759.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03245, over 972140.50 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:04:57,864 INFO [train.py:715] (3/8) Epoch 12, batch 10250, loss[loss=0.1575, simple_loss=0.2293, pruned_loss=0.04282, over 4924.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03198, over 972162.83 frames.], batch size: 39, lr: 1.82e-04
+2022-05-07 10:05:36,037 INFO [train.py:715] (3/8) Epoch 12, batch 10300, loss[loss=0.1613, simple_loss=0.225, pruned_loss=0.04873, over 4753.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03184, over 971206.09 frames.], batch size: 19, lr: 1.82e-04
+2022-05-07 10:06:14,196 INFO [train.py:715] (3/8) Epoch 12, batch 10350, loss[loss=0.125, simple_loss=0.2046, pruned_loss=0.0227, over 4931.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03221, over 972705.33 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:06:52,243 INFO [train.py:715] (3/8) Epoch 12, batch 10400, loss[loss=0.1379, simple_loss=0.2122, pruned_loss=0.03179, over 4904.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03208, over 972827.88 frames.], batch size: 17, lr: 1.82e-04
+2022-05-07 10:07:29,797 INFO [train.py:715] (3/8) Epoch 12, batch 10450, loss[loss=0.1454, simple_loss=0.2226, pruned_loss=0.03413, over 4848.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03253, over 972900.39 frames.], batch size: 20, lr: 1.82e-04
+2022-05-07 10:08:07,727 INFO [train.py:715] (3/8) Epoch 12, batch 10500, loss[loss=0.119, simple_loss=0.201, pruned_loss=0.01847, over 4866.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03241, over 971982.59 frames.], batch size: 20, lr: 1.82e-04
+2022-05-07 10:08:46,134 INFO [train.py:715] (3/8) Epoch 12, batch 10550, loss[loss=0.1299, simple_loss=0.2089, pruned_loss=0.02544, over 4929.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03242, over 972563.77 frames.], batch size: 35, lr: 1.82e-04
+2022-05-07 10:09:23,508 INFO [train.py:715] (3/8) Epoch 12, batch 10600, loss[loss=0.1437, simple_loss=0.2137, pruned_loss=0.03683, over 4985.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03205, over 972531.77 frames.], batch size: 24, lr: 1.82e-04
+2022-05-07 10:10:01,497 INFO [train.py:715] (3/8) Epoch 12, batch 10650, loss[loss=0.1308, simple_loss=0.2018, pruned_loss=0.02993, over 4980.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03183, over 971660.81 frames.], batch size: 25, lr: 1.82e-04
+2022-05-07 10:10:39,355 INFO [train.py:715] (3/8) Epoch 12, batch 10700, loss[loss=0.15, simple_loss=0.2223, pruned_loss=0.03885, over 4853.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03195, over 971934.66 frames.], batch size: 30, lr: 1.82e-04
+2022-05-07 10:11:16,858 INFO [train.py:715] (3/8) Epoch 12, batch 10750, loss[loss=0.121, simple_loss=0.1934, pruned_loss=0.02431, over 4819.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03212, over 971883.76 frames.], batch size: 26, lr: 1.82e-04
+2022-05-07 10:11:54,744 INFO [train.py:715] (3/8) Epoch 12, batch 10800, loss[loss=0.1229, simple_loss=0.1957, pruned_loss=0.02504, over 4848.00 frames.], tot_loss[loss=0.1371, simple_loss=0.21, pruned_loss=0.0321, over 972084.64 frames.], batch size: 20, lr: 1.82e-04
+2022-05-07 10:12:32,734 INFO [train.py:715] (3/8) Epoch 12, batch 10850, loss[loss=0.1297, simple_loss=0.2089, pruned_loss=0.02525, over 4872.00 frames.], tot_loss[loss=0.1371, simple_loss=0.21, pruned_loss=0.03213, over 971977.88 frames.], batch size: 20, lr: 1.82e-04
+2022-05-07 10:13:11,527 INFO [train.py:715] (3/8) Epoch 12, batch 10900, loss[loss=0.1328, simple_loss=0.2141, pruned_loss=0.02571, over 4772.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2097, pruned_loss=0.03191, over 971564.57 frames.], batch size: 17, lr: 1.82e-04
+2022-05-07 10:13:48,734 INFO [train.py:715] (3/8) Epoch 12, batch 10950, loss[loss=0.1454, simple_loss=0.2152, pruned_loss=0.03777, over 4915.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03204, over 972608.88 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:14:26,875 INFO [train.py:715] (3/8) Epoch 12, batch 11000, loss[loss=0.1451, simple_loss=0.207, pruned_loss=0.04156, over 4789.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03139, over 972423.25 frames.], batch size: 17, lr: 1.82e-04
+2022-05-07 10:15:05,146 INFO [train.py:715] (3/8) Epoch 12, batch 11050, loss[loss=0.134, simple_loss=0.2063, pruned_loss=0.03085, over 4964.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03199, over 972561.38 frames.], batch size: 35, lr: 1.82e-04
+2022-05-07 10:15:42,772 INFO [train.py:715] (3/8) Epoch 12, batch 11100, loss[loss=0.1319, simple_loss=0.2012, pruned_loss=0.03132, over 4902.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03167, over 972526.09 frames.], batch size: 19, lr: 1.82e-04
+2022-05-07 10:16:21,273 INFO [train.py:715] (3/8) Epoch 12, batch 11150, loss[loss=0.1007, simple_loss=0.164, pruned_loss=0.01871, over 4810.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03162, over 972697.96 frames.], batch size: 12, lr: 1.82e-04
+2022-05-07 10:16:58,890 INFO [train.py:715] (3/8) Epoch 12, batch 11200, loss[loss=0.1267, simple_loss=0.2062, pruned_loss=0.02356, over 4760.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.0313, over 972124.08 frames.], batch size: 14, lr: 1.82e-04
+2022-05-07 10:17:36,988 INFO [train.py:715] (3/8) Epoch 12, batch 11250, loss[loss=0.1321, simple_loss=0.2122, pruned_loss=0.02601, over 4692.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03116, over 972545.94 frames.], batch size: 15, lr: 1.82e-04
+2022-05-07 10:18:14,710 INFO [train.py:715] (3/8) Epoch 12, batch 11300, loss[loss=0.1546, simple_loss=0.2237, pruned_loss=0.04275, over 4690.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.0313, over 971690.31 frames.], batch size: 15, lr: 1.82e-04
+2022-05-07 10:18:51,980 INFO [train.py:715] (3/8) Epoch 12, batch 11350, loss[loss=0.1235, simple_loss=0.1943, pruned_loss=0.02632, over 4858.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03093, over 972287.43 frames.], batch size: 12, lr: 1.82e-04
+2022-05-07 10:19:30,201 INFO [train.py:715] (3/8) Epoch 12, batch 11400, loss[loss=0.1256, simple_loss=0.1972, pruned_loss=0.02697, over 4917.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03058, over 971666.82 frames.], batch size: 17, lr: 1.82e-04
+2022-05-07 10:20:07,743 INFO [train.py:715] (3/8) Epoch 12, batch 11450, loss[loss=0.1377, simple_loss=0.2081, pruned_loss=0.03363, over 4784.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03082, over 971288.76 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:20:45,257 INFO [train.py:715] (3/8) Epoch 12, batch 11500, loss[loss=0.1586, simple_loss=0.2296, pruned_loss=0.04382, over 4838.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.0313, over 971578.66 frames.], batch size: 30, lr: 1.82e-04
+2022-05-07 10:21:23,004 INFO [train.py:715] (3/8) Epoch 12, batch 11550, loss[loss=0.1586, simple_loss=0.2322, pruned_loss=0.04247, over 4874.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03161, over 972531.00 frames.], batch size: 38, lr: 1.82e-04
+2022-05-07 10:22:01,394 INFO [train.py:715] (3/8) Epoch 12, batch 11600, loss[loss=0.1199, simple_loss=0.1943, pruned_loss=0.0227, over 4955.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2112, pruned_loss=0.03168, over 972498.63 frames.], batch size: 21, lr: 1.82e-04
+2022-05-07 10:22:38,882 INFO [train.py:715] (3/8) Epoch 12, batch 11650, loss[loss=0.1411, simple_loss=0.2149, pruned_loss=0.03362, over 4779.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03151, over 972210.21 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:23:16,092 INFO [train.py:715] (3/8) Epoch 12, batch 11700, loss[loss=0.1539, simple_loss=0.2192, pruned_loss=0.04436, over 4785.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03156, over 972378.59 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:23:53,750 INFO [train.py:715] (3/8) Epoch 12, batch 11750, loss[loss=0.1438, simple_loss=0.2174, pruned_loss=0.03506, over 4772.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03099, over 972655.35 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:24:31,083 INFO [train.py:715] (3/8) Epoch 12, batch 11800, loss[loss=0.1404, simple_loss=0.2065, pruned_loss=0.03713, over 4888.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03123, over 972817.94 frames.], batch size: 19, lr: 1.82e-04
+2022-05-07 10:25:08,779 INFO [train.py:715] (3/8) Epoch 12, batch 11850, loss[loss=0.1143, simple_loss=0.1923, pruned_loss=0.01811, over 4805.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03092, over 973077.98 frames.], batch size: 21, lr: 1.82e-04
+2022-05-07 10:25:46,626 INFO [train.py:715] (3/8) Epoch 12, batch 11900, loss[loss=0.1188, simple_loss=0.1981, pruned_loss=0.01971, over 4842.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2106, pruned_loss=0.03117, over 972685.68 frames.], batch size: 30, lr: 1.82e-04
+2022-05-07 10:26:24,515 INFO [train.py:715] (3/8) Epoch 12, batch 11950, loss[loss=0.1232, simple_loss=0.2039, pruned_loss=0.02127, over 4900.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2103, pruned_loss=0.03094, over 972615.45 frames.], batch size: 19, lr: 1.82e-04
+2022-05-07 10:27:01,977 INFO [train.py:715] (3/8) Epoch 12, batch 12000, loss[loss=0.1274, simple_loss=0.2024, pruned_loss=0.02614, over 4773.00 frames.], tot_loss[loss=0.137, simple_loss=0.2111, pruned_loss=0.03144, over 972356.75 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:27:01,977 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 10:27:11,323 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.1058, simple_loss=0.1897, pruned_loss=0.01095, over 914524.00 frames.
+2022-05-07 10:27:50,015 INFO [train.py:715] (3/8) Epoch 12, batch 12050, loss[loss=0.1381, simple_loss=0.2154, pruned_loss=0.03038, over 4808.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2112, pruned_loss=0.0316, over 972527.78 frames.], batch size: 26, lr: 1.82e-04
+2022-05-07 10:28:29,092 INFO [train.py:715] (3/8) Epoch 12, batch 12100, loss[loss=0.1189, simple_loss=0.2035, pruned_loss=0.01714, over 4815.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2111, pruned_loss=0.0314, over 972356.13 frames.], batch size: 21, lr: 1.82e-04
+2022-05-07 10:29:08,847 INFO [train.py:715] (3/8) Epoch 12, batch 12150, loss[loss=0.1263, simple_loss=0.2064, pruned_loss=0.0231, over 4754.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2109, pruned_loss=0.03117, over 972068.62 frames.], batch size: 19, lr: 1.82e-04
+2022-05-07 10:29:47,132 INFO [train.py:715] (3/8) Epoch 12, batch 12200, loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03436, over 4976.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2108, pruned_loss=0.03128, over 971816.28 frames.], batch size: 14, lr: 1.82e-04
+2022-05-07 10:30:25,385 INFO [train.py:715] (3/8) Epoch 12, batch 12250, loss[loss=0.1361, simple_loss=0.2154, pruned_loss=0.02837, over 4819.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03212, over 971796.50 frames.], batch size: 27, lr: 1.82e-04
+2022-05-07 10:31:04,239 INFO [train.py:715] (3/8) Epoch 12, batch 12300, loss[loss=0.1466, simple_loss=0.217, pruned_loss=0.03814, over 4833.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2117, pruned_loss=0.032, over 971702.43 frames.], batch size: 13, lr: 1.82e-04
+2022-05-07 10:31:42,816 INFO [train.py:715] (3/8) Epoch 12, batch 12350, loss[loss=0.1179, simple_loss=0.1961, pruned_loss=0.01985, over 4979.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2119, pruned_loss=0.03227, over 972531.76 frames.], batch size: 25, lr: 1.82e-04
+2022-05-07 10:32:20,262 INFO [train.py:715] (3/8) Epoch 12, batch 12400, loss[loss=0.09555, simple_loss=0.1661, pruned_loss=0.01249, over 4732.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03211, over 971963.52 frames.], batch size: 12, lr: 1.82e-04
+2022-05-07 10:32:57,987 INFO [train.py:715] (3/8) Epoch 12, batch 12450, loss[loss=0.1543, simple_loss=0.2206, pruned_loss=0.04401, over 4751.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03207, over 972143.04 frames.], batch size: 19, lr: 1.82e-04
+2022-05-07 10:33:36,209 INFO [train.py:715] (3/8) Epoch 12, batch 12500, loss[loss=0.1276, simple_loss=0.1979, pruned_loss=0.0286, over 4821.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03209, over 972537.95 frames.], batch size: 25, lr: 1.82e-04
+2022-05-07 10:34:13,319 INFO [train.py:715] (3/8) Epoch 12, batch 12550, loss[loss=0.1331, simple_loss=0.2164, pruned_loss=0.02493, over 4812.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03245, over 972604.60 frames.], batch size: 26, lr: 1.82e-04
+2022-05-07 10:34:51,155 INFO [train.py:715] (3/8) Epoch 12, batch 12600, loss[loss=0.1296, simple_loss=0.1942, pruned_loss=0.0325, over 4809.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2122, pruned_loss=0.03267, over 973404.39 frames.], batch size: 25, lr: 1.82e-04
+2022-05-07 10:35:28,922 INFO [train.py:715] (3/8) Epoch 12, batch 12650, loss[loss=0.137, simple_loss=0.2113, pruned_loss=0.03135, over 4830.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03278, over 972839.34 frames.], batch size: 25, lr: 1.82e-04
+2022-05-07 10:36:06,674 INFO [train.py:715] (3/8) Epoch 12, batch 12700, loss[loss=0.1287, simple_loss=0.2075, pruned_loss=0.02495, over 4940.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.0332, over 972869.43 frames.], batch size: 39, lr: 1.82e-04
+2022-05-07 10:36:44,127 INFO [train.py:715] (3/8) Epoch 12, batch 12750, loss[loss=0.165, simple_loss=0.235, pruned_loss=0.04746, over 4958.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.03302, over 972649.65 frames.], batch size: 24, lr: 1.82e-04
+2022-05-07 10:37:22,155 INFO [train.py:715] (3/8) Epoch 12, batch 12800, loss[loss=0.1563, simple_loss=0.2282, pruned_loss=0.04216, over 4985.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.03303, over 973080.68 frames.], batch size: 15, lr: 1.82e-04
+2022-05-07 10:38:00,584 INFO [train.py:715] (3/8) Epoch 12, batch 12850, loss[loss=0.1328, simple_loss=0.1993, pruned_loss=0.03317, over 4928.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2106, pruned_loss=0.03227, over 974270.22 frames.], batch size: 29, lr: 1.82e-04
+2022-05-07 10:38:37,912 INFO [train.py:715] (3/8) Epoch 12, batch 12900, loss[loss=0.1339, simple_loss=0.2034, pruned_loss=0.03226, over 4704.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03231, over 973952.74 frames.], batch size: 15, lr: 1.82e-04
+2022-05-07 10:39:15,004 INFO [train.py:715] (3/8) Epoch 12, batch 12950, loss[loss=0.1431, simple_loss=0.2253, pruned_loss=0.03042, over 4820.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03246, over 973648.64 frames.], batch size: 25, lr: 1.82e-04
+2022-05-07 10:39:52,998 INFO [train.py:715] (3/8) Epoch 12, batch 13000, loss[loss=0.1293, simple_loss=0.2033, pruned_loss=0.02759, over 4811.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03261, over 972733.15 frames.], batch size: 13, lr: 1.82e-04
+2022-05-07 10:40:30,780 INFO [train.py:715] (3/8) Epoch 12, batch 13050, loss[loss=0.1412, simple_loss=0.2224, pruned_loss=0.02999, over 4727.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03246, over 971072.24 frames.], batch size: 16, lr: 1.82e-04
+2022-05-07 10:41:08,531 INFO [train.py:715] (3/8) Epoch 12, batch 13100, loss[loss=0.1611, simple_loss=0.2503, pruned_loss=0.03598, over 4958.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2114, pruned_loss=0.03194, over 971872.36 frames.], batch size: 21, lr: 1.82e-04
+2022-05-07 10:41:46,123 INFO [train.py:715] (3/8) Epoch 12, batch 13150, loss[loss=0.1458, simple_loss=0.2146, pruned_loss=0.03844, over 4966.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2113, pruned_loss=0.03161, over 971610.53 frames.], batch size: 15, lr: 1.82e-04
+2022-05-07 10:42:23,789 INFO [train.py:715] (3/8) Epoch 12, batch 13200, loss[loss=0.148, simple_loss=0.2243, pruned_loss=0.03587, over 4819.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03185, over 971167.70 frames.], batch size: 27, lr: 1.82e-04
+2022-05-07 10:43:01,015 INFO [train.py:715] (3/8) Epoch 12, batch 13250, loss[loss=0.125, simple_loss=0.1975, pruned_loss=0.02628, over 4807.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.0316, over 971270.21 frames.], batch size: 25, lr: 1.82e-04
+2022-05-07 10:43:38,188 INFO [train.py:715] (3/8) Epoch 12, batch 13300, loss[loss=0.1387, simple_loss=0.2051, pruned_loss=0.03612, over 4885.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03162, over 971948.01 frames.], batch size: 19, lr: 1.82e-04
+2022-05-07 10:44:16,078 INFO [train.py:715] (3/8) Epoch 12, batch 13350, loss[loss=0.1322, simple_loss=0.2153, pruned_loss=0.02451, over 4928.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03165, over 972548.39 frames.], batch size: 23, lr: 1.82e-04
+2022-05-07 10:44:54,316 INFO [train.py:715] (3/8) Epoch 12, batch 13400, loss[loss=0.113, simple_loss=0.1792, pruned_loss=0.02339, over 4699.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2096, pruned_loss=0.03169, over 972755.28 frames.], batch size: 15, lr: 1.82e-04
+2022-05-07 10:45:31,693 INFO [train.py:715] (3/8) Epoch 12, batch 13450, loss[loss=0.1188, simple_loss=0.1952, pruned_loss=0.02126, over 4957.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03149, over 971968.17 frames.], batch size: 24, lr: 1.82e-04
+2022-05-07 10:46:09,030 INFO [train.py:715] (3/8) Epoch 12, batch 13500, loss[loss=0.1228, simple_loss=0.1899, pruned_loss=0.02788, over 4946.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03133, over 972531.50 frames.], batch size: 21, lr: 1.82e-04
+2022-05-07 10:46:47,475 INFO [train.py:715] (3/8) Epoch 12, batch 13550, loss[loss=0.1454, simple_loss=0.2204, pruned_loss=0.03524, over 4947.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03183, over 972751.61 frames.], batch size: 39, lr: 1.82e-04
+2022-05-07 10:47:24,687 INFO [train.py:715] (3/8) Epoch 12, batch 13600, loss[loss=0.1099, simple_loss=0.1783, pruned_loss=0.02072, over 4801.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03134, over 973394.57 frames.], batch size: 12, lr: 1.82e-04
+2022-05-07 10:48:02,573 INFO [train.py:715] (3/8) Epoch 12, batch 13650, loss[loss=0.1453, simple_loss=0.2151, pruned_loss=0.0378, over 4978.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03167, over 973110.65 frames.], batch size: 15, lr: 1.82e-04
+2022-05-07 10:48:40,710 INFO [train.py:715] (3/8) Epoch 12, batch 13700, loss[loss=0.1284, simple_loss=0.2098, pruned_loss=0.02354, over 4909.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03164, over 972728.03 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:49:18,442 INFO [train.py:715] (3/8) Epoch 12, batch 13750, loss[loss=0.1233, simple_loss=0.2022, pruned_loss=0.0222, over 4988.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2097, pruned_loss=0.03164, over 972258.78 frames.], batch size: 24, lr: 1.82e-04
+2022-05-07 10:49:56,509 INFO [train.py:715] (3/8) Epoch 12, batch 13800, loss[loss=0.1533, simple_loss=0.2219, pruned_loss=0.04236, over 4965.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2101, pruned_loss=0.03219, over 973016.99 frames.], batch size: 24, lr: 1.82e-04
+2022-05-07 10:50:34,449 INFO [train.py:715] (3/8) Epoch 12, batch 13850, loss[loss=0.1331, simple_loss=0.2117, pruned_loss=0.02723, over 4814.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2102, pruned_loss=0.0321, over 973048.50 frames.], batch size: 15, lr: 1.82e-04
+2022-05-07 10:51:12,971 INFO [train.py:715] (3/8) Epoch 12, batch 13900, loss[loss=0.1321, simple_loss=0.2072, pruned_loss=0.02844, over 4820.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03165, over 973120.14 frames.], batch size: 12, lr: 1.82e-04
+2022-05-07 10:51:50,186 INFO [train.py:715] (3/8) Epoch 12, batch 13950, loss[loss=0.1453, simple_loss=0.2193, pruned_loss=0.03562, over 4970.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03219, over 973336.41 frames.], batch size: 28, lr: 1.82e-04
+2022-05-07 10:52:28,378 INFO [train.py:715] (3/8) Epoch 12, batch 14000, loss[loss=0.1163, simple_loss=0.1959, pruned_loss=0.01835, over 4816.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.0319, over 973158.72 frames.], batch size: 26, lr: 1.82e-04
+2022-05-07 10:53:06,890 INFO [train.py:715] (3/8) Epoch 12, batch 14050, loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03438, over 4914.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03247, over 973087.85 frames.], batch size: 18, lr: 1.82e-04
+2022-05-07 10:53:44,260 INFO [train.py:715] (3/8) Epoch 12, batch 14100, loss[loss=0.1462, simple_loss=0.211, pruned_loss=0.04071, over 4892.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03308, over 972208.05 frames.], batch size: 16, lr: 1.82e-04
+2022-05-07 10:54:21,695 INFO [train.py:715] (3/8) Epoch 12, batch 14150, loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03007, over 4959.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.0332, over 972014.51 frames.], batch size: 29, lr: 1.82e-04
+2022-05-07 10:55:00,104 INFO [train.py:715] (3/8) Epoch 12, batch 14200, loss[loss=0.1277, simple_loss=0.2034, pruned_loss=0.02601, over 4962.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03275, over 972132.69 frames.], batch size: 35, lr: 1.82e-04
+2022-05-07 10:55:38,425 INFO [train.py:715] (3/8) Epoch 12, batch 14250, loss[loss=0.1269, simple_loss=0.2014, pruned_loss=0.02622, over 4978.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03245, over 971934.38 frames.], batch size: 28, lr: 1.81e-04
+2022-05-07 10:56:18,083 INFO [train.py:715] (3/8) Epoch 12, batch 14300, loss[loss=0.1317, simple_loss=0.203, pruned_loss=0.03026, over 4844.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2099, pruned_loss=0.03191, over 972111.00 frames.], batch size: 26, lr: 1.81e-04
+2022-05-07 10:56:56,582 INFO [train.py:715] (3/8) Epoch 12, batch 14350, loss[loss=0.1251, simple_loss=0.2041, pruned_loss=0.02301, over 4840.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.0317, over 972280.28 frames.], batch size: 26, lr: 1.81e-04
+2022-05-07 10:57:35,967 INFO [train.py:715] (3/8) Epoch 12, batch 14400, loss[loss=0.1394, simple_loss=0.2169, pruned_loss=0.03093, over 4970.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03163, over 971300.31 frames.], batch size: 15, lr: 1.81e-04
+2022-05-07 10:58:14,112 INFO [train.py:715] (3/8) Epoch 12, batch 14450, loss[loss=0.1244, simple_loss=0.1924, pruned_loss=0.02821, over 4937.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03206, over 972453.69 frames.], batch size: 29, lr: 1.81e-04
+2022-05-07 10:58:53,035 INFO [train.py:715] (3/8) Epoch 12, batch 14500, loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02921, over 4824.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03254, over 972690.46 frames.], batch size: 15, lr: 1.81e-04
+2022-05-07 10:59:32,145 INFO [train.py:715] (3/8) Epoch 12, batch 14550, loss[loss=0.1336, simple_loss=0.2039, pruned_loss=0.0316, over 4916.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.03255, over 972715.10 frames.], batch size: 29, lr: 1.81e-04
+2022-05-07 11:00:11,029 INFO [train.py:715] (3/8) Epoch 12, batch 14600, loss[loss=0.1237, simple_loss=0.1912, pruned_loss=0.02807, over 4854.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03272, over 972735.19 frames.], batch size: 30, lr: 1.81e-04
+2022-05-07 11:00:49,645 INFO [train.py:715] (3/8) Epoch 12, batch 14650, loss[loss=0.1215, simple_loss=0.2069, pruned_loss=0.01803, over 4817.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03186, over 971902.34 frames.], batch size: 26, lr: 1.81e-04
+2022-05-07 11:01:27,545 INFO [train.py:715] (3/8) Epoch 12, batch 14700, loss[loss=0.1369, simple_loss=0.2118, pruned_loss=0.03107, over 4976.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2101, pruned_loss=0.03205, over 972167.67 frames.], batch size: 24, lr: 1.81e-04
+2022-05-07 11:02:06,068 INFO [train.py:715] (3/8) Epoch 12, batch 14750, loss[loss=0.1449, simple_loss=0.2173, pruned_loss=0.03624, over 4784.00 frames.], tot_loss[loss=0.1371, simple_loss=0.21, pruned_loss=0.03208, over 970993.72 frames.], batch size: 14, lr: 1.81e-04
+2022-05-07 11:02:43,583 INFO [train.py:715] (3/8) Epoch 12, batch 14800, loss[loss=0.1188, simple_loss=0.1992, pruned_loss=0.01916, over 4901.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2097, pruned_loss=0.03176, over 970352.32 frames.], batch size: 17, lr: 1.81e-04
+2022-05-07 11:03:21,328 INFO [train.py:715] (3/8) Epoch 12, batch 14850, loss[loss=0.1262, simple_loss=0.1959, pruned_loss=0.02822, over 4874.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03156, over 970677.63 frames.], batch size: 22, lr: 1.81e-04
+2022-05-07 11:03:59,688 INFO [train.py:715] (3/8) Epoch 12, batch 14900, loss[loss=0.1411, simple_loss=0.2195, pruned_loss=0.03139, over 4806.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03168, over 971527.66 frames.], batch size: 21, lr: 1.81e-04
+2022-05-07 11:04:38,248 INFO [train.py:715] (3/8) Epoch 12, batch 14950, loss[loss=0.1425, simple_loss=0.2087, pruned_loss=0.03817, over 4860.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03211, over 972144.78 frames.], batch size: 32, lr: 1.81e-04
+2022-05-07 11:05:15,439 INFO [train.py:715] (3/8) Epoch 12, batch 15000, loss[loss=0.1549, simple_loss=0.2298, pruned_loss=0.03997, over 4828.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03215, over 973070.68 frames.], batch size: 26, lr: 1.81e-04
+2022-05-07 11:05:15,440 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 11:05:25,069 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1897, pruned_loss=0.01083, over 914524.00 frames.
+2022-05-07 11:06:02,916 INFO [train.py:715] (3/8) Epoch 12, batch 15050, loss[loss=0.1153, simple_loss=0.183, pruned_loss=0.02379, over 4980.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2105, pruned_loss=0.03232, over 973045.43 frames.], batch size: 14, lr: 1.81e-04
+2022-05-07 11:06:41,209 INFO [train.py:715] (3/8) Epoch 12, batch 15100, loss[loss=0.1306, simple_loss=0.1877, pruned_loss=0.03675, over 4887.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.03189, over 973687.24 frames.], batch size: 32, lr: 1.81e-04
+2022-05-07 11:07:20,389 INFO [train.py:715] (3/8) Epoch 12, batch 15150, loss[loss=0.1258, simple_loss=0.2017, pruned_loss=0.02493, over 4691.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03187, over 973203.24 frames.], batch size: 15, lr: 1.81e-04
+2022-05-07 11:07:58,862 INFO [train.py:715] (3/8) Epoch 12, batch 15200, loss[loss=0.1029, simple_loss=0.1792, pruned_loss=0.01331, over 4968.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2112, pruned_loss=0.0323, over 973811.92 frames.], batch size: 24, lr: 1.81e-04
+2022-05-07 11:08:37,648 INFO [train.py:715] (3/8) Epoch 12, batch 15250, loss[loss=0.1551, simple_loss=0.2223, pruned_loss=0.04396, over 4970.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03199, over 973911.93 frames.], batch size: 39, lr: 1.81e-04
+2022-05-07 11:09:16,367 INFO [train.py:715] (3/8) Epoch 12, batch 15300, loss[loss=0.1122, simple_loss=0.1912, pruned_loss=0.01656, over 4802.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03278, over 973627.45 frames.], batch size: 25, lr: 1.81e-04
+2022-05-07 11:09:54,568 INFO [train.py:715] (3/8) Epoch 12, batch 15350, loss[loss=0.1453, simple_loss=0.2078, pruned_loss=0.04142, over 4750.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.0329, over 973486.53 frames.], batch size: 16, lr: 1.81e-04
+2022-05-07 11:10:31,953 INFO [train.py:715] (3/8) Epoch 12, batch 15400, loss[loss=0.1491, simple_loss=0.218, pruned_loss=0.04005, over 4872.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.0331, over 973307.78 frames.], batch size: 39, lr: 1.81e-04
+2022-05-07 11:11:09,688 INFO [train.py:715] (3/8) Epoch 12, batch 15450, loss[loss=0.1175, simple_loss=0.1925, pruned_loss=0.02129, over 4919.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03315, over 972889.54 frames.], batch size: 19, lr: 1.81e-04
+2022-05-07 11:11:48,438 INFO [train.py:715] (3/8) Epoch 12, batch 15500, loss[loss=0.1327, simple_loss=0.2057, pruned_loss=0.0299, over 4877.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03293, over 972390.13 frames.], batch size: 20, lr: 1.81e-04
+2022-05-07 11:12:26,565 INFO [train.py:715] (3/8) Epoch 12, batch 15550, loss[loss=0.1395, simple_loss=0.209, pruned_loss=0.03494, over 4816.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03275, over 972276.96 frames.], batch size: 25, lr: 1.81e-04
+2022-05-07 11:13:04,459 INFO [train.py:715] (3/8) Epoch 12, batch 15600, loss[loss=0.1281, simple_loss=0.2017, pruned_loss=0.02723, over 4982.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03164, over 972869.78 frames.], batch size: 25, lr: 1.81e-04
+2022-05-07 11:13:42,238 INFO [train.py:715] (3/8) Epoch 12, batch 15650, loss[loss=0.1212, simple_loss=0.196, pruned_loss=0.02322, over 4897.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03164, over 973236.75 frames.], batch size: 19, lr: 1.81e-04
+2022-05-07 11:14:20,674 INFO [train.py:715] (3/8) Epoch 12, batch 15700, loss[loss=0.121, simple_loss=0.1974, pruned_loss=0.02224, over 4862.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2106, pruned_loss=0.03124, over 973292.30 frames.], batch size: 16, lr: 1.81e-04
+2022-05-07 11:14:58,370 INFO [train.py:715] (3/8) Epoch 12, batch 15750, loss[loss=0.1522, simple_loss=0.2233, pruned_loss=0.04055, over 4840.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2115, pruned_loss=0.03188, over 973006.70 frames.], batch size: 15, lr: 1.81e-04
+2022-05-07 11:15:36,105 INFO [train.py:715] (3/8) Epoch 12, batch 15800, loss[loss=0.1425, simple_loss=0.2166, pruned_loss=0.03418, over 4810.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03179, over 971582.74 frames.], batch size: 26, lr: 1.81e-04
+2022-05-07 11:16:14,198 INFO [train.py:715] (3/8) Epoch 12, batch 15850, loss[loss=0.141, simple_loss=0.2209, pruned_loss=0.03052, over 4792.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03189, over 972270.43 frames.], batch size: 14, lr: 1.81e-04
+2022-05-07 11:16:51,697 INFO [train.py:715] (3/8) Epoch 12, batch 15900, loss[loss=0.1517, simple_loss=0.2216, pruned_loss=0.04092, over 4790.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.0325, over 973249.26 frames.], batch size: 24, lr: 1.81e-04
+2022-05-07 11:17:29,510 INFO [train.py:715] (3/8) Epoch 12, batch 15950, loss[loss=0.1131, simple_loss=0.1842, pruned_loss=0.02104, over 4975.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03257, over 973860.50 frames.], batch size: 14, lr: 1.81e-04
+2022-05-07 11:18:07,569 INFO [train.py:715] (3/8) Epoch 12, batch 16000, loss[loss=0.1467, simple_loss=0.2123, pruned_loss=0.04052, over 4849.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2123, pruned_loss=0.03266, over 974172.56 frames.], batch size: 32, lr: 1.81e-04
+2022-05-07 11:18:47,329 INFO [train.py:715] (3/8) Epoch 12, batch 16050, loss[loss=0.1187, simple_loss=0.1869, pruned_loss=0.02525, over 4769.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03221, over 973253.57 frames.], batch size: 12, lr: 1.81e-04
+2022-05-07 11:19:25,277 INFO [train.py:715] (3/8) Epoch 12, batch 16100, loss[loss=0.1245, simple_loss=0.1958, pruned_loss=0.02655, over 4886.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03193, over 973006.49 frames.], batch size: 19, lr: 1.81e-04
+2022-05-07 11:20:04,189 INFO [train.py:715] (3/8) Epoch 12, batch 16150, loss[loss=0.1769, simple_loss=0.2456, pruned_loss=0.05409, over 4863.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2118, pruned_loss=0.03192, over 973054.20 frames.], batch size: 34, lr: 1.81e-04
+2022-05-07 11:20:43,068 INFO [train.py:715] (3/8) Epoch 12, batch 16200, loss[loss=0.1528, simple_loss=0.2222, pruned_loss=0.04168, over 4889.00 frames.], tot_loss[loss=0.1379, simple_loss=0.212, pruned_loss=0.03192, over 972991.84 frames.], batch size: 19, lr: 1.81e-04
+2022-05-07 11:21:21,842 INFO [train.py:715] (3/8) Epoch 12, batch 16250, loss[loss=0.1543, simple_loss=0.2271, pruned_loss=0.04073, over 4984.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2127, pruned_loss=0.0323, over 972934.31 frames.], batch size: 24, lr: 1.81e-04
+2022-05-07 11:21:59,696 INFO [train.py:715] (3/8) Epoch 12, batch 16300, loss[loss=0.1295, simple_loss=0.2057, pruned_loss=0.02669, over 4836.00 frames.], tot_loss[loss=0.1381, simple_loss=0.212, pruned_loss=0.03213, over 973492.87 frames.], batch size: 26, lr: 1.81e-04
+2022-05-07 11:22:37,477 INFO [train.py:715] (3/8) Epoch 12, batch 16350, loss[loss=0.1347, simple_loss=0.2171, pruned_loss=0.02618, over 4858.00 frames.], tot_loss[loss=0.138, simple_loss=0.2118, pruned_loss=0.03207, over 973785.99 frames.], batch size: 20, lr: 1.81e-04
+2022-05-07 11:23:16,251 INFO [train.py:715] (3/8) Epoch 12, batch 16400, loss[loss=0.1562, simple_loss=0.2212, pruned_loss=0.04557, over 4854.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2124, pruned_loss=0.03219, over 973550.60 frames.], batch size: 34, lr: 1.81e-04
+2022-05-07 11:23:54,211 INFO [train.py:715] (3/8) Epoch 12, batch 16450, loss[loss=0.1139, simple_loss=0.1866, pruned_loss=0.02063, over 4828.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2118, pruned_loss=0.03238, over 973862.28 frames.], batch size: 13, lr: 1.81e-04
+2022-05-07 11:24:33,096 INFO [train.py:715] (3/8) Epoch 12, batch 16500, loss[loss=0.1428, simple_loss=0.2181, pruned_loss=0.03377, over 4868.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03208, over 972478.39 frames.], batch size: 20, lr: 1.81e-04
+2022-05-07 11:25:12,169 INFO [train.py:715] (3/8) Epoch 12, batch 16550, loss[loss=0.1609, simple_loss=0.2296, pruned_loss=0.04606, over 4974.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2115, pruned_loss=0.03196, over 973074.30 frames.], batch size: 35, lr: 1.81e-04
+2022-05-07 11:25:51,306 INFO [train.py:715] (3/8) Epoch 12, batch 16600, loss[loss=0.1208, simple_loss=0.2004, pruned_loss=0.02059, over 4990.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03158, over 973549.58 frames.], batch size: 26, lr: 1.81e-04
+2022-05-07 11:26:29,845 INFO [train.py:715] (3/8) Epoch 12, batch 16650, loss[loss=0.1405, simple_loss=0.2178, pruned_loss=0.03165, over 4935.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03155, over 973038.74 frames.], batch size: 21, lr: 1.81e-04
+2022-05-07 11:27:08,908 INFO [train.py:715] (3/8) Epoch 12, batch 16700, loss[loss=0.13, simple_loss=0.2007, pruned_loss=0.02963, over 4981.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03189, over 973572.42 frames.], batch size: 28, lr: 1.81e-04
+2022-05-07 11:27:48,110 INFO [train.py:715] (3/8) Epoch 12, batch 16750, loss[loss=0.1345, simple_loss=0.1997, pruned_loss=0.03462, over 4777.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03194, over 973012.54 frames.], batch size: 19, lr: 1.81e-04
+2022-05-07 11:28:26,498 INFO [train.py:715] (3/8) Epoch 12, batch 16800, loss[loss=0.1187, simple_loss=0.1861, pruned_loss=0.02564, over 4798.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.032, over 973803.03 frames.], batch size: 12, lr: 1.81e-04
+2022-05-07 11:29:05,273 INFO [train.py:715] (3/8) Epoch 12, batch 16850, loss[loss=0.1236, simple_loss=0.2043, pruned_loss=0.02142, over 4882.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2111, pruned_loss=0.0317, over 972884.31 frames.], batch size: 16, lr: 1.81e-04
+2022-05-07 11:29:44,424 INFO [train.py:715] (3/8) Epoch 12, batch 16900, loss[loss=0.1239, simple_loss=0.2054, pruned_loss=0.0212, over 4740.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2116, pruned_loss=0.03199, over 972237.59 frames.], batch size: 16, lr: 1.81e-04
+2022-05-07 11:30:24,179 INFO [train.py:715] (3/8) Epoch 12, batch 16950, loss[loss=0.1366, simple_loss=0.2108, pruned_loss=0.03125, over 4765.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2119, pruned_loss=0.03213, over 972883.45 frames.], batch size: 14, lr: 1.81e-04
+2022-05-07 11:31:02,693 INFO [train.py:715] (3/8) Epoch 12, batch 17000, loss[loss=0.1533, simple_loss=0.2159, pruned_loss=0.04531, over 4846.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03236, over 973118.53 frames.], batch size: 30, lr: 1.81e-04
+2022-05-07 11:31:40,879 INFO [train.py:715] (3/8) Epoch 12, batch 17050, loss[loss=0.1412, simple_loss=0.2152, pruned_loss=0.03359, over 4973.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03247, over 973587.01 frames.], batch size: 15, lr: 1.81e-04
+2022-05-07 11:32:19,763 INFO [train.py:715] (3/8) Epoch 12, batch 17100, loss[loss=0.126, simple_loss=0.2069, pruned_loss=0.02258, over 4917.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03208, over 973866.40 frames.], batch size: 23, lr: 1.81e-04
+2022-05-07 11:32:58,566 INFO [train.py:715] (3/8) Epoch 12, batch 17150, loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03034, over 4811.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.0321, over 973746.06 frames.], batch size: 21, lr: 1.81e-04
+2022-05-07 11:33:37,598 INFO [train.py:715] (3/8) Epoch 12, batch 17200, loss[loss=0.1424, simple_loss=0.2005, pruned_loss=0.04213, over 4782.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03219, over 973515.98 frames.], batch size: 14, lr: 1.81e-04
+2022-05-07 11:34:16,028 INFO [train.py:715] (3/8) Epoch 12, batch 17250, loss[loss=0.1409, simple_loss=0.2204, pruned_loss=0.0307, over 4827.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.032, over 974005.41 frames.], batch size: 15, lr: 1.81e-04
+2022-05-07 11:34:54,494 INFO [train.py:715] (3/8) Epoch 12, batch 17300, loss[loss=0.1498, simple_loss=0.2301, pruned_loss=0.03472, over 4840.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03169, over 973499.47 frames.], batch size: 15, lr: 1.81e-04
+2022-05-07 11:35:32,127 INFO [train.py:715] (3/8) Epoch 12, batch 17350, loss[loss=0.1093, simple_loss=0.1757, pruned_loss=0.02146, over 4788.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03154, over 974148.83 frames.], batch size: 14, lr: 1.81e-04
+2022-05-07 11:36:10,079 INFO [train.py:715] (3/8) Epoch 12, batch 17400, loss[loss=0.1221, simple_loss=0.2046, pruned_loss=0.0198, over 4782.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03137, over 973786.14 frames.], batch size: 17, lr: 1.81e-04
+2022-05-07 11:36:47,846 INFO [train.py:715] (3/8) Epoch 12, batch 17450, loss[loss=0.1326, simple_loss=0.2085, pruned_loss=0.02832, over 4886.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03165, over 973256.19 frames.], batch size: 19, lr: 1.81e-04
+2022-05-07 11:37:26,180 INFO [train.py:715] (3/8) Epoch 12, batch 17500, loss[loss=0.1462, simple_loss=0.2263, pruned_loss=0.03307, over 4796.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03137, over 972927.77 frames.], batch size: 24, lr: 1.81e-04
+2022-05-07 11:38:04,042 INFO [train.py:715] (3/8) Epoch 12, batch 17550, loss[loss=0.1469, simple_loss=0.2147, pruned_loss=0.0396, over 4772.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03207, over 972334.13 frames.], batch size: 18, lr: 1.81e-04
+2022-05-07 11:38:42,239 INFO [train.py:715] (3/8) Epoch 12, batch 17600, loss[loss=0.1535, simple_loss=0.2194, pruned_loss=0.04381, over 4909.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03199, over 972165.03 frames.], batch size: 18, lr: 1.81e-04
+2022-05-07 11:39:19,885 INFO [train.py:715] (3/8) Epoch 12, batch 17650, loss[loss=0.1172, simple_loss=0.1919, pruned_loss=0.02119, over 4940.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03151, over 971447.69 frames.], batch size: 14, lr: 1.81e-04
+2022-05-07 11:39:57,989 INFO [train.py:715] (3/8) Epoch 12, batch 17700, loss[loss=0.1344, simple_loss=0.2013, pruned_loss=0.03381, over 4843.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03209, over 971757.42 frames.], batch size: 32, lr: 1.81e-04
+2022-05-07 11:40:36,847 INFO [train.py:715] (3/8) Epoch 12, batch 17750, loss[loss=0.1365, simple_loss=0.2129, pruned_loss=0.03004, over 4817.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2107, pruned_loss=0.03221, over 972178.07 frames.], batch size: 25, lr: 1.81e-04
+2022-05-07 11:41:15,688 INFO [train.py:715] (3/8) Epoch 12, batch 17800, loss[loss=0.1315, simple_loss=0.2032, pruned_loss=0.02989, over 4691.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03189, over 971739.20 frames.], batch size: 15, lr: 1.81e-04
+2022-05-07 11:41:54,189 INFO [train.py:715] (3/8) Epoch 12, batch 17850, loss[loss=0.1409, simple_loss=0.219, pruned_loss=0.03142, over 4883.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03202, over 972050.63 frames.], batch size: 16, lr: 1.81e-04
+2022-05-07 11:42:32,959 INFO [train.py:715] (3/8) Epoch 12, batch 17900, loss[loss=0.1697, simple_loss=0.2363, pruned_loss=0.05152, over 4772.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03197, over 971572.52 frames.], batch size: 18, lr: 1.81e-04
+2022-05-07 11:43:10,438 INFO [train.py:715] (3/8) Epoch 12, batch 17950, loss[loss=0.1823, simple_loss=0.2402, pruned_loss=0.06221, over 4739.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03248, over 970890.73 frames.], batch size: 16, lr: 1.81e-04
+2022-05-07 11:43:48,629 INFO [train.py:715] (3/8) Epoch 12, batch 18000, loss[loss=0.1631, simple_loss=0.2455, pruned_loss=0.04038, over 4929.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03228, over 970340.50 frames.], batch size: 18, lr: 1.81e-04
+2022-05-07 11:43:48,630 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 11:43:58,181 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.106, simple_loss=0.19, pruned_loss=0.011, over 914524.00 frames.
+2022-05-07 11:44:36,606 INFO [train.py:715] (3/8) Epoch 12, batch 18050, loss[loss=0.1253, simple_loss=0.2005, pruned_loss=0.02509, over 4737.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03264, over 969831.18 frames.], batch size: 16, lr: 1.81e-04
+2022-05-07 11:45:14,477 INFO [train.py:715] (3/8) Epoch 12, batch 18100, loss[loss=0.1216, simple_loss=0.198, pruned_loss=0.02258, over 4795.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03203, over 969890.59 frames.], batch size: 24, lr: 1.81e-04
+2022-05-07 11:45:52,626 INFO [train.py:715] (3/8) Epoch 12, batch 18150, loss[loss=0.1382, simple_loss=0.2159, pruned_loss=0.03022, over 4988.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03231, over 970408.71 frames.], batch size: 20, lr: 1.81e-04
+2022-05-07 11:46:30,451 INFO [train.py:715] (3/8) Epoch 12, batch 18200, loss[loss=0.1277, simple_loss=0.1999, pruned_loss=0.02771, over 4943.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2107, pruned_loss=0.03222, over 971143.66 frames.], batch size: 21, lr: 1.81e-04
+2022-05-07 11:47:08,252 INFO [train.py:715] (3/8) Epoch 12, batch 18250, loss[loss=0.12, simple_loss=0.1958, pruned_loss=0.02214, over 4764.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03234, over 971606.60 frames.], batch size: 19, lr: 1.81e-04
+2022-05-07 11:47:46,408 INFO [train.py:715] (3/8) Epoch 12, batch 18300, loss[loss=0.1367, simple_loss=0.2098, pruned_loss=0.03183, over 4821.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.032, over 972078.65 frames.], batch size: 27, lr: 1.81e-04
+2022-05-07 11:48:24,293 INFO [train.py:715] (3/8) Epoch 12, batch 18350, loss[loss=0.1489, simple_loss=0.2133, pruned_loss=0.04224, over 4839.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03246, over 972391.93 frames.], batch size: 30, lr: 1.81e-04
+2022-05-07 11:49:02,250 INFO [train.py:715] (3/8) Epoch 12, batch 18400, loss[loss=0.1393, simple_loss=0.2101, pruned_loss=0.03429, over 4972.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03201, over 972163.55 frames.], batch size: 24, lr: 1.81e-04
+2022-05-07 11:49:39,755 INFO [train.py:715] (3/8) Epoch 12, batch 18450, loss[loss=0.1121, simple_loss=0.192, pruned_loss=0.01607, over 4810.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03199, over 972073.81 frames.], batch size: 24, lr: 1.81e-04
+2022-05-07 11:50:17,838 INFO [train.py:715] (3/8) Epoch 12, batch 18500, loss[loss=0.1335, simple_loss=0.2176, pruned_loss=0.02464, over 4842.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2125, pruned_loss=0.03261, over 971560.54 frames.], batch size: 26, lr: 1.81e-04
+2022-05-07 11:50:55,666 INFO [train.py:715] (3/8) Epoch 12, batch 18550, loss[loss=0.1354, simple_loss=0.2065, pruned_loss=0.0322, over 4944.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.0327, over 972022.48 frames.], batch size: 23, lr: 1.81e-04
+2022-05-07 11:51:33,501 INFO [train.py:715] (3/8) Epoch 12, batch 18600, loss[loss=0.1396, simple_loss=0.2217, pruned_loss=0.02878, over 4917.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2125, pruned_loss=0.03254, over 972798.25 frames.], batch size: 18, lr: 1.81e-04
+2022-05-07 11:52:11,114 INFO [train.py:715] (3/8) Epoch 12, batch 18650, loss[loss=0.107, simple_loss=0.1863, pruned_loss=0.01381, over 4801.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.0319, over 972314.29 frames.], batch size: 21, lr: 1.81e-04
+2022-05-07 11:52:48,674 INFO [train.py:715] (3/8) Epoch 12, batch 18700, loss[loss=0.1739, simple_loss=0.2414, pruned_loss=0.05314, over 4768.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03254, over 972317.88 frames.], batch size: 18, lr: 1.81e-04
+2022-05-07 11:53:26,073 INFO [train.py:715] (3/8) Epoch 12, batch 18750, loss[loss=0.1524, simple_loss=0.2356, pruned_loss=0.0346, over 4901.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03187, over 972043.32 frames.], batch size: 19, lr: 1.81e-04
+2022-05-07 11:54:04,013 INFO [train.py:715] (3/8) Epoch 12, batch 18800, loss[loss=0.1344, simple_loss=0.2208, pruned_loss=0.02404, over 4850.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2103, pruned_loss=0.03112, over 971946.18 frames.], batch size: 20, lr: 1.81e-04
+2022-05-07 11:54:41,894 INFO [train.py:715] (3/8) Epoch 12, batch 18850, loss[loss=0.1473, simple_loss=0.2287, pruned_loss=0.03295, over 4799.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03124, over 972633.70 frames.], batch size: 24, lr: 1.81e-04
+2022-05-07 11:55:19,708 INFO [train.py:715] (3/8) Epoch 12, batch 18900, loss[loss=0.1655, simple_loss=0.2224, pruned_loss=0.05429, over 4852.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03154, over 972820.68 frames.], batch size: 13, lr: 1.81e-04
+2022-05-07 11:55:57,998 INFO [train.py:715] (3/8) Epoch 12, batch 18950, loss[loss=0.1552, simple_loss=0.2221, pruned_loss=0.04413, over 4847.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03156, over 972129.78 frames.], batch size: 34, lr: 1.81e-04
+2022-05-07 11:56:35,808 INFO [train.py:715] (3/8) Epoch 12, batch 19000, loss[loss=0.1344, simple_loss=0.2072, pruned_loss=0.03084, over 4819.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2108, pruned_loss=0.03127, over 972757.35 frames.], batch size: 26, lr: 1.81e-04
+2022-05-07 11:57:13,289 INFO [train.py:715] (3/8) Epoch 12, batch 19050, loss[loss=0.1493, simple_loss=0.2271, pruned_loss=0.03581, over 4880.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.0312, over 972727.28 frames.], batch size: 20, lr: 1.80e-04
+2022-05-07 11:57:50,569 INFO [train.py:715] (3/8) Epoch 12, batch 19100, loss[loss=0.1452, simple_loss=0.2066, pruned_loss=0.04186, over 4875.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03156, over 972928.89 frames.], batch size: 16, lr: 1.80e-04
+2022-05-07 11:58:28,559 INFO [train.py:715] (3/8) Epoch 12, batch 19150, loss[loss=0.1508, simple_loss=0.2269, pruned_loss=0.03739, over 4695.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03175, over 972704.68 frames.], batch size: 15, lr: 1.80e-04
+2022-05-07 11:59:07,194 INFO [train.py:715] (3/8) Epoch 12, batch 19200, loss[loss=0.1186, simple_loss=0.1946, pruned_loss=0.02131, over 4810.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03156, over 973499.06 frames.], batch size: 25, lr: 1.80e-04
+2022-05-07 11:59:45,240 INFO [train.py:715] (3/8) Epoch 12, batch 19250, loss[loss=0.1293, simple_loss=0.207, pruned_loss=0.02576, over 4820.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03124, over 972785.23 frames.], batch size: 25, lr: 1.80e-04
+2022-05-07 12:00:23,722 INFO [train.py:715] (3/8) Epoch 12, batch 19300, loss[loss=0.1358, simple_loss=0.2175, pruned_loss=0.02701, over 4877.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2096, pruned_loss=0.03035, over 972776.34 frames.], batch size: 39, lr: 1.80e-04
+2022-05-07 12:01:01,910 INFO [train.py:715] (3/8) Epoch 12, batch 19350, loss[loss=0.1444, simple_loss=0.2131, pruned_loss=0.03789, over 4981.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2106, pruned_loss=0.03082, over 973146.33 frames.], batch size: 28, lr: 1.80e-04
+2022-05-07 12:01:39,912 INFO [train.py:715] (3/8) Epoch 12, batch 19400, loss[loss=0.16, simple_loss=0.231, pruned_loss=0.04454, over 4800.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2102, pruned_loss=0.03081, over 972558.52 frames.], batch size: 21, lr: 1.80e-04
+2022-05-07 12:02:17,950 INFO [train.py:715] (3/8) Epoch 12, batch 19450, loss[loss=0.1333, simple_loss=0.2062, pruned_loss=0.0302, over 4787.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2103, pruned_loss=0.03097, over 972212.28 frames.], batch size: 17, lr: 1.80e-04
+2022-05-07 12:02:56,771 INFO [train.py:715] (3/8) Epoch 12, batch 19500, loss[loss=0.1165, simple_loss=0.1877, pruned_loss=0.02261, over 4980.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2109, pruned_loss=0.03138, over 971911.65 frames.], batch size: 35, lr: 1.80e-04
+2022-05-07 12:03:35,596 INFO [train.py:715] (3/8) Epoch 12, batch 19550, loss[loss=0.1402, simple_loss=0.2098, pruned_loss=0.0353, over 4878.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.03186, over 972170.18 frames.], batch size: 16, lr: 1.80e-04
+2022-05-07 12:04:14,318 INFO [train.py:715] (3/8) Epoch 12, batch 19600, loss[loss=0.1364, simple_loss=0.2007, pruned_loss=0.03606, over 4857.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03205, over 972300.08 frames.], batch size: 32, lr: 1.80e-04
+2022-05-07 12:04:53,462 INFO [train.py:715] (3/8) Epoch 12, batch 19650, loss[loss=0.1519, simple_loss=0.2211, pruned_loss=0.0413, over 4910.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2123, pruned_loss=0.03262, over 973464.80 frames.], batch size: 18, lr: 1.80e-04
+2022-05-07 12:05:32,629 INFO [train.py:715] (3/8) Epoch 12, batch 19700, loss[loss=0.1397, simple_loss=0.2136, pruned_loss=0.03286, over 4983.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03283, over 973656.90 frames.], batch size: 28, lr: 1.80e-04
+2022-05-07 12:06:12,004 INFO [train.py:715] (3/8) Epoch 12, batch 19750, loss[loss=0.1158, simple_loss=0.1896, pruned_loss=0.021, over 4925.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2118, pruned_loss=0.03242, over 973515.68 frames.], batch size: 18, lr: 1.80e-04
+2022-05-07 12:06:52,639 INFO [train.py:715] (3/8) Epoch 12, batch 19800, loss[loss=0.1853, simple_loss=0.2516, pruned_loss=0.05951, over 4798.00 frames.], tot_loss[loss=0.138, simple_loss=0.2117, pruned_loss=0.03211, over 973098.38 frames.], batch size: 21, lr: 1.80e-04
+2022-05-07 12:07:33,085 INFO [train.py:715] (3/8) Epoch 12, batch 19850, loss[loss=0.1449, simple_loss=0.2085, pruned_loss=0.0406, over 4644.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03279, over 972790.19 frames.], batch size: 13, lr: 1.80e-04
+2022-05-07 12:08:14,256 INFO [train.py:715] (3/8) Epoch 12, batch 19900, loss[loss=0.146, simple_loss=0.218, pruned_loss=0.03702, over 4984.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03228, over 972937.00 frames.], batch size: 39, lr: 1.80e-04
+2022-05-07 12:08:54,592 INFO [train.py:715] (3/8) Epoch 12, batch 19950, loss[loss=0.1293, simple_loss=0.2002, pruned_loss=0.02922, over 4701.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03279, over 972505.56 frames.], batch size: 15, lr: 1.80e-04
+2022-05-07 12:09:35,208 INFO [train.py:715] (3/8) Epoch 12, batch 20000, loss[loss=0.1401, simple_loss=0.2111, pruned_loss=0.03451, over 4854.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2106, pruned_loss=0.03234, over 973173.31 frames.], batch size: 20, lr: 1.80e-04
+2022-05-07 12:10:15,441 INFO [train.py:715] (3/8) Epoch 12, batch 20050, loss[loss=0.1537, simple_loss=0.2262, pruned_loss=0.0406, over 4853.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2102, pruned_loss=0.03227, over 972793.99 frames.], batch size: 16, lr: 1.80e-04
+2022-05-07 12:10:55,689 INFO [train.py:715] (3/8) Epoch 12, batch 20100, loss[loss=0.1297, simple_loss=0.1967, pruned_loss=0.0313, over 4701.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2102, pruned_loss=0.03206, over 972824.03 frames.], batch size: 15, lr: 1.80e-04
+2022-05-07 12:11:35,653 INFO [train.py:715] (3/8) Epoch 12, batch 20150, loss[loss=0.1353, simple_loss=0.2155, pruned_loss=0.02759, over 4935.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03138, over 972470.19 frames.], batch size: 18, lr: 1.80e-04
+2022-05-07 12:12:16,047 INFO [train.py:715] (3/8) Epoch 12, batch 20200, loss[loss=0.1124, simple_loss=0.1868, pruned_loss=0.01902, over 4919.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03137, over 972345.84 frames.], batch size: 23, lr: 1.80e-04
+2022-05-07 12:12:56,153 INFO [train.py:715] (3/8) Epoch 12, batch 20250, loss[loss=0.1301, simple_loss=0.2041, pruned_loss=0.02807, over 4821.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03163, over 972275.73 frames.], batch size: 25, lr: 1.80e-04
+2022-05-07 12:13:36,213 INFO [train.py:715] (3/8) Epoch 12, batch 20300, loss[loss=0.1348, simple_loss=0.2151, pruned_loss=0.02723, over 4864.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03146, over 971959.47 frames.], batch size: 20, lr: 1.80e-04
+2022-05-07 12:14:16,804 INFO [train.py:715] (3/8) Epoch 12, batch 20350, loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03062, over 4821.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03142, over 972509.76 frames.], batch size: 15, lr: 1.80e-04
+2022-05-07 12:14:56,468 INFO [train.py:715] (3/8) Epoch 12, batch 20400, loss[loss=0.1455, simple_loss=0.2217, pruned_loss=0.03461, over 4824.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03166, over 971634.02 frames.], batch size: 26, lr: 1.80e-04
+2022-05-07 12:15:36,231 INFO [train.py:715] (3/8) Epoch 12, batch 20450, loss[loss=0.1231, simple_loss=0.202, pruned_loss=0.02216, over 4943.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03232, over 971613.99 frames.], batch size: 21, lr: 1.80e-04
+2022-05-07 12:16:15,879 INFO [train.py:715] (3/8) Epoch 12, batch 20500, loss[loss=0.1372, simple_loss=0.2084, pruned_loss=0.03296, over 4915.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03198, over 972359.67 frames.], batch size: 17, lr: 1.80e-04
+2022-05-07 12:16:56,323 INFO [train.py:715] (3/8) Epoch 12, batch 20550, loss[loss=0.1253, simple_loss=0.2036, pruned_loss=0.02347, over 4914.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03212, over 972175.42 frames.], batch size: 17, lr: 1.80e-04
+2022-05-07 12:17:36,240 INFO [train.py:715] (3/8) Epoch 12, batch 20600, loss[loss=0.1244, simple_loss=0.1951, pruned_loss=0.02679, over 4943.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03231, over 971988.30 frames.], batch size: 21, lr: 1.80e-04
+2022-05-07 12:18:15,189 INFO [train.py:715] (3/8) Epoch 12, batch 20650, loss[loss=0.1129, simple_loss=0.1851, pruned_loss=0.0203, over 4987.00 frames.], tot_loss[loss=0.1383, simple_loss=0.212, pruned_loss=0.03232, over 972902.10 frames.], batch size: 14, lr: 1.80e-04
+2022-05-07 12:18:54,298 INFO [train.py:715] (3/8) Epoch 12, batch 20700, loss[loss=0.1317, simple_loss=0.2077, pruned_loss=0.02779, over 4810.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.03156, over 972742.62 frames.], batch size: 24, lr: 1.80e-04
+2022-05-07 12:19:32,273 INFO [train.py:715] (3/8) Epoch 12, batch 20750, loss[loss=0.1258, simple_loss=0.1888, pruned_loss=0.03143, over 4991.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03137, over 972730.14 frames.], batch size: 16, lr: 1.80e-04
+2022-05-07 12:20:10,575 INFO [train.py:715] (3/8) Epoch 12, batch 20800, loss[loss=0.1523, simple_loss=0.2177, pruned_loss=0.04349, over 4910.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03182, over 972860.05 frames.], batch size: 18, lr: 1.80e-04
+2022-05-07 12:20:48,328 INFO [train.py:715] (3/8) Epoch 12, batch 20850, loss[loss=0.1438, simple_loss=0.2171, pruned_loss=0.03526, over 4777.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03255, over 972250.57 frames.], batch size: 18, lr: 1.80e-04
+2022-05-07 12:21:26,468 INFO [train.py:715] (3/8) Epoch 12, batch 20900, loss[loss=0.142, simple_loss=0.2284, pruned_loss=0.02781, over 4990.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03206, over 972075.53 frames.], batch size: 28, lr: 1.80e-04
+2022-05-07 12:22:04,012 INFO [train.py:715] (3/8) Epoch 12, batch 20950, loss[loss=0.1353, simple_loss=0.2079, pruned_loss=0.03136, over 4916.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03203, over 972588.68 frames.], batch size: 29, lr: 1.80e-04
+2022-05-07 12:22:41,375 INFO [train.py:715] (3/8) Epoch 12, batch 21000, loss[loss=0.1064, simple_loss=0.1786, pruned_loss=0.01708, over 4924.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.0319, over 973636.86 frames.], batch size: 29, lr: 1.80e-04
+2022-05-07 12:22:41,375 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 12:22:50,899 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.1056, simple_loss=0.1896, pruned_loss=0.01081, over 914524.00 frames.
+2022-05-07 12:23:28,722 INFO [train.py:715] (3/8) Epoch 12, batch 21050, loss[loss=0.1541, simple_loss=0.2143, pruned_loss=0.04689, over 4861.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03194, over 973459.80 frames.], batch size: 32, lr: 1.80e-04
+2022-05-07 12:24:06,827 INFO [train.py:715] (3/8) Epoch 12, batch 21100, loss[loss=0.1292, simple_loss=0.1911, pruned_loss=0.03365, over 4843.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03166, over 973133.63 frames.], batch size: 32, lr: 1.80e-04
+2022-05-07 12:24:44,628 INFO [train.py:715] (3/8) Epoch 12, batch 21150, loss[loss=0.1162, simple_loss=0.1912, pruned_loss=0.02061, over 4783.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03221, over 973208.57 frames.], batch size: 14, lr: 1.80e-04
+2022-05-07 12:25:22,419 INFO [train.py:715] (3/8) Epoch 12, batch 21200, loss[loss=0.1261, simple_loss=0.2012, pruned_loss=0.02551, over 4918.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03194, over 973167.13 frames.], batch size: 17, lr: 1.80e-04
+2022-05-07 12:26:00,693 INFO [train.py:715] (3/8) Epoch 12, batch 21250, loss[loss=0.1279, simple_loss=0.2046, pruned_loss=0.02563, over 4774.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03147, over 972852.57 frames.], batch size: 18, lr: 1.80e-04
+2022-05-07 12:26:39,510 INFO [train.py:715] (3/8) Epoch 12, batch 21300, loss[loss=0.1273, simple_loss=0.1966, pruned_loss=0.02899, over 4918.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.03151, over 973032.15 frames.], batch size: 29, lr: 1.80e-04
+2022-05-07 12:27:17,265 INFO [train.py:715] (3/8) Epoch 12, batch 21350, loss[loss=0.1337, simple_loss=0.2044, pruned_loss=0.03148, over 4789.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.0313, over 973248.22 frames.], batch size: 14, lr: 1.80e-04
+2022-05-07 12:27:56,358 INFO [train.py:715] (3/8) Epoch 12, batch 21400, loss[loss=0.1366, simple_loss=0.2143, pruned_loss=0.02948, over 4703.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2099, pruned_loss=0.0308, over 971741.19 frames.], batch size: 15, lr: 1.80e-04
+2022-05-07 12:28:35,913 INFO [train.py:715] (3/8) Epoch 12, batch 21450, loss[loss=0.1489, simple_loss=0.2205, pruned_loss=0.03868, over 4783.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03164, over 971872.52 frames.], batch size: 17, lr: 1.80e-04
+2022-05-07 12:29:14,511 INFO [train.py:715] (3/8) Epoch 12, batch 21500, loss[loss=0.1364, simple_loss=0.204, pruned_loss=0.03445, over 4913.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03164, over 971132.90 frames.], batch size: 17, lr: 1.80e-04
+2022-05-07 12:29:53,099 INFO [train.py:715] (3/8) Epoch 12, batch 21550, loss[loss=0.1675, simple_loss=0.2458, pruned_loss=0.04459, over 4691.00 frames.], tot_loss[loss=0.1359, simple_loss=0.209, pruned_loss=0.03134, over 971558.20 frames.], batch size: 15, lr: 1.80e-04
+2022-05-07 12:30:31,274 INFO [train.py:715] (3/8) Epoch 12, batch 21600, loss[loss=0.1264, simple_loss=0.206, pruned_loss=0.02344, over 4795.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03137, over 971644.38 frames.], batch size: 24, lr: 1.80e-04
+2022-05-07 12:31:09,733 INFO [train.py:715] (3/8) Epoch 12, batch 21650, loss[loss=0.1225, simple_loss=0.2009, pruned_loss=0.02204, over 4941.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03156, over 972091.16 frames.], batch size: 29, lr: 1.80e-04
+2022-05-07 12:31:46,934 INFO [train.py:715] (3/8) Epoch 12, batch 21700, loss[loss=0.1229, simple_loss=0.1963, pruned_loss=0.02478, over 4896.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03176, over 971640.07 frames.], batch size: 19, lr: 1.80e-04
+2022-05-07 12:32:25,496 INFO [train.py:715] (3/8) Epoch 12, batch 21750, loss[loss=0.1118, simple_loss=0.186, pruned_loss=0.01881, over 4869.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03188, over 972079.64 frames.], batch size: 16, lr: 1.80e-04
+2022-05-07 12:33:04,220 INFO [train.py:715] (3/8) Epoch 12, batch 21800, loss[loss=0.1362, simple_loss=0.2087, pruned_loss=0.03181, over 4861.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03166, over 972546.90 frames.], batch size: 34, lr: 1.80e-04
+2022-05-07 12:33:42,111 INFO [train.py:715] (3/8) Epoch 12, batch 21850, loss[loss=0.1446, simple_loss=0.2116, pruned_loss=0.03877, over 4981.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03125, over 972926.92 frames.], batch size: 14, lr: 1.80e-04
+2022-05-07 12:34:19,728 INFO [train.py:715] (3/8) Epoch 12, batch 21900, loss[loss=0.1485, simple_loss=0.2161, pruned_loss=0.04048, over 4911.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03173, over 973097.12 frames.], batch size: 17, lr: 1.80e-04
+2022-05-07 12:34:58,474 INFO [train.py:715] (3/8) Epoch 12, batch 21950, loss[loss=0.1207, simple_loss=0.2047, pruned_loss=0.01839, over 4880.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03111, over 971662.59 frames.], batch size: 20, lr: 1.80e-04
+2022-05-07 12:35:37,477 INFO [train.py:715] (3/8) Epoch 12, batch 22000, loss[loss=0.1701, simple_loss=0.2366, pruned_loss=0.05183, over 4973.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03127, over 972764.67 frames.], batch size: 15, lr: 1.80e-04
+2022-05-07 12:36:15,711 INFO [train.py:715] (3/8) Epoch 12, batch 22050, loss[loss=0.1197, simple_loss=0.1941, pruned_loss=0.0227, over 4853.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2086, pruned_loss=0.03129, over 972876.74 frames.], batch size: 13, lr: 1.80e-04
+2022-05-07 12:36:54,704 INFO [train.py:715] (3/8) Epoch 12, batch 22100, loss[loss=0.1369, simple_loss=0.2247, pruned_loss=0.02457, over 4886.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2097, pruned_loss=0.03159, over 973180.01 frames.], batch size: 22, lr: 1.80e-04
+2022-05-07 12:37:33,660 INFO [train.py:715] (3/8) Epoch 12, batch 22150, loss[loss=0.1263, simple_loss=0.2072, pruned_loss=0.02272, over 4797.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2087, pruned_loss=0.03125, over 972444.88 frames.], batch size: 21, lr: 1.80e-04
+2022-05-07 12:38:11,934 INFO [train.py:715] (3/8) Epoch 12, batch 22200, loss[loss=0.1289, simple_loss=0.2017, pruned_loss=0.02805, over 4731.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03101, over 972299.33 frames.], batch size: 16, lr: 1.80e-04
+2022-05-07 12:38:49,699 INFO [train.py:715] (3/8) Epoch 12, batch 22250, loss[loss=0.1478, simple_loss=0.2215, pruned_loss=0.03704, over 4815.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03123, over 973085.89 frames.], batch size: 15, lr: 1.80e-04
+2022-05-07 12:39:30,403 INFO [train.py:715] (3/8) Epoch 12, batch 22300, loss[loss=0.1417, simple_loss=0.2109, pruned_loss=0.03623, over 4877.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03136, over 972689.96 frames.], batch size: 30, lr: 1.80e-04
+2022-05-07 12:40:08,652 INFO [train.py:715] (3/8) Epoch 12, batch 22350, loss[loss=0.1227, simple_loss=0.2051, pruned_loss=0.02022, over 4959.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03086, over 973166.98 frames.], batch size: 24, lr: 1.80e-04
+2022-05-07 12:40:46,759 INFO [train.py:715] (3/8) Epoch 12, batch 22400, loss[loss=0.1306, simple_loss=0.2063, pruned_loss=0.0275, over 4799.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03107, over 972531.82 frames.], batch size: 21, lr: 1.80e-04
+2022-05-07 12:41:25,341 INFO [train.py:715] (3/8) Epoch 12, batch 22450, loss[loss=0.1372, simple_loss=0.2211, pruned_loss=0.02668, over 4873.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03116, over 972001.27 frames.], batch size: 16, lr: 1.80e-04
+2022-05-07 12:42:03,781 INFO [train.py:715] (3/8) Epoch 12, batch 22500, loss[loss=0.09908, simple_loss=0.1628, pruned_loss=0.01766, over 4804.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03103, over 972064.98 frames.], batch size: 12, lr: 1.80e-04
+2022-05-07 12:42:42,487 INFO [train.py:715] (3/8) Epoch 12, batch 22550, loss[loss=0.1393, simple_loss=0.2137, pruned_loss=0.03242, over 4748.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03115, over 971434.12 frames.], batch size: 19, lr: 1.80e-04
+2022-05-07 12:43:20,635 INFO [train.py:715] (3/8) Epoch 12, batch 22600, loss[loss=0.1237, simple_loss=0.2105, pruned_loss=0.01845, over 4799.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03132, over 971337.12 frames.], batch size: 14, lr: 1.80e-04
+2022-05-07 12:43:58,690 INFO [train.py:715] (3/8) Epoch 12, batch 22650, loss[loss=0.1564, simple_loss=0.2271, pruned_loss=0.04283, over 4987.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03153, over 971211.04 frames.], batch size: 31, lr: 1.80e-04
+2022-05-07 12:44:36,594 INFO [train.py:715] (3/8) Epoch 12, batch 22700, loss[loss=0.1675, simple_loss=0.2404, pruned_loss=0.04732, over 4972.00 frames.], tot_loss[loss=0.137, simple_loss=0.2099, pruned_loss=0.03199, over 971995.45 frames.], batch size: 35, lr: 1.80e-04
+2022-05-07 12:45:14,816 INFO [train.py:715] (3/8) Epoch 12, batch 22750, loss[loss=0.1382, simple_loss=0.22, pruned_loss=0.0282, over 4948.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03195, over 971317.94 frames.], batch size: 21, lr: 1.80e-04
+2022-05-07 12:45:53,320 INFO [train.py:715] (3/8) Epoch 12, batch 22800, loss[loss=0.1227, simple_loss=0.1985, pruned_loss=0.02344, over 4794.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03221, over 970678.84 frames.], batch size: 21, lr: 1.80e-04
+2022-05-07 12:46:32,313 INFO [train.py:715] (3/8) Epoch 12, batch 22850, loss[loss=0.1487, simple_loss=0.2142, pruned_loss=0.04155, over 4851.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03235, over 971645.48 frames.], batch size: 30, lr: 1.80e-04
+2022-05-07 12:47:10,525 INFO [train.py:715] (3/8) Epoch 12, batch 22900, loss[loss=0.1196, simple_loss=0.195, pruned_loss=0.0221, over 4822.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.03261, over 971171.17 frames.], batch size: 13, lr: 1.80e-04
+2022-05-07 12:47:48,404 INFO [train.py:715] (3/8) Epoch 12, batch 22950, loss[loss=0.1428, simple_loss=0.2196, pruned_loss=0.03296, over 4979.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.03237, over 971773.00 frames.], batch size: 35, lr: 1.80e-04
+2022-05-07 12:48:26,681 INFO [train.py:715] (3/8) Epoch 12, batch 23000, loss[loss=0.1157, simple_loss=0.1958, pruned_loss=0.01779, over 4856.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03213, over 971695.95 frames.], batch size: 32, lr: 1.80e-04
+2022-05-07 12:49:04,950 INFO [train.py:715] (3/8) Epoch 12, batch 23050, loss[loss=0.1404, simple_loss=0.2137, pruned_loss=0.03356, over 4925.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03201, over 971314.57 frames.], batch size: 23, lr: 1.80e-04
+2022-05-07 12:49:43,058 INFO [train.py:715] (3/8) Epoch 12, batch 23100, loss[loss=0.1176, simple_loss=0.1892, pruned_loss=0.02299, over 4768.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03136, over 971758.63 frames.], batch size: 14, lr: 1.80e-04
+2022-05-07 12:50:21,955 INFO [train.py:715] (3/8) Epoch 12, batch 23150, loss[loss=0.1296, simple_loss=0.2033, pruned_loss=0.02799, over 4885.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03141, over 972044.58 frames.], batch size: 16, lr: 1.80e-04
+2022-05-07 12:51:01,024 INFO [train.py:715] (3/8) Epoch 12, batch 23200, loss[loss=0.1615, simple_loss=0.232, pruned_loss=0.0455, over 4806.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03148, over 971773.59 frames.], batch size: 21, lr: 1.80e-04
+2022-05-07 12:51:39,416 INFO [train.py:715] (3/8) Epoch 12, batch 23250, loss[loss=0.1403, simple_loss=0.2141, pruned_loss=0.03323, over 4944.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03194, over 971478.50 frames.], batch size: 21, lr: 1.80e-04
+2022-05-07 12:52:17,110 INFO [train.py:715] (3/8) Epoch 12, batch 23300, loss[loss=0.118, simple_loss=0.1943, pruned_loss=0.02085, over 4868.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2098, pruned_loss=0.03148, over 972118.42 frames.], batch size: 20, lr: 1.80e-04
+2022-05-07 12:52:55,811 INFO [train.py:715] (3/8) Epoch 12, batch 23350, loss[loss=0.138, simple_loss=0.2126, pruned_loss=0.03172, over 4798.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03165, over 972628.35 frames.], batch size: 17, lr: 1.80e-04
+2022-05-07 12:53:33,838 INFO [train.py:715] (3/8) Epoch 12, batch 23400, loss[loss=0.152, simple_loss=0.2241, pruned_loss=0.03992, over 4950.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03228, over 972416.97 frames.], batch size: 15, lr: 1.80e-04
+2022-05-07 12:54:11,387 INFO [train.py:715] (3/8) Epoch 12, batch 23450, loss[loss=0.152, simple_loss=0.2261, pruned_loss=0.03897, over 4918.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03246, over 971599.80 frames.], batch size: 17, lr: 1.80e-04
+2022-05-07 12:54:49,573 INFO [train.py:715] (3/8) Epoch 12, batch 23500, loss[loss=0.1295, simple_loss=0.2111, pruned_loss=0.0239, over 4862.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03223, over 971293.94 frames.], batch size: 20, lr: 1.80e-04
+2022-05-07 12:55:28,412 INFO [train.py:715] (3/8) Epoch 12, batch 23550, loss[loss=0.1218, simple_loss=0.201, pruned_loss=0.02125, over 4816.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03213, over 971008.55 frames.], batch size: 26, lr: 1.80e-04
+2022-05-07 12:56:07,100 INFO [train.py:715] (3/8) Epoch 12, batch 23600, loss[loss=0.1334, simple_loss=0.2093, pruned_loss=0.02874, over 4799.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.0321, over 971152.98 frames.], batch size: 24, lr: 1.80e-04
+2022-05-07 12:56:45,799 INFO [train.py:715] (3/8) Epoch 12, batch 23650, loss[loss=0.1479, simple_loss=0.2223, pruned_loss=0.03675, over 4636.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03222, over 971496.38 frames.], batch size: 13, lr: 1.80e-04
+2022-05-07 12:57:24,210 INFO [train.py:715] (3/8) Epoch 12, batch 23700, loss[loss=0.1208, simple_loss=0.1877, pruned_loss=0.02694, over 4821.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03183, over 971456.92 frames.], batch size: 13, lr: 1.80e-04
+2022-05-07 12:58:02,489 INFO [train.py:715] (3/8) Epoch 12, batch 23750, loss[loss=0.1469, simple_loss=0.2251, pruned_loss=0.03428, over 4746.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2106, pruned_loss=0.03107, over 971336.72 frames.], batch size: 16, lr: 1.80e-04
+2022-05-07 12:58:41,205 INFO [train.py:715] (3/8) Epoch 12, batch 23800, loss[loss=0.13, simple_loss=0.2107, pruned_loss=0.02463, over 4914.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2108, pruned_loss=0.03139, over 971943.35 frames.], batch size: 18, lr: 1.80e-04
+2022-05-07 12:59:20,123 INFO [train.py:715] (3/8) Epoch 12, batch 23850, loss[loss=0.13, simple_loss=0.1985, pruned_loss=0.03076, over 4786.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03142, over 971963.26 frames.], batch size: 14, lr: 1.80e-04
+2022-05-07 12:59:59,700 INFO [train.py:715] (3/8) Epoch 12, batch 23900, loss[loss=0.1463, simple_loss=0.207, pruned_loss=0.04285, over 4914.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.0318, over 972280.84 frames.], batch size: 18, lr: 1.80e-04
+2022-05-07 13:00:39,416 INFO [train.py:715] (3/8) Epoch 12, batch 23950, loss[loss=0.1258, simple_loss=0.211, pruned_loss=0.02027, over 4904.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03166, over 972266.95 frames.], batch size: 18, lr: 1.79e-04
+2022-05-07 13:01:18,265 INFO [train.py:715] (3/8) Epoch 12, batch 24000, loss[loss=0.1387, simple_loss=0.2157, pruned_loss=0.03089, over 4816.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03179, over 972298.29 frames.], batch size: 26, lr: 1.79e-04
+2022-05-07 13:01:18,266 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 13:01:27,802 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.1054, simple_loss=0.1895, pruned_loss=0.01071, over 914524.00 frames.
+2022-05-07 13:02:06,830 INFO [train.py:715] (3/8) Epoch 12, batch 24050, loss[loss=0.1395, simple_loss=0.2027, pruned_loss=0.03815, over 4847.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03124, over 972574.16 frames.], batch size: 30, lr: 1.79e-04
+2022-05-07 13:02:47,353 INFO [train.py:715] (3/8) Epoch 12, batch 24100, loss[loss=0.1317, simple_loss=0.2049, pruned_loss=0.02923, over 4943.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03158, over 972441.41 frames.], batch size: 23, lr: 1.79e-04
+2022-05-07 13:03:27,835 INFO [train.py:715] (3/8) Epoch 12, batch 24150, loss[loss=0.1257, simple_loss=0.2014, pruned_loss=0.02498, over 4945.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03131, over 972997.40 frames.], batch size: 24, lr: 1.79e-04
+2022-05-07 13:04:07,866 INFO [train.py:715] (3/8) Epoch 12, batch 24200, loss[loss=0.1251, simple_loss=0.1974, pruned_loss=0.02643, over 4962.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03078, over 973223.84 frames.], batch size: 14, lr: 1.79e-04
+2022-05-07 13:04:47,989 INFO [train.py:715] (3/8) Epoch 12, batch 24250, loss[loss=0.1447, simple_loss=0.2154, pruned_loss=0.03703, over 4852.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03094, over 972136.59 frames.], batch size: 30, lr: 1.79e-04
+2022-05-07 13:05:28,029 INFO [train.py:715] (3/8) Epoch 12, batch 24300, loss[loss=0.1511, simple_loss=0.2224, pruned_loss=0.03989, over 4841.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03117, over 972078.64 frames.], batch size: 15, lr: 1.79e-04
+2022-05-07 13:06:07,758 INFO [train.py:715] (3/8) Epoch 12, batch 24350, loss[loss=0.151, simple_loss=0.2251, pruned_loss=0.03845, over 4807.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03178, over 972784.20 frames.], batch size: 21, lr: 1.79e-04
+2022-05-07 13:06:47,581 INFO [train.py:715] (3/8) Epoch 12, batch 24400, loss[loss=0.122, simple_loss=0.2013, pruned_loss=0.02135, over 4764.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.0317, over 973757.39 frames.], batch size: 18, lr: 1.79e-04
+2022-05-07 13:07:27,540 INFO [train.py:715] (3/8) Epoch 12, batch 24450, loss[loss=0.1302, simple_loss=0.209, pruned_loss=0.02575, over 4785.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03163, over 973839.66 frames.], batch size: 14, lr: 1.79e-04
+2022-05-07 13:08:07,313 INFO [train.py:715] (3/8) Epoch 12, batch 24500, loss[loss=0.1151, simple_loss=0.1946, pruned_loss=0.01782, over 4922.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.0318, over 973530.77 frames.], batch size: 18, lr: 1.79e-04
+2022-05-07 13:08:46,556 INFO [train.py:715] (3/8) Epoch 12, batch 24550, loss[loss=0.1094, simple_loss=0.1823, pruned_loss=0.01824, over 4835.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03194, over 972775.31 frames.], batch size: 13, lr: 1.79e-04
+2022-05-07 13:09:26,205 INFO [train.py:715] (3/8) Epoch 12, batch 24600, loss[loss=0.1452, simple_loss=0.2103, pruned_loss=0.04002, over 4782.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.0323, over 972499.52 frames.], batch size: 18, lr: 1.79e-04
+2022-05-07 13:10:05,928 INFO [train.py:715] (3/8) Epoch 12, batch 24650, loss[loss=0.1415, simple_loss=0.2182, pruned_loss=0.03242, over 4948.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.0315, over 972590.59 frames.], batch size: 21, lr: 1.79e-04
+2022-05-07 13:10:45,628 INFO [train.py:715] (3/8) Epoch 12, batch 24700, loss[loss=0.133, simple_loss=0.203, pruned_loss=0.03148, over 4941.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03184, over 973728.27 frames.], batch size: 21, lr: 1.79e-04
+2022-05-07 13:11:24,795 INFO [train.py:715] (3/8) Epoch 12, batch 24750, loss[loss=0.1144, simple_loss=0.1878, pruned_loss=0.02054, over 4864.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03143, over 973284.46 frames.], batch size: 12, lr: 1.79e-04
+2022-05-07 13:12:05,001 INFO [train.py:715] (3/8) Epoch 12, batch 24800, loss[loss=0.1637, simple_loss=0.2467, pruned_loss=0.04034, over 4801.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03173, over 973642.96 frames.], batch size: 14, lr: 1.79e-04
+2022-05-07 13:12:44,866 INFO [train.py:715] (3/8) Epoch 12, batch 24850, loss[loss=0.167, simple_loss=0.2325, pruned_loss=0.05077, over 4781.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.0316, over 972783.41 frames.], batch size: 18, lr: 1.79e-04
+2022-05-07 13:13:24,114 INFO [train.py:715] (3/8) Epoch 12, batch 24900, loss[loss=0.1117, simple_loss=0.1857, pruned_loss=0.01889, over 4936.00 frames.], tot_loss[loss=0.1358, simple_loss=0.21, pruned_loss=0.03084, over 972903.74 frames.], batch size: 29, lr: 1.79e-04
+2022-05-07 13:14:03,442 INFO [train.py:715] (3/8) Epoch 12, batch 24950, loss[loss=0.1168, simple_loss=0.199, pruned_loss=0.01729, over 4716.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03096, over 973008.73 frames.], batch size: 15, lr: 1.79e-04
+2022-05-07 13:14:42,358 INFO [train.py:715] (3/8) Epoch 12, batch 25000, loss[loss=0.1401, simple_loss=0.219, pruned_loss=0.03062, over 4988.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03133, over 971949.02 frames.], batch size: 25, lr: 1.79e-04
+2022-05-07 13:15:20,412 INFO [train.py:715] (3/8) Epoch 12, batch 25050, loss[loss=0.1675, simple_loss=0.2431, pruned_loss=0.04592, over 4950.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03102, over 972491.58 frames.], batch size: 21, lr: 1.79e-04
+2022-05-07 13:15:58,462 INFO [train.py:715] (3/8) Epoch 12, batch 25100, loss[loss=0.1145, simple_loss=0.1863, pruned_loss=0.02131, over 4920.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03139, over 973246.55 frames.], batch size: 21, lr: 1.79e-04
+2022-05-07 13:16:36,854 INFO [train.py:715] (3/8) Epoch 12, batch 25150, loss[loss=0.1403, simple_loss=0.2071, pruned_loss=0.03675, over 4954.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.03184, over 972564.87 frames.], batch size: 21, lr: 1.79e-04
+2022-05-07 13:17:15,107 INFO [train.py:715] (3/8) Epoch 12, batch 25200, loss[loss=0.1323, simple_loss=0.1991, pruned_loss=0.0327, over 4840.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03198, over 972926.68 frames.], batch size: 30, lr: 1.79e-04
+2022-05-07 13:17:52,725 INFO [train.py:715] (3/8) Epoch 12, batch 25250, loss[loss=0.1369, simple_loss=0.2046, pruned_loss=0.03461, over 4928.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03224, over 973047.78 frames.], batch size: 29, lr: 1.79e-04
+2022-05-07 13:18:30,736 INFO [train.py:715] (3/8) Epoch 12, batch 25300, loss[loss=0.1279, simple_loss=0.1978, pruned_loss=0.02899, over 4805.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03244, over 973725.02 frames.], batch size: 13, lr: 1.79e-04
+2022-05-07 13:19:08,817 INFO [train.py:715] (3/8) Epoch 12, batch 25350, loss[loss=0.1203, simple_loss=0.1984, pruned_loss=0.02114, over 4793.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03251, over 972812.42 frames.], batch size: 24, lr: 1.79e-04
+2022-05-07 13:19:47,791 INFO [train.py:715] (3/8) Epoch 12, batch 25400, loss[loss=0.1606, simple_loss=0.2312, pruned_loss=0.045, over 4979.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03286, over 972568.92 frames.], batch size: 24, lr: 1.79e-04
+2022-05-07 13:20:26,681 INFO [train.py:715] (3/8) Epoch 12, batch 25450, loss[loss=0.1509, simple_loss=0.2364, pruned_loss=0.03263, over 4975.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03259, over 973361.90 frames.], batch size: 24, lr: 1.79e-04
+2022-05-07 13:21:06,564 INFO [train.py:715] (3/8) Epoch 12, batch 25500, loss[loss=0.1402, simple_loss=0.2136, pruned_loss=0.03346, over 4966.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03241, over 973365.86 frames.], batch size: 24, lr: 1.79e-04
+2022-05-07 13:21:45,632 INFO [train.py:715] (3/8) Epoch 12, batch 25550, loss[loss=0.1522, simple_loss=0.2131, pruned_loss=0.04568, over 4841.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03248, over 973625.24 frames.], batch size: 32, lr: 1.79e-04
+2022-05-07 13:22:23,735 INFO [train.py:715] (3/8) Epoch 12, batch 25600, loss[loss=0.1228, simple_loss=0.1988, pruned_loss=0.02342, over 4929.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03217, over 973106.99 frames.], batch size: 29, lr: 1.79e-04
+2022-05-07 13:23:02,065 INFO [train.py:715] (3/8) Epoch 12, batch 25650, loss[loss=0.1306, simple_loss=0.2044, pruned_loss=0.02841, over 4756.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.0315, over 974046.70 frames.], batch size: 16, lr: 1.79e-04
+2022-05-07 13:23:40,758 INFO [train.py:715] (3/8) Epoch 12, batch 25700, loss[loss=0.1494, simple_loss=0.229, pruned_loss=0.03492, over 4877.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2104, pruned_loss=0.0311, over 973232.26 frames.], batch size: 22, lr: 1.79e-04
+2022-05-07 13:24:19,543 INFO [train.py:715] (3/8) Epoch 12, batch 25750, loss[loss=0.1308, simple_loss=0.2045, pruned_loss=0.02854, over 4984.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03138, over 972547.97 frames.], batch size: 28, lr: 1.79e-04
+2022-05-07 13:24:58,009 INFO [train.py:715] (3/8) Epoch 12, batch 25800, loss[loss=0.1126, simple_loss=0.1801, pruned_loss=0.02255, over 4880.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03152, over 971908.41 frames.], batch size: 20, lr: 1.79e-04
+2022-05-07 13:25:36,921 INFO [train.py:715] (3/8) Epoch 12, batch 25850, loss[loss=0.1169, simple_loss=0.1956, pruned_loss=0.01908, over 4825.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03153, over 970596.35 frames.], batch size: 26, lr: 1.79e-04
+2022-05-07 13:26:15,480 INFO [train.py:715] (3/8) Epoch 12, batch 25900, loss[loss=0.1293, simple_loss=0.2011, pruned_loss=0.02879, over 4808.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03147, over 970803.02 frames.], batch size: 25, lr: 1.79e-04
+2022-05-07 13:26:53,772 INFO [train.py:715] (3/8) Epoch 12, batch 25950, loss[loss=0.1139, simple_loss=0.1911, pruned_loss=0.01836, over 4783.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03146, over 971059.86 frames.], batch size: 18, lr: 1.79e-04
+2022-05-07 13:27:31,255 INFO [train.py:715] (3/8) Epoch 12, batch 26000, loss[loss=0.1555, simple_loss=0.2223, pruned_loss=0.04438, over 4782.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.0317, over 971920.69 frames.], batch size: 14, lr: 1.79e-04
+2022-05-07 13:28:09,532 INFO [train.py:715] (3/8) Epoch 12, batch 26050, loss[loss=0.143, simple_loss=0.209, pruned_loss=0.03851, over 4832.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03158, over 971127.55 frames.], batch size: 15, lr: 1.79e-04
+2022-05-07 13:28:48,386 INFO [train.py:715] (3/8) Epoch 12, batch 26100, loss[loss=0.1181, simple_loss=0.1991, pruned_loss=0.01856, over 4830.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.0317, over 970839.61 frames.], batch size: 27, lr: 1.79e-04
+2022-05-07 13:29:27,201 INFO [train.py:715] (3/8) Epoch 12, batch 26150, loss[loss=0.1732, simple_loss=0.2422, pruned_loss=0.05209, over 4872.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03155, over 970450.67 frames.], batch size: 16, lr: 1.79e-04
+2022-05-07 13:30:06,153 INFO [train.py:715] (3/8) Epoch 12, batch 26200, loss[loss=0.1434, simple_loss=0.2136, pruned_loss=0.03658, over 4774.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03172, over 970095.17 frames.], batch size: 18, lr: 1.79e-04
+2022-05-07 13:30:44,508 INFO [train.py:715] (3/8) Epoch 12, batch 26250, loss[loss=0.1217, simple_loss=0.2013, pruned_loss=0.02104, over 4744.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03133, over 971353.71 frames.], batch size: 19, lr: 1.79e-04
+2022-05-07 13:31:23,012 INFO [train.py:715] (3/8) Epoch 12, batch 26300, loss[loss=0.1486, simple_loss=0.2238, pruned_loss=0.03668, over 4649.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03183, over 971423.90 frames.], batch size: 13, lr: 1.79e-04
+2022-05-07 13:32:02,154 INFO [train.py:715] (3/8) Epoch 12, batch 26350, loss[loss=0.1399, simple_loss=0.2085, pruned_loss=0.03565, over 4927.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.0317, over 970967.97 frames.], batch size: 21, lr: 1.79e-04
+2022-05-07 13:32:40,221 INFO [train.py:715] (3/8) Epoch 12, batch 26400, loss[loss=0.1155, simple_loss=0.1915, pruned_loss=0.01978, over 4761.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03192, over 971802.86 frames.], batch size: 19, lr: 1.79e-04
+2022-05-07 13:33:18,355 INFO [train.py:715] (3/8) Epoch 12, batch 26450, loss[loss=0.1554, simple_loss=0.2264, pruned_loss=0.04222, over 4939.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03196, over 972806.35 frames.], batch size: 21, lr: 1.79e-04
+2022-05-07 13:33:56,291 INFO [train.py:715] (3/8) Epoch 12, batch 26500, loss[loss=0.1141, simple_loss=0.189, pruned_loss=0.0196, over 4979.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03156, over 972368.34 frames.], batch size: 28, lr: 1.79e-04
+2022-05-07 13:34:34,591 INFO [train.py:715] (3/8) Epoch 12, batch 26550, loss[loss=0.1321, simple_loss=0.2113, pruned_loss=0.02646, over 4815.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03188, over 972070.52 frames.], batch size: 25, lr: 1.79e-04
+2022-05-07 13:35:12,934 INFO [train.py:715] (3/8) Epoch 12, batch 26600, loss[loss=0.1551, simple_loss=0.2331, pruned_loss=0.03855, over 4810.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03158, over 972041.04 frames.], batch size: 25, lr: 1.79e-04
+2022-05-07 13:35:51,456 INFO [train.py:715] (3/8) Epoch 12, batch 26650, loss[loss=0.1381, simple_loss=0.2071, pruned_loss=0.03458, over 4863.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03155, over 971680.94 frames.], batch size: 32, lr: 1.79e-04
+2022-05-07 13:36:30,042 INFO [train.py:715] (3/8) Epoch 12, batch 26700, loss[loss=0.1662, simple_loss=0.2373, pruned_loss=0.04748, over 4834.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03243, over 971518.40 frames.], batch size: 30, lr: 1.79e-04
+2022-05-07 13:37:08,437 INFO [train.py:715] (3/8) Epoch 12, batch 26750, loss[loss=0.1304, simple_loss=0.2036, pruned_loss=0.02867, over 4814.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03211, over 972025.78 frames.], batch size: 25, lr: 1.79e-04
+2022-05-07 13:37:47,908 INFO [train.py:715] (3/8) Epoch 12, batch 26800, loss[loss=0.135, simple_loss=0.2165, pruned_loss=0.02674, over 4933.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2122, pruned_loss=0.03271, over 972451.11 frames.], batch size: 29, lr: 1.79e-04
+2022-05-07 13:38:27,723 INFO [train.py:715] (3/8) Epoch 12, batch 26850, loss[loss=0.1374, simple_loss=0.2125, pruned_loss=0.03111, over 4851.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2123, pruned_loss=0.03255, over 973570.77 frames.], batch size: 32, lr: 1.79e-04
+2022-05-07 13:39:07,107 INFO [train.py:715] (3/8) Epoch 12, batch 26900, loss[loss=0.1169, simple_loss=0.2, pruned_loss=0.01686, over 4776.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.0321, over 973051.44 frames.], batch size: 18, lr: 1.79e-04
+2022-05-07 13:39:45,936 INFO [train.py:715] (3/8) Epoch 12, batch 26950, loss[loss=0.1418, simple_loss=0.2218, pruned_loss=0.03094, over 4769.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2117, pruned_loss=0.03208, over 973396.23 frames.], batch size: 18, lr: 1.79e-04
+2022-05-07 13:40:25,470 INFO [train.py:715] (3/8) Epoch 12, batch 27000, loss[loss=0.1412, simple_loss=0.222, pruned_loss=0.03025, over 4936.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2119, pruned_loss=0.03224, over 974083.02 frames.], batch size: 39, lr: 1.79e-04
+2022-05-07 13:40:25,471 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 13:40:37,911 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.1054, simple_loss=0.1894, pruned_loss=0.01072, over 914524.00 frames.
+2022-05-07 13:41:17,235 INFO [train.py:715] (3/8) Epoch 12, batch 27050, loss[loss=0.1583, simple_loss=0.2314, pruned_loss=0.04261, over 4779.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03216, over 973152.57 frames.], batch size: 14, lr: 1.79e-04
+2022-05-07 13:41:55,463 INFO [train.py:715] (3/8) Epoch 12, batch 27100, loss[loss=0.1152, simple_loss=0.1886, pruned_loss=0.02085, over 4941.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03222, over 972866.39 frames.], batch size: 23, lr: 1.79e-04
+2022-05-07 13:42:33,820 INFO [train.py:715] (3/8) Epoch 12, batch 27150, loss[loss=0.1274, simple_loss=0.2089, pruned_loss=0.02294, over 4815.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03241, over 973135.36 frames.], batch size: 26, lr: 1.79e-04
+2022-05-07 13:43:12,676 INFO [train.py:715] (3/8) Epoch 12, batch 27200, loss[loss=0.1117, simple_loss=0.1834, pruned_loss=0.01999, over 4835.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03238, over 973402.73 frames.], batch size: 30, lr: 1.79e-04
+2022-05-07 13:43:50,976 INFO [train.py:715] (3/8) Epoch 12, batch 27250, loss[loss=0.1421, simple_loss=0.2116, pruned_loss=0.03629, over 4761.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03247, over 972779.52 frames.], batch size: 16, lr: 1.79e-04
+2022-05-07 13:44:29,601 INFO [train.py:715] (3/8) Epoch 12, batch 27300, loss[loss=0.134, simple_loss=0.2164, pruned_loss=0.02584, over 4840.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03247, over 972686.79 frames.], batch size: 30, lr: 1.79e-04
+2022-05-07 13:45:08,185 INFO [train.py:715] (3/8) Epoch 12, batch 27350, loss[loss=0.1481, simple_loss=0.2094, pruned_loss=0.04338, over 4883.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2104, pruned_loss=0.03216, over 973162.82 frames.], batch size: 22, lr: 1.79e-04
+2022-05-07 13:45:47,173 INFO [train.py:715] (3/8) Epoch 12, batch 27400, loss[loss=0.1221, simple_loss=0.1926, pruned_loss=0.02584, over 4889.00 frames.], tot_loss[loss=0.1368, simple_loss=0.21, pruned_loss=0.03183, over 973776.46 frames.], batch size: 19, lr: 1.79e-04
+2022-05-07 13:46:25,848 INFO [train.py:715] (3/8) Epoch 12, batch 27450, loss[loss=0.1347, simple_loss=0.1955, pruned_loss=0.03697, over 4985.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2102, pruned_loss=0.03223, over 973015.28 frames.], batch size: 26, lr: 1.79e-04
+2022-05-07 13:47:04,346 INFO [train.py:715] (3/8) Epoch 12, batch 27500, loss[loss=0.171, simple_loss=0.2384, pruned_loss=0.05183, over 4844.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.0322, over 973261.22 frames.], batch size: 15, lr: 1.79e-04
+2022-05-07 13:47:43,119 INFO [train.py:715] (3/8) Epoch 12, batch 27550, loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.03004, over 4827.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2097, pruned_loss=0.03194, over 972368.88 frames.], batch size: 27, lr: 1.79e-04
+2022-05-07 13:48:21,800 INFO [train.py:715] (3/8) Epoch 12, batch 27600, loss[loss=0.1115, simple_loss=0.1835, pruned_loss=0.01971, over 4792.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03203, over 971549.44 frames.], batch size: 12, lr: 1.79e-04
+2022-05-07 13:49:00,949 INFO [train.py:715] (3/8) Epoch 12, batch 27650, loss[loss=0.1295, simple_loss=0.2015, pruned_loss=0.02873, over 4849.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03232, over 971760.47 frames.], batch size: 15, lr: 1.79e-04
+2022-05-07 13:49:39,560 INFO [train.py:715] (3/8) Epoch 12, batch 27700, loss[loss=0.1308, simple_loss=0.2048, pruned_loss=0.0284, over 4755.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03182, over 971661.82 frames.], batch size: 16, lr: 1.79e-04
+2022-05-07 13:50:18,424 INFO [train.py:715] (3/8) Epoch 12, batch 27750, loss[loss=0.1363, simple_loss=0.2194, pruned_loss=0.02662, over 4790.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03153, over 971476.81 frames.], batch size: 14, lr: 1.79e-04
+2022-05-07 13:50:56,329 INFO [train.py:715] (3/8) Epoch 12, batch 27800, loss[loss=0.1286, simple_loss=0.209, pruned_loss=0.0241, over 4823.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03154, over 972158.40 frames.], batch size: 26, lr: 1.79e-04
+2022-05-07 13:51:34,004 INFO [train.py:715] (3/8) Epoch 12, batch 27850, loss[loss=0.1194, simple_loss=0.1996, pruned_loss=0.0196, over 4753.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03217, over 971673.40 frames.], batch size: 16, lr: 1.79e-04
+2022-05-07 13:52:12,421 INFO [train.py:715] (3/8) Epoch 12, batch 27900, loss[loss=0.1352, simple_loss=0.204, pruned_loss=0.03318, over 4890.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03184, over 972092.18 frames.], batch size: 22, lr: 1.79e-04
+2022-05-07 13:52:50,386 INFO [train.py:715] (3/8) Epoch 12, batch 27950, loss[loss=0.1309, simple_loss=0.1969, pruned_loss=0.03244, over 4692.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03125, over 972844.88 frames.], batch size: 15, lr: 1.79e-04
+2022-05-07 13:53:28,678 INFO [train.py:715] (3/8) Epoch 12, batch 28000, loss[loss=0.117, simple_loss=0.1862, pruned_loss=0.02389, over 4923.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03143, over 972634.51 frames.], batch size: 18, lr: 1.79e-04
+2022-05-07 13:54:06,333 INFO [train.py:715] (3/8) Epoch 12, batch 28050, loss[loss=0.1637, simple_loss=0.2212, pruned_loss=0.05314, over 4854.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03142, over 972509.99 frames.], batch size: 32, lr: 1.79e-04
+2022-05-07 13:54:44,518 INFO [train.py:715] (3/8) Epoch 12, batch 28100, loss[loss=0.1491, simple_loss=0.2276, pruned_loss=0.03537, over 4919.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.0317, over 972236.07 frames.], batch size: 23, lr: 1.79e-04
+2022-05-07 13:55:22,258 INFO [train.py:715] (3/8) Epoch 12, batch 28150, loss[loss=0.1617, simple_loss=0.2394, pruned_loss=0.042, over 4775.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2116, pruned_loss=0.03193, over 972178.14 frames.], batch size: 17, lr: 1.79e-04
+2022-05-07 13:56:00,659 INFO [train.py:715] (3/8) Epoch 12, batch 28200, loss[loss=0.1128, simple_loss=0.1799, pruned_loss=0.02288, over 4955.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.03202, over 972514.01 frames.], batch size: 21, lr: 1.79e-04
+2022-05-07 13:56:39,080 INFO [train.py:715] (3/8) Epoch 12, batch 28250, loss[loss=0.1171, simple_loss=0.1974, pruned_loss=0.01842, over 4932.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2117, pruned_loss=0.03197, over 972495.29 frames.], batch size: 29, lr: 1.79e-04
+2022-05-07 13:57:17,045 INFO [train.py:715] (3/8) Epoch 12, batch 28300, loss[loss=0.1305, simple_loss=0.2121, pruned_loss=0.02443, over 4938.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03184, over 972847.59 frames.], batch size: 21, lr: 1.79e-04
+2022-05-07 13:57:55,849 INFO [train.py:715] (3/8) Epoch 12, batch 28350, loss[loss=0.1553, simple_loss=0.2169, pruned_loss=0.04689, over 4827.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03153, over 972559.46 frames.], batch size: 30, lr: 1.79e-04
+2022-05-07 13:58:33,888 INFO [train.py:715] (3/8) Epoch 12, batch 28400, loss[loss=0.1619, simple_loss=0.2395, pruned_loss=0.0422, over 4879.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.0318, over 972158.54 frames.], batch size: 16, lr: 1.79e-04
+2022-05-07 13:59:12,075 INFO [train.py:715] (3/8) Epoch 12, batch 28450, loss[loss=0.1284, simple_loss=0.2018, pruned_loss=0.02754, over 4935.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03171, over 972094.73 frames.], batch size: 29, lr: 1.79e-04
+2022-05-07 13:59:49,933 INFO [train.py:715] (3/8) Epoch 12, batch 28500, loss[loss=0.1269, simple_loss=0.1991, pruned_loss=0.0274, over 4756.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03214, over 971343.67 frames.], batch size: 19, lr: 1.79e-04
+2022-05-07 14:00:27,901 INFO [train.py:715] (3/8) Epoch 12, batch 28550, loss[loss=0.1064, simple_loss=0.1766, pruned_loss=0.01808, over 4797.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03201, over 971441.57 frames.], batch size: 12, lr: 1.79e-04
+2022-05-07 14:01:06,320 INFO [train.py:715] (3/8) Epoch 12, batch 28600, loss[loss=0.1112, simple_loss=0.1894, pruned_loss=0.01649, over 4971.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03202, over 971260.36 frames.], batch size: 14, lr: 1.79e-04
+2022-05-07 14:01:44,217 INFO [train.py:715] (3/8) Epoch 12, batch 28650, loss[loss=0.1424, simple_loss=0.2156, pruned_loss=0.03461, over 4820.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03212, over 972257.06 frames.], batch size: 15, lr: 1.79e-04
+2022-05-07 14:02:23,315 INFO [train.py:715] (3/8) Epoch 12, batch 28700, loss[loss=0.133, simple_loss=0.2115, pruned_loss=0.02726, over 4783.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03189, over 971837.89 frames.], batch size: 14, lr: 1.79e-04
+2022-05-07 14:03:01,819 INFO [train.py:715] (3/8) Epoch 12, batch 28750, loss[loss=0.1378, simple_loss=0.2145, pruned_loss=0.0305, over 4893.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03188, over 971922.30 frames.], batch size: 17, lr: 1.79e-04
+2022-05-07 14:03:40,787 INFO [train.py:715] (3/8) Epoch 12, batch 28800, loss[loss=0.1204, simple_loss=0.1993, pruned_loss=0.02079, over 4744.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.03192, over 971536.39 frames.], batch size: 16, lr: 1.79e-04
+2022-05-07 14:04:18,678 INFO [train.py:715] (3/8) Epoch 12, batch 28850, loss[loss=0.1144, simple_loss=0.1904, pruned_loss=0.01924, over 4918.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03223, over 972147.59 frames.], batch size: 29, lr: 1.79e-04
+2022-05-07 14:04:57,033 INFO [train.py:715] (3/8) Epoch 12, batch 28900, loss[loss=0.1209, simple_loss=0.2036, pruned_loss=0.01917, over 4937.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03183, over 972672.73 frames.], batch size: 29, lr: 1.78e-04
+2022-05-07 14:05:35,792 INFO [train.py:715] (3/8) Epoch 12, batch 28950, loss[loss=0.1255, simple_loss=0.1963, pruned_loss=0.02734, over 4942.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.0314, over 972599.10 frames.], batch size: 29, lr: 1.78e-04
+2022-05-07 14:06:14,145 INFO [train.py:715] (3/8) Epoch 12, batch 29000, loss[loss=0.1464, simple_loss=0.2221, pruned_loss=0.03538, over 4814.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03151, over 973005.79 frames.], batch size: 21, lr: 1.78e-04
+2022-05-07 14:06:53,418 INFO [train.py:715] (3/8) Epoch 12, batch 29050, loss[loss=0.1584, simple_loss=0.2285, pruned_loss=0.04411, over 4981.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03197, over 972306.17 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 14:07:31,883 INFO [train.py:715] (3/8) Epoch 12, batch 29100, loss[loss=0.1436, simple_loss=0.2223, pruned_loss=0.03243, over 4776.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03163, over 972185.40 frames.], batch size: 19, lr: 1.78e-04
+2022-05-07 14:08:10,553 INFO [train.py:715] (3/8) Epoch 12, batch 29150, loss[loss=0.1585, simple_loss=0.2214, pruned_loss=0.04778, over 4847.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03188, over 971707.15 frames.], batch size: 32, lr: 1.78e-04
+2022-05-07 14:08:48,981 INFO [train.py:715] (3/8) Epoch 12, batch 29200, loss[loss=0.1438, simple_loss=0.2188, pruned_loss=0.0344, over 4753.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03158, over 972175.69 frames.], batch size: 19, lr: 1.78e-04
+2022-05-07 14:09:27,675 INFO [train.py:715] (3/8) Epoch 12, batch 29250, loss[loss=0.1495, simple_loss=0.223, pruned_loss=0.03803, over 4970.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03145, over 971788.43 frames.], batch size: 35, lr: 1.78e-04
+2022-05-07 14:10:05,810 INFO [train.py:715] (3/8) Epoch 12, batch 29300, loss[loss=0.1264, simple_loss=0.2047, pruned_loss=0.02402, over 4920.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03153, over 971198.06 frames.], batch size: 18, lr: 1.78e-04
+2022-05-07 14:10:43,234 INFO [train.py:715] (3/8) Epoch 12, batch 29350, loss[loss=0.1421, simple_loss=0.2151, pruned_loss=0.0346, over 4817.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03177, over 972292.34 frames.], batch size: 25, lr: 1.78e-04
+2022-05-07 14:11:22,340 INFO [train.py:715] (3/8) Epoch 12, batch 29400, loss[loss=0.1569, simple_loss=0.2217, pruned_loss=0.04603, over 4882.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03208, over 971750.28 frames.], batch size: 22, lr: 1.78e-04
+2022-05-07 14:12:00,594 INFO [train.py:715] (3/8) Epoch 12, batch 29450, loss[loss=0.1445, simple_loss=0.2221, pruned_loss=0.03344, over 4920.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2111, pruned_loss=0.03253, over 971614.18 frames.], batch size: 23, lr: 1.78e-04
+2022-05-07 14:12:38,754 INFO [train.py:715] (3/8) Epoch 12, batch 29500, loss[loss=0.1399, simple_loss=0.2188, pruned_loss=0.03049, over 4811.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03196, over 970960.49 frames.], batch size: 25, lr: 1.78e-04
+2022-05-07 14:13:16,880 INFO [train.py:715] (3/8) Epoch 12, batch 29550, loss[loss=0.119, simple_loss=0.186, pruned_loss=0.02607, over 4825.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03194, over 970863.38 frames.], batch size: 13, lr: 1.78e-04
+2022-05-07 14:13:55,808 INFO [train.py:715] (3/8) Epoch 12, batch 29600, loss[loss=0.121, simple_loss=0.1871, pruned_loss=0.02749, over 4907.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03196, over 970665.22 frames.], batch size: 17, lr: 1.78e-04
+2022-05-07 14:14:34,034 INFO [train.py:715] (3/8) Epoch 12, batch 29650, loss[loss=0.1128, simple_loss=0.1894, pruned_loss=0.01815, over 4761.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03173, over 971326.51 frames.], batch size: 18, lr: 1.78e-04
+2022-05-07 14:15:11,744 INFO [train.py:715] (3/8) Epoch 12, batch 29700, loss[loss=0.1487, simple_loss=0.2191, pruned_loss=0.03915, over 4832.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2111, pruned_loss=0.03168, over 971428.20 frames.], batch size: 30, lr: 1.78e-04
+2022-05-07 14:15:51,274 INFO [train.py:715] (3/8) Epoch 12, batch 29750, loss[loss=0.1889, simple_loss=0.2505, pruned_loss=0.06369, over 4833.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03121, over 971159.38 frames.], batch size: 30, lr: 1.78e-04
+2022-05-07 14:16:30,394 INFO [train.py:715] (3/8) Epoch 12, batch 29800, loss[loss=0.159, simple_loss=0.2302, pruned_loss=0.04387, over 4975.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03144, over 971656.12 frames.], batch size: 25, lr: 1.78e-04
+2022-05-07 14:17:09,205 INFO [train.py:715] (3/8) Epoch 12, batch 29850, loss[loss=0.212, simple_loss=0.2681, pruned_loss=0.07792, over 4752.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03165, over 971660.38 frames.], batch size: 16, lr: 1.78e-04
+2022-05-07 14:17:47,534 INFO [train.py:715] (3/8) Epoch 12, batch 29900, loss[loss=0.1253, simple_loss=0.1942, pruned_loss=0.02822, over 4812.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2105, pruned_loss=0.03126, over 970920.79 frames.], batch size: 12, lr: 1.78e-04
+2022-05-07 14:18:26,386 INFO [train.py:715] (3/8) Epoch 12, batch 29950, loss[loss=0.1375, simple_loss=0.2103, pruned_loss=0.03232, over 4955.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2099, pruned_loss=0.0308, over 971133.84 frames.], batch size: 21, lr: 1.78e-04
+2022-05-07 14:19:04,508 INFO [train.py:715] (3/8) Epoch 12, batch 30000, loss[loss=0.1412, simple_loss=0.2036, pruned_loss=0.03945, over 4967.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03046, over 971940.86 frames.], batch size: 14, lr: 1.78e-04
+2022-05-07 14:19:04,509 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 14:19:14,011 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.1054, simple_loss=0.1894, pruned_loss=0.01072, over 914524.00 frames.
+2022-05-07 14:19:52,927 INFO [train.py:715] (3/8) Epoch 12, batch 30050, loss[loss=0.1435, simple_loss=0.2115, pruned_loss=0.03773, over 4913.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03075, over 972221.53 frames.], batch size: 17, lr: 1.78e-04
+2022-05-07 14:20:31,330 INFO [train.py:715] (3/8) Epoch 12, batch 30100, loss[loss=0.1419, simple_loss=0.2102, pruned_loss=0.03678, over 4829.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.0309, over 972059.95 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 14:21:10,496 INFO [train.py:715] (3/8) Epoch 12, batch 30150, loss[loss=0.1494, simple_loss=0.2264, pruned_loss=0.03619, over 4971.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03127, over 971796.22 frames.], batch size: 39, lr: 1.78e-04
+2022-05-07 14:21:48,960 INFO [train.py:715] (3/8) Epoch 12, batch 30200, loss[loss=0.1327, simple_loss=0.2023, pruned_loss=0.0315, over 4792.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03144, over 971144.00 frames.], batch size: 17, lr: 1.78e-04
+2022-05-07 14:22:28,440 INFO [train.py:715] (3/8) Epoch 12, batch 30250, loss[loss=0.1223, simple_loss=0.1924, pruned_loss=0.02615, over 4846.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03149, over 971899.67 frames.], batch size: 30, lr: 1.78e-04
+2022-05-07 14:23:07,603 INFO [train.py:715] (3/8) Epoch 12, batch 30300, loss[loss=0.134, simple_loss=0.2102, pruned_loss=0.02893, over 4990.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03142, over 973079.92 frames.], batch size: 20, lr: 1.78e-04
+2022-05-07 14:23:45,573 INFO [train.py:715] (3/8) Epoch 12, batch 30350, loss[loss=0.1348, simple_loss=0.2081, pruned_loss=0.03073, over 4835.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03164, over 972961.31 frames.], batch size: 27, lr: 1.78e-04
+2022-05-07 14:24:23,562 INFO [train.py:715] (3/8) Epoch 12, batch 30400, loss[loss=0.1282, simple_loss=0.1947, pruned_loss=0.03083, over 4806.00 frames.], tot_loss[loss=0.1368, simple_loss=0.21, pruned_loss=0.03177, over 972748.97 frames.], batch size: 12, lr: 1.78e-04
+2022-05-07 14:25:01,296 INFO [train.py:715] (3/8) Epoch 12, batch 30450, loss[loss=0.1519, simple_loss=0.2233, pruned_loss=0.04028, over 4982.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03138, over 973372.24 frames.], batch size: 28, lr: 1.78e-04
+2022-05-07 14:25:39,284 INFO [train.py:715] (3/8) Epoch 12, batch 30500, loss[loss=0.1309, simple_loss=0.2134, pruned_loss=0.02418, over 4797.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03111, over 973886.55 frames.], batch size: 24, lr: 1.78e-04
+2022-05-07 14:26:17,290 INFO [train.py:715] (3/8) Epoch 12, batch 30550, loss[loss=0.125, simple_loss=0.1972, pruned_loss=0.02639, over 4989.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03111, over 973947.85 frames.], batch size: 26, lr: 1.78e-04
+2022-05-07 14:26:55,239 INFO [train.py:715] (3/8) Epoch 12, batch 30600, loss[loss=0.1304, simple_loss=0.1966, pruned_loss=0.03208, over 4964.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03083, over 974317.32 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 14:27:32,190 INFO [train.py:715] (3/8) Epoch 12, batch 30650, loss[loss=0.1331, simple_loss=0.2102, pruned_loss=0.02799, over 4856.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.0313, over 974106.57 frames.], batch size: 20, lr: 1.78e-04
+2022-05-07 14:28:10,734 INFO [train.py:715] (3/8) Epoch 12, batch 30700, loss[loss=0.133, simple_loss=0.2115, pruned_loss=0.02725, over 4950.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03161, over 973888.47 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 14:28:48,655 INFO [train.py:715] (3/8) Epoch 12, batch 30750, loss[loss=0.1455, simple_loss=0.2167, pruned_loss=0.03721, over 4915.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03124, over 973326.60 frames.], batch size: 18, lr: 1.78e-04
+2022-05-07 14:29:27,168 INFO [train.py:715] (3/8) Epoch 12, batch 30800, loss[loss=0.151, simple_loss=0.212, pruned_loss=0.04501, over 4842.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.0313, over 972348.44 frames.], batch size: 30, lr: 1.78e-04
+2022-05-07 14:30:05,817 INFO [train.py:715] (3/8) Epoch 12, batch 30850, loss[loss=0.1359, simple_loss=0.2017, pruned_loss=0.03501, over 4992.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03173, over 972974.44 frames.], batch size: 14, lr: 1.78e-04
+2022-05-07 14:30:45,021 INFO [train.py:715] (3/8) Epoch 12, batch 30900, loss[loss=0.14, simple_loss=0.2074, pruned_loss=0.03631, over 4789.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03137, over 973255.68 frames.], batch size: 17, lr: 1.78e-04
+2022-05-07 14:31:23,359 INFO [train.py:715] (3/8) Epoch 12, batch 30950, loss[loss=0.1413, simple_loss=0.2218, pruned_loss=0.03038, over 4804.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03156, over 973528.55 frames.], batch size: 25, lr: 1.78e-04
+2022-05-07 14:32:02,066 INFO [train.py:715] (3/8) Epoch 12, batch 31000, loss[loss=0.1411, simple_loss=0.2074, pruned_loss=0.0374, over 4645.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.032, over 972681.59 frames.], batch size: 13, lr: 1.78e-04
+2022-05-07 14:32:41,214 INFO [train.py:715] (3/8) Epoch 12, batch 31050, loss[loss=0.1456, simple_loss=0.2138, pruned_loss=0.03868, over 4773.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03211, over 971856.70 frames.], batch size: 16, lr: 1.78e-04
+2022-05-07 14:33:19,692 INFO [train.py:715] (3/8) Epoch 12, batch 31100, loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03285, over 4844.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03231, over 971542.67 frames.], batch size: 20, lr: 1.78e-04
+2022-05-07 14:33:57,507 INFO [train.py:715] (3/8) Epoch 12, batch 31150, loss[loss=0.1071, simple_loss=0.1887, pruned_loss=0.01271, over 4794.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03225, over 971520.22 frames.], batch size: 14, lr: 1.78e-04
+2022-05-07 14:34:36,504 INFO [train.py:715] (3/8) Epoch 12, batch 31200, loss[loss=0.1268, simple_loss=0.2003, pruned_loss=0.02664, over 4891.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03217, over 971395.87 frames.], batch size: 22, lr: 1.78e-04
+2022-05-07 14:35:15,346 INFO [train.py:715] (3/8) Epoch 12, batch 31250, loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03416, over 4986.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.0324, over 971382.82 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 14:35:54,050 INFO [train.py:715] (3/8) Epoch 12, batch 31300, loss[loss=0.141, simple_loss=0.2163, pruned_loss=0.03287, over 4934.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.0323, over 971714.43 frames.], batch size: 29, lr: 1.78e-04
+2022-05-07 14:36:32,570 INFO [train.py:715] (3/8) Epoch 12, batch 31350, loss[loss=0.1261, simple_loss=0.1964, pruned_loss=0.02787, over 4779.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03217, over 971708.93 frames.], batch size: 12, lr: 1.78e-04
+2022-05-07 14:37:11,736 INFO [train.py:715] (3/8) Epoch 12, batch 31400, loss[loss=0.1432, simple_loss=0.215, pruned_loss=0.03569, over 4953.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.0321, over 972238.78 frames.], batch size: 24, lr: 1.78e-04
+2022-05-07 14:37:50,139 INFO [train.py:715] (3/8) Epoch 12, batch 31450, loss[loss=0.1713, simple_loss=0.2406, pruned_loss=0.05099, over 4851.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03198, over 972484.62 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 14:38:28,381 INFO [train.py:715] (3/8) Epoch 12, batch 31500, loss[loss=0.1526, simple_loss=0.2279, pruned_loss=0.03863, over 4852.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03193, over 972166.94 frames.], batch size: 34, lr: 1.78e-04
+2022-05-07 14:39:06,658 INFO [train.py:715] (3/8) Epoch 12, batch 31550, loss[loss=0.1225, simple_loss=0.2029, pruned_loss=0.02107, over 4894.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03208, over 972418.54 frames.], batch size: 22, lr: 1.78e-04
+2022-05-07 14:39:45,223 INFO [train.py:715] (3/8) Epoch 12, batch 31600, loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02907, over 4712.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03183, over 972563.56 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 14:40:22,891 INFO [train.py:715] (3/8) Epoch 12, batch 31650, loss[loss=0.1191, simple_loss=0.188, pruned_loss=0.02504, over 4781.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03232, over 972222.42 frames.], batch size: 14, lr: 1.78e-04
+2022-05-07 14:41:00,519 INFO [train.py:715] (3/8) Epoch 12, batch 31700, loss[loss=0.1222, simple_loss=0.2046, pruned_loss=0.01987, over 4980.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2106, pruned_loss=0.03225, over 973160.78 frames.], batch size: 14, lr: 1.78e-04
+2022-05-07 14:41:38,634 INFO [train.py:715] (3/8) Epoch 12, batch 31750, loss[loss=0.1428, simple_loss=0.2197, pruned_loss=0.03297, over 4974.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03223, over 973775.31 frames.], batch size: 24, lr: 1.78e-04
+2022-05-07 14:42:16,747 INFO [train.py:715] (3/8) Epoch 12, batch 31800, loss[loss=0.1224, simple_loss=0.2011, pruned_loss=0.02185, over 4752.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03201, over 973471.46 frames.], batch size: 16, lr: 1.78e-04
+2022-05-07 14:42:54,699 INFO [train.py:715] (3/8) Epoch 12, batch 31850, loss[loss=0.1279, simple_loss=0.194, pruned_loss=0.03083, over 4860.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03216, over 973503.11 frames.], batch size: 30, lr: 1.78e-04
+2022-05-07 14:43:32,406 INFO [train.py:715] (3/8) Epoch 12, batch 31900, loss[loss=0.1511, simple_loss=0.2202, pruned_loss=0.04106, over 4861.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03181, over 973472.06 frames.], batch size: 13, lr: 1.78e-04
+2022-05-07 14:44:10,699 INFO [train.py:715] (3/8) Epoch 12, batch 31950, loss[loss=0.1319, simple_loss=0.208, pruned_loss=0.0279, over 4988.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03182, over 973344.44 frames.], batch size: 28, lr: 1.78e-04
+2022-05-07 14:44:48,297 INFO [train.py:715] (3/8) Epoch 12, batch 32000, loss[loss=0.1477, simple_loss=0.2201, pruned_loss=0.03766, over 4778.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03151, over 973216.41 frames.], batch size: 18, lr: 1.78e-04
+2022-05-07 14:45:26,162 INFO [train.py:715] (3/8) Epoch 12, batch 32050, loss[loss=0.1373, simple_loss=0.2163, pruned_loss=0.02912, over 4811.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.03214, over 973687.28 frames.], batch size: 25, lr: 1.78e-04
+2022-05-07 14:46:04,021 INFO [train.py:715] (3/8) Epoch 12, batch 32100, loss[loss=0.134, simple_loss=0.2163, pruned_loss=0.02584, over 4849.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03186, over 973714.64 frames.], batch size: 20, lr: 1.78e-04
+2022-05-07 14:46:42,429 INFO [train.py:715] (3/8) Epoch 12, batch 32150, loss[loss=0.1499, simple_loss=0.226, pruned_loss=0.03692, over 4702.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.03242, over 973266.18 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 14:47:20,024 INFO [train.py:715] (3/8) Epoch 12, batch 32200, loss[loss=0.1276, simple_loss=0.2031, pruned_loss=0.02602, over 4979.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2105, pruned_loss=0.03244, over 973330.44 frames.], batch size: 35, lr: 1.78e-04
+2022-05-07 14:47:58,174 INFO [train.py:715] (3/8) Epoch 12, batch 32250, loss[loss=0.1315, simple_loss=0.2116, pruned_loss=0.02572, over 4831.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2096, pruned_loss=0.03202, over 972489.03 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 14:48:36,825 INFO [train.py:715] (3/8) Epoch 12, batch 32300, loss[loss=0.1302, simple_loss=0.2037, pruned_loss=0.02835, over 4945.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2104, pruned_loss=0.03227, over 972357.59 frames.], batch size: 21, lr: 1.78e-04
+2022-05-07 14:49:14,384 INFO [train.py:715] (3/8) Epoch 12, batch 32350, loss[loss=0.1211, simple_loss=0.1906, pruned_loss=0.02578, over 4925.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.03194, over 973219.90 frames.], batch size: 23, lr: 1.78e-04
+2022-05-07 14:49:52,727 INFO [train.py:715] (3/8) Epoch 12, batch 32400, loss[loss=0.1644, simple_loss=0.228, pruned_loss=0.05038, over 4870.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2095, pruned_loss=0.03173, over 972597.85 frames.], batch size: 22, lr: 1.78e-04
+2022-05-07 14:50:30,827 INFO [train.py:715] (3/8) Epoch 12, batch 32450, loss[loss=0.1294, simple_loss=0.2031, pruned_loss=0.02786, over 4958.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2095, pruned_loss=0.03162, over 972232.76 frames.], batch size: 21, lr: 1.78e-04
+2022-05-07 14:51:09,334 INFO [train.py:715] (3/8) Epoch 12, batch 32500, loss[loss=0.1455, simple_loss=0.2214, pruned_loss=0.03484, over 4762.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03107, over 972152.68 frames.], batch size: 19, lr: 1.78e-04
+2022-05-07 14:51:46,830 INFO [train.py:715] (3/8) Epoch 12, batch 32550, loss[loss=0.1407, simple_loss=0.221, pruned_loss=0.03021, over 4885.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03091, over 972031.61 frames.], batch size: 22, lr: 1.78e-04
+2022-05-07 14:52:25,070 INFO [train.py:715] (3/8) Epoch 12, batch 32600, loss[loss=0.1242, simple_loss=0.2038, pruned_loss=0.02227, over 4794.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03096, over 971368.82 frames.], batch size: 24, lr: 1.78e-04
+2022-05-07 14:53:03,208 INFO [train.py:715] (3/8) Epoch 12, batch 32650, loss[loss=0.1493, simple_loss=0.2294, pruned_loss=0.03458, over 4839.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2092, pruned_loss=0.03145, over 972111.58 frames.], batch size: 20, lr: 1.78e-04
+2022-05-07 14:53:40,738 INFO [train.py:715] (3/8) Epoch 12, batch 32700, loss[loss=0.1717, simple_loss=0.2471, pruned_loss=0.04818, over 4759.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2089, pruned_loss=0.0317, over 971973.25 frames.], batch size: 16, lr: 1.78e-04
+2022-05-07 14:54:18,462 INFO [train.py:715] (3/8) Epoch 12, batch 32750, loss[loss=0.1202, simple_loss=0.1981, pruned_loss=0.02113, over 4769.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2096, pruned_loss=0.03172, over 972030.49 frames.], batch size: 19, lr: 1.78e-04
+2022-05-07 14:54:56,867 INFO [train.py:715] (3/8) Epoch 12, batch 32800, loss[loss=0.1193, simple_loss=0.1902, pruned_loss=0.02417, over 4742.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2099, pruned_loss=0.03185, over 971792.93 frames.], batch size: 16, lr: 1.78e-04
+2022-05-07 14:55:35,235 INFO [train.py:715] (3/8) Epoch 12, batch 32850, loss[loss=0.1184, simple_loss=0.1917, pruned_loss=0.02252, over 4916.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.03216, over 971846.48 frames.], batch size: 29, lr: 1.78e-04
+2022-05-07 14:56:12,924 INFO [train.py:715] (3/8) Epoch 12, batch 32900, loss[loss=0.1435, simple_loss=0.2273, pruned_loss=0.02983, over 4773.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03193, over 971675.20 frames.], batch size: 18, lr: 1.78e-04
+2022-05-07 14:56:51,023 INFO [train.py:715] (3/8) Epoch 12, batch 32950, loss[loss=0.1636, simple_loss=0.2444, pruned_loss=0.04142, over 4927.00 frames.], tot_loss[loss=0.1368, simple_loss=0.21, pruned_loss=0.03181, over 972788.25 frames.], batch size: 29, lr: 1.78e-04
+2022-05-07 14:57:29,167 INFO [train.py:715] (3/8) Epoch 12, batch 33000, loss[loss=0.1399, simple_loss=0.2065, pruned_loss=0.03659, over 4814.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03238, over 972437.73 frames.], batch size: 12, lr: 1.78e-04
+2022-05-07 14:57:29,168 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 14:57:38,688 INFO [train.py:742] (3/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1896, pruned_loss=0.01085, over 914524.00 frames.
+2022-05-07 14:58:18,190 INFO [train.py:715] (3/8) Epoch 12, batch 33050, loss[loss=0.1542, simple_loss=0.2323, pruned_loss=0.03801, over 4913.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03245, over 972563.07 frames.], batch size: 17, lr: 1.78e-04
+2022-05-07 14:58:56,560 INFO [train.py:715] (3/8) Epoch 12, batch 33100, loss[loss=0.1336, simple_loss=0.2054, pruned_loss=0.03091, over 4924.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03296, over 972696.42 frames.], batch size: 23, lr: 1.78e-04
+2022-05-07 14:59:34,844 INFO [train.py:715] (3/8) Epoch 12, batch 33150, loss[loss=0.113, simple_loss=0.1886, pruned_loss=0.01871, over 4891.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2121, pruned_loss=0.03246, over 972716.84 frames.], batch size: 39, lr: 1.78e-04
+2022-05-07 15:00:12,868 INFO [train.py:715] (3/8) Epoch 12, batch 33200, loss[loss=0.1337, simple_loss=0.2086, pruned_loss=0.02938, over 4925.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03255, over 972154.18 frames.], batch size: 18, lr: 1.78e-04
+2022-05-07 15:00:51,451 INFO [train.py:715] (3/8) Epoch 12, batch 33250, loss[loss=0.1164, simple_loss=0.1872, pruned_loss=0.02279, over 4979.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2097, pruned_loss=0.03169, over 971037.31 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 15:01:29,592 INFO [train.py:715] (3/8) Epoch 12, batch 33300, loss[loss=0.1125, simple_loss=0.1828, pruned_loss=0.02111, over 4899.00 frames.], tot_loss[loss=0.1368, simple_loss=0.21, pruned_loss=0.03178, over 971325.02 frames.], batch size: 18, lr: 1.78e-04
+2022-05-07 15:02:07,722 INFO [train.py:715] (3/8) Epoch 12, batch 33350, loss[loss=0.13, simple_loss=0.2068, pruned_loss=0.02661, over 4988.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03185, over 971284.65 frames.], batch size: 28, lr: 1.78e-04
+2022-05-07 15:02:46,383 INFO [train.py:715] (3/8) Epoch 12, batch 33400, loss[loss=0.1368, simple_loss=0.2131, pruned_loss=0.03019, over 4840.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.03192, over 971536.48 frames.], batch size: 25, lr: 1.78e-04
+2022-05-07 15:03:25,038 INFO [train.py:715] (3/8) Epoch 12, batch 33450, loss[loss=0.1416, simple_loss=0.2043, pruned_loss=0.03943, over 4819.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.03215, over 971910.29 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 15:04:03,394 INFO [train.py:715] (3/8) Epoch 12, batch 33500, loss[loss=0.1435, simple_loss=0.2255, pruned_loss=0.03081, over 4806.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03193, over 972194.87 frames.], batch size: 24, lr: 1.78e-04
+2022-05-07 15:04:42,494 INFO [train.py:715] (3/8) Epoch 12, batch 33550, loss[loss=0.1451, simple_loss=0.2221, pruned_loss=0.0341, over 4755.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03158, over 971862.19 frames.], batch size: 19, lr: 1.78e-04
+2022-05-07 15:05:21,129 INFO [train.py:715] (3/8) Epoch 12, batch 33600, loss[loss=0.1271, simple_loss=0.2027, pruned_loss=0.02571, over 4988.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03146, over 971564.89 frames.], batch size: 14, lr: 1.78e-04
+2022-05-07 15:05:59,984 INFO [train.py:715] (3/8) Epoch 12, batch 33650, loss[loss=0.1296, simple_loss=0.2044, pruned_loss=0.02741, over 4702.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03153, over 971449.38 frames.], batch size: 15, lr: 1.78e-04
+2022-05-07 15:06:38,063 INFO [train.py:715] (3/8) Epoch 12, batch 33700, loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02942, over 4935.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03155, over 971619.15 frames.], batch size: 39, lr: 1.78e-04
+2022-05-07 15:07:16,845 INFO [train.py:715] (3/8) Epoch 12, batch 33750, loss[loss=0.1326, simple_loss=0.1962, pruned_loss=0.03447, over 4772.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.03131, over 970717.25 frames.], batch size: 14, lr: 1.78e-04
+2022-05-07 15:07:55,112 INFO [train.py:715] (3/8) Epoch 12, batch 33800, loss[loss=0.1657, simple_loss=0.2391, pruned_loss=0.04613, over 4789.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2107, pruned_loss=0.03112, over 972003.17 frames.], batch size: 21, lr: 1.78e-04
+2022-05-07 15:08:32,476 INFO [train.py:715] (3/8) Epoch 12, batch 33850, loss[loss=0.1248, simple_loss=0.2081, pruned_loss=0.02076, over 4805.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2107, pruned_loss=0.03109, over 972391.37 frames.], batch size: 25, lr: 1.78e-04
+2022-05-07 15:09:10,656 INFO [train.py:715] (3/8) Epoch 12, batch 33900, loss[loss=0.1238, simple_loss=0.2009, pruned_loss=0.02335, over 4868.00 frames.], tot_loss[loss=0.136, simple_loss=0.2102, pruned_loss=0.03086, over 971752.75 frames.], batch size: 32, lr: 1.78e-04
+2022-05-07 15:09:47,910 INFO [train.py:715] (3/8) Epoch 12, batch 33950, loss[loss=0.1394, simple_loss=0.217, pruned_loss=0.03086, over 4878.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2106, pruned_loss=0.03115, over 972073.05 frames.], batch size: 16, lr: 1.77e-04
+2022-05-07 15:10:26,071 INFO [train.py:715] (3/8) Epoch 12, batch 34000, loss[loss=0.1434, simple_loss=0.2222, pruned_loss=0.03233, over 4935.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2112, pruned_loss=0.03174, over 971910.59 frames.], batch size: 21, lr: 1.77e-04
+2022-05-07 15:11:03,703 INFO [train.py:715] (3/8) Epoch 12, batch 34050, loss[loss=0.1582, simple_loss=0.2314, pruned_loss=0.04247, over 4924.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03202, over 972279.14 frames.], batch size: 18, lr: 1.77e-04
+2022-05-07 15:11:41,637 INFO [train.py:715] (3/8) Epoch 12, batch 34100, loss[loss=0.186, simple_loss=0.2441, pruned_loss=0.06395, over 4910.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03238, over 971838.61 frames.], batch size: 18, lr: 1.77e-04
+2022-05-07 15:12:19,671 INFO [train.py:715] (3/8) Epoch 12, batch 34150, loss[loss=0.1354, simple_loss=0.2195, pruned_loss=0.02566, over 4752.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03278, over 971136.39 frames.], batch size: 16, lr: 1.77e-04
+2022-05-07 15:12:57,180 INFO [train.py:715] (3/8) Epoch 12, batch 34200, loss[loss=0.1477, simple_loss=0.2207, pruned_loss=0.03733, over 4829.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2121, pruned_loss=0.03258, over 971723.86 frames.], batch size: 26, lr: 1.77e-04
+2022-05-07 15:13:35,449 INFO [train.py:715] (3/8) Epoch 12, batch 34250, loss[loss=0.1234, simple_loss=0.1988, pruned_loss=0.02399, over 4798.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.03181, over 971292.24 frames.], batch size: 24, lr: 1.77e-04
+2022-05-07 15:14:12,818 INFO [train.py:715] (3/8) Epoch 12, batch 34300, loss[loss=0.1297, simple_loss=0.2095, pruned_loss=0.02494, over 4925.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03162, over 971756.25 frames.], batch size: 21, lr: 1.77e-04
+2022-05-07 15:14:51,107 INFO [train.py:715] (3/8) Epoch 12, batch 34350, loss[loss=0.1282, simple_loss=0.204, pruned_loss=0.02619, over 4885.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03138, over 972563.89 frames.], batch size: 16, lr: 1.77e-04
+2022-05-07 15:15:28,882 INFO [train.py:715] (3/8) Epoch 12, batch 34400, loss[loss=0.142, simple_loss=0.2267, pruned_loss=0.02862, over 4848.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03136, over 972493.94 frames.], batch size: 15, lr: 1.77e-04
+2022-05-07 15:16:07,252 INFO [train.py:715] (3/8) Epoch 12, batch 34450, loss[loss=0.1066, simple_loss=0.1747, pruned_loss=0.01925, over 4807.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03137, over 972508.34 frames.], batch size: 26, lr: 1.77e-04
+2022-05-07 15:16:45,350 INFO [train.py:715] (3/8) Epoch 12, batch 34500, loss[loss=0.143, simple_loss=0.2178, pruned_loss=0.0341, over 4850.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2098, pruned_loss=0.03147, over 972578.24 frames.], batch size: 30, lr: 1.77e-04
+2022-05-07 15:17:23,596 INFO [train.py:715] (3/8) Epoch 12, batch 34550, loss[loss=0.1278, simple_loss=0.2026, pruned_loss=0.02653, over 4936.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03147, over 971751.57 frames.], batch size: 21, lr: 1.77e-04
+2022-05-07 15:18:02,262 INFO [train.py:715] (3/8) Epoch 12, batch 34600, loss[loss=0.1387, simple_loss=0.2209, pruned_loss=0.02828, over 4916.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03111, over 971960.48 frames.], batch size: 39, lr: 1.77e-04
+2022-05-07 15:18:41,658 INFO [train.py:715] (3/8) Epoch 12, batch 34650, loss[loss=0.1355, simple_loss=0.2115, pruned_loss=0.02972, over 4924.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03151, over 972560.51 frames.], batch size: 18, lr: 1.77e-04
+2022-05-07 15:19:21,041 INFO [train.py:715] (3/8) Epoch 12, batch 34700, loss[loss=0.1428, simple_loss=0.2166, pruned_loss=0.03448, over 4987.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03165, over 972924.85 frames.], batch size: 14, lr: 1.77e-04
+2022-05-07 15:19:58,682 INFO [train.py:715] (3/8) Epoch 12, batch 34750, loss[loss=0.1353, simple_loss=0.2111, pruned_loss=0.02972, over 4759.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03191, over 972450.15 frames.], batch size: 19, lr: 1.77e-04
+2022-05-07 15:20:34,680 INFO [train.py:715] (3/8) Epoch 12, batch 34800, loss[loss=0.1243, simple_loss=0.1991, pruned_loss=0.0248, over 4923.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03067, over 972090.11 frames.], batch size: 18, lr: 1.77e-04
+2022-05-07 15:21:23,129 INFO [train.py:715] (3/8) Epoch 13, batch 0, loss[loss=0.109, simple_loss=0.1738, pruned_loss=0.02205, over 4801.00 frames.], tot_loss[loss=0.109, simple_loss=0.1738, pruned_loss=0.02205, over 4801.00 frames.], batch size: 12, lr: 1.71e-04
+2022-05-07 15:22:01,155 INFO [train.py:715] (3/8) Epoch 13, batch 50, loss[loss=0.1497, simple_loss=0.221, pruned_loss=0.0392, over 4804.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2105, pruned_loss=0.03102, over 219733.63 frames.], batch size: 21, lr: 1.71e-04
+2022-05-07 15:22:39,462 INFO [train.py:715] (3/8) Epoch 13, batch 100, loss[loss=0.1528, simple_loss=0.2242, pruned_loss=0.04072, over 4924.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03106, over 387036.94 frames.], batch size: 18, lr: 1.71e-04
+2022-05-07 15:23:17,858 INFO [train.py:715] (3/8) Epoch 13, batch 150, loss[loss=0.1278, simple_loss=0.2117, pruned_loss=0.02193, over 4797.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2106, pruned_loss=0.03096, over 517341.54 frames.], batch size: 24, lr: 1.71e-04
+2022-05-07 15:23:57,326 INFO [train.py:715] (3/8) Epoch 13, batch 200, loss[loss=0.1383, simple_loss=0.214, pruned_loss=0.0313, over 4882.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.0309, over 618840.51 frames.], batch size: 16, lr: 1.71e-04
+2022-05-07 15:24:35,735 INFO [train.py:715] (3/8) Epoch 13, batch 250, loss[loss=0.1296, simple_loss=0.2074, pruned_loss=0.02589, over 4958.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03045, over 696954.10 frames.], batch size: 14, lr: 1.71e-04
+2022-05-07 15:25:15,232 INFO [train.py:715] (3/8) Epoch 13, batch 300, loss[loss=0.1595, simple_loss=0.2345, pruned_loss=0.04222, over 4888.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03084, over 757848.93 frames.], batch size: 22, lr: 1.71e-04
+2022-05-07 15:25:53,994 INFO [train.py:715] (3/8) Epoch 13, batch 350, loss[loss=0.1431, simple_loss=0.2148, pruned_loss=0.03564, over 4864.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.03103, over 805008.92 frames.], batch size: 38, lr: 1.71e-04
+2022-05-07 15:26:33,534 INFO [train.py:715] (3/8) Epoch 13, batch 400, loss[loss=0.141, simple_loss=0.2219, pruned_loss=0.03003, over 4857.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2106, pruned_loss=0.03119, over 842246.06 frames.], batch size: 20, lr: 1.71e-04
+2022-05-07 15:27:13,023 INFO [train.py:715] (3/8) Epoch 13, batch 450, loss[loss=0.1185, simple_loss=0.1911, pruned_loss=0.02302, over 4794.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03152, over 871115.99 frames.], batch size: 12, lr: 1.71e-04
+2022-05-07 15:27:53,176 INFO [train.py:715] (3/8) Epoch 13, batch 500, loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03032, over 4971.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03091, over 894471.07 frames.], batch size: 35, lr: 1.71e-04
+2022-05-07 15:28:33,647 INFO [train.py:715] (3/8) Epoch 13, batch 550, loss[loss=0.1533, simple_loss=0.2262, pruned_loss=0.04021, over 4949.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.0305, over 911774.22 frames.], batch size: 21, lr: 1.71e-04
+2022-05-07 15:29:12,912 INFO [train.py:715] (3/8) Epoch 13, batch 600, loss[loss=0.1558, simple_loss=0.2267, pruned_loss=0.04241, over 4736.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03116, over 924928.97 frames.], batch size: 16, lr: 1.71e-04
+2022-05-07 15:29:53,388 INFO [train.py:715] (3/8) Epoch 13, batch 650, loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.03, over 4888.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.0309, over 935320.70 frames.], batch size: 22, lr: 1.71e-04
+2022-05-07 15:30:33,369 INFO [train.py:715] (3/8) Epoch 13, batch 700, loss[loss=0.1694, simple_loss=0.2438, pruned_loss=0.04743, over 4940.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03149, over 943194.24 frames.], batch size: 21, lr: 1.71e-04
+2022-05-07 15:31:13,981 INFO [train.py:715] (3/8) Epoch 13, batch 750, loss[loss=0.1701, simple_loss=0.2425, pruned_loss=0.04889, over 4694.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03163, over 949606.10 frames.], batch size: 15, lr: 1.71e-04
+2022-05-07 15:31:53,295 INFO [train.py:715] (3/8) Epoch 13, batch 800, loss[loss=0.1271, simple_loss=0.2004, pruned_loss=0.02688, over 4906.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.0315, over 954174.17 frames.], batch size: 17, lr: 1.71e-04
+2022-05-07 15:32:32,575 INFO [train.py:715] (3/8) Epoch 13, batch 850, loss[loss=0.1394, simple_loss=0.2162, pruned_loss=0.03129, over 4875.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.0314, over 958542.08 frames.], batch size: 20, lr: 1.71e-04
+2022-05-07 15:33:12,800 INFO [train.py:715] (3/8) Epoch 13, batch 900, loss[loss=0.1683, simple_loss=0.2431, pruned_loss=0.0467, over 4772.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03156, over 961634.14 frames.], batch size: 18, lr: 1.71e-04
+2022-05-07 15:33:52,198 INFO [train.py:715] (3/8) Epoch 13, batch 950, loss[loss=0.1206, simple_loss=0.2031, pruned_loss=0.01905, over 4879.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03128, over 964381.84 frames.], batch size: 16, lr: 1.71e-04
+2022-05-07 15:34:32,777 INFO [train.py:715] (3/8) Epoch 13, batch 1000, loss[loss=0.201, simple_loss=0.259, pruned_loss=0.07149, over 4829.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.0316, over 966589.50 frames.], batch size: 15, lr: 1.71e-04
+2022-05-07 15:35:12,239 INFO [train.py:715] (3/8) Epoch 13, batch 1050, loss[loss=0.1121, simple_loss=0.1857, pruned_loss=0.01929, over 4777.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03135, over 968450.91 frames.], batch size: 17, lr: 1.71e-04
+2022-05-07 15:35:52,554 INFO [train.py:715] (3/8) Epoch 13, batch 1100, loss[loss=0.1356, simple_loss=0.2064, pruned_loss=0.03241, over 4958.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03114, over 969493.43 frames.], batch size: 35, lr: 1.71e-04
+2022-05-07 15:36:32,028 INFO [train.py:715] (3/8) Epoch 13, batch 1150, loss[loss=0.1407, simple_loss=0.2076, pruned_loss=0.03692, over 4682.00 frames.], tot_loss[loss=0.136, simple_loss=0.2101, pruned_loss=0.03096, over 970501.90 frames.], batch size: 15, lr: 1.71e-04
+2022-05-07 15:37:11,796 INFO [train.py:715] (3/8) Epoch 13, batch 1200, loss[loss=0.149, simple_loss=0.2213, pruned_loss=0.03837, over 4955.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2107, pruned_loss=0.03115, over 971784.93 frames.], batch size: 21, lr: 1.71e-04
+2022-05-07 15:37:52,137 INFO [train.py:715] (3/8) Epoch 13, batch 1250, loss[loss=0.1197, simple_loss=0.197, pruned_loss=0.02122, over 4963.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03073, over 972010.31 frames.], batch size: 24, lr: 1.71e-04
+2022-05-07 15:38:31,097 INFO [train.py:715] (3/8) Epoch 13, batch 1300, loss[loss=0.1259, simple_loss=0.1952, pruned_loss=0.02828, over 4826.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03122, over 972019.26 frames.], batch size: 25, lr: 1.71e-04
+2022-05-07 15:39:11,011 INFO [train.py:715] (3/8) Epoch 13, batch 1350, loss[loss=0.1222, simple_loss=0.2012, pruned_loss=0.02158, over 4785.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.03148, over 971283.63 frames.], batch size: 18, lr: 1.71e-04
+2022-05-07 15:39:49,775 INFO [train.py:715] (3/8) Epoch 13, batch 1400, loss[loss=0.1081, simple_loss=0.183, pruned_loss=0.01659, over 4809.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03102, over 971608.14 frames.], batch size: 14, lr: 1.71e-04
+2022-05-07 15:40:28,860 INFO [train.py:715] (3/8) Epoch 13, batch 1450, loss[loss=0.1194, simple_loss=0.199, pruned_loss=0.01991, over 4978.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03098, over 972406.75 frames.], batch size: 24, lr: 1.71e-04
+2022-05-07 15:41:06,536 INFO [train.py:715] (3/8) Epoch 13, batch 1500, loss[loss=0.1176, simple_loss=0.1956, pruned_loss=0.01985, over 4805.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.0311, over 972585.15 frames.], batch size: 12, lr: 1.71e-04
+2022-05-07 15:41:44,153 INFO [train.py:715] (3/8) Epoch 13, batch 1550, loss[loss=0.1054, simple_loss=0.1765, pruned_loss=0.01718, over 4796.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03104, over 971577.91 frames.], batch size: 12, lr: 1.71e-04
+2022-05-07 15:42:22,723 INFO [train.py:715] (3/8) Epoch 13, batch 1600, loss[loss=0.1547, simple_loss=0.2393, pruned_loss=0.03504, over 4809.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.0309, over 971782.33 frames.], batch size: 21, lr: 1.71e-04
+2022-05-07 15:43:00,640 INFO [train.py:715] (3/8) Epoch 13, batch 1650, loss[loss=0.1616, simple_loss=0.226, pruned_loss=0.04861, over 4859.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.0312, over 971490.43 frames.], batch size: 32, lr: 1.71e-04
+2022-05-07 15:43:39,379 INFO [train.py:715] (3/8) Epoch 13, batch 1700, loss[loss=0.1792, simple_loss=0.2362, pruned_loss=0.06111, over 4824.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03113, over 971306.24 frames.], batch size: 15, lr: 1.71e-04
+2022-05-07 15:44:17,663 INFO [train.py:715] (3/8) Epoch 13, batch 1750, loss[loss=0.1186, simple_loss=0.1913, pruned_loss=0.02298, over 4979.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03144, over 972150.62 frames.], batch size: 15, lr: 1.71e-04
+2022-05-07 15:44:57,090 INFO [train.py:715] (3/8) Epoch 13, batch 1800, loss[loss=0.1419, simple_loss=0.2126, pruned_loss=0.0356, over 4980.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03174, over 972550.11 frames.], batch size: 33, lr: 1.71e-04
+2022-05-07 15:45:35,170 INFO [train.py:715] (3/8) Epoch 13, batch 1850, loss[loss=0.1583, simple_loss=0.2388, pruned_loss=0.03888, over 4918.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03121, over 972868.02 frames.], batch size: 17, lr: 1.71e-04
+2022-05-07 15:46:13,430 INFO [train.py:715] (3/8) Epoch 13, batch 1900, loss[loss=0.1471, simple_loss=0.2232, pruned_loss=0.03548, over 4918.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03161, over 973251.27 frames.], batch size: 23, lr: 1.71e-04
+2022-05-07 15:46:52,089 INFO [train.py:715] (3/8) Epoch 13, batch 1950, loss[loss=0.1414, simple_loss=0.2158, pruned_loss=0.03351, over 4791.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03143, over 973421.27 frames.], batch size: 14, lr: 1.71e-04
+2022-05-07 15:47:30,465 INFO [train.py:715] (3/8) Epoch 13, batch 2000, loss[loss=0.1388, simple_loss=0.204, pruned_loss=0.03681, over 4795.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.032, over 972424.23 frames.], batch size: 12, lr: 1.71e-04
+2022-05-07 15:48:09,018 INFO [train.py:715] (3/8) Epoch 13, batch 2050, loss[loss=0.141, simple_loss=0.2187, pruned_loss=0.03166, over 4813.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03156, over 972141.65 frames.], batch size: 25, lr: 1.71e-04
+2022-05-07 15:48:47,022 INFO [train.py:715] (3/8) Epoch 13, batch 2100, loss[loss=0.1419, simple_loss=0.2209, pruned_loss=0.0314, over 4774.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03142, over 970976.62 frames.], batch size: 17, lr: 1.71e-04
+2022-05-07 15:49:26,188 INFO [train.py:715] (3/8) Epoch 13, batch 2150, loss[loss=0.1234, simple_loss=0.2004, pruned_loss=0.02321, over 4854.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03147, over 971008.83 frames.], batch size: 20, lr: 1.71e-04
+2022-05-07 15:50:04,032 INFO [train.py:715] (3/8) Epoch 13, batch 2200, loss[loss=0.1286, simple_loss=0.1855, pruned_loss=0.03589, over 4818.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03118, over 971144.79 frames.], batch size: 13, lr: 1.71e-04
+2022-05-07 15:50:42,242 INFO [train.py:715] (3/8) Epoch 13, batch 2250, loss[loss=0.1524, simple_loss=0.2268, pruned_loss=0.03901, over 4889.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03097, over 972141.26 frames.], batch size: 16, lr: 1.71e-04
+2022-05-07 15:51:20,492 INFO [train.py:715] (3/8) Epoch 13, batch 2300, loss[loss=0.1407, simple_loss=0.2266, pruned_loss=0.02739, over 4821.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.0309, over 972606.25 frames.], batch size: 15, lr: 1.71e-04
+2022-05-07 15:51:59,645 INFO [train.py:715] (3/8) Epoch 13, batch 2350, loss[loss=0.1276, simple_loss=0.1992, pruned_loss=0.02801, over 4969.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03055, over 972659.93 frames.], batch size: 24, lr: 1.71e-04
+2022-05-07 15:52:38,010 INFO [train.py:715] (3/8) Epoch 13, batch 2400, loss[loss=0.1319, simple_loss=0.2043, pruned_loss=0.02973, over 4781.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2081, pruned_loss=0.03081, over 971557.86 frames.], batch size: 14, lr: 1.71e-04
+2022-05-07 15:53:16,746 INFO [train.py:715] (3/8) Epoch 13, batch 2450, loss[loss=0.1607, simple_loss=0.2259, pruned_loss=0.04774, over 4804.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2087, pruned_loss=0.03128, over 971084.30 frames.], batch size: 21, lr: 1.71e-04
+2022-05-07 15:53:55,652 INFO [train.py:715] (3/8) Epoch 13, batch 2500, loss[loss=0.1083, simple_loss=0.1763, pruned_loss=0.0201, over 4837.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2083, pruned_loss=0.03091, over 971672.84 frames.], batch size: 13, lr: 1.71e-04
+2022-05-07 15:54:34,063 INFO [train.py:715] (3/8) Epoch 13, batch 2550, loss[loss=0.1356, simple_loss=0.2121, pruned_loss=0.0296, over 4786.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03171, over 972285.50 frames.], batch size: 14, lr: 1.71e-04
+2022-05-07 15:55:12,160 INFO [train.py:715] (3/8) Epoch 13, batch 2600, loss[loss=0.1413, simple_loss=0.2069, pruned_loss=0.03783, over 4884.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.032, over 973243.58 frames.], batch size: 16, lr: 1.71e-04
+2022-05-07 15:55:50,583 INFO [train.py:715] (3/8) Epoch 13, batch 2650, loss[loss=0.1331, simple_loss=0.1996, pruned_loss=0.03333, over 4903.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2107, pruned_loss=0.03222, over 973652.11 frames.], batch size: 17, lr: 1.71e-04
+2022-05-07 15:56:28,665 INFO [train.py:715] (3/8) Epoch 13, batch 2700, loss[loss=0.1344, simple_loss=0.2049, pruned_loss=0.03194, over 4689.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03241, over 973161.47 frames.], batch size: 15, lr: 1.70e-04
+2022-05-07 15:57:06,440 INFO [train.py:715] (3/8) Epoch 13, batch 2750, loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.0301, over 4935.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.0324, over 972819.28 frames.], batch size: 29, lr: 1.70e-04
+2022-05-07 15:57:43,969 INFO [train.py:715] (3/8) Epoch 13, batch 2800, loss[loss=0.1436, simple_loss=0.2225, pruned_loss=0.03236, over 4988.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.0321, over 972767.00 frames.], batch size: 27, lr: 1.70e-04
+2022-05-07 15:58:22,564 INFO [train.py:715] (3/8) Epoch 13, batch 2850, loss[loss=0.1428, simple_loss=0.2103, pruned_loss=0.03763, over 4686.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03168, over 972783.88 frames.], batch size: 15, lr: 1.70e-04
+2022-05-07 15:59:00,071 INFO [train.py:715] (3/8) Epoch 13, batch 2900, loss[loss=0.164, simple_loss=0.2526, pruned_loss=0.03768, over 4791.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03142, over 973744.23 frames.], batch size: 18, lr: 1.70e-04
+2022-05-07 15:59:37,967 INFO [train.py:715] (3/8) Epoch 13, batch 2950, loss[loss=0.1193, simple_loss=0.1991, pruned_loss=0.01973, over 4759.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03136, over 973889.34 frames.], batch size: 19, lr: 1.70e-04
+2022-05-07 16:00:15,989 INFO [train.py:715] (3/8) Epoch 13, batch 3000, loss[loss=0.1406, simple_loss=0.222, pruned_loss=0.02959, over 4736.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.0316, over 973772.11 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 16:00:15,989 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 16:00:25,446 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1052, simple_loss=0.1893, pruned_loss=0.01058, over 914524.00 frames.
+2022-05-07 16:01:03,672 INFO [train.py:715] (3/8) Epoch 13, batch 3050, loss[loss=0.1436, simple_loss=0.2235, pruned_loss=0.03182, over 4959.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03108, over 974216.02 frames.], batch size: 25, lr: 1.70e-04
+2022-05-07 16:01:42,203 INFO [train.py:715] (3/8) Epoch 13, batch 3100, loss[loss=0.1822, simple_loss=0.2541, pruned_loss=0.05513, over 4857.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03177, over 974401.16 frames.], batch size: 20, lr: 1.70e-04
+2022-05-07 16:02:19,746 INFO [train.py:715] (3/8) Epoch 13, batch 3150, loss[loss=0.1311, simple_loss=0.1953, pruned_loss=0.0334, over 4812.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03179, over 973381.67 frames.], batch size: 12, lr: 1.70e-04
+2022-05-07 16:02:57,076 INFO [train.py:715] (3/8) Epoch 13, batch 3200, loss[loss=0.126, simple_loss=0.2013, pruned_loss=0.02531, over 4813.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.0318, over 973397.77 frames.], batch size: 12, lr: 1.70e-04
+2022-05-07 16:03:35,544 INFO [train.py:715] (3/8) Epoch 13, batch 3250, loss[loss=0.1354, simple_loss=0.2059, pruned_loss=0.03248, over 4955.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03192, over 972596.68 frames.], batch size: 21, lr: 1.70e-04
+2022-05-07 16:04:13,564 INFO [train.py:715] (3/8) Epoch 13, batch 3300, loss[loss=0.1377, simple_loss=0.2097, pruned_loss=0.03287, over 4959.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03158, over 973457.87 frames.], batch size: 15, lr: 1.70e-04
+2022-05-07 16:04:51,388 INFO [train.py:715] (3/8) Epoch 13, batch 3350, loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03248, over 4933.00 frames.], tot_loss[loss=0.1369, simple_loss=0.211, pruned_loss=0.03142, over 974178.06 frames.], batch size: 29, lr: 1.70e-04
+2022-05-07 16:05:29,077 INFO [train.py:715] (3/8) Epoch 13, batch 3400, loss[loss=0.1246, simple_loss=0.2025, pruned_loss=0.02333, over 4798.00 frames.], tot_loss[loss=0.1368, simple_loss=0.211, pruned_loss=0.03127, over 974141.29 frames.], batch size: 12, lr: 1.70e-04
+2022-05-07 16:06:07,372 INFO [train.py:715] (3/8) Epoch 13, batch 3450, loss[loss=0.1465, simple_loss=0.21, pruned_loss=0.04146, over 4749.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.03156, over 974044.81 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 16:06:47,672 INFO [train.py:715] (3/8) Epoch 13, batch 3500, loss[loss=0.1214, simple_loss=0.1955, pruned_loss=0.02368, over 4821.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.0314, over 972841.71 frames.], batch size: 13, lr: 1.70e-04
+2022-05-07 16:07:25,031 INFO [train.py:715] (3/8) Epoch 13, batch 3550, loss[loss=0.1571, simple_loss=0.2205, pruned_loss=0.04689, over 4878.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2099, pruned_loss=0.03171, over 973008.66 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 16:08:03,490 INFO [train.py:715] (3/8) Epoch 13, batch 3600, loss[loss=0.1222, simple_loss=0.1912, pruned_loss=0.02657, over 4834.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2095, pruned_loss=0.03178, over 973014.09 frames.], batch size: 13, lr: 1.70e-04
+2022-05-07 16:08:41,278 INFO [train.py:715] (3/8) Epoch 13, batch 3650, loss[loss=0.1349, simple_loss=0.219, pruned_loss=0.02541, over 4803.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2106, pruned_loss=0.0323, over 972152.05 frames.], batch size: 21, lr: 1.70e-04
+2022-05-07 16:09:18,852 INFO [train.py:715] (3/8) Epoch 13, batch 3700, loss[loss=0.141, simple_loss=0.2108, pruned_loss=0.0356, over 4903.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03149, over 972903.03 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 16:09:56,568 INFO [train.py:715] (3/8) Epoch 13, batch 3750, loss[loss=0.1841, simple_loss=0.2417, pruned_loss=0.06324, over 4820.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03143, over 973151.43 frames.], batch size: 13, lr: 1.70e-04
+2022-05-07 16:10:34,803 INFO [train.py:715] (3/8) Epoch 13, batch 3800, loss[loss=0.1367, simple_loss=0.2084, pruned_loss=0.03257, over 4881.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2088, pruned_loss=0.03101, over 973316.76 frames.], batch size: 22, lr: 1.70e-04
+2022-05-07 16:11:11,947 INFO [train.py:715] (3/8) Epoch 13, batch 3850, loss[loss=0.1102, simple_loss=0.1921, pruned_loss=0.01411, over 4772.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2078, pruned_loss=0.03066, over 973023.72 frames.], batch size: 14, lr: 1.70e-04
+2022-05-07 16:11:49,244 INFO [train.py:715] (3/8) Epoch 13, batch 3900, loss[loss=0.1655, simple_loss=0.2376, pruned_loss=0.04668, over 4948.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2075, pruned_loss=0.03061, over 972935.31 frames.], batch size: 35, lr: 1.70e-04
+2022-05-07 16:12:27,131 INFO [train.py:715] (3/8) Epoch 13, batch 3950, loss[loss=0.1336, simple_loss=0.2061, pruned_loss=0.03057, over 4779.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2082, pruned_loss=0.03067, over 972778.40 frames.], batch size: 18, lr: 1.70e-04
+2022-05-07 16:13:05,300 INFO [train.py:715] (3/8) Epoch 13, batch 4000, loss[loss=0.1327, simple_loss=0.21, pruned_loss=0.02768, over 4782.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2078, pruned_loss=0.03059, over 971205.56 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 16:13:42,998 INFO [train.py:715] (3/8) Epoch 13, batch 4050, loss[loss=0.1292, simple_loss=0.2032, pruned_loss=0.02762, over 4750.00 frames.], tot_loss[loss=0.134, simple_loss=0.2071, pruned_loss=0.03043, over 971491.87 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 16:14:20,644 INFO [train.py:715] (3/8) Epoch 13, batch 4100, loss[loss=0.1361, simple_loss=0.2202, pruned_loss=0.02599, over 4922.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2077, pruned_loss=0.03046, over 971553.83 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 16:14:59,185 INFO [train.py:715] (3/8) Epoch 13, batch 4150, loss[loss=0.1392, simple_loss=0.2203, pruned_loss=0.029, over 4809.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.03002, over 971287.43 frames.], batch size: 21, lr: 1.70e-04
+2022-05-07 16:15:36,529 INFO [train.py:715] (3/8) Epoch 13, batch 4200, loss[loss=0.1388, simple_loss=0.2208, pruned_loss=0.02842, over 4943.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03083, over 971892.95 frames.], batch size: 21, lr: 1.70e-04
+2022-05-07 16:16:14,502 INFO [train.py:715] (3/8) Epoch 13, batch 4250, loss[loss=0.1409, simple_loss=0.2141, pruned_loss=0.03381, over 4775.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.0309, over 971142.42 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 16:16:52,599 INFO [train.py:715] (3/8) Epoch 13, batch 4300, loss[loss=0.1301, simple_loss=0.1979, pruned_loss=0.03113, over 4689.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03141, over 971067.79 frames.], batch size: 15, lr: 1.70e-04
+2022-05-07 16:17:30,605 INFO [train.py:715] (3/8) Epoch 13, batch 4350, loss[loss=0.1335, simple_loss=0.2091, pruned_loss=0.0289, over 4788.00 frames.], tot_loss[loss=0.1359, simple_loss=0.209, pruned_loss=0.03133, over 971635.06 frames.], batch size: 18, lr: 1.70e-04
+2022-05-07 16:18:08,277 INFO [train.py:715] (3/8) Epoch 13, batch 4400, loss[loss=0.1457, simple_loss=0.2172, pruned_loss=0.03715, over 4835.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2091, pruned_loss=0.03166, over 972098.68 frames.], batch size: 13, lr: 1.70e-04
+2022-05-07 16:18:46,446 INFO [train.py:715] (3/8) Epoch 13, batch 4450, loss[loss=0.1202, simple_loss=0.1917, pruned_loss=0.02435, over 4838.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2095, pruned_loss=0.03176, over 970985.03 frames.], batch size: 15, lr: 1.70e-04
+2022-05-07 16:19:25,668 INFO [train.py:715] (3/8) Epoch 13, batch 4500, loss[loss=0.1439, simple_loss=0.2161, pruned_loss=0.03583, over 4896.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03187, over 971434.51 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 16:20:03,830 INFO [train.py:715] (3/8) Epoch 13, batch 4550, loss[loss=0.1294, simple_loss=0.2121, pruned_loss=0.02331, over 4797.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.0318, over 972033.83 frames.], batch size: 25, lr: 1.70e-04
+2022-05-07 16:20:40,816 INFO [train.py:715] (3/8) Epoch 13, batch 4600, loss[loss=0.1384, simple_loss=0.2261, pruned_loss=0.02536, over 4947.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03164, over 971454.45 frames.], batch size: 23, lr: 1.70e-04
+2022-05-07 16:21:19,535 INFO [train.py:715] (3/8) Epoch 13, batch 4650, loss[loss=0.1551, simple_loss=0.223, pruned_loss=0.04354, over 4918.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03181, over 971759.82 frames.], batch size: 23, lr: 1.70e-04
+2022-05-07 16:21:57,440 INFO [train.py:715] (3/8) Epoch 13, batch 4700, loss[loss=0.1165, simple_loss=0.1865, pruned_loss=0.02327, over 4825.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03136, over 972413.27 frames.], batch size: 13, lr: 1.70e-04
+2022-05-07 16:22:35,613 INFO [train.py:715] (3/8) Epoch 13, batch 4750, loss[loss=0.1201, simple_loss=0.195, pruned_loss=0.02264, over 4685.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03086, over 971685.75 frames.], batch size: 15, lr: 1.70e-04
+2022-05-07 16:23:13,892 INFO [train.py:715] (3/8) Epoch 13, batch 4800, loss[loss=0.14, simple_loss=0.2178, pruned_loss=0.03109, over 4910.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03116, over 972763.67 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 16:23:53,168 INFO [train.py:715] (3/8) Epoch 13, batch 4850, loss[loss=0.1628, simple_loss=0.2387, pruned_loss=0.04343, over 4887.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03163, over 973462.52 frames.], batch size: 22, lr: 1.70e-04
+2022-05-07 16:24:31,291 INFO [train.py:715] (3/8) Epoch 13, batch 4900, loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.0289, over 4889.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03169, over 973242.52 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 16:25:10,150 INFO [train.py:715] (3/8) Epoch 13, batch 4950, loss[loss=0.1073, simple_loss=0.1808, pruned_loss=0.01691, over 4817.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03141, over 972688.70 frames.], batch size: 27, lr: 1.70e-04
+2022-05-07 16:25:49,563 INFO [train.py:715] (3/8) Epoch 13, batch 5000, loss[loss=0.1588, simple_loss=0.2243, pruned_loss=0.04661, over 4887.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03127, over 972254.38 frames.], batch size: 32, lr: 1.70e-04
+2022-05-07 16:26:28,898 INFO [train.py:715] (3/8) Epoch 13, batch 5050, loss[loss=0.1326, simple_loss=0.1977, pruned_loss=0.03377, over 4840.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.0315, over 971881.53 frames.], batch size: 30, lr: 1.70e-04
+2022-05-07 16:27:07,532 INFO [train.py:715] (3/8) Epoch 13, batch 5100, loss[loss=0.1587, simple_loss=0.2339, pruned_loss=0.04176, over 4983.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03164, over 972195.72 frames.], batch size: 39, lr: 1.70e-04
+2022-05-07 16:27:46,964 INFO [train.py:715] (3/8) Epoch 13, batch 5150, loss[loss=0.1336, simple_loss=0.2138, pruned_loss=0.02673, over 4774.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03149, over 972421.80 frames.], batch size: 14, lr: 1.70e-04
+2022-05-07 16:28:26,706 INFO [train.py:715] (3/8) Epoch 13, batch 5200, loss[loss=0.1168, simple_loss=0.1897, pruned_loss=0.02194, over 4744.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.0312, over 971778.14 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 16:29:06,555 INFO [train.py:715] (3/8) Epoch 13, batch 5250, loss[loss=0.1309, simple_loss=0.1985, pruned_loss=0.03161, over 4854.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03108, over 972585.30 frames.], batch size: 30, lr: 1.70e-04
+2022-05-07 16:29:45,232 INFO [train.py:715] (3/8) Epoch 13, batch 5300, loss[loss=0.1358, simple_loss=0.2053, pruned_loss=0.03314, over 4796.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03136, over 973545.29 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 16:30:25,374 INFO [train.py:715] (3/8) Epoch 13, batch 5350, loss[loss=0.1482, simple_loss=0.2207, pruned_loss=0.03782, over 4684.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03126, over 973702.99 frames.], batch size: 15, lr: 1.70e-04
+2022-05-07 16:31:05,477 INFO [train.py:715] (3/8) Epoch 13, batch 5400, loss[loss=0.1134, simple_loss=0.1842, pruned_loss=0.02129, over 4992.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03108, over 973434.96 frames.], batch size: 14, lr: 1.70e-04
+2022-05-07 16:31:45,406 INFO [train.py:715] (3/8) Epoch 13, batch 5450, loss[loss=0.1226, simple_loss=0.1919, pruned_loss=0.02665, over 4894.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03099, over 973456.30 frames.], batch size: 19, lr: 1.70e-04
+2022-05-07 16:32:24,988 INFO [train.py:715] (3/8) Epoch 13, batch 5500, loss[loss=0.1407, simple_loss=0.2186, pruned_loss=0.03142, over 4977.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03099, over 973420.70 frames.], batch size: 25, lr: 1.70e-04
+2022-05-07 16:33:04,814 INFO [train.py:715] (3/8) Epoch 13, batch 5550, loss[loss=0.1391, simple_loss=0.2165, pruned_loss=0.03085, over 4869.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03127, over 972314.33 frames.], batch size: 20, lr: 1.70e-04
+2022-05-07 16:33:44,070 INFO [train.py:715] (3/8) Epoch 13, batch 5600, loss[loss=0.1277, simple_loss=0.2039, pruned_loss=0.02579, over 4792.00 frames.], tot_loss[loss=0.1358, simple_loss=0.209, pruned_loss=0.03128, over 971909.59 frames.], batch size: 14, lr: 1.70e-04
+2022-05-07 16:34:23,513 INFO [train.py:715] (3/8) Epoch 13, batch 5650, loss[loss=0.1121, simple_loss=0.1889, pruned_loss=0.01766, over 4918.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2086, pruned_loss=0.0311, over 972222.04 frames.], batch size: 21, lr: 1.70e-04
+2022-05-07 16:35:03,786 INFO [train.py:715] (3/8) Epoch 13, batch 5700, loss[loss=0.1326, simple_loss=0.2044, pruned_loss=0.03044, over 4786.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2085, pruned_loss=0.03096, over 972421.91 frames.], batch size: 14, lr: 1.70e-04
+2022-05-07 16:35:43,899 INFO [train.py:715] (3/8) Epoch 13, batch 5750, loss[loss=0.18, simple_loss=0.2412, pruned_loss=0.05944, over 4888.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.0316, over 972246.91 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 16:36:22,747 INFO [train.py:715] (3/8) Epoch 13, batch 5800, loss[loss=0.1442, simple_loss=0.2109, pruned_loss=0.03879, over 4928.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2085, pruned_loss=0.03116, over 972406.28 frames.], batch size: 39, lr: 1.70e-04
+2022-05-07 16:37:02,238 INFO [train.py:715] (3/8) Epoch 13, batch 5850, loss[loss=0.1324, simple_loss=0.2046, pruned_loss=0.03009, over 4926.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2089, pruned_loss=0.03122, over 972582.15 frames.], batch size: 23, lr: 1.70e-04
+2022-05-07 16:37:42,376 INFO [train.py:715] (3/8) Epoch 13, batch 5900, loss[loss=0.153, simple_loss=0.2289, pruned_loss=0.03854, over 4989.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2088, pruned_loss=0.031, over 972398.65 frames.], batch size: 25, lr: 1.70e-04
+2022-05-07 16:38:21,735 INFO [train.py:715] (3/8) Epoch 13, batch 5950, loss[loss=0.1619, simple_loss=0.233, pruned_loss=0.04536, over 4902.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03105, over 971492.59 frames.], batch size: 19, lr: 1.70e-04
+2022-05-07 16:39:01,216 INFO [train.py:715] (3/8) Epoch 13, batch 6000, loss[loss=0.1163, simple_loss=0.1819, pruned_loss=0.02533, over 4913.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03054, over 971106.48 frames.], batch size: 18, lr: 1.70e-04
+2022-05-07 16:39:01,217 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 16:39:10,780 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1893, pruned_loss=0.01078, over 914524.00 frames.
+2022-05-07 16:39:50,261 INFO [train.py:715] (3/8) Epoch 13, batch 6050, loss[loss=0.1109, simple_loss=0.1866, pruned_loss=0.0176, over 4912.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.0308, over 972164.00 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 16:40:29,776 INFO [train.py:715] (3/8) Epoch 13, batch 6100, loss[loss=0.1445, simple_loss=0.2132, pruned_loss=0.03792, over 4845.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2084, pruned_loss=0.03087, over 971543.22 frames.], batch size: 15, lr: 1.70e-04
+2022-05-07 16:41:09,343 INFO [train.py:715] (3/8) Epoch 13, batch 6150, loss[loss=0.1325, simple_loss=0.2044, pruned_loss=0.0303, over 4763.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03117, over 971663.17 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 16:41:47,239 INFO [train.py:715] (3/8) Epoch 13, batch 6200, loss[loss=0.1368, simple_loss=0.2169, pruned_loss=0.02838, over 4871.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03095, over 971352.87 frames.], batch size: 22, lr: 1.70e-04
+2022-05-07 16:42:26,291 INFO [train.py:715] (3/8) Epoch 13, batch 6250, loss[loss=0.1364, simple_loss=0.2163, pruned_loss=0.02826, over 4875.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03116, over 971495.68 frames.], batch size: 22, lr: 1.70e-04
+2022-05-07 16:43:05,824 INFO [train.py:715] (3/8) Epoch 13, batch 6300, loss[loss=0.1192, simple_loss=0.1936, pruned_loss=0.02242, over 4915.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03149, over 971876.13 frames.], batch size: 23, lr: 1.70e-04
+2022-05-07 16:43:44,412 INFO [train.py:715] (3/8) Epoch 13, batch 6350, loss[loss=0.149, simple_loss=0.2228, pruned_loss=0.03759, over 4911.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03111, over 972321.31 frames.], batch size: 23, lr: 1.70e-04
+2022-05-07 16:44:24,228 INFO [train.py:715] (3/8) Epoch 13, batch 6400, loss[loss=0.1593, simple_loss=0.2197, pruned_loss=0.04948, over 4851.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.0312, over 972450.34 frames.], batch size: 32, lr: 1.70e-04
+2022-05-07 16:45:04,048 INFO [train.py:715] (3/8) Epoch 13, batch 6450, loss[loss=0.1279, simple_loss=0.1954, pruned_loss=0.03021, over 4917.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03146, over 972003.39 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 16:45:44,140 INFO [train.py:715] (3/8) Epoch 13, batch 6500, loss[loss=0.1331, simple_loss=0.2032, pruned_loss=0.03154, over 4804.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03101, over 972526.86 frames.], batch size: 21, lr: 1.70e-04
+2022-05-07 16:46:23,313 INFO [train.py:715] (3/8) Epoch 13, batch 6550, loss[loss=0.1147, simple_loss=0.1879, pruned_loss=0.02077, over 4810.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03174, over 972381.17 frames.], batch size: 21, lr: 1.70e-04
+2022-05-07 16:47:02,650 INFO [train.py:715] (3/8) Epoch 13, batch 6600, loss[loss=0.1183, simple_loss=0.2037, pruned_loss=0.01643, over 4812.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03165, over 972463.17 frames.], batch size: 26, lr: 1.70e-04
+2022-05-07 16:47:42,041 INFO [train.py:715] (3/8) Epoch 13, batch 6650, loss[loss=0.1485, simple_loss=0.2156, pruned_loss=0.04066, over 4993.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.03149, over 972450.91 frames.], batch size: 14, lr: 1.70e-04
+2022-05-07 16:48:20,276 INFO [train.py:715] (3/8) Epoch 13, batch 6700, loss[loss=0.1405, simple_loss=0.2172, pruned_loss=0.03189, over 4960.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.03149, over 971250.54 frames.], batch size: 35, lr: 1.70e-04
+2022-05-07 16:48:58,715 INFO [train.py:715] (3/8) Epoch 13, batch 6750, loss[loss=0.1592, simple_loss=0.2307, pruned_loss=0.04383, over 4865.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03123, over 971491.96 frames.], batch size: 32, lr: 1.70e-04
+2022-05-07 16:49:37,982 INFO [train.py:715] (3/8) Epoch 13, batch 6800, loss[loss=0.1505, simple_loss=0.2111, pruned_loss=0.04491, over 4873.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03111, over 971893.08 frames.], batch size: 32, lr: 1.70e-04
+2022-05-07 16:50:17,431 INFO [train.py:715] (3/8) Epoch 13, batch 6850, loss[loss=0.1709, simple_loss=0.2394, pruned_loss=0.05116, over 4779.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03119, over 972049.65 frames.], batch size: 14, lr: 1.70e-04
+2022-05-07 16:50:55,364 INFO [train.py:715] (3/8) Epoch 13, batch 6900, loss[loss=0.152, simple_loss=0.2199, pruned_loss=0.04202, over 4686.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2098, pruned_loss=0.03187, over 971549.70 frames.], batch size: 15, lr: 1.70e-04
+2022-05-07 16:51:33,403 INFO [train.py:715] (3/8) Epoch 13, batch 6950, loss[loss=0.1446, simple_loss=0.2082, pruned_loss=0.04048, over 4890.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03191, over 971295.18 frames.], batch size: 19, lr: 1.70e-04
+2022-05-07 16:52:12,640 INFO [train.py:715] (3/8) Epoch 13, batch 7000, loss[loss=0.1674, simple_loss=0.2389, pruned_loss=0.04792, over 4866.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03204, over 972225.77 frames.], batch size: 30, lr: 1.70e-04
+2022-05-07 16:52:51,282 INFO [train.py:715] (3/8) Epoch 13, batch 7050, loss[loss=0.1288, simple_loss=0.205, pruned_loss=0.02635, over 4967.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03163, over 971825.41 frames.], batch size: 35, lr: 1.70e-04
+2022-05-07 16:53:30,246 INFO [train.py:715] (3/8) Epoch 13, batch 7100, loss[loss=0.1148, simple_loss=0.1971, pruned_loss=0.01621, over 4943.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03097, over 971658.26 frames.], batch size: 29, lr: 1.70e-04
+2022-05-07 16:54:09,705 INFO [train.py:715] (3/8) Epoch 13, batch 7150, loss[loss=0.1121, simple_loss=0.1909, pruned_loss=0.01668, over 4816.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03147, over 971537.00 frames.], batch size: 26, lr: 1.70e-04
+2022-05-07 16:54:49,406 INFO [train.py:715] (3/8) Epoch 13, batch 7200, loss[loss=0.148, simple_loss=0.2292, pruned_loss=0.03345, over 4799.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03124, over 972288.18 frames.], batch size: 24, lr: 1.70e-04
+2022-05-07 16:55:27,554 INFO [train.py:715] (3/8) Epoch 13, batch 7250, loss[loss=0.141, simple_loss=0.2198, pruned_loss=0.03104, over 4734.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03101, over 971886.59 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 16:56:05,825 INFO [train.py:715] (3/8) Epoch 13, batch 7300, loss[loss=0.1312, simple_loss=0.204, pruned_loss=0.02918, over 4778.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03125, over 972117.29 frames.], batch size: 18, lr: 1.70e-04
+2022-05-07 16:56:45,077 INFO [train.py:715] (3/8) Epoch 13, batch 7350, loss[loss=0.1416, simple_loss=0.2258, pruned_loss=0.02866, over 4814.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.0311, over 972750.54 frames.], batch size: 25, lr: 1.70e-04
+2022-05-07 16:57:23,717 INFO [train.py:715] (3/8) Epoch 13, batch 7400, loss[loss=0.1401, simple_loss=0.2109, pruned_loss=0.03464, over 4809.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03155, over 973339.41 frames.], batch size: 25, lr: 1.70e-04
+2022-05-07 16:58:01,540 INFO [train.py:715] (3/8) Epoch 13, batch 7450, loss[loss=0.15, simple_loss=0.2158, pruned_loss=0.04213, over 4750.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03051, over 973527.89 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 16:58:40,994 INFO [train.py:715] (3/8) Epoch 13, batch 7500, loss[loss=0.1593, simple_loss=0.2365, pruned_loss=0.041, over 4942.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03031, over 973125.46 frames.], batch size: 21, lr: 1.70e-04
+2022-05-07 16:59:20,235 INFO [train.py:715] (3/8) Epoch 13, batch 7550, loss[loss=0.1295, simple_loss=0.2086, pruned_loss=0.02518, over 4878.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03002, over 973178.61 frames.], batch size: 20, lr: 1.70e-04
+2022-05-07 16:59:57,837 INFO [train.py:715] (3/8) Epoch 13, batch 7600, loss[loss=0.1425, simple_loss=0.2197, pruned_loss=0.03266, over 4983.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2089, pruned_loss=0.03008, over 973758.52 frames.], batch size: 25, lr: 1.70e-04
+2022-05-07 17:00:36,715 INFO [train.py:715] (3/8) Epoch 13, batch 7650, loss[loss=0.1407, simple_loss=0.2176, pruned_loss=0.03192, over 4810.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03043, over 973158.70 frames.], batch size: 15, lr: 1.70e-04
+2022-05-07 17:01:15,685 INFO [train.py:715] (3/8) Epoch 13, batch 7700, loss[loss=0.1768, simple_loss=0.237, pruned_loss=0.05835, over 4881.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03022, over 973614.98 frames.], batch size: 16, lr: 1.70e-04
+2022-05-07 17:01:54,650 INFO [train.py:715] (3/8) Epoch 13, batch 7750, loss[loss=0.1411, simple_loss=0.2132, pruned_loss=0.03444, over 4788.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03076, over 973453.54 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 17:02:32,576 INFO [train.py:715] (3/8) Epoch 13, batch 7800, loss[loss=0.1328, simple_loss=0.2201, pruned_loss=0.02277, over 4758.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03099, over 973256.95 frames.], batch size: 19, lr: 1.70e-04
+2022-05-07 17:03:11,061 INFO [train.py:715] (3/8) Epoch 13, batch 7850, loss[loss=0.1708, simple_loss=0.239, pruned_loss=0.0513, over 4843.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03106, over 972930.12 frames.], batch size: 32, lr: 1.70e-04
+2022-05-07 17:03:50,704 INFO [train.py:715] (3/8) Epoch 13, batch 7900, loss[loss=0.1579, simple_loss=0.229, pruned_loss=0.04339, over 4846.00 frames.], tot_loss[loss=0.136, simple_loss=0.2101, pruned_loss=0.03094, over 973401.47 frames.], batch size: 20, lr: 1.70e-04
+2022-05-07 17:04:28,752 INFO [train.py:715] (3/8) Epoch 13, batch 7950, loss[loss=0.1319, simple_loss=0.2092, pruned_loss=0.02736, over 4913.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03088, over 974063.36 frames.], batch size: 17, lr: 1.70e-04
+2022-05-07 17:05:07,214 INFO [train.py:715] (3/8) Epoch 13, batch 8000, loss[loss=0.1662, simple_loss=0.222, pruned_loss=0.05515, over 4916.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03124, over 973971.12 frames.], batch size: 19, lr: 1.70e-04
+2022-05-07 17:05:45,982 INFO [train.py:715] (3/8) Epoch 13, batch 8050, loss[loss=0.1559, simple_loss=0.2323, pruned_loss=0.03971, over 4938.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2111, pruned_loss=0.03164, over 973992.94 frames.], batch size: 29, lr: 1.70e-04
+2022-05-07 17:06:24,532 INFO [train.py:715] (3/8) Epoch 13, batch 8100, loss[loss=0.1374, simple_loss=0.2071, pruned_loss=0.03383, over 4946.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2113, pruned_loss=0.03188, over 973365.52 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 17:07:02,516 INFO [train.py:715] (3/8) Epoch 13, batch 8150, loss[loss=0.1311, simple_loss=0.2137, pruned_loss=0.02422, over 4836.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2115, pruned_loss=0.03216, over 971779.74 frames.], batch size: 26, lr: 1.69e-04
+2022-05-07 17:07:40,993 INFO [train.py:715] (3/8) Epoch 13, batch 8200, loss[loss=0.1581, simple_loss=0.2265, pruned_loss=0.04488, over 4756.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.032, over 971121.71 frames.], batch size: 14, lr: 1.69e-04
+2022-05-07 17:08:20,204 INFO [train.py:715] (3/8) Epoch 13, batch 8250, loss[loss=0.1606, simple_loss=0.2274, pruned_loss=0.0469, over 4771.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03202, over 970656.21 frames.], batch size: 17, lr: 1.69e-04
+2022-05-07 17:08:58,110 INFO [train.py:715] (3/8) Epoch 13, batch 8300, loss[loss=0.1389, simple_loss=0.206, pruned_loss=0.03586, over 4871.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03222, over 971745.86 frames.], batch size: 32, lr: 1.69e-04
+2022-05-07 17:09:36,542 INFO [train.py:715] (3/8) Epoch 13, batch 8350, loss[loss=0.17, simple_loss=0.2412, pruned_loss=0.04934, over 4856.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03199, over 971252.00 frames.], batch size: 32, lr: 1.69e-04
+2022-05-07 17:10:15,703 INFO [train.py:715] (3/8) Epoch 13, batch 8400, loss[loss=0.1647, simple_loss=0.2328, pruned_loss=0.04825, over 4902.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2121, pruned_loss=0.03212, over 971299.82 frames.], batch size: 17, lr: 1.69e-04
+2022-05-07 17:10:54,563 INFO [train.py:715] (3/8) Epoch 13, batch 8450, loss[loss=0.1099, simple_loss=0.183, pruned_loss=0.01836, over 4691.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2119, pruned_loss=0.03195, over 971709.32 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 17:11:32,554 INFO [train.py:715] (3/8) Epoch 13, batch 8500, loss[loss=0.1187, simple_loss=0.1962, pruned_loss=0.02059, over 4900.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2118, pruned_loss=0.03218, over 972687.58 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:12:11,696 INFO [train.py:715] (3/8) Epoch 13, batch 8550, loss[loss=0.1284, simple_loss=0.2018, pruned_loss=0.02748, over 4758.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03192, over 972818.69 frames.], batch size: 19, lr: 1.69e-04
+2022-05-07 17:12:50,647 INFO [train.py:715] (3/8) Epoch 13, batch 8600, loss[loss=0.147, simple_loss=0.2105, pruned_loss=0.04176, over 4796.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03158, over 971999.84 frames.], batch size: 14, lr: 1.69e-04
+2022-05-07 17:13:28,882 INFO [train.py:715] (3/8) Epoch 13, batch 8650, loss[loss=0.1015, simple_loss=0.1697, pruned_loss=0.01667, over 4884.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.03154, over 972073.00 frames.], batch size: 22, lr: 1.69e-04
+2022-05-07 17:14:07,226 INFO [train.py:715] (3/8) Epoch 13, batch 8700, loss[loss=0.1369, simple_loss=0.2143, pruned_loss=0.02974, over 4934.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.03179, over 972316.92 frames.], batch size: 23, lr: 1.69e-04
+2022-05-07 17:14:45,867 INFO [train.py:715] (3/8) Epoch 13, batch 8750, loss[loss=0.1376, simple_loss=0.204, pruned_loss=0.03563, over 4943.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03208, over 973113.29 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 17:15:24,586 INFO [train.py:715] (3/8) Epoch 13, batch 8800, loss[loss=0.1441, simple_loss=0.2191, pruned_loss=0.03453, over 4799.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03192, over 972948.97 frames.], batch size: 25, lr: 1.69e-04
+2022-05-07 17:16:02,885 INFO [train.py:715] (3/8) Epoch 13, batch 8850, loss[loss=0.1369, simple_loss=0.2157, pruned_loss=0.02904, over 4969.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2112, pruned_loss=0.03175, over 972646.02 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 17:16:40,974 INFO [train.py:715] (3/8) Epoch 13, batch 8900, loss[loss=0.1318, simple_loss=0.2084, pruned_loss=0.0276, over 4776.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03201, over 972571.68 frames.], batch size: 17, lr: 1.69e-04
+2022-05-07 17:17:19,699 INFO [train.py:715] (3/8) Epoch 13, batch 8950, loss[loss=0.1699, simple_loss=0.236, pruned_loss=0.05188, over 4709.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03133, over 971915.77 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 17:17:57,826 INFO [train.py:715] (3/8) Epoch 13, batch 9000, loss[loss=0.1465, simple_loss=0.23, pruned_loss=0.03154, over 4923.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03148, over 971879.78 frames.], batch size: 39, lr: 1.69e-04
+2022-05-07 17:17:57,827 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 17:18:07,451 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1055, simple_loss=0.1893, pruned_loss=0.01084, over 914524.00 frames.
+2022-05-07 17:18:45,503 INFO [train.py:715] (3/8) Epoch 13, batch 9050, loss[loss=0.1371, simple_loss=0.2239, pruned_loss=0.02515, over 4901.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2093, pruned_loss=0.0316, over 972652.06 frames.], batch size: 19, lr: 1.69e-04
+2022-05-07 17:19:23,911 INFO [train.py:715] (3/8) Epoch 13, batch 9100, loss[loss=0.1497, simple_loss=0.2289, pruned_loss=0.03525, over 4921.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03106, over 973001.14 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:20:03,100 INFO [train.py:715] (3/8) Epoch 13, batch 9150, loss[loss=0.1632, simple_loss=0.2316, pruned_loss=0.04741, over 4812.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03108, over 972549.28 frames.], batch size: 25, lr: 1.69e-04
+2022-05-07 17:20:42,097 INFO [train.py:715] (3/8) Epoch 13, batch 9200, loss[loss=0.1551, simple_loss=0.2232, pruned_loss=0.04345, over 4700.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03143, over 972472.18 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 17:21:20,012 INFO [train.py:715] (3/8) Epoch 13, batch 9250, loss[loss=0.1349, simple_loss=0.2076, pruned_loss=0.03108, over 4892.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03132, over 972642.60 frames.], batch size: 16, lr: 1.69e-04
+2022-05-07 17:21:58,915 INFO [train.py:715] (3/8) Epoch 13, batch 9300, loss[loss=0.1192, simple_loss=0.1986, pruned_loss=0.01996, over 4870.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03125, over 971652.16 frames.], batch size: 16, lr: 1.69e-04
+2022-05-07 17:22:37,767 INFO [train.py:715] (3/8) Epoch 13, batch 9350, loss[loss=0.1538, simple_loss=0.2319, pruned_loss=0.03784, over 4882.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03114, over 971741.97 frames.], batch size: 22, lr: 1.69e-04
+2022-05-07 17:23:15,581 INFO [train.py:715] (3/8) Epoch 13, batch 9400, loss[loss=0.1346, simple_loss=0.2074, pruned_loss=0.0309, over 4960.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03109, over 972209.27 frames.], batch size: 24, lr: 1.69e-04
+2022-05-07 17:23:54,032 INFO [train.py:715] (3/8) Epoch 13, batch 9450, loss[loss=0.1293, simple_loss=0.1976, pruned_loss=0.03045, over 4948.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03091, over 971998.25 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 17:24:32,854 INFO [train.py:715] (3/8) Epoch 13, batch 9500, loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02921, over 4921.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03075, over 972015.19 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:25:11,109 INFO [train.py:715] (3/8) Epoch 13, batch 9550, loss[loss=0.145, simple_loss=0.2145, pruned_loss=0.03773, over 4775.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.0314, over 971667.27 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:25:49,079 INFO [train.py:715] (3/8) Epoch 13, batch 9600, loss[loss=0.1294, simple_loss=0.1953, pruned_loss=0.03169, over 4973.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03118, over 971836.85 frames.], batch size: 14, lr: 1.69e-04
+2022-05-07 17:26:28,021 INFO [train.py:715] (3/8) Epoch 13, batch 9650, loss[loss=0.1371, simple_loss=0.2058, pruned_loss=0.03425, over 4937.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03131, over 971848.57 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:27:06,438 INFO [train.py:715] (3/8) Epoch 13, batch 9700, loss[loss=0.1377, simple_loss=0.2069, pruned_loss=0.03422, over 4969.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03168, over 972345.49 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 17:27:44,979 INFO [train.py:715] (3/8) Epoch 13, batch 9750, loss[loss=0.1322, simple_loss=0.1964, pruned_loss=0.03402, over 4957.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03171, over 971893.99 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 17:28:23,843 INFO [train.py:715] (3/8) Epoch 13, batch 9800, loss[loss=0.1344, simple_loss=0.2013, pruned_loss=0.03379, over 4907.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03127, over 971733.47 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:29:03,034 INFO [train.py:715] (3/8) Epoch 13, batch 9850, loss[loss=0.1228, simple_loss=0.2037, pruned_loss=0.02099, over 4899.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03132, over 972087.13 frames.], batch size: 22, lr: 1.69e-04
+2022-05-07 17:29:41,582 INFO [train.py:715] (3/8) Epoch 13, batch 9900, loss[loss=0.1383, simple_loss=0.2102, pruned_loss=0.03325, over 4943.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03149, over 972944.93 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 17:30:19,824 INFO [train.py:715] (3/8) Epoch 13, batch 9950, loss[loss=0.1398, simple_loss=0.2104, pruned_loss=0.03456, over 4864.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03138, over 973570.56 frames.], batch size: 30, lr: 1.69e-04
+2022-05-07 17:30:58,616 INFO [train.py:715] (3/8) Epoch 13, batch 10000, loss[loss=0.124, simple_loss=0.198, pruned_loss=0.02496, over 4954.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03111, over 973481.40 frames.], batch size: 24, lr: 1.69e-04
+2022-05-07 17:31:37,786 INFO [train.py:715] (3/8) Epoch 13, batch 10050, loss[loss=0.1505, simple_loss=0.2225, pruned_loss=0.03923, over 4863.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03154, over 973435.75 frames.], batch size: 30, lr: 1.69e-04
+2022-05-07 17:32:16,721 INFO [train.py:715] (3/8) Epoch 13, batch 10100, loss[loss=0.1384, simple_loss=0.218, pruned_loss=0.02936, over 4797.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.0316, over 972694.12 frames.], batch size: 17, lr: 1.69e-04
+2022-05-07 17:32:54,965 INFO [train.py:715] (3/8) Epoch 13, batch 10150, loss[loss=0.1552, simple_loss=0.2159, pruned_loss=0.0473, over 4746.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.03183, over 972623.53 frames.], batch size: 16, lr: 1.69e-04
+2022-05-07 17:33:33,998 INFO [train.py:715] (3/8) Epoch 13, batch 10200, loss[loss=0.1115, simple_loss=0.1875, pruned_loss=0.01771, over 4784.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03201, over 973066.93 frames.], batch size: 14, lr: 1.69e-04
+2022-05-07 17:34:13,393 INFO [train.py:715] (3/8) Epoch 13, batch 10250, loss[loss=0.1361, simple_loss=0.2141, pruned_loss=0.02907, over 4914.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03139, over 972496.55 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:34:52,083 INFO [train.py:715] (3/8) Epoch 13, batch 10300, loss[loss=0.1289, simple_loss=0.206, pruned_loss=0.02587, over 4846.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2101, pruned_loss=0.03086, over 972758.11 frames.], batch size: 20, lr: 1.69e-04
+2022-05-07 17:35:31,127 INFO [train.py:715] (3/8) Epoch 13, batch 10350, loss[loss=0.157, simple_loss=0.2297, pruned_loss=0.04212, over 4972.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03117, over 973114.63 frames.], batch size: 28, lr: 1.69e-04
+2022-05-07 17:36:10,304 INFO [train.py:715] (3/8) Epoch 13, batch 10400, loss[loss=0.15, simple_loss=0.2071, pruned_loss=0.04646, over 4808.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03185, over 972494.61 frames.], batch size: 13, lr: 1.69e-04
+2022-05-07 17:36:49,251 INFO [train.py:715] (3/8) Epoch 13, batch 10450, loss[loss=0.158, simple_loss=0.2228, pruned_loss=0.04655, over 4883.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03158, over 972269.71 frames.], batch size: 22, lr: 1.69e-04
+2022-05-07 17:37:26,678 INFO [train.py:715] (3/8) Epoch 13, batch 10500, loss[loss=0.1281, simple_loss=0.2046, pruned_loss=0.02585, over 4749.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03218, over 972372.77 frames.], batch size: 16, lr: 1.69e-04
+2022-05-07 17:38:05,567 INFO [train.py:715] (3/8) Epoch 13, batch 10550, loss[loss=0.1209, simple_loss=0.2056, pruned_loss=0.01812, over 4798.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03223, over 972537.51 frames.], batch size: 13, lr: 1.69e-04
+2022-05-07 17:38:44,488 INFO [train.py:715] (3/8) Epoch 13, batch 10600, loss[loss=0.132, simple_loss=0.2124, pruned_loss=0.02581, over 4886.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2118, pruned_loss=0.03218, over 972676.36 frames.], batch size: 22, lr: 1.69e-04
+2022-05-07 17:39:22,595 INFO [train.py:715] (3/8) Epoch 13, batch 10650, loss[loss=0.1441, simple_loss=0.2214, pruned_loss=0.0334, over 4792.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2117, pruned_loss=0.03182, over 971964.19 frames.], batch size: 17, lr: 1.69e-04
+2022-05-07 17:40:01,765 INFO [train.py:715] (3/8) Epoch 13, batch 10700, loss[loss=0.1437, simple_loss=0.2243, pruned_loss=0.03152, over 4701.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03134, over 972434.93 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 17:40:41,062 INFO [train.py:715] (3/8) Epoch 13, batch 10750, loss[loss=0.1116, simple_loss=0.1896, pruned_loss=0.01684, over 4937.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03132, over 972979.24 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 17:41:19,861 INFO [train.py:715] (3/8) Epoch 13, batch 10800, loss[loss=0.1667, simple_loss=0.2336, pruned_loss=0.04989, over 4838.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03132, over 972979.62 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 17:41:57,881 INFO [train.py:715] (3/8) Epoch 13, batch 10850, loss[loss=0.1388, simple_loss=0.2139, pruned_loss=0.03189, over 4830.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03128, over 973638.27 frames.], batch size: 30, lr: 1.69e-04
+2022-05-07 17:42:37,032 INFO [train.py:715] (3/8) Epoch 13, batch 10900, loss[loss=0.1245, simple_loss=0.2025, pruned_loss=0.02328, over 4786.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03166, over 973353.23 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:43:16,892 INFO [train.py:715] (3/8) Epoch 13, batch 10950, loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03473, over 4869.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03175, over 974318.90 frames.], batch size: 20, lr: 1.69e-04
+2022-05-07 17:43:56,321 INFO [train.py:715] (3/8) Epoch 13, batch 11000, loss[loss=0.1402, simple_loss=0.2173, pruned_loss=0.0315, over 4941.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03156, over 974375.54 frames.], batch size: 23, lr: 1.69e-04
+2022-05-07 17:44:34,954 INFO [train.py:715] (3/8) Epoch 13, batch 11050, loss[loss=0.1466, simple_loss=0.2066, pruned_loss=0.0433, over 4964.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.032, over 974062.47 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 17:45:14,252 INFO [train.py:715] (3/8) Epoch 13, batch 11100, loss[loss=0.1482, simple_loss=0.2214, pruned_loss=0.03751, over 4879.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2099, pruned_loss=0.03171, over 973188.44 frames.], batch size: 16, lr: 1.69e-04
+2022-05-07 17:45:53,236 INFO [train.py:715] (3/8) Epoch 13, batch 11150, loss[loss=0.144, simple_loss=0.2207, pruned_loss=0.03365, over 4824.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03146, over 973209.72 frames.], batch size: 25, lr: 1.69e-04
+2022-05-07 17:46:30,991 INFO [train.py:715] (3/8) Epoch 13, batch 11200, loss[loss=0.1299, simple_loss=0.2039, pruned_loss=0.02792, over 4799.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03154, over 972519.20 frames.], batch size: 17, lr: 1.69e-04
+2022-05-07 17:47:09,193 INFO [train.py:715] (3/8) Epoch 13, batch 11250, loss[loss=0.1368, simple_loss=0.1999, pruned_loss=0.03685, over 4838.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2086, pruned_loss=0.03146, over 973312.44 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 17:47:48,139 INFO [train.py:715] (3/8) Epoch 13, batch 11300, loss[loss=0.1474, simple_loss=0.2167, pruned_loss=0.03905, over 4845.00 frames.], tot_loss[loss=0.135, simple_loss=0.2081, pruned_loss=0.03098, over 973349.75 frames.], batch size: 30, lr: 1.69e-04
+2022-05-07 17:48:27,086 INFO [train.py:715] (3/8) Epoch 13, batch 11350, loss[loss=0.1531, simple_loss=0.2204, pruned_loss=0.04291, over 4946.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2093, pruned_loss=0.03162, over 973017.07 frames.], batch size: 35, lr: 1.69e-04
+2022-05-07 17:49:05,292 INFO [train.py:715] (3/8) Epoch 13, batch 11400, loss[loss=0.1071, simple_loss=0.1797, pruned_loss=0.01721, over 4976.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2086, pruned_loss=0.03158, over 972963.83 frames.], batch size: 14, lr: 1.69e-04
+2022-05-07 17:49:44,157 INFO [train.py:715] (3/8) Epoch 13, batch 11450, loss[loss=0.1224, simple_loss=0.2006, pruned_loss=0.0221, over 4927.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2086, pruned_loss=0.03132, over 973332.43 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:50:25,718 INFO [train.py:715] (3/8) Epoch 13, batch 11500, loss[loss=0.1243, simple_loss=0.197, pruned_loss=0.02582, over 4781.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03139, over 973235.58 frames.], batch size: 17, lr: 1.69e-04
+2022-05-07 17:51:03,652 INFO [train.py:715] (3/8) Epoch 13, batch 11550, loss[loss=0.1161, simple_loss=0.1931, pruned_loss=0.01956, over 4965.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03137, over 972907.38 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 17:51:42,315 INFO [train.py:715] (3/8) Epoch 13, batch 11600, loss[loss=0.1474, simple_loss=0.2261, pruned_loss=0.03433, over 4757.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03122, over 972974.89 frames.], batch size: 16, lr: 1.69e-04
+2022-05-07 17:52:21,599 INFO [train.py:715] (3/8) Epoch 13, batch 11650, loss[loss=0.1423, simple_loss=0.2151, pruned_loss=0.03478, over 4912.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03121, over 973511.36 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:53:00,308 INFO [train.py:715] (3/8) Epoch 13, batch 11700, loss[loss=0.115, simple_loss=0.1862, pruned_loss=0.02189, over 4808.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03132, over 973806.48 frames.], batch size: 14, lr: 1.69e-04
+2022-05-07 17:53:38,277 INFO [train.py:715] (3/8) Epoch 13, batch 11750, loss[loss=0.1323, simple_loss=0.2137, pruned_loss=0.02545, over 4784.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03114, over 973774.73 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 17:54:16,754 INFO [train.py:715] (3/8) Epoch 13, batch 11800, loss[loss=0.1376, simple_loss=0.2068, pruned_loss=0.0342, over 4881.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03091, over 974262.07 frames.], batch size: 22, lr: 1.69e-04
+2022-05-07 17:54:55,480 INFO [train.py:715] (3/8) Epoch 13, batch 11850, loss[loss=0.1212, simple_loss=0.1966, pruned_loss=0.02291, over 4824.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03127, over 974460.27 frames.], batch size: 25, lr: 1.69e-04
+2022-05-07 17:55:32,888 INFO [train.py:715] (3/8) Epoch 13, batch 11900, loss[loss=0.1248, simple_loss=0.2005, pruned_loss=0.02456, over 4946.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03119, over 974314.56 frames.], batch size: 39, lr: 1.69e-04
+2022-05-07 17:56:11,548 INFO [train.py:715] (3/8) Epoch 13, batch 11950, loss[loss=0.1589, simple_loss=0.238, pruned_loss=0.03991, over 4803.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03103, over 973679.84 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 17:56:50,610 INFO [train.py:715] (3/8) Epoch 13, batch 12000, loss[loss=0.1611, simple_loss=0.2371, pruned_loss=0.04254, over 4962.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03172, over 973809.46 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 17:56:50,611 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 17:57:00,356 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1055, simple_loss=0.1893, pruned_loss=0.01081, over 914524.00 frames.
+2022-05-07 17:57:40,025 INFO [train.py:715] (3/8) Epoch 13, batch 12050, loss[loss=0.1605, simple_loss=0.2423, pruned_loss=0.03938, over 4978.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03181, over 974145.37 frames.], batch size: 28, lr: 1.69e-04
+2022-05-07 17:58:18,317 INFO [train.py:715] (3/8) Epoch 13, batch 12100, loss[loss=0.1337, simple_loss=0.2125, pruned_loss=0.02747, over 4980.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03109, over 973366.59 frames.], batch size: 24, lr: 1.69e-04
+2022-05-07 17:58:56,072 INFO [train.py:715] (3/8) Epoch 13, batch 12150, loss[loss=0.1301, simple_loss=0.1999, pruned_loss=0.03012, over 4977.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03093, over 973597.31 frames.], batch size: 35, lr: 1.69e-04
+2022-05-07 17:59:34,973 INFO [train.py:715] (3/8) Epoch 13, batch 12200, loss[loss=0.1662, simple_loss=0.2181, pruned_loss=0.05711, over 4651.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03111, over 972925.66 frames.], batch size: 13, lr: 1.69e-04
+2022-05-07 18:00:13,890 INFO [train.py:715] (3/8) Epoch 13, batch 12250, loss[loss=0.1282, simple_loss=0.2027, pruned_loss=0.02689, over 4960.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03088, over 973754.07 frames.], batch size: 24, lr: 1.69e-04
+2022-05-07 18:00:52,459 INFO [train.py:715] (3/8) Epoch 13, batch 12300, loss[loss=0.1599, simple_loss=0.2313, pruned_loss=0.04424, over 4861.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03103, over 973099.85 frames.], batch size: 20, lr: 1.69e-04
+2022-05-07 18:01:30,136 INFO [train.py:715] (3/8) Epoch 13, batch 12350, loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02784, over 4886.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2097, pruned_loss=0.03077, over 973489.72 frames.], batch size: 32, lr: 1.69e-04
+2022-05-07 18:02:09,068 INFO [train.py:715] (3/8) Epoch 13, batch 12400, loss[loss=0.1522, simple_loss=0.2327, pruned_loss=0.03581, over 4760.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2093, pruned_loss=0.03017, over 973438.09 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 18:02:47,459 INFO [train.py:715] (3/8) Epoch 13, batch 12450, loss[loss=0.1519, simple_loss=0.2158, pruned_loss=0.04407, over 4950.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03056, over 973834.26 frames.], batch size: 39, lr: 1.69e-04
+2022-05-07 18:03:24,472 INFO [train.py:715] (3/8) Epoch 13, batch 12500, loss[loss=0.173, simple_loss=0.2526, pruned_loss=0.04663, over 4949.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03089, over 972958.56 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 18:04:03,261 INFO [train.py:715] (3/8) Epoch 13, batch 12550, loss[loss=0.1427, simple_loss=0.212, pruned_loss=0.03671, over 4893.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03145, over 971775.62 frames.], batch size: 19, lr: 1.69e-04
+2022-05-07 18:04:41,882 INFO [train.py:715] (3/8) Epoch 13, batch 12600, loss[loss=0.1259, simple_loss=0.1953, pruned_loss=0.02821, over 4842.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03152, over 971296.18 frames.], batch size: 13, lr: 1.69e-04
+2022-05-07 18:05:20,412 INFO [train.py:715] (3/8) Epoch 13, batch 12650, loss[loss=0.1445, simple_loss=0.2187, pruned_loss=0.03518, over 4943.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03146, over 971970.63 frames.], batch size: 35, lr: 1.69e-04
+2022-05-07 18:05:58,206 INFO [train.py:715] (3/8) Epoch 13, batch 12700, loss[loss=0.1338, simple_loss=0.1941, pruned_loss=0.03674, over 4863.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03125, over 971950.07 frames.], batch size: 12, lr: 1.69e-04
+2022-05-07 18:06:37,493 INFO [train.py:715] (3/8) Epoch 13, batch 12750, loss[loss=0.1445, simple_loss=0.2226, pruned_loss=0.03327, over 4936.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03137, over 973055.32 frames.], batch size: 23, lr: 1.69e-04
+2022-05-07 18:07:16,116 INFO [train.py:715] (3/8) Epoch 13, batch 12800, loss[loss=0.1279, simple_loss=0.2013, pruned_loss=0.02724, over 4917.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03136, over 972801.24 frames.], batch size: 17, lr: 1.69e-04
+2022-05-07 18:07:53,800 INFO [train.py:715] (3/8) Epoch 13, batch 12850, loss[loss=0.1541, simple_loss=0.2061, pruned_loss=0.05111, over 4987.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.0308, over 973142.90 frames.], batch size: 14, lr: 1.69e-04
+2022-05-07 18:08:32,302 INFO [train.py:715] (3/8) Epoch 13, batch 12900, loss[loss=0.1525, simple_loss=0.2265, pruned_loss=0.03925, over 4941.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03037, over 973199.49 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 18:09:10,901 INFO [train.py:715] (3/8) Epoch 13, batch 12950, loss[loss=0.1231, simple_loss=0.1902, pruned_loss=0.02801, over 4908.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03051, over 973224.59 frames.], batch size: 19, lr: 1.69e-04
+2022-05-07 18:09:48,857 INFO [train.py:715] (3/8) Epoch 13, batch 13000, loss[loss=0.1405, simple_loss=0.2228, pruned_loss=0.02907, over 4807.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03065, over 972568.05 frames.], batch size: 25, lr: 1.69e-04
+2022-05-07 18:10:26,258 INFO [train.py:715] (3/8) Epoch 13, batch 13050, loss[loss=0.123, simple_loss=0.1953, pruned_loss=0.02539, over 4984.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2101, pruned_loss=0.03072, over 972274.05 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 18:11:05,301 INFO [train.py:715] (3/8) Epoch 13, batch 13100, loss[loss=0.1163, simple_loss=0.2005, pruned_loss=0.01609, over 4837.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03126, over 971955.84 frames.], batch size: 26, lr: 1.69e-04
+2022-05-07 18:11:43,996 INFO [train.py:715] (3/8) Epoch 13, batch 13150, loss[loss=0.1438, simple_loss=0.2184, pruned_loss=0.03456, over 4794.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03162, over 971343.87 frames.], batch size: 18, lr: 1.69e-04
+2022-05-07 18:12:21,749 INFO [train.py:715] (3/8) Epoch 13, batch 13200, loss[loss=0.1277, simple_loss=0.2082, pruned_loss=0.02364, over 4799.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03179, over 971271.97 frames.], batch size: 17, lr: 1.69e-04
+2022-05-07 18:13:00,177 INFO [train.py:715] (3/8) Epoch 13, batch 13250, loss[loss=0.112, simple_loss=0.1892, pruned_loss=0.01744, over 4971.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03197, over 971799.69 frames.], batch size: 24, lr: 1.69e-04
+2022-05-07 18:13:38,870 INFO [train.py:715] (3/8) Epoch 13, batch 13300, loss[loss=0.1231, simple_loss=0.1999, pruned_loss=0.02316, over 4951.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03139, over 972688.31 frames.], batch size: 35, lr: 1.69e-04
+2022-05-07 18:14:17,605 INFO [train.py:715] (3/8) Epoch 13, batch 13350, loss[loss=0.1248, simple_loss=0.2093, pruned_loss=0.02019, over 4796.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03143, over 972863.89 frames.], batch size: 21, lr: 1.69e-04
+2022-05-07 18:14:55,894 INFO [train.py:715] (3/8) Epoch 13, batch 13400, loss[loss=0.1392, simple_loss=0.2096, pruned_loss=0.03442, over 4963.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03111, over 971670.70 frames.], batch size: 25, lr: 1.69e-04
+2022-05-07 18:15:35,680 INFO [train.py:715] (3/8) Epoch 13, batch 13450, loss[loss=0.1473, simple_loss=0.2168, pruned_loss=0.03886, over 4981.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03133, over 972237.89 frames.], batch size: 15, lr: 1.69e-04
+2022-05-07 18:16:14,408 INFO [train.py:715] (3/8) Epoch 13, batch 13500, loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.03104, over 4765.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03153, over 972551.92 frames.], batch size: 12, lr: 1.69e-04
+2022-05-07 18:16:52,060 INFO [train.py:715] (3/8) Epoch 13, batch 13550, loss[loss=0.138, simple_loss=0.216, pruned_loss=0.03, over 4760.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03136, over 973356.26 frames.], batch size: 19, lr: 1.69e-04
+2022-05-07 18:17:29,850 INFO [train.py:715] (3/8) Epoch 13, batch 13600, loss[loss=0.1392, simple_loss=0.2146, pruned_loss=0.03195, over 4820.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03128, over 973727.54 frames.], batch size: 15, lr: 1.68e-04
+2022-05-07 18:18:08,970 INFO [train.py:715] (3/8) Epoch 13, batch 13650, loss[loss=0.1522, simple_loss=0.2288, pruned_loss=0.03782, over 4791.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03101, over 973972.63 frames.], batch size: 18, lr: 1.68e-04
+2022-05-07 18:18:47,086 INFO [train.py:715] (3/8) Epoch 13, batch 13700, loss[loss=0.1601, simple_loss=0.2433, pruned_loss=0.03846, over 4876.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03096, over 973180.57 frames.], batch size: 22, lr: 1.68e-04
+2022-05-07 18:19:24,725 INFO [train.py:715] (3/8) Epoch 13, batch 13750, loss[loss=0.1334, simple_loss=0.2055, pruned_loss=0.03064, over 4886.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03066, over 972652.26 frames.], batch size: 19, lr: 1.68e-04
+2022-05-07 18:20:03,321 INFO [train.py:715] (3/8) Epoch 13, batch 13800, loss[loss=0.1542, simple_loss=0.2236, pruned_loss=0.04238, over 4978.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03123, over 971752.33 frames.], batch size: 39, lr: 1.68e-04
+2022-05-07 18:20:41,460 INFO [train.py:715] (3/8) Epoch 13, batch 13850, loss[loss=0.128, simple_loss=0.1887, pruned_loss=0.03366, over 4776.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03093, over 970981.41 frames.], batch size: 19, lr: 1.68e-04
+2022-05-07 18:21:19,875 INFO [train.py:715] (3/8) Epoch 13, batch 13900, loss[loss=0.1467, simple_loss=0.2281, pruned_loss=0.03262, over 4952.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03098, over 970336.55 frames.], batch size: 29, lr: 1.68e-04
+2022-05-07 18:21:58,635 INFO [train.py:715] (3/8) Epoch 13, batch 13950, loss[loss=0.1663, simple_loss=0.2334, pruned_loss=0.04966, over 4930.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.0316, over 971363.90 frames.], batch size: 18, lr: 1.68e-04
+2022-05-07 18:22:37,441 INFO [train.py:715] (3/8) Epoch 13, batch 14000, loss[loss=0.1414, simple_loss=0.2302, pruned_loss=0.02633, over 4771.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03183, over 971743.97 frames.], batch size: 18, lr: 1.68e-04
+2022-05-07 18:23:15,660 INFO [train.py:715] (3/8) Epoch 13, batch 14050, loss[loss=0.1214, simple_loss=0.2068, pruned_loss=0.01794, over 4744.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03145, over 972333.05 frames.], batch size: 16, lr: 1.68e-04
+2022-05-07 18:23:53,252 INFO [train.py:715] (3/8) Epoch 13, batch 14100, loss[loss=0.1287, simple_loss=0.2014, pruned_loss=0.02799, over 4802.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.0319, over 972265.15 frames.], batch size: 12, lr: 1.68e-04
+2022-05-07 18:24:32,482 INFO [train.py:715] (3/8) Epoch 13, batch 14150, loss[loss=0.1175, simple_loss=0.1896, pruned_loss=0.02269, over 4847.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2116, pruned_loss=0.03197, over 973097.06 frames.], batch size: 26, lr: 1.68e-04
+2022-05-07 18:25:10,630 INFO [train.py:715] (3/8) Epoch 13, batch 14200, loss[loss=0.1238, simple_loss=0.2006, pruned_loss=0.02345, over 4936.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2113, pruned_loss=0.03167, over 972654.80 frames.], batch size: 29, lr: 1.68e-04
+2022-05-07 18:25:48,510 INFO [train.py:715] (3/8) Epoch 13, batch 14250, loss[loss=0.1183, simple_loss=0.1897, pruned_loss=0.02348, over 4827.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03137, over 972951.04 frames.], batch size: 30, lr: 1.68e-04
+2022-05-07 18:26:26,776 INFO [train.py:715] (3/8) Epoch 13, batch 14300, loss[loss=0.1264, simple_loss=0.1915, pruned_loss=0.03062, over 4869.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.0312, over 973080.87 frames.], batch size: 32, lr: 1.68e-04
+2022-05-07 18:27:06,170 INFO [train.py:715] (3/8) Epoch 13, batch 14350, loss[loss=0.1502, simple_loss=0.2247, pruned_loss=0.03781, over 4909.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03101, over 973498.64 frames.], batch size: 18, lr: 1.68e-04
+2022-05-07 18:27:44,509 INFO [train.py:715] (3/8) Epoch 13, batch 14400, loss[loss=0.1145, simple_loss=0.183, pruned_loss=0.02306, over 4789.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03118, over 971853.80 frames.], batch size: 14, lr: 1.68e-04
+2022-05-07 18:28:22,438 INFO [train.py:715] (3/8) Epoch 13, batch 14450, loss[loss=0.1311, simple_loss=0.2081, pruned_loss=0.02703, over 4869.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03169, over 972010.21 frames.], batch size: 16, lr: 1.68e-04
+2022-05-07 18:29:01,543 INFO [train.py:715] (3/8) Epoch 13, batch 14500, loss[loss=0.1294, simple_loss=0.2133, pruned_loss=0.02274, over 4853.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03158, over 971846.88 frames.], batch size: 13, lr: 1.68e-04
+2022-05-07 18:29:40,344 INFO [train.py:715] (3/8) Epoch 13, batch 14550, loss[loss=0.1112, simple_loss=0.1892, pruned_loss=0.01662, over 4828.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03167, over 972840.47 frames.], batch size: 26, lr: 1.68e-04
+2022-05-07 18:30:18,694 INFO [train.py:715] (3/8) Epoch 13, batch 14600, loss[loss=0.1418, simple_loss=0.2122, pruned_loss=0.03567, over 4678.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.0318, over 972413.83 frames.], batch size: 15, lr: 1.68e-04
+2022-05-07 18:30:57,057 INFO [train.py:715] (3/8) Epoch 13, batch 14650, loss[loss=0.151, simple_loss=0.2329, pruned_loss=0.03456, over 4932.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03143, over 972426.91 frames.], batch size: 39, lr: 1.68e-04
+2022-05-07 18:31:35,708 INFO [train.py:715] (3/8) Epoch 13, batch 14700, loss[loss=0.1319, simple_loss=0.2079, pruned_loss=0.02796, over 4848.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03201, over 972480.46 frames.], batch size: 20, lr: 1.68e-04
+2022-05-07 18:32:13,647 INFO [train.py:715] (3/8) Epoch 13, batch 14750, loss[loss=0.1627, simple_loss=0.2243, pruned_loss=0.05057, over 4784.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03185, over 972475.27 frames.], batch size: 18, lr: 1.68e-04
+2022-05-07 18:32:50,800 INFO [train.py:715] (3/8) Epoch 13, batch 14800, loss[loss=0.1323, simple_loss=0.2079, pruned_loss=0.02835, over 4957.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2107, pruned_loss=0.03222, over 971810.65 frames.], batch size: 21, lr: 1.68e-04
+2022-05-07 18:33:29,890 INFO [train.py:715] (3/8) Epoch 13, batch 14850, loss[loss=0.1188, simple_loss=0.1976, pruned_loss=0.02001, over 4791.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2107, pruned_loss=0.03227, over 971256.78 frames.], batch size: 14, lr: 1.68e-04
+2022-05-07 18:34:08,570 INFO [train.py:715] (3/8) Epoch 13, batch 14900, loss[loss=0.1282, simple_loss=0.1938, pruned_loss=0.03131, over 4861.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03212, over 971363.08 frames.], batch size: 13, lr: 1.68e-04
+2022-05-07 18:34:46,492 INFO [train.py:715] (3/8) Epoch 13, batch 14950, loss[loss=0.1255, simple_loss=0.1909, pruned_loss=0.03006, over 4698.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03184, over 970840.55 frames.], batch size: 15, lr: 1.68e-04
+2022-05-07 18:35:24,995 INFO [train.py:715] (3/8) Epoch 13, batch 15000, loss[loss=0.1281, simple_loss=0.2084, pruned_loss=0.02392, over 4793.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03241, over 970352.77 frames.], batch size: 17, lr: 1.68e-04
+2022-05-07 18:35:24,996 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 18:35:34,567 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1052, simple_loss=0.189, pruned_loss=0.01074, over 914524.00 frames.
+2022-05-07 18:36:13,159 INFO [train.py:715] (3/8) Epoch 13, batch 15050, loss[loss=0.1123, simple_loss=0.1943, pruned_loss=0.01511, over 4806.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03141, over 970613.64 frames.], batch size: 21, lr: 1.68e-04
+2022-05-07 18:36:52,714 INFO [train.py:715] (3/8) Epoch 13, batch 15100, loss[loss=0.1124, simple_loss=0.1828, pruned_loss=0.02099, over 4862.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03125, over 970608.35 frames.], batch size: 13, lr: 1.68e-04
+2022-05-07 18:37:31,196 INFO [train.py:715] (3/8) Epoch 13, batch 15150, loss[loss=0.1091, simple_loss=0.1797, pruned_loss=0.01925, over 4810.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03126, over 971042.57 frames.], batch size: 13, lr: 1.68e-04
+2022-05-07 18:38:09,448 INFO [train.py:715] (3/8) Epoch 13, batch 15200, loss[loss=0.1169, simple_loss=0.1836, pruned_loss=0.02504, over 4791.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03102, over 970706.66 frames.], batch size: 24, lr: 1.68e-04
+2022-05-07 18:38:49,229 INFO [train.py:715] (3/8) Epoch 13, batch 15250, loss[loss=0.1027, simple_loss=0.1703, pruned_loss=0.0175, over 4769.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03098, over 971381.65 frames.], batch size: 12, lr: 1.68e-04
+2022-05-07 18:39:27,976 INFO [train.py:715] (3/8) Epoch 13, batch 15300, loss[loss=0.1064, simple_loss=0.1769, pruned_loss=0.01794, over 4813.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03111, over 972119.48 frames.], batch size: 12, lr: 1.68e-04
+2022-05-07 18:40:06,014 INFO [train.py:715] (3/8) Epoch 13, batch 15350, loss[loss=0.13, simple_loss=0.1949, pruned_loss=0.03253, over 4873.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2102, pruned_loss=0.03109, over 972509.01 frames.], batch size: 32, lr: 1.68e-04
+2022-05-07 18:40:45,015 INFO [train.py:715] (3/8) Epoch 13, batch 15400, loss[loss=0.1252, simple_loss=0.2053, pruned_loss=0.02253, over 4820.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.03099, over 972778.17 frames.], batch size: 15, lr: 1.68e-04
+2022-05-07 18:41:23,903 INFO [train.py:715] (3/8) Epoch 13, batch 15450, loss[loss=0.1197, simple_loss=0.189, pruned_loss=0.02519, over 4968.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03158, over 973177.83 frames.], batch size: 35, lr: 1.68e-04
+2022-05-07 18:42:03,713 INFO [train.py:715] (3/8) Epoch 13, batch 15500, loss[loss=0.1352, simple_loss=0.2061, pruned_loss=0.03216, over 4969.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03139, over 973026.63 frames.], batch size: 24, lr: 1.68e-04
+2022-05-07 18:42:41,962 INFO [train.py:715] (3/8) Epoch 13, batch 15550, loss[loss=0.1636, simple_loss=0.2326, pruned_loss=0.04727, over 4916.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03172, over 973092.22 frames.], batch size: 18, lr: 1.68e-04
+2022-05-07 18:43:21,699 INFO [train.py:715] (3/8) Epoch 13, batch 15600, loss[loss=0.1465, simple_loss=0.2269, pruned_loss=0.03305, over 4990.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03165, over 973501.36 frames.], batch size: 15, lr: 1.68e-04
+2022-05-07 18:44:01,140 INFO [train.py:715] (3/8) Epoch 13, batch 15650, loss[loss=0.1209, simple_loss=0.1937, pruned_loss=0.02405, over 4930.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03171, over 973340.72 frames.], batch size: 18, lr: 1.68e-04
+2022-05-07 18:44:39,625 INFO [train.py:715] (3/8) Epoch 13, batch 15700, loss[loss=0.1319, simple_loss=0.209, pruned_loss=0.02736, over 4898.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03102, over 972845.81 frames.], batch size: 19, lr: 1.68e-04
+2022-05-07 18:45:18,633 INFO [train.py:715] (3/8) Epoch 13, batch 15750, loss[loss=0.1429, simple_loss=0.2048, pruned_loss=0.0405, over 4783.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03081, over 972989.75 frames.], batch size: 14, lr: 1.68e-04
+2022-05-07 18:45:57,411 INFO [train.py:715] (3/8) Epoch 13, batch 15800, loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02901, over 4881.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03071, over 973020.62 frames.], batch size: 19, lr: 1.68e-04
+2022-05-07 18:46:35,695 INFO [train.py:715] (3/8) Epoch 13, batch 15850, loss[loss=0.1371, simple_loss=0.2141, pruned_loss=0.03, over 4896.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.0307, over 972624.07 frames.], batch size: 22, lr: 1.68e-04
+2022-05-07 18:47:13,599 INFO [train.py:715] (3/8) Epoch 13, batch 15900, loss[loss=0.1207, simple_loss=0.2015, pruned_loss=0.01988, over 4952.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03068, over 972886.04 frames.], batch size: 21, lr: 1.68e-04
+2022-05-07 18:47:52,837 INFO [train.py:715] (3/8) Epoch 13, batch 15950, loss[loss=0.1636, simple_loss=0.2263, pruned_loss=0.05042, over 4866.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03102, over 972905.85 frames.], batch size: 22, lr: 1.68e-04
+2022-05-07 18:48:31,349 INFO [train.py:715] (3/8) Epoch 13, batch 16000, loss[loss=0.1126, simple_loss=0.1903, pruned_loss=0.01741, over 4866.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03055, over 972153.85 frames.], batch size: 32, lr: 1.68e-04
+2022-05-07 18:49:09,602 INFO [train.py:715] (3/8) Epoch 13, batch 16050, loss[loss=0.1548, simple_loss=0.2405, pruned_loss=0.03452, over 4966.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2103, pruned_loss=0.03105, over 971893.90 frames.], batch size: 35, lr: 1.68e-04
+2022-05-07 18:49:48,081 INFO [train.py:715] (3/8) Epoch 13, batch 16100, loss[loss=0.1379, simple_loss=0.2136, pruned_loss=0.03105, over 4742.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03072, over 971960.70 frames.], batch size: 16, lr: 1.68e-04
+2022-05-07 18:50:27,335 INFO [train.py:715] (3/8) Epoch 13, batch 16150, loss[loss=0.1306, simple_loss=0.1979, pruned_loss=0.03163, over 4959.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03091, over 971995.48 frames.], batch size: 15, lr: 1.68e-04
+2022-05-07 18:51:05,994 INFO [train.py:715] (3/8) Epoch 13, batch 16200, loss[loss=0.138, simple_loss=0.208, pruned_loss=0.03398, over 4762.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03042, over 971207.03 frames.], batch size: 16, lr: 1.68e-04
+2022-05-07 18:51:42,924 INFO [train.py:715] (3/8) Epoch 13, batch 16250, loss[loss=0.1296, simple_loss=0.1985, pruned_loss=0.0304, over 4948.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.0304, over 971812.83 frames.], batch size: 14, lr: 1.68e-04
+2022-05-07 18:52:22,102 INFO [train.py:715] (3/8) Epoch 13, batch 16300, loss[loss=0.147, simple_loss=0.2206, pruned_loss=0.03671, over 4869.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03028, over 972098.97 frames.], batch size: 20, lr: 1.68e-04
+2022-05-07 18:53:00,700 INFO [train.py:715] (3/8) Epoch 13, batch 16350, loss[loss=0.1239, simple_loss=0.1934, pruned_loss=0.02715, over 4874.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03052, over 972614.52 frames.], batch size: 16, lr: 1.68e-04
+2022-05-07 18:53:39,045 INFO [train.py:715] (3/8) Epoch 13, batch 16400, loss[loss=0.1372, simple_loss=0.2112, pruned_loss=0.03161, over 4748.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03042, over 973113.53 frames.], batch size: 12, lr: 1.68e-04
+2022-05-07 18:54:18,189 INFO [train.py:715] (3/8) Epoch 13, batch 16450, loss[loss=0.1703, simple_loss=0.2343, pruned_loss=0.05318, over 4974.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03091, over 973823.68 frames.], batch size: 31, lr: 1.68e-04
+2022-05-07 18:54:57,402 INFO [train.py:715] (3/8) Epoch 13, batch 16500, loss[loss=0.1203, simple_loss=0.202, pruned_loss=0.01933, over 4783.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03082, over 973560.47 frames.], batch size: 18, lr: 1.68e-04
+2022-05-07 18:55:36,544 INFO [train.py:715] (3/8) Epoch 13, batch 16550, loss[loss=0.1235, simple_loss=0.2052, pruned_loss=0.02091, over 4883.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03099, over 973951.82 frames.], batch size: 22, lr: 1.68e-04
+2022-05-07 18:56:13,926 INFO [train.py:715] (3/8) Epoch 13, batch 16600, loss[loss=0.1429, simple_loss=0.2103, pruned_loss=0.03776, over 4934.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03086, over 974926.12 frames.], batch size: 23, lr: 1.68e-04
+2022-05-07 18:56:53,167 INFO [train.py:715] (3/8) Epoch 13, batch 16650, loss[loss=0.1489, simple_loss=0.2199, pruned_loss=0.0389, over 4984.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03061, over 974567.38 frames.], batch size: 15, lr: 1.68e-04
+2022-05-07 18:57:31,701 INFO [train.py:715] (3/8) Epoch 13, batch 16700, loss[loss=0.1513, simple_loss=0.2256, pruned_loss=0.0385, over 4896.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03123, over 973803.51 frames.], batch size: 22, lr: 1.68e-04
+2022-05-07 18:58:09,693 INFO [train.py:715] (3/8) Epoch 13, batch 16750, loss[loss=0.1212, simple_loss=0.1947, pruned_loss=0.02385, over 4811.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03163, over 973742.04 frames.], batch size: 26, lr: 1.68e-04
+2022-05-07 18:58:48,292 INFO [train.py:715] (3/8) Epoch 13, batch 16800, loss[loss=0.1315, simple_loss=0.2065, pruned_loss=0.02822, over 4819.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03192, over 973786.22 frames.], batch size: 27, lr: 1.68e-04
+2022-05-07 18:59:27,924 INFO [train.py:715] (3/8) Epoch 13, batch 16850, loss[loss=0.1538, simple_loss=0.2202, pruned_loss=0.04374, over 4954.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03152, over 973821.58 frames.], batch size: 35, lr: 1.68e-04
+2022-05-07 19:00:06,299 INFO [train.py:715] (3/8) Epoch 13, batch 16900, loss[loss=0.1418, simple_loss=0.2199, pruned_loss=0.03179, over 4776.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.0317, over 973205.75 frames.], batch size: 17, lr: 1.68e-04
+2022-05-07 19:00:44,804 INFO [train.py:715] (3/8) Epoch 13, batch 16950, loss[loss=0.1548, simple_loss=0.2212, pruned_loss=0.04417, over 4892.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03168, over 973019.67 frames.], batch size: 17, lr: 1.68e-04
+2022-05-07 19:01:23,720 INFO [train.py:715] (3/8) Epoch 13, batch 17000, loss[loss=0.158, simple_loss=0.2437, pruned_loss=0.03614, over 4774.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03213, over 972867.34 frames.], batch size: 18, lr: 1.68e-04
+2022-05-07 19:02:02,415 INFO [train.py:715] (3/8) Epoch 13, batch 17050, loss[loss=0.1309, simple_loss=0.208, pruned_loss=0.02689, over 4941.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03188, over 972997.56 frames.], batch size: 21, lr: 1.68e-04
+2022-05-07 19:02:40,530 INFO [train.py:715] (3/8) Epoch 13, batch 17100, loss[loss=0.1371, simple_loss=0.2078, pruned_loss=0.03319, over 4745.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03244, over 973582.74 frames.], batch size: 16, lr: 1.68e-04
+2022-05-07 19:03:19,262 INFO [train.py:715] (3/8) Epoch 13, batch 17150, loss[loss=0.1654, simple_loss=0.2487, pruned_loss=0.041, over 4776.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03256, over 972982.76 frames.], batch size: 17, lr: 1.68e-04
+2022-05-07 19:03:58,100 INFO [train.py:715] (3/8) Epoch 13, batch 17200, loss[loss=0.1248, simple_loss=0.2007, pruned_loss=0.02448, over 4805.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03202, over 972739.89 frames.], batch size: 12, lr: 1.68e-04
+2022-05-07 19:04:36,808 INFO [train.py:715] (3/8) Epoch 13, batch 17250, loss[loss=0.1191, simple_loss=0.1932, pruned_loss=0.0225, over 4906.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03144, over 972060.53 frames.], batch size: 29, lr: 1.68e-04
+2022-05-07 19:05:14,779 INFO [train.py:715] (3/8) Epoch 13, batch 17300, loss[loss=0.1386, simple_loss=0.2205, pruned_loss=0.02837, over 4924.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03197, over 972657.18 frames.], batch size: 23, lr: 1.68e-04
+2022-05-07 19:05:53,539 INFO [train.py:715] (3/8) Epoch 13, batch 17350, loss[loss=0.1437, simple_loss=0.2219, pruned_loss=0.03277, over 4884.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03173, over 973218.87 frames.], batch size: 22, lr: 1.68e-04
+2022-05-07 19:06:32,452 INFO [train.py:715] (3/8) Epoch 13, batch 17400, loss[loss=0.1613, simple_loss=0.2407, pruned_loss=0.04093, over 4826.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03156, over 973132.40 frames.], batch size: 26, lr: 1.68e-04
+2022-05-07 19:07:10,069 INFO [train.py:715] (3/8) Epoch 13, batch 17450, loss[loss=0.1429, simple_loss=0.2182, pruned_loss=0.03378, over 4901.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03121, over 972515.49 frames.], batch size: 22, lr: 1.68e-04
+2022-05-07 19:07:48,569 INFO [train.py:715] (3/8) Epoch 13, batch 17500, loss[loss=0.1295, simple_loss=0.2001, pruned_loss=0.02945, over 4796.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03104, over 972827.72 frames.], batch size: 14, lr: 1.68e-04
+2022-05-07 19:08:27,655 INFO [train.py:715] (3/8) Epoch 13, batch 17550, loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03057, over 4749.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2105, pruned_loss=0.03119, over 972958.71 frames.], batch size: 19, lr: 1.68e-04
+2022-05-07 19:09:06,326 INFO [train.py:715] (3/8) Epoch 13, batch 17600, loss[loss=0.1593, simple_loss=0.2167, pruned_loss=0.051, over 4971.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03109, over 972565.21 frames.], batch size: 15, lr: 1.68e-04
+2022-05-07 19:09:43,948 INFO [train.py:715] (3/8) Epoch 13, batch 17650, loss[loss=0.127, simple_loss=0.2064, pruned_loss=0.02374, over 4925.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03108, over 971522.61 frames.], batch size: 39, lr: 1.68e-04
+2022-05-07 19:10:23,208 INFO [train.py:715] (3/8) Epoch 13, batch 17700, loss[loss=0.1357, simple_loss=0.2037, pruned_loss=0.03388, over 4852.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03138, over 971915.70 frames.], batch size: 26, lr: 1.68e-04
+2022-05-07 19:11:02,062 INFO [train.py:715] (3/8) Epoch 13, batch 17750, loss[loss=0.1253, simple_loss=0.2061, pruned_loss=0.02223, over 4769.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03115, over 971676.50 frames.], batch size: 19, lr: 1.68e-04
+2022-05-07 19:11:39,680 INFO [train.py:715] (3/8) Epoch 13, batch 17800, loss[loss=0.1438, simple_loss=0.2117, pruned_loss=0.0379, over 4931.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03091, over 972482.63 frames.], batch size: 35, lr: 1.68e-04
+2022-05-07 19:12:18,453 INFO [train.py:715] (3/8) Epoch 13, batch 17850, loss[loss=0.1269, simple_loss=0.1966, pruned_loss=0.0286, over 4796.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03059, over 971484.88 frames.], batch size: 24, lr: 1.68e-04
+2022-05-07 19:12:57,285 INFO [train.py:715] (3/8) Epoch 13, batch 17900, loss[loss=0.1386, simple_loss=0.2165, pruned_loss=0.03038, over 4768.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03111, over 971475.31 frames.], batch size: 14, lr: 1.68e-04
+2022-05-07 19:13:35,481 INFO [train.py:715] (3/8) Epoch 13, batch 17950, loss[loss=0.1548, simple_loss=0.2234, pruned_loss=0.04313, over 4978.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03127, over 971895.89 frames.], batch size: 33, lr: 1.68e-04
+2022-05-07 19:14:13,540 INFO [train.py:715] (3/8) Epoch 13, batch 18000, loss[loss=0.133, simple_loss=0.2177, pruned_loss=0.02413, over 4833.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.0315, over 972231.27 frames.], batch size: 26, lr: 1.68e-04
+2022-05-07 19:14:13,541 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 19:14:23,028 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1055, simple_loss=0.1892, pruned_loss=0.01083, over 914524.00 frames.
+2022-05-07 19:15:00,697 INFO [train.py:715] (3/8) Epoch 13, batch 18050, loss[loss=0.1296, simple_loss=0.2062, pruned_loss=0.02655, over 4984.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03109, over 972982.60 frames.], batch size: 35, lr: 1.68e-04
+2022-05-07 19:15:39,773 INFO [train.py:715] (3/8) Epoch 13, batch 18100, loss[loss=0.09911, simple_loss=0.1696, pruned_loss=0.0143, over 4742.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03095, over 972886.81 frames.], batch size: 12, lr: 1.68e-04
+2022-05-07 19:16:18,125 INFO [train.py:715] (3/8) Epoch 13, batch 18150, loss[loss=0.1419, simple_loss=0.2022, pruned_loss=0.04079, over 4945.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03067, over 972852.49 frames.], batch size: 35, lr: 1.68e-04
+2022-05-07 19:16:55,372 INFO [train.py:715] (3/8) Epoch 13, batch 18200, loss[loss=0.1373, simple_loss=0.216, pruned_loss=0.02926, over 4925.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03055, over 973360.01 frames.], batch size: 23, lr: 1.68e-04
+2022-05-07 19:17:33,691 INFO [train.py:715] (3/8) Epoch 13, batch 18250, loss[loss=0.1285, simple_loss=0.192, pruned_loss=0.03251, over 4783.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03055, over 972507.54 frames.], batch size: 18, lr: 1.68e-04
+2022-05-07 19:18:12,483 INFO [train.py:715] (3/8) Epoch 13, batch 18300, loss[loss=0.1408, simple_loss=0.2093, pruned_loss=0.03616, over 4957.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03119, over 972239.22 frames.], batch size: 35, lr: 1.68e-04
+2022-05-07 19:18:51,122 INFO [train.py:715] (3/8) Epoch 13, batch 18350, loss[loss=0.1266, simple_loss=0.2062, pruned_loss=0.02351, over 4981.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03118, over 972171.30 frames.], batch size: 14, lr: 1.68e-04
+2022-05-07 19:19:29,022 INFO [train.py:715] (3/8) Epoch 13, batch 18400, loss[loss=0.1273, simple_loss=0.1943, pruned_loss=0.03018, over 4937.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03132, over 972181.16 frames.], batch size: 23, lr: 1.68e-04
+2022-05-07 19:20:07,829 INFO [train.py:715] (3/8) Epoch 13, batch 18450, loss[loss=0.1587, simple_loss=0.2306, pruned_loss=0.04344, over 4887.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03127, over 972641.17 frames.], batch size: 19, lr: 1.68e-04
+2022-05-07 19:20:46,497 INFO [train.py:715] (3/8) Epoch 13, batch 18500, loss[loss=0.1594, simple_loss=0.2272, pruned_loss=0.04583, over 4883.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2107, pruned_loss=0.03138, over 972619.03 frames.], batch size: 39, lr: 1.68e-04
+2022-05-07 19:21:23,939 INFO [train.py:715] (3/8) Epoch 13, batch 18550, loss[loss=0.1434, simple_loss=0.2261, pruned_loss=0.03031, over 4800.00 frames.], tot_loss[loss=0.137, simple_loss=0.211, pruned_loss=0.03146, over 971808.15 frames.], batch size: 21, lr: 1.68e-04
+2022-05-07 19:22:01,960 INFO [train.py:715] (3/8) Epoch 13, batch 18600, loss[loss=0.1253, simple_loss=0.1973, pruned_loss=0.02662, over 4759.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03121, over 971569.53 frames.], batch size: 16, lr: 1.68e-04
+2022-05-07 19:22:40,555 INFO [train.py:715] (3/8) Epoch 13, batch 18650, loss[loss=0.1558, simple_loss=0.2391, pruned_loss=0.03627, over 4862.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03152, over 971420.16 frames.], batch size: 22, lr: 1.68e-04
+2022-05-07 19:23:18,503 INFO [train.py:715] (3/8) Epoch 13, batch 18700, loss[loss=0.1366, simple_loss=0.2172, pruned_loss=0.02803, over 4760.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03166, over 971554.60 frames.], batch size: 19, lr: 1.68e-04
+2022-05-07 19:23:56,290 INFO [train.py:715] (3/8) Epoch 13, batch 18750, loss[loss=0.1334, simple_loss=0.1957, pruned_loss=0.03552, over 4764.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03162, over 971617.21 frames.], batch size: 12, lr: 1.68e-04
+2022-05-07 19:24:35,596 INFO [train.py:715] (3/8) Epoch 13, batch 18800, loss[loss=0.1524, simple_loss=0.2208, pruned_loss=0.04206, over 4858.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03171, over 971584.69 frames.], batch size: 30, lr: 1.68e-04
+2022-05-07 19:25:14,015 INFO [train.py:715] (3/8) Epoch 13, batch 18850, loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02831, over 4848.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.0314, over 972165.87 frames.], batch size: 20, lr: 1.68e-04
+2022-05-07 19:25:52,020 INFO [train.py:715] (3/8) Epoch 13, batch 18900, loss[loss=0.1228, simple_loss=0.1971, pruned_loss=0.02428, over 4819.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03137, over 972881.61 frames.], batch size: 26, lr: 1.68e-04
+2022-05-07 19:26:30,884 INFO [train.py:715] (3/8) Epoch 13, batch 18950, loss[loss=0.1079, simple_loss=0.1851, pruned_loss=0.01533, over 4941.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03089, over 972250.64 frames.], batch size: 21, lr: 1.68e-04
+2022-05-07 19:27:09,768 INFO [train.py:715] (3/8) Epoch 13, batch 19000, loss[loss=0.1196, simple_loss=0.1874, pruned_loss=0.02589, over 4991.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03111, over 972876.70 frames.], batch size: 14, lr: 1.68e-04
+2022-05-07 19:27:48,115 INFO [train.py:715] (3/8) Epoch 13, batch 19050, loss[loss=0.168, simple_loss=0.247, pruned_loss=0.04451, over 4792.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2086, pruned_loss=0.03101, over 972320.91 frames.], batch size: 24, lr: 1.68e-04
+2022-05-07 19:28:26,437 INFO [train.py:715] (3/8) Epoch 13, batch 19100, loss[loss=0.1771, simple_loss=0.2471, pruned_loss=0.05354, over 4819.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2087, pruned_loss=0.03107, over 972054.21 frames.], batch size: 15, lr: 1.68e-04
+2022-05-07 19:29:05,443 INFO [train.py:715] (3/8) Epoch 13, batch 19150, loss[loss=0.162, simple_loss=0.2358, pruned_loss=0.04406, over 4840.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.0313, over 970305.20 frames.], batch size: 32, lr: 1.67e-04
+2022-05-07 19:29:44,103 INFO [train.py:715] (3/8) Epoch 13, batch 19200, loss[loss=0.1348, simple_loss=0.1989, pruned_loss=0.03538, over 4981.00 frames.], tot_loss[loss=0.1358, simple_loss=0.209, pruned_loss=0.03131, over 970553.43 frames.], batch size: 35, lr: 1.67e-04
+2022-05-07 19:30:21,502 INFO [train.py:715] (3/8) Epoch 13, batch 19250, loss[loss=0.1088, simple_loss=0.1896, pruned_loss=0.014, over 4817.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03112, over 970974.21 frames.], batch size: 27, lr: 1.67e-04
+2022-05-07 19:31:00,079 INFO [train.py:715] (3/8) Epoch 13, batch 19300, loss[loss=0.1729, simple_loss=0.2419, pruned_loss=0.052, over 4849.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2086, pruned_loss=0.03109, over 971346.34 frames.], batch size: 20, lr: 1.67e-04
+2022-05-07 19:31:39,543 INFO [train.py:715] (3/8) Epoch 13, batch 19350, loss[loss=0.1432, simple_loss=0.2236, pruned_loss=0.0314, over 4816.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03097, over 971652.34 frames.], batch size: 26, lr: 1.67e-04
+2022-05-07 19:32:18,082 INFO [train.py:715] (3/8) Epoch 13, batch 19400, loss[loss=0.147, simple_loss=0.228, pruned_loss=0.03301, over 4849.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03087, over 971249.32 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 19:32:56,517 INFO [train.py:715] (3/8) Epoch 13, batch 19450, loss[loss=0.1496, simple_loss=0.2207, pruned_loss=0.03929, over 4799.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03107, over 971788.83 frames.], batch size: 18, lr: 1.67e-04
+2022-05-07 19:33:37,809 INFO [train.py:715] (3/8) Epoch 13, batch 19500, loss[loss=0.1608, simple_loss=0.2252, pruned_loss=0.04826, over 4921.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03105, over 972273.01 frames.], batch size: 18, lr: 1.67e-04
+2022-05-07 19:34:16,750 INFO [train.py:715] (3/8) Epoch 13, batch 19550, loss[loss=0.1438, simple_loss=0.2218, pruned_loss=0.03289, over 4804.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03147, over 972532.08 frames.], batch size: 25, lr: 1.67e-04
+2022-05-07 19:34:54,319 INFO [train.py:715] (3/8) Epoch 13, batch 19600, loss[loss=0.1281, simple_loss=0.2088, pruned_loss=0.02368, over 4931.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03109, over 972419.59 frames.], batch size: 39, lr: 1.67e-04
+2022-05-07 19:35:32,449 INFO [train.py:715] (3/8) Epoch 13, batch 19650, loss[loss=0.1054, simple_loss=0.1806, pruned_loss=0.01505, over 4893.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03071, over 972541.65 frames.], batch size: 19, lr: 1.67e-04
+2022-05-07 19:36:11,255 INFO [train.py:715] (3/8) Epoch 13, batch 19700, loss[loss=0.1398, simple_loss=0.2057, pruned_loss=0.03689, over 4759.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03068, over 972390.40 frames.], batch size: 19, lr: 1.67e-04
+2022-05-07 19:36:49,086 INFO [train.py:715] (3/8) Epoch 13, batch 19750, loss[loss=0.1218, simple_loss=0.1955, pruned_loss=0.02403, over 4798.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03164, over 972343.84 frames.], batch size: 12, lr: 1.67e-04
+2022-05-07 19:37:26,939 INFO [train.py:715] (3/8) Epoch 13, batch 19800, loss[loss=0.1118, simple_loss=0.1867, pruned_loss=0.01849, over 4727.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03156, over 971732.78 frames.], batch size: 16, lr: 1.67e-04
+2022-05-07 19:38:05,611 INFO [train.py:715] (3/8) Epoch 13, batch 19850, loss[loss=0.1455, simple_loss=0.2173, pruned_loss=0.0368, over 4981.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.03146, over 971899.09 frames.], batch size: 25, lr: 1.67e-04
+2022-05-07 19:38:44,224 INFO [train.py:715] (3/8) Epoch 13, batch 19900, loss[loss=0.1301, simple_loss=0.2147, pruned_loss=0.02276, over 4932.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03153, over 972098.83 frames.], batch size: 18, lr: 1.67e-04
+2022-05-07 19:39:22,425 INFO [train.py:715] (3/8) Epoch 13, batch 19950, loss[loss=0.1398, simple_loss=0.2101, pruned_loss=0.03472, over 4842.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03132, over 971990.79 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 19:40:01,314 INFO [train.py:715] (3/8) Epoch 13, batch 20000, loss[loss=0.1654, simple_loss=0.2464, pruned_loss=0.04221, over 4836.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03173, over 972641.58 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 19:40:39,757 INFO [train.py:715] (3/8) Epoch 13, batch 20050, loss[loss=0.1477, simple_loss=0.2151, pruned_loss=0.04015, over 4713.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03113, over 971964.56 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 19:41:16,930 INFO [train.py:715] (3/8) Epoch 13, batch 20100, loss[loss=0.1565, simple_loss=0.2358, pruned_loss=0.03856, over 4918.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2097, pruned_loss=0.03081, over 972039.99 frames.], batch size: 17, lr: 1.67e-04
+2022-05-07 19:41:54,380 INFO [train.py:715] (3/8) Epoch 13, batch 20150, loss[loss=0.1081, simple_loss=0.1884, pruned_loss=0.01391, over 4834.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03031, over 972248.11 frames.], batch size: 26, lr: 1.67e-04
+2022-05-07 19:42:33,107 INFO [train.py:715] (3/8) Epoch 13, batch 20200, loss[loss=0.1379, simple_loss=0.2133, pruned_loss=0.03123, over 4918.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03033, over 973128.34 frames.], batch size: 18, lr: 1.67e-04
+2022-05-07 19:43:11,187 INFO [train.py:715] (3/8) Epoch 13, batch 20250, loss[loss=0.1166, simple_loss=0.187, pruned_loss=0.02308, over 4981.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02998, over 972224.54 frames.], batch size: 35, lr: 1.67e-04
+2022-05-07 19:43:48,892 INFO [train.py:715] (3/8) Epoch 13, batch 20300, loss[loss=0.1335, simple_loss=0.2095, pruned_loss=0.02877, over 4969.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03033, over 971962.19 frames.], batch size: 35, lr: 1.67e-04
+2022-05-07 19:44:26,994 INFO [train.py:715] (3/8) Epoch 13, batch 20350, loss[loss=0.1237, simple_loss=0.2071, pruned_loss=0.02016, over 4762.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03024, over 971593.75 frames.], batch size: 19, lr: 1.67e-04
+2022-05-07 19:45:05,763 INFO [train.py:715] (3/8) Epoch 13, batch 20400, loss[loss=0.1314, simple_loss=0.209, pruned_loss=0.02685, over 4931.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03073, over 971572.69 frames.], batch size: 29, lr: 1.67e-04
+2022-05-07 19:45:43,494 INFO [train.py:715] (3/8) Epoch 13, batch 20450, loss[loss=0.1464, simple_loss=0.2097, pruned_loss=0.04155, over 4901.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03135, over 971707.08 frames.], batch size: 17, lr: 1.67e-04
+2022-05-07 19:46:21,265 INFO [train.py:715] (3/8) Epoch 13, batch 20500, loss[loss=0.1443, simple_loss=0.2088, pruned_loss=0.03994, over 4791.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03127, over 972872.75 frames.], batch size: 14, lr: 1.67e-04
+2022-05-07 19:46:59,824 INFO [train.py:715] (3/8) Epoch 13, batch 20550, loss[loss=0.1354, simple_loss=0.2179, pruned_loss=0.02639, over 4895.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2106, pruned_loss=0.03106, over 974139.08 frames.], batch size: 22, lr: 1.67e-04
+2022-05-07 19:47:37,480 INFO [train.py:715] (3/8) Epoch 13, batch 20600, loss[loss=0.158, simple_loss=0.2234, pruned_loss=0.04627, over 4931.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2107, pruned_loss=0.03139, over 973603.90 frames.], batch size: 23, lr: 1.67e-04
+2022-05-07 19:48:15,108 INFO [train.py:715] (3/8) Epoch 13, batch 20650, loss[loss=0.1386, simple_loss=0.2115, pruned_loss=0.0329, over 4865.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03131, over 972483.25 frames.], batch size: 32, lr: 1.67e-04
+2022-05-07 19:48:52,914 INFO [train.py:715] (3/8) Epoch 13, batch 20700, loss[loss=0.1432, simple_loss=0.2105, pruned_loss=0.03794, over 4940.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03081, over 971190.24 frames.], batch size: 21, lr: 1.67e-04
+2022-05-07 19:49:31,352 INFO [train.py:715] (3/8) Epoch 13, batch 20750, loss[loss=0.1434, simple_loss=0.2213, pruned_loss=0.03281, over 4989.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03089, over 971655.27 frames.], batch size: 14, lr: 1.67e-04
+2022-05-07 19:50:08,697 INFO [train.py:715] (3/8) Epoch 13, batch 20800, loss[loss=0.1182, simple_loss=0.1933, pruned_loss=0.02158, over 4903.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03112, over 972073.92 frames.], batch size: 16, lr: 1.67e-04
+2022-05-07 19:50:46,282 INFO [train.py:715] (3/8) Epoch 13, batch 20850, loss[loss=0.1433, simple_loss=0.228, pruned_loss=0.02929, over 4853.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03078, over 972416.96 frames.], batch size: 32, lr: 1.67e-04
+2022-05-07 19:51:24,968 INFO [train.py:715] (3/8) Epoch 13, batch 20900, loss[loss=0.1311, simple_loss=0.1984, pruned_loss=0.03189, over 4915.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03059, over 973248.35 frames.], batch size: 19, lr: 1.67e-04
+2022-05-07 19:52:03,242 INFO [train.py:715] (3/8) Epoch 13, batch 20950, loss[loss=0.1269, simple_loss=0.2054, pruned_loss=0.02422, over 4915.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03063, over 973093.52 frames.], batch size: 18, lr: 1.67e-04
+2022-05-07 19:52:40,747 INFO [train.py:715] (3/8) Epoch 13, batch 21000, loss[loss=0.1179, simple_loss=0.182, pruned_loss=0.02691, over 4828.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03007, over 973306.37 frames.], batch size: 26, lr: 1.67e-04
+2022-05-07 19:52:40,748 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 19:52:50,263 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1891, pruned_loss=0.01084, over 914524.00 frames.
+2022-05-07 19:53:28,434 INFO [train.py:715] (3/8) Epoch 13, batch 21050, loss[loss=0.1489, simple_loss=0.2099, pruned_loss=0.04401, over 4821.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03037, over 973921.10 frames.], batch size: 13, lr: 1.67e-04
+2022-05-07 19:54:06,971 INFO [train.py:715] (3/8) Epoch 13, batch 21100, loss[loss=0.1344, simple_loss=0.2097, pruned_loss=0.02957, over 4754.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03055, over 973391.50 frames.], batch size: 16, lr: 1.67e-04
+2022-05-07 19:54:46,057 INFO [train.py:715] (3/8) Epoch 13, batch 21150, loss[loss=0.1498, simple_loss=0.2237, pruned_loss=0.03794, over 4980.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03061, over 974181.25 frames.], batch size: 14, lr: 1.67e-04
+2022-05-07 19:55:23,881 INFO [train.py:715] (3/8) Epoch 13, batch 21200, loss[loss=0.1323, simple_loss=0.2087, pruned_loss=0.02796, over 4784.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.0308, over 973061.32 frames.], batch size: 18, lr: 1.67e-04
+2022-05-07 19:56:02,466 INFO [train.py:715] (3/8) Epoch 13, batch 21250, loss[loss=0.1091, simple_loss=0.193, pruned_loss=0.01262, over 4897.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03049, over 972668.18 frames.], batch size: 19, lr: 1.67e-04
+2022-05-07 19:56:41,276 INFO [train.py:715] (3/8) Epoch 13, batch 21300, loss[loss=0.1686, simple_loss=0.2251, pruned_loss=0.05604, over 4921.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.0304, over 972411.42 frames.], batch size: 39, lr: 1.67e-04
+2022-05-07 19:57:19,154 INFO [train.py:715] (3/8) Epoch 13, batch 21350, loss[loss=0.1431, simple_loss=0.2132, pruned_loss=0.03648, over 4853.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03057, over 972330.64 frames.], batch size: 30, lr: 1.67e-04
+2022-05-07 19:57:57,084 INFO [train.py:715] (3/8) Epoch 13, batch 21400, loss[loss=0.1527, simple_loss=0.2262, pruned_loss=0.03958, over 4766.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.0304, over 973010.59 frames.], batch size: 19, lr: 1.67e-04
+2022-05-07 19:58:35,346 INFO [train.py:715] (3/8) Epoch 13, batch 21450, loss[loss=0.1255, simple_loss=0.207, pruned_loss=0.02203, over 4935.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03031, over 972850.99 frames.], batch size: 21, lr: 1.67e-04
+2022-05-07 19:59:14,500 INFO [train.py:715] (3/8) Epoch 13, batch 21500, loss[loss=0.1278, simple_loss=0.2083, pruned_loss=0.02367, over 4687.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.0308, over 972570.68 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 19:59:52,263 INFO [train.py:715] (3/8) Epoch 13, batch 21550, loss[loss=0.1485, simple_loss=0.2172, pruned_loss=0.03995, over 4856.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03054, over 972511.06 frames.], batch size: 34, lr: 1.67e-04
+2022-05-07 20:00:30,902 INFO [train.py:715] (3/8) Epoch 13, batch 21600, loss[loss=0.1573, simple_loss=0.2275, pruned_loss=0.04358, over 4898.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03035, over 973460.23 frames.], batch size: 17, lr: 1.67e-04
+2022-05-07 20:01:09,865 INFO [train.py:715] (3/8) Epoch 13, batch 21650, loss[loss=0.1428, simple_loss=0.214, pruned_loss=0.03581, over 4748.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03098, over 973478.65 frames.], batch size: 16, lr: 1.67e-04
+2022-05-07 20:01:48,624 INFO [train.py:715] (3/8) Epoch 13, batch 21700, loss[loss=0.145, simple_loss=0.226, pruned_loss=0.03198, over 4980.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03081, over 973498.56 frames.], batch size: 25, lr: 1.67e-04
+2022-05-07 20:02:27,467 INFO [train.py:715] (3/8) Epoch 13, batch 21750, loss[loss=0.1497, simple_loss=0.2287, pruned_loss=0.03538, over 4896.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03135, over 973353.77 frames.], batch size: 19, lr: 1.67e-04
+2022-05-07 20:03:06,114 INFO [train.py:715] (3/8) Epoch 13, batch 21800, loss[loss=0.1179, simple_loss=0.1786, pruned_loss=0.02859, over 4974.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03169, over 973891.71 frames.], batch size: 14, lr: 1.67e-04
+2022-05-07 20:03:45,415 INFO [train.py:715] (3/8) Epoch 13, batch 21850, loss[loss=0.132, simple_loss=0.2184, pruned_loss=0.02283, over 4854.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03146, over 973674.11 frames.], batch size: 20, lr: 1.67e-04
+2022-05-07 20:04:23,521 INFO [train.py:715] (3/8) Epoch 13, batch 21900, loss[loss=0.1234, simple_loss=0.2023, pruned_loss=0.02229, over 4948.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2099, pruned_loss=0.03174, over 972689.60 frames.], batch size: 21, lr: 1.67e-04
+2022-05-07 20:05:01,704 INFO [train.py:715] (3/8) Epoch 13, batch 21950, loss[loss=0.151, simple_loss=0.2261, pruned_loss=0.03792, over 4902.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03157, over 972701.70 frames.], batch size: 19, lr: 1.67e-04
+2022-05-07 20:05:40,176 INFO [train.py:715] (3/8) Epoch 13, batch 22000, loss[loss=0.1261, simple_loss=0.2066, pruned_loss=0.02283, over 4816.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03132, over 972566.94 frames.], batch size: 25, lr: 1.67e-04
+2022-05-07 20:06:17,894 INFO [train.py:715] (3/8) Epoch 13, batch 22050, loss[loss=0.1194, simple_loss=0.1953, pruned_loss=0.02173, over 4828.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03088, over 972696.67 frames.], batch size: 26, lr: 1.67e-04
+2022-05-07 20:06:55,942 INFO [train.py:715] (3/8) Epoch 13, batch 22100, loss[loss=0.1606, simple_loss=0.2292, pruned_loss=0.04596, over 4966.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03116, over 972894.62 frames.], batch size: 39, lr: 1.67e-04
+2022-05-07 20:07:33,695 INFO [train.py:715] (3/8) Epoch 13, batch 22150, loss[loss=0.1135, simple_loss=0.1898, pruned_loss=0.01858, over 4809.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03116, over 972364.62 frames.], batch size: 25, lr: 1.67e-04
+2022-05-07 20:08:12,648 INFO [train.py:715] (3/8) Epoch 13, batch 22200, loss[loss=0.1325, simple_loss=0.2051, pruned_loss=0.02994, over 4770.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03102, over 972402.41 frames.], batch size: 18, lr: 1.67e-04
+2022-05-07 20:08:50,193 INFO [train.py:715] (3/8) Epoch 13, batch 22250, loss[loss=0.1413, simple_loss=0.2088, pruned_loss=0.03691, over 4837.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03045, over 972705.96 frames.], batch size: 30, lr: 1.67e-04
+2022-05-07 20:09:28,955 INFO [train.py:715] (3/8) Epoch 13, batch 22300, loss[loss=0.1259, simple_loss=0.1992, pruned_loss=0.02629, over 4976.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03053, over 973812.66 frames.], batch size: 14, lr: 1.67e-04
+2022-05-07 20:10:07,703 INFO [train.py:715] (3/8) Epoch 13, batch 22350, loss[loss=0.1353, simple_loss=0.2157, pruned_loss=0.02744, over 4814.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03086, over 973446.17 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 20:10:45,730 INFO [train.py:715] (3/8) Epoch 13, batch 22400, loss[loss=0.1321, simple_loss=0.2003, pruned_loss=0.03197, over 4957.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03077, over 973464.14 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 20:11:23,413 INFO [train.py:715] (3/8) Epoch 13, batch 22450, loss[loss=0.1463, simple_loss=0.2222, pruned_loss=0.03526, over 4989.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03093, over 972997.81 frames.], batch size: 14, lr: 1.67e-04
+2022-05-07 20:12:01,256 INFO [train.py:715] (3/8) Epoch 13, batch 22500, loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03029, over 4805.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03075, over 973187.15 frames.], batch size: 25, lr: 1.67e-04
+2022-05-07 20:12:39,612 INFO [train.py:715] (3/8) Epoch 13, batch 22550, loss[loss=0.1201, simple_loss=0.192, pruned_loss=0.02409, over 4925.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03089, over 972843.88 frames.], batch size: 18, lr: 1.67e-04
+2022-05-07 20:13:16,804 INFO [train.py:715] (3/8) Epoch 13, batch 22600, loss[loss=0.1368, simple_loss=0.2134, pruned_loss=0.03012, over 4902.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03127, over 972524.60 frames.], batch size: 19, lr: 1.67e-04
+2022-05-07 20:13:54,711 INFO [train.py:715] (3/8) Epoch 13, batch 22650, loss[loss=0.1391, simple_loss=0.2127, pruned_loss=0.03277, over 4842.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03156, over 972959.58 frames.], batch size: 30, lr: 1.67e-04
+2022-05-07 20:14:32,803 INFO [train.py:715] (3/8) Epoch 13, batch 22700, loss[loss=0.1495, simple_loss=0.213, pruned_loss=0.04293, over 4781.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03149, over 973591.42 frames.], batch size: 17, lr: 1.67e-04
+2022-05-07 20:15:11,034 INFO [train.py:715] (3/8) Epoch 13, batch 22750, loss[loss=0.1807, simple_loss=0.2454, pruned_loss=0.05799, over 4805.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03171, over 973860.23 frames.], batch size: 24, lr: 1.67e-04
+2022-05-07 20:15:49,014 INFO [train.py:715] (3/8) Epoch 13, batch 22800, loss[loss=0.1257, simple_loss=0.1964, pruned_loss=0.02753, over 4805.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2111, pruned_loss=0.03139, over 973693.81 frames.], batch size: 12, lr: 1.67e-04
+2022-05-07 20:16:27,580 INFO [train.py:715] (3/8) Epoch 13, batch 22850, loss[loss=0.1317, simple_loss=0.2103, pruned_loss=0.02657, over 4857.00 frames.], tot_loss[loss=0.137, simple_loss=0.2114, pruned_loss=0.03129, over 973584.08 frames.], batch size: 32, lr: 1.67e-04
+2022-05-07 20:17:06,831 INFO [train.py:715] (3/8) Epoch 13, batch 22900, loss[loss=0.1386, simple_loss=0.2075, pruned_loss=0.0348, over 4838.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2115, pruned_loss=0.03163, over 973981.79 frames.], batch size: 13, lr: 1.67e-04
+2022-05-07 20:17:44,514 INFO [train.py:715] (3/8) Epoch 13, batch 22950, loss[loss=0.1272, simple_loss=0.2086, pruned_loss=0.02284, over 4988.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2114, pruned_loss=0.03145, over 974178.29 frames.], batch size: 28, lr: 1.67e-04
+2022-05-07 20:18:23,098 INFO [train.py:715] (3/8) Epoch 13, batch 23000, loss[loss=0.1255, simple_loss=0.1875, pruned_loss=0.0317, over 4962.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2111, pruned_loss=0.03169, over 972476.86 frames.], batch size: 14, lr: 1.67e-04
+2022-05-07 20:19:01,744 INFO [train.py:715] (3/8) Epoch 13, batch 23050, loss[loss=0.1151, simple_loss=0.1878, pruned_loss=0.02116, over 4780.00 frames.], tot_loss[loss=0.137, simple_loss=0.211, pruned_loss=0.03145, over 972788.05 frames.], batch size: 12, lr: 1.67e-04
+2022-05-07 20:19:40,071 INFO [train.py:715] (3/8) Epoch 13, batch 23100, loss[loss=0.1445, simple_loss=0.2188, pruned_loss=0.03507, over 4964.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2106, pruned_loss=0.03124, over 973168.85 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 20:20:17,987 INFO [train.py:715] (3/8) Epoch 13, batch 23150, loss[loss=0.1314, simple_loss=0.212, pruned_loss=0.02538, over 4818.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2108, pruned_loss=0.03142, over 972881.52 frames.], batch size: 21, lr: 1.67e-04
+2022-05-07 20:20:56,165 INFO [train.py:715] (3/8) Epoch 13, batch 23200, loss[loss=0.1236, simple_loss=0.1944, pruned_loss=0.02645, over 4700.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03118, over 972630.91 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 20:21:34,317 INFO [train.py:715] (3/8) Epoch 13, batch 23250, loss[loss=0.1235, simple_loss=0.2012, pruned_loss=0.02284, over 4808.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03094, over 973318.55 frames.], batch size: 25, lr: 1.67e-04
+2022-05-07 20:22:11,786 INFO [train.py:715] (3/8) Epoch 13, batch 23300, loss[loss=0.1221, simple_loss=0.1887, pruned_loss=0.02771, over 4935.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.03099, over 972151.00 frames.], batch size: 29, lr: 1.67e-04
+2022-05-07 20:22:50,107 INFO [train.py:715] (3/8) Epoch 13, batch 23350, loss[loss=0.1417, simple_loss=0.2199, pruned_loss=0.03171, over 4787.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.03107, over 972593.22 frames.], batch size: 14, lr: 1.67e-04
+2022-05-07 20:23:28,677 INFO [train.py:715] (3/8) Epoch 13, batch 23400, loss[loss=0.1216, simple_loss=0.197, pruned_loss=0.02314, over 4874.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03093, over 972379.00 frames.], batch size: 20, lr: 1.67e-04
+2022-05-07 20:24:06,994 INFO [train.py:715] (3/8) Epoch 13, batch 23450, loss[loss=0.1041, simple_loss=0.181, pruned_loss=0.01358, over 4972.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03083, over 971897.06 frames.], batch size: 25, lr: 1.67e-04
+2022-05-07 20:24:45,014 INFO [train.py:715] (3/8) Epoch 13, batch 23500, loss[loss=0.1173, simple_loss=0.1981, pruned_loss=0.01823, over 4945.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03069, over 971748.20 frames.], batch size: 21, lr: 1.67e-04
+2022-05-07 20:25:23,769 INFO [train.py:715] (3/8) Epoch 13, batch 23550, loss[loss=0.1387, simple_loss=0.209, pruned_loss=0.0342, over 4883.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.031, over 971319.66 frames.], batch size: 22, lr: 1.67e-04
+2022-05-07 20:26:02,268 INFO [train.py:715] (3/8) Epoch 13, batch 23600, loss[loss=0.1456, simple_loss=0.1998, pruned_loss=0.04572, over 4846.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03106, over 971461.94 frames.], batch size: 30, lr: 1.67e-04
+2022-05-07 20:26:39,840 INFO [train.py:715] (3/8) Epoch 13, batch 23650, loss[loss=0.1518, simple_loss=0.2101, pruned_loss=0.04675, over 4956.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03115, over 972052.40 frames.], batch size: 35, lr: 1.67e-04
+2022-05-07 20:27:18,105 INFO [train.py:715] (3/8) Epoch 13, batch 23700, loss[loss=0.181, simple_loss=0.2672, pruned_loss=0.04746, over 4829.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03138, over 972155.95 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 20:27:56,588 INFO [train.py:715] (3/8) Epoch 13, batch 23750, loss[loss=0.1242, simple_loss=0.2014, pruned_loss=0.02353, over 4936.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03077, over 972041.35 frames.], batch size: 21, lr: 1.67e-04
+2022-05-07 20:28:34,760 INFO [train.py:715] (3/8) Epoch 13, batch 23800, loss[loss=0.1554, simple_loss=0.2345, pruned_loss=0.0382, over 4962.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03129, over 971488.65 frames.], batch size: 15, lr: 1.67e-04
+2022-05-07 20:29:12,134 INFO [train.py:715] (3/8) Epoch 13, batch 23850, loss[loss=0.1478, simple_loss=0.2261, pruned_loss=0.03477, over 4744.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03129, over 970952.81 frames.], batch size: 16, lr: 1.67e-04
+2022-05-07 20:29:51,251 INFO [train.py:715] (3/8) Epoch 13, batch 23900, loss[loss=0.1923, simple_loss=0.2709, pruned_loss=0.05687, over 4928.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03119, over 971085.44 frames.], batch size: 18, lr: 1.67e-04
+2022-05-07 20:30:29,201 INFO [train.py:715] (3/8) Epoch 13, batch 23950, loss[loss=0.1136, simple_loss=0.1868, pruned_loss=0.02024, over 4929.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03093, over 971674.85 frames.], batch size: 29, lr: 1.67e-04
+2022-05-07 20:31:06,579 INFO [train.py:715] (3/8) Epoch 13, batch 24000, loss[loss=0.1497, simple_loss=0.2329, pruned_loss=0.0332, over 4823.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03118, over 971925.32 frames.], batch size: 25, lr: 1.67e-04
+2022-05-07 20:31:06,580 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 20:31:16,108 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1053, simple_loss=0.1891, pruned_loss=0.01069, over 914524.00 frames.
+2022-05-07 20:31:53,723 INFO [train.py:715] (3/8) Epoch 13, batch 24050, loss[loss=0.1255, simple_loss=0.1961, pruned_loss=0.02742, over 4865.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03044, over 972330.45 frames.], batch size: 16, lr: 1.67e-04
+2022-05-07 20:32:31,541 INFO [train.py:715] (3/8) Epoch 13, batch 24100, loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03729, over 4801.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03042, over 972084.70 frames.], batch size: 25, lr: 1.67e-04
+2022-05-07 20:33:10,919 INFO [train.py:715] (3/8) Epoch 13, batch 24150, loss[loss=0.1378, simple_loss=0.2081, pruned_loss=0.0337, over 4749.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03105, over 972423.38 frames.], batch size: 16, lr: 1.67e-04
+2022-05-07 20:33:49,886 INFO [train.py:715] (3/8) Epoch 13, batch 24200, loss[loss=0.1575, simple_loss=0.2338, pruned_loss=0.04065, over 4752.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03059, over 972777.90 frames.], batch size: 16, lr: 1.67e-04
+2022-05-07 20:34:28,088 INFO [train.py:715] (3/8) Epoch 13, batch 24250, loss[loss=0.1244, simple_loss=0.1907, pruned_loss=0.02901, over 4943.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03038, over 972550.93 frames.], batch size: 29, lr: 1.67e-04
+2022-05-07 20:35:06,952 INFO [train.py:715] (3/8) Epoch 13, batch 24300, loss[loss=0.1229, simple_loss=0.1915, pruned_loss=0.02718, over 4956.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03076, over 972518.83 frames.], batch size: 35, lr: 1.67e-04
+2022-05-07 20:35:45,649 INFO [train.py:715] (3/8) Epoch 13, batch 24350, loss[loss=0.1319, simple_loss=0.1966, pruned_loss=0.03364, over 4958.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03123, over 971948.17 frames.], batch size: 21, lr: 1.67e-04
+2022-05-07 20:36:23,175 INFO [train.py:715] (3/8) Epoch 13, batch 24400, loss[loss=0.154, simple_loss=0.2209, pruned_loss=0.04351, over 4902.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03153, over 971590.41 frames.], batch size: 17, lr: 1.67e-04
+2022-05-07 20:37:01,583 INFO [train.py:715] (3/8) Epoch 13, batch 24450, loss[loss=0.1229, simple_loss=0.199, pruned_loss=0.02343, over 4947.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03141, over 971468.65 frames.], batch size: 39, lr: 1.67e-04
+2022-05-07 20:37:40,237 INFO [train.py:715] (3/8) Epoch 13, batch 24500, loss[loss=0.1172, simple_loss=0.1848, pruned_loss=0.02478, over 4801.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03143, over 971522.35 frames.], batch size: 17, lr: 1.67e-04
+2022-05-07 20:38:18,536 INFO [train.py:715] (3/8) Epoch 13, batch 24550, loss[loss=0.1254, simple_loss=0.2072, pruned_loss=0.02176, over 4974.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03162, over 972190.23 frames.], batch size: 28, lr: 1.67e-04
+2022-05-07 20:38:56,921 INFO [train.py:715] (3/8) Epoch 13, batch 24600, loss[loss=0.1145, simple_loss=0.1941, pruned_loss=0.01751, over 4913.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2107, pruned_loss=0.03113, over 972114.38 frames.], batch size: 17, lr: 1.67e-04
+2022-05-07 20:39:36,092 INFO [train.py:715] (3/8) Epoch 13, batch 24650, loss[loss=0.1243, simple_loss=0.1977, pruned_loss=0.02543, over 4768.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.03101, over 972080.76 frames.], batch size: 19, lr: 1.67e-04
+2022-05-07 20:40:14,991 INFO [train.py:715] (3/8) Epoch 13, batch 24700, loss[loss=0.1395, simple_loss=0.216, pruned_loss=0.03147, over 4947.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03092, over 972760.79 frames.], batch size: 21, lr: 1.67e-04
+2022-05-07 20:40:52,894 INFO [train.py:715] (3/8) Epoch 13, batch 24750, loss[loss=0.1282, simple_loss=0.1951, pruned_loss=0.03068, over 4879.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03094, over 973096.30 frames.], batch size: 22, lr: 1.67e-04
+2022-05-07 20:41:31,284 INFO [train.py:715] (3/8) Epoch 13, batch 24800, loss[loss=0.141, simple_loss=0.2254, pruned_loss=0.02828, over 4772.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.03132, over 972991.65 frames.], batch size: 18, lr: 1.67e-04
+2022-05-07 20:42:10,093 INFO [train.py:715] (3/8) Epoch 13, batch 24850, loss[loss=0.1104, simple_loss=0.1826, pruned_loss=0.01909, over 4797.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03101, over 972654.60 frames.], batch size: 24, lr: 1.66e-04
+2022-05-07 20:42:48,217 INFO [train.py:715] (3/8) Epoch 13, batch 24900, loss[loss=0.1226, simple_loss=0.2035, pruned_loss=0.02082, over 4776.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03106, over 972340.60 frames.], batch size: 18, lr: 1.66e-04
+2022-05-07 20:43:26,335 INFO [train.py:715] (3/8) Epoch 13, batch 24950, loss[loss=0.1286, simple_loss=0.2107, pruned_loss=0.02326, over 4885.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03084, over 972211.43 frames.], batch size: 39, lr: 1.66e-04
+2022-05-07 20:44:04,944 INFO [train.py:715] (3/8) Epoch 13, batch 25000, loss[loss=0.1515, simple_loss=0.2104, pruned_loss=0.04627, over 4931.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03123, over 972163.24 frames.], batch size: 39, lr: 1.66e-04
+2022-05-07 20:44:43,239 INFO [train.py:715] (3/8) Epoch 13, batch 25050, loss[loss=0.1337, simple_loss=0.2062, pruned_loss=0.03057, over 4928.00 frames.], tot_loss[loss=0.1359, simple_loss=0.21, pruned_loss=0.03089, over 973041.52 frames.], batch size: 21, lr: 1.66e-04
+2022-05-07 20:45:20,927 INFO [train.py:715] (3/8) Epoch 13, batch 25100, loss[loss=0.1763, simple_loss=0.2385, pruned_loss=0.05707, over 4926.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03133, over 972266.14 frames.], batch size: 39, lr: 1.66e-04
+2022-05-07 20:46:00,040 INFO [train.py:715] (3/8) Epoch 13, batch 25150, loss[loss=0.1543, simple_loss=0.2249, pruned_loss=0.04181, over 4919.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03138, over 972765.11 frames.], batch size: 18, lr: 1.66e-04
+2022-05-07 20:46:38,587 INFO [train.py:715] (3/8) Epoch 13, batch 25200, loss[loss=0.1405, simple_loss=0.2062, pruned_loss=0.03741, over 4983.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03165, over 972999.12 frames.], batch size: 39, lr: 1.66e-04
+2022-05-07 20:47:17,719 INFO [train.py:715] (3/8) Epoch 13, batch 25250, loss[loss=0.1109, simple_loss=0.1856, pruned_loss=0.01814, over 4973.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03136, over 973004.76 frames.], batch size: 24, lr: 1.66e-04
+2022-05-07 20:47:55,928 INFO [train.py:715] (3/8) Epoch 13, batch 25300, loss[loss=0.1506, simple_loss=0.2339, pruned_loss=0.03366, over 4774.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03183, over 973315.86 frames.], batch size: 18, lr: 1.66e-04
+2022-05-07 20:48:34,493 INFO [train.py:715] (3/8) Epoch 13, batch 25350, loss[loss=0.1506, simple_loss=0.2119, pruned_loss=0.0447, over 4888.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03236, over 972665.43 frames.], batch size: 32, lr: 1.66e-04
+2022-05-07 20:49:13,703 INFO [train.py:715] (3/8) Epoch 13, batch 25400, loss[loss=0.1251, simple_loss=0.2014, pruned_loss=0.02446, over 4791.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03168, over 972733.06 frames.], batch size: 24, lr: 1.66e-04
+2022-05-07 20:49:51,567 INFO [train.py:715] (3/8) Epoch 13, batch 25450, loss[loss=0.1322, simple_loss=0.1939, pruned_loss=0.03529, over 4875.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.0318, over 972366.67 frames.], batch size: 16, lr: 1.66e-04
+2022-05-07 20:50:30,630 INFO [train.py:715] (3/8) Epoch 13, batch 25500, loss[loss=0.1331, simple_loss=0.1999, pruned_loss=0.03317, over 4844.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03113, over 972830.94 frames.], batch size: 13, lr: 1.66e-04
+2022-05-07 20:51:09,203 INFO [train.py:715] (3/8) Epoch 13, batch 25550, loss[loss=0.1477, simple_loss=0.2277, pruned_loss=0.03379, over 4957.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03077, over 972353.34 frames.], batch size: 39, lr: 1.66e-04
+2022-05-07 20:51:47,750 INFO [train.py:715] (3/8) Epoch 13, batch 25600, loss[loss=0.1315, simple_loss=0.2093, pruned_loss=0.02685, over 4820.00 frames.], tot_loss[loss=0.136, simple_loss=0.2101, pruned_loss=0.03092, over 972060.92 frames.], batch size: 27, lr: 1.66e-04
+2022-05-07 20:52:25,799 INFO [train.py:715] (3/8) Epoch 13, batch 25650, loss[loss=0.1264, simple_loss=0.1999, pruned_loss=0.02648, over 4756.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2101, pruned_loss=0.03069, over 971612.21 frames.], batch size: 14, lr: 1.66e-04
+2022-05-07 20:53:05,134 INFO [train.py:715] (3/8) Epoch 13, batch 25700, loss[loss=0.1382, simple_loss=0.22, pruned_loss=0.02823, over 4697.00 frames.], tot_loss[loss=0.136, simple_loss=0.2104, pruned_loss=0.03087, over 971955.70 frames.], batch size: 15, lr: 1.66e-04
+2022-05-07 20:53:43,488 INFO [train.py:715] (3/8) Epoch 13, batch 25750, loss[loss=0.1418, simple_loss=0.2215, pruned_loss=0.03109, over 4745.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03163, over 972183.24 frames.], batch size: 16, lr: 1.66e-04
+2022-05-07 20:54:21,673 INFO [train.py:715] (3/8) Epoch 13, batch 25800, loss[loss=0.1584, simple_loss=0.2331, pruned_loss=0.04185, over 4737.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03142, over 972086.07 frames.], batch size: 16, lr: 1.66e-04
+2022-05-07 20:55:00,565 INFO [train.py:715] (3/8) Epoch 13, batch 25850, loss[loss=0.1286, simple_loss=0.2082, pruned_loss=0.0245, over 4966.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.0314, over 971586.63 frames.], batch size: 28, lr: 1.66e-04
+2022-05-07 20:55:39,361 INFO [train.py:715] (3/8) Epoch 13, batch 25900, loss[loss=0.1537, simple_loss=0.2176, pruned_loss=0.04484, over 4833.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03124, over 972561.73 frames.], batch size: 30, lr: 1.66e-04
+2022-05-07 20:56:18,178 INFO [train.py:715] (3/8) Epoch 13, batch 25950, loss[loss=0.1627, simple_loss=0.2374, pruned_loss=0.04398, over 4879.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2103, pruned_loss=0.031, over 972437.01 frames.], batch size: 30, lr: 1.66e-04
+2022-05-07 20:56:57,181 INFO [train.py:715] (3/8) Epoch 13, batch 26000, loss[loss=0.1481, simple_loss=0.2301, pruned_loss=0.03309, over 4811.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2106, pruned_loss=0.03116, over 971927.21 frames.], batch size: 25, lr: 1.66e-04
+2022-05-07 20:57:36,541 INFO [train.py:715] (3/8) Epoch 13, batch 26050, loss[loss=0.1127, simple_loss=0.1809, pruned_loss=0.02224, over 4777.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03095, over 971705.12 frames.], batch size: 12, lr: 1.66e-04
+2022-05-07 20:58:15,738 INFO [train.py:715] (3/8) Epoch 13, batch 26100, loss[loss=0.14, simple_loss=0.2145, pruned_loss=0.03274, over 4831.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03113, over 972078.54 frames.], batch size: 13, lr: 1.66e-04
+2022-05-07 20:58:54,122 INFO [train.py:715] (3/8) Epoch 13, batch 26150, loss[loss=0.1211, simple_loss=0.1909, pruned_loss=0.02565, over 4788.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03151, over 972287.09 frames.], batch size: 14, lr: 1.66e-04
+2022-05-07 20:59:33,346 INFO [train.py:715] (3/8) Epoch 13, batch 26200, loss[loss=0.1406, simple_loss=0.219, pruned_loss=0.03113, over 4898.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03145, over 971747.40 frames.], batch size: 17, lr: 1.66e-04
+2022-05-07 21:00:12,169 INFO [train.py:715] (3/8) Epoch 13, batch 26250, loss[loss=0.15, simple_loss=0.2174, pruned_loss=0.04132, over 4693.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03142, over 970539.94 frames.], batch size: 15, lr: 1.66e-04
+2022-05-07 21:00:50,344 INFO [train.py:715] (3/8) Epoch 13, batch 26300, loss[loss=0.1428, simple_loss=0.2239, pruned_loss=0.03084, over 4756.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03118, over 971216.71 frames.], batch size: 16, lr: 1.66e-04
+2022-05-07 21:01:28,298 INFO [train.py:715] (3/8) Epoch 13, batch 26350, loss[loss=0.1303, simple_loss=0.2045, pruned_loss=0.02803, over 4822.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03125, over 971604.22 frames.], batch size: 26, lr: 1.66e-04
+2022-05-07 21:02:07,165 INFO [train.py:715] (3/8) Epoch 13, batch 26400, loss[loss=0.134, simple_loss=0.2184, pruned_loss=0.02479, over 4978.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03094, over 971738.93 frames.], batch size: 24, lr: 1.66e-04
+2022-05-07 21:02:46,105 INFO [train.py:715] (3/8) Epoch 13, batch 26450, loss[loss=0.1168, simple_loss=0.199, pruned_loss=0.01728, over 4989.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03074, over 971665.23 frames.], batch size: 26, lr: 1.66e-04
+2022-05-07 21:03:24,278 INFO [train.py:715] (3/8) Epoch 13, batch 26500, loss[loss=0.1555, simple_loss=0.2233, pruned_loss=0.04383, over 4914.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03117, over 970540.43 frames.], batch size: 17, lr: 1.66e-04
+2022-05-07 21:04:03,398 INFO [train.py:715] (3/8) Epoch 13, batch 26550, loss[loss=0.1613, simple_loss=0.2272, pruned_loss=0.04772, over 4934.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2089, pruned_loss=0.03114, over 971158.37 frames.], batch size: 23, lr: 1.66e-04
+2022-05-07 21:04:41,839 INFO [train.py:715] (3/8) Epoch 13, batch 26600, loss[loss=0.1116, simple_loss=0.1857, pruned_loss=0.01869, over 4803.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03093, over 970675.32 frames.], batch size: 24, lr: 1.66e-04
+2022-05-07 21:05:20,066 INFO [train.py:715] (3/8) Epoch 13, batch 26650, loss[loss=0.1275, simple_loss=0.2026, pruned_loss=0.02625, over 4933.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2098, pruned_loss=0.03147, over 971652.59 frames.], batch size: 18, lr: 1.66e-04
+2022-05-07 21:05:58,318 INFO [train.py:715] (3/8) Epoch 13, batch 26700, loss[loss=0.1356, simple_loss=0.2127, pruned_loss=0.02921, over 4976.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03086, over 972793.75 frames.], batch size: 25, lr: 1.66e-04
+2022-05-07 21:06:37,481 INFO [train.py:715] (3/8) Epoch 13, batch 26750, loss[loss=0.1483, simple_loss=0.2246, pruned_loss=0.03595, over 4765.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03119, over 972768.12 frames.], batch size: 19, lr: 1.66e-04
+2022-05-07 21:07:15,990 INFO [train.py:715] (3/8) Epoch 13, batch 26800, loss[loss=0.1383, simple_loss=0.2152, pruned_loss=0.03071, over 4945.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03109, over 972810.38 frames.], batch size: 23, lr: 1.66e-04
+2022-05-07 21:07:54,603 INFO [train.py:715] (3/8) Epoch 13, batch 26850, loss[loss=0.1532, simple_loss=0.2244, pruned_loss=0.04099, over 4919.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03099, over 971841.19 frames.], batch size: 21, lr: 1.66e-04
+2022-05-07 21:08:33,347 INFO [train.py:715] (3/8) Epoch 13, batch 26900, loss[loss=0.121, simple_loss=0.2022, pruned_loss=0.0199, over 4817.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03089, over 972214.70 frames.], batch size: 25, lr: 1.66e-04
+2022-05-07 21:09:11,794 INFO [train.py:715] (3/8) Epoch 13, batch 26950, loss[loss=0.1302, simple_loss=0.2066, pruned_loss=0.02695, over 4867.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03072, over 972183.59 frames.], batch size: 32, lr: 1.66e-04
+2022-05-07 21:09:50,378 INFO [train.py:715] (3/8) Epoch 13, batch 27000, loss[loss=0.1145, simple_loss=0.186, pruned_loss=0.02148, over 4882.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03084, over 972042.34 frames.], batch size: 16, lr: 1.66e-04
+2022-05-07 21:09:50,378 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 21:09:59,935 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1053, simple_loss=0.1891, pruned_loss=0.01077, over 914524.00 frames.
+2022-05-07 21:10:39,027 INFO [train.py:715] (3/8) Epoch 13, batch 27050, loss[loss=0.1452, simple_loss=0.2189, pruned_loss=0.03582, over 4975.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03094, over 971554.65 frames.], batch size: 24, lr: 1.66e-04
+2022-05-07 21:11:17,913 INFO [train.py:715] (3/8) Epoch 13, batch 27100, loss[loss=0.121, simple_loss=0.2015, pruned_loss=0.02025, over 4737.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.0308, over 970850.93 frames.], batch size: 16, lr: 1.66e-04
+2022-05-07 21:11:57,149 INFO [train.py:715] (3/8) Epoch 13, batch 27150, loss[loss=0.1395, simple_loss=0.2161, pruned_loss=0.03149, over 4770.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03087, over 970391.70 frames.], batch size: 14, lr: 1.66e-04
+2022-05-07 21:12:36,111 INFO [train.py:715] (3/8) Epoch 13, batch 27200, loss[loss=0.1212, simple_loss=0.196, pruned_loss=0.02319, over 4768.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03063, over 970971.15 frames.], batch size: 19, lr: 1.66e-04
+2022-05-07 21:13:14,912 INFO [train.py:715] (3/8) Epoch 13, batch 27250, loss[loss=0.1211, simple_loss=0.1948, pruned_loss=0.02367, over 4819.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03044, over 971669.35 frames.], batch size: 27, lr: 1.66e-04
+2022-05-07 21:13:54,908 INFO [train.py:715] (3/8) Epoch 13, batch 27300, loss[loss=0.157, simple_loss=0.2222, pruned_loss=0.04591, over 4793.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03111, over 971928.45 frames.], batch size: 24, lr: 1.66e-04
+2022-05-07 21:14:33,864 INFO [train.py:715] (3/8) Epoch 13, batch 27350, loss[loss=0.1243, simple_loss=0.187, pruned_loss=0.03082, over 4773.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03103, over 972462.14 frames.], batch size: 17, lr: 1.66e-04
+2022-05-07 21:15:11,637 INFO [train.py:715] (3/8) Epoch 13, batch 27400, loss[loss=0.1306, simple_loss=0.2044, pruned_loss=0.02846, over 4899.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03106, over 972712.65 frames.], batch size: 19, lr: 1.66e-04
+2022-05-07 21:15:49,744 INFO [train.py:715] (3/8) Epoch 13, batch 27450, loss[loss=0.1302, simple_loss=0.2043, pruned_loss=0.02803, over 4765.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03126, over 973359.86 frames.], batch size: 18, lr: 1.66e-04
+2022-05-07 21:16:30,589 INFO [train.py:715] (3/8) Epoch 13, batch 27500, loss[loss=0.1121, simple_loss=0.1871, pruned_loss=0.01861, over 4935.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03144, over 972952.80 frames.], batch size: 21, lr: 1.66e-04
+2022-05-07 21:17:08,828 INFO [train.py:715] (3/8) Epoch 13, batch 27550, loss[loss=0.1371, simple_loss=0.2147, pruned_loss=0.02973, over 4919.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03142, over 972829.35 frames.], batch size: 23, lr: 1.66e-04
+2022-05-07 21:17:46,778 INFO [train.py:715] (3/8) Epoch 13, batch 27600, loss[loss=0.1392, simple_loss=0.2069, pruned_loss=0.03581, over 4734.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03061, over 972319.38 frames.], batch size: 16, lr: 1.66e-04
+2022-05-07 21:18:25,957 INFO [train.py:715] (3/8) Epoch 13, batch 27650, loss[loss=0.1189, simple_loss=0.1978, pruned_loss=0.01996, over 4936.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03119, over 972054.60 frames.], batch size: 29, lr: 1.66e-04
+2022-05-07 21:19:03,877 INFO [train.py:715] (3/8) Epoch 13, batch 27700, loss[loss=0.1074, simple_loss=0.1833, pruned_loss=0.01572, over 4931.00 frames.], tot_loss[loss=0.1357, simple_loss=0.209, pruned_loss=0.03119, over 973027.99 frames.], batch size: 29, lr: 1.66e-04
+2022-05-07 21:19:42,882 INFO [train.py:715] (3/8) Epoch 13, batch 27750, loss[loss=0.127, simple_loss=0.2069, pruned_loss=0.02358, over 4988.00 frames.], tot_loss[loss=0.136, simple_loss=0.209, pruned_loss=0.03149, over 972987.56 frames.], batch size: 28, lr: 1.66e-04
+2022-05-07 21:20:21,393 INFO [train.py:715] (3/8) Epoch 13, batch 27800, loss[loss=0.1549, simple_loss=0.2394, pruned_loss=0.0352, over 4949.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03193, over 973443.69 frames.], batch size: 39, lr: 1.66e-04
+2022-05-07 21:21:00,120 INFO [train.py:715] (3/8) Epoch 13, batch 27850, loss[loss=0.1352, simple_loss=0.2041, pruned_loss=0.03318, over 4839.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.0319, over 972163.01 frames.], batch size: 12, lr: 1.66e-04
+2022-05-07 21:21:38,313 INFO [train.py:715] (3/8) Epoch 13, batch 27900, loss[loss=0.1416, simple_loss=0.2261, pruned_loss=0.02857, over 4810.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.032, over 972730.92 frames.], batch size: 25, lr: 1.66e-04
+2022-05-07 21:22:16,097 INFO [train.py:715] (3/8) Epoch 13, batch 27950, loss[loss=0.1249, simple_loss=0.1933, pruned_loss=0.02823, over 4837.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03193, over 973015.28 frames.], batch size: 13, lr: 1.66e-04
+2022-05-07 21:22:55,053 INFO [train.py:715] (3/8) Epoch 13, batch 28000, loss[loss=0.1394, simple_loss=0.2165, pruned_loss=0.03112, over 4785.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03166, over 972711.16 frames.], batch size: 14, lr: 1.66e-04
+2022-05-07 21:23:33,525 INFO [train.py:715] (3/8) Epoch 13, batch 28050, loss[loss=0.1391, simple_loss=0.2243, pruned_loss=0.02694, over 4753.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.03148, over 972689.63 frames.], batch size: 16, lr: 1.66e-04
+2022-05-07 21:24:11,552 INFO [train.py:715] (3/8) Epoch 13, batch 28100, loss[loss=0.1169, simple_loss=0.1943, pruned_loss=0.01971, over 4990.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.03176, over 972484.14 frames.], batch size: 28, lr: 1.66e-04
+2022-05-07 21:24:49,598 INFO [train.py:715] (3/8) Epoch 13, batch 28150, loss[loss=0.1276, simple_loss=0.2045, pruned_loss=0.02533, over 4828.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03166, over 972452.87 frames.], batch size: 15, lr: 1.66e-04
+2022-05-07 21:25:28,817 INFO [train.py:715] (3/8) Epoch 13, batch 28200, loss[loss=0.1323, simple_loss=0.2091, pruned_loss=0.02775, over 4895.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03141, over 972685.29 frames.], batch size: 19, lr: 1.66e-04
+2022-05-07 21:26:06,611 INFO [train.py:715] (3/8) Epoch 13, batch 28250, loss[loss=0.1347, simple_loss=0.2118, pruned_loss=0.0288, over 4829.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03121, over 972971.14 frames.], batch size: 15, lr: 1.66e-04
+2022-05-07 21:26:44,753 INFO [train.py:715] (3/8) Epoch 13, batch 28300, loss[loss=0.1409, simple_loss=0.2179, pruned_loss=0.03201, over 4854.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03171, over 973343.78 frames.], batch size: 15, lr: 1.66e-04
+2022-05-07 21:27:23,462 INFO [train.py:715] (3/8) Epoch 13, batch 28350, loss[loss=0.1172, simple_loss=0.1937, pruned_loss=0.02034, over 4929.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03159, over 973739.71 frames.], batch size: 21, lr: 1.66e-04
+2022-05-07 21:28:01,609 INFO [train.py:715] (3/8) Epoch 13, batch 28400, loss[loss=0.144, simple_loss=0.2184, pruned_loss=0.03479, over 4904.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.0313, over 974154.54 frames.], batch size: 17, lr: 1.66e-04
+2022-05-07 21:28:40,048 INFO [train.py:715] (3/8) Epoch 13, batch 28450, loss[loss=0.1367, simple_loss=0.2084, pruned_loss=0.03248, over 4700.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03074, over 974376.39 frames.], batch size: 15, lr: 1.66e-04
+2022-05-07 21:29:18,387 INFO [train.py:715] (3/8) Epoch 13, batch 28500, loss[loss=0.1281, simple_loss=0.208, pruned_loss=0.02417, over 4984.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03078, over 974575.01 frames.], batch size: 28, lr: 1.66e-04
+2022-05-07 21:29:57,060 INFO [train.py:715] (3/8) Epoch 13, batch 28550, loss[loss=0.1965, simple_loss=0.2588, pruned_loss=0.06711, over 4991.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03091, over 974279.37 frames.], batch size: 16, lr: 1.66e-04
+2022-05-07 21:30:35,261 INFO [train.py:715] (3/8) Epoch 13, batch 28600, loss[loss=0.1246, simple_loss=0.199, pruned_loss=0.02511, over 4872.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03078, over 973390.19 frames.], batch size: 13, lr: 1.66e-04
+2022-05-07 21:31:13,616 INFO [train.py:715] (3/8) Epoch 13, batch 28650, loss[loss=0.128, simple_loss=0.2063, pruned_loss=0.02484, over 4871.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03036, over 972529.02 frames.], batch size: 20, lr: 1.66e-04
+2022-05-07 21:31:52,262 INFO [train.py:715] (3/8) Epoch 13, batch 28700, loss[loss=0.1211, simple_loss=0.1941, pruned_loss=0.02409, over 4895.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03059, over 972407.33 frames.], batch size: 32, lr: 1.66e-04
+2022-05-07 21:32:30,333 INFO [train.py:715] (3/8) Epoch 13, batch 28750, loss[loss=0.1604, simple_loss=0.2301, pruned_loss=0.04535, over 4932.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03083, over 972578.45 frames.], batch size: 23, lr: 1.66e-04
+2022-05-07 21:33:08,637 INFO [train.py:715] (3/8) Epoch 13, batch 28800, loss[loss=0.1414, simple_loss=0.2061, pruned_loss=0.03838, over 4914.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03091, over 972014.73 frames.], batch size: 19, lr: 1.66e-04
+2022-05-07 21:33:47,845 INFO [train.py:715] (3/8) Epoch 13, batch 28850, loss[loss=0.1365, simple_loss=0.2108, pruned_loss=0.03109, over 4829.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03148, over 972353.25 frames.], batch size: 15, lr: 1.66e-04
+2022-05-07 21:34:26,366 INFO [train.py:715] (3/8) Epoch 13, batch 28900, loss[loss=0.1421, simple_loss=0.2139, pruned_loss=0.03511, over 4918.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03114, over 972099.98 frames.], batch size: 23, lr: 1.66e-04
+2022-05-07 21:35:04,279 INFO [train.py:715] (3/8) Epoch 13, batch 28950, loss[loss=0.1396, simple_loss=0.2248, pruned_loss=0.02721, over 4975.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03133, over 972513.11 frames.], batch size: 15, lr: 1.66e-04
+2022-05-07 21:35:42,443 INFO [train.py:715] (3/8) Epoch 13, batch 29000, loss[loss=0.1411, simple_loss=0.2194, pruned_loss=0.03141, over 4917.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.0308, over 972806.93 frames.], batch size: 18, lr: 1.66e-04
+2022-05-07 21:36:21,624 INFO [train.py:715] (3/8) Epoch 13, batch 29050, loss[loss=0.1343, simple_loss=0.2109, pruned_loss=0.02885, over 4845.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03104, over 972923.98 frames.], batch size: 20, lr: 1.66e-04
+2022-05-07 21:37:00,158 INFO [train.py:715] (3/8) Epoch 13, batch 29100, loss[loss=0.1612, simple_loss=0.2265, pruned_loss=0.04795, over 4984.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03113, over 972833.35 frames.], batch size: 35, lr: 1.66e-04
+2022-05-07 21:37:38,204 INFO [train.py:715] (3/8) Epoch 13, batch 29150, loss[loss=0.1175, simple_loss=0.191, pruned_loss=0.02201, over 4898.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03094, over 972997.72 frames.], batch size: 19, lr: 1.66e-04
+2022-05-07 21:38:16,964 INFO [train.py:715] (3/8) Epoch 13, batch 29200, loss[loss=0.1227, simple_loss=0.1979, pruned_loss=0.02381, over 4875.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03084, over 973473.78 frames.], batch size: 22, lr: 1.66e-04
+2022-05-07 21:38:55,210 INFO [train.py:715] (3/8) Epoch 13, batch 29250, loss[loss=0.1194, simple_loss=0.198, pruned_loss=0.02044, over 4776.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03103, over 972738.90 frames.], batch size: 17, lr: 1.66e-04
+2022-05-07 21:39:34,055 INFO [train.py:715] (3/8) Epoch 13, batch 29300, loss[loss=0.1492, simple_loss=0.216, pruned_loss=0.04121, over 4921.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03098, over 972717.03 frames.], batch size: 39, lr: 1.66e-04
+2022-05-07 21:40:12,801 INFO [train.py:715] (3/8) Epoch 13, batch 29350, loss[loss=0.1297, simple_loss=0.2017, pruned_loss=0.02888, over 4886.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.031, over 973249.98 frames.], batch size: 22, lr: 1.66e-04
+2022-05-07 21:40:51,676 INFO [train.py:715] (3/8) Epoch 13, batch 29400, loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.0297, over 4690.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03111, over 972661.48 frames.], batch size: 15, lr: 1.66e-04
+2022-05-07 21:41:29,698 INFO [train.py:715] (3/8) Epoch 13, batch 29450, loss[loss=0.1295, simple_loss=0.1975, pruned_loss=0.03078, over 4973.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03078, over 973543.21 frames.], batch size: 35, lr: 1.66e-04
+2022-05-07 21:42:08,738 INFO [train.py:715] (3/8) Epoch 13, batch 29500, loss[loss=0.1297, simple_loss=0.2117, pruned_loss=0.02382, over 4923.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03099, over 973206.77 frames.], batch size: 21, lr: 1.66e-04
+2022-05-07 21:42:47,373 INFO [train.py:715] (3/8) Epoch 13, batch 29550, loss[loss=0.1262, simple_loss=0.2041, pruned_loss=0.02408, over 4758.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03085, over 972294.07 frames.], batch size: 12, lr: 1.66e-04
+2022-05-07 21:43:25,735 INFO [train.py:715] (3/8) Epoch 13, batch 29600, loss[loss=0.1346, simple_loss=0.2114, pruned_loss=0.02892, over 4774.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03113, over 972035.75 frames.], batch size: 12, lr: 1.66e-04
+2022-05-07 21:44:03,483 INFO [train.py:715] (3/8) Epoch 13, batch 29650, loss[loss=0.1436, simple_loss=0.2171, pruned_loss=0.03502, over 4866.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03252, over 971971.09 frames.], batch size: 20, lr: 1.66e-04
+2022-05-07 21:44:41,767 INFO [train.py:715] (3/8) Epoch 13, batch 29700, loss[loss=0.1279, simple_loss=0.2045, pruned_loss=0.02572, over 4793.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2103, pruned_loss=0.03218, over 972403.19 frames.], batch size: 14, lr: 1.66e-04
+2022-05-07 21:45:20,127 INFO [train.py:715] (3/8) Epoch 13, batch 29750, loss[loss=0.1361, simple_loss=0.211, pruned_loss=0.03062, over 4914.00 frames.], tot_loss[loss=0.1371, simple_loss=0.21, pruned_loss=0.03209, over 972064.46 frames.], batch size: 19, lr: 1.66e-04
+2022-05-07 21:45:59,498 INFO [train.py:715] (3/8) Epoch 13, batch 29800, loss[loss=0.1399, simple_loss=0.2131, pruned_loss=0.0334, over 4973.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.0314, over 972568.28 frames.], batch size: 27, lr: 1.66e-04
+2022-05-07 21:46:38,731 INFO [train.py:715] (3/8) Epoch 13, batch 29850, loss[loss=0.1215, simple_loss=0.1985, pruned_loss=0.02224, over 4936.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03108, over 972890.87 frames.], batch size: 23, lr: 1.66e-04
+2022-05-07 21:47:18,340 INFO [train.py:715] (3/8) Epoch 13, batch 29900, loss[loss=0.1328, simple_loss=0.2052, pruned_loss=0.03018, over 4880.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03153, over 972107.96 frames.], batch size: 16, lr: 1.66e-04
+2022-05-07 21:47:57,736 INFO [train.py:715] (3/8) Epoch 13, batch 29950, loss[loss=0.1265, simple_loss=0.1999, pruned_loss=0.02659, over 4853.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.0313, over 972594.02 frames.], batch size: 13, lr: 1.66e-04
+2022-05-07 21:48:36,366 INFO [train.py:715] (3/8) Epoch 13, batch 30000, loss[loss=0.1378, simple_loss=0.2122, pruned_loss=0.03167, over 4805.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03102, over 972201.23 frames.], batch size: 21, lr: 1.66e-04
+2022-05-07 21:48:36,366 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 21:48:45,862 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1891, pruned_loss=0.01083, over 914524.00 frames.
+2022-05-07 21:49:25,291 INFO [train.py:715] (3/8) Epoch 13, batch 30050, loss[loss=0.1477, simple_loss=0.2162, pruned_loss=0.03957, over 4940.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03139, over 972958.78 frames.], batch size: 21, lr: 1.66e-04
+2022-05-07 21:50:05,123 INFO [train.py:715] (3/8) Epoch 13, batch 30100, loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03029, over 4861.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03198, over 972619.97 frames.], batch size: 30, lr: 1.66e-04
+2022-05-07 21:50:44,564 INFO [train.py:715] (3/8) Epoch 13, batch 30150, loss[loss=0.139, simple_loss=0.2075, pruned_loss=0.03524, over 4915.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03145, over 972369.90 frames.], batch size: 17, lr: 1.66e-04
+2022-05-07 21:51:23,147 INFO [train.py:715] (3/8) Epoch 13, batch 30200, loss[loss=0.1571, simple_loss=0.2142, pruned_loss=0.05001, over 4942.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2088, pruned_loss=0.03141, over 972128.01 frames.], batch size: 29, lr: 1.66e-04
+2022-05-07 21:52:02,986 INFO [train.py:715] (3/8) Epoch 13, batch 30250, loss[loss=0.131, simple_loss=0.1975, pruned_loss=0.03224, over 4854.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2078, pruned_loss=0.03087, over 971197.47 frames.], batch size: 13, lr: 1.66e-04
+2022-05-07 21:52:42,786 INFO [train.py:715] (3/8) Epoch 13, batch 30300, loss[loss=0.1567, simple_loss=0.2377, pruned_loss=0.03784, over 4981.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2088, pruned_loss=0.0312, over 972108.46 frames.], batch size: 24, lr: 1.66e-04
+2022-05-07 21:53:22,305 INFO [train.py:715] (3/8) Epoch 13, batch 30350, loss[loss=0.1374, simple_loss=0.1988, pruned_loss=0.03801, over 4815.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03065, over 971583.45 frames.], batch size: 25, lr: 1.66e-04
+2022-05-07 21:54:01,878 INFO [train.py:715] (3/8) Epoch 13, batch 30400, loss[loss=0.1419, simple_loss=0.2229, pruned_loss=0.03044, over 4932.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03039, over 971495.94 frames.], batch size: 23, lr: 1.66e-04
+2022-05-07 21:54:42,500 INFO [train.py:715] (3/8) Epoch 13, batch 30450, loss[loss=0.11, simple_loss=0.1872, pruned_loss=0.01643, over 4984.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2093, pruned_loss=0.03058, over 971556.99 frames.], batch size: 25, lr: 1.66e-04
+2022-05-07 21:55:22,609 INFO [train.py:715] (3/8) Epoch 13, batch 30500, loss[loss=0.1284, simple_loss=0.2019, pruned_loss=0.02752, over 4980.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03064, over 972276.35 frames.], batch size: 35, lr: 1.66e-04
+2022-05-07 21:56:02,393 INFO [train.py:715] (3/8) Epoch 13, batch 30550, loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03261, over 4904.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03065, over 972323.64 frames.], batch size: 23, lr: 1.66e-04
+2022-05-07 21:56:43,838 INFO [train.py:715] (3/8) Epoch 13, batch 30600, loss[loss=0.14, simple_loss=0.2138, pruned_loss=0.03306, over 4794.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03049, over 971945.51 frames.], batch size: 24, lr: 1.66e-04
+2022-05-07 21:57:24,954 INFO [train.py:715] (3/8) Epoch 13, batch 30650, loss[loss=0.1407, simple_loss=0.2115, pruned_loss=0.03492, over 4848.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2096, pruned_loss=0.0303, over 972801.83 frames.], batch size: 34, lr: 1.65e-04
+2022-05-07 21:58:05,361 INFO [train.py:715] (3/8) Epoch 13, batch 30700, loss[loss=0.1359, simple_loss=0.2265, pruned_loss=0.02265, over 4909.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03043, over 972626.33 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 21:58:45,825 INFO [train.py:715] (3/8) Epoch 13, batch 30750, loss[loss=0.131, simple_loss=0.2046, pruned_loss=0.02866, over 4871.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03041, over 973466.77 frames.], batch size: 16, lr: 1.65e-04
+2022-05-07 21:59:26,819 INFO [train.py:715] (3/8) Epoch 13, batch 30800, loss[loss=0.126, simple_loss=0.2165, pruned_loss=0.01774, over 4975.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03035, over 973381.89 frames.], batch size: 24, lr: 1.65e-04
+2022-05-07 22:00:07,578 INFO [train.py:715] (3/8) Epoch 13, batch 30850, loss[loss=0.114, simple_loss=0.1784, pruned_loss=0.02478, over 4787.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03059, over 972771.27 frames.], batch size: 14, lr: 1.65e-04
+2022-05-07 22:00:48,211 INFO [train.py:715] (3/8) Epoch 13, batch 30900, loss[loss=0.1236, simple_loss=0.1986, pruned_loss=0.02437, over 4802.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.0308, over 972697.77 frames.], batch size: 24, lr: 1.65e-04
+2022-05-07 22:01:29,254 INFO [train.py:715] (3/8) Epoch 13, batch 30950, loss[loss=0.1514, simple_loss=0.2231, pruned_loss=0.03986, over 4931.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03063, over 973281.00 frames.], batch size: 39, lr: 1.65e-04
+2022-05-07 22:02:09,963 INFO [train.py:715] (3/8) Epoch 13, batch 31000, loss[loss=0.1303, simple_loss=0.2047, pruned_loss=0.02795, over 4944.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.0305, over 973826.99 frames.], batch size: 23, lr: 1.65e-04
+2022-05-07 22:02:50,144 INFO [train.py:715] (3/8) Epoch 13, batch 31050, loss[loss=0.1404, simple_loss=0.2199, pruned_loss=0.03041, over 4881.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03081, over 974098.57 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:03:30,716 INFO [train.py:715] (3/8) Epoch 13, batch 31100, loss[loss=0.1258, simple_loss=0.2007, pruned_loss=0.02547, over 4901.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03095, over 971998.19 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:04:11,685 INFO [train.py:715] (3/8) Epoch 13, batch 31150, loss[loss=0.1344, simple_loss=0.2063, pruned_loss=0.03127, over 4750.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03132, over 972268.72 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:04:52,787 INFO [train.py:715] (3/8) Epoch 13, batch 31200, loss[loss=0.1482, simple_loss=0.2233, pruned_loss=0.03651, over 4804.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03127, over 971821.80 frames.], batch size: 21, lr: 1.65e-04
+2022-05-07 22:05:32,915 INFO [train.py:715] (3/8) Epoch 13, batch 31250, loss[loss=0.1507, simple_loss=0.2192, pruned_loss=0.04107, over 4858.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03168, over 971712.74 frames.], batch size: 30, lr: 1.65e-04
+2022-05-07 22:06:13,243 INFO [train.py:715] (3/8) Epoch 13, batch 31300, loss[loss=0.185, simple_loss=0.2497, pruned_loss=0.06014, over 4751.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03188, over 972317.89 frames.], batch size: 16, lr: 1.65e-04
+2022-05-07 22:06:53,514 INFO [train.py:715] (3/8) Epoch 13, batch 31350, loss[loss=0.1375, simple_loss=0.206, pruned_loss=0.03452, over 4830.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03189, over 972249.65 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:07:33,261 INFO [train.py:715] (3/8) Epoch 13, batch 31400, loss[loss=0.1355, simple_loss=0.2072, pruned_loss=0.0319, over 4690.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03162, over 971765.99 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:08:13,735 INFO [train.py:715] (3/8) Epoch 13, batch 31450, loss[loss=0.1302, simple_loss=0.2078, pruned_loss=0.02632, over 4932.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03129, over 972481.53 frames.], batch size: 23, lr: 1.65e-04
+2022-05-07 22:08:54,100 INFO [train.py:715] (3/8) Epoch 13, batch 31500, loss[loss=0.1614, simple_loss=0.2339, pruned_loss=0.04441, over 4839.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03158, over 972142.70 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:09:33,927 INFO [train.py:715] (3/8) Epoch 13, batch 31550, loss[loss=0.1238, simple_loss=0.1839, pruned_loss=0.03184, over 4814.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03102, over 972408.74 frames.], batch size: 13, lr: 1.65e-04
+2022-05-07 22:10:14,441 INFO [train.py:715] (3/8) Epoch 13, batch 31600, loss[loss=0.1202, simple_loss=0.19, pruned_loss=0.02518, over 4688.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03112, over 971833.73 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:10:55,015 INFO [train.py:715] (3/8) Epoch 13, batch 31650, loss[loss=0.1223, simple_loss=0.1938, pruned_loss=0.02545, over 4752.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03095, over 971275.91 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:11:35,403 INFO [train.py:715] (3/8) Epoch 13, batch 31700, loss[loss=0.1667, simple_loss=0.2396, pruned_loss=0.04689, over 4814.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03121, over 970874.58 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:12:15,842 INFO [train.py:715] (3/8) Epoch 13, batch 31750, loss[loss=0.1321, simple_loss=0.1964, pruned_loss=0.0339, over 4794.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03116, over 971666.69 frames.], batch size: 12, lr: 1.65e-04
+2022-05-07 22:12:56,364 INFO [train.py:715] (3/8) Epoch 13, batch 31800, loss[loss=0.1171, simple_loss=0.203, pruned_loss=0.01556, over 4975.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03074, over 972517.07 frames.], batch size: 25, lr: 1.65e-04
+2022-05-07 22:13:37,274 INFO [train.py:715] (3/8) Epoch 13, batch 31850, loss[loss=0.1611, simple_loss=0.2326, pruned_loss=0.04483, over 4962.00 frames.], tot_loss[loss=0.135, simple_loss=0.2094, pruned_loss=0.03027, over 972769.55 frames.], batch size: 39, lr: 1.65e-04
+2022-05-07 22:14:18,123 INFO [train.py:715] (3/8) Epoch 13, batch 31900, loss[loss=0.1243, simple_loss=0.2058, pruned_loss=0.0214, over 4842.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03067, over 973063.87 frames.], batch size: 26, lr: 1.65e-04
+2022-05-07 22:14:59,146 INFO [train.py:715] (3/8) Epoch 13, batch 31950, loss[loss=0.1275, simple_loss=0.1997, pruned_loss=0.02766, over 4781.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03107, over 973570.58 frames.], batch size: 12, lr: 1.65e-04
+2022-05-07 22:15:39,541 INFO [train.py:715] (3/8) Epoch 13, batch 32000, loss[loss=0.1134, simple_loss=0.1851, pruned_loss=0.02086, over 4846.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03054, over 973739.33 frames.], batch size: 13, lr: 1.65e-04
+2022-05-07 22:16:20,156 INFO [train.py:715] (3/8) Epoch 13, batch 32050, loss[loss=0.1334, simple_loss=0.2087, pruned_loss=0.02902, over 4888.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03071, over 973135.81 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:17:00,696 INFO [train.py:715] (3/8) Epoch 13, batch 32100, loss[loss=0.1319, simple_loss=0.2043, pruned_loss=0.02978, over 4887.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03102, over 972321.51 frames.], batch size: 17, lr: 1.65e-04
+2022-05-07 22:17:41,703 INFO [train.py:715] (3/8) Epoch 13, batch 32150, loss[loss=0.1412, simple_loss=0.2106, pruned_loss=0.03593, over 4928.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03112, over 973244.07 frames.], batch size: 21, lr: 1.65e-04
+2022-05-07 22:18:22,395 INFO [train.py:715] (3/8) Epoch 13, batch 32200, loss[loss=0.1477, simple_loss=0.2263, pruned_loss=0.03457, over 4803.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03127, over 973509.80 frames.], batch size: 24, lr: 1.65e-04
+2022-05-07 22:19:03,051 INFO [train.py:715] (3/8) Epoch 13, batch 32250, loss[loss=0.1579, simple_loss=0.238, pruned_loss=0.03894, over 4888.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03074, over 973151.52 frames.], batch size: 38, lr: 1.65e-04
+2022-05-07 22:19:43,880 INFO [train.py:715] (3/8) Epoch 13, batch 32300, loss[loss=0.1039, simple_loss=0.1785, pruned_loss=0.01462, over 4783.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03082, over 973614.82 frames.], batch size: 17, lr: 1.65e-04
+2022-05-07 22:20:24,950 INFO [train.py:715] (3/8) Epoch 13, batch 32350, loss[loss=0.1357, simple_loss=0.2112, pruned_loss=0.03012, over 4754.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2089, pruned_loss=0.03129, over 973316.28 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:21:06,368 INFO [train.py:715] (3/8) Epoch 13, batch 32400, loss[loss=0.1608, simple_loss=0.2409, pruned_loss=0.04035, over 4772.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03134, over 973356.12 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:21:47,425 INFO [train.py:715] (3/8) Epoch 13, batch 32450, loss[loss=0.1197, simple_loss=0.1989, pruned_loss=0.02023, over 4830.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2088, pruned_loss=0.03128, over 972837.99 frames.], batch size: 26, lr: 1.65e-04
+2022-05-07 22:22:28,212 INFO [train.py:715] (3/8) Epoch 13, batch 32500, loss[loss=0.1406, simple_loss=0.2157, pruned_loss=0.03278, over 4982.00 frames.], tot_loss[loss=0.136, simple_loss=0.209, pruned_loss=0.03154, over 973679.74 frames.], batch size: 25, lr: 1.65e-04
+2022-05-07 22:23:09,252 INFO [train.py:715] (3/8) Epoch 13, batch 32550, loss[loss=0.1319, simple_loss=0.2057, pruned_loss=0.02901, over 4888.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2085, pruned_loss=0.03106, over 973404.45 frames.], batch size: 22, lr: 1.65e-04
+2022-05-07 22:23:49,651 INFO [train.py:715] (3/8) Epoch 13, batch 32600, loss[loss=0.1716, simple_loss=0.2469, pruned_loss=0.04816, over 4695.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.0307, over 973653.20 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:24:29,999 INFO [train.py:715] (3/8) Epoch 13, batch 32650, loss[loss=0.13, simple_loss=0.2092, pruned_loss=0.02536, over 4773.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03082, over 973401.19 frames.], batch size: 14, lr: 1.65e-04
+2022-05-07 22:25:10,589 INFO [train.py:715] (3/8) Epoch 13, batch 32700, loss[loss=0.1167, simple_loss=0.1969, pruned_loss=0.0182, over 4968.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2081, pruned_loss=0.03069, over 973608.54 frames.], batch size: 24, lr: 1.65e-04
+2022-05-07 22:25:50,914 INFO [train.py:715] (3/8) Epoch 13, batch 32750, loss[loss=0.1118, simple_loss=0.1802, pruned_loss=0.02166, over 4850.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03019, over 973445.75 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:26:31,936 INFO [train.py:715] (3/8) Epoch 13, batch 32800, loss[loss=0.1557, simple_loss=0.2221, pruned_loss=0.04467, over 4968.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03108, over 973567.97 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:27:12,670 INFO [train.py:715] (3/8) Epoch 13, batch 32850, loss[loss=0.1621, simple_loss=0.2192, pruned_loss=0.05252, over 4980.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2079, pruned_loss=0.03069, over 972455.60 frames.], batch size: 14, lr: 1.65e-04
+2022-05-07 22:27:53,752 INFO [train.py:715] (3/8) Epoch 13, batch 32900, loss[loss=0.1565, simple_loss=0.2203, pruned_loss=0.04636, over 4787.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2082, pruned_loss=0.03073, over 972679.02 frames.], batch size: 17, lr: 1.65e-04
+2022-05-07 22:28:33,953 INFO [train.py:715] (3/8) Epoch 13, batch 32950, loss[loss=0.1583, simple_loss=0.227, pruned_loss=0.04475, over 4945.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03115, over 973546.77 frames.], batch size: 39, lr: 1.65e-04
+2022-05-07 22:29:14,626 INFO [train.py:715] (3/8) Epoch 13, batch 33000, loss[loss=0.1369, simple_loss=0.2064, pruned_loss=0.03372, over 4744.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03137, over 973089.88 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:29:14,626 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 22:29:24,503 INFO [train.py:742] (3/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1892, pruned_loss=0.01081, over 914524.00 frames.
+2022-05-07 22:30:05,559 INFO [train.py:715] (3/8) Epoch 13, batch 33050, loss[loss=0.1536, simple_loss=0.2248, pruned_loss=0.04121, over 4959.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03133, over 972652.82 frames.], batch size: 24, lr: 1.65e-04
+2022-05-07 22:30:45,212 INFO [train.py:715] (3/8) Epoch 13, batch 33100, loss[loss=0.143, simple_loss=0.2118, pruned_loss=0.03712, over 4801.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03094, over 972092.53 frames.], batch size: 25, lr: 1.65e-04
+2022-05-07 22:31:25,148 INFO [train.py:715] (3/8) Epoch 13, batch 33150, loss[loss=0.1578, simple_loss=0.2375, pruned_loss=0.03902, over 4793.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2103, pruned_loss=0.03107, over 972367.82 frames.], batch size: 24, lr: 1.65e-04
+2022-05-07 22:32:05,570 INFO [train.py:715] (3/8) Epoch 13, batch 33200, loss[loss=0.1658, simple_loss=0.2333, pruned_loss=0.04912, over 4832.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03102, over 972454.10 frames.], batch size: 32, lr: 1.65e-04
+2022-05-07 22:32:46,035 INFO [train.py:715] (3/8) Epoch 13, batch 33250, loss[loss=0.1281, simple_loss=0.1993, pruned_loss=0.02849, over 4908.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03169, over 973299.36 frames.], batch size: 17, lr: 1.65e-04
+2022-05-07 22:33:26,587 INFO [train.py:715] (3/8) Epoch 13, batch 33300, loss[loss=0.1386, simple_loss=0.2202, pruned_loss=0.0285, over 4818.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03113, over 973676.30 frames.], batch size: 27, lr: 1.65e-04
+2022-05-07 22:34:07,015 INFO [train.py:715] (3/8) Epoch 13, batch 33350, loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03301, over 4845.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03083, over 974286.52 frames.], batch size: 34, lr: 1.65e-04
+2022-05-07 22:34:47,633 INFO [train.py:715] (3/8) Epoch 13, batch 33400, loss[loss=0.128, simple_loss=0.2066, pruned_loss=0.02469, over 4823.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03086, over 974610.32 frames.], batch size: 25, lr: 1.65e-04
+2022-05-07 22:35:28,235 INFO [train.py:715] (3/8) Epoch 13, batch 33450, loss[loss=0.1471, simple_loss=0.2255, pruned_loss=0.03441, over 4802.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03086, over 974486.07 frames.], batch size: 21, lr: 1.65e-04
+2022-05-07 22:36:08,957 INFO [train.py:715] (3/8) Epoch 13, batch 33500, loss[loss=0.1439, simple_loss=0.2148, pruned_loss=0.0365, over 4957.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03139, over 973316.37 frames.], batch size: 35, lr: 1.65e-04
+2022-05-07 22:36:49,606 INFO [train.py:715] (3/8) Epoch 13, batch 33550, loss[loss=0.1165, simple_loss=0.1915, pruned_loss=0.02073, over 4880.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.0313, over 972731.78 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:37:30,304 INFO [train.py:715] (3/8) Epoch 13, batch 33600, loss[loss=0.1457, simple_loss=0.2187, pruned_loss=0.03636, over 4757.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03064, over 972945.37 frames.], batch size: 16, lr: 1.65e-04
+2022-05-07 22:38:10,828 INFO [train.py:715] (3/8) Epoch 13, batch 33650, loss[loss=0.1373, simple_loss=0.213, pruned_loss=0.03081, over 4906.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.0302, over 972270.07 frames.], batch size: 18, lr: 1.65e-04
+2022-05-07 22:38:51,061 INFO [train.py:715] (3/8) Epoch 13, batch 33700, loss[loss=0.142, simple_loss=0.2088, pruned_loss=0.0376, over 4910.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03036, over 973286.99 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:39:32,032 INFO [train.py:715] (3/8) Epoch 13, batch 33750, loss[loss=0.1468, simple_loss=0.2167, pruned_loss=0.03842, over 4849.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02978, over 973389.44 frames.], batch size: 30, lr: 1.65e-04
+2022-05-07 22:40:12,828 INFO [train.py:715] (3/8) Epoch 13, batch 33800, loss[loss=0.1185, simple_loss=0.2006, pruned_loss=0.01822, over 4699.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03036, over 972073.18 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:40:53,573 INFO [train.py:715] (3/8) Epoch 13, batch 33850, loss[loss=0.1129, simple_loss=0.1909, pruned_loss=0.01749, over 4915.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03062, over 971531.11 frames.], batch size: 23, lr: 1.65e-04
+2022-05-07 22:41:34,020 INFO [train.py:715] (3/8) Epoch 13, batch 33900, loss[loss=0.1209, simple_loss=0.1943, pruned_loss=0.02372, over 4902.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03033, over 971829.55 frames.], batch size: 19, lr: 1.65e-04
+2022-05-07 22:42:15,283 INFO [train.py:715] (3/8) Epoch 13, batch 33950, loss[loss=0.1223, simple_loss=0.1941, pruned_loss=0.02523, over 4785.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03007, over 971576.96 frames.], batch size: 14, lr: 1.65e-04
+2022-05-07 22:42:56,289 INFO [train.py:715] (3/8) Epoch 13, batch 34000, loss[loss=0.133, simple_loss=0.2035, pruned_loss=0.03126, over 4974.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03051, over 971073.06 frames.], batch size: 39, lr: 1.65e-04
+2022-05-07 22:43:36,858 INFO [train.py:715] (3/8) Epoch 13, batch 34050, loss[loss=0.1317, simple_loss=0.2196, pruned_loss=0.02189, over 4823.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2103, pruned_loss=0.03052, over 971903.75 frames.], batch size: 26, lr: 1.65e-04
+2022-05-07 22:44:17,681 INFO [train.py:715] (3/8) Epoch 13, batch 34100, loss[loss=0.1051, simple_loss=0.1853, pruned_loss=0.01245, over 4828.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2096, pruned_loss=0.03038, over 972471.30 frames.], batch size: 26, lr: 1.65e-04
+2022-05-07 22:44:57,554 INFO [train.py:715] (3/8) Epoch 13, batch 34150, loss[loss=0.1294, simple_loss=0.2086, pruned_loss=0.02507, over 4869.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2097, pruned_loss=0.03052, over 972089.56 frames.], batch size: 20, lr: 1.65e-04
+2022-05-07 22:45:38,245 INFO [train.py:715] (3/8) Epoch 13, batch 34200, loss[loss=0.116, simple_loss=0.1993, pruned_loss=0.01633, over 4964.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2102, pruned_loss=0.03054, over 971955.06 frames.], batch size: 24, lr: 1.65e-04
+2022-05-07 22:46:18,602 INFO [train.py:715] (3/8) Epoch 13, batch 34250, loss[loss=0.1452, simple_loss=0.2125, pruned_loss=0.03899, over 4778.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2105, pruned_loss=0.03061, over 972354.31 frames.], batch size: 17, lr: 1.65e-04
+2022-05-07 22:46:59,528 INFO [train.py:715] (3/8) Epoch 13, batch 34300, loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03166, over 4890.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2106, pruned_loss=0.03056, over 972423.38 frames.], batch size: 22, lr: 1.65e-04
+2022-05-07 22:47:39,594 INFO [train.py:715] (3/8) Epoch 13, batch 34350, loss[loss=0.1764, simple_loss=0.2459, pruned_loss=0.05345, over 4975.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2104, pruned_loss=0.03091, over 972078.97 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:48:20,188 INFO [train.py:715] (3/8) Epoch 13, batch 34400, loss[loss=0.1357, simple_loss=0.2067, pruned_loss=0.03237, over 4885.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2102, pruned_loss=0.03079, over 972495.78 frames.], batch size: 22, lr: 1.65e-04
+2022-05-07 22:49:01,283 INFO [train.py:715] (3/8) Epoch 13, batch 34450, loss[loss=0.1325, simple_loss=0.1998, pruned_loss=0.0326, over 4820.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.0307, over 971478.00 frames.], batch size: 25, lr: 1.65e-04
+2022-05-07 22:49:41,688 INFO [train.py:715] (3/8) Epoch 13, batch 34500, loss[loss=0.1315, simple_loss=0.2164, pruned_loss=0.02327, over 4902.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03101, over 971909.98 frames.], batch size: 39, lr: 1.65e-04
+2022-05-07 22:50:21,495 INFO [train.py:715] (3/8) Epoch 13, batch 34550, loss[loss=0.1476, simple_loss=0.2195, pruned_loss=0.03787, over 4971.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03139, over 972950.93 frames.], batch size: 15, lr: 1.65e-04
+2022-05-07 22:51:01,503 INFO [train.py:715] (3/8) Epoch 13, batch 34600, loss[loss=0.1267, simple_loss=0.2037, pruned_loss=0.02482, over 4975.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03138, over 973666.39 frames.], batch size: 24, lr: 1.65e-04
+2022-05-07 22:51:40,885 INFO [train.py:715] (3/8) Epoch 13, batch 34650, loss[loss=0.136, simple_loss=0.2083, pruned_loss=0.03186, over 4915.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.03136, over 973041.05 frames.], batch size: 17, lr: 1.65e-04
+2022-05-07 22:52:20,404 INFO [train.py:715] (3/8) Epoch 13, batch 34700, loss[loss=0.1209, simple_loss=0.1933, pruned_loss=0.0243, over 4739.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03085, over 972951.83 frames.], batch size: 16, lr: 1.65e-04
+2022-05-07 22:52:59,364 INFO [train.py:715] (3/8) Epoch 13, batch 34750, loss[loss=0.1412, simple_loss=0.2039, pruned_loss=0.03922, over 4808.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03097, over 972101.04 frames.], batch size: 12, lr: 1.65e-04
+2022-05-07 22:53:36,107 INFO [train.py:715] (3/8) Epoch 13, batch 34800, loss[loss=0.1184, simple_loss=0.1957, pruned_loss=0.02054, over 4737.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03109, over 971006.52 frames.], batch size: 12, lr: 1.65e-04
+2022-05-07 22:54:25,047 INFO [train.py:715] (3/8) Epoch 14, batch 0, loss[loss=0.1614, simple_loss=0.2413, pruned_loss=0.04072, over 4825.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2413, pruned_loss=0.04072, over 4825.00 frames.], batch size: 15, lr: 1.59e-04
+2022-05-07 22:55:04,011 INFO [train.py:715] (3/8) Epoch 14, batch 50, loss[loss=0.1603, simple_loss=0.2284, pruned_loss=0.04609, over 4793.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2086, pruned_loss=0.0318, over 219565.56 frames.], batch size: 14, lr: 1.59e-04
+2022-05-07 22:55:42,422 INFO [train.py:715] (3/8) Epoch 14, batch 100, loss[loss=0.1212, simple_loss=0.2008, pruned_loss=0.02076, over 4976.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03024, over 386895.47 frames.], batch size: 14, lr: 1.59e-04
+2022-05-07 22:56:21,302 INFO [train.py:715] (3/8) Epoch 14, batch 150, loss[loss=0.124, simple_loss=0.1966, pruned_loss=0.02571, over 4975.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03032, over 517057.09 frames.], batch size: 27, lr: 1.59e-04
+2022-05-07 22:56:59,875 INFO [train.py:715] (3/8) Epoch 14, batch 200, loss[loss=0.104, simple_loss=0.1724, pruned_loss=0.01787, over 4985.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03001, over 618530.48 frames.], batch size: 14, lr: 1.59e-04
+2022-05-07 22:57:38,471 INFO [train.py:715] (3/8) Epoch 14, batch 250, loss[loss=0.1462, simple_loss=0.2269, pruned_loss=0.03271, over 4820.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03056, over 697515.47 frames.], batch size: 26, lr: 1.59e-04
+2022-05-07 22:58:17,250 INFO [train.py:715] (3/8) Epoch 14, batch 300, loss[loss=0.1698, simple_loss=0.2543, pruned_loss=0.04266, over 4956.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03031, over 758698.61 frames.], batch size: 21, lr: 1.59e-04
+2022-05-07 22:58:56,807 INFO [train.py:715] (3/8) Epoch 14, batch 350, loss[loss=0.1339, simple_loss=0.1993, pruned_loss=0.03425, over 4887.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03001, over 806813.15 frames.], batch size: 16, lr: 1.59e-04
+2022-05-07 22:59:35,350 INFO [train.py:715] (3/8) Epoch 14, batch 400, loss[loss=0.1214, simple_loss=0.1971, pruned_loss=0.02289, over 4660.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.0301, over 844490.79 frames.], batch size: 13, lr: 1.59e-04
+2022-05-07 23:00:14,781 INFO [train.py:715] (3/8) Epoch 14, batch 450, loss[loss=0.1128, simple_loss=0.183, pruned_loss=0.02134, over 4874.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03003, over 873931.19 frames.], batch size: 20, lr: 1.59e-04
+2022-05-07 23:00:54,068 INFO [train.py:715] (3/8) Epoch 14, batch 500, loss[loss=0.1267, simple_loss=0.2014, pruned_loss=0.02601, over 4748.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03055, over 895366.50 frames.], batch size: 16, lr: 1.59e-04
+2022-05-07 23:01:33,691 INFO [train.py:715] (3/8) Epoch 14, batch 550, loss[loss=0.1273, simple_loss=0.2047, pruned_loss=0.02492, over 4880.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03056, over 912120.96 frames.], batch size: 19, lr: 1.59e-04
+2022-05-07 23:02:12,467 INFO [train.py:715] (3/8) Epoch 14, batch 600, loss[loss=0.1311, simple_loss=0.2028, pruned_loss=0.02976, over 4945.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.0312, over 924978.66 frames.], batch size: 24, lr: 1.59e-04
+2022-05-07 23:02:51,130 INFO [train.py:715] (3/8) Epoch 14, batch 650, loss[loss=0.12, simple_loss=0.2, pruned_loss=0.02001, over 4960.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03107, over 935095.14 frames.], batch size: 35, lr: 1.59e-04
+2022-05-07 23:03:32,630 INFO [train.py:715] (3/8) Epoch 14, batch 700, loss[loss=0.129, simple_loss=0.2034, pruned_loss=0.02736, over 4894.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03101, over 943600.11 frames.], batch size: 19, lr: 1.59e-04
+2022-05-07 23:04:11,049 INFO [train.py:715] (3/8) Epoch 14, batch 750, loss[loss=0.1385, simple_loss=0.2305, pruned_loss=0.02326, over 4904.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03084, over 949863.90 frames.], batch size: 23, lr: 1.59e-04
+2022-05-07 23:04:51,157 INFO [train.py:715] (3/8) Epoch 14, batch 800, loss[loss=0.1251, simple_loss=0.1958, pruned_loss=0.02718, over 4832.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03055, over 955217.75 frames.], batch size: 26, lr: 1.59e-04
+2022-05-07 23:05:30,246 INFO [train.py:715] (3/8) Epoch 14, batch 850, loss[loss=0.1598, simple_loss=0.2377, pruned_loss=0.04094, over 4900.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03064, over 959683.30 frames.], batch size: 17, lr: 1.59e-04
+2022-05-07 23:06:09,706 INFO [train.py:715] (3/8) Epoch 14, batch 900, loss[loss=0.1392, simple_loss=0.2143, pruned_loss=0.03203, over 4836.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03043, over 962738.34 frames.], batch size: 15, lr: 1.59e-04
+2022-05-07 23:06:48,331 INFO [train.py:715] (3/8) Epoch 14, batch 950, loss[loss=0.1298, simple_loss=0.2064, pruned_loss=0.02656, over 4832.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03069, over 964310.23 frames.], batch size: 13, lr: 1.59e-04
+2022-05-07 23:07:27,882 INFO [train.py:715] (3/8) Epoch 14, batch 1000, loss[loss=0.1213, simple_loss=0.1973, pruned_loss=0.02268, over 4983.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03115, over 966195.32 frames.], batch size: 25, lr: 1.59e-04
+2022-05-07 23:08:07,946 INFO [train.py:715] (3/8) Epoch 14, batch 1050, loss[loss=0.1266, simple_loss=0.1927, pruned_loss=0.03022, over 4791.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03092, over 966920.48 frames.], batch size: 17, lr: 1.59e-04
+2022-05-07 23:08:47,254 INFO [train.py:715] (3/8) Epoch 14, batch 1100, loss[loss=0.1266, simple_loss=0.1964, pruned_loss=0.02843, over 4827.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.031, over 968159.32 frames.], batch size: 27, lr: 1.59e-04
+2022-05-07 23:09:26,968 INFO [train.py:715] (3/8) Epoch 14, batch 1150, loss[loss=0.191, simple_loss=0.2568, pruned_loss=0.06256, over 4871.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03105, over 969021.62 frames.], batch size: 16, lr: 1.59e-04
+2022-05-07 23:10:07,016 INFO [train.py:715] (3/8) Epoch 14, batch 1200, loss[loss=0.1191, simple_loss=0.1948, pruned_loss=0.02172, over 4841.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03063, over 968968.51 frames.], batch size: 25, lr: 1.59e-04
+2022-05-07 23:10:47,175 INFO [train.py:715] (3/8) Epoch 14, batch 1250, loss[loss=0.1531, simple_loss=0.2362, pruned_loss=0.03498, over 4944.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03046, over 969174.19 frames.], batch size: 29, lr: 1.59e-04
+2022-05-07 23:11:26,193 INFO [train.py:715] (3/8) Epoch 14, batch 1300, loss[loss=0.1341, simple_loss=0.2201, pruned_loss=0.02402, over 4984.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.0306, over 970530.91 frames.], batch size: 28, lr: 1.59e-04
+2022-05-07 23:12:05,715 INFO [train.py:715] (3/8) Epoch 14, batch 1350, loss[loss=0.1268, simple_loss=0.2015, pruned_loss=0.02608, over 4774.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03061, over 970363.27 frames.], batch size: 14, lr: 1.59e-04
+2022-05-07 23:12:45,084 INFO [train.py:715] (3/8) Epoch 14, batch 1400, loss[loss=0.1158, simple_loss=0.1871, pruned_loss=0.02227, over 4964.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03124, over 971396.44 frames.], batch size: 35, lr: 1.59e-04
+2022-05-07 23:13:24,657 INFO [train.py:715] (3/8) Epoch 14, batch 1450, loss[loss=0.1592, simple_loss=0.2184, pruned_loss=0.05004, over 4867.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03163, over 971093.90 frames.], batch size: 32, lr: 1.59e-04
+2022-05-07 23:14:04,620 INFO [train.py:715] (3/8) Epoch 14, batch 1500, loss[loss=0.1042, simple_loss=0.1769, pruned_loss=0.01578, over 4930.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03123, over 971735.11 frames.], batch size: 21, lr: 1.59e-04
+2022-05-07 23:14:44,300 INFO [train.py:715] (3/8) Epoch 14, batch 1550, loss[loss=0.1288, simple_loss=0.2047, pruned_loss=0.02646, over 4836.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03135, over 971803.77 frames.], batch size: 15, lr: 1.59e-04
+2022-05-07 23:15:24,190 INFO [train.py:715] (3/8) Epoch 14, batch 1600, loss[loss=0.1504, simple_loss=0.2285, pruned_loss=0.03614, over 4752.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03077, over 972731.02 frames.], batch size: 16, lr: 1.59e-04
+2022-05-07 23:16:03,431 INFO [train.py:715] (3/8) Epoch 14, batch 1650, loss[loss=0.1498, simple_loss=0.2286, pruned_loss=0.03552, over 4973.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.031, over 973199.49 frames.], batch size: 15, lr: 1.59e-04
+2022-05-07 23:16:43,079 INFO [train.py:715] (3/8) Epoch 14, batch 1700, loss[loss=0.122, simple_loss=0.1866, pruned_loss=0.02865, over 4850.00 frames.], tot_loss[loss=0.1358, simple_loss=0.209, pruned_loss=0.0313, over 972242.34 frames.], batch size: 30, lr: 1.59e-04
+2022-05-07 23:17:22,560 INFO [train.py:715] (3/8) Epoch 14, batch 1750, loss[loss=0.1233, simple_loss=0.1917, pruned_loss=0.02747, over 4759.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03127, over 972276.22 frames.], batch size: 19, lr: 1.59e-04
+2022-05-07 23:18:02,286 INFO [train.py:715] (3/8) Epoch 14, batch 1800, loss[loss=0.121, simple_loss=0.191, pruned_loss=0.02546, over 4822.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03089, over 972491.45 frames.], batch size: 25, lr: 1.59e-04
+2022-05-07 23:18:40,627 INFO [train.py:715] (3/8) Epoch 14, batch 1850, loss[loss=0.1257, simple_loss=0.1971, pruned_loss=0.0271, over 4791.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03083, over 972068.13 frames.], batch size: 12, lr: 1.59e-04
+2022-05-07 23:19:19,862 INFO [train.py:715] (3/8) Epoch 14, batch 1900, loss[loss=0.1314, simple_loss=0.2042, pruned_loss=0.0293, over 4856.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03071, over 971838.36 frames.], batch size: 20, lr: 1.59e-04
+2022-05-07 23:19:59,664 INFO [train.py:715] (3/8) Epoch 14, batch 1950, loss[loss=0.1317, simple_loss=0.2115, pruned_loss=0.02596, over 4829.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03063, over 971522.60 frames.], batch size: 26, lr: 1.59e-04
+2022-05-07 23:20:39,813 INFO [train.py:715] (3/8) Epoch 14, batch 2000, loss[loss=0.1347, simple_loss=0.2161, pruned_loss=0.02666, over 4684.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03086, over 971940.95 frames.], batch size: 15, lr: 1.59e-04
+2022-05-07 23:21:19,095 INFO [train.py:715] (3/8) Epoch 14, batch 2050, loss[loss=0.1178, simple_loss=0.1907, pruned_loss=0.02247, over 4789.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03058, over 971800.09 frames.], batch size: 14, lr: 1.59e-04
+2022-05-07 23:21:58,550 INFO [train.py:715] (3/8) Epoch 14, batch 2100, loss[loss=0.1227, simple_loss=0.1918, pruned_loss=0.02684, over 4824.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03064, over 970925.71 frames.], batch size: 25, lr: 1.59e-04
+2022-05-07 23:22:38,248 INFO [train.py:715] (3/8) Epoch 14, batch 2150, loss[loss=0.14, simple_loss=0.2111, pruned_loss=0.03446, over 4930.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.0308, over 971409.30 frames.], batch size: 18, lr: 1.59e-04
+2022-05-07 23:23:16,938 INFO [train.py:715] (3/8) Epoch 14, batch 2200, loss[loss=0.1332, simple_loss=0.214, pruned_loss=0.02621, over 4827.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03105, over 971061.76 frames.], batch size: 25, lr: 1.59e-04
+2022-05-07 23:23:55,889 INFO [train.py:715] (3/8) Epoch 14, batch 2250, loss[loss=0.1614, simple_loss=0.2309, pruned_loss=0.04591, over 4825.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03107, over 971917.44 frames.], batch size: 15, lr: 1.59e-04
+2022-05-07 23:24:34,964 INFO [train.py:715] (3/8) Epoch 14, batch 2300, loss[loss=0.1422, simple_loss=0.2172, pruned_loss=0.03362, over 4948.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03082, over 972006.23 frames.], batch size: 21, lr: 1.59e-04
+2022-05-07 23:25:14,131 INFO [train.py:715] (3/8) Epoch 14, batch 2350, loss[loss=0.1192, simple_loss=0.1998, pruned_loss=0.01933, over 4905.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03081, over 972380.60 frames.], batch size: 18, lr: 1.59e-04
+2022-05-07 23:25:53,246 INFO [train.py:715] (3/8) Epoch 14, batch 2400, loss[loss=0.1334, simple_loss=0.2132, pruned_loss=0.02681, over 4883.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.0309, over 972397.72 frames.], batch size: 38, lr: 1.59e-04
+2022-05-07 23:26:32,287 INFO [train.py:715] (3/8) Epoch 14, batch 2450, loss[loss=0.1441, simple_loss=0.205, pruned_loss=0.0416, over 4823.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03122, over 972848.71 frames.], batch size: 15, lr: 1.59e-04
+2022-05-07 23:27:11,607 INFO [train.py:715] (3/8) Epoch 14, batch 2500, loss[loss=0.1276, simple_loss=0.2003, pruned_loss=0.02752, over 4909.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2086, pruned_loss=0.03108, over 972871.44 frames.], batch size: 17, lr: 1.59e-04
+2022-05-07 23:27:50,109 INFO [train.py:715] (3/8) Epoch 14, batch 2550, loss[loss=0.142, simple_loss=0.2121, pruned_loss=0.03595, over 4816.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03074, over 973231.53 frames.], batch size: 26, lr: 1.59e-04
+2022-05-07 23:28:29,686 INFO [train.py:715] (3/8) Epoch 14, batch 2600, loss[loss=0.144, simple_loss=0.2137, pruned_loss=0.03712, over 4895.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03101, over 973325.02 frames.], batch size: 18, lr: 1.59e-04
+2022-05-07 23:29:09,143 INFO [train.py:715] (3/8) Epoch 14, batch 2650, loss[loss=0.1297, simple_loss=0.2026, pruned_loss=0.02841, over 4916.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2089, pruned_loss=0.03121, over 974118.92 frames.], batch size: 39, lr: 1.59e-04
+2022-05-07 23:29:48,498 INFO [train.py:715] (3/8) Epoch 14, batch 2700, loss[loss=0.114, simple_loss=0.1866, pruned_loss=0.02066, over 4801.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03084, over 973861.08 frames.], batch size: 21, lr: 1.59e-04
+2022-05-07 23:30:27,053 INFO [train.py:715] (3/8) Epoch 14, batch 2750, loss[loss=0.1228, simple_loss=0.1963, pruned_loss=0.02466, over 4986.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03024, over 973656.76 frames.], batch size: 28, lr: 1.59e-04
+2022-05-07 23:31:06,234 INFO [train.py:715] (3/8) Epoch 14, batch 2800, loss[loss=0.1413, simple_loss=0.201, pruned_loss=0.04078, over 4813.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03031, over 973795.82 frames.], batch size: 13, lr: 1.59e-04
+2022-05-07 23:31:45,882 INFO [train.py:715] (3/8) Epoch 14, batch 2850, loss[loss=0.1192, simple_loss=0.1937, pruned_loss=0.02237, over 4852.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03042, over 973553.53 frames.], batch size: 20, lr: 1.59e-04
+2022-05-07 23:32:24,327 INFO [train.py:715] (3/8) Epoch 14, batch 2900, loss[loss=0.1109, simple_loss=0.1901, pruned_loss=0.0158, over 4816.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03013, over 973472.32 frames.], batch size: 26, lr: 1.59e-04
+2022-05-07 23:33:06,133 INFO [train.py:715] (3/8) Epoch 14, batch 2950, loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03078, over 4863.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02975, over 972442.58 frames.], batch size: 20, lr: 1.59e-04
+2022-05-07 23:33:45,667 INFO [train.py:715] (3/8) Epoch 14, batch 3000, loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03197, over 4942.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03017, over 972494.49 frames.], batch size: 29, lr: 1.59e-04
+2022-05-07 23:33:45,668 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-07 23:33:55,239 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1891, pruned_loss=0.01067, over 914524.00 frames.
+2022-05-07 23:34:34,251 INFO [train.py:715] (3/8) Epoch 14, batch 3050, loss[loss=0.1139, simple_loss=0.1877, pruned_loss=0.02007, over 4817.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03024, over 970960.82 frames.], batch size: 21, lr: 1.59e-04
+2022-05-07 23:35:14,218 INFO [train.py:715] (3/8) Epoch 14, batch 3100, loss[loss=0.1434, simple_loss=0.2003, pruned_loss=0.04327, over 4784.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03085, over 971303.96 frames.], batch size: 17, lr: 1.59e-04
+2022-05-07 23:35:53,769 INFO [train.py:715] (3/8) Epoch 14, batch 3150, loss[loss=0.1399, simple_loss=0.2114, pruned_loss=0.03414, over 4710.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2106, pruned_loss=0.03112, over 972206.23 frames.], batch size: 15, lr: 1.59e-04
+2022-05-07 23:36:33,460 INFO [train.py:715] (3/8) Epoch 14, batch 3200, loss[loss=0.1429, simple_loss=0.2177, pruned_loss=0.03405, over 4917.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03111, over 972136.69 frames.], batch size: 17, lr: 1.59e-04
+2022-05-07 23:37:14,484 INFO [train.py:715] (3/8) Epoch 14, batch 3250, loss[loss=0.1249, simple_loss=0.198, pruned_loss=0.0259, over 4689.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03167, over 972457.06 frames.], batch size: 15, lr: 1.59e-04
+2022-05-07 23:37:54,310 INFO [train.py:715] (3/8) Epoch 14, batch 3300, loss[loss=0.1421, simple_loss=0.2123, pruned_loss=0.03598, over 4837.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.0318, over 971983.41 frames.], batch size: 13, lr: 1.59e-04
+2022-05-07 23:38:34,437 INFO [train.py:715] (3/8) Epoch 14, batch 3350, loss[loss=0.1431, simple_loss=0.2159, pruned_loss=0.03517, over 4990.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.0316, over 973154.62 frames.], batch size: 16, lr: 1.59e-04
+2022-05-07 23:39:15,379 INFO [train.py:715] (3/8) Epoch 14, batch 3400, loss[loss=0.1475, simple_loss=0.22, pruned_loss=0.03753, over 4870.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2088, pruned_loss=0.03103, over 973399.52 frames.], batch size: 32, lr: 1.59e-04
+2022-05-07 23:39:56,033 INFO [train.py:715] (3/8) Epoch 14, batch 3450, loss[loss=0.1216, simple_loss=0.1988, pruned_loss=0.02221, over 4871.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03121, over 973044.40 frames.], batch size: 16, lr: 1.59e-04
+2022-05-07 23:40:35,907 INFO [train.py:715] (3/8) Epoch 14, batch 3500, loss[loss=0.1133, simple_loss=0.1814, pruned_loss=0.02259, over 4830.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03102, over 973092.02 frames.], batch size: 13, lr: 1.59e-04
+2022-05-07 23:41:15,983 INFO [train.py:715] (3/8) Epoch 14, batch 3550, loss[loss=0.1317, simple_loss=0.2106, pruned_loss=0.02644, over 4949.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.0303, over 973239.30 frames.], batch size: 21, lr: 1.59e-04
+2022-05-07 23:41:56,122 INFO [train.py:715] (3/8) Epoch 14, batch 3600, loss[loss=0.1265, simple_loss=0.1989, pruned_loss=0.02708, over 4959.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03029, over 972786.94 frames.], batch size: 14, lr: 1.59e-04
+2022-05-07 23:42:36,127 INFO [train.py:715] (3/8) Epoch 14, batch 3650, loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03182, over 4947.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03064, over 972521.18 frames.], batch size: 21, lr: 1.59e-04
+2022-05-07 23:43:16,032 INFO [train.py:715] (3/8) Epoch 14, batch 3700, loss[loss=0.1203, simple_loss=0.1939, pruned_loss=0.02334, over 4976.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03104, over 972743.85 frames.], batch size: 29, lr: 1.59e-04
+2022-05-07 23:43:56,765 INFO [train.py:715] (3/8) Epoch 14, batch 3750, loss[loss=0.1594, simple_loss=0.2284, pruned_loss=0.04522, over 4846.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03087, over 973509.50 frames.], batch size: 32, lr: 1.59e-04
+2022-05-07 23:44:36,926 INFO [train.py:715] (3/8) Epoch 14, batch 3800, loss[loss=0.1417, simple_loss=0.2261, pruned_loss=0.02861, over 4743.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03108, over 972080.10 frames.], batch size: 16, lr: 1.59e-04
+2022-05-07 23:45:16,168 INFO [train.py:715] (3/8) Epoch 14, batch 3850, loss[loss=0.1574, simple_loss=0.2196, pruned_loss=0.04757, over 4872.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03118, over 973268.24 frames.], batch size: 30, lr: 1.59e-04
+2022-05-07 23:45:56,642 INFO [train.py:715] (3/8) Epoch 14, batch 3900, loss[loss=0.1205, simple_loss=0.195, pruned_loss=0.02301, over 4879.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2086, pruned_loss=0.03117, over 972182.00 frames.], batch size: 13, lr: 1.59e-04
+2022-05-07 23:46:37,883 INFO [train.py:715] (3/8) Epoch 14, batch 3950, loss[loss=0.1266, simple_loss=0.1871, pruned_loss=0.03305, over 4789.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2079, pruned_loss=0.03061, over 972852.59 frames.], batch size: 14, lr: 1.59e-04
+2022-05-07 23:47:18,824 INFO [train.py:715] (3/8) Epoch 14, batch 4000, loss[loss=0.1158, simple_loss=0.1891, pruned_loss=0.02125, over 4790.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.03023, over 972514.22 frames.], batch size: 24, lr: 1.59e-04
+2022-05-07 23:47:59,307 INFO [train.py:715] (3/8) Epoch 14, batch 4050, loss[loss=0.1398, simple_loss=0.2149, pruned_loss=0.03235, over 4877.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.0305, over 973304.85 frames.], batch size: 16, lr: 1.59e-04
+2022-05-07 23:48:40,126 INFO [train.py:715] (3/8) Epoch 14, batch 4100, loss[loss=0.1492, simple_loss=0.2288, pruned_loss=0.03478, over 4842.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03091, over 973335.29 frames.], batch size: 32, lr: 1.59e-04
+2022-05-07 23:49:21,557 INFO [train.py:715] (3/8) Epoch 14, batch 4150, loss[loss=0.1698, simple_loss=0.241, pruned_loss=0.04926, over 4921.00 frames.], tot_loss[loss=0.1358, simple_loss=0.209, pruned_loss=0.03128, over 972560.29 frames.], batch size: 39, lr: 1.59e-04
+2022-05-07 23:50:02,217 INFO [train.py:715] (3/8) Epoch 14, batch 4200, loss[loss=0.1236, simple_loss=0.1997, pruned_loss=0.02375, over 4831.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2088, pruned_loss=0.031, over 972198.83 frames.], batch size: 30, lr: 1.59e-04
+2022-05-07 23:50:43,286 INFO [train.py:715] (3/8) Epoch 14, batch 4250, loss[loss=0.138, simple_loss=0.2125, pruned_loss=0.03175, over 4785.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03025, over 971700.37 frames.], batch size: 18, lr: 1.59e-04
+2022-05-07 23:51:25,172 INFO [train.py:715] (3/8) Epoch 14, batch 4300, loss[loss=0.1067, simple_loss=0.1789, pruned_loss=0.01724, over 4870.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02997, over 972051.01 frames.], batch size: 16, lr: 1.59e-04
+2022-05-07 23:52:06,419 INFO [train.py:715] (3/8) Epoch 14, batch 4350, loss[loss=0.1378, simple_loss=0.2158, pruned_loss=0.02986, over 4954.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03045, over 972900.61 frames.], batch size: 21, lr: 1.59e-04
+2022-05-07 23:52:46,952 INFO [train.py:715] (3/8) Epoch 14, batch 4400, loss[loss=0.1321, simple_loss=0.2013, pruned_loss=0.03151, over 4936.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03081, over 973217.69 frames.], batch size: 29, lr: 1.59e-04
+2022-05-07 23:53:27,640 INFO [train.py:715] (3/8) Epoch 14, batch 4450, loss[loss=0.1176, simple_loss=0.1886, pruned_loss=0.0233, over 4855.00 frames.], tot_loss[loss=0.136, simple_loss=0.21, pruned_loss=0.03094, over 973059.62 frames.], batch size: 30, lr: 1.59e-04
+2022-05-07 23:54:08,650 INFO [train.py:715] (3/8) Epoch 14, batch 4500, loss[loss=0.1198, simple_loss=0.1848, pruned_loss=0.02736, over 4829.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03126, over 973329.53 frames.], batch size: 30, lr: 1.59e-04
+2022-05-07 23:54:48,679 INFO [train.py:715] (3/8) Epoch 14, batch 4550, loss[loss=0.09616, simple_loss=0.1675, pruned_loss=0.01239, over 4788.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03098, over 973245.49 frames.], batch size: 12, lr: 1.59e-04
+2022-05-07 23:55:27,631 INFO [train.py:715] (3/8) Epoch 14, batch 4600, loss[loss=0.1269, simple_loss=0.204, pruned_loss=0.0249, over 4903.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03036, over 972995.60 frames.], batch size: 18, lr: 1.59e-04
+2022-05-07 23:56:08,467 INFO [train.py:715] (3/8) Epoch 14, batch 4650, loss[loss=0.1248, simple_loss=0.2064, pruned_loss=0.02156, over 4860.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03036, over 972111.92 frames.], batch size: 20, lr: 1.59e-04
+2022-05-07 23:56:48,195 INFO [train.py:715] (3/8) Epoch 14, batch 4700, loss[loss=0.1351, simple_loss=0.2144, pruned_loss=0.02794, over 4812.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03036, over 971456.11 frames.], batch size: 21, lr: 1.59e-04
+2022-05-07 23:57:26,880 INFO [train.py:715] (3/8) Epoch 14, batch 4750, loss[loss=0.1322, simple_loss=0.2088, pruned_loss=0.02783, over 4749.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02994, over 970281.25 frames.], batch size: 14, lr: 1.58e-04
+2022-05-07 23:58:06,244 INFO [train.py:715] (3/8) Epoch 14, batch 4800, loss[loss=0.1297, simple_loss=0.2059, pruned_loss=0.02672, over 4976.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.0298, over 971204.72 frames.], batch size: 33, lr: 1.58e-04
+2022-05-07 23:58:46,077 INFO [train.py:715] (3/8) Epoch 14, batch 4850, loss[loss=0.1405, simple_loss=0.2114, pruned_loss=0.03483, over 4858.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02976, over 971109.88 frames.], batch size: 20, lr: 1.58e-04
+2022-05-07 23:59:25,003 INFO [train.py:715] (3/8) Epoch 14, batch 4900, loss[loss=0.1398, simple_loss=0.2048, pruned_loss=0.0374, over 4901.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03022, over 971858.17 frames.], batch size: 18, lr: 1.58e-04
+2022-05-08 00:00:04,156 INFO [train.py:715] (3/8) Epoch 14, batch 4950, loss[loss=0.123, simple_loss=0.1944, pruned_loss=0.02583, over 4840.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03075, over 972741.18 frames.], batch size: 32, lr: 1.58e-04
+2022-05-08 00:00:44,234 INFO [train.py:715] (3/8) Epoch 14, batch 5000, loss[loss=0.1137, simple_loss=0.1907, pruned_loss=0.01837, over 4920.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03114, over 972984.21 frames.], batch size: 17, lr: 1.58e-04
+2022-05-08 00:01:23,509 INFO [train.py:715] (3/8) Epoch 14, batch 5050, loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03156, over 4925.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03093, over 973914.37 frames.], batch size: 29, lr: 1.58e-04
+2022-05-08 00:02:02,200 INFO [train.py:715] (3/8) Epoch 14, batch 5100, loss[loss=0.131, simple_loss=0.2028, pruned_loss=0.02955, over 4991.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03088, over 973596.86 frames.], batch size: 20, lr: 1.58e-04
+2022-05-08 00:02:41,811 INFO [train.py:715] (3/8) Epoch 14, batch 5150, loss[loss=0.1448, simple_loss=0.2203, pruned_loss=0.03469, over 4836.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03071, over 973525.00 frames.], batch size: 27, lr: 1.58e-04
+2022-05-08 00:03:21,426 INFO [train.py:715] (3/8) Epoch 14, batch 5200, loss[loss=0.1315, simple_loss=0.209, pruned_loss=0.02702, over 4849.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03053, over 973747.60 frames.], batch size: 20, lr: 1.58e-04
+2022-05-08 00:03:59,952 INFO [train.py:715] (3/8) Epoch 14, batch 5250, loss[loss=0.1413, simple_loss=0.2132, pruned_loss=0.03471, over 4972.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03073, over 974178.84 frames.], batch size: 14, lr: 1.58e-04
+2022-05-08 00:04:38,460 INFO [train.py:715] (3/8) Epoch 14, batch 5300, loss[loss=0.1249, simple_loss=0.2047, pruned_loss=0.02259, over 4772.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03056, over 973457.30 frames.], batch size: 18, lr: 1.58e-04
+2022-05-08 00:05:17,646 INFO [train.py:715] (3/8) Epoch 14, batch 5350, loss[loss=0.1213, simple_loss=0.2026, pruned_loss=0.02005, over 4847.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.03094, over 973726.12 frames.], batch size: 26, lr: 1.58e-04
+2022-05-08 00:05:56,199 INFO [train.py:715] (3/8) Epoch 14, batch 5400, loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02832, over 4812.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03115, over 973728.56 frames.], batch size: 26, lr: 1.58e-04
+2022-05-08 00:06:34,702 INFO [train.py:715] (3/8) Epoch 14, batch 5450, loss[loss=0.1221, simple_loss=0.1975, pruned_loss=0.02332, over 4950.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03089, over 974020.79 frames.], batch size: 24, lr: 1.58e-04
+2022-05-08 00:07:13,537 INFO [train.py:715] (3/8) Epoch 14, batch 5500, loss[loss=0.124, simple_loss=0.188, pruned_loss=0.03, over 4799.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.0306, over 974671.56 frames.], batch size: 12, lr: 1.58e-04
+2022-05-08 00:07:53,215 INFO [train.py:715] (3/8) Epoch 14, batch 5550, loss[loss=0.1343, simple_loss=0.2133, pruned_loss=0.02764, over 4820.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03068, over 973574.54 frames.], batch size: 25, lr: 1.58e-04
+2022-05-08 00:08:31,528 INFO [train.py:715] (3/8) Epoch 14, batch 5600, loss[loss=0.1434, simple_loss=0.2227, pruned_loss=0.03202, over 4826.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03083, over 973538.23 frames.], batch size: 25, lr: 1.58e-04
+2022-05-08 00:09:10,034 INFO [train.py:715] (3/8) Epoch 14, batch 5650, loss[loss=0.134, simple_loss=0.2024, pruned_loss=0.03279, over 4834.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03115, over 972931.41 frames.], batch size: 13, lr: 1.58e-04
+2022-05-08 00:09:49,145 INFO [train.py:715] (3/8) Epoch 14, batch 5700, loss[loss=0.1313, simple_loss=0.2013, pruned_loss=0.03065, over 4905.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03098, over 973165.50 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 00:10:27,420 INFO [train.py:715] (3/8) Epoch 14, batch 5750, loss[loss=0.1429, simple_loss=0.2038, pruned_loss=0.04097, over 4645.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03109, over 972977.20 frames.], batch size: 13, lr: 1.58e-04
+2022-05-08 00:11:05,798 INFO [train.py:715] (3/8) Epoch 14, batch 5800, loss[loss=0.1514, simple_loss=0.2252, pruned_loss=0.03879, over 4754.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.0311, over 972667.09 frames.], batch size: 16, lr: 1.58e-04
+2022-05-08 00:11:44,414 INFO [train.py:715] (3/8) Epoch 14, batch 5850, loss[loss=0.1223, simple_loss=0.2047, pruned_loss=0.01992, over 4956.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.0306, over 972891.21 frames.], batch size: 14, lr: 1.58e-04
+2022-05-08 00:12:23,183 INFO [train.py:715] (3/8) Epoch 14, batch 5900, loss[loss=0.1296, simple_loss=0.1986, pruned_loss=0.03026, over 4775.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.0304, over 972301.74 frames.], batch size: 12, lr: 1.58e-04
+2022-05-08 00:13:02,942 INFO [train.py:715] (3/8) Epoch 14, batch 5950, loss[loss=0.1431, simple_loss=0.2124, pruned_loss=0.03691, over 4732.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.031, over 971960.39 frames.], batch size: 16, lr: 1.58e-04
+2022-05-08 00:13:42,635 INFO [train.py:715] (3/8) Epoch 14, batch 6000, loss[loss=0.1352, simple_loss=0.2046, pruned_loss=0.03289, over 4959.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03105, over 972043.86 frames.], batch size: 21, lr: 1.58e-04
+2022-05-08 00:13:42,636 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 00:13:52,503 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.105, simple_loss=0.1888, pruned_loss=0.01057, over 914524.00 frames.
+2022-05-08 00:14:31,596 INFO [train.py:715] (3/8) Epoch 14, batch 6050, loss[loss=0.112, simple_loss=0.1858, pruned_loss=0.01912, over 4927.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03091, over 971528.52 frames.], batch size: 23, lr: 1.58e-04
+2022-05-08 00:15:10,774 INFO [train.py:715] (3/8) Epoch 14, batch 6100, loss[loss=0.1283, simple_loss=0.1919, pruned_loss=0.03235, over 4870.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03101, over 972366.00 frames.], batch size: 30, lr: 1.58e-04
+2022-05-08 00:15:50,808 INFO [train.py:715] (3/8) Epoch 14, batch 6150, loss[loss=0.1261, simple_loss=0.2007, pruned_loss=0.02576, over 4844.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03106, over 972441.52 frames.], batch size: 30, lr: 1.58e-04
+2022-05-08 00:16:30,404 INFO [train.py:715] (3/8) Epoch 14, batch 6200, loss[loss=0.1254, simple_loss=0.1881, pruned_loss=0.03141, over 4772.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03128, over 972541.95 frames.], batch size: 12, lr: 1.58e-04
+2022-05-08 00:17:10,267 INFO [train.py:715] (3/8) Epoch 14, batch 6250, loss[loss=0.1519, simple_loss=0.2226, pruned_loss=0.04058, over 4684.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03069, over 972188.57 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 00:17:49,640 INFO [train.py:715] (3/8) Epoch 14, batch 6300, loss[loss=0.1526, simple_loss=0.2237, pruned_loss=0.04079, over 4830.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03093, over 972457.94 frames.], batch size: 30, lr: 1.58e-04
+2022-05-08 00:18:29,669 INFO [train.py:715] (3/8) Epoch 14, batch 6350, loss[loss=0.1632, simple_loss=0.234, pruned_loss=0.04625, over 4771.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03137, over 972462.53 frames.], batch size: 17, lr: 1.58e-04
+2022-05-08 00:19:09,445 INFO [train.py:715] (3/8) Epoch 14, batch 6400, loss[loss=0.1169, simple_loss=0.1989, pruned_loss=0.01742, over 4870.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03156, over 972152.09 frames.], batch size: 20, lr: 1.58e-04
+2022-05-08 00:19:49,550 INFO [train.py:715] (3/8) Epoch 14, batch 6450, loss[loss=0.14, simple_loss=0.2047, pruned_loss=0.03761, over 4826.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.0314, over 972287.42 frames.], batch size: 13, lr: 1.58e-04
+2022-05-08 00:20:29,523 INFO [train.py:715] (3/8) Epoch 14, batch 6500, loss[loss=0.1229, simple_loss=0.2009, pruned_loss=0.02241, over 4903.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03118, over 971981.41 frames.], batch size: 23, lr: 1.58e-04
+2022-05-08 00:21:09,179 INFO [train.py:715] (3/8) Epoch 14, batch 6550, loss[loss=0.1318, simple_loss=0.2109, pruned_loss=0.02633, over 4768.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03089, over 971896.56 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 00:21:49,070 INFO [train.py:715] (3/8) Epoch 14, batch 6600, loss[loss=0.1214, simple_loss=0.1981, pruned_loss=0.02233, over 4946.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03086, over 973036.80 frames.], batch size: 21, lr: 1.58e-04
+2022-05-08 00:22:29,234 INFO [train.py:715] (3/8) Epoch 14, batch 6650, loss[loss=0.1543, simple_loss=0.2198, pruned_loss=0.04438, over 4878.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03112, over 973531.02 frames.], batch size: 32, lr: 1.58e-04
+2022-05-08 00:23:08,971 INFO [train.py:715] (3/8) Epoch 14, batch 6700, loss[loss=0.1304, simple_loss=0.2067, pruned_loss=0.02702, over 4888.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.03106, over 973836.54 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 00:23:48,852 INFO [train.py:715] (3/8) Epoch 14, batch 6750, loss[loss=0.1257, simple_loss=0.1972, pruned_loss=0.02703, over 4813.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2103, pruned_loss=0.03093, over 973975.30 frames.], batch size: 26, lr: 1.58e-04
+2022-05-08 00:24:28,844 INFO [train.py:715] (3/8) Epoch 14, batch 6800, loss[loss=0.1333, simple_loss=0.2144, pruned_loss=0.0261, over 4644.00 frames.], tot_loss[loss=0.136, simple_loss=0.2104, pruned_loss=0.0308, over 973669.64 frames.], batch size: 13, lr: 1.58e-04
+2022-05-08 00:25:08,851 INFO [train.py:715] (3/8) Epoch 14, batch 6850, loss[loss=0.1499, simple_loss=0.2252, pruned_loss=0.03729, over 4878.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2107, pruned_loss=0.03112, over 973805.46 frames.], batch size: 22, lr: 1.58e-04
+2022-05-08 00:25:48,273 INFO [train.py:715] (3/8) Epoch 14, batch 6900, loss[loss=0.1593, simple_loss=0.2241, pruned_loss=0.04728, over 4828.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03096, over 973306.02 frames.], batch size: 30, lr: 1.58e-04
+2022-05-08 00:26:28,467 INFO [train.py:715] (3/8) Epoch 14, batch 6950, loss[loss=0.129, simple_loss=0.1975, pruned_loss=0.03029, over 4968.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03055, over 973939.95 frames.], batch size: 33, lr: 1.58e-04
+2022-05-08 00:27:08,571 INFO [train.py:715] (3/8) Epoch 14, batch 7000, loss[loss=0.1563, simple_loss=0.2353, pruned_loss=0.03866, over 4899.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.0307, over 973431.18 frames.], batch size: 18, lr: 1.58e-04
+2022-05-08 00:27:48,560 INFO [train.py:715] (3/8) Epoch 14, batch 7050, loss[loss=0.1332, simple_loss=0.204, pruned_loss=0.03118, over 4851.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03071, over 972241.58 frames.], batch size: 30, lr: 1.58e-04
+2022-05-08 00:28:27,885 INFO [train.py:715] (3/8) Epoch 14, batch 7100, loss[loss=0.166, simple_loss=0.228, pruned_loss=0.05197, over 4730.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03101, over 971957.66 frames.], batch size: 16, lr: 1.58e-04
+2022-05-08 00:29:07,967 INFO [train.py:715] (3/8) Epoch 14, batch 7150, loss[loss=0.1171, simple_loss=0.1865, pruned_loss=0.02383, over 4923.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03124, over 972470.98 frames.], batch size: 18, lr: 1.58e-04
+2022-05-08 00:29:48,193 INFO [train.py:715] (3/8) Epoch 14, batch 7200, loss[loss=0.13, simple_loss=0.2091, pruned_loss=0.02543, over 4766.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03084, over 973026.86 frames.], batch size: 14, lr: 1.58e-04
+2022-05-08 00:30:28,018 INFO [train.py:715] (3/8) Epoch 14, batch 7250, loss[loss=0.1311, simple_loss=0.2043, pruned_loss=0.02895, over 4787.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03093, over 973259.38 frames.], batch size: 14, lr: 1.58e-04
+2022-05-08 00:31:08,165 INFO [train.py:715] (3/8) Epoch 14, batch 7300, loss[loss=0.1466, simple_loss=0.2169, pruned_loss=0.03816, over 4809.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03082, over 972400.07 frames.], batch size: 24, lr: 1.58e-04
+2022-05-08 00:31:48,270 INFO [train.py:715] (3/8) Epoch 14, batch 7350, loss[loss=0.1421, simple_loss=0.2128, pruned_loss=0.03567, over 4866.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03082, over 972453.37 frames.], batch size: 13, lr: 1.58e-04
+2022-05-08 00:32:28,614 INFO [train.py:715] (3/8) Epoch 14, batch 7400, loss[loss=0.1397, simple_loss=0.2135, pruned_loss=0.03294, over 4982.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.0309, over 973437.46 frames.], batch size: 14, lr: 1.58e-04
+2022-05-08 00:33:08,067 INFO [train.py:715] (3/8) Epoch 14, batch 7450, loss[loss=0.1432, simple_loss=0.2113, pruned_loss=0.03753, over 4834.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03082, over 972141.81 frames.], batch size: 30, lr: 1.58e-04
+2022-05-08 00:33:47,757 INFO [train.py:715] (3/8) Epoch 14, batch 7500, loss[loss=0.1218, simple_loss=0.1994, pruned_loss=0.02211, over 4960.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03086, over 973251.33 frames.], batch size: 21, lr: 1.58e-04
+2022-05-08 00:34:27,409 INFO [train.py:715] (3/8) Epoch 14, batch 7550, loss[loss=0.1502, simple_loss=0.2223, pruned_loss=0.03904, over 4829.00 frames.], tot_loss[loss=0.1357, simple_loss=0.209, pruned_loss=0.03116, over 973409.92 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 00:35:06,410 INFO [train.py:715] (3/8) Epoch 14, batch 7600, loss[loss=0.1176, simple_loss=0.1954, pruned_loss=0.01987, over 4815.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03145, over 973432.24 frames.], batch size: 21, lr: 1.58e-04
+2022-05-08 00:35:46,364 INFO [train.py:715] (3/8) Epoch 14, batch 7650, loss[loss=0.1293, simple_loss=0.2122, pruned_loss=0.02318, over 4782.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03158, over 972318.66 frames.], batch size: 17, lr: 1.58e-04
+2022-05-08 00:36:25,267 INFO [train.py:715] (3/8) Epoch 14, batch 7700, loss[loss=0.1205, simple_loss=0.1902, pruned_loss=0.02543, over 4646.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03124, over 972009.21 frames.], batch size: 13, lr: 1.58e-04
+2022-05-08 00:37:05,576 INFO [train.py:715] (3/8) Epoch 14, batch 7750, loss[loss=0.136, simple_loss=0.2104, pruned_loss=0.03077, over 4870.00 frames.], tot_loss[loss=0.1357, simple_loss=0.209, pruned_loss=0.03116, over 972158.65 frames.], batch size: 32, lr: 1.58e-04
+2022-05-08 00:37:44,377 INFO [train.py:715] (3/8) Epoch 14, batch 7800, loss[loss=0.1447, simple_loss=0.2322, pruned_loss=0.02853, over 4956.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03149, over 972510.00 frames.], batch size: 39, lr: 1.58e-04
+2022-05-08 00:38:23,469 INFO [train.py:715] (3/8) Epoch 14, batch 7850, loss[loss=0.1376, simple_loss=0.2239, pruned_loss=0.02568, over 4892.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03136, over 972379.11 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 00:39:03,273 INFO [train.py:715] (3/8) Epoch 14, batch 7900, loss[loss=0.1281, simple_loss=0.2014, pruned_loss=0.02736, over 4834.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03151, over 972218.68 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 00:39:42,079 INFO [train.py:715] (3/8) Epoch 14, batch 7950, loss[loss=0.1538, simple_loss=0.2266, pruned_loss=0.04051, over 4869.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03132, over 972528.67 frames.], batch size: 20, lr: 1.58e-04
+2022-05-08 00:40:21,689 INFO [train.py:715] (3/8) Epoch 14, batch 8000, loss[loss=0.1723, simple_loss=0.2394, pruned_loss=0.05262, over 4972.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.0315, over 971996.67 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 00:41:00,526 INFO [train.py:715] (3/8) Epoch 14, batch 8050, loss[loss=0.1333, simple_loss=0.2027, pruned_loss=0.03191, over 4824.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03146, over 972323.38 frames.], batch size: 26, lr: 1.58e-04
+2022-05-08 00:41:40,052 INFO [train.py:715] (3/8) Epoch 14, batch 8100, loss[loss=0.1378, simple_loss=0.2197, pruned_loss=0.02793, over 4799.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03155, over 971719.67 frames.], batch size: 21, lr: 1.58e-04
+2022-05-08 00:42:18,786 INFO [train.py:715] (3/8) Epoch 14, batch 8150, loss[loss=0.1216, simple_loss=0.1984, pruned_loss=0.02236, over 4682.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03077, over 972104.99 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 00:42:58,273 INFO [train.py:715] (3/8) Epoch 14, batch 8200, loss[loss=0.1208, simple_loss=0.2043, pruned_loss=0.0186, over 4819.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03042, over 972761.20 frames.], batch size: 24, lr: 1.58e-04
+2022-05-08 00:43:37,711 INFO [train.py:715] (3/8) Epoch 14, batch 8250, loss[loss=0.1534, simple_loss=0.2366, pruned_loss=0.03514, over 4771.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03087, over 971978.33 frames.], batch size: 17, lr: 1.58e-04
+2022-05-08 00:44:17,183 INFO [train.py:715] (3/8) Epoch 14, batch 8300, loss[loss=0.1537, simple_loss=0.2394, pruned_loss=0.03403, over 4969.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03139, over 972479.23 frames.], batch size: 21, lr: 1.58e-04
+2022-05-08 00:44:56,124 INFO [train.py:715] (3/8) Epoch 14, batch 8350, loss[loss=0.158, simple_loss=0.2219, pruned_loss=0.04711, over 4793.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.0315, over 972817.83 frames.], batch size: 14, lr: 1.58e-04
+2022-05-08 00:45:35,324 INFO [train.py:715] (3/8) Epoch 14, batch 8400, loss[loss=0.1268, simple_loss=0.2031, pruned_loss=0.02523, over 4957.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.0316, over 972343.04 frames.], batch size: 21, lr: 1.58e-04
+2022-05-08 00:46:14,805 INFO [train.py:715] (3/8) Epoch 14, batch 8450, loss[loss=0.1224, simple_loss=0.1933, pruned_loss=0.0258, over 4980.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03112, over 972878.11 frames.], batch size: 14, lr: 1.58e-04
+2022-05-08 00:46:53,356 INFO [train.py:715] (3/8) Epoch 14, batch 8500, loss[loss=0.1031, simple_loss=0.1736, pruned_loss=0.01632, over 4789.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03104, over 973310.00 frames.], batch size: 12, lr: 1.58e-04
+2022-05-08 00:47:32,469 INFO [train.py:715] (3/8) Epoch 14, batch 8550, loss[loss=0.1448, simple_loss=0.2205, pruned_loss=0.03454, over 4790.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2103, pruned_loss=0.03119, over 973377.93 frames.], batch size: 17, lr: 1.58e-04
+2022-05-08 00:48:13,440 INFO [train.py:715] (3/8) Epoch 14, batch 8600, loss[loss=0.1379, simple_loss=0.212, pruned_loss=0.03184, over 4693.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03116, over 973562.35 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 00:48:52,731 INFO [train.py:715] (3/8) Epoch 14, batch 8650, loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02882, over 4822.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03089, over 973684.82 frames.], batch size: 25, lr: 1.58e-04
+2022-05-08 00:49:34,157 INFO [train.py:715] (3/8) Epoch 14, batch 8700, loss[loss=0.1355, simple_loss=0.2111, pruned_loss=0.02997, over 4910.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03109, over 973939.88 frames.], batch size: 39, lr: 1.58e-04
+2022-05-08 00:50:13,526 INFO [train.py:715] (3/8) Epoch 14, batch 8750, loss[loss=0.118, simple_loss=0.1912, pruned_loss=0.02243, over 4949.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.0309, over 973824.10 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 00:50:53,244 INFO [train.py:715] (3/8) Epoch 14, batch 8800, loss[loss=0.1293, simple_loss=0.201, pruned_loss=0.0288, over 4798.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03094, over 972950.37 frames.], batch size: 24, lr: 1.58e-04
+2022-05-08 00:51:32,824 INFO [train.py:715] (3/8) Epoch 14, batch 8850, loss[loss=0.1584, simple_loss=0.2251, pruned_loss=0.04586, over 4791.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03099, over 972322.72 frames.], batch size: 14, lr: 1.58e-04
+2022-05-08 00:52:13,346 INFO [train.py:715] (3/8) Epoch 14, batch 8900, loss[loss=0.1197, simple_loss=0.1895, pruned_loss=0.02491, over 4961.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03071, over 972271.98 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 00:52:53,213 INFO [train.py:715] (3/8) Epoch 14, batch 8950, loss[loss=0.1212, simple_loss=0.1866, pruned_loss=0.02794, over 4824.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03083, over 972313.48 frames.], batch size: 27, lr: 1.58e-04
+2022-05-08 00:53:33,008 INFO [train.py:715] (3/8) Epoch 14, batch 9000, loss[loss=0.128, simple_loss=0.207, pruned_loss=0.02449, over 4885.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03082, over 972971.31 frames.], batch size: 22, lr: 1.58e-04
+2022-05-08 00:53:33,009 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 00:53:47,939 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.1052, simple_loss=0.189, pruned_loss=0.01074, over 914524.00 frames.
+2022-05-08 00:54:27,481 INFO [train.py:715] (3/8) Epoch 14, batch 9050, loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03048, over 4886.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03011, over 972962.25 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 00:55:07,803 INFO [train.py:715] (3/8) Epoch 14, batch 9100, loss[loss=0.1224, simple_loss=0.2004, pruned_loss=0.02223, over 4988.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02992, over 972814.29 frames.], batch size: 28, lr: 1.58e-04
+2022-05-08 00:55:47,312 INFO [train.py:715] (3/8) Epoch 14, batch 9150, loss[loss=0.1273, simple_loss=0.2033, pruned_loss=0.02564, over 4981.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03062, over 972350.93 frames.], batch size: 28, lr: 1.58e-04
+2022-05-08 00:56:27,173 INFO [train.py:715] (3/8) Epoch 14, batch 9200, loss[loss=0.1418, simple_loss=0.2152, pruned_loss=0.03417, over 4759.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2085, pruned_loss=0.03093, over 972571.63 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 00:57:06,889 INFO [train.py:715] (3/8) Epoch 14, batch 9250, loss[loss=0.1343, simple_loss=0.209, pruned_loss=0.0298, over 4879.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2085, pruned_loss=0.031, over 972389.49 frames.], batch size: 16, lr: 1.58e-04
+2022-05-08 00:57:46,604 INFO [train.py:715] (3/8) Epoch 14, batch 9300, loss[loss=0.1466, simple_loss=0.2161, pruned_loss=0.03855, over 4886.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03089, over 971744.34 frames.], batch size: 16, lr: 1.58e-04
+2022-05-08 00:58:26,526 INFO [train.py:715] (3/8) Epoch 14, batch 9350, loss[loss=0.1392, simple_loss=0.2164, pruned_loss=0.03103, over 4966.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03115, over 972702.44 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 00:59:06,672 INFO [train.py:715] (3/8) Epoch 14, batch 9400, loss[loss=0.1376, simple_loss=0.2073, pruned_loss=0.03396, over 4759.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03131, over 973094.96 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 00:59:46,291 INFO [train.py:715] (3/8) Epoch 14, batch 9450, loss[loss=0.1297, simple_loss=0.2116, pruned_loss=0.02389, over 4832.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03088, over 972731.37 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 01:00:26,048 INFO [train.py:715] (3/8) Epoch 14, batch 9500, loss[loss=0.1316, simple_loss=0.2086, pruned_loss=0.02727, over 4903.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03112, over 972686.78 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 01:01:05,840 INFO [train.py:715] (3/8) Epoch 14, batch 9550, loss[loss=0.1136, simple_loss=0.1892, pruned_loss=0.01905, over 4772.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03098, over 972450.35 frames.], batch size: 18, lr: 1.58e-04
+2022-05-08 01:01:45,998 INFO [train.py:715] (3/8) Epoch 14, batch 9600, loss[loss=0.1455, simple_loss=0.2183, pruned_loss=0.0363, over 4768.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2081, pruned_loss=0.03071, over 972163.63 frames.], batch size: 18, lr: 1.58e-04
+2022-05-08 01:02:25,428 INFO [train.py:715] (3/8) Epoch 14, batch 9650, loss[loss=0.1309, simple_loss=0.216, pruned_loss=0.02291, over 4870.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2079, pruned_loss=0.03072, over 972430.28 frames.], batch size: 20, lr: 1.58e-04
+2022-05-08 01:03:05,453 INFO [train.py:715] (3/8) Epoch 14, batch 9700, loss[loss=0.1278, simple_loss=0.2119, pruned_loss=0.02182, over 4976.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2086, pruned_loss=0.03093, over 973172.44 frames.], batch size: 25, lr: 1.58e-04
+2022-05-08 01:03:45,039 INFO [train.py:715] (3/8) Epoch 14, batch 9750, loss[loss=0.126, simple_loss=0.2117, pruned_loss=0.02018, over 4751.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03108, over 973638.75 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 01:04:25,346 INFO [train.py:715] (3/8) Epoch 14, batch 9800, loss[loss=0.134, simple_loss=0.2044, pruned_loss=0.03184, over 4890.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03139, over 973354.24 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 01:05:04,565 INFO [train.py:715] (3/8) Epoch 14, batch 9850, loss[loss=0.1223, simple_loss=0.1934, pruned_loss=0.02557, over 4698.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03071, over 972783.98 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 01:05:44,638 INFO [train.py:715] (3/8) Epoch 14, batch 9900, loss[loss=0.1235, simple_loss=0.2062, pruned_loss=0.02037, over 4759.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03079, over 972537.96 frames.], batch size: 17, lr: 1.58e-04
+2022-05-08 01:06:24,618 INFO [train.py:715] (3/8) Epoch 14, batch 9950, loss[loss=0.1119, simple_loss=0.1919, pruned_loss=0.01589, over 4822.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03125, over 972691.77 frames.], batch size: 27, lr: 1.58e-04
+2022-05-08 01:07:03,942 INFO [train.py:715] (3/8) Epoch 14, batch 10000, loss[loss=0.1283, simple_loss=0.2044, pruned_loss=0.02613, over 4958.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03058, over 972740.24 frames.], batch size: 24, lr: 1.58e-04
+2022-05-08 01:07:43,993 INFO [train.py:715] (3/8) Epoch 14, batch 10050, loss[loss=0.1191, simple_loss=0.1868, pruned_loss=0.02563, over 4828.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03008, over 973958.66 frames.], batch size: 12, lr: 1.58e-04
+2022-05-08 01:08:23,515 INFO [train.py:715] (3/8) Epoch 14, batch 10100, loss[loss=0.1123, simple_loss=0.1838, pruned_loss=0.02038, over 4984.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03046, over 973585.75 frames.], batch size: 24, lr: 1.58e-04
+2022-05-08 01:09:03,293 INFO [train.py:715] (3/8) Epoch 14, batch 10150, loss[loss=0.1308, simple_loss=0.2094, pruned_loss=0.02607, over 4807.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03052, over 973224.49 frames.], batch size: 13, lr: 1.58e-04
+2022-05-08 01:09:42,487 INFO [train.py:715] (3/8) Epoch 14, batch 10200, loss[loss=0.1249, simple_loss=0.1971, pruned_loss=0.02633, over 4781.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03035, over 973507.04 frames.], batch size: 18, lr: 1.58e-04
+2022-05-08 01:10:22,731 INFO [train.py:715] (3/8) Epoch 14, batch 10250, loss[loss=0.1217, simple_loss=0.1981, pruned_loss=0.02263, over 4918.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03058, over 972755.42 frames.], batch size: 18, lr: 1.58e-04
+2022-05-08 01:11:02,455 INFO [train.py:715] (3/8) Epoch 14, batch 10300, loss[loss=0.1479, simple_loss=0.2176, pruned_loss=0.03914, over 4959.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03109, over 972541.74 frames.], batch size: 39, lr: 1.58e-04
+2022-05-08 01:11:41,906 INFO [train.py:715] (3/8) Epoch 14, batch 10350, loss[loss=0.1562, simple_loss=0.2343, pruned_loss=0.03907, over 4768.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03078, over 970963.09 frames.], batch size: 18, lr: 1.58e-04
+2022-05-08 01:12:22,108 INFO [train.py:715] (3/8) Epoch 14, batch 10400, loss[loss=0.1381, simple_loss=0.2172, pruned_loss=0.02955, over 4814.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.0303, over 970974.32 frames.], batch size: 26, lr: 1.58e-04
+2022-05-08 01:13:01,497 INFO [train.py:715] (3/8) Epoch 14, batch 10450, loss[loss=0.135, simple_loss=0.2064, pruned_loss=0.03181, over 4901.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03037, over 971733.60 frames.], batch size: 39, lr: 1.58e-04
+2022-05-08 01:13:41,729 INFO [train.py:715] (3/8) Epoch 14, batch 10500, loss[loss=0.1367, simple_loss=0.2145, pruned_loss=0.02948, over 4907.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03068, over 972007.59 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 01:14:21,000 INFO [train.py:715] (3/8) Epoch 14, batch 10550, loss[loss=0.1457, simple_loss=0.2318, pruned_loss=0.02974, over 4858.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03063, over 972257.28 frames.], batch size: 13, lr: 1.58e-04
+2022-05-08 01:15:01,263 INFO [train.py:715] (3/8) Epoch 14, batch 10600, loss[loss=0.151, simple_loss=0.2297, pruned_loss=0.03621, over 4899.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03024, over 971794.95 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 01:15:40,588 INFO [train.py:715] (3/8) Epoch 14, batch 10650, loss[loss=0.1045, simple_loss=0.174, pruned_loss=0.0175, over 4732.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03029, over 972108.08 frames.], batch size: 12, lr: 1.58e-04
+2022-05-08 01:16:19,716 INFO [train.py:715] (3/8) Epoch 14, batch 10700, loss[loss=0.1346, simple_loss=0.2098, pruned_loss=0.02968, over 4737.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03058, over 971791.09 frames.], batch size: 16, lr: 1.58e-04
+2022-05-08 01:16:58,898 INFO [train.py:715] (3/8) Epoch 14, batch 10750, loss[loss=0.1576, simple_loss=0.234, pruned_loss=0.04059, over 4819.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03037, over 972477.40 frames.], batch size: 26, lr: 1.58e-04
+2022-05-08 01:17:38,324 INFO [train.py:715] (3/8) Epoch 14, batch 10800, loss[loss=0.1428, simple_loss=0.2178, pruned_loss=0.03386, over 4978.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03129, over 972630.39 frames.], batch size: 25, lr: 1.58e-04
+2022-05-08 01:18:17,862 INFO [train.py:715] (3/8) Epoch 14, batch 10850, loss[loss=0.1597, simple_loss=0.2357, pruned_loss=0.04188, over 4891.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03159, over 972683.67 frames.], batch size: 19, lr: 1.58e-04
+2022-05-08 01:18:56,527 INFO [train.py:715] (3/8) Epoch 14, batch 10900, loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03115, over 4693.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03145, over 972778.26 frames.], batch size: 15, lr: 1.58e-04
+2022-05-08 01:19:36,724 INFO [train.py:715] (3/8) Epoch 14, batch 10950, loss[loss=0.1248, simple_loss=0.1932, pruned_loss=0.02816, over 4876.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03131, over 972863.32 frames.], batch size: 12, lr: 1.58e-04
+2022-05-08 01:20:17,493 INFO [train.py:715] (3/8) Epoch 14, batch 11000, loss[loss=0.1238, simple_loss=0.1961, pruned_loss=0.0257, over 4975.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03103, over 972261.32 frames.], batch size: 14, lr: 1.58e-04
+2022-05-08 01:20:56,619 INFO [train.py:715] (3/8) Epoch 14, batch 11050, loss[loss=0.1278, simple_loss=0.2004, pruned_loss=0.02758, over 4942.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03062, over 972128.11 frames.], batch size: 23, lr: 1.57e-04
+2022-05-08 01:21:37,660 INFO [train.py:715] (3/8) Epoch 14, batch 11100, loss[loss=0.09806, simple_loss=0.1656, pruned_loss=0.01528, over 4706.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03016, over 972050.19 frames.], batch size: 12, lr: 1.57e-04
+2022-05-08 01:22:18,221 INFO [train.py:715] (3/8) Epoch 14, batch 11150, loss[loss=0.151, simple_loss=0.2303, pruned_loss=0.03583, over 4980.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03068, over 972366.51 frames.], batch size: 24, lr: 1.57e-04
+2022-05-08 01:22:58,453 INFO [train.py:715] (3/8) Epoch 14, batch 11200, loss[loss=0.1369, simple_loss=0.2077, pruned_loss=0.03301, over 4741.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03086, over 972916.88 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 01:23:37,875 INFO [train.py:715] (3/8) Epoch 14, batch 11250, loss[loss=0.1558, simple_loss=0.2274, pruned_loss=0.04211, over 4876.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03087, over 973100.03 frames.], batch size: 32, lr: 1.57e-04
+2022-05-08 01:24:18,305 INFO [train.py:715] (3/8) Epoch 14, batch 11300, loss[loss=0.1323, simple_loss=0.2161, pruned_loss=0.02426, over 4812.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.0305, over 972465.11 frames.], batch size: 25, lr: 1.57e-04
+2022-05-08 01:24:58,563 INFO [train.py:715] (3/8) Epoch 14, batch 11350, loss[loss=0.1176, simple_loss=0.1921, pruned_loss=0.02159, over 4931.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03054, over 973543.06 frames.], batch size: 29, lr: 1.57e-04
+2022-05-08 01:25:37,729 INFO [train.py:715] (3/8) Epoch 14, batch 11400, loss[loss=0.1108, simple_loss=0.1915, pruned_loss=0.01504, over 4976.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03063, over 973399.44 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 01:26:18,739 INFO [train.py:715] (3/8) Epoch 14, batch 11450, loss[loss=0.1321, simple_loss=0.2155, pruned_loss=0.0243, over 4948.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2075, pruned_loss=0.03014, over 973559.52 frames.], batch size: 21, lr: 1.57e-04
+2022-05-08 01:26:59,114 INFO [train.py:715] (3/8) Epoch 14, batch 11500, loss[loss=0.1391, simple_loss=0.2147, pruned_loss=0.03176, over 4928.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03026, over 973605.13 frames.], batch size: 18, lr: 1.57e-04
+2022-05-08 01:27:39,024 INFO [train.py:715] (3/8) Epoch 14, batch 11550, loss[loss=0.1389, simple_loss=0.2152, pruned_loss=0.03132, over 4747.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02991, over 973372.31 frames.], batch size: 19, lr: 1.57e-04
+2022-05-08 01:28:18,476 INFO [train.py:715] (3/8) Epoch 14, batch 11600, loss[loss=0.1297, simple_loss=0.1999, pruned_loss=0.02971, over 4787.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03006, over 972820.66 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 01:28:58,177 INFO [train.py:715] (3/8) Epoch 14, batch 11650, loss[loss=0.1351, simple_loss=0.2003, pruned_loss=0.03491, over 4745.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03011, over 972460.72 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 01:29:37,887 INFO [train.py:715] (3/8) Epoch 14, batch 11700, loss[loss=0.1419, simple_loss=0.2217, pruned_loss=0.03103, over 4969.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02982, over 972243.52 frames.], batch size: 39, lr: 1.57e-04
+2022-05-08 01:30:17,152 INFO [train.py:715] (3/8) Epoch 14, batch 11750, loss[loss=0.1331, simple_loss=0.1988, pruned_loss=0.03373, over 4974.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03012, over 972193.17 frames.], batch size: 25, lr: 1.57e-04
+2022-05-08 01:30:56,856 INFO [train.py:715] (3/8) Epoch 14, batch 11800, loss[loss=0.1263, simple_loss=0.1979, pruned_loss=0.02729, over 4695.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03069, over 971878.03 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 01:31:35,983 INFO [train.py:715] (3/8) Epoch 14, batch 11850, loss[loss=0.1231, simple_loss=0.2004, pruned_loss=0.02291, over 4850.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.0308, over 972481.42 frames.], batch size: 34, lr: 1.57e-04
+2022-05-08 01:32:14,889 INFO [train.py:715] (3/8) Epoch 14, batch 11900, loss[loss=0.1205, simple_loss=0.1889, pruned_loss=0.02601, over 4881.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.0307, over 971581.29 frames.], batch size: 32, lr: 1.57e-04
+2022-05-08 01:32:54,215 INFO [train.py:715] (3/8) Epoch 14, batch 11950, loss[loss=0.1432, simple_loss=0.2147, pruned_loss=0.03582, over 4934.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.0306, over 971827.76 frames.], batch size: 23, lr: 1.57e-04
+2022-05-08 01:33:33,586 INFO [train.py:715] (3/8) Epoch 14, batch 12000, loss[loss=0.1672, simple_loss=0.2295, pruned_loss=0.05238, over 4986.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03041, over 972746.30 frames.], batch size: 33, lr: 1.57e-04
+2022-05-08 01:33:33,586 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 01:33:43,198 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.1051, simple_loss=0.1889, pruned_loss=0.01067, over 914524.00 frames.
+2022-05-08 01:34:22,502 INFO [train.py:715] (3/8) Epoch 14, batch 12050, loss[loss=0.1255, simple_loss=0.1996, pruned_loss=0.02564, over 4962.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03054, over 972228.26 frames.], batch size: 24, lr: 1.57e-04
+2022-05-08 01:35:01,859 INFO [train.py:715] (3/8) Epoch 14, batch 12100, loss[loss=0.1359, simple_loss=0.2076, pruned_loss=0.03211, over 4922.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03079, over 972065.29 frames.], batch size: 23, lr: 1.57e-04
+2022-05-08 01:35:41,278 INFO [train.py:715] (3/8) Epoch 14, batch 12150, loss[loss=0.1275, simple_loss=0.1978, pruned_loss=0.02864, over 4941.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03082, over 972976.65 frames.], batch size: 18, lr: 1.57e-04
+2022-05-08 01:36:20,618 INFO [train.py:715] (3/8) Epoch 14, batch 12200, loss[loss=0.1299, simple_loss=0.2053, pruned_loss=0.02731, over 4869.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03073, over 973118.61 frames.], batch size: 22, lr: 1.57e-04
+2022-05-08 01:37:00,488 INFO [train.py:715] (3/8) Epoch 14, batch 12250, loss[loss=0.1314, simple_loss=0.2025, pruned_loss=0.03011, over 4968.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03119, over 972245.31 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 01:37:39,676 INFO [train.py:715] (3/8) Epoch 14, batch 12300, loss[loss=0.1225, simple_loss=0.1841, pruned_loss=0.03047, over 4779.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03123, over 971625.38 frames.], batch size: 12, lr: 1.57e-04
+2022-05-08 01:38:19,190 INFO [train.py:715] (3/8) Epoch 14, batch 12350, loss[loss=0.1139, simple_loss=0.1915, pruned_loss=0.01821, over 4976.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03108, over 971197.50 frames.], batch size: 24, lr: 1.57e-04
+2022-05-08 01:38:58,797 INFO [train.py:715] (3/8) Epoch 14, batch 12400, loss[loss=0.144, simple_loss=0.2235, pruned_loss=0.03228, over 4784.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03042, over 971456.10 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 01:39:37,830 INFO [train.py:715] (3/8) Epoch 14, batch 12450, loss[loss=0.1582, simple_loss=0.2226, pruned_loss=0.04697, over 4846.00 frames.], tot_loss[loss=0.136, simple_loss=0.2101, pruned_loss=0.03093, over 971332.84 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 01:40:17,256 INFO [train.py:715] (3/8) Epoch 14, batch 12500, loss[loss=0.09878, simple_loss=0.1731, pruned_loss=0.01225, over 4824.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03106, over 971700.88 frames.], batch size: 12, lr: 1.57e-04
+2022-05-08 01:40:57,006 INFO [train.py:715] (3/8) Epoch 14, batch 12550, loss[loss=0.1181, simple_loss=0.1874, pruned_loss=0.02438, over 4828.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.03109, over 971667.71 frames.], batch size: 12, lr: 1.57e-04
+2022-05-08 01:41:36,646 INFO [train.py:715] (3/8) Epoch 14, batch 12600, loss[loss=0.1655, simple_loss=0.237, pruned_loss=0.04695, over 4953.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03111, over 973095.82 frames.], batch size: 24, lr: 1.57e-04
+2022-05-08 01:42:15,594 INFO [train.py:715] (3/8) Epoch 14, batch 12650, loss[loss=0.1376, simple_loss=0.2133, pruned_loss=0.03092, over 4786.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03151, over 972354.86 frames.], batch size: 18, lr: 1.57e-04
+2022-05-08 01:42:55,473 INFO [train.py:715] (3/8) Epoch 14, batch 12700, loss[loss=0.1213, simple_loss=0.2026, pruned_loss=0.02001, over 4802.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03116, over 972018.66 frames.], batch size: 21, lr: 1.57e-04
+2022-05-08 01:43:35,530 INFO [train.py:715] (3/8) Epoch 14, batch 12750, loss[loss=0.1328, simple_loss=0.2057, pruned_loss=0.02996, over 4850.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03139, over 971773.17 frames.], batch size: 32, lr: 1.57e-04
+2022-05-08 01:44:15,506 INFO [train.py:715] (3/8) Epoch 14, batch 12800, loss[loss=0.1159, simple_loss=0.1927, pruned_loss=0.0196, over 4977.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03133, over 971626.99 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 01:44:55,334 INFO [train.py:715] (3/8) Epoch 14, batch 12850, loss[loss=0.15, simple_loss=0.216, pruned_loss=0.04194, over 4919.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.0311, over 971379.18 frames.], batch size: 23, lr: 1.57e-04
+2022-05-08 01:45:35,540 INFO [train.py:715] (3/8) Epoch 14, batch 12900, loss[loss=0.1492, simple_loss=0.2144, pruned_loss=0.04197, over 4883.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03121, over 971521.28 frames.], batch size: 22, lr: 1.57e-04
+2022-05-08 01:46:15,894 INFO [train.py:715] (3/8) Epoch 14, batch 12950, loss[loss=0.1728, simple_loss=0.2512, pruned_loss=0.0472, over 4816.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03085, over 970628.07 frames.], batch size: 21, lr: 1.57e-04
+2022-05-08 01:46:55,855 INFO [train.py:715] (3/8) Epoch 14, batch 13000, loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03506, over 4764.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03071, over 971152.71 frames.], batch size: 19, lr: 1.57e-04
+2022-05-08 01:47:36,098 INFO [train.py:715] (3/8) Epoch 14, batch 13050, loss[loss=0.1353, simple_loss=0.1979, pruned_loss=0.03633, over 4981.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03034, over 970753.44 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 01:48:16,116 INFO [train.py:715] (3/8) Epoch 14, batch 13100, loss[loss=0.127, simple_loss=0.203, pruned_loss=0.02552, over 4681.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03017, over 969833.40 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 01:48:56,300 INFO [train.py:715] (3/8) Epoch 14, batch 13150, loss[loss=0.1214, simple_loss=0.2008, pruned_loss=0.02099, over 4800.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03011, over 970765.80 frames.], batch size: 12, lr: 1.57e-04
+2022-05-08 01:49:36,396 INFO [train.py:715] (3/8) Epoch 14, batch 13200, loss[loss=0.1168, simple_loss=0.1961, pruned_loss=0.01878, over 4914.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2094, pruned_loss=0.03023, over 971399.74 frames.], batch size: 29, lr: 1.57e-04
+2022-05-08 01:50:16,602 INFO [train.py:715] (3/8) Epoch 14, batch 13250, loss[loss=0.1192, simple_loss=0.1891, pruned_loss=0.02466, over 4858.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03032, over 970884.88 frames.], batch size: 32, lr: 1.57e-04
+2022-05-08 01:50:56,858 INFO [train.py:715] (3/8) Epoch 14, batch 13300, loss[loss=0.1265, simple_loss=0.1976, pruned_loss=0.0277, over 4885.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02998, over 970600.18 frames.], batch size: 19, lr: 1.57e-04
+2022-05-08 01:51:36,426 INFO [train.py:715] (3/8) Epoch 14, batch 13350, loss[loss=0.134, simple_loss=0.2, pruned_loss=0.03399, over 4705.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03003, over 971505.88 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 01:52:15,920 INFO [train.py:715] (3/8) Epoch 14, batch 13400, loss[loss=0.1208, simple_loss=0.1965, pruned_loss=0.02257, over 4834.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03034, over 971519.01 frames.], batch size: 13, lr: 1.57e-04
+2022-05-08 01:52:55,515 INFO [train.py:715] (3/8) Epoch 14, batch 13450, loss[loss=0.151, simple_loss=0.2365, pruned_loss=0.0328, over 4911.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03014, over 972597.61 frames.], batch size: 17, lr: 1.57e-04
+2022-05-08 01:53:35,078 INFO [train.py:715] (3/8) Epoch 14, batch 13500, loss[loss=0.1289, simple_loss=0.2155, pruned_loss=0.02109, over 4992.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03016, over 972188.12 frames.], batch size: 26, lr: 1.57e-04
+2022-05-08 01:54:14,285 INFO [train.py:715] (3/8) Epoch 14, batch 13550, loss[loss=0.1334, simple_loss=0.213, pruned_loss=0.02693, over 4873.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03057, over 971494.09 frames.], batch size: 22, lr: 1.57e-04
+2022-05-08 01:54:53,678 INFO [train.py:715] (3/8) Epoch 14, batch 13600, loss[loss=0.108, simple_loss=0.1876, pruned_loss=0.01418, over 4812.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03049, over 971500.02 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 01:55:32,972 INFO [train.py:715] (3/8) Epoch 14, batch 13650, loss[loss=0.1542, simple_loss=0.2314, pruned_loss=0.03843, over 4993.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03024, over 972293.39 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 01:56:12,538 INFO [train.py:715] (3/8) Epoch 14, batch 13700, loss[loss=0.1452, simple_loss=0.2235, pruned_loss=0.03342, over 4856.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03031, over 971877.10 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 01:56:51,586 INFO [train.py:715] (3/8) Epoch 14, batch 13750, loss[loss=0.1517, simple_loss=0.2192, pruned_loss=0.04208, over 4803.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03057, over 972536.22 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 01:57:30,923 INFO [train.py:715] (3/8) Epoch 14, batch 13800, loss[loss=0.1283, simple_loss=0.2041, pruned_loss=0.0262, over 4950.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03046, over 972207.38 frames.], batch size: 24, lr: 1.57e-04
+2022-05-08 01:58:12,476 INFO [train.py:715] (3/8) Epoch 14, batch 13850, loss[loss=0.1339, simple_loss=0.213, pruned_loss=0.02739, over 4990.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2075, pruned_loss=0.03047, over 972543.31 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 01:58:51,820 INFO [train.py:715] (3/8) Epoch 14, batch 13900, loss[loss=0.123, simple_loss=0.2068, pruned_loss=0.01966, over 4745.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2078, pruned_loss=0.0307, over 972574.46 frames.], batch size: 19, lr: 1.57e-04
+2022-05-08 01:59:31,446 INFO [train.py:715] (3/8) Epoch 14, batch 13950, loss[loss=0.1199, simple_loss=0.1941, pruned_loss=0.02289, over 4817.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.0305, over 972105.54 frames.], batch size: 25, lr: 1.57e-04
+2022-05-08 02:00:10,941 INFO [train.py:715] (3/8) Epoch 14, batch 14000, loss[loss=0.1259, simple_loss=0.1987, pruned_loss=0.0265, over 4882.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03057, over 971803.62 frames.], batch size: 22, lr: 1.57e-04
+2022-05-08 02:00:50,381 INFO [train.py:715] (3/8) Epoch 14, batch 14050, loss[loss=0.1536, simple_loss=0.2218, pruned_loss=0.0427, over 4962.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03069, over 971599.70 frames.], batch size: 35, lr: 1.57e-04
+2022-05-08 02:01:30,046 INFO [train.py:715] (3/8) Epoch 14, batch 14100, loss[loss=0.1195, simple_loss=0.1865, pruned_loss=0.02627, over 4963.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03077, over 972917.96 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 02:02:09,595 INFO [train.py:715] (3/8) Epoch 14, batch 14150, loss[loss=0.1229, simple_loss=0.1947, pruned_loss=0.02555, over 4895.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03115, over 973805.75 frames.], batch size: 19, lr: 1.57e-04
+2022-05-08 02:02:49,095 INFO [train.py:715] (3/8) Epoch 14, batch 14200, loss[loss=0.1554, simple_loss=0.2267, pruned_loss=0.04208, over 4810.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.0313, over 972453.75 frames.], batch size: 21, lr: 1.57e-04
+2022-05-08 02:03:28,352 INFO [train.py:715] (3/8) Epoch 14, batch 14250, loss[loss=0.1372, simple_loss=0.2115, pruned_loss=0.03141, over 4987.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03097, over 972124.85 frames.], batch size: 28, lr: 1.57e-04
+2022-05-08 02:04:08,206 INFO [train.py:715] (3/8) Epoch 14, batch 14300, loss[loss=0.1335, simple_loss=0.2133, pruned_loss=0.02679, over 4834.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03098, over 971178.61 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 02:04:47,397 INFO [train.py:715] (3/8) Epoch 14, batch 14350, loss[loss=0.1429, simple_loss=0.216, pruned_loss=0.03491, over 4753.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03121, over 971737.86 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 02:05:26,851 INFO [train.py:715] (3/8) Epoch 14, batch 14400, loss[loss=0.1476, simple_loss=0.2305, pruned_loss=0.03237, over 4891.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.0309, over 971285.80 frames.], batch size: 22, lr: 1.57e-04
+2022-05-08 02:06:06,342 INFO [train.py:715] (3/8) Epoch 14, batch 14450, loss[loss=0.1498, simple_loss=0.2232, pruned_loss=0.03823, over 4885.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03122, over 971988.14 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 02:06:45,899 INFO [train.py:715] (3/8) Epoch 14, batch 14500, loss[loss=0.138, simple_loss=0.2172, pruned_loss=0.02942, over 4864.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2105, pruned_loss=0.03096, over 971684.56 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 02:07:25,176 INFO [train.py:715] (3/8) Epoch 14, batch 14550, loss[loss=0.1515, simple_loss=0.2205, pruned_loss=0.0412, over 4979.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2104, pruned_loss=0.03093, over 972038.44 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 02:08:04,456 INFO [train.py:715] (3/8) Epoch 14, batch 14600, loss[loss=0.1322, simple_loss=0.2052, pruned_loss=0.02959, over 4910.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2099, pruned_loss=0.03076, over 972426.45 frames.], batch size: 18, lr: 1.57e-04
+2022-05-08 02:08:44,680 INFO [train.py:715] (3/8) Epoch 14, batch 14650, loss[loss=0.1297, simple_loss=0.2017, pruned_loss=0.02884, over 4924.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03068, over 972464.31 frames.], batch size: 39, lr: 1.57e-04
+2022-05-08 02:09:24,103 INFO [train.py:715] (3/8) Epoch 14, batch 14700, loss[loss=0.1547, simple_loss=0.2226, pruned_loss=0.04336, over 4943.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03024, over 972122.69 frames.], batch size: 39, lr: 1.57e-04
+2022-05-08 02:10:03,917 INFO [train.py:715] (3/8) Epoch 14, batch 14750, loss[loss=0.1538, simple_loss=0.2118, pruned_loss=0.04787, over 4745.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03041, over 972083.80 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 02:10:43,092 INFO [train.py:715] (3/8) Epoch 14, batch 14800, loss[loss=0.1307, simple_loss=0.2004, pruned_loss=0.03049, over 4812.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03052, over 971988.93 frames.], batch size: 12, lr: 1.57e-04
+2022-05-08 02:11:23,010 INFO [train.py:715] (3/8) Epoch 14, batch 14850, loss[loss=0.1487, simple_loss=0.224, pruned_loss=0.03672, over 4985.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03016, over 971986.47 frames.], batch size: 28, lr: 1.57e-04
+2022-05-08 02:12:02,549 INFO [train.py:715] (3/8) Epoch 14, batch 14900, loss[loss=0.1396, simple_loss=0.2007, pruned_loss=0.03923, over 4803.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03044, over 971849.44 frames.], batch size: 13, lr: 1.57e-04
+2022-05-08 02:12:41,998 INFO [train.py:715] (3/8) Epoch 14, batch 14950, loss[loss=0.1245, simple_loss=0.2009, pruned_loss=0.02409, over 4965.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03012, over 972089.59 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 02:13:22,059 INFO [train.py:715] (3/8) Epoch 14, batch 15000, loss[loss=0.1537, simple_loss=0.2228, pruned_loss=0.04235, over 4741.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03042, over 971675.99 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 02:13:22,060 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 02:13:31,706 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1889, pruned_loss=0.01079, over 914524.00 frames.
+2022-05-08 02:14:12,555 INFO [train.py:715] (3/8) Epoch 14, batch 15050, loss[loss=0.1134, simple_loss=0.1878, pruned_loss=0.01949, over 4796.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03033, over 972046.10 frames.], batch size: 12, lr: 1.57e-04
+2022-05-08 02:14:52,638 INFO [train.py:715] (3/8) Epoch 14, batch 15100, loss[loss=0.1277, simple_loss=0.2117, pruned_loss=0.02189, over 4952.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02998, over 972021.48 frames.], batch size: 21, lr: 1.57e-04
+2022-05-08 02:15:33,285 INFO [train.py:715] (3/8) Epoch 14, batch 15150, loss[loss=0.1276, simple_loss=0.1988, pruned_loss=0.02816, over 4986.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.0303, over 972155.91 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 02:16:13,413 INFO [train.py:715] (3/8) Epoch 14, batch 15200, loss[loss=0.1208, simple_loss=0.1882, pruned_loss=0.02673, over 4982.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03004, over 971884.61 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 02:16:54,057 INFO [train.py:715] (3/8) Epoch 14, batch 15250, loss[loss=0.1588, simple_loss=0.2282, pruned_loss=0.04473, over 4916.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03048, over 971192.71 frames.], batch size: 17, lr: 1.57e-04
+2022-05-08 02:17:33,927 INFO [train.py:715] (3/8) Epoch 14, batch 15300, loss[loss=0.1653, simple_loss=0.2272, pruned_loss=0.05174, over 4857.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03029, over 971304.59 frames.], batch size: 38, lr: 1.57e-04
+2022-05-08 02:18:13,479 INFO [train.py:715] (3/8) Epoch 14, batch 15350, loss[loss=0.1489, simple_loss=0.2295, pruned_loss=0.0341, over 4844.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02976, over 970994.92 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 02:18:53,584 INFO [train.py:715] (3/8) Epoch 14, batch 15400, loss[loss=0.1461, simple_loss=0.2347, pruned_loss=0.02881, over 4743.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03055, over 972202.61 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 02:19:32,974 INFO [train.py:715] (3/8) Epoch 14, batch 15450, loss[loss=0.1423, simple_loss=0.2177, pruned_loss=0.03345, over 4868.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03055, over 972353.92 frames.], batch size: 32, lr: 1.57e-04
+2022-05-08 02:20:12,213 INFO [train.py:715] (3/8) Epoch 14, batch 15500, loss[loss=0.1316, simple_loss=0.2088, pruned_loss=0.02719, over 4925.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03033, over 972878.59 frames.], batch size: 29, lr: 1.57e-04
+2022-05-08 02:20:51,549 INFO [train.py:715] (3/8) Epoch 14, batch 15550, loss[loss=0.1435, simple_loss=0.2243, pruned_loss=0.03132, over 4908.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2104, pruned_loss=0.03054, over 971677.60 frames.], batch size: 17, lr: 1.57e-04
+2022-05-08 02:21:31,495 INFO [train.py:715] (3/8) Epoch 14, batch 15600, loss[loss=0.1403, simple_loss=0.214, pruned_loss=0.03334, over 4792.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2095, pruned_loss=0.03022, over 971573.16 frames.], batch size: 17, lr: 1.57e-04
+2022-05-08 02:22:10,935 INFO [train.py:715] (3/8) Epoch 14, batch 15650, loss[loss=0.1363, simple_loss=0.2087, pruned_loss=0.03197, over 4954.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.031, over 971717.52 frames.], batch size: 21, lr: 1.57e-04
+2022-05-08 02:22:49,322 INFO [train.py:715] (3/8) Epoch 14, batch 15700, loss[loss=0.158, simple_loss=0.2342, pruned_loss=0.04088, over 4768.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2103, pruned_loss=0.03095, over 971663.24 frames.], batch size: 18, lr: 1.57e-04
+2022-05-08 02:23:29,529 INFO [train.py:715] (3/8) Epoch 14, batch 15750, loss[loss=0.1268, simple_loss=0.1999, pruned_loss=0.02688, over 4786.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03086, over 971485.78 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 02:24:09,056 INFO [train.py:715] (3/8) Epoch 14, batch 15800, loss[loss=0.1468, simple_loss=0.2286, pruned_loss=0.03253, over 4918.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03047, over 972379.16 frames.], batch size: 17, lr: 1.57e-04
+2022-05-08 02:24:48,296 INFO [train.py:715] (3/8) Epoch 14, batch 15850, loss[loss=0.1078, simple_loss=0.1779, pruned_loss=0.01885, over 4886.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03046, over 971802.05 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 02:25:27,575 INFO [train.py:715] (3/8) Epoch 14, batch 15900, loss[loss=0.1255, simple_loss=0.1992, pruned_loss=0.02595, over 4873.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.0311, over 971546.18 frames.], batch size: 22, lr: 1.57e-04
+2022-05-08 02:26:07,618 INFO [train.py:715] (3/8) Epoch 14, batch 15950, loss[loss=0.1106, simple_loss=0.1872, pruned_loss=0.01697, over 4942.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03076, over 971328.14 frames.], batch size: 21, lr: 1.57e-04
+2022-05-08 02:26:47,030 INFO [train.py:715] (3/8) Epoch 14, batch 16000, loss[loss=0.1171, simple_loss=0.2009, pruned_loss=0.01669, over 4884.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03032, over 971832.19 frames.], batch size: 38, lr: 1.57e-04
+2022-05-08 02:27:25,749 INFO [train.py:715] (3/8) Epoch 14, batch 16050, loss[loss=0.1337, simple_loss=0.2056, pruned_loss=0.03091, over 4841.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2103, pruned_loss=0.03056, over 972011.50 frames.], batch size: 13, lr: 1.57e-04
+2022-05-08 02:28:04,469 INFO [train.py:715] (3/8) Epoch 14, batch 16100, loss[loss=0.1458, simple_loss=0.2094, pruned_loss=0.04112, over 4848.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2099, pruned_loss=0.03048, over 972333.70 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 02:28:42,585 INFO [train.py:715] (3/8) Epoch 14, batch 16150, loss[loss=0.1404, simple_loss=0.221, pruned_loss=0.02993, over 4982.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2108, pruned_loss=0.03096, over 973123.94 frames.], batch size: 28, lr: 1.57e-04
+2022-05-08 02:29:20,837 INFO [train.py:715] (3/8) Epoch 14, batch 16200, loss[loss=0.1552, simple_loss=0.2172, pruned_loss=0.04655, over 4788.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2108, pruned_loss=0.03104, over 973083.44 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 02:29:59,439 INFO [train.py:715] (3/8) Epoch 14, batch 16250, loss[loss=0.1276, simple_loss=0.2042, pruned_loss=0.02555, over 4985.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03092, over 973022.06 frames.], batch size: 25, lr: 1.57e-04
+2022-05-08 02:30:38,581 INFO [train.py:715] (3/8) Epoch 14, batch 16300, loss[loss=0.1715, simple_loss=0.2428, pruned_loss=0.0501, over 4770.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03057, over 973114.66 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 02:31:16,527 INFO [train.py:715] (3/8) Epoch 14, batch 16350, loss[loss=0.2112, simple_loss=0.2831, pruned_loss=0.06968, over 4796.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2102, pruned_loss=0.03063, over 972861.44 frames.], batch size: 24, lr: 1.57e-04
+2022-05-08 02:31:55,702 INFO [train.py:715] (3/8) Epoch 14, batch 16400, loss[loss=0.1446, simple_loss=0.2272, pruned_loss=0.03095, over 4908.00 frames.], tot_loss[loss=0.1357, simple_loss=0.21, pruned_loss=0.03069, over 973081.18 frames.], batch size: 22, lr: 1.57e-04
+2022-05-08 02:32:35,413 INFO [train.py:715] (3/8) Epoch 14, batch 16450, loss[loss=0.1177, simple_loss=0.1978, pruned_loss=0.01877, over 4913.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03073, over 973150.49 frames.], batch size: 29, lr: 1.57e-04
+2022-05-08 02:33:14,850 INFO [train.py:715] (3/8) Epoch 14, batch 16500, loss[loss=0.1293, simple_loss=0.2004, pruned_loss=0.02907, over 4956.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03032, over 973837.02 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 02:33:53,750 INFO [train.py:715] (3/8) Epoch 14, batch 16550, loss[loss=0.12, simple_loss=0.1977, pruned_loss=0.0212, over 4739.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03048, over 974449.35 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 02:34:34,128 INFO [train.py:715] (3/8) Epoch 14, batch 16600, loss[loss=0.1462, simple_loss=0.2154, pruned_loss=0.03853, over 4841.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03122, over 974629.92 frames.], batch size: 32, lr: 1.57e-04
+2022-05-08 02:35:13,401 INFO [train.py:715] (3/8) Epoch 14, batch 16650, loss[loss=0.1355, simple_loss=0.2168, pruned_loss=0.02709, over 4890.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.0308, over 973983.32 frames.], batch size: 22, lr: 1.57e-04
+2022-05-08 02:35:55,027 INFO [train.py:715] (3/8) Epoch 14, batch 16700, loss[loss=0.1359, simple_loss=0.2054, pruned_loss=0.03325, over 4972.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2093, pruned_loss=0.03052, over 973993.60 frames.], batch size: 35, lr: 1.57e-04
+2022-05-08 02:36:34,909 INFO [train.py:715] (3/8) Epoch 14, batch 16750, loss[loss=0.1475, simple_loss=0.2141, pruned_loss=0.04044, over 4842.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03117, over 972578.11 frames.], batch size: 30, lr: 1.57e-04
+2022-05-08 02:37:15,262 INFO [train.py:715] (3/8) Epoch 14, batch 16800, loss[loss=0.1484, simple_loss=0.2162, pruned_loss=0.04031, over 4779.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03091, over 972040.28 frames.], batch size: 14, lr: 1.57e-04
+2022-05-08 02:37:54,771 INFO [train.py:715] (3/8) Epoch 14, batch 16850, loss[loss=0.1547, simple_loss=0.2193, pruned_loss=0.04508, over 4973.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.03104, over 972280.82 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 02:38:34,397 INFO [train.py:715] (3/8) Epoch 14, batch 16900, loss[loss=0.1416, simple_loss=0.2115, pruned_loss=0.03589, over 4955.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03075, over 971772.77 frames.], batch size: 39, lr: 1.57e-04
+2022-05-08 02:39:15,369 INFO [train.py:715] (3/8) Epoch 14, batch 16950, loss[loss=0.1147, simple_loss=0.1806, pruned_loss=0.02438, over 4915.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03083, over 972516.02 frames.], batch size: 19, lr: 1.57e-04
+2022-05-08 02:39:56,930 INFO [train.py:715] (3/8) Epoch 14, batch 17000, loss[loss=0.1354, simple_loss=0.2173, pruned_loss=0.02676, over 4927.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.0307, over 972667.10 frames.], batch size: 23, lr: 1.57e-04
+2022-05-08 02:40:37,816 INFO [train.py:715] (3/8) Epoch 14, batch 17050, loss[loss=0.1311, simple_loss=0.2135, pruned_loss=0.02432, over 4800.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03037, over 972691.77 frames.], batch size: 21, lr: 1.57e-04
+2022-05-08 02:41:18,913 INFO [train.py:715] (3/8) Epoch 14, batch 17100, loss[loss=0.1648, simple_loss=0.2391, pruned_loss=0.04527, over 4919.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03062, over 972305.59 frames.], batch size: 29, lr: 1.57e-04
+2022-05-08 02:42:01,005 INFO [train.py:715] (3/8) Epoch 14, batch 17150, loss[loss=0.1789, simple_loss=0.2347, pruned_loss=0.06158, over 4690.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03068, over 972403.91 frames.], batch size: 15, lr: 1.57e-04
+2022-05-08 02:42:41,748 INFO [train.py:715] (3/8) Epoch 14, batch 17200, loss[loss=0.194, simple_loss=0.2688, pruned_loss=0.05961, over 4882.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03076, over 971837.19 frames.], batch size: 22, lr: 1.57e-04
+2022-05-08 02:43:22,733 INFO [train.py:715] (3/8) Epoch 14, batch 17250, loss[loss=0.1441, simple_loss=0.2181, pruned_loss=0.03501, over 4745.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03078, over 972424.69 frames.], batch size: 16, lr: 1.57e-04
+2022-05-08 02:44:04,207 INFO [train.py:715] (3/8) Epoch 14, batch 17300, loss[loss=0.1418, simple_loss=0.2237, pruned_loss=0.02998, over 4815.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03102, over 971480.97 frames.], batch size: 27, lr: 1.57e-04
+2022-05-08 02:44:45,873 INFO [train.py:715] (3/8) Epoch 14, batch 17350, loss[loss=0.1287, simple_loss=0.211, pruned_loss=0.02317, over 4979.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03086, over 971260.52 frames.], batch size: 24, lr: 1.57e-04
+2022-05-08 02:45:26,240 INFO [train.py:715] (3/8) Epoch 14, batch 17400, loss[loss=0.1522, simple_loss=0.2228, pruned_loss=0.04084, over 4857.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.0307, over 971181.13 frames.], batch size: 34, lr: 1.56e-04
+2022-05-08 02:46:07,489 INFO [train.py:715] (3/8) Epoch 14, batch 17450, loss[loss=0.1662, simple_loss=0.2406, pruned_loss=0.04585, over 4987.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.0307, over 970946.26 frames.], batch size: 28, lr: 1.56e-04
+2022-05-08 02:46:49,065 INFO [train.py:715] (3/8) Epoch 14, batch 17500, loss[loss=0.127, simple_loss=0.1975, pruned_loss=0.02821, over 4940.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03022, over 971127.90 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 02:47:29,793 INFO [train.py:715] (3/8) Epoch 14, batch 17550, loss[loss=0.1504, simple_loss=0.2243, pruned_loss=0.03822, over 4760.00 frames.], tot_loss[loss=0.135, simple_loss=0.2094, pruned_loss=0.03028, over 971584.63 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 02:48:10,334 INFO [train.py:715] (3/8) Epoch 14, batch 17600, loss[loss=0.1364, simple_loss=0.2147, pruned_loss=0.02901, over 4841.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03035, over 971786.18 frames.], batch size: 15, lr: 1.56e-04
+2022-05-08 02:48:52,026 INFO [train.py:715] (3/8) Epoch 14, batch 17650, loss[loss=0.1503, simple_loss=0.2303, pruned_loss=0.03514, over 4889.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.03016, over 972299.56 frames.], batch size: 22, lr: 1.56e-04
+2022-05-08 02:49:33,169 INFO [train.py:715] (3/8) Epoch 14, batch 17700, loss[loss=0.1378, simple_loss=0.2069, pruned_loss=0.03434, over 4777.00 frames.], tot_loss[loss=0.134, simple_loss=0.2086, pruned_loss=0.0297, over 972321.03 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 02:50:13,657 INFO [train.py:715] (3/8) Epoch 14, batch 17750, loss[loss=0.1532, simple_loss=0.239, pruned_loss=0.03367, over 4760.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03027, over 971994.37 frames.], batch size: 16, lr: 1.56e-04
+2022-05-08 02:50:55,021 INFO [train.py:715] (3/8) Epoch 14, batch 17800, loss[loss=0.1261, simple_loss=0.1978, pruned_loss=0.02717, over 4899.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03037, over 972992.92 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 02:51:35,974 INFO [train.py:715] (3/8) Epoch 14, batch 17850, loss[loss=0.1411, simple_loss=0.2207, pruned_loss=0.03071, over 4922.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03032, over 971938.85 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 02:52:16,730 INFO [train.py:715] (3/8) Epoch 14, batch 17900, loss[loss=0.1616, simple_loss=0.2275, pruned_loss=0.04784, over 4966.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03019, over 971980.50 frames.], batch size: 15, lr: 1.56e-04
+2022-05-08 02:52:57,208 INFO [train.py:715] (3/8) Epoch 14, batch 17950, loss[loss=0.1556, simple_loss=0.2227, pruned_loss=0.04423, over 4888.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.0305, over 971943.79 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 02:53:38,599 INFO [train.py:715] (3/8) Epoch 14, batch 18000, loss[loss=0.1153, simple_loss=0.1952, pruned_loss=0.01766, over 4951.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03093, over 972278.23 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 02:53:38,600 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 02:53:48,447 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1889, pruned_loss=0.01075, over 914524.00 frames.
+2022-05-08 02:54:29,837 INFO [train.py:715] (3/8) Epoch 14, batch 18050, loss[loss=0.1331, simple_loss=0.2101, pruned_loss=0.02802, over 4984.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03125, over 972089.63 frames.], batch size: 35, lr: 1.56e-04
+2022-05-08 02:55:10,986 INFO [train.py:715] (3/8) Epoch 14, batch 18100, loss[loss=0.1927, simple_loss=0.2803, pruned_loss=0.05257, over 4792.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03103, over 971653.27 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 02:55:52,588 INFO [train.py:715] (3/8) Epoch 14, batch 18150, loss[loss=0.1297, simple_loss=0.1964, pruned_loss=0.03152, over 4860.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03117, over 970937.56 frames.], batch size: 30, lr: 1.56e-04
+2022-05-08 02:56:33,507 INFO [train.py:715] (3/8) Epoch 14, batch 18200, loss[loss=0.1432, simple_loss=0.2127, pruned_loss=0.03683, over 4964.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03102, over 971692.77 frames.], batch size: 35, lr: 1.56e-04
+2022-05-08 02:57:15,452 INFO [train.py:715] (3/8) Epoch 14, batch 18250, loss[loss=0.1146, simple_loss=0.189, pruned_loss=0.02009, over 4766.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03079, over 970464.09 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 02:57:56,896 INFO [train.py:715] (3/8) Epoch 14, batch 18300, loss[loss=0.1565, simple_loss=0.2363, pruned_loss=0.03835, over 4910.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03051, over 971120.36 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 02:58:36,497 INFO [train.py:715] (3/8) Epoch 14, batch 18350, loss[loss=0.1264, simple_loss=0.2041, pruned_loss=0.02433, over 4982.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03071, over 972032.44 frames.], batch size: 25, lr: 1.56e-04
+2022-05-08 02:59:17,360 INFO [train.py:715] (3/8) Epoch 14, batch 18400, loss[loss=0.1585, simple_loss=0.2315, pruned_loss=0.0427, over 4824.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03085, over 972451.17 frames.], batch size: 15, lr: 1.56e-04
+2022-05-08 02:59:57,996 INFO [train.py:715] (3/8) Epoch 14, batch 18450, loss[loss=0.1433, simple_loss=0.2125, pruned_loss=0.03706, over 4918.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.0305, over 972885.72 frames.], batch size: 39, lr: 1.56e-04
+2022-05-08 03:00:38,246 INFO [train.py:715] (3/8) Epoch 14, batch 18500, loss[loss=0.1135, simple_loss=0.1962, pruned_loss=0.01537, over 4958.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03005, over 972431.43 frames.], batch size: 24, lr: 1.56e-04
+2022-05-08 03:01:18,701 INFO [train.py:715] (3/8) Epoch 14, batch 18550, loss[loss=0.1354, simple_loss=0.2004, pruned_loss=0.03521, over 4844.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02972, over 972805.89 frames.], batch size: 13, lr: 1.56e-04
+2022-05-08 03:01:59,559 INFO [train.py:715] (3/8) Epoch 14, batch 18600, loss[loss=0.1327, simple_loss=0.1984, pruned_loss=0.03355, over 4848.00 frames.], tot_loss[loss=0.1345, simple_loss=0.209, pruned_loss=0.03, over 973512.18 frames.], batch size: 30, lr: 1.56e-04
+2022-05-08 03:02:39,863 INFO [train.py:715] (3/8) Epoch 14, batch 18650, loss[loss=0.1461, simple_loss=0.2233, pruned_loss=0.03449, over 4803.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03007, over 974427.42 frames.], batch size: 25, lr: 1.56e-04
+2022-05-08 03:03:20,570 INFO [train.py:715] (3/8) Epoch 14, batch 18700, loss[loss=0.1478, simple_loss=0.2156, pruned_loss=0.04004, over 4775.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03025, over 973610.46 frames.], batch size: 14, lr: 1.56e-04
+2022-05-08 03:04:01,157 INFO [train.py:715] (3/8) Epoch 14, batch 18750, loss[loss=0.1316, simple_loss=0.2122, pruned_loss=0.02546, over 4785.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03041, over 972258.09 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 03:04:41,119 INFO [train.py:715] (3/8) Epoch 14, batch 18800, loss[loss=0.1514, simple_loss=0.2346, pruned_loss=0.03409, over 4963.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03004, over 972574.39 frames.], batch size: 40, lr: 1.56e-04
+2022-05-08 03:05:21,086 INFO [train.py:715] (3/8) Epoch 14, batch 18850, loss[loss=0.1413, simple_loss=0.2176, pruned_loss=0.03251, over 4721.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03044, over 971394.95 frames.], batch size: 15, lr: 1.56e-04
+2022-05-08 03:06:01,830 INFO [train.py:715] (3/8) Epoch 14, batch 18900, loss[loss=0.1414, simple_loss=0.2154, pruned_loss=0.03369, over 4916.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.0308, over 973131.01 frames.], batch size: 23, lr: 1.56e-04
+2022-05-08 03:06:42,902 INFO [train.py:715] (3/8) Epoch 14, batch 18950, loss[loss=0.1294, simple_loss=0.2003, pruned_loss=0.02928, over 4856.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03037, over 974161.93 frames.], batch size: 20, lr: 1.56e-04
+2022-05-08 03:07:23,142 INFO [train.py:715] (3/8) Epoch 14, batch 19000, loss[loss=0.1439, simple_loss=0.2184, pruned_loss=0.03469, over 4970.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03048, over 974003.50 frames.], batch size: 15, lr: 1.56e-04
+2022-05-08 03:08:04,089 INFO [train.py:715] (3/8) Epoch 14, batch 19050, loss[loss=0.1361, simple_loss=0.2082, pruned_loss=0.03202, over 4650.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.0303, over 973422.98 frames.], batch size: 13, lr: 1.56e-04
+2022-05-08 03:08:45,084 INFO [train.py:715] (3/8) Epoch 14, batch 19100, loss[loss=0.1448, simple_loss=0.22, pruned_loss=0.03478, over 4981.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03054, over 973994.65 frames.], batch size: 25, lr: 1.56e-04
+2022-05-08 03:09:25,467 INFO [train.py:715] (3/8) Epoch 14, batch 19150, loss[loss=0.1488, simple_loss=0.2105, pruned_loss=0.04358, over 4864.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03044, over 973441.08 frames.], batch size: 32, lr: 1.56e-04
+2022-05-08 03:10:04,871 INFO [train.py:715] (3/8) Epoch 14, batch 19200, loss[loss=0.1034, simple_loss=0.176, pruned_loss=0.01544, over 4980.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03019, over 973806.95 frames.], batch size: 28, lr: 1.56e-04
+2022-05-08 03:10:45,987 INFO [train.py:715] (3/8) Epoch 14, batch 19250, loss[loss=0.1276, simple_loss=0.1999, pruned_loss=0.02762, over 4819.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03029, over 973992.78 frames.], batch size: 25, lr: 1.56e-04
+2022-05-08 03:11:26,904 INFO [train.py:715] (3/8) Epoch 14, batch 19300, loss[loss=0.1156, simple_loss=0.1973, pruned_loss=0.01698, over 4899.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02988, over 973418.52 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 03:12:06,952 INFO [train.py:715] (3/8) Epoch 14, batch 19350, loss[loss=0.1575, simple_loss=0.2228, pruned_loss=0.04612, over 4864.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03063, over 973629.26 frames.], batch size: 16, lr: 1.56e-04
+2022-05-08 03:12:47,195 INFO [train.py:715] (3/8) Epoch 14, batch 19400, loss[loss=0.1456, simple_loss=0.2312, pruned_loss=0.03004, over 4978.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03035, over 973496.96 frames.], batch size: 40, lr: 1.56e-04
+2022-05-08 03:13:28,647 INFO [train.py:715] (3/8) Epoch 14, batch 19450, loss[loss=0.1632, simple_loss=0.2312, pruned_loss=0.0476, over 4807.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03048, over 973173.01 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 03:14:08,959 INFO [train.py:715] (3/8) Epoch 14, batch 19500, loss[loss=0.138, simple_loss=0.2126, pruned_loss=0.03174, over 4956.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03055, over 973001.21 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 03:14:49,606 INFO [train.py:715] (3/8) Epoch 14, batch 19550, loss[loss=0.1456, simple_loss=0.2219, pruned_loss=0.03464, over 4903.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.0306, over 973498.23 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 03:15:30,062 INFO [train.py:715] (3/8) Epoch 14, batch 19600, loss[loss=0.1142, simple_loss=0.1934, pruned_loss=0.01753, over 4891.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03076, over 972387.46 frames.], batch size: 22, lr: 1.56e-04
+2022-05-08 03:16:10,997 INFO [train.py:715] (3/8) Epoch 14, batch 19650, loss[loss=0.151, simple_loss=0.2167, pruned_loss=0.04263, over 4960.00 frames.], tot_loss[loss=0.135, simple_loss=0.2083, pruned_loss=0.03086, over 972498.65 frames.], batch size: 24, lr: 1.56e-04
+2022-05-08 03:16:51,977 INFO [train.py:715] (3/8) Epoch 14, batch 19700, loss[loss=0.1475, simple_loss=0.2146, pruned_loss=0.04023, over 4863.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.0306, over 971734.42 frames.], batch size: 32, lr: 1.56e-04
+2022-05-08 03:17:32,732 INFO [train.py:715] (3/8) Epoch 14, batch 19750, loss[loss=0.1339, simple_loss=0.2023, pruned_loss=0.03279, over 4923.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03052, over 971875.78 frames.], batch size: 23, lr: 1.56e-04
+2022-05-08 03:18:13,651 INFO [train.py:715] (3/8) Epoch 14, batch 19800, loss[loss=0.1048, simple_loss=0.1887, pruned_loss=0.01039, over 4946.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03089, over 971735.72 frames.], batch size: 29, lr: 1.56e-04
+2022-05-08 03:18:54,282 INFO [train.py:715] (3/8) Epoch 14, batch 19850, loss[loss=0.1289, simple_loss=0.2094, pruned_loss=0.0242, over 4914.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03054, over 971585.93 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 03:19:35,281 INFO [train.py:715] (3/8) Epoch 14, batch 19900, loss[loss=0.1377, simple_loss=0.2071, pruned_loss=0.03415, over 4968.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03063, over 971764.28 frames.], batch size: 35, lr: 1.56e-04
+2022-05-08 03:20:15,390 INFO [train.py:715] (3/8) Epoch 14, batch 19950, loss[loss=0.1559, simple_loss=0.2249, pruned_loss=0.04342, over 4931.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03037, over 972054.16 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 03:20:55,690 INFO [train.py:715] (3/8) Epoch 14, batch 20000, loss[loss=0.1343, simple_loss=0.2014, pruned_loss=0.03359, over 4794.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03083, over 972186.88 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 03:21:35,499 INFO [train.py:715] (3/8) Epoch 14, batch 20050, loss[loss=0.1447, simple_loss=0.2143, pruned_loss=0.03755, over 4773.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03079, over 972098.64 frames.], batch size: 12, lr: 1.56e-04
+2022-05-08 03:22:15,343 INFO [train.py:715] (3/8) Epoch 14, batch 20100, loss[loss=0.1462, simple_loss=0.2205, pruned_loss=0.03595, over 4839.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03072, over 972163.69 frames.], batch size: 20, lr: 1.56e-04
+2022-05-08 03:22:55,786 INFO [train.py:715] (3/8) Epoch 14, batch 20150, loss[loss=0.1484, simple_loss=0.2159, pruned_loss=0.04043, over 4752.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03077, over 971984.42 frames.], batch size: 16, lr: 1.56e-04
+2022-05-08 03:23:35,888 INFO [train.py:715] (3/8) Epoch 14, batch 20200, loss[loss=0.144, simple_loss=0.2289, pruned_loss=0.02958, over 4892.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03066, over 972119.31 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 03:24:16,356 INFO [train.py:715] (3/8) Epoch 14, batch 20250, loss[loss=0.1304, simple_loss=0.2088, pruned_loss=0.02602, over 4757.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03042, over 972918.80 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 03:24:56,502 INFO [train.py:715] (3/8) Epoch 14, batch 20300, loss[loss=0.1279, simple_loss=0.2082, pruned_loss=0.0238, over 4768.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02978, over 972077.06 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 03:25:37,279 INFO [train.py:715] (3/8) Epoch 14, batch 20350, loss[loss=0.1036, simple_loss=0.1786, pruned_loss=0.01429, over 4976.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03037, over 971023.45 frames.], batch size: 14, lr: 1.56e-04
+2022-05-08 03:26:17,610 INFO [train.py:715] (3/8) Epoch 14, batch 20400, loss[loss=0.1479, simple_loss=0.2138, pruned_loss=0.04094, over 4844.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02986, over 971782.33 frames.], batch size: 30, lr: 1.56e-04
+2022-05-08 03:26:58,059 INFO [train.py:715] (3/8) Epoch 14, batch 20450, loss[loss=0.1718, simple_loss=0.2434, pruned_loss=0.05012, over 4779.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03006, over 971561.52 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 03:27:39,216 INFO [train.py:715] (3/8) Epoch 14, batch 20500, loss[loss=0.1491, simple_loss=0.2222, pruned_loss=0.038, over 4912.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03054, over 972300.68 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 03:28:19,571 INFO [train.py:715] (3/8) Epoch 14, batch 20550, loss[loss=0.105, simple_loss=0.1834, pruned_loss=0.01326, over 4890.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.0307, over 971786.85 frames.], batch size: 22, lr: 1.56e-04
+2022-05-08 03:29:00,473 INFO [train.py:715] (3/8) Epoch 14, batch 20600, loss[loss=0.1331, simple_loss=0.2116, pruned_loss=0.02732, over 4903.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03058, over 972243.59 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 03:29:41,269 INFO [train.py:715] (3/8) Epoch 14, batch 20650, loss[loss=0.139, simple_loss=0.206, pruned_loss=0.03593, over 4760.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03068, over 972317.99 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 03:30:22,922 INFO [train.py:715] (3/8) Epoch 14, batch 20700, loss[loss=0.1507, simple_loss=0.232, pruned_loss=0.0347, over 4809.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03032, over 972622.31 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 03:31:03,259 INFO [train.py:715] (3/8) Epoch 14, batch 20750, loss[loss=0.1492, simple_loss=0.2176, pruned_loss=0.04038, over 4901.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02999, over 972873.96 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 03:31:43,458 INFO [train.py:715] (3/8) Epoch 14, batch 20800, loss[loss=0.1334, simple_loss=0.2059, pruned_loss=0.03048, over 4743.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.0301, over 973423.32 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 03:32:24,156 INFO [train.py:715] (3/8) Epoch 14, batch 20850, loss[loss=0.1627, simple_loss=0.2411, pruned_loss=0.04219, over 4853.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03003, over 972695.10 frames.], batch size: 30, lr: 1.56e-04
+2022-05-08 03:33:04,696 INFO [train.py:715] (3/8) Epoch 14, batch 20900, loss[loss=0.1535, simple_loss=0.2245, pruned_loss=0.04127, over 4933.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03023, over 972123.47 frames.], batch size: 23, lr: 1.56e-04
+2022-05-08 03:33:45,371 INFO [train.py:715] (3/8) Epoch 14, batch 20950, loss[loss=0.1283, simple_loss=0.2083, pruned_loss=0.0241, over 4798.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2097, pruned_loss=0.0305, over 972338.23 frames.], batch size: 14, lr: 1.56e-04
+2022-05-08 03:34:25,918 INFO [train.py:715] (3/8) Epoch 14, batch 21000, loss[loss=0.1153, simple_loss=0.1994, pruned_loss=0.01559, over 4935.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.0303, over 972219.05 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 03:34:25,919 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 03:34:36,999 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.1051, simple_loss=0.1889, pruned_loss=0.0107, over 914524.00 frames.
+2022-05-08 03:35:17,901 INFO [train.py:715] (3/8) Epoch 14, batch 21050, loss[loss=0.147, simple_loss=0.2264, pruned_loss=0.03382, over 4818.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03073, over 972306.30 frames.], batch size: 26, lr: 1.56e-04
+2022-05-08 03:35:58,606 INFO [train.py:715] (3/8) Epoch 14, batch 21100, loss[loss=0.139, simple_loss=0.2103, pruned_loss=0.03384, over 4929.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03021, over 971972.71 frames.], batch size: 29, lr: 1.56e-04
+2022-05-08 03:36:39,420 INFO [train.py:715] (3/8) Epoch 14, batch 21150, loss[loss=0.1346, simple_loss=0.2031, pruned_loss=0.03306, over 4800.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03041, over 972645.63 frames.], batch size: 25, lr: 1.56e-04
+2022-05-08 03:37:18,915 INFO [train.py:715] (3/8) Epoch 14, batch 21200, loss[loss=0.1349, simple_loss=0.2001, pruned_loss=0.03486, over 4862.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03054, over 972655.88 frames.], batch size: 32, lr: 1.56e-04
+2022-05-08 03:37:59,327 INFO [train.py:715] (3/8) Epoch 14, batch 21250, loss[loss=0.1326, simple_loss=0.2085, pruned_loss=0.02836, over 4881.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03024, over 973402.92 frames.], batch size: 22, lr: 1.56e-04
+2022-05-08 03:38:39,035 INFO [train.py:715] (3/8) Epoch 14, batch 21300, loss[loss=0.1186, simple_loss=0.1809, pruned_loss=0.02815, over 4769.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03062, over 973016.01 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 03:39:17,956 INFO [train.py:715] (3/8) Epoch 14, batch 21350, loss[loss=0.1447, simple_loss=0.2243, pruned_loss=0.03251, over 4751.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03042, over 972677.41 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 03:39:58,399 INFO [train.py:715] (3/8) Epoch 14, batch 21400, loss[loss=0.1366, simple_loss=0.2063, pruned_loss=0.03343, over 4890.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02993, over 972692.95 frames.], batch size: 22, lr: 1.56e-04
+2022-05-08 03:40:38,652 INFO [train.py:715] (3/8) Epoch 14, batch 21450, loss[loss=0.1237, simple_loss=0.1957, pruned_loss=0.02585, over 4942.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02983, over 972974.69 frames.], batch size: 29, lr: 1.56e-04
+2022-05-08 03:41:18,061 INFO [train.py:715] (3/8) Epoch 14, batch 21500, loss[loss=0.1381, simple_loss=0.2187, pruned_loss=0.02875, over 4829.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02974, over 973065.73 frames.], batch size: 13, lr: 1.56e-04
+2022-05-08 03:41:57,080 INFO [train.py:715] (3/8) Epoch 14, batch 21550, loss[loss=0.1065, simple_loss=0.1822, pruned_loss=0.01537, over 4824.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03035, over 972749.99 frames.], batch size: 12, lr: 1.56e-04
+2022-05-08 03:42:37,071 INFO [train.py:715] (3/8) Epoch 14, batch 21600, loss[loss=0.1174, simple_loss=0.2017, pruned_loss=0.01659, over 4916.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03039, over 972594.68 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 03:43:16,848 INFO [train.py:715] (3/8) Epoch 14, batch 21650, loss[loss=0.1105, simple_loss=0.1875, pruned_loss=0.01672, over 4847.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.03021, over 972385.45 frames.], batch size: 20, lr: 1.56e-04
+2022-05-08 03:43:55,951 INFO [train.py:715] (3/8) Epoch 14, batch 21700, loss[loss=0.117, simple_loss=0.1855, pruned_loss=0.02432, over 4843.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03001, over 972485.16 frames.], batch size: 30, lr: 1.56e-04
+2022-05-08 03:44:36,362 INFO [train.py:715] (3/8) Epoch 14, batch 21750, loss[loss=0.1164, simple_loss=0.1922, pruned_loss=0.02029, over 4798.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02981, over 971591.89 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 03:45:16,754 INFO [train.py:715] (3/8) Epoch 14, batch 21800, loss[loss=0.1171, simple_loss=0.1967, pruned_loss=0.01872, over 4783.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03052, over 971494.92 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 03:45:56,149 INFO [train.py:715] (3/8) Epoch 14, batch 21850, loss[loss=0.137, simple_loss=0.2159, pruned_loss=0.02908, over 4926.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03077, over 971653.50 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 03:46:35,754 INFO [train.py:715] (3/8) Epoch 14, batch 21900, loss[loss=0.139, simple_loss=0.2025, pruned_loss=0.0378, over 4818.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03055, over 971587.38 frames.], batch size: 13, lr: 1.56e-04
+2022-05-08 03:47:16,026 INFO [train.py:715] (3/8) Epoch 14, batch 21950, loss[loss=0.1507, simple_loss=0.212, pruned_loss=0.0447, over 4930.00 frames.], tot_loss[loss=0.135, simple_loss=0.208, pruned_loss=0.03102, over 972321.09 frames.], batch size: 23, lr: 1.56e-04
+2022-05-08 03:47:55,287 INFO [train.py:715] (3/8) Epoch 14, batch 22000, loss[loss=0.1591, simple_loss=0.243, pruned_loss=0.03759, over 4784.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2079, pruned_loss=0.03067, over 971590.85 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 03:48:34,007 INFO [train.py:715] (3/8) Epoch 14, batch 22050, loss[loss=0.1335, simple_loss=0.2111, pruned_loss=0.02792, over 4898.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2079, pruned_loss=0.03048, over 972066.19 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 03:49:14,110 INFO [train.py:715] (3/8) Epoch 14, batch 22100, loss[loss=0.1117, simple_loss=0.186, pruned_loss=0.01869, over 4807.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03047, over 971708.87 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 03:49:53,818 INFO [train.py:715] (3/8) Epoch 14, batch 22150, loss[loss=0.1167, simple_loss=0.1972, pruned_loss=0.01806, over 4908.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03092, over 972654.49 frames.], batch size: 39, lr: 1.56e-04
+2022-05-08 03:50:32,844 INFO [train.py:715] (3/8) Epoch 14, batch 22200, loss[loss=0.1353, simple_loss=0.2008, pruned_loss=0.0349, over 4787.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03064, over 972208.89 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 03:51:12,589 INFO [train.py:715] (3/8) Epoch 14, batch 22250, loss[loss=0.1249, simple_loss=0.2015, pruned_loss=0.0241, over 4852.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03025, over 972434.52 frames.], batch size: 32, lr: 1.56e-04
+2022-05-08 03:51:52,764 INFO [train.py:715] (3/8) Epoch 14, batch 22300, loss[loss=0.08767, simple_loss=0.1596, pruned_loss=0.007879, over 4978.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02969, over 972227.08 frames.], batch size: 14, lr: 1.56e-04
+2022-05-08 03:52:32,252 INFO [train.py:715] (3/8) Epoch 14, batch 22350, loss[loss=0.1608, simple_loss=0.2393, pruned_loss=0.04119, over 4925.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02998, over 972357.86 frames.], batch size: 29, lr: 1.56e-04
+2022-05-08 03:53:11,404 INFO [train.py:715] (3/8) Epoch 14, batch 22400, loss[loss=0.1154, simple_loss=0.1895, pruned_loss=0.02063, over 4818.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02949, over 972220.45 frames.], batch size: 13, lr: 1.56e-04
+2022-05-08 03:53:51,751 INFO [train.py:715] (3/8) Epoch 14, batch 22450, loss[loss=0.1273, simple_loss=0.1969, pruned_loss=0.02888, over 4813.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02996, over 971762.71 frames.], batch size: 14, lr: 1.56e-04
+2022-05-08 03:54:31,162 INFO [train.py:715] (3/8) Epoch 14, batch 22500, loss[loss=0.1612, simple_loss=0.2404, pruned_loss=0.04096, over 4749.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02991, over 971007.85 frames.], batch size: 16, lr: 1.56e-04
+2022-05-08 03:55:10,456 INFO [train.py:715] (3/8) Epoch 14, batch 22550, loss[loss=0.1341, simple_loss=0.2035, pruned_loss=0.03232, over 4779.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02976, over 971109.94 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 03:55:50,812 INFO [train.py:715] (3/8) Epoch 14, batch 22600, loss[loss=0.1086, simple_loss=0.1844, pruned_loss=0.01637, over 4788.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03004, over 971297.73 frames.], batch size: 18, lr: 1.56e-04
+2022-05-08 03:56:31,697 INFO [train.py:715] (3/8) Epoch 14, batch 22650, loss[loss=0.1655, simple_loss=0.2311, pruned_loss=0.05, over 4947.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02929, over 971391.08 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 03:57:11,534 INFO [train.py:715] (3/8) Epoch 14, batch 22700, loss[loss=0.136, simple_loss=0.2101, pruned_loss=0.03102, over 4954.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03006, over 971844.45 frames.], batch size: 35, lr: 1.56e-04
+2022-05-08 03:57:50,666 INFO [train.py:715] (3/8) Epoch 14, batch 22750, loss[loss=0.1268, simple_loss=0.2076, pruned_loss=0.02299, over 4849.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03024, over 972110.30 frames.], batch size: 20, lr: 1.56e-04
+2022-05-08 03:58:32,001 INFO [train.py:715] (3/8) Epoch 14, batch 22800, loss[loss=0.1267, simple_loss=0.1945, pruned_loss=0.02949, over 4839.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03029, over 972930.36 frames.], batch size: 15, lr: 1.56e-04
+2022-05-08 03:59:12,920 INFO [train.py:715] (3/8) Epoch 14, batch 22850, loss[loss=0.1042, simple_loss=0.1752, pruned_loss=0.01657, over 4958.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02969, over 972822.62 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 03:59:53,207 INFO [train.py:715] (3/8) Epoch 14, batch 22900, loss[loss=0.1502, simple_loss=0.2189, pruned_loss=0.04076, over 4839.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02999, over 972615.46 frames.], batch size: 32, lr: 1.56e-04
+2022-05-08 04:00:33,080 INFO [train.py:715] (3/8) Epoch 14, batch 22950, loss[loss=0.1275, simple_loss=0.1993, pruned_loss=0.02786, over 4748.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.0307, over 972239.24 frames.], batch size: 16, lr: 1.56e-04
+2022-05-08 04:01:13,586 INFO [train.py:715] (3/8) Epoch 14, batch 23000, loss[loss=0.1547, simple_loss=0.2186, pruned_loss=0.04539, over 4906.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03145, over 972274.21 frames.], batch size: 17, lr: 1.56e-04
+2022-05-08 04:01:53,103 INFO [train.py:715] (3/8) Epoch 14, batch 23050, loss[loss=0.1253, simple_loss=0.1998, pruned_loss=0.02535, over 4777.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03105, over 972171.02 frames.], batch size: 12, lr: 1.56e-04
+2022-05-08 04:02:32,416 INFO [train.py:715] (3/8) Epoch 14, batch 23100, loss[loss=0.1234, simple_loss=0.1871, pruned_loss=0.02992, over 4967.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.0312, over 972210.57 frames.], batch size: 14, lr: 1.56e-04
+2022-05-08 04:03:13,065 INFO [train.py:715] (3/8) Epoch 14, batch 23150, loss[loss=0.1162, simple_loss=0.1982, pruned_loss=0.01708, over 4804.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03059, over 971838.91 frames.], batch size: 25, lr: 1.56e-04
+2022-05-08 04:03:54,320 INFO [train.py:715] (3/8) Epoch 14, batch 23200, loss[loss=0.1451, simple_loss=0.2196, pruned_loss=0.03533, over 4808.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03098, over 972085.45 frames.], batch size: 25, lr: 1.56e-04
+2022-05-08 04:04:33,069 INFO [train.py:715] (3/8) Epoch 14, batch 23250, loss[loss=0.1456, simple_loss=0.2212, pruned_loss=0.03499, over 4890.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03115, over 972186.37 frames.], batch size: 22, lr: 1.56e-04
+2022-05-08 04:05:13,471 INFO [train.py:715] (3/8) Epoch 14, batch 23300, loss[loss=0.1269, simple_loss=0.2053, pruned_loss=0.0242, over 4931.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03085, over 972403.57 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 04:05:54,162 INFO [train.py:715] (3/8) Epoch 14, batch 23350, loss[loss=0.1407, simple_loss=0.2181, pruned_loss=0.03163, over 4741.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03064, over 972458.41 frames.], batch size: 16, lr: 1.56e-04
+2022-05-08 04:06:33,757 INFO [train.py:715] (3/8) Epoch 14, batch 23400, loss[loss=0.1177, simple_loss=0.1951, pruned_loss=0.02017, over 4932.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03021, over 973227.70 frames.], batch size: 29, lr: 1.56e-04
+2022-05-08 04:07:12,804 INFO [train.py:715] (3/8) Epoch 14, batch 23450, loss[loss=0.1346, simple_loss=0.2077, pruned_loss=0.03073, over 4859.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03047, over 972212.20 frames.], batch size: 20, lr: 1.56e-04
+2022-05-08 04:07:53,403 INFO [train.py:715] (3/8) Epoch 14, batch 23500, loss[loss=0.1246, simple_loss=0.1931, pruned_loss=0.02804, over 4959.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03058, over 972619.99 frames.], batch size: 15, lr: 1.56e-04
+2022-05-08 04:08:34,059 INFO [train.py:715] (3/8) Epoch 14, batch 23550, loss[loss=0.1717, simple_loss=0.2421, pruned_loss=0.05066, over 4769.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03118, over 972215.33 frames.], batch size: 14, lr: 1.56e-04
+2022-05-08 04:09:13,321 INFO [train.py:715] (3/8) Epoch 14, batch 23600, loss[loss=0.1342, simple_loss=0.2032, pruned_loss=0.03258, over 4929.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03153, over 972402.95 frames.], batch size: 23, lr: 1.56e-04
+2022-05-08 04:09:52,600 INFO [train.py:715] (3/8) Epoch 14, batch 23650, loss[loss=0.1119, simple_loss=0.1864, pruned_loss=0.01863, over 4916.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03175, over 972472.29 frames.], batch size: 19, lr: 1.56e-04
+2022-05-08 04:10:32,138 INFO [train.py:715] (3/8) Epoch 14, batch 23700, loss[loss=0.1294, simple_loss=0.2102, pruned_loss=0.02425, over 4977.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03168, over 972695.11 frames.], batch size: 28, lr: 1.56e-04
+2022-05-08 04:11:11,201 INFO [train.py:715] (3/8) Epoch 14, batch 23750, loss[loss=0.1443, simple_loss=0.2168, pruned_loss=0.03589, over 4965.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.0318, over 973156.86 frames.], batch size: 15, lr: 1.56e-04
+2022-05-08 04:11:50,484 INFO [train.py:715] (3/8) Epoch 14, batch 23800, loss[loss=0.132, simple_loss=0.2112, pruned_loss=0.02641, over 4803.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03159, over 972950.50 frames.], batch size: 21, lr: 1.56e-04
+2022-05-08 04:12:30,658 INFO [train.py:715] (3/8) Epoch 14, batch 23850, loss[loss=0.1495, simple_loss=0.2171, pruned_loss=0.04098, over 4980.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03148, over 973242.90 frames.], batch size: 14, lr: 1.56e-04
+2022-05-08 04:13:10,490 INFO [train.py:715] (3/8) Epoch 14, batch 23900, loss[loss=0.1245, simple_loss=0.1895, pruned_loss=0.0297, over 4857.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03126, over 973228.89 frames.], batch size: 20, lr: 1.56e-04
+2022-05-08 04:13:49,756 INFO [train.py:715] (3/8) Epoch 14, batch 23950, loss[loss=0.1294, simple_loss=0.1958, pruned_loss=0.03154, over 4745.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03142, over 972703.23 frames.], batch size: 19, lr: 1.55e-04
+2022-05-08 04:14:30,063 INFO [train.py:715] (3/8) Epoch 14, batch 24000, loss[loss=0.1428, simple_loss=0.2106, pruned_loss=0.03747, over 4814.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03119, over 972957.97 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 04:14:30,064 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 04:14:41,437 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1889, pruned_loss=0.01074, over 914524.00 frames.
+2022-05-08 04:15:21,384 INFO [train.py:715] (3/8) Epoch 14, batch 24050, loss[loss=0.1212, simple_loss=0.1915, pruned_loss=0.02547, over 4865.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03114, over 971898.53 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:16:02,438 INFO [train.py:715] (3/8) Epoch 14, batch 24100, loss[loss=0.1217, simple_loss=0.187, pruned_loss=0.02818, over 4777.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03115, over 971595.77 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 04:16:41,512 INFO [train.py:715] (3/8) Epoch 14, batch 24150, loss[loss=0.1112, simple_loss=0.181, pruned_loss=0.02067, over 4760.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2088, pruned_loss=0.03106, over 970973.43 frames.], batch size: 12, lr: 1.55e-04
+2022-05-08 04:17:21,102 INFO [train.py:715] (3/8) Epoch 14, batch 24200, loss[loss=0.1244, simple_loss=0.1956, pruned_loss=0.02664, over 4793.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.0305, over 972018.17 frames.], batch size: 14, lr: 1.55e-04
+2022-05-08 04:18:01,397 INFO [train.py:715] (3/8) Epoch 14, batch 24250, loss[loss=0.1474, simple_loss=0.2255, pruned_loss=0.03464, over 4819.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.0303, over 972023.13 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 04:18:41,643 INFO [train.py:715] (3/8) Epoch 14, batch 24300, loss[loss=0.1636, simple_loss=0.237, pruned_loss=0.04511, over 4873.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.0303, over 971394.04 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:19:20,605 INFO [train.py:715] (3/8) Epoch 14, batch 24350, loss[loss=0.126, simple_loss=0.1975, pruned_loss=0.02729, over 4756.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03007, over 971230.26 frames.], batch size: 19, lr: 1.55e-04
+2022-05-08 04:20:01,380 INFO [train.py:715] (3/8) Epoch 14, batch 24400, loss[loss=0.1274, simple_loss=0.2024, pruned_loss=0.02617, over 4923.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03022, over 971627.04 frames.], batch size: 23, lr: 1.55e-04
+2022-05-08 04:20:43,004 INFO [train.py:715] (3/8) Epoch 14, batch 24450, loss[loss=0.1523, simple_loss=0.2168, pruned_loss=0.0439, over 4876.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2076, pruned_loss=0.0304, over 972208.99 frames.], batch size: 32, lr: 1.55e-04
+2022-05-08 04:21:22,338 INFO [train.py:715] (3/8) Epoch 14, batch 24500, loss[loss=0.1264, simple_loss=0.2021, pruned_loss=0.0253, over 4939.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2076, pruned_loss=0.03043, over 972031.73 frames.], batch size: 21, lr: 1.55e-04
+2022-05-08 04:22:02,598 INFO [train.py:715] (3/8) Epoch 14, batch 24550, loss[loss=0.1394, simple_loss=0.2211, pruned_loss=0.02885, over 4754.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03024, over 972983.44 frames.], batch size: 19, lr: 1.55e-04
+2022-05-08 04:22:43,754 INFO [train.py:715] (3/8) Epoch 14, batch 24600, loss[loss=0.1775, simple_loss=0.2423, pruned_loss=0.05637, over 4916.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2067, pruned_loss=0.02981, over 973072.14 frames.], batch size: 39, lr: 1.55e-04
+2022-05-08 04:23:25,377 INFO [train.py:715] (3/8) Epoch 14, batch 24650, loss[loss=0.1421, simple_loss=0.2123, pruned_loss=0.03593, over 4888.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02986, over 973102.35 frames.], batch size: 22, lr: 1.55e-04
+2022-05-08 04:24:07,556 INFO [train.py:715] (3/8) Epoch 14, batch 24700, loss[loss=0.1555, simple_loss=0.2285, pruned_loss=0.04126, over 4974.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02992, over 972521.77 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 04:24:48,436 INFO [train.py:715] (3/8) Epoch 14, batch 24750, loss[loss=0.1363, simple_loss=0.2038, pruned_loss=0.03435, over 4643.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02996, over 971844.39 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 04:25:30,054 INFO [train.py:715] (3/8) Epoch 14, batch 24800, loss[loss=0.1412, simple_loss=0.2115, pruned_loss=0.03544, over 4697.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03015, over 971448.55 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 04:26:10,636 INFO [train.py:715] (3/8) Epoch 14, batch 24850, loss[loss=0.117, simple_loss=0.1913, pruned_loss=0.02135, over 4985.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03046, over 971006.55 frames.], batch size: 28, lr: 1.55e-04
+2022-05-08 04:26:50,217 INFO [train.py:715] (3/8) Epoch 14, batch 24900, loss[loss=0.1341, simple_loss=0.2157, pruned_loss=0.0262, over 4818.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2075, pruned_loss=0.03034, over 971628.40 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 04:27:31,157 INFO [train.py:715] (3/8) Epoch 14, batch 24950, loss[loss=0.1972, simple_loss=0.2749, pruned_loss=0.05974, over 4928.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03017, over 971663.00 frames.], batch size: 29, lr: 1.55e-04
+2022-05-08 04:28:12,055 INFO [train.py:715] (3/8) Epoch 14, batch 25000, loss[loss=0.1464, simple_loss=0.2127, pruned_loss=0.04003, over 4749.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03006, over 971559.93 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:28:51,322 INFO [train.py:715] (3/8) Epoch 14, batch 25050, loss[loss=0.1438, simple_loss=0.2105, pruned_loss=0.03853, over 4809.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03019, over 971399.72 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 04:29:32,185 INFO [train.py:715] (3/8) Epoch 14, batch 25100, loss[loss=0.1382, simple_loss=0.2268, pruned_loss=0.02483, over 4973.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03013, over 972775.24 frames.], batch size: 14, lr: 1.55e-04
+2022-05-08 04:30:13,136 INFO [train.py:715] (3/8) Epoch 14, batch 25150, loss[loss=0.1102, simple_loss=0.1857, pruned_loss=0.0174, over 4880.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02978, over 973522.30 frames.], batch size: 22, lr: 1.55e-04
+2022-05-08 04:30:53,337 INFO [train.py:715] (3/8) Epoch 14, batch 25200, loss[loss=0.1533, simple_loss=0.2318, pruned_loss=0.03736, over 4805.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02982, over 973735.88 frames.], batch size: 21, lr: 1.55e-04
+2022-05-08 04:31:31,962 INFO [train.py:715] (3/8) Epoch 14, batch 25250, loss[loss=0.135, simple_loss=0.2051, pruned_loss=0.03242, over 4869.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03032, over 973607.90 frames.], batch size: 32, lr: 1.55e-04
+2022-05-08 04:32:12,614 INFO [train.py:715] (3/8) Epoch 14, batch 25300, loss[loss=0.124, simple_loss=0.1978, pruned_loss=0.02506, over 4792.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03051, over 973470.17 frames.], batch size: 14, lr: 1.55e-04
+2022-05-08 04:32:53,033 INFO [train.py:715] (3/8) Epoch 14, batch 25350, loss[loss=0.1181, simple_loss=0.1916, pruned_loss=0.0223, over 4830.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03036, over 973941.58 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 04:33:31,587 INFO [train.py:715] (3/8) Epoch 14, batch 25400, loss[loss=0.1414, simple_loss=0.218, pruned_loss=0.03237, over 4756.00 frames.], tot_loss[loss=0.136, simple_loss=0.2103, pruned_loss=0.0309, over 972764.72 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:34:11,983 INFO [train.py:715] (3/8) Epoch 14, batch 25450, loss[loss=0.09877, simple_loss=0.1711, pruned_loss=0.0132, over 4742.00 frames.], tot_loss[loss=0.136, simple_loss=0.2103, pruned_loss=0.03086, over 973190.75 frames.], batch size: 12, lr: 1.55e-04
+2022-05-08 04:34:52,386 INFO [train.py:715] (3/8) Epoch 14, batch 25500, loss[loss=0.1398, simple_loss=0.2121, pruned_loss=0.0337, over 4952.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03067, over 974094.57 frames.], batch size: 29, lr: 1.55e-04
+2022-05-08 04:35:31,818 INFO [train.py:715] (3/8) Epoch 14, batch 25550, loss[loss=0.1214, simple_loss=0.1997, pruned_loss=0.02156, over 4883.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03014, over 973549.83 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:36:10,560 INFO [train.py:715] (3/8) Epoch 14, batch 25600, loss[loss=0.1535, simple_loss=0.2412, pruned_loss=0.03293, over 4867.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.0302, over 973466.09 frames.], batch size: 20, lr: 1.55e-04
+2022-05-08 04:36:50,633 INFO [train.py:715] (3/8) Epoch 14, batch 25650, loss[loss=0.1437, simple_loss=0.2196, pruned_loss=0.0339, over 4841.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02985, over 972873.81 frames.], batch size: 26, lr: 1.55e-04
+2022-05-08 04:37:30,746 INFO [train.py:715] (3/8) Epoch 14, batch 25700, loss[loss=0.1619, simple_loss=0.2203, pruned_loss=0.05173, over 4928.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02981, over 973383.16 frames.], batch size: 18, lr: 1.55e-04
+2022-05-08 04:38:09,214 INFO [train.py:715] (3/8) Epoch 14, batch 25750, loss[loss=0.1417, simple_loss=0.224, pruned_loss=0.02972, over 4839.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03002, over 972385.81 frames.], batch size: 30, lr: 1.55e-04
+2022-05-08 04:38:48,531 INFO [train.py:715] (3/8) Epoch 14, batch 25800, loss[loss=0.152, simple_loss=0.2292, pruned_loss=0.03738, over 4989.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03046, over 971879.52 frames.], batch size: 20, lr: 1.55e-04
+2022-05-08 04:39:28,743 INFO [train.py:715] (3/8) Epoch 14, batch 25850, loss[loss=0.1285, simple_loss=0.206, pruned_loss=0.02551, over 4786.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03074, over 971041.35 frames.], batch size: 18, lr: 1.55e-04
+2022-05-08 04:40:07,963 INFO [train.py:715] (3/8) Epoch 14, batch 25900, loss[loss=0.1334, simple_loss=0.2173, pruned_loss=0.02474, over 4904.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03026, over 970977.54 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 04:40:46,739 INFO [train.py:715] (3/8) Epoch 14, batch 25950, loss[loss=0.1374, simple_loss=0.2236, pruned_loss=0.02558, over 4845.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03017, over 971715.92 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 04:41:26,883 INFO [train.py:715] (3/8) Epoch 14, batch 26000, loss[loss=0.1278, simple_loss=0.2028, pruned_loss=0.02638, over 4812.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03026, over 971672.55 frames.], batch size: 21, lr: 1.55e-04
+2022-05-08 04:42:06,869 INFO [train.py:715] (3/8) Epoch 14, batch 26050, loss[loss=0.1521, simple_loss=0.2145, pruned_loss=0.04482, over 4801.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02994, over 971173.69 frames.], batch size: 21, lr: 1.55e-04
+2022-05-08 04:42:44,778 INFO [train.py:715] (3/8) Epoch 14, batch 26100, loss[loss=0.1442, simple_loss=0.2098, pruned_loss=0.03931, over 4921.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03002, over 971549.51 frames.], batch size: 21, lr: 1.55e-04
+2022-05-08 04:43:24,715 INFO [train.py:715] (3/8) Epoch 14, batch 26150, loss[loss=0.1567, simple_loss=0.2304, pruned_loss=0.04148, over 4870.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02991, over 971632.36 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:44:05,199 INFO [train.py:715] (3/8) Epoch 14, batch 26200, loss[loss=0.1819, simple_loss=0.2408, pruned_loss=0.06153, over 4850.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02994, over 971771.76 frames.], batch size: 34, lr: 1.55e-04
+2022-05-08 04:44:44,005 INFO [train.py:715] (3/8) Epoch 14, batch 26250, loss[loss=0.145, simple_loss=0.2206, pruned_loss=0.03464, over 4735.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02996, over 971334.35 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:45:23,185 INFO [train.py:715] (3/8) Epoch 14, batch 26300, loss[loss=0.128, simple_loss=0.2004, pruned_loss=0.02776, over 4765.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02981, over 972355.17 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:46:03,662 INFO [train.py:715] (3/8) Epoch 14, batch 26350, loss[loss=0.09703, simple_loss=0.1683, pruned_loss=0.01288, over 4826.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02991, over 971744.73 frames.], batch size: 27, lr: 1.55e-04
+2022-05-08 04:46:43,192 INFO [train.py:715] (3/8) Epoch 14, batch 26400, loss[loss=0.144, simple_loss=0.2144, pruned_loss=0.03685, over 4695.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03004, over 972064.07 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 04:47:21,824 INFO [train.py:715] (3/8) Epoch 14, batch 26450, loss[loss=0.1224, simple_loss=0.2053, pruned_loss=0.01975, over 4822.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03009, over 971368.22 frames.], batch size: 25, lr: 1.55e-04
+2022-05-08 04:48:02,185 INFO [train.py:715] (3/8) Epoch 14, batch 26500, loss[loss=0.1216, simple_loss=0.1958, pruned_loss=0.02374, over 4795.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02988, over 971583.37 frames.], batch size: 12, lr: 1.55e-04
+2022-05-08 04:48:42,600 INFO [train.py:715] (3/8) Epoch 14, batch 26550, loss[loss=0.1309, simple_loss=0.2025, pruned_loss=0.02968, over 4979.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.0296, over 971475.73 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 04:49:21,895 INFO [train.py:715] (3/8) Epoch 14, batch 26600, loss[loss=0.1181, simple_loss=0.192, pruned_loss=0.02203, over 4791.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02944, over 972128.87 frames.], batch size: 12, lr: 1.55e-04
+2022-05-08 04:50:00,867 INFO [train.py:715] (3/8) Epoch 14, batch 26650, loss[loss=0.1287, simple_loss=0.1982, pruned_loss=0.02964, over 4891.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02983, over 972532.97 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 04:50:41,182 INFO [train.py:715] (3/8) Epoch 14, batch 26700, loss[loss=0.1226, simple_loss=0.2032, pruned_loss=0.02105, over 4823.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.0298, over 971581.41 frames.], batch size: 26, lr: 1.55e-04
+2022-05-08 04:51:21,682 INFO [train.py:715] (3/8) Epoch 14, batch 26750, loss[loss=0.1488, simple_loss=0.215, pruned_loss=0.04133, over 4882.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02992, over 972310.71 frames.], batch size: 22, lr: 1.55e-04
+2022-05-08 04:52:00,698 INFO [train.py:715] (3/8) Epoch 14, batch 26800, loss[loss=0.1322, simple_loss=0.2137, pruned_loss=0.02538, over 4939.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02961, over 972275.49 frames.], batch size: 29, lr: 1.55e-04
+2022-05-08 04:52:40,480 INFO [train.py:715] (3/8) Epoch 14, batch 26850, loss[loss=0.1129, simple_loss=0.1934, pruned_loss=0.01625, over 4876.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02988, over 972164.89 frames.], batch size: 22, lr: 1.55e-04
+2022-05-08 04:53:20,916 INFO [train.py:715] (3/8) Epoch 14, batch 26900, loss[loss=0.1294, simple_loss=0.2054, pruned_loss=0.02666, over 4989.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02965, over 973463.01 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:54:00,759 INFO [train.py:715] (3/8) Epoch 14, batch 26950, loss[loss=0.148, simple_loss=0.2057, pruned_loss=0.04512, over 4651.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.0301, over 973204.49 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 04:54:39,965 INFO [train.py:715] (3/8) Epoch 14, batch 27000, loss[loss=0.1305, simple_loss=0.1954, pruned_loss=0.03277, over 4835.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03035, over 972938.41 frames.], batch size: 30, lr: 1.55e-04
+2022-05-08 04:54:39,966 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 04:54:49,613 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.1049, simple_loss=0.1886, pruned_loss=0.01053, over 914524.00 frames.
+2022-05-08 04:55:29,146 INFO [train.py:715] (3/8) Epoch 14, batch 27050, loss[loss=0.1163, simple_loss=0.1877, pruned_loss=0.02241, over 4939.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03028, over 972523.74 frames.], batch size: 21, lr: 1.55e-04
+2022-05-08 04:56:09,800 INFO [train.py:715] (3/8) Epoch 14, batch 27100, loss[loss=0.1942, simple_loss=0.2624, pruned_loss=0.063, over 4918.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03037, over 972608.02 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 04:56:50,328 INFO [train.py:715] (3/8) Epoch 14, batch 27150, loss[loss=0.1218, simple_loss=0.1934, pruned_loss=0.02515, over 4757.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03005, over 973633.29 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:57:29,047 INFO [train.py:715] (3/8) Epoch 14, batch 27200, loss[loss=0.143, simple_loss=0.2191, pruned_loss=0.03343, over 4784.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.0301, over 973750.78 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 04:58:08,435 INFO [train.py:715] (3/8) Epoch 14, batch 27250, loss[loss=0.1609, simple_loss=0.2331, pruned_loss=0.04436, over 4921.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02993, over 973401.94 frames.], batch size: 18, lr: 1.55e-04
+2022-05-08 04:58:48,577 INFO [train.py:715] (3/8) Epoch 14, batch 27300, loss[loss=0.1323, simple_loss=0.2014, pruned_loss=0.03159, over 4873.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.03, over 972514.62 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 04:59:28,193 INFO [train.py:715] (3/8) Epoch 14, batch 27350, loss[loss=0.1139, simple_loss=0.1918, pruned_loss=0.01799, over 4958.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03008, over 972764.46 frames.], batch size: 24, lr: 1.55e-04
+2022-05-08 05:00:06,593 INFO [train.py:715] (3/8) Epoch 14, batch 27400, loss[loss=0.1175, simple_loss=0.1904, pruned_loss=0.02235, over 4692.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02985, over 973065.19 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 05:00:46,868 INFO [train.py:715] (3/8) Epoch 14, batch 27450, loss[loss=0.1133, simple_loss=0.1843, pruned_loss=0.02117, over 4775.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03034, over 972362.76 frames.], batch size: 18, lr: 1.55e-04
+2022-05-08 05:01:26,698 INFO [train.py:715] (3/8) Epoch 14, batch 27500, loss[loss=0.1811, simple_loss=0.2632, pruned_loss=0.04952, over 4952.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03033, over 973598.69 frames.], batch size: 21, lr: 1.55e-04
+2022-05-08 05:02:05,455 INFO [train.py:715] (3/8) Epoch 14, batch 27550, loss[loss=0.168, simple_loss=0.2384, pruned_loss=0.04885, over 4797.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03008, over 973333.23 frames.], batch size: 21, lr: 1.55e-04
+2022-05-08 05:02:45,161 INFO [train.py:715] (3/8) Epoch 14, batch 27600, loss[loss=0.1618, simple_loss=0.2396, pruned_loss=0.04202, over 4820.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2079, pruned_loss=0.03044, over 973745.36 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 05:03:25,490 INFO [train.py:715] (3/8) Epoch 14, batch 27650, loss[loss=0.1231, simple_loss=0.1979, pruned_loss=0.02413, over 4773.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03073, over 973814.98 frames.], batch size: 18, lr: 1.55e-04
+2022-05-08 05:04:04,755 INFO [train.py:715] (3/8) Epoch 14, batch 27700, loss[loss=0.1202, simple_loss=0.1826, pruned_loss=0.02888, over 4803.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03072, over 973409.89 frames.], batch size: 12, lr: 1.55e-04
+2022-05-08 05:04:43,282 INFO [train.py:715] (3/8) Epoch 14, batch 27750, loss[loss=0.1527, simple_loss=0.2245, pruned_loss=0.04042, over 4885.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03048, over 972696.94 frames.], batch size: 22, lr: 1.55e-04
+2022-05-08 05:05:23,451 INFO [train.py:715] (3/8) Epoch 14, batch 27800, loss[loss=0.1319, simple_loss=0.2044, pruned_loss=0.02971, over 4894.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03016, over 972809.51 frames.], batch size: 19, lr: 1.55e-04
+2022-05-08 05:06:03,188 INFO [train.py:715] (3/8) Epoch 14, batch 27850, loss[loss=0.09859, simple_loss=0.172, pruned_loss=0.01261, over 4917.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03063, over 973163.11 frames.], batch size: 23, lr: 1.55e-04
+2022-05-08 05:06:41,702 INFO [train.py:715] (3/8) Epoch 14, batch 27900, loss[loss=0.1227, simple_loss=0.2002, pruned_loss=0.02257, over 4760.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03083, over 973627.77 frames.], batch size: 19, lr: 1.55e-04
+2022-05-08 05:07:21,727 INFO [train.py:715] (3/8) Epoch 14, batch 27950, loss[loss=0.1089, simple_loss=0.1872, pruned_loss=0.01534, over 4816.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.0304, over 972732.10 frames.], batch size: 25, lr: 1.55e-04
+2022-05-08 05:08:01,577 INFO [train.py:715] (3/8) Epoch 14, batch 28000, loss[loss=0.1112, simple_loss=0.1769, pruned_loss=0.02276, over 4652.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.0307, over 972596.90 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 05:08:40,620 INFO [train.py:715] (3/8) Epoch 14, batch 28050, loss[loss=0.1023, simple_loss=0.1746, pruned_loss=0.01499, over 4934.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03047, over 973275.22 frames.], batch size: 29, lr: 1.55e-04
+2022-05-08 05:09:19,680 INFO [train.py:715] (3/8) Epoch 14, batch 28100, loss[loss=0.1416, simple_loss=0.2179, pruned_loss=0.0326, over 4885.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03079, over 972590.31 frames.], batch size: 22, lr: 1.55e-04
+2022-05-08 05:10:00,234 INFO [train.py:715] (3/8) Epoch 14, batch 28150, loss[loss=0.1123, simple_loss=0.1892, pruned_loss=0.01767, over 4805.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03039, over 972635.94 frames.], batch size: 12, lr: 1.55e-04
+2022-05-08 05:10:39,941 INFO [train.py:715] (3/8) Epoch 14, batch 28200, loss[loss=0.1271, simple_loss=0.2104, pruned_loss=0.02192, over 4963.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03029, over 973114.01 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 05:11:17,981 INFO [train.py:715] (3/8) Epoch 14, batch 28250, loss[loss=0.1303, simple_loss=0.2055, pruned_loss=0.02753, over 4806.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03007, over 972543.52 frames.], batch size: 12, lr: 1.55e-04
+2022-05-08 05:11:58,123 INFO [train.py:715] (3/8) Epoch 14, batch 28300, loss[loss=0.1442, simple_loss=0.213, pruned_loss=0.03775, over 4806.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03008, over 972883.92 frames.], batch size: 24, lr: 1.55e-04
+2022-05-08 05:12:38,002 INFO [train.py:715] (3/8) Epoch 14, batch 28350, loss[loss=0.1679, simple_loss=0.2353, pruned_loss=0.05024, over 4787.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03047, over 972463.60 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 05:13:16,552 INFO [train.py:715] (3/8) Epoch 14, batch 28400, loss[loss=0.1662, simple_loss=0.2315, pruned_loss=0.0504, over 4960.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.0306, over 972820.58 frames.], batch size: 35, lr: 1.55e-04
+2022-05-08 05:13:56,137 INFO [train.py:715] (3/8) Epoch 14, batch 28450, loss[loss=0.09772, simple_loss=0.1716, pruned_loss=0.01191, over 4809.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03081, over 973277.53 frames.], batch size: 12, lr: 1.55e-04
+2022-05-08 05:14:36,399 INFO [train.py:715] (3/8) Epoch 14, batch 28500, loss[loss=0.1364, simple_loss=0.2173, pruned_loss=0.02779, over 4900.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03024, over 973246.07 frames.], batch size: 19, lr: 1.55e-04
+2022-05-08 05:15:15,662 INFO [train.py:715] (3/8) Epoch 14, batch 28550, loss[loss=0.1437, simple_loss=0.2193, pruned_loss=0.03405, over 4767.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03023, over 972295.69 frames.], batch size: 19, lr: 1.55e-04
+2022-05-08 05:15:54,183 INFO [train.py:715] (3/8) Epoch 14, batch 28600, loss[loss=0.1135, simple_loss=0.1865, pruned_loss=0.02031, over 4774.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2097, pruned_loss=0.03051, over 973505.99 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 05:16:34,513 INFO [train.py:715] (3/8) Epoch 14, batch 28650, loss[loss=0.1381, simple_loss=0.2137, pruned_loss=0.03124, over 4814.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03042, over 972501.84 frames.], batch size: 21, lr: 1.55e-04
+2022-05-08 05:17:14,555 INFO [train.py:715] (3/8) Epoch 14, batch 28700, loss[loss=0.1357, simple_loss=0.2201, pruned_loss=0.02566, over 4971.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03063, over 971996.22 frames.], batch size: 14, lr: 1.55e-04
+2022-05-08 05:17:52,650 INFO [train.py:715] (3/8) Epoch 14, batch 28750, loss[loss=0.1283, simple_loss=0.193, pruned_loss=0.03185, over 4967.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03019, over 971818.81 frames.], batch size: 35, lr: 1.55e-04
+2022-05-08 05:18:32,374 INFO [train.py:715] (3/8) Epoch 14, batch 28800, loss[loss=0.1394, simple_loss=0.2182, pruned_loss=0.03033, over 4768.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2089, pruned_loss=0.03005, over 971567.84 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 05:19:12,480 INFO [train.py:715] (3/8) Epoch 14, batch 28850, loss[loss=0.1404, simple_loss=0.2226, pruned_loss=0.02903, over 4912.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02969, over 971765.01 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 05:19:52,381 INFO [train.py:715] (3/8) Epoch 14, batch 28900, loss[loss=0.1372, simple_loss=0.217, pruned_loss=0.02865, over 4779.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03007, over 971521.53 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 05:20:30,224 INFO [train.py:715] (3/8) Epoch 14, batch 28950, loss[loss=0.1805, simple_loss=0.2492, pruned_loss=0.05596, over 4957.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03054, over 970960.56 frames.], batch size: 39, lr: 1.55e-04
+2022-05-08 05:21:10,702 INFO [train.py:715] (3/8) Epoch 14, batch 29000, loss[loss=0.129, simple_loss=0.1898, pruned_loss=0.03411, over 4984.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03041, over 971485.78 frames.], batch size: 14, lr: 1.55e-04
+2022-05-08 05:21:50,335 INFO [train.py:715] (3/8) Epoch 14, batch 29050, loss[loss=0.1534, simple_loss=0.2283, pruned_loss=0.0393, over 4809.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03046, over 970849.05 frames.], batch size: 25, lr: 1.55e-04
+2022-05-08 05:22:29,105 INFO [train.py:715] (3/8) Epoch 14, batch 29100, loss[loss=0.1283, simple_loss=0.2123, pruned_loss=0.02219, over 4771.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03016, over 970437.20 frames.], batch size: 17, lr: 1.55e-04
+2022-05-08 05:23:08,496 INFO [train.py:715] (3/8) Epoch 14, batch 29150, loss[loss=0.1285, simple_loss=0.2055, pruned_loss=0.02579, over 4852.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2092, pruned_loss=0.03011, over 970793.70 frames.], batch size: 20, lr: 1.55e-04
+2022-05-08 05:23:48,532 INFO [train.py:715] (3/8) Epoch 14, batch 29200, loss[loss=0.134, simple_loss=0.2031, pruned_loss=0.03251, over 4867.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.03006, over 970685.17 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 05:24:28,392 INFO [train.py:715] (3/8) Epoch 14, batch 29250, loss[loss=0.127, simple_loss=0.1965, pruned_loss=0.0288, over 4962.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03003, over 971524.24 frames.], batch size: 35, lr: 1.55e-04
+2022-05-08 05:25:06,490 INFO [train.py:715] (3/8) Epoch 14, batch 29300, loss[loss=0.1587, simple_loss=0.2232, pruned_loss=0.04704, over 4786.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.0296, over 972017.73 frames.], batch size: 14, lr: 1.55e-04
+2022-05-08 05:25:46,606 INFO [train.py:715] (3/8) Epoch 14, batch 29350, loss[loss=0.1394, simple_loss=0.2013, pruned_loss=0.0388, over 4695.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02948, over 971670.68 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 05:26:26,516 INFO [train.py:715] (3/8) Epoch 14, batch 29400, loss[loss=0.1132, simple_loss=0.1924, pruned_loss=0.017, over 4840.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2085, pruned_loss=0.02956, over 971237.17 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 05:27:05,390 INFO [train.py:715] (3/8) Epoch 14, batch 29450, loss[loss=0.152, simple_loss=0.2356, pruned_loss=0.03416, over 4843.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02967, over 971608.57 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 05:27:45,241 INFO [train.py:715] (3/8) Epoch 14, batch 29500, loss[loss=0.1237, simple_loss=0.1986, pruned_loss=0.02439, over 4695.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03, over 971508.74 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 05:28:25,577 INFO [train.py:715] (3/8) Epoch 14, batch 29550, loss[loss=0.1099, simple_loss=0.18, pruned_loss=0.01995, over 4815.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.0299, over 973149.65 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 05:29:05,392 INFO [train.py:715] (3/8) Epoch 14, batch 29600, loss[loss=0.1246, simple_loss=0.2011, pruned_loss=0.02403, over 4869.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02998, over 973056.35 frames.], batch size: 22, lr: 1.55e-04
+2022-05-08 05:29:44,397 INFO [train.py:715] (3/8) Epoch 14, batch 29650, loss[loss=0.136, simple_loss=0.2011, pruned_loss=0.03549, over 4924.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03003, over 972688.17 frames.], batch size: 23, lr: 1.55e-04
+2022-05-08 05:30:25,191 INFO [train.py:715] (3/8) Epoch 14, batch 29700, loss[loss=0.1653, simple_loss=0.2179, pruned_loss=0.05634, over 4904.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.0303, over 972246.19 frames.], batch size: 19, lr: 1.55e-04
+2022-05-08 05:31:06,284 INFO [train.py:715] (3/8) Epoch 14, batch 29750, loss[loss=0.1368, simple_loss=0.2071, pruned_loss=0.03324, over 4844.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03089, over 972157.27 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 05:31:45,876 INFO [train.py:715] (3/8) Epoch 14, batch 29800, loss[loss=0.1111, simple_loss=0.1783, pruned_loss=0.02198, over 4830.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2097, pruned_loss=0.03054, over 972121.22 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 05:32:26,699 INFO [train.py:715] (3/8) Epoch 14, batch 29850, loss[loss=0.1111, simple_loss=0.1868, pruned_loss=0.01764, over 4808.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02992, over 972197.90 frames.], batch size: 25, lr: 1.55e-04
+2022-05-08 05:33:06,682 INFO [train.py:715] (3/8) Epoch 14, batch 29900, loss[loss=0.1435, simple_loss=0.2112, pruned_loss=0.03792, over 4960.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2101, pruned_loss=0.03083, over 972253.41 frames.], batch size: 14, lr: 1.55e-04
+2022-05-08 05:33:46,337 INFO [train.py:715] (3/8) Epoch 14, batch 29950, loss[loss=0.119, simple_loss=0.2024, pruned_loss=0.01783, over 4764.00 frames.], tot_loss[loss=0.136, simple_loss=0.2106, pruned_loss=0.03075, over 972757.24 frames.], batch size: 19, lr: 1.55e-04
+2022-05-08 05:34:25,101 INFO [train.py:715] (3/8) Epoch 14, batch 30000, loss[loss=0.1283, simple_loss=0.2079, pruned_loss=0.02435, over 4987.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2103, pruned_loss=0.03081, over 972810.28 frames.], batch size: 28, lr: 1.55e-04
+2022-05-08 05:34:25,102 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 05:34:42,242 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.1052, simple_loss=0.189, pruned_loss=0.01075, over 914524.00 frames.
+2022-05-08 05:35:21,215 INFO [train.py:715] (3/8) Epoch 14, batch 30050, loss[loss=0.1488, simple_loss=0.2279, pruned_loss=0.03489, over 4866.00 frames.], tot_loss[loss=0.1357, simple_loss=0.21, pruned_loss=0.03073, over 972992.61 frames.], batch size: 22, lr: 1.55e-04
+2022-05-08 05:36:01,187 INFO [train.py:715] (3/8) Epoch 14, batch 30100, loss[loss=0.1411, simple_loss=0.2122, pruned_loss=0.03499, over 4774.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.0308, over 972763.66 frames.], batch size: 18, lr: 1.55e-04
+2022-05-08 05:36:42,311 INFO [train.py:715] (3/8) Epoch 14, batch 30150, loss[loss=0.1741, simple_loss=0.2384, pruned_loss=0.05489, over 4697.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03041, over 971296.08 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 05:37:21,244 INFO [train.py:715] (3/8) Epoch 14, batch 30200, loss[loss=0.1415, simple_loss=0.2227, pruned_loss=0.03015, over 4689.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03053, over 970714.02 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 05:38:01,178 INFO [train.py:715] (3/8) Epoch 14, batch 30250, loss[loss=0.1365, simple_loss=0.2038, pruned_loss=0.03462, over 4849.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03002, over 971207.58 frames.], batch size: 13, lr: 1.55e-04
+2022-05-08 05:38:41,857 INFO [train.py:715] (3/8) Epoch 14, batch 30300, loss[loss=0.1614, simple_loss=0.2284, pruned_loss=0.04715, over 4830.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02977, over 971043.44 frames.], batch size: 30, lr: 1.55e-04
+2022-05-08 05:39:21,372 INFO [train.py:715] (3/8) Epoch 14, batch 30350, loss[loss=0.1295, simple_loss=0.1944, pruned_loss=0.03231, over 4710.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03062, over 970413.27 frames.], batch size: 15, lr: 1.55e-04
+2022-05-08 05:40:00,596 INFO [train.py:715] (3/8) Epoch 14, batch 30400, loss[loss=0.1747, simple_loss=0.2404, pruned_loss=0.0545, over 4883.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03051, over 970412.60 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 05:40:40,499 INFO [train.py:715] (3/8) Epoch 14, batch 30450, loss[loss=0.1396, simple_loss=0.2063, pruned_loss=0.03645, over 4938.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03063, over 971780.04 frames.], batch size: 24, lr: 1.55e-04
+2022-05-08 05:41:20,821 INFO [train.py:715] (3/8) Epoch 14, batch 30500, loss[loss=0.1348, simple_loss=0.2153, pruned_loss=0.02718, over 4764.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.0309, over 971439.73 frames.], batch size: 16, lr: 1.55e-04
+2022-05-08 05:41:59,762 INFO [train.py:715] (3/8) Epoch 14, batch 30550, loss[loss=0.1455, simple_loss=0.2168, pruned_loss=0.03705, over 4836.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2104, pruned_loss=0.03099, over 971935.98 frames.], batch size: 15, lr: 1.54e-04
+2022-05-08 05:42:39,646 INFO [train.py:715] (3/8) Epoch 14, batch 30600, loss[loss=0.1303, simple_loss=0.2148, pruned_loss=0.02293, over 4860.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03111, over 972831.93 frames.], batch size: 34, lr: 1.54e-04
+2022-05-08 05:43:20,419 INFO [train.py:715] (3/8) Epoch 14, batch 30650, loss[loss=0.1489, simple_loss=0.2167, pruned_loss=0.04056, over 4890.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.03134, over 971678.52 frames.], batch size: 16, lr: 1.54e-04
+2022-05-08 05:43:59,994 INFO [train.py:715] (3/8) Epoch 14, batch 30700, loss[loss=0.1293, simple_loss=0.2021, pruned_loss=0.02821, over 4941.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03148, over 972067.79 frames.], batch size: 23, lr: 1.54e-04
+2022-05-08 05:44:39,762 INFO [train.py:715] (3/8) Epoch 14, batch 30750, loss[loss=0.1231, simple_loss=0.1907, pruned_loss=0.02778, over 4806.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03123, over 972938.88 frames.], batch size: 21, lr: 1.54e-04
+2022-05-08 05:45:19,658 INFO [train.py:715] (3/8) Epoch 14, batch 30800, loss[loss=0.1237, simple_loss=0.1971, pruned_loss=0.02516, over 4752.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03076, over 972169.69 frames.], batch size: 19, lr: 1.54e-04
+2022-05-08 05:46:00,463 INFO [train.py:715] (3/8) Epoch 14, batch 30850, loss[loss=0.1238, simple_loss=0.1939, pruned_loss=0.02682, over 4818.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03085, over 972393.64 frames.], batch size: 27, lr: 1.54e-04
+2022-05-08 05:46:39,515 INFO [train.py:715] (3/8) Epoch 14, batch 30900, loss[loss=0.1196, simple_loss=0.1872, pruned_loss=0.02597, over 4799.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2093, pruned_loss=0.03024, over 973742.41 frames.], batch size: 17, lr: 1.54e-04
+2022-05-08 05:47:18,044 INFO [train.py:715] (3/8) Epoch 14, batch 30950, loss[loss=0.17, simple_loss=0.2361, pruned_loss=0.05196, over 4911.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2102, pruned_loss=0.03085, over 973913.53 frames.], batch size: 39, lr: 1.54e-04
+2022-05-08 05:47:57,806 INFO [train.py:715] (3/8) Epoch 14, batch 31000, loss[loss=0.1338, simple_loss=0.2135, pruned_loss=0.02709, over 4869.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2109, pruned_loss=0.03105, over 972902.84 frames.], batch size: 20, lr: 1.54e-04
+2022-05-08 05:48:37,488 INFO [train.py:715] (3/8) Epoch 14, batch 31050, loss[loss=0.1406, simple_loss=0.2189, pruned_loss=0.03114, over 4793.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2104, pruned_loss=0.03119, over 972801.43 frames.], batch size: 17, lr: 1.54e-04
+2022-05-08 05:49:17,855 INFO [train.py:715] (3/8) Epoch 14, batch 31100, loss[loss=0.1318, simple_loss=0.2028, pruned_loss=0.03044, over 4778.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03122, over 972076.79 frames.], batch size: 14, lr: 1.54e-04
+2022-05-08 05:49:58,979 INFO [train.py:715] (3/8) Epoch 14, batch 31150, loss[loss=0.1339, simple_loss=0.2182, pruned_loss=0.02479, over 4919.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03042, over 971378.60 frames.], batch size: 23, lr: 1.54e-04
+2022-05-08 05:50:40,129 INFO [train.py:715] (3/8) Epoch 14, batch 31200, loss[loss=0.1358, simple_loss=0.2122, pruned_loss=0.02974, over 4930.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03045, over 971358.90 frames.], batch size: 23, lr: 1.54e-04
+2022-05-08 05:51:19,912 INFO [train.py:715] (3/8) Epoch 14, batch 31250, loss[loss=0.151, simple_loss=0.2311, pruned_loss=0.03549, over 4874.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.0304, over 971595.63 frames.], batch size: 20, lr: 1.54e-04
+2022-05-08 05:52:00,313 INFO [train.py:715] (3/8) Epoch 14, batch 31300, loss[loss=0.1419, simple_loss=0.2037, pruned_loss=0.04004, over 4761.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02989, over 971688.27 frames.], batch size: 19, lr: 1.54e-04
+2022-05-08 05:52:41,155 INFO [train.py:715] (3/8) Epoch 14, batch 31350, loss[loss=0.1517, simple_loss=0.2188, pruned_loss=0.04226, over 4806.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03055, over 971847.68 frames.], batch size: 21, lr: 1.54e-04
+2022-05-08 05:53:21,042 INFO [train.py:715] (3/8) Epoch 14, batch 31400, loss[loss=0.1274, simple_loss=0.1976, pruned_loss=0.02863, over 4761.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03053, over 972418.45 frames.], batch size: 18, lr: 1.54e-04
+2022-05-08 05:54:00,723 INFO [train.py:715] (3/8) Epoch 14, batch 31450, loss[loss=0.1223, simple_loss=0.1936, pruned_loss=0.0255, over 4764.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2083, pruned_loss=0.03074, over 971757.21 frames.], batch size: 19, lr: 1.54e-04
+2022-05-08 05:54:40,752 INFO [train.py:715] (3/8) Epoch 14, batch 31500, loss[loss=0.1562, simple_loss=0.2268, pruned_loss=0.04277, over 4982.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03092, over 972217.16 frames.], batch size: 33, lr: 1.54e-04
+2022-05-08 05:55:21,336 INFO [train.py:715] (3/8) Epoch 14, batch 31550, loss[loss=0.1312, simple_loss=0.1995, pruned_loss=0.03141, over 4773.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03059, over 972409.64 frames.], batch size: 14, lr: 1.54e-04
+2022-05-08 05:56:01,192 INFO [train.py:715] (3/8) Epoch 14, batch 31600, loss[loss=0.1333, simple_loss=0.2157, pruned_loss=0.02546, over 4902.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.0305, over 971897.52 frames.], batch size: 22, lr: 1.54e-04
+2022-05-08 05:56:40,698 INFO [train.py:715] (3/8) Epoch 14, batch 31650, loss[loss=0.1316, simple_loss=0.2108, pruned_loss=0.02618, over 4785.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03065, over 971963.91 frames.], batch size: 17, lr: 1.54e-04
+2022-05-08 05:57:21,075 INFO [train.py:715] (3/8) Epoch 14, batch 31700, loss[loss=0.1495, simple_loss=0.227, pruned_loss=0.036, over 4887.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03087, over 972448.25 frames.], batch size: 32, lr: 1.54e-04
+2022-05-08 05:58:00,667 INFO [train.py:715] (3/8) Epoch 14, batch 31750, loss[loss=0.1162, simple_loss=0.1944, pruned_loss=0.019, over 4932.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03122, over 972017.08 frames.], batch size: 29, lr: 1.54e-04
+2022-05-08 05:58:40,576 INFO [train.py:715] (3/8) Epoch 14, batch 31800, loss[loss=0.1283, simple_loss=0.2009, pruned_loss=0.02787, over 4890.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03107, over 972073.79 frames.], batch size: 19, lr: 1.54e-04
+2022-05-08 05:59:20,881 INFO [train.py:715] (3/8) Epoch 14, batch 31850, loss[loss=0.1257, simple_loss=0.1999, pruned_loss=0.0257, over 4780.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03128, over 971927.86 frames.], batch size: 17, lr: 1.54e-04
+2022-05-08 06:00:01,592 INFO [train.py:715] (3/8) Epoch 14, batch 31900, loss[loss=0.1473, simple_loss=0.2181, pruned_loss=0.03824, over 4979.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03064, over 972081.53 frames.], batch size: 28, lr: 1.54e-04
+2022-05-08 06:00:40,983 INFO [train.py:715] (3/8) Epoch 14, batch 31950, loss[loss=0.1269, simple_loss=0.2117, pruned_loss=0.02112, over 4985.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03054, over 971711.79 frames.], batch size: 25, lr: 1.54e-04
+2022-05-08 06:01:20,565 INFO [train.py:715] (3/8) Epoch 14, batch 32000, loss[loss=0.1274, simple_loss=0.19, pruned_loss=0.03241, over 4963.00 frames.], tot_loss[loss=0.1347, simple_loss=0.208, pruned_loss=0.03064, over 971084.91 frames.], batch size: 14, lr: 1.54e-04
+2022-05-08 06:02:01,144 INFO [train.py:715] (3/8) Epoch 14, batch 32050, loss[loss=0.1352, simple_loss=0.2058, pruned_loss=0.03231, over 4814.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.03063, over 971502.23 frames.], batch size: 27, lr: 1.54e-04
+2022-05-08 06:02:40,618 INFO [train.py:715] (3/8) Epoch 14, batch 32100, loss[loss=0.1181, simple_loss=0.1876, pruned_loss=0.02434, over 4932.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03009, over 971573.03 frames.], batch size: 18, lr: 1.54e-04
+2022-05-08 06:03:20,381 INFO [train.py:715] (3/8) Epoch 14, batch 32150, loss[loss=0.121, simple_loss=0.1989, pruned_loss=0.02153, over 4811.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03007, over 973104.45 frames.], batch size: 26, lr: 1.54e-04
+2022-05-08 06:04:00,810 INFO [train.py:715] (3/8) Epoch 14, batch 32200, loss[loss=0.1382, simple_loss=0.2201, pruned_loss=0.0281, over 4873.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02986, over 972624.29 frames.], batch size: 22, lr: 1.54e-04
+2022-05-08 06:04:41,246 INFO [train.py:715] (3/8) Epoch 14, batch 32250, loss[loss=0.1403, simple_loss=0.2075, pruned_loss=0.03654, over 4906.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.0298, over 973153.55 frames.], batch size: 32, lr: 1.54e-04
+2022-05-08 06:05:20,521 INFO [train.py:715] (3/8) Epoch 14, batch 32300, loss[loss=0.1275, simple_loss=0.2096, pruned_loss=0.02267, over 4968.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.0305, over 974098.99 frames.], batch size: 24, lr: 1.54e-04
+2022-05-08 06:06:00,149 INFO [train.py:715] (3/8) Epoch 14, batch 32350, loss[loss=0.1181, simple_loss=0.1972, pruned_loss=0.01946, over 4984.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03045, over 973833.88 frames.], batch size: 39, lr: 1.54e-04
+2022-05-08 06:06:40,262 INFO [train.py:715] (3/8) Epoch 14, batch 32400, loss[loss=0.1506, simple_loss=0.2246, pruned_loss=0.03828, over 4772.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03061, over 973150.43 frames.], batch size: 19, lr: 1.54e-04
+2022-05-08 06:07:19,951 INFO [train.py:715] (3/8) Epoch 14, batch 32450, loss[loss=0.12, simple_loss=0.1923, pruned_loss=0.02379, over 4840.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03085, over 972918.08 frames.], batch size: 26, lr: 1.54e-04
+2022-05-08 06:07:59,618 INFO [train.py:715] (3/8) Epoch 14, batch 32500, loss[loss=0.1572, simple_loss=0.2314, pruned_loss=0.04153, over 4685.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03093, over 972398.87 frames.], batch size: 15, lr: 1.54e-04
+2022-05-08 06:08:39,988 INFO [train.py:715] (3/8) Epoch 14, batch 32550, loss[loss=0.1255, simple_loss=0.2111, pruned_loss=0.01992, over 4815.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.0308, over 972305.93 frames.], batch size: 25, lr: 1.54e-04
+2022-05-08 06:09:20,734 INFO [train.py:715] (3/8) Epoch 14, batch 32600, loss[loss=0.1157, simple_loss=0.1974, pruned_loss=0.017, over 4937.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03071, over 972598.08 frames.], batch size: 21, lr: 1.54e-04
+2022-05-08 06:10:00,315 INFO [train.py:715] (3/8) Epoch 14, batch 32650, loss[loss=0.1397, simple_loss=0.2149, pruned_loss=0.03219, over 4789.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03043, over 972732.27 frames.], batch size: 18, lr: 1.54e-04
+2022-05-08 06:10:43,606 INFO [train.py:715] (3/8) Epoch 14, batch 32700, loss[loss=0.1524, simple_loss=0.2294, pruned_loss=0.03771, over 4742.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03085, over 973447.81 frames.], batch size: 16, lr: 1.54e-04
+2022-05-08 06:11:24,768 INFO [train.py:715] (3/8) Epoch 14, batch 32750, loss[loss=0.137, simple_loss=0.2077, pruned_loss=0.0331, over 4808.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.0304, over 973880.17 frames.], batch size: 14, lr: 1.54e-04
+2022-05-08 06:12:05,085 INFO [train.py:715] (3/8) Epoch 14, batch 32800, loss[loss=0.139, simple_loss=0.2172, pruned_loss=0.03036, over 4798.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03047, over 973891.32 frames.], batch size: 24, lr: 1.54e-04
+2022-05-08 06:12:45,514 INFO [train.py:715] (3/8) Epoch 14, batch 32850, loss[loss=0.1487, simple_loss=0.2205, pruned_loss=0.03846, over 4987.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03066, over 973838.04 frames.], batch size: 15, lr: 1.54e-04
+2022-05-08 06:13:26,812 INFO [train.py:715] (3/8) Epoch 14, batch 32900, loss[loss=0.1766, simple_loss=0.2298, pruned_loss=0.06175, over 4704.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.0307, over 974364.25 frames.], batch size: 15, lr: 1.54e-04
+2022-05-08 06:14:07,969 INFO [train.py:715] (3/8) Epoch 14, batch 32950, loss[loss=0.1544, simple_loss=0.2271, pruned_loss=0.04086, over 4903.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03067, over 974149.04 frames.], batch size: 17, lr: 1.54e-04
+2022-05-08 06:14:47,670 INFO [train.py:715] (3/8) Epoch 14, batch 33000, loss[loss=0.1308, simple_loss=0.211, pruned_loss=0.02531, over 4807.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03048, over 974195.90 frames.], batch size: 26, lr: 1.54e-04
+2022-05-08 06:14:47,670 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 06:15:25,559 INFO [train.py:742] (3/8) Epoch 14, validation: loss=0.1051, simple_loss=0.1889, pruned_loss=0.01071, over 914524.00 frames.
+2022-05-08 06:16:05,299 INFO [train.py:715] (3/8) Epoch 14, batch 33050, loss[loss=0.1409, simple_loss=0.2127, pruned_loss=0.03456, over 4750.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03012, over 973251.18 frames.], batch size: 16, lr: 1.54e-04
+2022-05-08 06:16:46,145 INFO [train.py:715] (3/8) Epoch 14, batch 33100, loss[loss=0.1359, simple_loss=0.2155, pruned_loss=0.02808, over 4959.00 frames.], tot_loss[loss=0.134, simple_loss=0.2086, pruned_loss=0.02971, over 973683.95 frames.], batch size: 21, lr: 1.54e-04
+2022-05-08 06:17:27,371 INFO [train.py:715] (3/8) Epoch 14, batch 33150, loss[loss=0.1268, simple_loss=0.2032, pruned_loss=0.02518, over 4873.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2091, pruned_loss=0.03001, over 973269.11 frames.], batch size: 16, lr: 1.54e-04
+2022-05-08 06:18:07,432 INFO [train.py:715] (3/8) Epoch 14, batch 33200, loss[loss=0.1308, simple_loss=0.2146, pruned_loss=0.02349, over 4843.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2099, pruned_loss=0.03035, over 974030.29 frames.], batch size: 20, lr: 1.54e-04
+2022-05-08 06:18:47,776 INFO [train.py:715] (3/8) Epoch 14, batch 33250, loss[loss=0.131, simple_loss=0.1999, pruned_loss=0.03105, over 4760.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03041, over 973948.72 frames.], batch size: 19, lr: 1.54e-04
+2022-05-08 06:19:28,527 INFO [train.py:715] (3/8) Epoch 14, batch 33300, loss[loss=0.1158, simple_loss=0.1869, pruned_loss=0.02233, over 4868.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2093, pruned_loss=0.03023, over 973831.47 frames.], batch size: 20, lr: 1.54e-04
+2022-05-08 06:20:09,727 INFO [train.py:715] (3/8) Epoch 14, batch 33350, loss[loss=0.1233, simple_loss=0.1939, pruned_loss=0.02639, over 4908.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03014, over 973721.88 frames.], batch size: 18, lr: 1.54e-04
+2022-05-08 06:20:49,898 INFO [train.py:715] (3/8) Epoch 14, batch 33400, loss[loss=0.1335, simple_loss=0.202, pruned_loss=0.03249, over 4860.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03024, over 973760.65 frames.], batch size: 30, lr: 1.54e-04
+2022-05-08 06:21:30,275 INFO [train.py:715] (3/8) Epoch 14, batch 33450, loss[loss=0.1095, simple_loss=0.1895, pruned_loss=0.01471, over 4925.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03026, over 973449.84 frames.], batch size: 18, lr: 1.54e-04
+2022-05-08 06:22:11,511 INFO [train.py:715] (3/8) Epoch 14, batch 33500, loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02885, over 4943.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.0306, over 973160.56 frames.], batch size: 21, lr: 1.54e-04
+2022-05-08 06:22:51,808 INFO [train.py:715] (3/8) Epoch 14, batch 33550, loss[loss=0.1417, simple_loss=0.2096, pruned_loss=0.03694, over 4864.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03027, over 972619.37 frames.], batch size: 13, lr: 1.54e-04
+2022-05-08 06:23:33,006 INFO [train.py:715] (3/8) Epoch 14, batch 33600, loss[loss=0.1307, simple_loss=0.2034, pruned_loss=0.02897, over 4831.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03046, over 972577.36 frames.], batch size: 26, lr: 1.54e-04
+2022-05-08 06:24:14,051 INFO [train.py:715] (3/8) Epoch 14, batch 33650, loss[loss=0.1262, simple_loss=0.1911, pruned_loss=0.03063, over 4743.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03119, over 972306.55 frames.], batch size: 12, lr: 1.54e-04
+2022-05-08 06:24:54,972 INFO [train.py:715] (3/8) Epoch 14, batch 33700, loss[loss=0.1697, simple_loss=0.2449, pruned_loss=0.04727, over 4944.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03103, over 971222.70 frames.], batch size: 39, lr: 1.54e-04
+2022-05-08 06:25:35,117 INFO [train.py:715] (3/8) Epoch 14, batch 33750, loss[loss=0.1321, simple_loss=0.2161, pruned_loss=0.02409, over 4929.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03071, over 971952.68 frames.], batch size: 39, lr: 1.54e-04
+2022-05-08 06:26:15,687 INFO [train.py:715] (3/8) Epoch 14, batch 33800, loss[loss=0.1202, simple_loss=0.1968, pruned_loss=0.02178, over 4803.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03015, over 972228.02 frames.], batch size: 24, lr: 1.54e-04
+2022-05-08 06:26:56,937 INFO [train.py:715] (3/8) Epoch 14, batch 33850, loss[loss=0.134, simple_loss=0.2062, pruned_loss=0.03093, over 4764.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.0304, over 972358.80 frames.], batch size: 18, lr: 1.54e-04
+2022-05-08 06:27:37,016 INFO [train.py:715] (3/8) Epoch 14, batch 33900, loss[loss=0.1306, simple_loss=0.2118, pruned_loss=0.02472, over 4809.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03007, over 971816.96 frames.], batch size: 25, lr: 1.54e-04
+2022-05-08 06:28:17,550 INFO [train.py:715] (3/8) Epoch 14, batch 33950, loss[loss=0.1636, simple_loss=0.2346, pruned_loss=0.04633, over 4980.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03049, over 972616.53 frames.], batch size: 35, lr: 1.54e-04
+2022-05-08 06:28:58,269 INFO [train.py:715] (3/8) Epoch 14, batch 34000, loss[loss=0.1567, simple_loss=0.2312, pruned_loss=0.0411, over 4783.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.0307, over 971893.00 frames.], batch size: 18, lr: 1.54e-04
+2022-05-08 06:29:39,261 INFO [train.py:715] (3/8) Epoch 14, batch 34050, loss[loss=0.1294, simple_loss=0.2172, pruned_loss=0.02082, over 4931.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2098, pruned_loss=0.03064, over 971846.60 frames.], batch size: 29, lr: 1.54e-04
+2022-05-08 06:30:19,210 INFO [train.py:715] (3/8) Epoch 14, batch 34100, loss[loss=0.1072, simple_loss=0.1768, pruned_loss=0.01879, over 4820.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03086, over 971447.07 frames.], batch size: 13, lr: 1.54e-04
+2022-05-08 06:30:59,703 INFO [train.py:715] (3/8) Epoch 14, batch 34150, loss[loss=0.1215, simple_loss=0.1896, pruned_loss=0.02667, over 4929.00 frames.], tot_loss[loss=0.136, simple_loss=0.21, pruned_loss=0.03103, over 971996.06 frames.], batch size: 29, lr: 1.54e-04
+2022-05-08 06:31:40,135 INFO [train.py:715] (3/8) Epoch 14, batch 34200, loss[loss=0.1194, simple_loss=0.1992, pruned_loss=0.01979, over 4788.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.0307, over 972196.61 frames.], batch size: 24, lr: 1.54e-04
+2022-05-08 06:32:20,302 INFO [train.py:715] (3/8) Epoch 14, batch 34250, loss[loss=0.1137, simple_loss=0.18, pruned_loss=0.02365, over 4817.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03057, over 972048.75 frames.], batch size: 13, lr: 1.54e-04
+2022-05-08 06:33:00,841 INFO [train.py:715] (3/8) Epoch 14, batch 34300, loss[loss=0.1309, simple_loss=0.2026, pruned_loss=0.0296, over 4842.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03084, over 972571.37 frames.], batch size: 32, lr: 1.54e-04
+2022-05-08 06:33:41,487 INFO [train.py:715] (3/8) Epoch 14, batch 34350, loss[loss=0.1449, simple_loss=0.2282, pruned_loss=0.03084, over 4892.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03077, over 972222.44 frames.], batch size: 19, lr: 1.54e-04
+2022-05-08 06:34:22,184 INFO [train.py:715] (3/8) Epoch 14, batch 34400, loss[loss=0.1279, simple_loss=0.2042, pruned_loss=0.02578, over 4873.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03042, over 972065.99 frames.], batch size: 32, lr: 1.54e-04
+2022-05-08 06:35:01,771 INFO [train.py:715] (3/8) Epoch 14, batch 34450, loss[loss=0.1542, simple_loss=0.2371, pruned_loss=0.03569, over 4951.00 frames.], tot_loss[loss=0.136, simple_loss=0.2103, pruned_loss=0.03084, over 971755.80 frames.], batch size: 39, lr: 1.54e-04
+2022-05-08 06:35:42,628 INFO [train.py:715] (3/8) Epoch 14, batch 34500, loss[loss=0.1306, simple_loss=0.2047, pruned_loss=0.02823, over 4968.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2103, pruned_loss=0.03072, over 972016.25 frames.], batch size: 24, lr: 1.54e-04
+2022-05-08 06:36:23,323 INFO [train.py:715] (3/8) Epoch 14, batch 34550, loss[loss=0.1174, simple_loss=0.1964, pruned_loss=0.01914, over 4758.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2106, pruned_loss=0.03104, over 972258.80 frames.], batch size: 19, lr: 1.54e-04
+2022-05-08 06:37:03,436 INFO [train.py:715] (3/8) Epoch 14, batch 34600, loss[loss=0.1538, simple_loss=0.2262, pruned_loss=0.04071, over 4964.00 frames.], tot_loss[loss=0.136, simple_loss=0.2103, pruned_loss=0.0309, over 972398.75 frames.], batch size: 14, lr: 1.54e-04
+2022-05-08 06:37:43,656 INFO [train.py:715] (3/8) Epoch 14, batch 34650, loss[loss=0.1151, simple_loss=0.1897, pruned_loss=0.02028, over 4945.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03077, over 973445.38 frames.], batch size: 23, lr: 1.54e-04
+2022-05-08 06:38:24,398 INFO [train.py:715] (3/8) Epoch 14, batch 34700, loss[loss=0.1145, simple_loss=0.187, pruned_loss=0.02099, over 4992.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03092, over 972939.71 frames.], batch size: 15, lr: 1.54e-04
+2022-05-08 06:39:03,271 INFO [train.py:715] (3/8) Epoch 14, batch 34750, loss[loss=0.1376, simple_loss=0.2193, pruned_loss=0.02795, over 4822.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03135, over 973113.98 frames.], batch size: 26, lr: 1.54e-04
+2022-05-08 06:39:40,046 INFO [train.py:715] (3/8) Epoch 14, batch 34800, loss[loss=0.213, simple_loss=0.2837, pruned_loss=0.07114, over 4934.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03121, over 972972.38 frames.], batch size: 18, lr: 1.54e-04
+2022-05-08 06:40:33,616 INFO [train.py:715] (3/8) Epoch 15, batch 0, loss[loss=0.1397, simple_loss=0.2186, pruned_loss=0.03042, over 4693.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2186, pruned_loss=0.03042, over 4693.00 frames.], batch size: 15, lr: 1.49e-04
+2022-05-08 06:41:12,925 INFO [train.py:715] (3/8) Epoch 15, batch 50, loss[loss=0.1635, simple_loss=0.2262, pruned_loss=0.05036, over 4844.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.0314, over 219661.54 frames.], batch size: 30, lr: 1.49e-04
+2022-05-08 06:41:54,169 INFO [train.py:715] (3/8) Epoch 15, batch 100, loss[loss=0.1414, simple_loss=0.2121, pruned_loss=0.03537, over 4964.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2096, pruned_loss=0.0317, over 386590.10 frames.], batch size: 39, lr: 1.49e-04
+2022-05-08 06:42:35,663 INFO [train.py:715] (3/8) Epoch 15, batch 150, loss[loss=0.1504, simple_loss=0.2183, pruned_loss=0.04125, over 4887.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03121, over 517056.96 frames.], batch size: 19, lr: 1.49e-04
+2022-05-08 06:43:15,919 INFO [train.py:715] (3/8) Epoch 15, batch 200, loss[loss=0.1468, simple_loss=0.2319, pruned_loss=0.03086, over 4949.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03114, over 618272.36 frames.], batch size: 21, lr: 1.49e-04
+2022-05-08 06:43:56,385 INFO [train.py:715] (3/8) Epoch 15, batch 250, loss[loss=0.1379, simple_loss=0.2046, pruned_loss=0.0356, over 4749.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.0313, over 696530.11 frames.], batch size: 12, lr: 1.49e-04
+2022-05-08 06:44:37,769 INFO [train.py:715] (3/8) Epoch 15, batch 300, loss[loss=0.143, simple_loss=0.2077, pruned_loss=0.03916, over 4791.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03161, over 757841.53 frames.], batch size: 14, lr: 1.49e-04
+2022-05-08 06:45:18,789 INFO [train.py:715] (3/8) Epoch 15, batch 350, loss[loss=0.1234, simple_loss=0.1976, pruned_loss=0.02456, over 4753.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03156, over 805785.85 frames.], batch size: 19, lr: 1.49e-04
+2022-05-08 06:45:58,475 INFO [train.py:715] (3/8) Epoch 15, batch 400, loss[loss=0.1435, simple_loss=0.2124, pruned_loss=0.03728, over 4981.00 frames.], tot_loss[loss=0.136, simple_loss=0.2103, pruned_loss=0.03089, over 843858.24 frames.], batch size: 28, lr: 1.49e-04
+2022-05-08 06:46:39,368 INFO [train.py:715] (3/8) Epoch 15, batch 450, loss[loss=0.1577, simple_loss=0.243, pruned_loss=0.03616, over 4954.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2105, pruned_loss=0.03091, over 873059.90 frames.], batch size: 21, lr: 1.49e-04
+2022-05-08 06:47:20,104 INFO [train.py:715] (3/8) Epoch 15, batch 500, loss[loss=0.1423, simple_loss=0.2169, pruned_loss=0.03389, over 4983.00 frames.], tot_loss[loss=0.1355, simple_loss=0.21, pruned_loss=0.03047, over 894705.84 frames.], batch size: 25, lr: 1.49e-04
+2022-05-08 06:48:00,516 INFO [train.py:715] (3/8) Epoch 15, batch 550, loss[loss=0.1422, simple_loss=0.2276, pruned_loss=0.02842, over 4986.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2102, pruned_loss=0.0307, over 912345.30 frames.], batch size: 28, lr: 1.49e-04
+2022-05-08 06:48:40,067 INFO [train.py:715] (3/8) Epoch 15, batch 600, loss[loss=0.1438, simple_loss=0.2129, pruned_loss=0.03734, over 4746.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2099, pruned_loss=0.03034, over 924621.32 frames.], batch size: 16, lr: 1.49e-04
+2022-05-08 06:49:21,142 INFO [train.py:715] (3/8) Epoch 15, batch 650, loss[loss=0.1332, simple_loss=0.2023, pruned_loss=0.03205, over 4863.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2108, pruned_loss=0.03104, over 934754.28 frames.], batch size: 12, lr: 1.49e-04
+2022-05-08 06:50:01,509 INFO [train.py:715] (3/8) Epoch 15, batch 700, loss[loss=0.1369, simple_loss=0.1998, pruned_loss=0.037, over 4809.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03114, over 943161.41 frames.], batch size: 24, lr: 1.49e-04
+2022-05-08 06:50:41,531 INFO [train.py:715] (3/8) Epoch 15, batch 750, loss[loss=0.1283, simple_loss=0.2055, pruned_loss=0.02553, over 4973.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2103, pruned_loss=0.03109, over 949584.84 frames.], batch size: 35, lr: 1.49e-04
+2022-05-08 06:51:22,005 INFO [train.py:715] (3/8) Epoch 15, batch 800, loss[loss=0.1182, simple_loss=0.1906, pruned_loss=0.02287, over 4823.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03059, over 954460.50 frames.], batch size: 25, lr: 1.49e-04
+2022-05-08 06:52:02,786 INFO [train.py:715] (3/8) Epoch 15, batch 850, loss[loss=0.1415, simple_loss=0.2158, pruned_loss=0.03363, over 4895.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.0309, over 957907.81 frames.], batch size: 19, lr: 1.49e-04
+2022-05-08 06:52:43,862 INFO [train.py:715] (3/8) Epoch 15, batch 900, loss[loss=0.1454, simple_loss=0.225, pruned_loss=0.03292, over 4754.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03072, over 961315.25 frames.], batch size: 16, lr: 1.49e-04
+2022-05-08 06:53:23,526 INFO [train.py:715] (3/8) Epoch 15, batch 950, loss[loss=0.1425, simple_loss=0.2205, pruned_loss=0.0323, over 4815.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03049, over 964252.40 frames.], batch size: 25, lr: 1.49e-04
+2022-05-08 06:54:04,075 INFO [train.py:715] (3/8) Epoch 15, batch 1000, loss[loss=0.1495, simple_loss=0.22, pruned_loss=0.03952, over 4694.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03081, over 965612.50 frames.], batch size: 15, lr: 1.49e-04
+2022-05-08 06:54:44,302 INFO [train.py:715] (3/8) Epoch 15, batch 1050, loss[loss=0.1347, simple_loss=0.2035, pruned_loss=0.03295, over 4877.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2078, pruned_loss=0.03057, over 966258.39 frames.], batch size: 16, lr: 1.49e-04
+2022-05-08 06:55:23,586 INFO [train.py:715] (3/8) Epoch 15, batch 1100, loss[loss=0.1717, simple_loss=0.2452, pruned_loss=0.04913, over 4965.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03063, over 967384.04 frames.], batch size: 24, lr: 1.49e-04
+2022-05-08 06:56:04,687 INFO [train.py:715] (3/8) Epoch 15, batch 1150, loss[loss=0.1342, simple_loss=0.2125, pruned_loss=0.02798, over 4741.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03086, over 968005.96 frames.], batch size: 16, lr: 1.49e-04
+2022-05-08 06:56:45,828 INFO [train.py:715] (3/8) Epoch 15, batch 1200, loss[loss=0.1292, simple_loss=0.2042, pruned_loss=0.02705, over 4929.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03076, over 968637.52 frames.], batch size: 18, lr: 1.49e-04
+2022-05-08 06:57:26,539 INFO [train.py:715] (3/8) Epoch 15, batch 1250, loss[loss=0.159, simple_loss=0.2296, pruned_loss=0.04418, over 4852.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03074, over 968749.48 frames.], batch size: 15, lr: 1.49e-04
+2022-05-08 06:58:06,004 INFO [train.py:715] (3/8) Epoch 15, batch 1300, loss[loss=0.1637, simple_loss=0.2221, pruned_loss=0.05264, over 4913.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2074, pruned_loss=0.03054, over 969634.05 frames.], batch size: 18, lr: 1.49e-04
+2022-05-08 06:58:46,684 INFO [train.py:715] (3/8) Epoch 15, batch 1350, loss[loss=0.1441, simple_loss=0.2178, pruned_loss=0.03518, over 4816.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2075, pruned_loss=0.03077, over 970747.93 frames.], batch size: 15, lr: 1.49e-04
+2022-05-08 06:59:27,344 INFO [train.py:715] (3/8) Epoch 15, batch 1400, loss[loss=0.135, simple_loss=0.2197, pruned_loss=0.0252, over 4800.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2082, pruned_loss=0.03073, over 971462.46 frames.], batch size: 21, lr: 1.49e-04
+2022-05-08 07:00:07,539 INFO [train.py:715] (3/8) Epoch 15, batch 1450, loss[loss=0.137, simple_loss=0.2053, pruned_loss=0.0344, over 4900.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03049, over 972333.62 frames.], batch size: 17, lr: 1.49e-04
+2022-05-08 07:00:47,341 INFO [train.py:715] (3/8) Epoch 15, batch 1500, loss[loss=0.105, simple_loss=0.178, pruned_loss=0.016, over 4881.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03031, over 971872.75 frames.], batch size: 19, lr: 1.49e-04
+2022-05-08 07:01:28,517 INFO [train.py:715] (3/8) Epoch 15, batch 1550, loss[loss=0.116, simple_loss=0.1851, pruned_loss=0.02346, over 4814.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03041, over 972037.85 frames.], batch size: 13, lr: 1.49e-04
+2022-05-08 07:02:08,736 INFO [train.py:715] (3/8) Epoch 15, batch 1600, loss[loss=0.1049, simple_loss=0.1864, pruned_loss=0.01172, over 4818.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.0308, over 971863.28 frames.], batch size: 15, lr: 1.49e-04
+2022-05-08 07:02:47,774 INFO [train.py:715] (3/8) Epoch 15, batch 1650, loss[loss=0.1195, simple_loss=0.1917, pruned_loss=0.02363, over 4745.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.0311, over 971377.87 frames.], batch size: 16, lr: 1.49e-04
+2022-05-08 07:03:28,304 INFO [train.py:715] (3/8) Epoch 15, batch 1700, loss[loss=0.1503, simple_loss=0.2227, pruned_loss=0.03891, over 4978.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03063, over 972359.28 frames.], batch size: 35, lr: 1.49e-04
+2022-05-08 07:04:08,885 INFO [train.py:715] (3/8) Epoch 15, batch 1750, loss[loss=0.1584, simple_loss=0.2208, pruned_loss=0.04797, over 4936.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03052, over 972746.94 frames.], batch size: 39, lr: 1.49e-04
+2022-05-08 07:04:48,964 INFO [train.py:715] (3/8) Epoch 15, batch 1800, loss[loss=0.1246, simple_loss=0.1912, pruned_loss=0.02897, over 4819.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03031, over 972910.93 frames.], batch size: 15, lr: 1.49e-04
+2022-05-08 07:05:28,950 INFO [train.py:715] (3/8) Epoch 15, batch 1850, loss[loss=0.1437, simple_loss=0.2196, pruned_loss=0.03392, over 4919.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03002, over 972921.25 frames.], batch size: 23, lr: 1.49e-04
+2022-05-08 07:06:09,784 INFO [train.py:715] (3/8) Epoch 15, batch 1900, loss[loss=0.1478, simple_loss=0.2218, pruned_loss=0.03691, over 4802.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03054, over 973795.78 frames.], batch size: 21, lr: 1.49e-04
+2022-05-08 07:06:50,237 INFO [train.py:715] (3/8) Epoch 15, batch 1950, loss[loss=0.1476, simple_loss=0.2048, pruned_loss=0.04523, over 4957.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03005, over 973676.01 frames.], batch size: 35, lr: 1.49e-04
+2022-05-08 07:07:29,411 INFO [train.py:715] (3/8) Epoch 15, batch 2000, loss[loss=0.1311, simple_loss=0.2116, pruned_loss=0.02529, over 4901.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03028, over 973730.51 frames.], batch size: 19, lr: 1.49e-04
+2022-05-08 07:08:10,506 INFO [train.py:715] (3/8) Epoch 15, batch 2050, loss[loss=0.1606, simple_loss=0.2245, pruned_loss=0.04835, over 4980.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03035, over 974152.86 frames.], batch size: 15, lr: 1.49e-04
+2022-05-08 07:08:50,818 INFO [train.py:715] (3/8) Epoch 15, batch 2100, loss[loss=0.1322, simple_loss=0.1985, pruned_loss=0.03294, over 4978.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.0301, over 972800.56 frames.], batch size: 25, lr: 1.49e-04
+2022-05-08 07:09:30,724 INFO [train.py:715] (3/8) Epoch 15, batch 2150, loss[loss=0.15, simple_loss=0.2328, pruned_loss=0.03359, over 4895.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02997, over 972330.05 frames.], batch size: 19, lr: 1.49e-04
+2022-05-08 07:10:10,980 INFO [train.py:715] (3/8) Epoch 15, batch 2200, loss[loss=0.1225, simple_loss=0.2013, pruned_loss=0.02188, over 4779.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.0297, over 972137.33 frames.], batch size: 18, lr: 1.49e-04
+2022-05-08 07:10:51,405 INFO [train.py:715] (3/8) Epoch 15, batch 2250, loss[loss=0.1313, simple_loss=0.2, pruned_loss=0.0313, over 4949.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02985, over 972636.10 frames.], batch size: 39, lr: 1.49e-04
+2022-05-08 07:11:31,553 INFO [train.py:715] (3/8) Epoch 15, batch 2300, loss[loss=0.1302, simple_loss=0.2048, pruned_loss=0.02777, over 4861.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02932, over 972651.76 frames.], batch size: 16, lr: 1.49e-04
+2022-05-08 07:12:11,044 INFO [train.py:715] (3/8) Epoch 15, batch 2350, loss[loss=0.1055, simple_loss=0.1859, pruned_loss=0.01251, over 4983.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02967, over 973079.27 frames.], batch size: 28, lr: 1.49e-04
+2022-05-08 07:12:51,318 INFO [train.py:715] (3/8) Epoch 15, batch 2400, loss[loss=0.155, simple_loss=0.2273, pruned_loss=0.04132, over 4918.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.0296, over 973046.63 frames.], batch size: 17, lr: 1.49e-04
+2022-05-08 07:13:31,566 INFO [train.py:715] (3/8) Epoch 15, batch 2450, loss[loss=0.1074, simple_loss=0.1816, pruned_loss=0.01656, over 4863.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03002, over 973813.36 frames.], batch size: 20, lr: 1.49e-04
+2022-05-08 07:14:11,490 INFO [train.py:715] (3/8) Epoch 15, batch 2500, loss[loss=0.1786, simple_loss=0.2454, pruned_loss=0.05587, over 4926.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02998, over 973817.45 frames.], batch size: 18, lr: 1.49e-04
+2022-05-08 07:14:50,607 INFO [train.py:715] (3/8) Epoch 15, batch 2550, loss[loss=0.1384, simple_loss=0.2073, pruned_loss=0.03476, over 4791.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03007, over 973929.01 frames.], batch size: 14, lr: 1.49e-04
+2022-05-08 07:15:31,418 INFO [train.py:715] (3/8) Epoch 15, batch 2600, loss[loss=0.1213, simple_loss=0.2004, pruned_loss=0.02105, over 4940.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03015, over 973643.97 frames.], batch size: 21, lr: 1.49e-04
+2022-05-08 07:16:12,104 INFO [train.py:715] (3/8) Epoch 15, batch 2650, loss[loss=0.1059, simple_loss=0.1788, pruned_loss=0.01644, over 4980.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.02999, over 974281.84 frames.], batch size: 14, lr: 1.49e-04
+2022-05-08 07:16:51,596 INFO [train.py:715] (3/8) Epoch 15, batch 2700, loss[loss=0.1189, simple_loss=0.1981, pruned_loss=0.01986, over 4815.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02973, over 973672.17 frames.], batch size: 27, lr: 1.49e-04
+2022-05-08 07:17:33,120 INFO [train.py:715] (3/8) Epoch 15, batch 2750, loss[loss=0.1311, simple_loss=0.218, pruned_loss=0.02205, over 4931.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03009, over 973735.35 frames.], batch size: 29, lr: 1.49e-04
+2022-05-08 07:18:14,189 INFO [train.py:715] (3/8) Epoch 15, batch 2800, loss[loss=0.1302, simple_loss=0.2008, pruned_loss=0.02977, over 4738.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03025, over 973267.51 frames.], batch size: 16, lr: 1.49e-04
+2022-05-08 07:18:54,901 INFO [train.py:715] (3/8) Epoch 15, batch 2850, loss[loss=0.1529, simple_loss=0.2313, pruned_loss=0.03726, over 4793.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03031, over 972961.58 frames.], batch size: 24, lr: 1.49e-04
+2022-05-08 07:19:34,221 INFO [train.py:715] (3/8) Epoch 15, batch 2900, loss[loss=0.1275, simple_loss=0.2058, pruned_loss=0.0246, over 4808.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02999, over 972419.12 frames.], batch size: 21, lr: 1.49e-04
+2022-05-08 07:20:14,829 INFO [train.py:715] (3/8) Epoch 15, batch 2950, loss[loss=0.128, simple_loss=0.2028, pruned_loss=0.02657, over 4791.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02976, over 972292.80 frames.], batch size: 24, lr: 1.49e-04
+2022-05-08 07:20:55,624 INFO [train.py:715] (3/8) Epoch 15, batch 3000, loss[loss=0.126, simple_loss=0.2032, pruned_loss=0.02435, over 4798.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02986, over 972232.08 frames.], batch size: 21, lr: 1.49e-04
+2022-05-08 07:20:55,625 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 07:21:13,096 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.1049, simple_loss=0.1887, pruned_loss=0.01057, over 914524.00 frames.
+2022-05-08 07:21:54,031 INFO [train.py:715] (3/8) Epoch 15, batch 3050, loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02986, over 4816.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03001, over 972306.69 frames.], batch size: 26, lr: 1.49e-04
+2022-05-08 07:22:33,938 INFO [train.py:715] (3/8) Epoch 15, batch 3100, loss[loss=0.1134, simple_loss=0.191, pruned_loss=0.0179, over 4925.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02942, over 971860.24 frames.], batch size: 18, lr: 1.49e-04
+2022-05-08 07:23:14,658 INFO [train.py:715] (3/8) Epoch 15, batch 3150, loss[loss=0.1364, simple_loss=0.207, pruned_loss=0.03292, over 4946.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02994, over 972234.68 frames.], batch size: 21, lr: 1.49e-04
+2022-05-08 07:23:55,204 INFO [train.py:715] (3/8) Epoch 15, batch 3200, loss[loss=0.1298, simple_loss=0.214, pruned_loss=0.02281, over 4798.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.0294, over 971378.10 frames.], batch size: 13, lr: 1.49e-04
+2022-05-08 07:24:35,383 INFO [train.py:715] (3/8) Epoch 15, batch 3250, loss[loss=0.134, simple_loss=0.2139, pruned_loss=0.02707, over 4828.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02936, over 971853.62 frames.], batch size: 15, lr: 1.49e-04
+2022-05-08 07:25:15,330 INFO [train.py:715] (3/8) Epoch 15, batch 3300, loss[loss=0.1307, simple_loss=0.2081, pruned_loss=0.02664, over 4896.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02963, over 972372.39 frames.], batch size: 19, lr: 1.49e-04
+2022-05-08 07:25:56,109 INFO [train.py:715] (3/8) Epoch 15, batch 3350, loss[loss=0.1069, simple_loss=0.1826, pruned_loss=0.01558, over 4777.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.03, over 972247.92 frames.], batch size: 18, lr: 1.49e-04
+2022-05-08 07:26:36,442 INFO [train.py:715] (3/8) Epoch 15, batch 3400, loss[loss=0.1614, simple_loss=0.2381, pruned_loss=0.04235, over 4906.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02961, over 972248.79 frames.], batch size: 17, lr: 1.49e-04
+2022-05-08 07:27:16,664 INFO [train.py:715] (3/8) Epoch 15, batch 3450, loss[loss=0.1553, simple_loss=0.2227, pruned_loss=0.04394, over 4756.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03038, over 971510.11 frames.], batch size: 16, lr: 1.49e-04
+2022-05-08 07:27:56,930 INFO [train.py:715] (3/8) Epoch 15, batch 3500, loss[loss=0.1457, simple_loss=0.2229, pruned_loss=0.03421, over 4904.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.0302, over 971742.50 frames.], batch size: 19, lr: 1.49e-04
+2022-05-08 07:28:37,338 INFO [train.py:715] (3/8) Epoch 15, batch 3550, loss[loss=0.1226, simple_loss=0.1952, pruned_loss=0.02499, over 4819.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03039, over 971824.94 frames.], batch size: 26, lr: 1.49e-04
+2022-05-08 07:29:17,846 INFO [train.py:715] (3/8) Epoch 15, batch 3600, loss[loss=0.126, simple_loss=0.1968, pruned_loss=0.02762, over 4878.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02989, over 971761.51 frames.], batch size: 16, lr: 1.49e-04
+2022-05-08 07:29:57,638 INFO [train.py:715] (3/8) Epoch 15, batch 3650, loss[loss=0.1408, simple_loss=0.2232, pruned_loss=0.02924, over 4911.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02968, over 971288.11 frames.], batch size: 17, lr: 1.48e-04
+2022-05-08 07:30:38,284 INFO [train.py:715] (3/8) Epoch 15, batch 3700, loss[loss=0.1338, simple_loss=0.1972, pruned_loss=0.03524, over 4774.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.03003, over 971008.57 frames.], batch size: 12, lr: 1.48e-04
+2022-05-08 07:31:19,139 INFO [train.py:715] (3/8) Epoch 15, batch 3750, loss[loss=0.1273, simple_loss=0.2106, pruned_loss=0.02198, over 4881.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02929, over 970440.33 frames.], batch size: 22, lr: 1.48e-04
+2022-05-08 07:31:58,798 INFO [train.py:715] (3/8) Epoch 15, batch 3800, loss[loss=0.1148, simple_loss=0.1909, pruned_loss=0.01938, over 4746.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02916, over 971363.28 frames.], batch size: 16, lr: 1.48e-04
+2022-05-08 07:32:38,806 INFO [train.py:715] (3/8) Epoch 15, batch 3850, loss[loss=0.1259, simple_loss=0.2046, pruned_loss=0.02364, over 4768.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02886, over 971280.77 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 07:33:19,085 INFO [train.py:715] (3/8) Epoch 15, batch 3900, loss[loss=0.1191, simple_loss=0.192, pruned_loss=0.02313, over 4646.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.02872, over 971254.27 frames.], batch size: 13, lr: 1.48e-04
+2022-05-08 07:33:58,252 INFO [train.py:715] (3/8) Epoch 15, batch 3950, loss[loss=0.1474, simple_loss=0.2227, pruned_loss=0.03602, over 4913.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02919, over 970950.41 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 07:34:37,990 INFO [train.py:715] (3/8) Epoch 15, batch 4000, loss[loss=0.1278, simple_loss=0.1996, pruned_loss=0.02801, over 4916.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02935, over 970535.35 frames.], batch size: 17, lr: 1.48e-04
+2022-05-08 07:35:17,771 INFO [train.py:715] (3/8) Epoch 15, batch 4050, loss[loss=0.1065, simple_loss=0.1816, pruned_loss=0.01565, over 4877.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02992, over 971039.22 frames.], batch size: 22, lr: 1.48e-04
+2022-05-08 07:35:58,780 INFO [train.py:715] (3/8) Epoch 15, batch 4100, loss[loss=0.1209, simple_loss=0.1825, pruned_loss=0.02966, over 4743.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03014, over 971502.51 frames.], batch size: 16, lr: 1.48e-04
+2022-05-08 07:36:37,611 INFO [train.py:715] (3/8) Epoch 15, batch 4150, loss[loss=0.1319, simple_loss=0.2008, pruned_loss=0.03157, over 4767.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02992, over 972014.61 frames.], batch size: 19, lr: 1.48e-04
+2022-05-08 07:37:17,777 INFO [train.py:715] (3/8) Epoch 15, batch 4200, loss[loss=0.1456, simple_loss=0.2251, pruned_loss=0.03311, over 4688.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03036, over 972699.11 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 07:37:58,203 INFO [train.py:715] (3/8) Epoch 15, batch 4250, loss[loss=0.1511, simple_loss=0.2242, pruned_loss=0.03904, over 4640.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02993, over 973014.40 frames.], batch size: 13, lr: 1.48e-04
+2022-05-08 07:38:38,203 INFO [train.py:715] (3/8) Epoch 15, batch 4300, loss[loss=0.1562, simple_loss=0.2381, pruned_loss=0.0371, over 4777.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03038, over 972780.70 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 07:39:18,225 INFO [train.py:715] (3/8) Epoch 15, batch 4350, loss[loss=0.1438, simple_loss=0.2181, pruned_loss=0.03474, over 4831.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03083, over 972449.30 frames.], batch size: 32, lr: 1.48e-04
+2022-05-08 07:39:58,270 INFO [train.py:715] (3/8) Epoch 15, batch 4400, loss[loss=0.127, simple_loss=0.1983, pruned_loss=0.0279, over 4778.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03085, over 972574.00 frames.], batch size: 17, lr: 1.48e-04
+2022-05-08 07:40:38,802 INFO [train.py:715] (3/8) Epoch 15, batch 4450, loss[loss=0.123, simple_loss=0.2009, pruned_loss=0.02251, over 4973.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03096, over 972262.66 frames.], batch size: 28, lr: 1.48e-04
+2022-05-08 07:41:18,470 INFO [train.py:715] (3/8) Epoch 15, batch 4500, loss[loss=0.1489, simple_loss=0.2101, pruned_loss=0.04383, over 4764.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03041, over 972248.36 frames.], batch size: 19, lr: 1.48e-04
+2022-05-08 07:41:58,879 INFO [train.py:715] (3/8) Epoch 15, batch 4550, loss[loss=0.1288, simple_loss=0.2046, pruned_loss=0.02653, over 4825.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.02995, over 971756.15 frames.], batch size: 26, lr: 1.48e-04
+2022-05-08 07:42:39,500 INFO [train.py:715] (3/8) Epoch 15, batch 4600, loss[loss=0.1389, simple_loss=0.2205, pruned_loss=0.02867, over 4789.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03005, over 971655.55 frames.], batch size: 21, lr: 1.48e-04
+2022-05-08 07:43:19,667 INFO [train.py:715] (3/8) Epoch 15, batch 4650, loss[loss=0.1391, simple_loss=0.2063, pruned_loss=0.03597, over 4886.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03037, over 971431.13 frames.], batch size: 16, lr: 1.48e-04
+2022-05-08 07:43:59,059 INFO [train.py:715] (3/8) Epoch 15, batch 4700, loss[loss=0.1248, simple_loss=0.197, pruned_loss=0.02629, over 4813.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.0306, over 971024.74 frames.], batch size: 27, lr: 1.48e-04
+2022-05-08 07:44:39,328 INFO [train.py:715] (3/8) Epoch 15, batch 4750, loss[loss=0.1464, simple_loss=0.2129, pruned_loss=0.03998, over 4909.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03065, over 972265.96 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 07:45:20,571 INFO [train.py:715] (3/8) Epoch 15, batch 4800, loss[loss=0.1296, simple_loss=0.1983, pruned_loss=0.0305, over 4847.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.0304, over 971760.30 frames.], batch size: 32, lr: 1.48e-04
+2022-05-08 07:46:00,547 INFO [train.py:715] (3/8) Epoch 15, batch 4850, loss[loss=0.1206, simple_loss=0.1933, pruned_loss=0.02401, over 4903.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03089, over 972654.66 frames.], batch size: 17, lr: 1.48e-04
+2022-05-08 07:46:41,241 INFO [train.py:715] (3/8) Epoch 15, batch 4900, loss[loss=0.1205, simple_loss=0.1983, pruned_loss=0.02133, over 4850.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03037, over 972726.91 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 07:47:21,684 INFO [train.py:715] (3/8) Epoch 15, batch 4950, loss[loss=0.1367, simple_loss=0.2057, pruned_loss=0.03383, over 4863.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.03002, over 972159.56 frames.], batch size: 20, lr: 1.48e-04
+2022-05-08 07:48:02,265 INFO [train.py:715] (3/8) Epoch 15, batch 5000, loss[loss=0.1546, simple_loss=0.2347, pruned_loss=0.03727, over 4962.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02988, over 971657.49 frames.], batch size: 24, lr: 1.48e-04
+2022-05-08 07:48:41,753 INFO [train.py:715] (3/8) Epoch 15, batch 5050, loss[loss=0.1338, simple_loss=0.2151, pruned_loss=0.02629, over 4964.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03029, over 971560.77 frames.], batch size: 21, lr: 1.48e-04
+2022-05-08 07:49:21,839 INFO [train.py:715] (3/8) Epoch 15, batch 5100, loss[loss=0.1223, simple_loss=0.2007, pruned_loss=0.02198, over 4783.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02993, over 972143.76 frames.], batch size: 14, lr: 1.48e-04
+2022-05-08 07:50:02,145 INFO [train.py:715] (3/8) Epoch 15, batch 5150, loss[loss=0.1398, simple_loss=0.223, pruned_loss=0.02828, over 4846.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02984, over 971963.31 frames.], batch size: 20, lr: 1.48e-04
+2022-05-08 07:50:42,085 INFO [train.py:715] (3/8) Epoch 15, batch 5200, loss[loss=0.1466, simple_loss=0.2259, pruned_loss=0.03367, over 4949.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03011, over 972807.68 frames.], batch size: 24, lr: 1.48e-04
+2022-05-08 07:51:22,084 INFO [train.py:715] (3/8) Epoch 15, batch 5250, loss[loss=0.136, simple_loss=0.2069, pruned_loss=0.03259, over 4919.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2092, pruned_loss=0.03008, over 972288.74 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 07:52:03,629 INFO [train.py:715] (3/8) Epoch 15, batch 5300, loss[loss=0.1268, simple_loss=0.2059, pruned_loss=0.02385, over 4919.00 frames.], tot_loss[loss=0.135, simple_loss=0.2094, pruned_loss=0.03034, over 972574.60 frames.], batch size: 29, lr: 1.48e-04
+2022-05-08 07:52:45,863 INFO [train.py:715] (3/8) Epoch 15, batch 5350, loss[loss=0.133, simple_loss=0.2002, pruned_loss=0.03289, over 4862.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03039, over 973040.00 frames.], batch size: 20, lr: 1.48e-04
+2022-05-08 07:53:26,856 INFO [train.py:715] (3/8) Epoch 15, batch 5400, loss[loss=0.1757, simple_loss=0.2437, pruned_loss=0.05383, over 4797.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03, over 973610.27 frames.], batch size: 14, lr: 1.48e-04
+2022-05-08 07:54:08,834 INFO [train.py:715] (3/8) Epoch 15, batch 5450, loss[loss=0.127, simple_loss=0.206, pruned_loss=0.02406, over 4840.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02995, over 972428.60 frames.], batch size: 30, lr: 1.48e-04
+2022-05-08 07:54:50,476 INFO [train.py:715] (3/8) Epoch 15, batch 5500, loss[loss=0.1293, simple_loss=0.2169, pruned_loss=0.02081, over 4805.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02971, over 973040.12 frames.], batch size: 21, lr: 1.48e-04
+2022-05-08 07:55:32,152 INFO [train.py:715] (3/8) Epoch 15, batch 5550, loss[loss=0.1241, simple_loss=0.2073, pruned_loss=0.02052, over 4896.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02906, over 973115.73 frames.], batch size: 23, lr: 1.48e-04
+2022-05-08 07:56:12,918 INFO [train.py:715] (3/8) Epoch 15, batch 5600, loss[loss=0.1236, simple_loss=0.2079, pruned_loss=0.01968, over 4836.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02946, over 972655.36 frames.], batch size: 26, lr: 1.48e-04
+2022-05-08 07:56:54,782 INFO [train.py:715] (3/8) Epoch 15, batch 5650, loss[loss=0.1314, simple_loss=0.2074, pruned_loss=0.0277, over 4943.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2085, pruned_loss=0.02966, over 972975.22 frames.], batch size: 29, lr: 1.48e-04
+2022-05-08 07:57:37,295 INFO [train.py:715] (3/8) Epoch 15, batch 5700, loss[loss=0.1188, simple_loss=0.1961, pruned_loss=0.02077, over 4948.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02975, over 972548.88 frames.], batch size: 23, lr: 1.48e-04
+2022-05-08 07:58:18,518 INFO [train.py:715] (3/8) Epoch 15, batch 5750, loss[loss=0.1751, simple_loss=0.2571, pruned_loss=0.04661, over 4973.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03002, over 973187.29 frames.], batch size: 24, lr: 1.48e-04
+2022-05-08 07:58:59,971 INFO [train.py:715] (3/8) Epoch 15, batch 5800, loss[loss=0.1619, simple_loss=0.2283, pruned_loss=0.04775, over 4929.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03067, over 974010.89 frames.], batch size: 35, lr: 1.48e-04
+2022-05-08 07:59:41,228 INFO [train.py:715] (3/8) Epoch 15, batch 5850, loss[loss=0.1205, simple_loss=0.1927, pruned_loss=0.02411, over 4751.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.0309, over 973792.43 frames.], batch size: 16, lr: 1.48e-04
+2022-05-08 08:00:25,525 INFO [train.py:715] (3/8) Epoch 15, batch 5900, loss[loss=0.1554, simple_loss=0.2286, pruned_loss=0.04115, over 4870.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03068, over 972854.30 frames.], batch size: 20, lr: 1.48e-04
+2022-05-08 08:01:06,122 INFO [train.py:715] (3/8) Epoch 15, batch 5950, loss[loss=0.1506, simple_loss=0.2199, pruned_loss=0.04063, over 4765.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03058, over 972655.29 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 08:01:47,605 INFO [train.py:715] (3/8) Epoch 15, batch 6000, loss[loss=0.1081, simple_loss=0.1805, pruned_loss=0.01786, over 4943.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02992, over 972470.51 frames.], batch size: 29, lr: 1.48e-04
+2022-05-08 08:01:47,605 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 08:01:57,158 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01077, over 914524.00 frames.
+2022-05-08 08:02:38,348 INFO [train.py:715] (3/8) Epoch 15, batch 6050, loss[loss=0.1117, simple_loss=0.1847, pruned_loss=0.0194, over 4800.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.0296, over 972801.91 frames.], batch size: 21, lr: 1.48e-04
+2022-05-08 08:03:20,377 INFO [train.py:715] (3/8) Epoch 15, batch 6100, loss[loss=0.1308, simple_loss=0.2126, pruned_loss=0.02448, over 4946.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03027, over 972279.47 frames.], batch size: 29, lr: 1.48e-04
+2022-05-08 08:04:00,137 INFO [train.py:715] (3/8) Epoch 15, batch 6150, loss[loss=0.134, simple_loss=0.2037, pruned_loss=0.03214, over 4850.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03023, over 972644.78 frames.], batch size: 20, lr: 1.48e-04
+2022-05-08 08:04:41,012 INFO [train.py:715] (3/8) Epoch 15, batch 6200, loss[loss=0.1261, simple_loss=0.1994, pruned_loss=0.02641, over 4750.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02987, over 971308.36 frames.], batch size: 16, lr: 1.48e-04
+2022-05-08 08:05:20,641 INFO [train.py:715] (3/8) Epoch 15, batch 6250, loss[loss=0.1451, simple_loss=0.2177, pruned_loss=0.0363, over 4980.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02994, over 971326.69 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 08:06:01,398 INFO [train.py:715] (3/8) Epoch 15, batch 6300, loss[loss=0.1314, simple_loss=0.2176, pruned_loss=0.02265, over 4805.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02963, over 971725.62 frames.], batch size: 25, lr: 1.48e-04
+2022-05-08 08:06:41,238 INFO [train.py:715] (3/8) Epoch 15, batch 6350, loss[loss=0.1274, simple_loss=0.204, pruned_loss=0.0254, over 4972.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02957, over 972082.86 frames.], batch size: 39, lr: 1.48e-04
+2022-05-08 08:07:21,270 INFO [train.py:715] (3/8) Epoch 15, batch 6400, loss[loss=0.1218, simple_loss=0.1995, pruned_loss=0.02207, over 4687.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03001, over 971783.07 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 08:08:01,849 INFO [train.py:715] (3/8) Epoch 15, batch 6450, loss[loss=0.1111, simple_loss=0.1821, pruned_loss=0.02001, over 4971.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02992, over 971237.35 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 08:08:41,388 INFO [train.py:715] (3/8) Epoch 15, batch 6500, loss[loss=0.1446, simple_loss=0.2242, pruned_loss=0.03252, over 4908.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02991, over 971657.57 frames.], batch size: 17, lr: 1.48e-04
+2022-05-08 08:09:21,821 INFO [train.py:715] (3/8) Epoch 15, batch 6550, loss[loss=0.1766, simple_loss=0.2471, pruned_loss=0.0531, over 4894.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03, over 972212.00 frames.], batch size: 19, lr: 1.48e-04
+2022-05-08 08:10:02,129 INFO [train.py:715] (3/8) Epoch 15, batch 6600, loss[loss=0.116, simple_loss=0.1882, pruned_loss=0.02193, over 4735.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03082, over 971646.61 frames.], batch size: 16, lr: 1.48e-04
+2022-05-08 08:10:42,819 INFO [train.py:715] (3/8) Epoch 15, batch 6650, loss[loss=0.1398, simple_loss=0.2081, pruned_loss=0.03574, over 4861.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03023, over 971097.63 frames.], batch size: 32, lr: 1.48e-04
+2022-05-08 08:11:22,258 INFO [train.py:715] (3/8) Epoch 15, batch 6700, loss[loss=0.1349, simple_loss=0.2031, pruned_loss=0.03337, over 4832.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02961, over 970758.59 frames.], batch size: 30, lr: 1.48e-04
+2022-05-08 08:12:02,759 INFO [train.py:715] (3/8) Epoch 15, batch 6750, loss[loss=0.1484, simple_loss=0.2106, pruned_loss=0.04313, over 4771.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02981, over 971089.70 frames.], batch size: 14, lr: 1.48e-04
+2022-05-08 08:12:44,119 INFO [train.py:715] (3/8) Epoch 15, batch 6800, loss[loss=0.1389, simple_loss=0.2151, pruned_loss=0.03137, over 4825.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02975, over 971934.99 frames.], batch size: 25, lr: 1.48e-04
+2022-05-08 08:13:23,952 INFO [train.py:715] (3/8) Epoch 15, batch 6850, loss[loss=0.1069, simple_loss=0.1756, pruned_loss=0.01912, over 4806.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02969, over 971910.94 frames.], batch size: 13, lr: 1.48e-04
+2022-05-08 08:14:03,536 INFO [train.py:715] (3/8) Epoch 15, batch 6900, loss[loss=0.139, simple_loss=0.2188, pruned_loss=0.02957, over 4897.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02973, over 971127.06 frames.], batch size: 19, lr: 1.48e-04
+2022-05-08 08:14:44,362 INFO [train.py:715] (3/8) Epoch 15, batch 6950, loss[loss=0.1429, simple_loss=0.2159, pruned_loss=0.03493, over 4777.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02959, over 970979.43 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 08:15:24,999 INFO [train.py:715] (3/8) Epoch 15, batch 7000, loss[loss=0.1467, simple_loss=0.2227, pruned_loss=0.03538, over 4796.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02961, over 970972.37 frames.], batch size: 25, lr: 1.48e-04
+2022-05-08 08:16:03,965 INFO [train.py:715] (3/8) Epoch 15, batch 7050, loss[loss=0.1408, simple_loss=0.2081, pruned_loss=0.03673, over 4757.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2067, pruned_loss=0.02957, over 971277.88 frames.], batch size: 19, lr: 1.48e-04
+2022-05-08 08:16:44,707 INFO [train.py:715] (3/8) Epoch 15, batch 7100, loss[loss=0.1333, simple_loss=0.1978, pruned_loss=0.03441, over 4893.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.02951, over 971805.75 frames.], batch size: 17, lr: 1.48e-04
+2022-05-08 08:17:25,232 INFO [train.py:715] (3/8) Epoch 15, batch 7150, loss[loss=0.1256, simple_loss=0.2009, pruned_loss=0.02522, over 4786.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02927, over 972347.58 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 08:18:05,135 INFO [train.py:715] (3/8) Epoch 15, batch 7200, loss[loss=0.1602, simple_loss=0.2284, pruned_loss=0.04598, over 4768.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.0296, over 972340.86 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 08:18:44,347 INFO [train.py:715] (3/8) Epoch 15, batch 7250, loss[loss=0.1439, simple_loss=0.2146, pruned_loss=0.03662, over 4971.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02989, over 973414.00 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 08:19:25,090 INFO [train.py:715] (3/8) Epoch 15, batch 7300, loss[loss=0.1115, simple_loss=0.1894, pruned_loss=0.01677, over 4853.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02949, over 973376.64 frames.], batch size: 20, lr: 1.48e-04
+2022-05-08 08:20:06,079 INFO [train.py:715] (3/8) Epoch 15, batch 7350, loss[loss=0.1286, simple_loss=0.2002, pruned_loss=0.02846, over 4822.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02964, over 972726.95 frames.], batch size: 25, lr: 1.48e-04
+2022-05-08 08:20:45,519 INFO [train.py:715] (3/8) Epoch 15, batch 7400, loss[loss=0.1248, simple_loss=0.1857, pruned_loss=0.03191, over 4862.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03018, over 972943.12 frames.], batch size: 12, lr: 1.48e-04
+2022-05-08 08:21:25,992 INFO [train.py:715] (3/8) Epoch 15, batch 7450, loss[loss=0.1296, simple_loss=0.2051, pruned_loss=0.02707, over 4914.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02995, over 972492.03 frames.], batch size: 17, lr: 1.48e-04
+2022-05-08 08:22:06,379 INFO [train.py:715] (3/8) Epoch 15, batch 7500, loss[loss=0.1254, simple_loss=0.2024, pruned_loss=0.02417, over 4843.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02982, over 972206.04 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 08:22:46,668 INFO [train.py:715] (3/8) Epoch 15, batch 7550, loss[loss=0.1464, simple_loss=0.2232, pruned_loss=0.03479, over 4879.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03001, over 971514.11 frames.], batch size: 22, lr: 1.48e-04
+2022-05-08 08:23:25,908 INFO [train.py:715] (3/8) Epoch 15, batch 7600, loss[loss=0.1211, simple_loss=0.1966, pruned_loss=0.02274, over 4799.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02965, over 971686.56 frames.], batch size: 21, lr: 1.48e-04
+2022-05-08 08:24:05,914 INFO [train.py:715] (3/8) Epoch 15, batch 7650, loss[loss=0.1105, simple_loss=0.1909, pruned_loss=0.01504, over 4683.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02975, over 971388.59 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 08:24:45,957 INFO [train.py:715] (3/8) Epoch 15, batch 7700, loss[loss=0.121, simple_loss=0.19, pruned_loss=0.02599, over 4817.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2085, pruned_loss=0.02967, over 971363.90 frames.], batch size: 27, lr: 1.48e-04
+2022-05-08 08:25:24,894 INFO [train.py:715] (3/8) Epoch 15, batch 7750, loss[loss=0.1646, simple_loss=0.2375, pruned_loss=0.0459, over 4820.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.0295, over 972119.31 frames.], batch size: 25, lr: 1.48e-04
+2022-05-08 08:26:04,549 INFO [train.py:715] (3/8) Epoch 15, batch 7800, loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02871, over 4921.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02976, over 972223.32 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 08:26:43,772 INFO [train.py:715] (3/8) Epoch 15, batch 7850, loss[loss=0.1169, simple_loss=0.1852, pruned_loss=0.02425, over 4864.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03006, over 972453.50 frames.], batch size: 32, lr: 1.48e-04
+2022-05-08 08:27:23,766 INFO [train.py:715] (3/8) Epoch 15, batch 7900, loss[loss=0.1403, simple_loss=0.2065, pruned_loss=0.03705, over 4973.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03056, over 972654.96 frames.], batch size: 35, lr: 1.48e-04
+2022-05-08 08:28:01,921 INFO [train.py:715] (3/8) Epoch 15, batch 7950, loss[loss=0.1295, simple_loss=0.2017, pruned_loss=0.0287, over 4823.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.0307, over 972355.91 frames.], batch size: 26, lr: 1.48e-04
+2022-05-08 08:28:41,235 INFO [train.py:715] (3/8) Epoch 15, batch 8000, loss[loss=0.1219, simple_loss=0.1944, pruned_loss=0.02469, over 4985.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03057, over 971937.65 frames.], batch size: 35, lr: 1.48e-04
+2022-05-08 08:29:20,799 INFO [train.py:715] (3/8) Epoch 15, batch 8050, loss[loss=0.1211, simple_loss=0.2018, pruned_loss=0.02019, over 4910.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03086, over 972295.37 frames.], batch size: 23, lr: 1.48e-04
+2022-05-08 08:29:59,765 INFO [train.py:715] (3/8) Epoch 15, batch 8100, loss[loss=0.135, simple_loss=0.2033, pruned_loss=0.03333, over 4691.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03061, over 972141.10 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 08:30:38,768 INFO [train.py:715] (3/8) Epoch 15, batch 8150, loss[loss=0.1169, simple_loss=0.1943, pruned_loss=0.01979, over 4925.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03043, over 971865.26 frames.], batch size: 29, lr: 1.48e-04
+2022-05-08 08:31:18,843 INFO [train.py:715] (3/8) Epoch 15, batch 8200, loss[loss=0.1135, simple_loss=0.2005, pruned_loss=0.01325, over 4809.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03039, over 971480.52 frames.], batch size: 21, lr: 1.48e-04
+2022-05-08 08:31:57,571 INFO [train.py:715] (3/8) Epoch 15, batch 8250, loss[loss=0.1533, simple_loss=0.2165, pruned_loss=0.04505, over 4983.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03068, over 971024.97 frames.], batch size: 35, lr: 1.48e-04
+2022-05-08 08:32:36,547 INFO [train.py:715] (3/8) Epoch 15, batch 8300, loss[loss=0.1525, simple_loss=0.23, pruned_loss=0.03749, over 4868.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03035, over 970978.72 frames.], batch size: 22, lr: 1.48e-04
+2022-05-08 08:33:15,772 INFO [train.py:715] (3/8) Epoch 15, batch 8350, loss[loss=0.142, simple_loss=0.2041, pruned_loss=0.03998, over 4877.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03049, over 971177.63 frames.], batch size: 16, lr: 1.48e-04
+2022-05-08 08:33:55,970 INFO [train.py:715] (3/8) Epoch 15, batch 8400, loss[loss=0.1199, simple_loss=0.1883, pruned_loss=0.02573, over 4987.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03054, over 972120.22 frames.], batch size: 31, lr: 1.48e-04
+2022-05-08 08:34:35,512 INFO [train.py:715] (3/8) Epoch 15, batch 8450, loss[loss=0.1316, simple_loss=0.1952, pruned_loss=0.03396, over 4965.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.0307, over 973047.45 frames.], batch size: 14, lr: 1.48e-04
+2022-05-08 08:35:14,651 INFO [train.py:715] (3/8) Epoch 15, batch 8500, loss[loss=0.1025, simple_loss=0.175, pruned_loss=0.01495, over 4781.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03041, over 973019.79 frames.], batch size: 12, lr: 1.48e-04
+2022-05-08 08:35:54,836 INFO [train.py:715] (3/8) Epoch 15, batch 8550, loss[loss=0.1189, simple_loss=0.1943, pruned_loss=0.02175, over 4779.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03017, over 973231.23 frames.], batch size: 14, lr: 1.48e-04
+2022-05-08 08:36:33,509 INFO [train.py:715] (3/8) Epoch 15, batch 8600, loss[loss=0.1543, simple_loss=0.2163, pruned_loss=0.04611, over 4778.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02991, over 973171.55 frames.], batch size: 14, lr: 1.48e-04
+2022-05-08 08:37:12,322 INFO [train.py:715] (3/8) Epoch 15, batch 8650, loss[loss=0.1298, simple_loss=0.2026, pruned_loss=0.02851, over 4874.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2069, pruned_loss=0.03021, over 972800.42 frames.], batch size: 22, lr: 1.48e-04
+2022-05-08 08:37:51,174 INFO [train.py:715] (3/8) Epoch 15, batch 8700, loss[loss=0.116, simple_loss=0.1895, pruned_loss=0.02124, over 4836.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2069, pruned_loss=0.03025, over 972819.52 frames.], batch size: 12, lr: 1.48e-04
+2022-05-08 08:38:30,425 INFO [train.py:715] (3/8) Epoch 15, batch 8750, loss[loss=0.1206, simple_loss=0.1956, pruned_loss=0.02282, over 4909.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2067, pruned_loss=0.03011, over 972019.76 frames.], batch size: 19, lr: 1.48e-04
+2022-05-08 08:39:08,912 INFO [train.py:715] (3/8) Epoch 15, batch 8800, loss[loss=0.116, simple_loss=0.1886, pruned_loss=0.02174, over 4896.00 frames.], tot_loss[loss=0.1336, simple_loss=0.207, pruned_loss=0.03013, over 972806.97 frames.], batch size: 17, lr: 1.48e-04
+2022-05-08 08:39:47,406 INFO [train.py:715] (3/8) Epoch 15, batch 8850, loss[loss=0.1202, simple_loss=0.2015, pruned_loss=0.0194, over 4804.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2072, pruned_loss=0.03025, over 972951.72 frames.], batch size: 21, lr: 1.48e-04
+2022-05-08 08:40:26,833 INFO [train.py:715] (3/8) Epoch 15, batch 8900, loss[loss=0.1497, simple_loss=0.2193, pruned_loss=0.04003, over 4853.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2067, pruned_loss=0.03007, over 972654.56 frames.], batch size: 34, lr: 1.48e-04
+2022-05-08 08:41:06,366 INFO [train.py:715] (3/8) Epoch 15, batch 8950, loss[loss=0.1111, simple_loss=0.1887, pruned_loss=0.01673, over 4842.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2065, pruned_loss=0.02997, over 972699.21 frames.], batch size: 13, lr: 1.48e-04
+2022-05-08 08:41:45,473 INFO [train.py:715] (3/8) Epoch 15, batch 9000, loss[loss=0.1385, simple_loss=0.2236, pruned_loss=0.02666, over 4785.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.02997, over 971748.41 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 08:41:45,474 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 08:42:05,028 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01074, over 914524.00 frames.
+2022-05-08 08:42:44,052 INFO [train.py:715] (3/8) Epoch 15, batch 9050, loss[loss=0.1494, simple_loss=0.2168, pruned_loss=0.04096, over 4920.00 frames.], tot_loss[loss=0.1335, simple_loss=0.207, pruned_loss=0.02999, over 971890.27 frames.], batch size: 39, lr: 1.48e-04
+2022-05-08 08:43:23,567 INFO [train.py:715] (3/8) Epoch 15, batch 9100, loss[loss=0.1216, simple_loss=0.1981, pruned_loss=0.0226, over 4823.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2077, pruned_loss=0.03033, over 972645.46 frames.], batch size: 26, lr: 1.48e-04
+2022-05-08 08:44:03,267 INFO [train.py:715] (3/8) Epoch 15, batch 9150, loss[loss=0.1299, simple_loss=0.2113, pruned_loss=0.02429, over 4766.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03051, over 971696.95 frames.], batch size: 14, lr: 1.48e-04
+2022-05-08 08:44:42,062 INFO [train.py:715] (3/8) Epoch 15, batch 9200, loss[loss=0.1419, simple_loss=0.2169, pruned_loss=0.03344, over 4924.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2084, pruned_loss=0.03105, over 972410.94 frames.], batch size: 23, lr: 1.48e-04
+2022-05-08 08:45:21,339 INFO [train.py:715] (3/8) Epoch 15, batch 9250, loss[loss=0.1366, simple_loss=0.2113, pruned_loss=0.03096, over 4953.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03039, over 972378.12 frames.], batch size: 21, lr: 1.48e-04
+2022-05-08 08:46:01,215 INFO [train.py:715] (3/8) Epoch 15, batch 9300, loss[loss=0.1319, simple_loss=0.2025, pruned_loss=0.03069, over 4948.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.0307, over 972349.13 frames.], batch size: 29, lr: 1.48e-04
+2022-05-08 08:46:41,142 INFO [train.py:715] (3/8) Epoch 15, batch 9350, loss[loss=0.1671, simple_loss=0.2388, pruned_loss=0.04772, over 4861.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03076, over 973298.51 frames.], batch size: 32, lr: 1.48e-04
+2022-05-08 08:47:19,985 INFO [train.py:715] (3/8) Epoch 15, batch 9400, loss[loss=0.133, simple_loss=0.189, pruned_loss=0.03851, over 4796.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2076, pruned_loss=0.0304, over 973037.21 frames.], batch size: 12, lr: 1.48e-04
+2022-05-08 08:47:59,297 INFO [train.py:715] (3/8) Epoch 15, batch 9450, loss[loss=0.1175, simple_loss=0.188, pruned_loss=0.0235, over 4935.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.03056, over 973371.85 frames.], batch size: 21, lr: 1.48e-04
+2022-05-08 08:48:38,584 INFO [train.py:715] (3/8) Epoch 15, batch 9500, loss[loss=0.1329, simple_loss=0.2098, pruned_loss=0.02802, over 4906.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2073, pruned_loss=0.03016, over 973675.01 frames.], batch size: 23, lr: 1.48e-04
+2022-05-08 08:49:16,973 INFO [train.py:715] (3/8) Epoch 15, batch 9550, loss[loss=0.1508, simple_loss=0.2388, pruned_loss=0.03141, over 4914.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02983, over 973871.43 frames.], batch size: 39, lr: 1.48e-04
+2022-05-08 08:49:56,305 INFO [train.py:715] (3/8) Epoch 15, batch 9600, loss[loss=0.1194, simple_loss=0.1873, pruned_loss=0.02577, over 4868.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02957, over 973679.28 frames.], batch size: 12, lr: 1.48e-04
+2022-05-08 08:50:35,894 INFO [train.py:715] (3/8) Epoch 15, batch 9650, loss[loss=0.1521, simple_loss=0.2293, pruned_loss=0.03742, over 4868.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02996, over 974205.28 frames.], batch size: 22, lr: 1.48e-04
+2022-05-08 08:51:15,449 INFO [train.py:715] (3/8) Epoch 15, batch 9700, loss[loss=0.1429, simple_loss=0.2208, pruned_loss=0.03254, over 4837.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03048, over 973573.74 frames.], batch size: 30, lr: 1.48e-04
+2022-05-08 08:51:53,983 INFO [train.py:715] (3/8) Epoch 15, batch 9750, loss[loss=0.1346, simple_loss=0.2184, pruned_loss=0.02535, over 4806.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.0309, over 972952.62 frames.], batch size: 25, lr: 1.48e-04
+2022-05-08 08:52:33,223 INFO [train.py:715] (3/8) Epoch 15, batch 9800, loss[loss=0.1193, simple_loss=0.1842, pruned_loss=0.02726, over 4909.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03082, over 972322.64 frames.], batch size: 17, lr: 1.48e-04
+2022-05-08 08:53:12,411 INFO [train.py:715] (3/8) Epoch 15, batch 9850, loss[loss=0.1186, simple_loss=0.1856, pruned_loss=0.02585, over 4779.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03052, over 971979.31 frames.], batch size: 14, lr: 1.48e-04
+2022-05-08 08:53:50,990 INFO [train.py:715] (3/8) Epoch 15, batch 9900, loss[loss=0.1115, simple_loss=0.1796, pruned_loss=0.02174, over 4785.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03076, over 971863.47 frames.], batch size: 14, lr: 1.48e-04
+2022-05-08 08:54:30,416 INFO [train.py:715] (3/8) Epoch 15, batch 9950, loss[loss=0.1316, simple_loss=0.2137, pruned_loss=0.02475, over 4799.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03057, over 971846.01 frames.], batch size: 24, lr: 1.48e-04
+2022-05-08 08:55:09,387 INFO [train.py:715] (3/8) Epoch 15, batch 10000, loss[loss=0.1614, simple_loss=0.2344, pruned_loss=0.04425, over 4955.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03046, over 972709.02 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 08:55:48,601 INFO [train.py:715] (3/8) Epoch 15, batch 10050, loss[loss=0.1155, simple_loss=0.1845, pruned_loss=0.02323, over 4707.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03022, over 972895.41 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 08:56:26,957 INFO [train.py:715] (3/8) Epoch 15, batch 10100, loss[loss=0.1219, simple_loss=0.1926, pruned_loss=0.02559, over 4693.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03003, over 972226.29 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 08:57:05,758 INFO [train.py:715] (3/8) Epoch 15, batch 10150, loss[loss=0.1257, simple_loss=0.2073, pruned_loss=0.02209, over 4902.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03037, over 972054.27 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 08:57:45,601 INFO [train.py:715] (3/8) Epoch 15, batch 10200, loss[loss=0.1246, simple_loss=0.1968, pruned_loss=0.02619, over 4969.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02989, over 972381.04 frames.], batch size: 35, lr: 1.48e-04
+2022-05-08 08:58:23,924 INFO [train.py:715] (3/8) Epoch 15, batch 10250, loss[loss=0.1492, simple_loss=0.2144, pruned_loss=0.04197, over 4947.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03019, over 972587.35 frames.], batch size: 35, lr: 1.48e-04
+2022-05-08 08:59:03,222 INFO [train.py:715] (3/8) Epoch 15, batch 10300, loss[loss=0.1327, simple_loss=0.2032, pruned_loss=0.03108, over 4834.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02976, over 972244.57 frames.], batch size: 12, lr: 1.48e-04
+2022-05-08 08:59:42,681 INFO [train.py:715] (3/8) Epoch 15, batch 10350, loss[loss=0.1514, simple_loss=0.2179, pruned_loss=0.04243, over 4853.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02963, over 972245.32 frames.], batch size: 32, lr: 1.48e-04
+2022-05-08 09:00:21,806 INFO [train.py:715] (3/8) Epoch 15, batch 10400, loss[loss=0.1515, simple_loss=0.2153, pruned_loss=0.04383, over 4801.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03006, over 972076.76 frames.], batch size: 24, lr: 1.48e-04
+2022-05-08 09:00:59,821 INFO [train.py:715] (3/8) Epoch 15, batch 10450, loss[loss=0.1408, simple_loss=0.2105, pruned_loss=0.03558, over 4850.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02992, over 971432.44 frames.], batch size: 32, lr: 1.48e-04
+2022-05-08 09:01:38,803 INFO [train.py:715] (3/8) Epoch 15, batch 10500, loss[loss=0.1486, simple_loss=0.218, pruned_loss=0.03954, over 4911.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02968, over 971073.62 frames.], batch size: 19, lr: 1.48e-04
+2022-05-08 09:02:18,521 INFO [train.py:715] (3/8) Epoch 15, batch 10550, loss[loss=0.1446, simple_loss=0.2117, pruned_loss=0.03873, over 4837.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02984, over 970817.61 frames.], batch size: 15, lr: 1.48e-04
+2022-05-08 09:02:56,681 INFO [train.py:715] (3/8) Epoch 15, batch 10600, loss[loss=0.1444, simple_loss=0.2127, pruned_loss=0.03806, over 4931.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2084, pruned_loss=0.02958, over 971408.15 frames.], batch size: 18, lr: 1.48e-04
+2022-05-08 09:03:35,333 INFO [train.py:715] (3/8) Epoch 15, batch 10650, loss[loss=0.1223, simple_loss=0.1999, pruned_loss=0.0223, over 4973.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02962, over 971923.18 frames.], batch size: 24, lr: 1.48e-04
+2022-05-08 09:04:14,417 INFO [train.py:715] (3/8) Epoch 15, batch 10700, loss[loss=0.1301, simple_loss=0.2086, pruned_loss=0.02576, over 4882.00 frames.], tot_loss[loss=0.134, simple_loss=0.2086, pruned_loss=0.02969, over 972479.84 frames.], batch size: 16, lr: 1.48e-04
+2022-05-08 09:04:53,635 INFO [train.py:715] (3/8) Epoch 15, batch 10750, loss[loss=0.1265, simple_loss=0.2033, pruned_loss=0.02481, over 4878.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03021, over 971757.27 frames.], batch size: 16, lr: 1.48e-04
+2022-05-08 09:05:31,576 INFO [train.py:715] (3/8) Epoch 15, batch 10800, loss[loss=0.1635, simple_loss=0.2386, pruned_loss=0.04423, over 4872.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03016, over 971822.98 frames.], batch size: 20, lr: 1.47e-04
+2022-05-08 09:06:11,099 INFO [train.py:715] (3/8) Epoch 15, batch 10850, loss[loss=0.123, simple_loss=0.194, pruned_loss=0.02598, over 4954.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.0293, over 971590.72 frames.], batch size: 35, lr: 1.47e-04
+2022-05-08 09:06:50,387 INFO [train.py:715] (3/8) Epoch 15, batch 10900, loss[loss=0.1288, simple_loss=0.2038, pruned_loss=0.02688, over 4817.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02928, over 971799.85 frames.], batch size: 13, lr: 1.47e-04
+2022-05-08 09:07:28,757 INFO [train.py:715] (3/8) Epoch 15, batch 10950, loss[loss=0.09883, simple_loss=0.1727, pruned_loss=0.01246, over 4974.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02923, over 971775.44 frames.], batch size: 25, lr: 1.47e-04
+2022-05-08 09:08:06,755 INFO [train.py:715] (3/8) Epoch 15, batch 11000, loss[loss=0.1321, simple_loss=0.2163, pruned_loss=0.02399, over 4969.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02921, over 972426.07 frames.], batch size: 35, lr: 1.47e-04
+2022-05-08 09:08:45,833 INFO [train.py:715] (3/8) Epoch 15, batch 11050, loss[loss=0.1289, simple_loss=0.204, pruned_loss=0.02688, over 4742.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.0291, over 972354.71 frames.], batch size: 16, lr: 1.47e-04
+2022-05-08 09:09:25,316 INFO [train.py:715] (3/8) Epoch 15, batch 11100, loss[loss=0.1573, simple_loss=0.2345, pruned_loss=0.04005, over 4947.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02952, over 972997.53 frames.], batch size: 35, lr: 1.47e-04
+2022-05-08 09:10:03,228 INFO [train.py:715] (3/8) Epoch 15, batch 11150, loss[loss=0.1489, simple_loss=0.2278, pruned_loss=0.03501, over 4682.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02944, over 972746.39 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 09:10:41,862 INFO [train.py:715] (3/8) Epoch 15, batch 11200, loss[loss=0.1562, simple_loss=0.2313, pruned_loss=0.04059, over 4963.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02973, over 972666.54 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 09:11:20,813 INFO [train.py:715] (3/8) Epoch 15, batch 11250, loss[loss=0.1154, simple_loss=0.1913, pruned_loss=0.01975, over 4931.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02939, over 972385.11 frames.], batch size: 29, lr: 1.47e-04
+2022-05-08 09:11:59,332 INFO [train.py:715] (3/8) Epoch 15, batch 11300, loss[loss=0.1193, simple_loss=0.1908, pruned_loss=0.02394, over 4978.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02934, over 972229.63 frames.], batch size: 28, lr: 1.47e-04
+2022-05-08 09:12:37,836 INFO [train.py:715] (3/8) Epoch 15, batch 11350, loss[loss=0.1187, simple_loss=0.1922, pruned_loss=0.02258, over 4856.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02967, over 972616.26 frames.], batch size: 13, lr: 1.47e-04
+2022-05-08 09:13:17,189 INFO [train.py:715] (3/8) Epoch 15, batch 11400, loss[loss=0.09769, simple_loss=0.1687, pruned_loss=0.01335, over 4786.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.0297, over 971841.61 frames.], batch size: 12, lr: 1.47e-04
+2022-05-08 09:13:55,481 INFO [train.py:715] (3/8) Epoch 15, batch 11450, loss[loss=0.1273, simple_loss=0.2019, pruned_loss=0.02632, over 4771.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02968, over 971587.19 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 09:14:34,171 INFO [train.py:715] (3/8) Epoch 15, batch 11500, loss[loss=0.1042, simple_loss=0.1793, pruned_loss=0.01452, over 4892.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02958, over 971536.49 frames.], batch size: 29, lr: 1.47e-04
+2022-05-08 09:15:13,133 INFO [train.py:715] (3/8) Epoch 15, batch 11550, loss[loss=0.1514, simple_loss=0.2326, pruned_loss=0.03512, over 4810.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02987, over 971953.42 frames.], batch size: 24, lr: 1.47e-04
+2022-05-08 09:15:52,415 INFO [train.py:715] (3/8) Epoch 15, batch 11600, loss[loss=0.1635, simple_loss=0.2293, pruned_loss=0.04885, over 4925.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03016, over 972315.16 frames.], batch size: 39, lr: 1.47e-04
+2022-05-08 09:16:30,746 INFO [train.py:715] (3/8) Epoch 15, batch 11650, loss[loss=0.1272, simple_loss=0.1956, pruned_loss=0.02944, over 4948.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.03, over 972610.66 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 09:17:09,222 INFO [train.py:715] (3/8) Epoch 15, batch 11700, loss[loss=0.139, simple_loss=0.2164, pruned_loss=0.03083, over 4778.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03024, over 971787.12 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 09:17:48,442 INFO [train.py:715] (3/8) Epoch 15, batch 11750, loss[loss=0.1336, simple_loss=0.2172, pruned_loss=0.02503, over 4908.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02991, over 971497.33 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 09:18:27,447 INFO [train.py:715] (3/8) Epoch 15, batch 11800, loss[loss=0.1308, simple_loss=0.2036, pruned_loss=0.02895, over 4781.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.0294, over 971407.18 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 09:19:05,513 INFO [train.py:715] (3/8) Epoch 15, batch 11850, loss[loss=0.1245, simple_loss=0.191, pruned_loss=0.02899, over 4764.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02959, over 971617.27 frames.], batch size: 14, lr: 1.47e-04
+2022-05-08 09:19:45,040 INFO [train.py:715] (3/8) Epoch 15, batch 11900, loss[loss=0.1253, simple_loss=0.1994, pruned_loss=0.02558, over 4913.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02951, over 971724.18 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 09:20:25,121 INFO [train.py:715] (3/8) Epoch 15, batch 11950, loss[loss=0.151, simple_loss=0.2242, pruned_loss=0.03888, over 4904.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02988, over 971667.32 frames.], batch size: 19, lr: 1.47e-04
+2022-05-08 09:21:03,708 INFO [train.py:715] (3/8) Epoch 15, batch 12000, loss[loss=0.1415, simple_loss=0.2277, pruned_loss=0.02762, over 4911.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03033, over 972858.19 frames.], batch size: 19, lr: 1.47e-04
+2022-05-08 09:21:03,709 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 09:21:20,395 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.105, simple_loss=0.1887, pruned_loss=0.01066, over 914524.00 frames.
+2022-05-08 09:21:59,114 INFO [train.py:715] (3/8) Epoch 15, batch 12050, loss[loss=0.1417, simple_loss=0.2146, pruned_loss=0.03443, over 4797.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.0306, over 973332.27 frames.], batch size: 25, lr: 1.47e-04
+2022-05-08 09:22:38,255 INFO [train.py:715] (3/8) Epoch 15, batch 12100, loss[loss=0.1444, simple_loss=0.2183, pruned_loss=0.0353, over 4815.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03047, over 971989.30 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 09:23:17,964 INFO [train.py:715] (3/8) Epoch 15, batch 12150, loss[loss=0.1507, simple_loss=0.2388, pruned_loss=0.03126, over 4979.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03078, over 972101.51 frames.], batch size: 25, lr: 1.47e-04
+2022-05-08 09:23:56,410 INFO [train.py:715] (3/8) Epoch 15, batch 12200, loss[loss=0.1489, simple_loss=0.2215, pruned_loss=0.03819, over 4955.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03027, over 972363.01 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 09:24:35,178 INFO [train.py:715] (3/8) Epoch 15, batch 12250, loss[loss=0.13, simple_loss=0.2023, pruned_loss=0.0289, over 4798.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03035, over 972625.82 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 09:25:14,196 INFO [train.py:715] (3/8) Epoch 15, batch 12300, loss[loss=0.137, simple_loss=0.2129, pruned_loss=0.03057, over 4928.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03066, over 973497.94 frames.], batch size: 23, lr: 1.47e-04
+2022-05-08 09:25:54,059 INFO [train.py:715] (3/8) Epoch 15, batch 12350, loss[loss=0.1304, simple_loss=0.2027, pruned_loss=0.02911, over 4790.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03025, over 973948.62 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 09:26:32,324 INFO [train.py:715] (3/8) Epoch 15, batch 12400, loss[loss=0.1597, simple_loss=0.2391, pruned_loss=0.04017, over 4734.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03104, over 972719.33 frames.], batch size: 16, lr: 1.47e-04
+2022-05-08 09:27:11,077 INFO [train.py:715] (3/8) Epoch 15, batch 12450, loss[loss=0.1293, simple_loss=0.1935, pruned_loss=0.03249, over 4983.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03088, over 973095.55 frames.], batch size: 33, lr: 1.47e-04
+2022-05-08 09:27:51,095 INFO [train.py:715] (3/8) Epoch 15, batch 12500, loss[loss=0.1448, simple_loss=0.2222, pruned_loss=0.03364, over 4872.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.0305, over 973638.61 frames.], batch size: 16, lr: 1.47e-04
+2022-05-08 09:28:29,290 INFO [train.py:715] (3/8) Epoch 15, batch 12550, loss[loss=0.1747, simple_loss=0.2356, pruned_loss=0.05688, over 4876.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03036, over 973256.57 frames.], batch size: 39, lr: 1.47e-04
+2022-05-08 09:29:08,352 INFO [train.py:715] (3/8) Epoch 15, batch 12600, loss[loss=0.1502, simple_loss=0.2247, pruned_loss=0.03779, over 4942.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03096, over 972691.83 frames.], batch size: 23, lr: 1.47e-04
+2022-05-08 09:29:46,866 INFO [train.py:715] (3/8) Epoch 15, batch 12650, loss[loss=0.1253, simple_loss=0.2007, pruned_loss=0.02497, over 4781.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03139, over 972889.93 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 09:30:26,464 INFO [train.py:715] (3/8) Epoch 15, batch 12700, loss[loss=0.1286, simple_loss=0.2099, pruned_loss=0.02363, over 4836.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03095, over 972564.55 frames.], batch size: 26, lr: 1.47e-04
+2022-05-08 09:31:04,801 INFO [train.py:715] (3/8) Epoch 15, batch 12750, loss[loss=0.149, simple_loss=0.2173, pruned_loss=0.04033, over 4808.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03126, over 971888.66 frames.], batch size: 14, lr: 1.47e-04
+2022-05-08 09:31:43,635 INFO [train.py:715] (3/8) Epoch 15, batch 12800, loss[loss=0.1191, simple_loss=0.1893, pruned_loss=0.02438, over 4784.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03168, over 972024.81 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 09:32:23,165 INFO [train.py:715] (3/8) Epoch 15, batch 12850, loss[loss=0.1395, simple_loss=0.2137, pruned_loss=0.03263, over 4780.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03107, over 971607.23 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 09:33:01,790 INFO [train.py:715] (3/8) Epoch 15, batch 12900, loss[loss=0.1403, simple_loss=0.2098, pruned_loss=0.03537, over 4811.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03112, over 971309.09 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 09:33:40,812 INFO [train.py:715] (3/8) Epoch 15, batch 12950, loss[loss=0.1391, simple_loss=0.2135, pruned_loss=0.03234, over 4962.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.0311, over 972015.79 frames.], batch size: 24, lr: 1.47e-04
+2022-05-08 09:34:20,126 INFO [train.py:715] (3/8) Epoch 15, batch 13000, loss[loss=0.1557, simple_loss=0.2225, pruned_loss=0.04446, over 4870.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03111, over 971697.51 frames.], batch size: 32, lr: 1.47e-04
+2022-05-08 09:34:59,664 INFO [train.py:715] (3/8) Epoch 15, batch 13050, loss[loss=0.1173, simple_loss=0.1994, pruned_loss=0.01755, over 4966.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03146, over 973066.13 frames.], batch size: 28, lr: 1.47e-04
+2022-05-08 09:35:38,148 INFO [train.py:715] (3/8) Epoch 15, batch 13100, loss[loss=0.1225, simple_loss=0.1975, pruned_loss=0.02375, over 4799.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03076, over 971802.50 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 09:36:17,622 INFO [train.py:715] (3/8) Epoch 15, batch 13150, loss[loss=0.1453, simple_loss=0.2228, pruned_loss=0.03387, over 4860.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03078, over 971505.01 frames.], batch size: 20, lr: 1.47e-04
+2022-05-08 09:36:57,403 INFO [train.py:715] (3/8) Epoch 15, batch 13200, loss[loss=0.137, simple_loss=0.2163, pruned_loss=0.02888, over 4736.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2083, pruned_loss=0.03111, over 971239.95 frames.], batch size: 16, lr: 1.47e-04
+2022-05-08 09:37:35,200 INFO [train.py:715] (3/8) Epoch 15, batch 13250, loss[loss=0.1339, simple_loss=0.2041, pruned_loss=0.03185, over 4984.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03064, over 971695.53 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 09:38:14,331 INFO [train.py:715] (3/8) Epoch 15, batch 13300, loss[loss=0.1216, simple_loss=0.1957, pruned_loss=0.02376, over 4825.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03063, over 971958.05 frames.], batch size: 26, lr: 1.47e-04
+2022-05-08 09:38:53,947 INFO [train.py:715] (3/8) Epoch 15, batch 13350, loss[loss=0.1371, simple_loss=0.2117, pruned_loss=0.03122, over 4786.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.0306, over 973002.32 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 09:39:34,559 INFO [train.py:715] (3/8) Epoch 15, batch 13400, loss[loss=0.1333, simple_loss=0.2081, pruned_loss=0.02922, over 4939.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.0304, over 972743.24 frames.], batch size: 29, lr: 1.47e-04
+2022-05-08 09:40:13,185 INFO [train.py:715] (3/8) Epoch 15, batch 13450, loss[loss=0.165, simple_loss=0.2433, pruned_loss=0.04333, over 4805.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03039, over 972626.73 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 09:40:51,766 INFO [train.py:715] (3/8) Epoch 15, batch 13500, loss[loss=0.1505, simple_loss=0.2311, pruned_loss=0.03498, over 4914.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03033, over 972293.64 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 09:41:31,304 INFO [train.py:715] (3/8) Epoch 15, batch 13550, loss[loss=0.1094, simple_loss=0.1829, pruned_loss=0.01797, over 4878.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2093, pruned_loss=0.03056, over 972282.21 frames.], batch size: 16, lr: 1.47e-04
+2022-05-08 09:42:09,583 INFO [train.py:715] (3/8) Epoch 15, batch 13600, loss[loss=0.1115, simple_loss=0.1807, pruned_loss=0.02109, over 4699.00 frames.], tot_loss[loss=0.1346, simple_loss=0.209, pruned_loss=0.03015, over 971926.22 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 09:42:48,566 INFO [train.py:715] (3/8) Epoch 15, batch 13650, loss[loss=0.1305, simple_loss=0.1903, pruned_loss=0.03534, over 4802.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02955, over 972302.28 frames.], batch size: 24, lr: 1.47e-04
+2022-05-08 09:43:27,805 INFO [train.py:715] (3/8) Epoch 15, batch 13700, loss[loss=0.1399, simple_loss=0.2096, pruned_loss=0.03513, over 4771.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.0299, over 971328.69 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 09:44:06,262 INFO [train.py:715] (3/8) Epoch 15, batch 13750, loss[loss=0.121, simple_loss=0.195, pruned_loss=0.02349, over 4685.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02991, over 970596.61 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 09:44:44,980 INFO [train.py:715] (3/8) Epoch 15, batch 13800, loss[loss=0.1084, simple_loss=0.1843, pruned_loss=0.01629, over 4757.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02958, over 970537.80 frames.], batch size: 19, lr: 1.47e-04
+2022-05-08 09:45:23,199 INFO [train.py:715] (3/8) Epoch 15, batch 13850, loss[loss=0.1195, simple_loss=0.1884, pruned_loss=0.02532, over 4809.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02932, over 970248.23 frames.], batch size: 13, lr: 1.47e-04
+2022-05-08 09:46:05,205 INFO [train.py:715] (3/8) Epoch 15, batch 13900, loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03501, over 4950.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02865, over 971071.54 frames.], batch size: 35, lr: 1.47e-04
+2022-05-08 09:46:43,313 INFO [train.py:715] (3/8) Epoch 15, batch 13950, loss[loss=0.1546, simple_loss=0.2294, pruned_loss=0.03991, over 4798.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02941, over 971385.71 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 09:47:21,602 INFO [train.py:715] (3/8) Epoch 15, batch 14000, loss[loss=0.1094, simple_loss=0.1883, pruned_loss=0.01525, over 4795.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02977, over 971037.68 frames.], batch size: 24, lr: 1.47e-04
+2022-05-08 09:48:00,883 INFO [train.py:715] (3/8) Epoch 15, batch 14050, loss[loss=0.153, simple_loss=0.2122, pruned_loss=0.04693, over 4828.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03021, over 971394.36 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 09:48:38,846 INFO [train.py:715] (3/8) Epoch 15, batch 14100, loss[loss=0.1604, simple_loss=0.2324, pruned_loss=0.0442, over 4767.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03084, over 971300.56 frames.], batch size: 19, lr: 1.47e-04
+2022-05-08 09:49:17,894 INFO [train.py:715] (3/8) Epoch 15, batch 14150, loss[loss=0.1354, simple_loss=0.2133, pruned_loss=0.02877, over 4870.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.0308, over 971785.72 frames.], batch size: 38, lr: 1.47e-04
+2022-05-08 09:49:56,536 INFO [train.py:715] (3/8) Epoch 15, batch 14200, loss[loss=0.1284, simple_loss=0.1964, pruned_loss=0.03023, over 4816.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2088, pruned_loss=0.03109, over 972222.65 frames.], batch size: 13, lr: 1.47e-04
+2022-05-08 09:50:35,494 INFO [train.py:715] (3/8) Epoch 15, batch 14250, loss[loss=0.1243, simple_loss=0.1995, pruned_loss=0.02456, over 4772.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03054, over 972454.24 frames.], batch size: 19, lr: 1.47e-04
+2022-05-08 09:51:13,321 INFO [train.py:715] (3/8) Epoch 15, batch 14300, loss[loss=0.1173, simple_loss=0.196, pruned_loss=0.01929, over 4820.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03048, over 972276.04 frames.], batch size: 25, lr: 1.47e-04
+2022-05-08 09:51:51,767 INFO [train.py:715] (3/8) Epoch 15, batch 14350, loss[loss=0.1666, simple_loss=0.2575, pruned_loss=0.03787, over 4635.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03065, over 971917.92 frames.], batch size: 13, lr: 1.47e-04
+2022-05-08 09:52:30,861 INFO [train.py:715] (3/8) Epoch 15, batch 14400, loss[loss=0.1222, simple_loss=0.1906, pruned_loss=0.02686, over 4939.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03007, over 971945.43 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 09:53:08,607 INFO [train.py:715] (3/8) Epoch 15, batch 14450, loss[loss=0.1554, simple_loss=0.2289, pruned_loss=0.04092, over 4754.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03009, over 972391.99 frames.], batch size: 16, lr: 1.47e-04
+2022-05-08 09:53:47,585 INFO [train.py:715] (3/8) Epoch 15, batch 14500, loss[loss=0.1202, simple_loss=0.1961, pruned_loss=0.02211, over 4928.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02992, over 972901.63 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 09:54:25,858 INFO [train.py:715] (3/8) Epoch 15, batch 14550, loss[loss=0.1217, simple_loss=0.207, pruned_loss=0.01823, over 4794.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03032, over 973915.98 frames.], batch size: 14, lr: 1.47e-04
+2022-05-08 09:55:04,849 INFO [train.py:715] (3/8) Epoch 15, batch 14600, loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.0284, over 4768.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2099, pruned_loss=0.03074, over 973859.28 frames.], batch size: 14, lr: 1.47e-04
+2022-05-08 09:55:42,673 INFO [train.py:715] (3/8) Epoch 15, batch 14650, loss[loss=0.1247, simple_loss=0.2169, pruned_loss=0.01624, over 4954.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03039, over 972785.97 frames.], batch size: 24, lr: 1.47e-04
+2022-05-08 09:56:20,652 INFO [train.py:715] (3/8) Epoch 15, batch 14700, loss[loss=0.124, simple_loss=0.2001, pruned_loss=0.02398, over 4923.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03021, over 973281.16 frames.], batch size: 29, lr: 1.47e-04
+2022-05-08 09:56:59,720 INFO [train.py:715] (3/8) Epoch 15, batch 14750, loss[loss=0.121, simple_loss=0.1953, pruned_loss=0.02334, over 4845.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03022, over 972762.96 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 09:57:37,353 INFO [train.py:715] (3/8) Epoch 15, batch 14800, loss[loss=0.1244, simple_loss=0.1964, pruned_loss=0.02625, over 4777.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03096, over 972202.27 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 09:58:16,194 INFO [train.py:715] (3/8) Epoch 15, batch 14850, loss[loss=0.1114, simple_loss=0.1711, pruned_loss=0.02579, over 4800.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2081, pruned_loss=0.03074, over 972000.14 frames.], batch size: 12, lr: 1.47e-04
+2022-05-08 09:58:55,099 INFO [train.py:715] (3/8) Epoch 15, batch 14900, loss[loss=0.1161, simple_loss=0.1882, pruned_loss=0.02202, over 4768.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03048, over 971855.17 frames.], batch size: 12, lr: 1.47e-04
+2022-05-08 09:59:33,273 INFO [train.py:715] (3/8) Epoch 15, batch 14950, loss[loss=0.1299, simple_loss=0.2012, pruned_loss=0.02929, over 4943.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2082, pruned_loss=0.03066, over 971618.09 frames.], batch size: 39, lr: 1.47e-04
+2022-05-08 10:00:11,565 INFO [train.py:715] (3/8) Epoch 15, batch 15000, loss[loss=0.1422, simple_loss=0.2141, pruned_loss=0.03512, over 4910.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03048, over 972504.04 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 10:00:11,566 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 10:00:26,344 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01077, over 914524.00 frames.
+2022-05-08 10:01:05,813 INFO [train.py:715] (3/8) Epoch 15, batch 15050, loss[loss=0.1397, simple_loss=0.206, pruned_loss=0.03671, over 4979.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2085, pruned_loss=0.03101, over 972342.77 frames.], batch size: 14, lr: 1.47e-04
+2022-05-08 10:01:43,981 INFO [train.py:715] (3/8) Epoch 15, batch 15100, loss[loss=0.1379, simple_loss=0.2123, pruned_loss=0.03172, over 4958.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2087, pruned_loss=0.03139, over 972494.84 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 10:02:23,334 INFO [train.py:715] (3/8) Epoch 15, batch 15150, loss[loss=0.1394, simple_loss=0.2189, pruned_loss=0.02997, over 4854.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03148, over 972101.91 frames.], batch size: 20, lr: 1.47e-04
+2022-05-08 10:03:01,056 INFO [train.py:715] (3/8) Epoch 15, batch 15200, loss[loss=0.1426, simple_loss=0.2104, pruned_loss=0.03735, over 4981.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03151, over 972569.52 frames.], batch size: 39, lr: 1.47e-04
+2022-05-08 10:03:39,354 INFO [train.py:715] (3/8) Epoch 15, batch 15250, loss[loss=0.1347, simple_loss=0.1989, pruned_loss=0.03525, over 4982.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2083, pruned_loss=0.03104, over 971529.57 frames.], batch size: 14, lr: 1.47e-04
+2022-05-08 10:04:18,903 INFO [train.py:715] (3/8) Epoch 15, batch 15300, loss[loss=0.1499, simple_loss=0.2315, pruned_loss=0.03415, over 4771.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03103, over 971124.52 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 10:04:56,987 INFO [train.py:715] (3/8) Epoch 15, batch 15350, loss[loss=0.1467, simple_loss=0.2142, pruned_loss=0.03961, over 4699.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.0307, over 972004.73 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 10:05:35,892 INFO [train.py:715] (3/8) Epoch 15, batch 15400, loss[loss=0.1432, simple_loss=0.2202, pruned_loss=0.03309, over 4813.00 frames.], tot_loss[loss=0.135, simple_loss=0.2082, pruned_loss=0.03094, over 971734.82 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 10:06:13,991 INFO [train.py:715] (3/8) Epoch 15, batch 15450, loss[loss=0.1638, simple_loss=0.2365, pruned_loss=0.04556, over 4863.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.0309, over 972571.48 frames.], batch size: 20, lr: 1.47e-04
+2022-05-08 10:06:52,881 INFO [train.py:715] (3/8) Epoch 15, batch 15500, loss[loss=0.1311, simple_loss=0.2086, pruned_loss=0.02679, over 4807.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03099, over 971881.09 frames.], batch size: 14, lr: 1.47e-04
+2022-05-08 10:07:31,446 INFO [train.py:715] (3/8) Epoch 15, batch 15550, loss[loss=0.1415, simple_loss=0.2075, pruned_loss=0.03773, over 4946.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03069, over 971515.55 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 10:08:10,328 INFO [train.py:715] (3/8) Epoch 15, batch 15600, loss[loss=0.155, simple_loss=0.2335, pruned_loss=0.03821, over 4987.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03047, over 971561.00 frames.], batch size: 24, lr: 1.47e-04
+2022-05-08 10:08:49,135 INFO [train.py:715] (3/8) Epoch 15, batch 15650, loss[loss=0.1366, simple_loss=0.2165, pruned_loss=0.0283, over 4953.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03052, over 972397.22 frames.], batch size: 24, lr: 1.47e-04
+2022-05-08 10:09:27,216 INFO [train.py:715] (3/8) Epoch 15, batch 15700, loss[loss=0.1253, simple_loss=0.2009, pruned_loss=0.02488, over 4826.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03062, over 971543.65 frames.], batch size: 25, lr: 1.47e-04
+2022-05-08 10:10:05,788 INFO [train.py:715] (3/8) Epoch 15, batch 15750, loss[loss=0.1344, simple_loss=0.2069, pruned_loss=0.03095, over 4941.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2082, pruned_loss=0.03073, over 971856.12 frames.], batch size: 23, lr: 1.47e-04
+2022-05-08 10:10:44,349 INFO [train.py:715] (3/8) Epoch 15, batch 15800, loss[loss=0.1324, simple_loss=0.2029, pruned_loss=0.03097, over 4762.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.03085, over 971867.17 frames.], batch size: 19, lr: 1.47e-04
+2022-05-08 10:11:23,023 INFO [train.py:715] (3/8) Epoch 15, batch 15850, loss[loss=0.1702, simple_loss=0.2408, pruned_loss=0.04982, over 4919.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2086, pruned_loss=0.03099, over 972433.38 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 10:12:01,148 INFO [train.py:715] (3/8) Epoch 15, batch 15900, loss[loss=0.1367, simple_loss=0.2132, pruned_loss=0.0301, over 4929.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03085, over 972457.51 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 10:12:39,308 INFO [train.py:715] (3/8) Epoch 15, batch 15950, loss[loss=0.1756, simple_loss=0.2434, pruned_loss=0.05389, over 4893.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03043, over 972031.64 frames.], batch size: 16, lr: 1.47e-04
+2022-05-08 10:13:18,371 INFO [train.py:715] (3/8) Epoch 15, batch 16000, loss[loss=0.1098, simple_loss=0.1877, pruned_loss=0.01598, over 4819.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.0304, over 971384.60 frames.], batch size: 27, lr: 1.47e-04
+2022-05-08 10:13:56,003 INFO [train.py:715] (3/8) Epoch 15, batch 16050, loss[loss=0.1256, simple_loss=0.1932, pruned_loss=0.02904, over 4841.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.0299, over 971390.56 frames.], batch size: 13, lr: 1.47e-04
+2022-05-08 10:14:34,593 INFO [train.py:715] (3/8) Epoch 15, batch 16100, loss[loss=0.1587, simple_loss=0.2365, pruned_loss=0.04042, over 4692.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02942, over 972246.46 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 10:15:13,040 INFO [train.py:715] (3/8) Epoch 15, batch 16150, loss[loss=0.1249, simple_loss=0.2042, pruned_loss=0.02277, over 4756.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2086, pruned_loss=0.02983, over 972313.77 frames.], batch size: 16, lr: 1.47e-04
+2022-05-08 10:15:51,557 INFO [train.py:715] (3/8) Epoch 15, batch 16200, loss[loss=0.1243, simple_loss=0.1981, pruned_loss=0.02531, over 4754.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02959, over 971952.29 frames.], batch size: 16, lr: 1.47e-04
+2022-05-08 10:16:29,838 INFO [train.py:715] (3/8) Epoch 15, batch 16250, loss[loss=0.1561, simple_loss=0.2198, pruned_loss=0.04619, over 4946.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02982, over 971599.81 frames.], batch size: 39, lr: 1.47e-04
+2022-05-08 10:17:08,217 INFO [train.py:715] (3/8) Epoch 15, batch 16300, loss[loss=0.1235, simple_loss=0.1953, pruned_loss=0.02583, over 4907.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02973, over 971198.65 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 10:17:46,754 INFO [train.py:715] (3/8) Epoch 15, batch 16350, loss[loss=0.157, simple_loss=0.2328, pruned_loss=0.04056, over 4879.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02956, over 971043.18 frames.], batch size: 19, lr: 1.47e-04
+2022-05-08 10:18:24,622 INFO [train.py:715] (3/8) Epoch 15, batch 16400, loss[loss=0.1515, simple_loss=0.2189, pruned_loss=0.04201, over 4911.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02971, over 971186.44 frames.], batch size: 23, lr: 1.47e-04
+2022-05-08 10:19:03,505 INFO [train.py:715] (3/8) Epoch 15, batch 16450, loss[loss=0.1363, simple_loss=0.2037, pruned_loss=0.03438, over 4965.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02961, over 971859.20 frames.], batch size: 14, lr: 1.47e-04
+2022-05-08 10:19:41,761 INFO [train.py:715] (3/8) Epoch 15, batch 16500, loss[loss=0.1384, simple_loss=0.2153, pruned_loss=0.03072, over 4978.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02942, over 972503.43 frames.], batch size: 25, lr: 1.47e-04
+2022-05-08 10:20:20,132 INFO [train.py:715] (3/8) Epoch 15, batch 16550, loss[loss=0.1382, simple_loss=0.2161, pruned_loss=0.03013, over 4858.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02972, over 972898.41 frames.], batch size: 20, lr: 1.47e-04
+2022-05-08 10:20:58,279 INFO [train.py:715] (3/8) Epoch 15, batch 16600, loss[loss=0.1404, simple_loss=0.2185, pruned_loss=0.03114, over 4988.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2082, pruned_loss=0.02946, over 973412.51 frames.], batch size: 28, lr: 1.47e-04
+2022-05-08 10:21:37,036 INFO [train.py:715] (3/8) Epoch 15, batch 16650, loss[loss=0.1378, simple_loss=0.2149, pruned_loss=0.03034, over 4955.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.0293, over 973047.67 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 10:22:16,800 INFO [train.py:715] (3/8) Epoch 15, batch 16700, loss[loss=0.1227, simple_loss=0.1995, pruned_loss=0.02298, over 4785.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02947, over 972828.08 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 10:22:55,522 INFO [train.py:715] (3/8) Epoch 15, batch 16750, loss[loss=0.1788, simple_loss=0.2465, pruned_loss=0.05555, over 4856.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02981, over 973184.10 frames.], batch size: 20, lr: 1.47e-04
+2022-05-08 10:23:34,514 INFO [train.py:715] (3/8) Epoch 15, batch 16800, loss[loss=0.1199, simple_loss=0.1945, pruned_loss=0.02264, over 4859.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.0304, over 973715.28 frames.], batch size: 20, lr: 1.47e-04
+2022-05-08 10:24:13,670 INFO [train.py:715] (3/8) Epoch 15, batch 16850, loss[loss=0.1377, simple_loss=0.2098, pruned_loss=0.03282, over 4980.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03108, over 973095.21 frames.], batch size: 31, lr: 1.47e-04
+2022-05-08 10:24:52,754 INFO [train.py:715] (3/8) Epoch 15, batch 16900, loss[loss=0.1237, simple_loss=0.203, pruned_loss=0.0222, over 4988.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.0305, over 973404.06 frames.], batch size: 25, lr: 1.47e-04
+2022-05-08 10:25:31,723 INFO [train.py:715] (3/8) Epoch 15, batch 16950, loss[loss=0.1343, simple_loss=0.1988, pruned_loss=0.03495, over 4638.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03019, over 971639.71 frames.], batch size: 13, lr: 1.47e-04
+2022-05-08 10:26:10,074 INFO [train.py:715] (3/8) Epoch 15, batch 17000, loss[loss=0.1377, simple_loss=0.215, pruned_loss=0.03013, over 4781.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03056, over 972840.19 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 10:26:49,334 INFO [train.py:715] (3/8) Epoch 15, batch 17050, loss[loss=0.1482, simple_loss=0.2261, pruned_loss=0.03518, over 4956.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.03016, over 973216.09 frames.], batch size: 35, lr: 1.47e-04
+2022-05-08 10:27:27,263 INFO [train.py:715] (3/8) Epoch 15, batch 17100, loss[loss=0.1146, simple_loss=0.1919, pruned_loss=0.01865, over 4988.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03023, over 972791.90 frames.], batch size: 25, lr: 1.47e-04
+2022-05-08 10:28:06,076 INFO [train.py:715] (3/8) Epoch 15, batch 17150, loss[loss=0.1226, simple_loss=0.1917, pruned_loss=0.02669, over 4869.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2089, pruned_loss=0.02987, over 973059.17 frames.], batch size: 30, lr: 1.47e-04
+2022-05-08 10:28:44,479 INFO [train.py:715] (3/8) Epoch 15, batch 17200, loss[loss=0.1363, simple_loss=0.2084, pruned_loss=0.03206, over 4824.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2083, pruned_loss=0.02899, over 974053.95 frames.], batch size: 26, lr: 1.47e-04
+2022-05-08 10:29:23,148 INFO [train.py:715] (3/8) Epoch 15, batch 17250, loss[loss=0.1442, simple_loss=0.2205, pruned_loss=0.03397, over 4930.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2086, pruned_loss=0.02918, over 973769.56 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 10:30:01,724 INFO [train.py:715] (3/8) Epoch 15, batch 17300, loss[loss=0.1219, simple_loss=0.207, pruned_loss=0.01843, over 4952.00 frames.], tot_loss[loss=0.134, simple_loss=0.2089, pruned_loss=0.02953, over 973668.93 frames.], batch size: 24, lr: 1.47e-04
+2022-05-08 10:30:40,362 INFO [train.py:715] (3/8) Epoch 15, batch 17350, loss[loss=0.1392, simple_loss=0.214, pruned_loss=0.03219, over 4764.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2087, pruned_loss=0.02989, over 973479.04 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 10:31:19,953 INFO [train.py:715] (3/8) Epoch 15, batch 17400, loss[loss=0.1489, simple_loss=0.2153, pruned_loss=0.04126, over 4862.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02972, over 973436.71 frames.], batch size: 32, lr: 1.47e-04
+2022-05-08 10:31:57,893 INFO [train.py:715] (3/8) Epoch 15, batch 17450, loss[loss=0.1743, simple_loss=0.2506, pruned_loss=0.04904, over 4934.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02978, over 972648.97 frames.], batch size: 23, lr: 1.47e-04
+2022-05-08 10:32:36,871 INFO [train.py:715] (3/8) Epoch 15, batch 17500, loss[loss=0.1098, simple_loss=0.185, pruned_loss=0.01723, over 4817.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02982, over 972949.94 frames.], batch size: 25, lr: 1.47e-04
+2022-05-08 10:33:15,846 INFO [train.py:715] (3/8) Epoch 15, batch 17550, loss[loss=0.1262, simple_loss=0.2092, pruned_loss=0.02158, over 4949.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.0299, over 972721.50 frames.], batch size: 21, lr: 1.47e-04
+2022-05-08 10:33:54,435 INFO [train.py:715] (3/8) Epoch 15, batch 17600, loss[loss=0.1041, simple_loss=0.1787, pruned_loss=0.01477, over 4914.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02955, over 972389.54 frames.], batch size: 23, lr: 1.47e-04
+2022-05-08 10:34:32,815 INFO [train.py:715] (3/8) Epoch 15, batch 17650, loss[loss=0.1032, simple_loss=0.1694, pruned_loss=0.01852, over 4819.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02928, over 973391.33 frames.], batch size: 13, lr: 1.47e-04
+2022-05-08 10:35:11,436 INFO [train.py:715] (3/8) Epoch 15, batch 17700, loss[loss=0.1233, simple_loss=0.1982, pruned_loss=0.02416, over 4749.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.0292, over 973818.34 frames.], batch size: 12, lr: 1.47e-04
+2022-05-08 10:35:50,325 INFO [train.py:715] (3/8) Epoch 15, batch 17750, loss[loss=0.135, simple_loss=0.2106, pruned_loss=0.02972, over 4923.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02909, over 973596.30 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 10:36:28,685 INFO [train.py:715] (3/8) Epoch 15, batch 17800, loss[loss=0.1725, simple_loss=0.2497, pruned_loss=0.04763, over 4702.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02887, over 972353.98 frames.], batch size: 15, lr: 1.47e-04
+2022-05-08 10:37:07,668 INFO [train.py:715] (3/8) Epoch 15, batch 17850, loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03293, over 4769.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02923, over 971934.01 frames.], batch size: 17, lr: 1.47e-04
+2022-05-08 10:37:46,658 INFO [train.py:715] (3/8) Epoch 15, batch 17900, loss[loss=0.1169, simple_loss=0.1881, pruned_loss=0.02288, over 4875.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2064, pruned_loss=0.02946, over 972476.66 frames.], batch size: 16, lr: 1.47e-04
+2022-05-08 10:38:25,489 INFO [train.py:715] (3/8) Epoch 15, batch 17950, loss[loss=0.1123, simple_loss=0.1892, pruned_loss=0.01769, over 4777.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02941, over 972344.71 frames.], batch size: 18, lr: 1.47e-04
+2022-05-08 10:39:03,820 INFO [train.py:715] (3/8) Epoch 15, batch 18000, loss[loss=0.1626, simple_loss=0.2456, pruned_loss=0.03981, over 4954.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02947, over 972344.69 frames.], batch size: 39, lr: 1.47e-04
+2022-05-08 10:39:03,821 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 10:39:13,328 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.1048, simple_loss=0.1885, pruned_loss=0.01059, over 914524.00 frames.
+2022-05-08 10:39:51,811 INFO [train.py:715] (3/8) Epoch 15, batch 18050, loss[loss=0.115, simple_loss=0.1868, pruned_loss=0.02166, over 4771.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02947, over 972579.99 frames.], batch size: 12, lr: 1.47e-04
+2022-05-08 10:40:30,480 INFO [train.py:715] (3/8) Epoch 15, batch 18100, loss[loss=0.1241, simple_loss=0.1967, pruned_loss=0.0258, over 4783.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02977, over 972980.52 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 10:41:09,235 INFO [train.py:715] (3/8) Epoch 15, batch 18150, loss[loss=0.157, simple_loss=0.2315, pruned_loss=0.04131, over 4872.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02962, over 972892.74 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 10:41:47,122 INFO [train.py:715] (3/8) Epoch 15, batch 18200, loss[loss=0.1371, simple_loss=0.208, pruned_loss=0.03307, over 4863.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02923, over 972041.24 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 10:42:25,785 INFO [train.py:715] (3/8) Epoch 15, batch 18250, loss[loss=0.1469, simple_loss=0.2288, pruned_loss=0.03244, over 4967.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02945, over 971965.30 frames.], batch size: 24, lr: 1.46e-04
+2022-05-08 10:43:04,446 INFO [train.py:715] (3/8) Epoch 15, batch 18300, loss[loss=0.1369, simple_loss=0.2148, pruned_loss=0.02948, over 4871.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2087, pruned_loss=0.02989, over 971413.76 frames.], batch size: 20, lr: 1.46e-04
+2022-05-08 10:43:42,535 INFO [train.py:715] (3/8) Epoch 15, batch 18350, loss[loss=0.1521, simple_loss=0.2374, pruned_loss=0.03335, over 4813.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.0302, over 971214.81 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 10:44:21,123 INFO [train.py:715] (3/8) Epoch 15, batch 18400, loss[loss=0.1246, simple_loss=0.1999, pruned_loss=0.02463, over 4979.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2097, pruned_loss=0.03077, over 971458.25 frames.], batch size: 28, lr: 1.46e-04
+2022-05-08 10:44:59,620 INFO [train.py:715] (3/8) Epoch 15, batch 18450, loss[loss=0.1316, simple_loss=0.2066, pruned_loss=0.02833, over 4903.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03085, over 970959.85 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 10:45:38,881 INFO [train.py:715] (3/8) Epoch 15, batch 18500, loss[loss=0.1288, simple_loss=0.2048, pruned_loss=0.02645, over 4845.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03046, over 970957.07 frames.], batch size: 20, lr: 1.46e-04
+2022-05-08 10:46:17,376 INFO [train.py:715] (3/8) Epoch 15, batch 18550, loss[loss=0.1305, simple_loss=0.2031, pruned_loss=0.02898, over 4847.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03075, over 971482.36 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 10:46:55,965 INFO [train.py:715] (3/8) Epoch 15, batch 18600, loss[loss=0.1252, simple_loss=0.2097, pruned_loss=0.02038, over 4903.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.0305, over 971579.54 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 10:47:34,881 INFO [train.py:715] (3/8) Epoch 15, batch 18650, loss[loss=0.1387, simple_loss=0.2032, pruned_loss=0.03708, over 4886.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03085, over 972082.47 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 10:48:13,537 INFO [train.py:715] (3/8) Epoch 15, batch 18700, loss[loss=0.1144, simple_loss=0.1892, pruned_loss=0.01981, over 4938.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03091, over 972778.26 frames.], batch size: 35, lr: 1.46e-04
+2022-05-08 10:48:52,386 INFO [train.py:715] (3/8) Epoch 15, batch 18750, loss[loss=0.1396, simple_loss=0.2063, pruned_loss=0.03649, over 4949.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03056, over 972635.59 frames.], batch size: 21, lr: 1.46e-04
+2022-05-08 10:49:31,674 INFO [train.py:715] (3/8) Epoch 15, batch 18800, loss[loss=0.0917, simple_loss=0.1657, pruned_loss=0.008847, over 4869.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03054, over 972265.14 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 10:50:10,918 INFO [train.py:715] (3/8) Epoch 15, batch 18850, loss[loss=0.1372, simple_loss=0.2126, pruned_loss=0.03087, over 4943.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.03062, over 972730.35 frames.], batch size: 29, lr: 1.46e-04
+2022-05-08 10:50:49,339 INFO [train.py:715] (3/8) Epoch 15, batch 18900, loss[loss=0.1552, simple_loss=0.2276, pruned_loss=0.04137, over 4948.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2085, pruned_loss=0.03113, over 972928.29 frames.], batch size: 39, lr: 1.46e-04
+2022-05-08 10:51:28,550 INFO [train.py:715] (3/8) Epoch 15, batch 18950, loss[loss=0.1175, simple_loss=0.1924, pruned_loss=0.02129, over 4758.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2089, pruned_loss=0.03112, over 973888.59 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 10:52:07,869 INFO [train.py:715] (3/8) Epoch 15, batch 19000, loss[loss=0.1521, simple_loss=0.2221, pruned_loss=0.04103, over 4701.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03068, over 973886.37 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 10:52:46,222 INFO [train.py:715] (3/8) Epoch 15, batch 19050, loss[loss=0.139, simple_loss=0.2082, pruned_loss=0.03493, over 4869.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03032, over 973144.64 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 10:53:25,396 INFO [train.py:715] (3/8) Epoch 15, batch 19100, loss[loss=0.1645, simple_loss=0.246, pruned_loss=0.04154, over 4949.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03049, over 974011.91 frames.], batch size: 21, lr: 1.46e-04
+2022-05-08 10:54:03,701 INFO [train.py:715] (3/8) Epoch 15, batch 19150, loss[loss=0.1503, simple_loss=0.2238, pruned_loss=0.03843, over 4879.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03069, over 973826.05 frames.], batch size: 22, lr: 1.46e-04
+2022-05-08 10:54:41,931 INFO [train.py:715] (3/8) Epoch 15, batch 19200, loss[loss=0.1569, simple_loss=0.227, pruned_loss=0.04341, over 4761.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03071, over 973872.70 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 10:55:19,948 INFO [train.py:715] (3/8) Epoch 15, batch 19250, loss[loss=0.1148, simple_loss=0.1911, pruned_loss=0.01928, over 4826.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03053, over 973039.50 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 10:55:58,067 INFO [train.py:715] (3/8) Epoch 15, batch 19300, loss[loss=0.1507, simple_loss=0.2203, pruned_loss=0.04055, over 4754.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03063, over 972378.01 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 10:56:36,952 INFO [train.py:715] (3/8) Epoch 15, batch 19350, loss[loss=0.134, simple_loss=0.198, pruned_loss=0.03502, over 4961.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03067, over 972303.60 frames.], batch size: 35, lr: 1.46e-04
+2022-05-08 10:57:14,730 INFO [train.py:715] (3/8) Epoch 15, batch 19400, loss[loss=0.1331, simple_loss=0.2136, pruned_loss=0.0263, over 4834.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03065, over 971165.72 frames.], batch size: 30, lr: 1.46e-04
+2022-05-08 10:57:53,616 INFO [train.py:715] (3/8) Epoch 15, batch 19450, loss[loss=0.1179, simple_loss=0.1909, pruned_loss=0.0225, over 4809.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.0303, over 971101.23 frames.], batch size: 21, lr: 1.46e-04
+2022-05-08 10:58:31,637 INFO [train.py:715] (3/8) Epoch 15, batch 19500, loss[loss=0.119, simple_loss=0.1916, pruned_loss=0.02313, over 4810.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02984, over 970666.85 frames.], batch size: 27, lr: 1.46e-04
+2022-05-08 10:59:09,772 INFO [train.py:715] (3/8) Epoch 15, batch 19550, loss[loss=0.1271, simple_loss=0.1884, pruned_loss=0.03288, over 4825.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03019, over 970433.57 frames.], batch size: 13, lr: 1.46e-04
+2022-05-08 10:59:48,219 INFO [train.py:715] (3/8) Epoch 15, batch 19600, loss[loss=0.1198, simple_loss=0.1944, pruned_loss=0.02265, over 4856.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02989, over 970781.01 frames.], batch size: 30, lr: 1.46e-04
+2022-05-08 11:00:26,255 INFO [train.py:715] (3/8) Epoch 15, batch 19650, loss[loss=0.1825, simple_loss=0.2521, pruned_loss=0.05645, over 4825.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02999, over 970612.22 frames.], batch size: 26, lr: 1.46e-04
+2022-05-08 11:01:05,293 INFO [train.py:715] (3/8) Epoch 15, batch 19700, loss[loss=0.1564, simple_loss=0.2348, pruned_loss=0.03902, over 4750.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03023, over 971347.96 frames.], batch size: 14, lr: 1.46e-04
+2022-05-08 11:01:42,989 INFO [train.py:715] (3/8) Epoch 15, batch 19750, loss[loss=0.1335, simple_loss=0.196, pruned_loss=0.03551, over 4835.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02976, over 972343.28 frames.], batch size: 30, lr: 1.46e-04
+2022-05-08 11:02:21,392 INFO [train.py:715] (3/8) Epoch 15, batch 19800, loss[loss=0.125, simple_loss=0.1893, pruned_loss=0.03034, over 4799.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03001, over 972295.00 frames.], batch size: 12, lr: 1.46e-04
+2022-05-08 11:02:59,699 INFO [train.py:715] (3/8) Epoch 15, batch 19850, loss[loss=0.1508, simple_loss=0.2191, pruned_loss=0.04119, over 4869.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03025, over 971688.07 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 11:03:37,787 INFO [train.py:715] (3/8) Epoch 15, batch 19900, loss[loss=0.1498, simple_loss=0.228, pruned_loss=0.03581, over 4906.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02965, over 972083.40 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 11:04:16,958 INFO [train.py:715] (3/8) Epoch 15, batch 19950, loss[loss=0.1422, simple_loss=0.2117, pruned_loss=0.03636, over 4919.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03004, over 972404.36 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 11:04:55,170 INFO [train.py:715] (3/8) Epoch 15, batch 20000, loss[loss=0.1185, simple_loss=0.1984, pruned_loss=0.01934, over 4830.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.0298, over 971812.23 frames.], batch size: 26, lr: 1.46e-04
+2022-05-08 11:05:33,568 INFO [train.py:715] (3/8) Epoch 15, batch 20050, loss[loss=0.1178, simple_loss=0.1962, pruned_loss=0.01971, over 4805.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02979, over 971326.99 frames.], batch size: 21, lr: 1.46e-04
+2022-05-08 11:06:11,840 INFO [train.py:715] (3/8) Epoch 15, batch 20100, loss[loss=0.1502, simple_loss=0.2212, pruned_loss=0.03955, over 4976.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03034, over 972157.87 frames.], batch size: 25, lr: 1.46e-04
+2022-05-08 11:06:50,119 INFO [train.py:715] (3/8) Epoch 15, batch 20150, loss[loss=0.1513, simple_loss=0.2256, pruned_loss=0.03849, over 4913.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02965, over 972663.49 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 11:07:28,126 INFO [train.py:715] (3/8) Epoch 15, batch 20200, loss[loss=0.1088, simple_loss=0.1798, pruned_loss=0.01884, over 4778.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02957, over 972879.91 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 11:08:05,821 INFO [train.py:715] (3/8) Epoch 15, batch 20250, loss[loss=0.1379, simple_loss=0.2091, pruned_loss=0.03339, over 4785.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02981, over 972554.81 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 11:08:44,518 INFO [train.py:715] (3/8) Epoch 15, batch 20300, loss[loss=0.1289, simple_loss=0.2078, pruned_loss=0.025, over 4983.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02996, over 973679.97 frames.], batch size: 25, lr: 1.46e-04
+2022-05-08 11:09:22,706 INFO [train.py:715] (3/8) Epoch 15, batch 20350, loss[loss=0.1248, simple_loss=0.1951, pruned_loss=0.0272, over 4781.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03044, over 973989.40 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 11:10:01,092 INFO [train.py:715] (3/8) Epoch 15, batch 20400, loss[loss=0.1193, simple_loss=0.2001, pruned_loss=0.01923, over 4944.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03059, over 973314.11 frames.], batch size: 21, lr: 1.46e-04
+2022-05-08 11:10:38,949 INFO [train.py:715] (3/8) Epoch 15, batch 20450, loss[loss=0.1392, simple_loss=0.2148, pruned_loss=0.03181, over 4967.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03037, over 973035.58 frames.], batch size: 39, lr: 1.46e-04
+2022-05-08 11:11:17,699 INFO [train.py:715] (3/8) Epoch 15, batch 20500, loss[loss=0.1308, simple_loss=0.2034, pruned_loss=0.0291, over 4915.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03051, over 972472.85 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 11:11:55,872 INFO [train.py:715] (3/8) Epoch 15, batch 20550, loss[loss=0.1624, simple_loss=0.2222, pruned_loss=0.05125, over 4919.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03062, over 972660.57 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 11:12:33,921 INFO [train.py:715] (3/8) Epoch 15, batch 20600, loss[loss=0.1372, simple_loss=0.2073, pruned_loss=0.03358, over 4781.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03027, over 972268.56 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 11:13:12,981 INFO [train.py:715] (3/8) Epoch 15, batch 20650, loss[loss=0.1117, simple_loss=0.1832, pruned_loss=0.02013, over 4871.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02991, over 973275.16 frames.], batch size: 32, lr: 1.46e-04
+2022-05-08 11:13:51,739 INFO [train.py:715] (3/8) Epoch 15, batch 20700, loss[loss=0.1133, simple_loss=0.1974, pruned_loss=0.01458, over 4985.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02928, over 973921.26 frames.], batch size: 28, lr: 1.46e-04
+2022-05-08 11:14:31,084 INFO [train.py:715] (3/8) Epoch 15, batch 20750, loss[loss=0.1242, simple_loss=0.1941, pruned_loss=0.02718, over 4991.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02927, over 973281.80 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 11:15:09,388 INFO [train.py:715] (3/8) Epoch 15, batch 20800, loss[loss=0.1345, simple_loss=0.2075, pruned_loss=0.03078, over 4782.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02903, over 972828.03 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 11:15:48,765 INFO [train.py:715] (3/8) Epoch 15, batch 20850, loss[loss=0.1369, simple_loss=0.2179, pruned_loss=0.02794, over 4828.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.0294, over 972283.07 frames.], batch size: 26, lr: 1.46e-04
+2022-05-08 11:16:27,992 INFO [train.py:715] (3/8) Epoch 15, batch 20900, loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03169, over 4952.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03012, over 972625.58 frames.], batch size: 24, lr: 1.46e-04
+2022-05-08 11:17:06,244 INFO [train.py:715] (3/8) Epoch 15, batch 20950, loss[loss=0.1403, simple_loss=0.2194, pruned_loss=0.03058, over 4957.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03022, over 972013.71 frames.], batch size: 21, lr: 1.46e-04
+2022-05-08 11:17:45,528 INFO [train.py:715] (3/8) Epoch 15, batch 21000, loss[loss=0.1279, simple_loss=0.1997, pruned_loss=0.02806, over 4938.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03022, over 972545.70 frames.], batch size: 23, lr: 1.46e-04
+2022-05-08 11:17:45,529 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 11:17:56,037 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01075, over 914524.00 frames.
+2022-05-08 11:18:35,288 INFO [train.py:715] (3/8) Epoch 15, batch 21050, loss[loss=0.1129, simple_loss=0.1841, pruned_loss=0.02089, over 4848.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03003, over 973377.98 frames.], batch size: 13, lr: 1.46e-04
+2022-05-08 11:19:14,770 INFO [train.py:715] (3/8) Epoch 15, batch 21100, loss[loss=0.1106, simple_loss=0.1889, pruned_loss=0.01619, over 4831.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02988, over 973852.75 frames.], batch size: 25, lr: 1.46e-04
+2022-05-08 11:19:53,788 INFO [train.py:715] (3/8) Epoch 15, batch 21150, loss[loss=0.1551, simple_loss=0.2287, pruned_loss=0.04077, over 4915.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02998, over 974171.67 frames.], batch size: 23, lr: 1.46e-04
+2022-05-08 11:20:32,268 INFO [train.py:715] (3/8) Epoch 15, batch 21200, loss[loss=0.1304, simple_loss=0.2014, pruned_loss=0.02974, over 4787.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03048, over 973656.85 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 11:21:11,106 INFO [train.py:715] (3/8) Epoch 15, batch 21250, loss[loss=0.1406, simple_loss=0.2246, pruned_loss=0.02832, over 4757.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03054, over 974521.46 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 11:21:49,146 INFO [train.py:715] (3/8) Epoch 15, batch 21300, loss[loss=0.1277, simple_loss=0.2031, pruned_loss=0.0261, over 4886.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03052, over 974274.68 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 11:22:26,789 INFO [train.py:715] (3/8) Epoch 15, batch 21350, loss[loss=0.1309, simple_loss=0.2035, pruned_loss=0.02921, over 4811.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03011, over 973522.26 frames.], batch size: 27, lr: 1.46e-04
+2022-05-08 11:23:05,097 INFO [train.py:715] (3/8) Epoch 15, batch 21400, loss[loss=0.1318, simple_loss=0.1993, pruned_loss=0.0321, over 4903.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03006, over 972701.77 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 11:23:43,354 INFO [train.py:715] (3/8) Epoch 15, batch 21450, loss[loss=0.138, simple_loss=0.2058, pruned_loss=0.0351, over 4882.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03067, over 972642.48 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 11:24:21,358 INFO [train.py:715] (3/8) Epoch 15, batch 21500, loss[loss=0.1473, simple_loss=0.2109, pruned_loss=0.04181, over 4793.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03062, over 972490.65 frames.], batch size: 24, lr: 1.46e-04
+2022-05-08 11:24:59,648 INFO [train.py:715] (3/8) Epoch 15, batch 21550, loss[loss=0.1553, simple_loss=0.2185, pruned_loss=0.0461, over 4751.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03018, over 972485.26 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 11:25:38,153 INFO [train.py:715] (3/8) Epoch 15, batch 21600, loss[loss=0.1082, simple_loss=0.1945, pruned_loss=0.011, over 4933.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02986, over 973004.47 frames.], batch size: 29, lr: 1.46e-04
+2022-05-08 11:26:16,021 INFO [train.py:715] (3/8) Epoch 15, batch 21650, loss[loss=0.1105, simple_loss=0.1747, pruned_loss=0.02317, over 4819.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03003, over 972806.14 frames.], batch size: 12, lr: 1.46e-04
+2022-05-08 11:26:54,240 INFO [train.py:715] (3/8) Epoch 15, batch 21700, loss[loss=0.1371, simple_loss=0.1996, pruned_loss=0.03725, over 4714.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03018, over 973050.04 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 11:27:32,378 INFO [train.py:715] (3/8) Epoch 15, batch 21750, loss[loss=0.1084, simple_loss=0.1795, pruned_loss=0.01867, over 4781.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03044, over 973298.38 frames.], batch size: 14, lr: 1.46e-04
+2022-05-08 11:28:10,477 INFO [train.py:715] (3/8) Epoch 15, batch 21800, loss[loss=0.1329, simple_loss=0.2026, pruned_loss=0.03154, over 4801.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02996, over 972806.08 frames.], batch size: 24, lr: 1.46e-04
+2022-05-08 11:28:48,404 INFO [train.py:715] (3/8) Epoch 15, batch 21850, loss[loss=0.151, simple_loss=0.2227, pruned_loss=0.03964, over 4850.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02971, over 972477.56 frames.], batch size: 30, lr: 1.46e-04
+2022-05-08 11:29:29,585 INFO [train.py:715] (3/8) Epoch 15, batch 21900, loss[loss=0.1178, simple_loss=0.1942, pruned_loss=0.02067, over 4826.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03017, over 972189.07 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 11:30:08,737 INFO [train.py:715] (3/8) Epoch 15, batch 21950, loss[loss=0.1155, simple_loss=0.1918, pruned_loss=0.01959, over 4854.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.0298, over 972881.80 frames.], batch size: 13, lr: 1.46e-04
+2022-05-08 11:30:47,270 INFO [train.py:715] (3/8) Epoch 15, batch 22000, loss[loss=0.1223, simple_loss=0.1942, pruned_loss=0.02526, over 4923.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02993, over 973445.38 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 11:31:25,791 INFO [train.py:715] (3/8) Epoch 15, batch 22050, loss[loss=0.145, simple_loss=0.2225, pruned_loss=0.03377, over 4980.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03011, over 973668.52 frames.], batch size: 24, lr: 1.46e-04
+2022-05-08 11:32:05,114 INFO [train.py:715] (3/8) Epoch 15, batch 22100, loss[loss=0.1461, simple_loss=0.2252, pruned_loss=0.03354, over 4752.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03027, over 973063.14 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 11:32:43,915 INFO [train.py:715] (3/8) Epoch 15, batch 22150, loss[loss=0.1497, simple_loss=0.2333, pruned_loss=0.03304, over 4831.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02993, over 973948.16 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 11:33:22,286 INFO [train.py:715] (3/8) Epoch 15, batch 22200, loss[loss=0.09475, simple_loss=0.1669, pruned_loss=0.01128, over 4759.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03006, over 973187.49 frames.], batch size: 12, lr: 1.46e-04
+2022-05-08 11:34:01,327 INFO [train.py:715] (3/8) Epoch 15, batch 22250, loss[loss=0.1231, simple_loss=0.2033, pruned_loss=0.02142, over 4753.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03046, over 973096.78 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 11:34:40,259 INFO [train.py:715] (3/8) Epoch 15, batch 22300, loss[loss=0.1449, simple_loss=0.2175, pruned_loss=0.03609, over 4782.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03039, over 973103.95 frames.], batch size: 14, lr: 1.46e-04
+2022-05-08 11:35:18,795 INFO [train.py:715] (3/8) Epoch 15, batch 22350, loss[loss=0.1405, simple_loss=0.2062, pruned_loss=0.03739, over 4808.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03034, over 972100.99 frames.], batch size: 25, lr: 1.46e-04
+2022-05-08 11:35:57,367 INFO [train.py:715] (3/8) Epoch 15, batch 22400, loss[loss=0.1364, simple_loss=0.2114, pruned_loss=0.03071, over 4819.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03094, over 971834.95 frames.], batch size: 26, lr: 1.46e-04
+2022-05-08 11:36:36,630 INFO [train.py:715] (3/8) Epoch 15, batch 22450, loss[loss=0.1134, simple_loss=0.1896, pruned_loss=0.01861, over 4796.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03096, over 971563.60 frames.], batch size: 13, lr: 1.46e-04
+2022-05-08 11:37:15,519 INFO [train.py:715] (3/8) Epoch 15, batch 22500, loss[loss=0.1388, simple_loss=0.2189, pruned_loss=0.02939, over 4913.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03038, over 971223.87 frames.], batch size: 23, lr: 1.46e-04
+2022-05-08 11:37:54,243 INFO [train.py:715] (3/8) Epoch 15, batch 22550, loss[loss=0.1159, simple_loss=0.1905, pruned_loss=0.02064, over 4832.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03022, over 971365.81 frames.], batch size: 13, lr: 1.46e-04
+2022-05-08 11:38:32,799 INFO [train.py:715] (3/8) Epoch 15, batch 22600, loss[loss=0.1274, simple_loss=0.1958, pruned_loss=0.02955, over 4930.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03061, over 971575.06 frames.], batch size: 29, lr: 1.46e-04
+2022-05-08 11:39:11,720 INFO [train.py:715] (3/8) Epoch 15, batch 22650, loss[loss=0.1156, simple_loss=0.1863, pruned_loss=0.02243, over 4968.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03059, over 971993.40 frames.], batch size: 24, lr: 1.46e-04
+2022-05-08 11:39:50,376 INFO [train.py:715] (3/8) Epoch 15, batch 22700, loss[loss=0.1484, simple_loss=0.2147, pruned_loss=0.04105, over 4753.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03052, over 972029.32 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 11:40:29,113 INFO [train.py:715] (3/8) Epoch 15, batch 22750, loss[loss=0.1471, simple_loss=0.2247, pruned_loss=0.03472, over 4915.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.02995, over 973274.93 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 11:41:08,458 INFO [train.py:715] (3/8) Epoch 15, batch 22800, loss[loss=0.1553, simple_loss=0.2261, pruned_loss=0.04228, over 4761.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03018, over 972817.12 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 11:41:47,282 INFO [train.py:715] (3/8) Epoch 15, batch 22850, loss[loss=0.1445, simple_loss=0.2114, pruned_loss=0.03877, over 4769.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03039, over 972634.52 frames.], batch size: 14, lr: 1.46e-04
+2022-05-08 11:42:26,024 INFO [train.py:715] (3/8) Epoch 15, batch 22900, loss[loss=0.1012, simple_loss=0.1799, pruned_loss=0.01129, over 4808.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2093, pruned_loss=0.02997, over 972332.81 frames.], batch size: 25, lr: 1.46e-04
+2022-05-08 11:43:05,210 INFO [train.py:715] (3/8) Epoch 15, batch 22950, loss[loss=0.1296, simple_loss=0.2118, pruned_loss=0.02368, over 4938.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02974, over 973158.41 frames.], batch size: 21, lr: 1.46e-04
+2022-05-08 11:43:43,833 INFO [train.py:715] (3/8) Epoch 15, batch 23000, loss[loss=0.1274, simple_loss=0.1986, pruned_loss=0.02805, over 4851.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02971, over 972923.83 frames.], batch size: 20, lr: 1.46e-04
+2022-05-08 11:44:22,239 INFO [train.py:715] (3/8) Epoch 15, batch 23050, loss[loss=0.1535, simple_loss=0.2351, pruned_loss=0.03597, over 4827.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03008, over 972624.74 frames.], batch size: 25, lr: 1.46e-04
+2022-05-08 11:45:00,631 INFO [train.py:715] (3/8) Epoch 15, batch 23100, loss[loss=0.1054, simple_loss=0.1713, pruned_loss=0.0198, over 4798.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03008, over 971689.01 frames.], batch size: 14, lr: 1.46e-04
+2022-05-08 11:45:39,481 INFO [train.py:715] (3/8) Epoch 15, batch 23150, loss[loss=0.1349, simple_loss=0.21, pruned_loss=0.02993, over 4925.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02992, over 972017.89 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 11:46:17,453 INFO [train.py:715] (3/8) Epoch 15, batch 23200, loss[loss=0.1309, simple_loss=0.1952, pruned_loss=0.03335, over 4795.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02994, over 972148.39 frames.], batch size: 12, lr: 1.46e-04
+2022-05-08 11:46:55,709 INFO [train.py:715] (3/8) Epoch 15, batch 23250, loss[loss=0.1191, simple_loss=0.1917, pruned_loss=0.02327, over 4882.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03008, over 972348.40 frames.], batch size: 22, lr: 1.46e-04
+2022-05-08 11:47:34,387 INFO [train.py:715] (3/8) Epoch 15, batch 23300, loss[loss=0.1581, simple_loss=0.2123, pruned_loss=0.05198, over 4834.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02966, over 971591.67 frames.], batch size: 13, lr: 1.46e-04
+2022-05-08 11:48:12,429 INFO [train.py:715] (3/8) Epoch 15, batch 23350, loss[loss=0.1545, simple_loss=0.234, pruned_loss=0.03745, over 4778.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02979, over 970969.56 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 11:48:50,740 INFO [train.py:715] (3/8) Epoch 15, batch 23400, loss[loss=0.1464, simple_loss=0.2077, pruned_loss=0.04258, over 4845.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02999, over 971590.37 frames.], batch size: 30, lr: 1.46e-04
+2022-05-08 11:49:28,563 INFO [train.py:715] (3/8) Epoch 15, batch 23450, loss[loss=0.1232, simple_loss=0.2019, pruned_loss=0.02219, over 4873.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.0298, over 971006.70 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 11:50:07,086 INFO [train.py:715] (3/8) Epoch 15, batch 23500, loss[loss=0.1254, simple_loss=0.1906, pruned_loss=0.03009, over 4825.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02951, over 970971.81 frames.], batch size: 12, lr: 1.46e-04
+2022-05-08 11:50:44,860 INFO [train.py:715] (3/8) Epoch 15, batch 23550, loss[loss=0.158, simple_loss=0.229, pruned_loss=0.0435, over 4837.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02987, over 972103.10 frames.], batch size: 26, lr: 1.46e-04
+2022-05-08 11:51:22,855 INFO [train.py:715] (3/8) Epoch 15, batch 23600, loss[loss=0.1459, simple_loss=0.2173, pruned_loss=0.03724, over 4929.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02927, over 972018.80 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 11:52:01,280 INFO [train.py:715] (3/8) Epoch 15, batch 23650, loss[loss=0.1082, simple_loss=0.1796, pruned_loss=0.01838, over 4834.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02936, over 971880.77 frames.], batch size: 13, lr: 1.46e-04
+2022-05-08 11:52:39,168 INFO [train.py:715] (3/8) Epoch 15, batch 23700, loss[loss=0.1067, simple_loss=0.1691, pruned_loss=0.02217, over 4750.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2059, pruned_loss=0.02928, over 971948.28 frames.], batch size: 14, lr: 1.46e-04
+2022-05-08 11:53:17,232 INFO [train.py:715] (3/8) Epoch 15, batch 23750, loss[loss=0.1382, simple_loss=0.207, pruned_loss=0.03467, over 4655.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.0294, over 972289.21 frames.], batch size: 13, lr: 1.46e-04
+2022-05-08 11:53:55,059 INFO [train.py:715] (3/8) Epoch 15, batch 23800, loss[loss=0.1177, simple_loss=0.1915, pruned_loss=0.02193, over 4754.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02937, over 972600.84 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 11:54:33,046 INFO [train.py:715] (3/8) Epoch 15, batch 23850, loss[loss=0.1525, simple_loss=0.2236, pruned_loss=0.04074, over 4640.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02963, over 972414.29 frames.], batch size: 13, lr: 1.46e-04
+2022-05-08 11:55:11,364 INFO [train.py:715] (3/8) Epoch 15, batch 23900, loss[loss=0.1689, simple_loss=0.2323, pruned_loss=0.05281, over 4975.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03024, over 972022.18 frames.], batch size: 35, lr: 1.46e-04
+2022-05-08 11:55:48,901 INFO [train.py:715] (3/8) Epoch 15, batch 23950, loss[loss=0.1392, simple_loss=0.2092, pruned_loss=0.03467, over 4941.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.03013, over 972331.06 frames.], batch size: 21, lr: 1.46e-04
+2022-05-08 11:56:27,443 INFO [train.py:715] (3/8) Epoch 15, batch 24000, loss[loss=0.1673, simple_loss=0.2252, pruned_loss=0.05473, over 4841.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2072, pruned_loss=0.03019, over 972254.68 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 11:56:27,444 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 11:56:37,033 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.105, simple_loss=0.1886, pruned_loss=0.01071, over 914524.00 frames.
+2022-05-08 11:57:15,622 INFO [train.py:715] (3/8) Epoch 15, batch 24050, loss[loss=0.1538, simple_loss=0.2214, pruned_loss=0.04309, over 4835.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.03004, over 971677.69 frames.], batch size: 30, lr: 1.46e-04
+2022-05-08 11:57:54,188 INFO [train.py:715] (3/8) Epoch 15, batch 24100, loss[loss=0.1189, simple_loss=0.1989, pruned_loss=0.01939, over 4838.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2061, pruned_loss=0.02954, over 971598.61 frames.], batch size: 30, lr: 1.46e-04
+2022-05-08 11:58:32,193 INFO [train.py:715] (3/8) Epoch 15, batch 24150, loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04387, over 4788.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2062, pruned_loss=0.02941, over 971046.34 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 11:59:10,406 INFO [train.py:715] (3/8) Epoch 15, batch 24200, loss[loss=0.1293, simple_loss=0.2018, pruned_loss=0.0284, over 4872.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03009, over 971643.44 frames.], batch size: 16, lr: 1.46e-04
+2022-05-08 11:59:48,422 INFO [train.py:715] (3/8) Epoch 15, batch 24250, loss[loss=0.1248, simple_loss=0.1974, pruned_loss=0.02612, over 4976.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02988, over 971464.53 frames.], batch size: 24, lr: 1.46e-04
+2022-05-08 12:00:26,748 INFO [train.py:715] (3/8) Epoch 15, batch 24300, loss[loss=0.1349, simple_loss=0.2048, pruned_loss=0.03252, over 4803.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03008, over 971497.39 frames.], batch size: 14, lr: 1.46e-04
+2022-05-08 12:01:03,899 INFO [train.py:715] (3/8) Epoch 15, batch 24350, loss[loss=0.1157, simple_loss=0.2021, pruned_loss=0.01469, over 4816.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02935, over 971166.93 frames.], batch size: 27, lr: 1.46e-04
+2022-05-08 12:01:42,323 INFO [train.py:715] (3/8) Epoch 15, batch 24400, loss[loss=0.1252, simple_loss=0.2098, pruned_loss=0.0203, over 4832.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02905, over 970568.64 frames.], batch size: 25, lr: 1.46e-04
+2022-05-08 12:02:20,846 INFO [train.py:715] (3/8) Epoch 15, batch 24450, loss[loss=0.1065, simple_loss=0.1826, pruned_loss=0.01522, over 4704.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02908, over 971330.13 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 12:02:58,826 INFO [train.py:715] (3/8) Epoch 15, batch 24500, loss[loss=0.1516, simple_loss=0.2142, pruned_loss=0.04447, over 4688.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02918, over 971142.34 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 12:03:36,485 INFO [train.py:715] (3/8) Epoch 15, batch 24550, loss[loss=0.143, simple_loss=0.206, pruned_loss=0.03999, over 4769.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.0291, over 971052.93 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 12:04:14,728 INFO [train.py:715] (3/8) Epoch 15, batch 24600, loss[loss=0.1354, simple_loss=0.2213, pruned_loss=0.02479, over 4961.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02886, over 971580.29 frames.], batch size: 21, lr: 1.46e-04
+2022-05-08 12:04:53,494 INFO [train.py:715] (3/8) Epoch 15, batch 24650, loss[loss=0.1302, simple_loss=0.206, pruned_loss=0.02726, over 4918.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02922, over 971685.82 frames.], batch size: 23, lr: 1.46e-04
+2022-05-08 12:05:31,177 INFO [train.py:715] (3/8) Epoch 15, batch 24700, loss[loss=0.1268, simple_loss=0.1906, pruned_loss=0.03149, over 4905.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2086, pruned_loss=0.02979, over 972076.61 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 12:06:09,581 INFO [train.py:715] (3/8) Epoch 15, batch 24750, loss[loss=0.1289, simple_loss=0.2065, pruned_loss=0.0256, over 4917.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03025, over 973061.80 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 12:06:47,908 INFO [train.py:715] (3/8) Epoch 15, batch 24800, loss[loss=0.1388, simple_loss=0.2172, pruned_loss=0.03019, over 4783.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02998, over 972679.48 frames.], batch size: 14, lr: 1.46e-04
+2022-05-08 12:07:25,660 INFO [train.py:715] (3/8) Epoch 15, batch 24850, loss[loss=0.1351, simple_loss=0.2105, pruned_loss=0.02979, over 4893.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03018, over 973432.42 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 12:08:03,593 INFO [train.py:715] (3/8) Epoch 15, batch 24900, loss[loss=0.1245, simple_loss=0.202, pruned_loss=0.02347, over 4861.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.0306, over 973438.34 frames.], batch size: 22, lr: 1.46e-04
+2022-05-08 12:08:41,839 INFO [train.py:715] (3/8) Epoch 15, batch 24950, loss[loss=0.1401, simple_loss=0.2167, pruned_loss=0.03171, over 4868.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2077, pruned_loss=0.03046, over 973277.23 frames.], batch size: 22, lr: 1.46e-04
+2022-05-08 12:09:20,949 INFO [train.py:715] (3/8) Epoch 15, batch 25000, loss[loss=0.1331, simple_loss=0.2049, pruned_loss=0.03065, over 4925.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03002, over 972369.08 frames.], batch size: 23, lr: 1.46e-04
+2022-05-08 12:09:58,499 INFO [train.py:715] (3/8) Epoch 15, batch 25050, loss[loss=0.1301, simple_loss=0.2027, pruned_loss=0.02873, over 4687.00 frames.], tot_loss[loss=0.134, simple_loss=0.2074, pruned_loss=0.03033, over 972467.58 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 12:10:36,536 INFO [train.py:715] (3/8) Epoch 15, batch 25100, loss[loss=0.154, simple_loss=0.2285, pruned_loss=0.03972, over 4767.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2066, pruned_loss=0.02979, over 971795.39 frames.], batch size: 19, lr: 1.46e-04
+2022-05-08 12:11:14,988 INFO [train.py:715] (3/8) Epoch 15, batch 25150, loss[loss=0.1147, simple_loss=0.1818, pruned_loss=0.02386, over 4830.00 frames.], tot_loss[loss=0.133, simple_loss=0.2066, pruned_loss=0.0297, over 973446.06 frames.], batch size: 25, lr: 1.46e-04
+2022-05-08 12:11:53,004 INFO [train.py:715] (3/8) Epoch 15, batch 25200, loss[loss=0.1541, simple_loss=0.2305, pruned_loss=0.03879, over 4777.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02994, over 973762.06 frames.], batch size: 17, lr: 1.46e-04
+2022-05-08 12:12:30,796 INFO [train.py:715] (3/8) Epoch 15, batch 25250, loss[loss=0.1224, simple_loss=0.197, pruned_loss=0.02388, over 4863.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03016, over 974213.17 frames.], batch size: 20, lr: 1.46e-04
+2022-05-08 12:13:09,121 INFO [train.py:715] (3/8) Epoch 15, batch 25300, loss[loss=0.1288, simple_loss=0.2059, pruned_loss=0.02587, over 4965.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03052, over 974621.75 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 12:13:47,202 INFO [train.py:715] (3/8) Epoch 15, batch 25350, loss[loss=0.104, simple_loss=0.1815, pruned_loss=0.01327, over 4772.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02973, over 974216.17 frames.], batch size: 18, lr: 1.46e-04
+2022-05-08 12:14:24,745 INFO [train.py:715] (3/8) Epoch 15, batch 25400, loss[loss=0.1328, simple_loss=0.2163, pruned_loss=0.02464, over 4707.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02988, over 973356.88 frames.], batch size: 15, lr: 1.46e-04
+2022-05-08 12:15:02,819 INFO [train.py:715] (3/8) Epoch 15, batch 25450, loss[loss=0.1218, simple_loss=0.2041, pruned_loss=0.01975, over 4858.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03064, over 973263.32 frames.], batch size: 20, lr: 1.46e-04
+2022-05-08 12:15:41,209 INFO [train.py:715] (3/8) Epoch 15, batch 25500, loss[loss=0.1375, simple_loss=0.2189, pruned_loss=0.02804, over 4931.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03013, over 974708.58 frames.], batch size: 29, lr: 1.46e-04
+2022-05-08 12:16:18,764 INFO [train.py:715] (3/8) Epoch 15, batch 25550, loss[loss=0.1347, simple_loss=0.2045, pruned_loss=0.03249, over 4855.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02972, over 974267.26 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 12:16:56,915 INFO [train.py:715] (3/8) Epoch 15, batch 25600, loss[loss=0.155, simple_loss=0.2098, pruned_loss=0.05009, over 4829.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.0297, over 973803.70 frames.], batch size: 30, lr: 1.45e-04
+2022-05-08 12:17:35,539 INFO [train.py:715] (3/8) Epoch 15, batch 25650, loss[loss=0.1143, simple_loss=0.1882, pruned_loss=0.02019, over 4807.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03024, over 973250.14 frames.], batch size: 27, lr: 1.45e-04
+2022-05-08 12:18:13,816 INFO [train.py:715] (3/8) Epoch 15, batch 25700, loss[loss=0.1314, simple_loss=0.2105, pruned_loss=0.02614, over 4866.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.0302, over 972954.46 frames.], batch size: 22, lr: 1.45e-04
+2022-05-08 12:18:51,203 INFO [train.py:715] (3/8) Epoch 15, batch 25750, loss[loss=0.1436, simple_loss=0.2082, pruned_loss=0.03951, over 4845.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.02999, over 973289.93 frames.], batch size: 30, lr: 1.45e-04
+2022-05-08 12:19:29,349 INFO [train.py:715] (3/8) Epoch 15, batch 25800, loss[loss=0.1325, simple_loss=0.2218, pruned_loss=0.02161, over 4826.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2092, pruned_loss=0.03, over 973151.78 frames.], batch size: 27, lr: 1.45e-04
+2022-05-08 12:20:07,976 INFO [train.py:715] (3/8) Epoch 15, batch 25850, loss[loss=0.1642, simple_loss=0.2326, pruned_loss=0.0479, over 4862.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2088, pruned_loss=0.02996, over 973425.21 frames.], batch size: 38, lr: 1.45e-04
+2022-05-08 12:20:45,418 INFO [train.py:715] (3/8) Epoch 15, batch 25900, loss[loss=0.1658, simple_loss=0.2349, pruned_loss=0.04829, over 4818.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02967, over 973548.15 frames.], batch size: 15, lr: 1.45e-04
+2022-05-08 12:21:24,014 INFO [train.py:715] (3/8) Epoch 15, batch 25950, loss[loss=0.1281, simple_loss=0.2015, pruned_loss=0.02733, over 4809.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02983, over 973482.29 frames.], batch size: 26, lr: 1.45e-04
+2022-05-08 12:22:02,167 INFO [train.py:715] (3/8) Epoch 15, batch 26000, loss[loss=0.1213, simple_loss=0.1952, pruned_loss=0.02367, over 4799.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03018, over 972049.43 frames.], batch size: 14, lr: 1.45e-04
+2022-05-08 12:22:39,854 INFO [train.py:715] (3/8) Epoch 15, batch 26050, loss[loss=0.122, simple_loss=0.2117, pruned_loss=0.01612, over 4931.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03002, over 971627.85 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 12:23:17,645 INFO [train.py:715] (3/8) Epoch 15, batch 26100, loss[loss=0.1223, simple_loss=0.1957, pruned_loss=0.02439, over 4763.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03016, over 972335.21 frames.], batch size: 19, lr: 1.45e-04
+2022-05-08 12:23:56,077 INFO [train.py:715] (3/8) Epoch 15, batch 26150, loss[loss=0.1459, simple_loss=0.2206, pruned_loss=0.03561, over 4783.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03005, over 972534.43 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 12:24:33,869 INFO [train.py:715] (3/8) Epoch 15, batch 26200, loss[loss=0.1687, simple_loss=0.2334, pruned_loss=0.05198, over 4773.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03016, over 972191.83 frames.], batch size: 12, lr: 1.45e-04
+2022-05-08 12:25:11,686 INFO [train.py:715] (3/8) Epoch 15, batch 26250, loss[loss=0.1395, simple_loss=0.2119, pruned_loss=0.03355, over 4777.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02976, over 971443.75 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 12:25:50,004 INFO [train.py:715] (3/8) Epoch 15, batch 26300, loss[loss=0.1662, simple_loss=0.2432, pruned_loss=0.0446, over 4761.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02989, over 971979.33 frames.], batch size: 19, lr: 1.45e-04
+2022-05-08 12:26:28,462 INFO [train.py:715] (3/8) Epoch 15, batch 26350, loss[loss=0.1367, simple_loss=0.2068, pruned_loss=0.0333, over 4802.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02986, over 971048.13 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 12:27:06,220 INFO [train.py:715] (3/8) Epoch 15, batch 26400, loss[loss=0.1266, simple_loss=0.2012, pruned_loss=0.02602, over 4808.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02997, over 971508.01 frames.], batch size: 25, lr: 1.45e-04
+2022-05-08 12:27:44,351 INFO [train.py:715] (3/8) Epoch 15, batch 26450, loss[loss=0.1152, simple_loss=0.1805, pruned_loss=0.02492, over 4984.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02971, over 971653.22 frames.], batch size: 14, lr: 1.45e-04
+2022-05-08 12:28:22,637 INFO [train.py:715] (3/8) Epoch 15, batch 26500, loss[loss=0.1582, simple_loss=0.2257, pruned_loss=0.0453, over 4807.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2067, pruned_loss=0.02989, over 972113.35 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 12:29:00,419 INFO [train.py:715] (3/8) Epoch 15, batch 26550, loss[loss=0.1453, simple_loss=0.2129, pruned_loss=0.03887, over 4724.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2066, pruned_loss=0.02983, over 972390.14 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 12:29:38,156 INFO [train.py:715] (3/8) Epoch 15, batch 26600, loss[loss=0.1266, simple_loss=0.1944, pruned_loss=0.02943, over 4801.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2062, pruned_loss=0.02979, over 973685.10 frames.], batch size: 14, lr: 1.45e-04
+2022-05-08 12:30:16,189 INFO [train.py:715] (3/8) Epoch 15, batch 26650, loss[loss=0.1277, simple_loss=0.1904, pruned_loss=0.03245, over 4797.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2069, pruned_loss=0.02996, over 973487.99 frames.], batch size: 14, lr: 1.45e-04
+2022-05-08 12:30:54,320 INFO [train.py:715] (3/8) Epoch 15, batch 26700, loss[loss=0.1216, simple_loss=0.2006, pruned_loss=0.02136, over 4977.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2076, pruned_loss=0.03026, over 972458.37 frames.], batch size: 24, lr: 1.45e-04
+2022-05-08 12:31:31,946 INFO [train.py:715] (3/8) Epoch 15, batch 26750, loss[loss=0.1568, simple_loss=0.2361, pruned_loss=0.03872, over 4801.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03079, over 972416.17 frames.], batch size: 25, lr: 1.45e-04
+2022-05-08 12:32:10,364 INFO [train.py:715] (3/8) Epoch 15, batch 26800, loss[loss=0.1313, simple_loss=0.2015, pruned_loss=0.0305, over 4645.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03108, over 971548.48 frames.], batch size: 13, lr: 1.45e-04
+2022-05-08 12:32:48,681 INFO [train.py:715] (3/8) Epoch 15, batch 26850, loss[loss=0.1278, simple_loss=0.2014, pruned_loss=0.02705, over 4990.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03099, over 971317.50 frames.], batch size: 25, lr: 1.45e-04
+2022-05-08 12:33:26,762 INFO [train.py:715] (3/8) Epoch 15, batch 26900, loss[loss=0.1014, simple_loss=0.1759, pruned_loss=0.01342, over 4917.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03013, over 971309.07 frames.], batch size: 29, lr: 1.45e-04
+2022-05-08 12:34:04,503 INFO [train.py:715] (3/8) Epoch 15, batch 26950, loss[loss=0.1266, simple_loss=0.2063, pruned_loss=0.02344, over 4927.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03037, over 971347.83 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 12:34:42,585 INFO [train.py:715] (3/8) Epoch 15, batch 27000, loss[loss=0.1238, simple_loss=0.197, pruned_loss=0.02528, over 4779.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03038, over 971353.18 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 12:34:42,585 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 12:34:52,202 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.1049, simple_loss=0.1884, pruned_loss=0.01064, over 914524.00 frames.
+2022-05-08 12:35:31,298 INFO [train.py:715] (3/8) Epoch 15, batch 27050, loss[loss=0.1528, simple_loss=0.2266, pruned_loss=0.03947, over 4700.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03021, over 971248.57 frames.], batch size: 15, lr: 1.45e-04
+2022-05-08 12:36:10,020 INFO [train.py:715] (3/8) Epoch 15, batch 27100, loss[loss=0.1453, simple_loss=0.2194, pruned_loss=0.03555, over 4880.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03101, over 971547.75 frames.], batch size: 30, lr: 1.45e-04
+2022-05-08 12:36:48,675 INFO [train.py:715] (3/8) Epoch 15, batch 27150, loss[loss=0.1222, simple_loss=0.1861, pruned_loss=0.02915, over 4851.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03087, over 972755.50 frames.], batch size: 32, lr: 1.45e-04
+2022-05-08 12:37:26,866 INFO [train.py:715] (3/8) Epoch 15, batch 27200, loss[loss=0.1218, simple_loss=0.198, pruned_loss=0.02276, over 4696.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03072, over 973020.77 frames.], batch size: 15, lr: 1.45e-04
+2022-05-08 12:38:05,903 INFO [train.py:715] (3/8) Epoch 15, batch 27250, loss[loss=0.1382, simple_loss=0.2152, pruned_loss=0.03056, over 4851.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03066, over 974068.95 frames.], batch size: 30, lr: 1.45e-04
+2022-05-08 12:38:43,694 INFO [train.py:715] (3/8) Epoch 15, batch 27300, loss[loss=0.1245, simple_loss=0.2059, pruned_loss=0.02161, over 4969.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03081, over 974401.34 frames.], batch size: 24, lr: 1.45e-04
+2022-05-08 12:39:21,921 INFO [train.py:715] (3/8) Epoch 15, batch 27350, loss[loss=0.1392, simple_loss=0.2089, pruned_loss=0.03473, over 4777.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03071, over 973887.70 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 12:40:00,097 INFO [train.py:715] (3/8) Epoch 15, batch 27400, loss[loss=0.1315, simple_loss=0.2028, pruned_loss=0.03012, over 4868.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.0307, over 972997.49 frames.], batch size: 20, lr: 1.45e-04
+2022-05-08 12:40:38,397 INFO [train.py:715] (3/8) Epoch 15, batch 27450, loss[loss=0.1354, simple_loss=0.2108, pruned_loss=0.02997, over 4916.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.0307, over 973112.14 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 12:41:16,662 INFO [train.py:715] (3/8) Epoch 15, batch 27500, loss[loss=0.1586, simple_loss=0.2263, pruned_loss=0.04549, over 4877.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03054, over 973408.08 frames.], batch size: 22, lr: 1.45e-04
+2022-05-08 12:41:54,851 INFO [train.py:715] (3/8) Epoch 15, batch 27550, loss[loss=0.1495, simple_loss=0.2331, pruned_loss=0.03293, over 4914.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.0305, over 973920.66 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 12:42:33,403 INFO [train.py:715] (3/8) Epoch 15, batch 27600, loss[loss=0.1293, simple_loss=0.2077, pruned_loss=0.02539, over 4730.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.0304, over 972947.75 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 12:43:10,761 INFO [train.py:715] (3/8) Epoch 15, batch 27650, loss[loss=0.1378, simple_loss=0.2213, pruned_loss=0.02714, over 4898.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03032, over 972691.94 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 12:43:49,460 INFO [train.py:715] (3/8) Epoch 15, batch 27700, loss[loss=0.1178, simple_loss=0.1865, pruned_loss=0.02459, over 4762.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03022, over 972614.35 frames.], batch size: 19, lr: 1.45e-04
+2022-05-08 12:44:27,757 INFO [train.py:715] (3/8) Epoch 15, batch 27750, loss[loss=0.1264, simple_loss=0.2096, pruned_loss=0.02162, over 4932.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03047, over 972352.68 frames.], batch size: 29, lr: 1.45e-04
+2022-05-08 12:45:06,223 INFO [train.py:715] (3/8) Epoch 15, batch 27800, loss[loss=0.1426, simple_loss=0.2101, pruned_loss=0.03754, over 4859.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2069, pruned_loss=0.02966, over 971752.55 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 12:45:44,233 INFO [train.py:715] (3/8) Epoch 15, batch 27850, loss[loss=0.1148, simple_loss=0.188, pruned_loss=0.02078, over 4739.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02963, over 971199.12 frames.], batch size: 12, lr: 1.45e-04
+2022-05-08 12:46:21,974 INFO [train.py:715] (3/8) Epoch 15, batch 27900, loss[loss=0.1161, simple_loss=0.2008, pruned_loss=0.01572, over 4925.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02905, over 971193.19 frames.], batch size: 23, lr: 1.45e-04
+2022-05-08 12:47:00,799 INFO [train.py:715] (3/8) Epoch 15, batch 27950, loss[loss=0.1642, simple_loss=0.2252, pruned_loss=0.05166, over 4848.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02923, over 971398.29 frames.], batch size: 15, lr: 1.45e-04
+2022-05-08 12:47:38,668 INFO [train.py:715] (3/8) Epoch 15, batch 28000, loss[loss=0.1545, simple_loss=0.2253, pruned_loss=0.04186, over 4900.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2063, pruned_loss=0.02942, over 972217.98 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 12:48:16,882 INFO [train.py:715] (3/8) Epoch 15, batch 28050, loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02837, over 4804.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.0296, over 971954.86 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 12:48:55,113 INFO [train.py:715] (3/8) Epoch 15, batch 28100, loss[loss=0.1231, simple_loss=0.1854, pruned_loss=0.03037, over 4725.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02937, over 971222.49 frames.], batch size: 12, lr: 1.45e-04
+2022-05-08 12:49:33,363 INFO [train.py:715] (3/8) Epoch 15, batch 28150, loss[loss=0.1329, simple_loss=0.2124, pruned_loss=0.02666, over 4793.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02924, over 972113.96 frames.], batch size: 14, lr: 1.45e-04
+2022-05-08 12:50:11,124 INFO [train.py:715] (3/8) Epoch 15, batch 28200, loss[loss=0.142, simple_loss=0.2273, pruned_loss=0.02837, over 4934.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2059, pruned_loss=0.02921, over 971962.37 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 12:50:49,027 INFO [train.py:715] (3/8) Epoch 15, batch 28250, loss[loss=0.1341, simple_loss=0.2062, pruned_loss=0.03101, over 4883.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.0295, over 971643.72 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 12:51:28,180 INFO [train.py:715] (3/8) Epoch 15, batch 28300, loss[loss=0.1364, simple_loss=0.2078, pruned_loss=0.03249, over 4785.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2065, pruned_loss=0.0296, over 971794.74 frames.], batch size: 14, lr: 1.45e-04
+2022-05-08 12:52:05,677 INFO [train.py:715] (3/8) Epoch 15, batch 28350, loss[loss=0.1501, simple_loss=0.2208, pruned_loss=0.03969, over 4738.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.0302, over 971955.46 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 12:52:43,906 INFO [train.py:715] (3/8) Epoch 15, batch 28400, loss[loss=0.1378, simple_loss=0.2195, pruned_loss=0.02803, over 4883.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03007, over 972491.62 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 12:53:22,225 INFO [train.py:715] (3/8) Epoch 15, batch 28450, loss[loss=0.1324, simple_loss=0.2024, pruned_loss=0.03115, over 4860.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.0301, over 972760.71 frames.], batch size: 20, lr: 1.45e-04
+2022-05-08 12:54:00,375 INFO [train.py:715] (3/8) Epoch 15, batch 28500, loss[loss=0.1361, simple_loss=0.2167, pruned_loss=0.02782, over 4946.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02978, over 972712.31 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 12:54:38,503 INFO [train.py:715] (3/8) Epoch 15, batch 28550, loss[loss=0.1342, simple_loss=0.2101, pruned_loss=0.02911, over 4879.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03, over 973171.44 frames.], batch size: 32, lr: 1.45e-04
+2022-05-08 12:55:16,670 INFO [train.py:715] (3/8) Epoch 15, batch 28600, loss[loss=0.1302, simple_loss=0.215, pruned_loss=0.02274, over 4759.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02985, over 972727.74 frames.], batch size: 17, lr: 1.45e-04
+2022-05-08 12:55:55,087 INFO [train.py:715] (3/8) Epoch 15, batch 28650, loss[loss=0.1216, simple_loss=0.2034, pruned_loss=0.01987, over 4770.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02974, over 972801.95 frames.], batch size: 17, lr: 1.45e-04
+2022-05-08 12:56:32,943 INFO [train.py:715] (3/8) Epoch 15, batch 28700, loss[loss=0.1629, simple_loss=0.2315, pruned_loss=0.04719, over 4832.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03011, over 973561.95 frames.], batch size: 30, lr: 1.45e-04
+2022-05-08 12:57:11,383 INFO [train.py:715] (3/8) Epoch 15, batch 28750, loss[loss=0.1213, simple_loss=0.2014, pruned_loss=0.02058, over 4801.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03019, over 973559.03 frames.], batch size: 24, lr: 1.45e-04
+2022-05-08 12:57:50,115 INFO [train.py:715] (3/8) Epoch 15, batch 28800, loss[loss=0.1509, simple_loss=0.2244, pruned_loss=0.03867, over 4826.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03024, over 973033.84 frames.], batch size: 15, lr: 1.45e-04
+2022-05-08 12:58:28,472 INFO [train.py:715] (3/8) Epoch 15, batch 28850, loss[loss=0.1311, simple_loss=0.2048, pruned_loss=0.02869, over 4858.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03049, over 972179.81 frames.], batch size: 34, lr: 1.45e-04
+2022-05-08 12:59:06,966 INFO [train.py:715] (3/8) Epoch 15, batch 28900, loss[loss=0.1553, simple_loss=0.2326, pruned_loss=0.03905, over 4752.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03016, over 972535.11 frames.], batch size: 19, lr: 1.45e-04
+2022-05-08 12:59:45,682 INFO [train.py:715] (3/8) Epoch 15, batch 28950, loss[loss=0.1179, simple_loss=0.1956, pruned_loss=0.02011, over 4858.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.0301, over 972449.64 frames.], batch size: 13, lr: 1.45e-04
+2022-05-08 13:00:24,854 INFO [train.py:715] (3/8) Epoch 15, batch 29000, loss[loss=0.138, simple_loss=0.2049, pruned_loss=0.03554, over 4856.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02994, over 972283.90 frames.], batch size: 32, lr: 1.45e-04
+2022-05-08 13:01:03,428 INFO [train.py:715] (3/8) Epoch 15, batch 29050, loss[loss=0.1328, simple_loss=0.2187, pruned_loss=0.02342, over 4771.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.0298, over 972651.06 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 13:01:42,351 INFO [train.py:715] (3/8) Epoch 15, batch 29100, loss[loss=0.117, simple_loss=0.189, pruned_loss=0.0225, over 4798.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02949, over 971615.14 frames.], batch size: 13, lr: 1.45e-04
+2022-05-08 13:02:21,519 INFO [train.py:715] (3/8) Epoch 15, batch 29150, loss[loss=0.1263, simple_loss=0.1986, pruned_loss=0.02703, over 4974.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02969, over 972817.78 frames.], batch size: 24, lr: 1.45e-04
+2022-05-08 13:03:00,531 INFO [train.py:715] (3/8) Epoch 15, batch 29200, loss[loss=0.1242, simple_loss=0.193, pruned_loss=0.02768, over 4840.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02985, over 971796.05 frames.], batch size: 15, lr: 1.45e-04
+2022-05-08 13:03:38,943 INFO [train.py:715] (3/8) Epoch 15, batch 29250, loss[loss=0.1275, simple_loss=0.2127, pruned_loss=0.02117, over 4976.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03023, over 972195.98 frames.], batch size: 24, lr: 1.45e-04
+2022-05-08 13:04:18,001 INFO [train.py:715] (3/8) Epoch 15, batch 29300, loss[loss=0.1489, simple_loss=0.2202, pruned_loss=0.0388, over 4886.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02988, over 972608.00 frames.], batch size: 22, lr: 1.45e-04
+2022-05-08 13:04:56,890 INFO [train.py:715] (3/8) Epoch 15, batch 29350, loss[loss=0.1523, simple_loss=0.2178, pruned_loss=0.04339, over 4933.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02999, over 972444.35 frames.], batch size: 35, lr: 1.45e-04
+2022-05-08 13:05:35,477 INFO [train.py:715] (3/8) Epoch 15, batch 29400, loss[loss=0.1227, simple_loss=0.1835, pruned_loss=0.03097, over 4778.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02986, over 972665.68 frames.], batch size: 12, lr: 1.45e-04
+2022-05-08 13:06:14,535 INFO [train.py:715] (3/8) Epoch 15, batch 29450, loss[loss=0.1263, simple_loss=0.1997, pruned_loss=0.02641, over 4943.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02956, over 972709.42 frames.], batch size: 29, lr: 1.45e-04
+2022-05-08 13:06:53,810 INFO [train.py:715] (3/8) Epoch 15, batch 29500, loss[loss=0.1203, simple_loss=0.1904, pruned_loss=0.02507, over 4826.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02986, over 973721.52 frames.], batch size: 15, lr: 1.45e-04
+2022-05-08 13:07:31,957 INFO [train.py:715] (3/8) Epoch 15, batch 29550, loss[loss=0.1362, simple_loss=0.2064, pruned_loss=0.03299, over 4788.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02988, over 973337.87 frames.], batch size: 17, lr: 1.45e-04
+2022-05-08 13:08:09,735 INFO [train.py:715] (3/8) Epoch 15, batch 29600, loss[loss=0.1569, simple_loss=0.2172, pruned_loss=0.04832, over 4914.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.0299, over 973597.46 frames.], batch size: 17, lr: 1.45e-04
+2022-05-08 13:08:48,780 INFO [train.py:715] (3/8) Epoch 15, batch 29650, loss[loss=0.1239, simple_loss=0.2002, pruned_loss=0.02378, over 4896.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.0302, over 972646.21 frames.], batch size: 19, lr: 1.45e-04
+2022-05-08 13:09:27,544 INFO [train.py:715] (3/8) Epoch 15, batch 29700, loss[loss=0.1251, simple_loss=0.2008, pruned_loss=0.02469, over 4851.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03038, over 973228.20 frames.], batch size: 20, lr: 1.45e-04
+2022-05-08 13:10:05,829 INFO [train.py:715] (3/8) Epoch 15, batch 29750, loss[loss=0.1223, simple_loss=0.1967, pruned_loss=0.02392, over 4761.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03042, over 972702.97 frames.], batch size: 19, lr: 1.45e-04
+2022-05-08 13:10:43,495 INFO [train.py:715] (3/8) Epoch 15, batch 29800, loss[loss=0.1099, simple_loss=0.1897, pruned_loss=0.01509, over 4776.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03026, over 972481.25 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 13:11:22,788 INFO [train.py:715] (3/8) Epoch 15, batch 29850, loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03418, over 4782.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02964, over 973396.41 frames.], batch size: 17, lr: 1.45e-04
+2022-05-08 13:12:04,498 INFO [train.py:715] (3/8) Epoch 15, batch 29900, loss[loss=0.1245, simple_loss=0.201, pruned_loss=0.02401, over 4967.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02976, over 973609.56 frames.], batch size: 15, lr: 1.45e-04
+2022-05-08 13:12:43,058 INFO [train.py:715] (3/8) Epoch 15, batch 29950, loss[loss=0.1237, simple_loss=0.1927, pruned_loss=0.02739, over 4786.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03011, over 972378.95 frames.], batch size: 12, lr: 1.45e-04
+2022-05-08 13:13:21,390 INFO [train.py:715] (3/8) Epoch 15, batch 30000, loss[loss=0.111, simple_loss=0.1929, pruned_loss=0.01451, over 4850.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.03004, over 972743.96 frames.], batch size: 32, lr: 1.45e-04
+2022-05-08 13:13:21,390 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 13:13:30,914 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.1049, simple_loss=0.1885, pruned_loss=0.01066, over 914524.00 frames.
+2022-05-08 13:14:09,970 INFO [train.py:715] (3/8) Epoch 15, batch 30050, loss[loss=0.1086, simple_loss=0.1853, pruned_loss=0.01599, over 4782.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03011, over 973498.93 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 13:14:49,059 INFO [train.py:715] (3/8) Epoch 15, batch 30100, loss[loss=0.1468, simple_loss=0.2168, pruned_loss=0.0384, over 4898.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03009, over 973695.62 frames.], batch size: 19, lr: 1.45e-04
+2022-05-08 13:15:28,218 INFO [train.py:715] (3/8) Epoch 15, batch 30150, loss[loss=0.1141, simple_loss=0.1874, pruned_loss=0.02045, over 4898.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02993, over 972821.48 frames.], batch size: 17, lr: 1.45e-04
+2022-05-08 13:16:07,081 INFO [train.py:715] (3/8) Epoch 15, batch 30200, loss[loss=0.1325, simple_loss=0.1954, pruned_loss=0.03482, over 4803.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.03016, over 972889.06 frames.], batch size: 17, lr: 1.45e-04
+2022-05-08 13:16:46,376 INFO [train.py:715] (3/8) Epoch 15, batch 30250, loss[loss=0.1097, simple_loss=0.1773, pruned_loss=0.02105, over 4804.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03013, over 973328.92 frames.], batch size: 13, lr: 1.45e-04
+2022-05-08 13:17:25,198 INFO [train.py:715] (3/8) Epoch 15, batch 30300, loss[loss=0.1223, simple_loss=0.1956, pruned_loss=0.02455, over 4754.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03049, over 973025.52 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 13:18:03,169 INFO [train.py:715] (3/8) Epoch 15, batch 30350, loss[loss=0.1457, simple_loss=0.2159, pruned_loss=0.03769, over 4738.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2092, pruned_loss=0.0301, over 972762.22 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 13:18:42,391 INFO [train.py:715] (3/8) Epoch 15, batch 30400, loss[loss=0.1281, simple_loss=0.1994, pruned_loss=0.02841, over 4694.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2088, pruned_loss=0.02994, over 972542.70 frames.], batch size: 15, lr: 1.45e-04
+2022-05-08 13:19:21,255 INFO [train.py:715] (3/8) Epoch 15, batch 30450, loss[loss=0.09614, simple_loss=0.1652, pruned_loss=0.01356, over 4799.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02974, over 972453.82 frames.], batch size: 13, lr: 1.45e-04
+2022-05-08 13:20:00,134 INFO [train.py:715] (3/8) Epoch 15, batch 30500, loss[loss=0.1384, simple_loss=0.203, pruned_loss=0.03685, over 4866.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02948, over 972631.99 frames.], batch size: 30, lr: 1.45e-04
+2022-05-08 13:20:38,345 INFO [train.py:715] (3/8) Epoch 15, batch 30550, loss[loss=0.1168, simple_loss=0.1874, pruned_loss=0.02316, over 4949.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2097, pruned_loss=0.03026, over 971899.48 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 13:21:17,389 INFO [train.py:715] (3/8) Epoch 15, batch 30600, loss[loss=0.137, simple_loss=0.2093, pruned_loss=0.03239, over 4811.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2087, pruned_loss=0.02978, over 971885.01 frames.], batch size: 25, lr: 1.45e-04
+2022-05-08 13:21:56,195 INFO [train.py:715] (3/8) Epoch 15, batch 30650, loss[loss=0.1288, simple_loss=0.2071, pruned_loss=0.02528, over 4804.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2092, pruned_loss=0.03003, over 971274.79 frames.], batch size: 25, lr: 1.45e-04
+2022-05-08 13:22:34,337 INFO [train.py:715] (3/8) Epoch 15, batch 30700, loss[loss=0.131, simple_loss=0.2005, pruned_loss=0.03074, over 4960.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2086, pruned_loss=0.02961, over 971238.45 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 13:23:13,403 INFO [train.py:715] (3/8) Epoch 15, batch 30750, loss[loss=0.1255, simple_loss=0.2006, pruned_loss=0.02517, over 4790.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2093, pruned_loss=0.03011, over 970603.93 frames.], batch size: 17, lr: 1.45e-04
+2022-05-08 13:23:52,075 INFO [train.py:715] (3/8) Epoch 15, batch 30800, loss[loss=0.1412, simple_loss=0.217, pruned_loss=0.03266, over 4794.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2086, pruned_loss=0.02983, over 970907.01 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 13:24:30,181 INFO [train.py:715] (3/8) Epoch 15, batch 30850, loss[loss=0.1222, simple_loss=0.2139, pruned_loss=0.01522, over 4819.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02925, over 971503.26 frames.], batch size: 27, lr: 1.45e-04
+2022-05-08 13:25:08,417 INFO [train.py:715] (3/8) Epoch 15, batch 30900, loss[loss=0.14, simple_loss=0.211, pruned_loss=0.03453, over 4802.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2079, pruned_loss=0.0293, over 971688.63 frames.], batch size: 14, lr: 1.45e-04
+2022-05-08 13:25:46,856 INFO [train.py:715] (3/8) Epoch 15, batch 30950, loss[loss=0.1259, simple_loss=0.2009, pruned_loss=0.02547, over 4779.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2085, pruned_loss=0.02967, over 972300.94 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 13:26:25,012 INFO [train.py:715] (3/8) Epoch 15, batch 31000, loss[loss=0.1568, simple_loss=0.2217, pruned_loss=0.04594, over 4851.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2088, pruned_loss=0.02985, over 972425.70 frames.], batch size: 32, lr: 1.45e-04
+2022-05-08 13:27:02,424 INFO [train.py:715] (3/8) Epoch 15, batch 31050, loss[loss=0.1196, simple_loss=0.1969, pruned_loss=0.02114, over 4990.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03025, over 972293.36 frames.], batch size: 28, lr: 1.45e-04
+2022-05-08 13:27:40,736 INFO [train.py:715] (3/8) Epoch 15, batch 31100, loss[loss=0.1664, simple_loss=0.2319, pruned_loss=0.0504, over 4958.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.0299, over 972724.94 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 13:28:18,888 INFO [train.py:715] (3/8) Epoch 15, batch 31150, loss[loss=0.1437, simple_loss=0.2156, pruned_loss=0.03588, over 4810.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2093, pruned_loss=0.0301, over 973095.15 frames.], batch size: 24, lr: 1.45e-04
+2022-05-08 13:28:57,280 INFO [train.py:715] (3/8) Epoch 15, batch 31200, loss[loss=0.1093, simple_loss=0.1847, pruned_loss=0.0169, over 4835.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03014, over 973359.45 frames.], batch size: 12, lr: 1.45e-04
+2022-05-08 13:29:34,877 INFO [train.py:715] (3/8) Epoch 15, batch 31250, loss[loss=0.1221, simple_loss=0.2033, pruned_loss=0.02048, over 4922.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02994, over 973311.02 frames.], batch size: 23, lr: 1.45e-04
+2022-05-08 13:30:13,200 INFO [train.py:715] (3/8) Epoch 15, batch 31300, loss[loss=0.1223, simple_loss=0.1913, pruned_loss=0.0267, over 4801.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02969, over 972782.68 frames.], batch size: 13, lr: 1.45e-04
+2022-05-08 13:30:51,250 INFO [train.py:715] (3/8) Epoch 15, batch 31350, loss[loss=0.1423, simple_loss=0.2113, pruned_loss=0.03668, over 4876.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02948, over 971925.80 frames.], batch size: 13, lr: 1.45e-04
+2022-05-08 13:31:28,513 INFO [train.py:715] (3/8) Epoch 15, batch 31400, loss[loss=0.1398, simple_loss=0.205, pruned_loss=0.03725, over 4921.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02963, over 971790.40 frames.], batch size: 35, lr: 1.45e-04
+2022-05-08 13:32:06,857 INFO [train.py:715] (3/8) Epoch 15, batch 31450, loss[loss=0.1211, simple_loss=0.1926, pruned_loss=0.02481, over 4906.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03, over 971952.87 frames.], batch size: 17, lr: 1.45e-04
+2022-05-08 13:32:45,119 INFO [train.py:715] (3/8) Epoch 15, batch 31500, loss[loss=0.1272, simple_loss=0.191, pruned_loss=0.03171, over 4787.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02957, over 972340.31 frames.], batch size: 12, lr: 1.45e-04
+2022-05-08 13:33:23,447 INFO [train.py:715] (3/8) Epoch 15, batch 31550, loss[loss=0.1191, simple_loss=0.2008, pruned_loss=0.01867, over 4869.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02939, over 973200.52 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 13:34:01,215 INFO [train.py:715] (3/8) Epoch 15, batch 31600, loss[loss=0.1452, simple_loss=0.2213, pruned_loss=0.03457, over 4869.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02916, over 973139.62 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 13:34:39,669 INFO [train.py:715] (3/8) Epoch 15, batch 31650, loss[loss=0.1323, simple_loss=0.2006, pruned_loss=0.03197, over 4745.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02939, over 973202.70 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 13:35:18,001 INFO [train.py:715] (3/8) Epoch 15, batch 31700, loss[loss=0.1524, simple_loss=0.2314, pruned_loss=0.0367, over 4825.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02965, over 973841.06 frames.], batch size: 26, lr: 1.45e-04
+2022-05-08 13:35:55,500 INFO [train.py:715] (3/8) Epoch 15, batch 31750, loss[loss=0.1265, simple_loss=0.2006, pruned_loss=0.02626, over 4973.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02965, over 972843.42 frames.], batch size: 24, lr: 1.45e-04
+2022-05-08 13:36:34,379 INFO [train.py:715] (3/8) Epoch 15, batch 31800, loss[loss=0.115, simple_loss=0.1876, pruned_loss=0.0212, over 4924.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02943, over 973407.53 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 13:37:12,851 INFO [train.py:715] (3/8) Epoch 15, batch 31850, loss[loss=0.1342, simple_loss=0.2115, pruned_loss=0.02849, over 4959.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02906, over 973340.50 frames.], batch size: 35, lr: 1.45e-04
+2022-05-08 13:37:52,389 INFO [train.py:715] (3/8) Epoch 15, batch 31900, loss[loss=0.1293, simple_loss=0.1932, pruned_loss=0.03269, over 4769.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02955, over 973197.80 frames.], batch size: 18, lr: 1.45e-04
+2022-05-08 13:38:29,678 INFO [train.py:715] (3/8) Epoch 15, batch 31950, loss[loss=0.1221, simple_loss=0.1988, pruned_loss=0.02268, over 4927.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2082, pruned_loss=0.02952, over 972550.20 frames.], batch size: 23, lr: 1.45e-04
+2022-05-08 13:39:08,341 INFO [train.py:715] (3/8) Epoch 15, batch 32000, loss[loss=0.1354, simple_loss=0.2068, pruned_loss=0.032, over 4835.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02976, over 972600.58 frames.], batch size: 30, lr: 1.45e-04
+2022-05-08 13:39:46,519 INFO [train.py:715] (3/8) Epoch 15, batch 32050, loss[loss=0.1198, simple_loss=0.2027, pruned_loss=0.01844, over 4915.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02967, over 972849.34 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 13:40:23,949 INFO [train.py:715] (3/8) Epoch 15, batch 32100, loss[loss=0.1453, simple_loss=0.218, pruned_loss=0.03634, over 4845.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03009, over 971828.95 frames.], batch size: 20, lr: 1.45e-04
+2022-05-08 13:41:02,342 INFO [train.py:715] (3/8) Epoch 15, batch 32150, loss[loss=0.1443, simple_loss=0.2171, pruned_loss=0.03573, over 4747.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03011, over 972123.07 frames.], batch size: 16, lr: 1.45e-04
+2022-05-08 13:41:40,504 INFO [train.py:715] (3/8) Epoch 15, batch 32200, loss[loss=0.1228, simple_loss=0.1904, pruned_loss=0.02756, over 4988.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02966, over 971869.12 frames.], batch size: 28, lr: 1.45e-04
+2022-05-08 13:42:19,024 INFO [train.py:715] (3/8) Epoch 15, batch 32250, loss[loss=0.1375, simple_loss=0.2211, pruned_loss=0.02695, over 4933.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.0297, over 971859.95 frames.], batch size: 29, lr: 1.45e-04
+2022-05-08 13:42:56,890 INFO [train.py:715] (3/8) Epoch 15, batch 32300, loss[loss=0.1842, simple_loss=0.265, pruned_loss=0.05169, over 4871.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02967, over 972075.50 frames.], batch size: 22, lr: 1.45e-04
+2022-05-08 13:43:35,759 INFO [train.py:715] (3/8) Epoch 15, batch 32350, loss[loss=0.1311, simple_loss=0.2136, pruned_loss=0.02436, over 4913.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.0297, over 972369.69 frames.], batch size: 17, lr: 1.45e-04
+2022-05-08 13:44:14,155 INFO [train.py:715] (3/8) Epoch 15, batch 32400, loss[loss=0.1174, simple_loss=0.2019, pruned_loss=0.01641, over 4925.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03007, over 972873.60 frames.], batch size: 23, lr: 1.45e-04
+2022-05-08 13:44:51,909 INFO [train.py:715] (3/8) Epoch 15, batch 32450, loss[loss=0.1404, simple_loss=0.2139, pruned_loss=0.03342, over 4981.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03037, over 973081.78 frames.], batch size: 35, lr: 1.45e-04
+2022-05-08 13:45:30,473 INFO [train.py:715] (3/8) Epoch 15, batch 32500, loss[loss=0.168, simple_loss=0.2314, pruned_loss=0.05234, over 4829.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.0307, over 973549.18 frames.], batch size: 30, lr: 1.45e-04
+2022-05-08 13:46:08,936 INFO [train.py:715] (3/8) Epoch 15, batch 32550, loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02899, over 4765.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03076, over 973021.03 frames.], batch size: 12, lr: 1.45e-04
+2022-05-08 13:46:47,815 INFO [train.py:715] (3/8) Epoch 15, batch 32600, loss[loss=0.1321, simple_loss=0.2133, pruned_loss=0.02543, over 4824.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03046, over 973033.84 frames.], batch size: 25, lr: 1.45e-04
+2022-05-08 13:47:26,418 INFO [train.py:715] (3/8) Epoch 15, batch 32650, loss[loss=0.1269, simple_loss=0.2114, pruned_loss=0.02124, over 4781.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03029, over 972511.53 frames.], batch size: 19, lr: 1.45e-04
+2022-05-08 13:48:05,091 INFO [train.py:715] (3/8) Epoch 15, batch 32700, loss[loss=0.118, simple_loss=0.1897, pruned_loss=0.02314, over 4806.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03007, over 972987.74 frames.], batch size: 25, lr: 1.45e-04
+2022-05-08 13:48:43,313 INFO [train.py:715] (3/8) Epoch 15, batch 32750, loss[loss=0.1397, simple_loss=0.2164, pruned_loss=0.03148, over 4898.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03011, over 973569.95 frames.], batch size: 19, lr: 1.45e-04
+2022-05-08 13:49:21,522 INFO [train.py:715] (3/8) Epoch 15, batch 32800, loss[loss=0.1279, simple_loss=0.1984, pruned_loss=0.02873, over 4872.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02983, over 973190.36 frames.], batch size: 30, lr: 1.45e-04
+2022-05-08 13:49:59,268 INFO [train.py:715] (3/8) Epoch 15, batch 32850, loss[loss=0.1324, simple_loss=0.2129, pruned_loss=0.02594, over 4691.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02968, over 972397.51 frames.], batch size: 15, lr: 1.45e-04
+2022-05-08 13:50:37,486 INFO [train.py:715] (3/8) Epoch 15, batch 32900, loss[loss=0.1219, simple_loss=0.2075, pruned_loss=0.01817, over 4814.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.0299, over 972029.68 frames.], batch size: 26, lr: 1.45e-04
+2022-05-08 13:51:16,079 INFO [train.py:715] (3/8) Epoch 15, batch 32950, loss[loss=0.1238, simple_loss=0.1978, pruned_loss=0.02491, over 4955.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02959, over 972927.79 frames.], batch size: 35, lr: 1.45e-04
+2022-05-08 13:51:54,467 INFO [train.py:715] (3/8) Epoch 15, batch 33000, loss[loss=0.1298, simple_loss=0.2138, pruned_loss=0.0229, over 4793.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02941, over 971558.90 frames.], batch size: 21, lr: 1.45e-04
+2022-05-08 13:51:54,467 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 13:52:03,985 INFO [train.py:742] (3/8) Epoch 15, validation: loss=0.1052, simple_loss=0.1886, pruned_loss=0.01088, over 914524.00 frames.
+2022-05-08 13:52:42,025 INFO [train.py:715] (3/8) Epoch 15, batch 33050, loss[loss=0.1069, simple_loss=0.1879, pruned_loss=0.0129, over 4871.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.0295, over 972403.62 frames.], batch size: 22, lr: 1.45e-04
+2022-05-08 13:53:20,377 INFO [train.py:715] (3/8) Epoch 15, batch 33100, loss[loss=0.1442, simple_loss=0.2055, pruned_loss=0.04142, over 4879.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02964, over 973072.66 frames.], batch size: 32, lr: 1.45e-04
+2022-05-08 13:53:58,083 INFO [train.py:715] (3/8) Epoch 15, batch 33150, loss[loss=0.137, simple_loss=0.206, pruned_loss=0.03403, over 4886.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03029, over 973469.31 frames.], batch size: 17, lr: 1.44e-04
+2022-05-08 13:54:37,163 INFO [train.py:715] (3/8) Epoch 15, batch 33200, loss[loss=0.1056, simple_loss=0.1875, pruned_loss=0.01187, over 4920.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.0302, over 973395.97 frames.], batch size: 29, lr: 1.44e-04
+2022-05-08 13:55:15,596 INFO [train.py:715] (3/8) Epoch 15, batch 33250, loss[loss=0.1532, simple_loss=0.2328, pruned_loss=0.03681, over 4949.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02977, over 973395.41 frames.], batch size: 39, lr: 1.44e-04
+2022-05-08 13:55:53,707 INFO [train.py:715] (3/8) Epoch 15, batch 33300, loss[loss=0.1316, simple_loss=0.2023, pruned_loss=0.03043, over 4961.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02971, over 973639.34 frames.], batch size: 14, lr: 1.44e-04
+2022-05-08 13:56:31,676 INFO [train.py:715] (3/8) Epoch 15, batch 33350, loss[loss=0.1604, simple_loss=0.2299, pruned_loss=0.04543, over 4819.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02987, over 972831.05 frames.], batch size: 25, lr: 1.44e-04
+2022-05-08 13:57:09,334 INFO [train.py:715] (3/8) Epoch 15, batch 33400, loss[loss=0.1267, simple_loss=0.194, pruned_loss=0.02969, over 4844.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02955, over 972426.15 frames.], batch size: 15, lr: 1.44e-04
+2022-05-08 13:57:47,386 INFO [train.py:715] (3/8) Epoch 15, batch 33450, loss[loss=0.139, simple_loss=0.2187, pruned_loss=0.02966, over 4972.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2087, pruned_loss=0.02992, over 973340.79 frames.], batch size: 28, lr: 1.44e-04
+2022-05-08 13:58:25,101 INFO [train.py:715] (3/8) Epoch 15, batch 33500, loss[loss=0.1222, simple_loss=0.2058, pruned_loss=0.01929, over 4880.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03031, over 974064.22 frames.], batch size: 22, lr: 1.44e-04
+2022-05-08 13:59:02,925 INFO [train.py:715] (3/8) Epoch 15, batch 33550, loss[loss=0.1414, simple_loss=0.1989, pruned_loss=0.04192, over 4860.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03013, over 974328.09 frames.], batch size: 13, lr: 1.44e-04
+2022-05-08 13:59:40,602 INFO [train.py:715] (3/8) Epoch 15, batch 33600, loss[loss=0.1485, simple_loss=0.2266, pruned_loss=0.03523, over 4839.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03007, over 974458.02 frames.], batch size: 30, lr: 1.44e-04
+2022-05-08 14:00:18,653 INFO [train.py:715] (3/8) Epoch 15, batch 33650, loss[loss=0.1357, simple_loss=0.2143, pruned_loss=0.02859, over 4651.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02978, over 973477.13 frames.], batch size: 13, lr: 1.44e-04
+2022-05-08 14:00:56,120 INFO [train.py:715] (3/8) Epoch 15, batch 33700, loss[loss=0.141, simple_loss=0.2215, pruned_loss=0.03021, over 4699.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03009, over 973708.72 frames.], batch size: 15, lr: 1.44e-04
+2022-05-08 14:01:33,646 INFO [train.py:715] (3/8) Epoch 15, batch 33750, loss[loss=0.1333, simple_loss=0.213, pruned_loss=0.02685, over 4792.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02998, over 973046.20 frames.], batch size: 18, lr: 1.44e-04
+2022-05-08 14:02:11,485 INFO [train.py:715] (3/8) Epoch 15, batch 33800, loss[loss=0.1085, simple_loss=0.1868, pruned_loss=0.01512, over 4895.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.0297, over 973091.49 frames.], batch size: 22, lr: 1.44e-04
+2022-05-08 14:02:48,675 INFO [train.py:715] (3/8) Epoch 15, batch 33850, loss[loss=0.1257, simple_loss=0.194, pruned_loss=0.02868, over 4932.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2069, pruned_loss=0.02965, over 972034.26 frames.], batch size: 21, lr: 1.44e-04
+2022-05-08 14:03:26,485 INFO [train.py:715] (3/8) Epoch 15, batch 33900, loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.0301, over 4940.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02996, over 972574.51 frames.], batch size: 29, lr: 1.44e-04
+2022-05-08 14:04:04,823 INFO [train.py:715] (3/8) Epoch 15, batch 33950, loss[loss=0.1393, simple_loss=0.2157, pruned_loss=0.0315, over 4809.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.0303, over 972851.77 frames.], batch size: 13, lr: 1.44e-04
+2022-05-08 14:04:42,874 INFO [train.py:715] (3/8) Epoch 15, batch 34000, loss[loss=0.1485, simple_loss=0.2276, pruned_loss=0.03464, over 4685.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03057, over 972948.23 frames.], batch size: 15, lr: 1.44e-04
+2022-05-08 14:05:20,769 INFO [train.py:715] (3/8) Epoch 15, batch 34050, loss[loss=0.1173, simple_loss=0.188, pruned_loss=0.02325, over 4776.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02986, over 972951.54 frames.], batch size: 17, lr: 1.44e-04
+2022-05-08 14:05:58,930 INFO [train.py:715] (3/8) Epoch 15, batch 34100, loss[loss=0.116, simple_loss=0.1972, pruned_loss=0.01735, over 4779.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02975, over 973431.24 frames.], batch size: 18, lr: 1.44e-04
+2022-05-08 14:06:37,189 INFO [train.py:715] (3/8) Epoch 15, batch 34150, loss[loss=0.1231, simple_loss=0.1995, pruned_loss=0.02332, over 4772.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02955, over 972780.98 frames.], batch size: 18, lr: 1.44e-04
+2022-05-08 14:07:14,887 INFO [train.py:715] (3/8) Epoch 15, batch 34200, loss[loss=0.133, simple_loss=0.2181, pruned_loss=0.02395, over 4751.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02933, over 973176.71 frames.], batch size: 16, lr: 1.44e-04
+2022-05-08 14:07:52,719 INFO [train.py:715] (3/8) Epoch 15, batch 34250, loss[loss=0.1367, simple_loss=0.2091, pruned_loss=0.03209, over 4971.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02947, over 973268.74 frames.], batch size: 28, lr: 1.44e-04
+2022-05-08 14:08:30,684 INFO [train.py:715] (3/8) Epoch 15, batch 34300, loss[loss=0.1403, simple_loss=0.219, pruned_loss=0.03081, over 4969.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2079, pruned_loss=0.02924, over 973427.24 frames.], batch size: 39, lr: 1.44e-04
+2022-05-08 14:09:08,611 INFO [train.py:715] (3/8) Epoch 15, batch 34350, loss[loss=0.1552, simple_loss=0.2259, pruned_loss=0.04225, over 4687.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02955, over 973729.52 frames.], batch size: 15, lr: 1.44e-04
+2022-05-08 14:09:45,972 INFO [train.py:715] (3/8) Epoch 15, batch 34400, loss[loss=0.1568, simple_loss=0.2084, pruned_loss=0.05255, over 4791.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02935, over 973947.84 frames.], batch size: 14, lr: 1.44e-04
+2022-05-08 14:10:24,173 INFO [train.py:715] (3/8) Epoch 15, batch 34450, loss[loss=0.1364, simple_loss=0.2122, pruned_loss=0.03028, over 4973.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02913, over 973681.51 frames.], batch size: 14, lr: 1.44e-04
+2022-05-08 14:11:02,054 INFO [train.py:715] (3/8) Epoch 15, batch 34500, loss[loss=0.1366, simple_loss=0.2172, pruned_loss=0.02802, over 4873.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02937, over 973065.36 frames.], batch size: 16, lr: 1.44e-04
+2022-05-08 14:11:39,391 INFO [train.py:715] (3/8) Epoch 15, batch 34550, loss[loss=0.1379, simple_loss=0.2084, pruned_loss=0.03371, over 4976.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.0294, over 972261.13 frames.], batch size: 14, lr: 1.44e-04
+2022-05-08 14:12:17,006 INFO [train.py:715] (3/8) Epoch 15, batch 34600, loss[loss=0.1857, simple_loss=0.2473, pruned_loss=0.06208, over 4908.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03028, over 971362.80 frames.], batch size: 39, lr: 1.44e-04
+2022-05-08 14:12:54,930 INFO [train.py:715] (3/8) Epoch 15, batch 34650, loss[loss=0.1399, simple_loss=0.22, pruned_loss=0.0299, over 4829.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03043, over 971567.01 frames.], batch size: 26, lr: 1.44e-04
+2022-05-08 14:13:32,476 INFO [train.py:715] (3/8) Epoch 15, batch 34700, loss[loss=0.1029, simple_loss=0.1815, pruned_loss=0.01214, over 4883.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03024, over 972077.49 frames.], batch size: 22, lr: 1.44e-04
+2022-05-08 14:14:09,604 INFO [train.py:715] (3/8) Epoch 15, batch 34750, loss[loss=0.1321, simple_loss=0.2105, pruned_loss=0.02686, over 4790.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03027, over 972018.69 frames.], batch size: 14, lr: 1.44e-04
+2022-05-08 14:14:44,841 INFO [train.py:715] (3/8) Epoch 15, batch 34800, loss[loss=0.1526, simple_loss=0.237, pruned_loss=0.03415, over 4918.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03021, over 972011.37 frames.], batch size: 18, lr: 1.44e-04
+2022-05-08 14:15:33,455 INFO [train.py:715] (3/8) Epoch 16, batch 0, loss[loss=0.1191, simple_loss=0.1983, pruned_loss=0.01995, over 4954.00 frames.], tot_loss[loss=0.1191, simple_loss=0.1983, pruned_loss=0.01995, over 4954.00 frames.], batch size: 24, lr: 1.40e-04
+2022-05-08 14:16:11,643 INFO [train.py:715] (3/8) Epoch 16, batch 50, loss[loss=0.1282, simple_loss=0.2013, pruned_loss=0.02751, over 4776.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2085, pruned_loss=0.02959, over 219036.71 frames.], batch size: 14, lr: 1.40e-04
+2022-05-08 14:16:50,213 INFO [train.py:715] (3/8) Epoch 16, batch 100, loss[loss=0.1266, simple_loss=0.1983, pruned_loss=0.02743, over 4969.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02995, over 386050.08 frames.], batch size: 28, lr: 1.40e-04
+2022-05-08 14:17:27,945 INFO [train.py:715] (3/8) Epoch 16, batch 150, loss[loss=0.1267, simple_loss=0.2013, pruned_loss=0.02606, over 4893.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2063, pruned_loss=0.02952, over 517154.38 frames.], batch size: 22, lr: 1.40e-04
+2022-05-08 14:18:06,155 INFO [train.py:715] (3/8) Epoch 16, batch 200, loss[loss=0.1381, simple_loss=0.2264, pruned_loss=0.02487, over 4769.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02994, over 617260.89 frames.], batch size: 18, lr: 1.40e-04
+2022-05-08 14:18:44,281 INFO [train.py:715] (3/8) Epoch 16, batch 250, loss[loss=0.1408, simple_loss=0.2178, pruned_loss=0.03186, over 4846.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2065, pruned_loss=0.02959, over 696552.18 frames.], batch size: 30, lr: 1.40e-04
+2022-05-08 14:19:22,601 INFO [train.py:715] (3/8) Epoch 16, batch 300, loss[loss=0.1622, simple_loss=0.2391, pruned_loss=0.04267, over 4936.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.02998, over 757998.05 frames.], batch size: 18, lr: 1.40e-04
+2022-05-08 14:20:01,030 INFO [train.py:715] (3/8) Epoch 16, batch 350, loss[loss=0.1467, simple_loss=0.2191, pruned_loss=0.03711, over 4869.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03037, over 806110.65 frames.], batch size: 16, lr: 1.40e-04
+2022-05-08 14:20:38,708 INFO [train.py:715] (3/8) Epoch 16, batch 400, loss[loss=0.1335, simple_loss=0.2024, pruned_loss=0.03233, over 4971.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03034, over 842415.55 frames.], batch size: 14, lr: 1.40e-04
+2022-05-08 14:21:17,415 INFO [train.py:715] (3/8) Epoch 16, batch 450, loss[loss=0.1107, simple_loss=0.182, pruned_loss=0.0197, over 4821.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02963, over 871588.30 frames.], batch size: 15, lr: 1.40e-04
+2022-05-08 14:21:55,827 INFO [train.py:715] (3/8) Epoch 16, batch 500, loss[loss=0.1844, simple_loss=0.2399, pruned_loss=0.0644, over 4789.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03, over 893863.83 frames.], batch size: 24, lr: 1.40e-04
+2022-05-08 14:22:33,537 INFO [train.py:715] (3/8) Epoch 16, batch 550, loss[loss=0.1502, simple_loss=0.2229, pruned_loss=0.03872, over 4700.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03097, over 911416.26 frames.], batch size: 15, lr: 1.40e-04
+2022-05-08 14:23:12,213 INFO [train.py:715] (3/8) Epoch 16, batch 600, loss[loss=0.1127, simple_loss=0.1867, pruned_loss=0.01935, over 4943.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03081, over 925539.62 frames.], batch size: 21, lr: 1.40e-04
+2022-05-08 14:23:50,876 INFO [train.py:715] (3/8) Epoch 16, batch 650, loss[loss=0.1362, simple_loss=0.2153, pruned_loss=0.02851, over 4798.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03071, over 935492.01 frames.], batch size: 21, lr: 1.40e-04
+2022-05-08 14:24:28,546 INFO [train.py:715] (3/8) Epoch 16, batch 700, loss[loss=0.1718, simple_loss=0.2428, pruned_loss=0.05037, over 4863.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03032, over 943706.22 frames.], batch size: 20, lr: 1.40e-04
+2022-05-08 14:25:06,446 INFO [train.py:715] (3/8) Epoch 16, batch 750, loss[loss=0.1281, simple_loss=0.2039, pruned_loss=0.0261, over 4990.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02987, over 949560.40 frames.], batch size: 28, lr: 1.40e-04
+2022-05-08 14:25:45,234 INFO [train.py:715] (3/8) Epoch 16, batch 800, loss[loss=0.1231, simple_loss=0.2026, pruned_loss=0.02184, over 4905.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.03, over 954055.48 frames.], batch size: 19, lr: 1.40e-04
+2022-05-08 14:26:23,533 INFO [train.py:715] (3/8) Epoch 16, batch 850, loss[loss=0.1212, simple_loss=0.1977, pruned_loss=0.02229, over 4788.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.0298, over 958029.14 frames.], batch size: 14, lr: 1.40e-04
+2022-05-08 14:27:01,576 INFO [train.py:715] (3/8) Epoch 16, batch 900, loss[loss=0.1064, simple_loss=0.1771, pruned_loss=0.0179, over 4783.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03018, over 961781.58 frames.], batch size: 17, lr: 1.40e-04
+2022-05-08 14:27:39,693 INFO [train.py:715] (3/8) Epoch 16, batch 950, loss[loss=0.1293, simple_loss=0.2036, pruned_loss=0.02751, over 4839.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03044, over 964295.47 frames.], batch size: 30, lr: 1.40e-04
+2022-05-08 14:28:18,129 INFO [train.py:715] (3/8) Epoch 16, batch 1000, loss[loss=0.1472, simple_loss=0.2202, pruned_loss=0.03712, over 4871.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03043, over 966171.99 frames.], batch size: 32, lr: 1.40e-04
+2022-05-08 14:28:55,786 INFO [train.py:715] (3/8) Epoch 16, batch 1050, loss[loss=0.1701, simple_loss=0.2394, pruned_loss=0.05045, over 4770.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03034, over 967307.39 frames.], batch size: 14, lr: 1.40e-04
+2022-05-08 14:29:33,189 INFO [train.py:715] (3/8) Epoch 16, batch 1100, loss[loss=0.1231, simple_loss=0.1936, pruned_loss=0.0263, over 4832.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03024, over 969048.86 frames.], batch size: 26, lr: 1.40e-04
+2022-05-08 14:30:11,814 INFO [train.py:715] (3/8) Epoch 16, batch 1150, loss[loss=0.1308, simple_loss=0.1955, pruned_loss=0.03301, over 4844.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.02999, over 970082.50 frames.], batch size: 30, lr: 1.40e-04
+2022-05-08 14:30:49,882 INFO [train.py:715] (3/8) Epoch 16, batch 1200, loss[loss=0.1427, simple_loss=0.2092, pruned_loss=0.03811, over 4928.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02982, over 970871.78 frames.], batch size: 18, lr: 1.40e-04
+2022-05-08 14:31:27,247 INFO [train.py:715] (3/8) Epoch 16, batch 1250, loss[loss=0.1482, simple_loss=0.2213, pruned_loss=0.03751, over 4943.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02957, over 970166.57 frames.], batch size: 21, lr: 1.40e-04
+2022-05-08 14:32:05,205 INFO [train.py:715] (3/8) Epoch 16, batch 1300, loss[loss=0.1361, simple_loss=0.2108, pruned_loss=0.03072, over 4899.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02993, over 970270.70 frames.], batch size: 19, lr: 1.40e-04
+2022-05-08 14:32:43,366 INFO [train.py:715] (3/8) Epoch 16, batch 1350, loss[loss=0.136, simple_loss=0.1981, pruned_loss=0.03694, over 4961.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03004, over 970818.53 frames.], batch size: 24, lr: 1.40e-04
+2022-05-08 14:33:21,096 INFO [train.py:715] (3/8) Epoch 16, batch 1400, loss[loss=0.1263, simple_loss=0.1924, pruned_loss=0.03005, over 4850.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02992, over 971202.88 frames.], batch size: 32, lr: 1.40e-04
+2022-05-08 14:33:59,221 INFO [train.py:715] (3/8) Epoch 16, batch 1450, loss[loss=0.1172, simple_loss=0.2038, pruned_loss=0.01527, over 4900.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03016, over 971094.25 frames.], batch size: 17, lr: 1.40e-04
+2022-05-08 14:34:37,200 INFO [train.py:715] (3/8) Epoch 16, batch 1500, loss[loss=0.146, simple_loss=0.2264, pruned_loss=0.03285, over 4816.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03044, over 971049.02 frames.], batch size: 25, lr: 1.40e-04
+2022-05-08 14:35:14,922 INFO [train.py:715] (3/8) Epoch 16, batch 1550, loss[loss=0.1482, simple_loss=0.2153, pruned_loss=0.04053, over 4892.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03018, over 970470.44 frames.], batch size: 19, lr: 1.40e-04
+2022-05-08 14:35:52,771 INFO [train.py:715] (3/8) Epoch 16, batch 1600, loss[loss=0.1652, simple_loss=0.2362, pruned_loss=0.04703, over 4975.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02986, over 971390.01 frames.], batch size: 39, lr: 1.40e-04
+2022-05-08 14:36:30,170 INFO [train.py:715] (3/8) Epoch 16, batch 1650, loss[loss=0.132, simple_loss=0.203, pruned_loss=0.0305, over 4700.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02963, over 970726.87 frames.], batch size: 15, lr: 1.40e-04
+2022-05-08 14:37:07,994 INFO [train.py:715] (3/8) Epoch 16, batch 1700, loss[loss=0.1379, simple_loss=0.2173, pruned_loss=0.02922, over 4745.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02977, over 971431.48 frames.], batch size: 16, lr: 1.40e-04
+2022-05-08 14:37:46,154 INFO [train.py:715] (3/8) Epoch 16, batch 1750, loss[loss=0.1154, simple_loss=0.1882, pruned_loss=0.02135, over 4764.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02961, over 971431.16 frames.], batch size: 19, lr: 1.40e-04
+2022-05-08 14:38:24,069 INFO [train.py:715] (3/8) Epoch 16, batch 1800, loss[loss=0.1338, simple_loss=0.2187, pruned_loss=0.02438, over 4773.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.0302, over 972208.26 frames.], batch size: 17, lr: 1.40e-04
+2022-05-08 14:39:02,378 INFO [train.py:715] (3/8) Epoch 16, batch 1850, loss[loss=0.1129, simple_loss=0.1885, pruned_loss=0.0186, over 4879.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02978, over 971551.29 frames.], batch size: 38, lr: 1.40e-04
+2022-05-08 14:39:41,006 INFO [train.py:715] (3/8) Epoch 16, batch 1900, loss[loss=0.1152, simple_loss=0.1923, pruned_loss=0.01905, over 4960.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02945, over 971247.10 frames.], batch size: 24, lr: 1.40e-04
+2022-05-08 14:40:18,872 INFO [train.py:715] (3/8) Epoch 16, batch 1950, loss[loss=0.1521, simple_loss=0.2186, pruned_loss=0.04286, over 4957.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02981, over 971522.04 frames.], batch size: 21, lr: 1.40e-04
+2022-05-08 14:40:57,049 INFO [train.py:715] (3/8) Epoch 16, batch 2000, loss[loss=0.139, simple_loss=0.209, pruned_loss=0.03455, over 4925.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03018, over 972096.88 frames.], batch size: 23, lr: 1.40e-04
+2022-05-08 14:41:35,848 INFO [train.py:715] (3/8) Epoch 16, batch 2050, loss[loss=0.1486, simple_loss=0.2148, pruned_loss=0.04121, over 4856.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03003, over 971357.82 frames.], batch size: 20, lr: 1.40e-04
+2022-05-08 14:42:14,575 INFO [train.py:715] (3/8) Epoch 16, batch 2100, loss[loss=0.1286, simple_loss=0.1991, pruned_loss=0.02906, over 4853.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03008, over 971506.10 frames.], batch size: 30, lr: 1.40e-04
+2022-05-08 14:42:52,429 INFO [train.py:715] (3/8) Epoch 16, batch 2150, loss[loss=0.1031, simple_loss=0.1844, pruned_loss=0.01089, over 4755.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02989, over 971839.81 frames.], batch size: 16, lr: 1.40e-04
+2022-05-08 14:43:31,556 INFO [train.py:715] (3/8) Epoch 16, batch 2200, loss[loss=0.1109, simple_loss=0.1743, pruned_loss=0.02371, over 4638.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02936, over 971623.44 frames.], batch size: 13, lr: 1.40e-04
+2022-05-08 14:44:09,851 INFO [train.py:715] (3/8) Epoch 16, batch 2250, loss[loss=0.1287, simple_loss=0.2054, pruned_loss=0.02607, over 4947.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02917, over 972838.16 frames.], batch size: 29, lr: 1.40e-04
+2022-05-08 14:44:47,484 INFO [train.py:715] (3/8) Epoch 16, batch 2300, loss[loss=0.1081, simple_loss=0.1819, pruned_loss=0.01715, over 4985.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02891, over 973252.49 frames.], batch size: 24, lr: 1.40e-04
+2022-05-08 14:45:25,052 INFO [train.py:715] (3/8) Epoch 16, batch 2350, loss[loss=0.136, simple_loss=0.221, pruned_loss=0.02552, over 4788.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02908, over 971724.43 frames.], batch size: 17, lr: 1.40e-04
+2022-05-08 14:46:03,344 INFO [train.py:715] (3/8) Epoch 16, batch 2400, loss[loss=0.1187, simple_loss=0.1847, pruned_loss=0.02628, over 4886.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.0293, over 972049.13 frames.], batch size: 16, lr: 1.40e-04
+2022-05-08 14:46:41,420 INFO [train.py:715] (3/8) Epoch 16, batch 2450, loss[loss=0.1443, simple_loss=0.2111, pruned_loss=0.0387, over 4753.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2087, pruned_loss=0.02999, over 972168.11 frames.], batch size: 16, lr: 1.40e-04
+2022-05-08 14:47:18,881 INFO [train.py:715] (3/8) Epoch 16, batch 2500, loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02865, over 4822.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02986, over 972550.59 frames.], batch size: 25, lr: 1.40e-04
+2022-05-08 14:47:57,274 INFO [train.py:715] (3/8) Epoch 16, batch 2550, loss[loss=0.1622, simple_loss=0.2263, pruned_loss=0.04907, over 4904.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02967, over 971698.76 frames.], batch size: 19, lr: 1.40e-04
+2022-05-08 14:48:35,428 INFO [train.py:715] (3/8) Epoch 16, batch 2600, loss[loss=0.1405, simple_loss=0.2235, pruned_loss=0.02879, over 4946.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02966, over 973048.24 frames.], batch size: 21, lr: 1.40e-04
+2022-05-08 14:49:13,160 INFO [train.py:715] (3/8) Epoch 16, batch 2650, loss[loss=0.128, simple_loss=0.2091, pruned_loss=0.02351, over 4982.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02961, over 972763.39 frames.], batch size: 28, lr: 1.40e-04
+2022-05-08 14:49:51,047 INFO [train.py:715] (3/8) Epoch 16, batch 2700, loss[loss=0.129, simple_loss=0.2079, pruned_loss=0.02507, over 4810.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02969, over 972852.26 frames.], batch size: 21, lr: 1.40e-04
+2022-05-08 14:50:29,659 INFO [train.py:715] (3/8) Epoch 16, batch 2750, loss[loss=0.1433, simple_loss=0.2137, pruned_loss=0.03643, over 4849.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02952, over 973289.55 frames.], batch size: 30, lr: 1.40e-04
+2022-05-08 14:51:08,572 INFO [train.py:715] (3/8) Epoch 16, batch 2800, loss[loss=0.1456, simple_loss=0.2241, pruned_loss=0.03359, over 4849.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02949, over 972113.71 frames.], batch size: 15, lr: 1.40e-04
+2022-05-08 14:51:46,950 INFO [train.py:715] (3/8) Epoch 16, batch 2850, loss[loss=0.1259, simple_loss=0.2062, pruned_loss=0.02281, over 4974.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02968, over 973153.16 frames.], batch size: 15, lr: 1.40e-04
+2022-05-08 14:52:24,999 INFO [train.py:715] (3/8) Epoch 16, batch 2900, loss[loss=0.1266, simple_loss=0.1919, pruned_loss=0.03071, over 4868.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02977, over 972881.00 frames.], batch size: 32, lr: 1.40e-04
+2022-05-08 14:53:03,774 INFO [train.py:715] (3/8) Epoch 16, batch 2950, loss[loss=0.1158, simple_loss=0.1849, pruned_loss=0.02329, over 4937.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02982, over 972606.33 frames.], batch size: 23, lr: 1.40e-04
+2022-05-08 14:53:41,758 INFO [train.py:715] (3/8) Epoch 16, batch 3000, loss[loss=0.1305, simple_loss=0.197, pruned_loss=0.03202, over 4966.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02968, over 972147.67 frames.], batch size: 15, lr: 1.40e-04
+2022-05-08 14:53:41,758 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 14:53:51,190 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.105, simple_loss=0.1885, pruned_loss=0.01074, over 914524.00 frames.
+2022-05-08 14:54:29,009 INFO [train.py:715] (3/8) Epoch 16, batch 3050, loss[loss=0.1416, simple_loss=0.2188, pruned_loss=0.03217, over 4776.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.0298, over 972383.30 frames.], batch size: 17, lr: 1.40e-04
+2022-05-08 14:55:09,458 INFO [train.py:715] (3/8) Epoch 16, batch 3100, loss[loss=0.134, simple_loss=0.1996, pruned_loss=0.03422, over 4745.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02976, over 971956.71 frames.], batch size: 12, lr: 1.40e-04
+2022-05-08 14:55:47,850 INFO [train.py:715] (3/8) Epoch 16, batch 3150, loss[loss=0.1264, simple_loss=0.2053, pruned_loss=0.02373, over 4827.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02952, over 971854.05 frames.], batch size: 15, lr: 1.40e-04
+2022-05-08 14:56:26,004 INFO [train.py:715] (3/8) Epoch 16, batch 3200, loss[loss=0.1214, simple_loss=0.2063, pruned_loss=0.01824, over 4807.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02918, over 972308.31 frames.], batch size: 25, lr: 1.40e-04
+2022-05-08 14:57:04,239 INFO [train.py:715] (3/8) Epoch 16, batch 3250, loss[loss=0.1273, simple_loss=0.1924, pruned_loss=0.03107, over 4775.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02888, over 972087.95 frames.], batch size: 14, lr: 1.40e-04
+2022-05-08 14:57:42,065 INFO [train.py:715] (3/8) Epoch 16, batch 3300, loss[loss=0.1256, simple_loss=0.2001, pruned_loss=0.0256, over 4889.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02911, over 971381.69 frames.], batch size: 19, lr: 1.40e-04
+2022-05-08 14:58:20,054 INFO [train.py:715] (3/8) Epoch 16, batch 3350, loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03333, over 4967.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02934, over 971923.27 frames.], batch size: 24, lr: 1.40e-04
+2022-05-08 14:58:57,931 INFO [train.py:715] (3/8) Epoch 16, batch 3400, loss[loss=0.141, simple_loss=0.2119, pruned_loss=0.03503, over 4876.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02955, over 972438.12 frames.], batch size: 30, lr: 1.40e-04
+2022-05-08 14:59:35,866 INFO [train.py:715] (3/8) Epoch 16, batch 3450, loss[loss=0.1291, simple_loss=0.1991, pruned_loss=0.02952, over 4799.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02935, over 972635.81 frames.], batch size: 17, lr: 1.40e-04
+2022-05-08 15:00:13,955 INFO [train.py:715] (3/8) Epoch 16, batch 3500, loss[loss=0.1281, simple_loss=0.2088, pruned_loss=0.02366, over 4751.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02936, over 972257.43 frames.], batch size: 19, lr: 1.40e-04
+2022-05-08 15:00:51,757 INFO [train.py:715] (3/8) Epoch 16, batch 3550, loss[loss=0.1157, simple_loss=0.1937, pruned_loss=0.01888, over 4974.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02921, over 972562.64 frames.], batch size: 15, lr: 1.40e-04
+2022-05-08 15:01:30,179 INFO [train.py:715] (3/8) Epoch 16, batch 3600, loss[loss=0.1277, simple_loss=0.2114, pruned_loss=0.02201, over 4822.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02923, over 972188.37 frames.], batch size: 25, lr: 1.40e-04
+2022-05-08 15:02:07,899 INFO [train.py:715] (3/8) Epoch 16, batch 3650, loss[loss=0.1248, simple_loss=0.1986, pruned_loss=0.02551, over 4782.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02942, over 971712.67 frames.], batch size: 17, lr: 1.40e-04
+2022-05-08 15:02:46,544 INFO [train.py:715] (3/8) Epoch 16, batch 3700, loss[loss=0.1115, simple_loss=0.1838, pruned_loss=0.01954, over 4924.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02945, over 971629.44 frames.], batch size: 18, lr: 1.40e-04
+2022-05-08 15:03:25,028 INFO [train.py:715] (3/8) Epoch 16, batch 3750, loss[loss=0.1644, simple_loss=0.2296, pruned_loss=0.04966, over 4864.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.0294, over 972386.42 frames.], batch size: 30, lr: 1.40e-04
+2022-05-08 15:04:03,393 INFO [train.py:715] (3/8) Epoch 16, batch 3800, loss[loss=0.1359, simple_loss=0.2028, pruned_loss=0.03447, over 4971.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02986, over 972756.36 frames.], batch size: 25, lr: 1.40e-04
+2022-05-08 15:04:42,257 INFO [train.py:715] (3/8) Epoch 16, batch 3850, loss[loss=0.1846, simple_loss=0.2535, pruned_loss=0.05789, over 4965.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.03004, over 972305.92 frames.], batch size: 35, lr: 1.40e-04
+2022-05-08 15:05:21,014 INFO [train.py:715] (3/8) Epoch 16, batch 3900, loss[loss=0.1174, simple_loss=0.1852, pruned_loss=0.02473, over 4783.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2071, pruned_loss=0.03011, over 971804.67 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 15:05:58,861 INFO [train.py:715] (3/8) Epoch 16, batch 3950, loss[loss=0.1308, simple_loss=0.1951, pruned_loss=0.03324, over 4955.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2069, pruned_loss=0.03024, over 971912.77 frames.], batch size: 14, lr: 1.39e-04
+2022-05-08 15:06:36,786 INFO [train.py:715] (3/8) Epoch 16, batch 4000, loss[loss=0.1348, simple_loss=0.2171, pruned_loss=0.0262, over 4882.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2078, pruned_loss=0.03051, over 972449.04 frames.], batch size: 22, lr: 1.39e-04
+2022-05-08 15:07:14,746 INFO [train.py:715] (3/8) Epoch 16, batch 4050, loss[loss=0.1348, simple_loss=0.2058, pruned_loss=0.0319, over 4851.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.0304, over 971998.09 frames.], batch size: 13, lr: 1.39e-04
+2022-05-08 15:07:52,149 INFO [train.py:715] (3/8) Epoch 16, batch 4100, loss[loss=0.1525, simple_loss=0.2257, pruned_loss=0.0396, over 4777.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03038, over 972192.00 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 15:08:29,799 INFO [train.py:715] (3/8) Epoch 16, batch 4150, loss[loss=0.1304, simple_loss=0.1962, pruned_loss=0.0323, over 4870.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.0306, over 972301.15 frames.], batch size: 32, lr: 1.39e-04
+2022-05-08 15:09:07,466 INFO [train.py:715] (3/8) Epoch 16, batch 4200, loss[loss=0.1011, simple_loss=0.1806, pruned_loss=0.01075, over 4903.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03006, over 972446.37 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 15:09:45,635 INFO [train.py:715] (3/8) Epoch 16, batch 4250, loss[loss=0.1104, simple_loss=0.1858, pruned_loss=0.0175, over 4757.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03052, over 972276.72 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 15:10:23,343 INFO [train.py:715] (3/8) Epoch 16, batch 4300, loss[loss=0.129, simple_loss=0.186, pruned_loss=0.03599, over 4904.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03046, over 972815.52 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 15:11:01,197 INFO [train.py:715] (3/8) Epoch 16, batch 4350, loss[loss=0.118, simple_loss=0.1915, pruned_loss=0.02221, over 4797.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03033, over 972813.63 frames.], batch size: 12, lr: 1.39e-04
+2022-05-08 15:11:39,307 INFO [train.py:715] (3/8) Epoch 16, batch 4400, loss[loss=0.1722, simple_loss=0.253, pruned_loss=0.04569, over 4961.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03034, over 972412.75 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 15:12:17,136 INFO [train.py:715] (3/8) Epoch 16, batch 4450, loss[loss=0.135, simple_loss=0.2206, pruned_loss=0.02469, over 4817.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03043, over 972435.13 frames.], batch size: 27, lr: 1.39e-04
+2022-05-08 15:12:54,753 INFO [train.py:715] (3/8) Epoch 16, batch 4500, loss[loss=0.123, simple_loss=0.1941, pruned_loss=0.02588, over 4929.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03018, over 972802.40 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 15:13:32,861 INFO [train.py:715] (3/8) Epoch 16, batch 4550, loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03412, over 4819.00 frames.], tot_loss[loss=0.1332, simple_loss=0.208, pruned_loss=0.02923, over 973261.10 frames.], batch size: 27, lr: 1.39e-04
+2022-05-08 15:14:11,256 INFO [train.py:715] (3/8) Epoch 16, batch 4600, loss[loss=0.1096, simple_loss=0.1801, pruned_loss=0.01953, over 4957.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2088, pruned_loss=0.02979, over 972950.15 frames.], batch size: 29, lr: 1.39e-04
+2022-05-08 15:14:49,230 INFO [train.py:715] (3/8) Epoch 16, batch 4650, loss[loss=0.1282, simple_loss=0.208, pruned_loss=0.02424, over 4914.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02962, over 973367.16 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 15:15:27,631 INFO [train.py:715] (3/8) Epoch 16, batch 4700, loss[loss=0.1454, simple_loss=0.2122, pruned_loss=0.03924, over 4928.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03, over 973081.41 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 15:16:06,228 INFO [train.py:715] (3/8) Epoch 16, batch 4750, loss[loss=0.1282, simple_loss=0.2005, pruned_loss=0.02796, over 4772.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02981, over 973109.46 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 15:16:44,830 INFO [train.py:715] (3/8) Epoch 16, batch 4800, loss[loss=0.1144, simple_loss=0.18, pruned_loss=0.02446, over 4688.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02936, over 972951.41 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 15:17:23,109 INFO [train.py:715] (3/8) Epoch 16, batch 4850, loss[loss=0.1558, simple_loss=0.2314, pruned_loss=0.04013, over 4973.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2059, pruned_loss=0.02923, over 971963.09 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 15:18:01,809 INFO [train.py:715] (3/8) Epoch 16, batch 4900, loss[loss=0.1397, simple_loss=0.2198, pruned_loss=0.02977, over 4982.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02905, over 971878.80 frames.], batch size: 33, lr: 1.39e-04
+2022-05-08 15:18:40,683 INFO [train.py:715] (3/8) Epoch 16, batch 4950, loss[loss=0.1265, simple_loss=0.1973, pruned_loss=0.02784, over 4959.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02909, over 972301.76 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 15:19:18,926 INFO [train.py:715] (3/8) Epoch 16, batch 5000, loss[loss=0.1429, simple_loss=0.2093, pruned_loss=0.0382, over 4975.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02941, over 972117.16 frames.], batch size: 28, lr: 1.39e-04
+2022-05-08 15:19:57,139 INFO [train.py:715] (3/8) Epoch 16, batch 5050, loss[loss=0.1467, simple_loss=0.2296, pruned_loss=0.03185, over 4893.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02891, over 972092.25 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 15:20:35,446 INFO [train.py:715] (3/8) Epoch 16, batch 5100, loss[loss=0.1141, simple_loss=0.1745, pruned_loss=0.02686, over 4770.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02862, over 971851.95 frames.], batch size: 12, lr: 1.39e-04
+2022-05-08 15:21:13,349 INFO [train.py:715] (3/8) Epoch 16, batch 5150, loss[loss=0.1257, simple_loss=0.2142, pruned_loss=0.01861, over 4755.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02875, over 972139.83 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 15:21:50,907 INFO [train.py:715] (3/8) Epoch 16, batch 5200, loss[loss=0.1407, simple_loss=0.2159, pruned_loss=0.03273, over 4950.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02843, over 973742.14 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 15:22:28,865 INFO [train.py:715] (3/8) Epoch 16, batch 5250, loss[loss=0.1349, simple_loss=0.1993, pruned_loss=0.0352, over 4743.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02844, over 974355.78 frames.], batch size: 16, lr: 1.39e-04
+2022-05-08 15:23:07,103 INFO [train.py:715] (3/8) Epoch 16, batch 5300, loss[loss=0.1306, simple_loss=0.2012, pruned_loss=0.03, over 4887.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.0287, over 973044.21 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 15:23:45,226 INFO [train.py:715] (3/8) Epoch 16, batch 5350, loss[loss=0.1448, simple_loss=0.2202, pruned_loss=0.03468, over 4884.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02893, over 973643.75 frames.], batch size: 22, lr: 1.39e-04
+2022-05-08 15:24:23,036 INFO [train.py:715] (3/8) Epoch 16, batch 5400, loss[loss=0.1298, simple_loss=0.2014, pruned_loss=0.0291, over 4811.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02936, over 973013.83 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 15:25:00,889 INFO [train.py:715] (3/8) Epoch 16, batch 5450, loss[loss=0.1292, simple_loss=0.204, pruned_loss=0.0272, over 4776.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02886, over 971495.31 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 15:25:38,708 INFO [train.py:715] (3/8) Epoch 16, batch 5500, loss[loss=0.1367, simple_loss=0.2209, pruned_loss=0.02625, over 4913.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02889, over 972981.88 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 15:26:16,325 INFO [train.py:715] (3/8) Epoch 16, batch 5550, loss[loss=0.1289, simple_loss=0.2008, pruned_loss=0.02846, over 4869.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02886, over 972823.89 frames.], batch size: 16, lr: 1.39e-04
+2022-05-08 15:26:54,074 INFO [train.py:715] (3/8) Epoch 16, batch 5600, loss[loss=0.1663, simple_loss=0.2346, pruned_loss=0.049, over 4807.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02903, over 972867.12 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 15:27:32,729 INFO [train.py:715] (3/8) Epoch 16, batch 5650, loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03185, over 4793.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02875, over 972770.69 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 15:28:10,546 INFO [train.py:715] (3/8) Epoch 16, batch 5700, loss[loss=0.1286, simple_loss=0.2042, pruned_loss=0.02649, over 4933.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02858, over 973423.85 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 15:28:48,368 INFO [train.py:715] (3/8) Epoch 16, batch 5750, loss[loss=0.1377, simple_loss=0.2092, pruned_loss=0.03312, over 4752.00 frames.], tot_loss[loss=0.1321, simple_loss=0.206, pruned_loss=0.02914, over 973543.87 frames.], batch size: 16, lr: 1.39e-04
+2022-05-08 15:29:26,213 INFO [train.py:715] (3/8) Epoch 16, batch 5800, loss[loss=0.1222, simple_loss=0.1868, pruned_loss=0.02882, over 4867.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2055, pruned_loss=0.02893, over 973959.46 frames.], batch size: 13, lr: 1.39e-04
+2022-05-08 15:30:04,476 INFO [train.py:715] (3/8) Epoch 16, batch 5850, loss[loss=0.1146, simple_loss=0.1764, pruned_loss=0.02643, over 4817.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2057, pruned_loss=0.02905, over 974429.11 frames.], batch size: 12, lr: 1.39e-04
+2022-05-08 15:30:42,018 INFO [train.py:715] (3/8) Epoch 16, batch 5900, loss[loss=0.1407, simple_loss=0.2037, pruned_loss=0.03889, over 4830.00 frames.], tot_loss[loss=0.1323, simple_loss=0.206, pruned_loss=0.02933, over 973846.44 frames.], batch size: 13, lr: 1.39e-04
+2022-05-08 15:31:19,661 INFO [train.py:715] (3/8) Epoch 16, batch 5950, loss[loss=0.1312, simple_loss=0.2087, pruned_loss=0.0269, over 4827.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2061, pruned_loss=0.0293, over 972575.84 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 15:31:58,428 INFO [train.py:715] (3/8) Epoch 16, batch 6000, loss[loss=0.1178, simple_loss=0.1882, pruned_loss=0.02368, over 4690.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02964, over 972241.22 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 15:31:58,429 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 15:32:07,944 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.105, simple_loss=0.1885, pruned_loss=0.01082, over 914524.00 frames.
+2022-05-08 15:32:46,980 INFO [train.py:715] (3/8) Epoch 16, batch 6050, loss[loss=0.1478, simple_loss=0.2338, pruned_loss=0.03091, over 4979.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.0301, over 972657.97 frames.], batch size: 28, lr: 1.39e-04
+2022-05-08 15:33:25,024 INFO [train.py:715] (3/8) Epoch 16, batch 6100, loss[loss=0.1257, simple_loss=0.2021, pruned_loss=0.02463, over 4790.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02972, over 972374.60 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 15:34:02,795 INFO [train.py:715] (3/8) Epoch 16, batch 6150, loss[loss=0.1143, simple_loss=0.1964, pruned_loss=0.01609, over 4934.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03002, over 973199.51 frames.], batch size: 23, lr: 1.39e-04
+2022-05-08 15:34:40,935 INFO [train.py:715] (3/8) Epoch 16, batch 6200, loss[loss=0.1601, simple_loss=0.2201, pruned_loss=0.05007, over 4929.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03035, over 973101.65 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 15:35:19,473 INFO [train.py:715] (3/8) Epoch 16, batch 6250, loss[loss=0.1089, simple_loss=0.1962, pruned_loss=0.01077, over 4964.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02989, over 973190.87 frames.], batch size: 24, lr: 1.39e-04
+2022-05-08 15:35:57,115 INFO [train.py:715] (3/8) Epoch 16, batch 6300, loss[loss=0.1328, simple_loss=0.2013, pruned_loss=0.03213, over 4688.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02957, over 972860.93 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 15:36:34,885 INFO [train.py:715] (3/8) Epoch 16, batch 6350, loss[loss=0.1237, simple_loss=0.1932, pruned_loss=0.02704, over 4899.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2061, pruned_loss=0.02935, over 972912.93 frames.], batch size: 22, lr: 1.39e-04
+2022-05-08 15:37:13,402 INFO [train.py:715] (3/8) Epoch 16, batch 6400, loss[loss=0.1187, simple_loss=0.1933, pruned_loss=0.02204, over 4946.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2065, pruned_loss=0.02964, over 973614.54 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 15:37:51,670 INFO [train.py:715] (3/8) Epoch 16, batch 6450, loss[loss=0.1357, simple_loss=0.2104, pruned_loss=0.03054, over 4964.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.03016, over 973554.95 frames.], batch size: 24, lr: 1.39e-04
+2022-05-08 15:38:29,441 INFO [train.py:715] (3/8) Epoch 16, batch 6500, loss[loss=0.1692, simple_loss=0.2445, pruned_loss=0.04697, over 4901.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2071, pruned_loss=0.03015, over 972709.59 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 15:39:07,582 INFO [train.py:715] (3/8) Epoch 16, batch 6550, loss[loss=0.1419, simple_loss=0.2168, pruned_loss=0.03351, over 4917.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2068, pruned_loss=0.02989, over 973189.29 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 15:39:46,029 INFO [train.py:715] (3/8) Epoch 16, batch 6600, loss[loss=0.1683, simple_loss=0.2521, pruned_loss=0.04222, over 4848.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02969, over 973839.36 frames.], batch size: 20, lr: 1.39e-04
+2022-05-08 15:40:23,830 INFO [train.py:715] (3/8) Epoch 16, batch 6650, loss[loss=0.1356, simple_loss=0.2212, pruned_loss=0.02501, over 4744.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03, over 973761.71 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 15:41:01,687 INFO [train.py:715] (3/8) Epoch 16, batch 6700, loss[loss=0.1321, simple_loss=0.2047, pruned_loss=0.02978, over 4923.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02997, over 972854.12 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 15:41:39,714 INFO [train.py:715] (3/8) Epoch 16, batch 6750, loss[loss=0.128, simple_loss=0.2082, pruned_loss=0.02389, over 4820.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03029, over 972733.06 frames.], batch size: 14, lr: 1.39e-04
+2022-05-08 15:42:17,832 INFO [train.py:715] (3/8) Epoch 16, batch 6800, loss[loss=0.143, simple_loss=0.2143, pruned_loss=0.03588, over 4901.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03064, over 972942.63 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 15:42:54,812 INFO [train.py:715] (3/8) Epoch 16, batch 6850, loss[loss=0.1449, simple_loss=0.2165, pruned_loss=0.03666, over 4911.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03005, over 973200.48 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 15:43:32,597 INFO [train.py:715] (3/8) Epoch 16, batch 6900, loss[loss=0.1336, simple_loss=0.204, pruned_loss=0.03163, over 4965.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03038, over 973430.17 frames.], batch size: 39, lr: 1.39e-04
+2022-05-08 15:44:10,715 INFO [train.py:715] (3/8) Epoch 16, batch 6950, loss[loss=0.1261, simple_loss=0.2145, pruned_loss=0.01878, over 4876.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03023, over 972917.34 frames.], batch size: 32, lr: 1.39e-04
+2022-05-08 15:44:48,421 INFO [train.py:715] (3/8) Epoch 16, batch 7000, loss[loss=0.1278, simple_loss=0.206, pruned_loss=0.02484, over 4984.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03028, over 971795.60 frames.], batch size: 26, lr: 1.39e-04
+2022-05-08 15:45:26,358 INFO [train.py:715] (3/8) Epoch 16, batch 7050, loss[loss=0.1289, simple_loss=0.213, pruned_loss=0.02237, over 4924.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02975, over 972830.44 frames.], batch size: 23, lr: 1.39e-04
+2022-05-08 15:46:04,189 INFO [train.py:715] (3/8) Epoch 16, batch 7100, loss[loss=0.1596, simple_loss=0.2305, pruned_loss=0.04429, over 4944.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03007, over 972671.66 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 15:46:42,646 INFO [train.py:715] (3/8) Epoch 16, batch 7150, loss[loss=0.1207, simple_loss=0.1893, pruned_loss=0.02607, over 4975.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.02975, over 972409.85 frames.], batch size: 25, lr: 1.39e-04
+2022-05-08 15:47:19,960 INFO [train.py:715] (3/8) Epoch 16, batch 7200, loss[loss=0.1412, simple_loss=0.2118, pruned_loss=0.03525, over 4891.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02989, over 972644.32 frames.], batch size: 22, lr: 1.39e-04
+2022-05-08 15:47:57,929 INFO [train.py:715] (3/8) Epoch 16, batch 7250, loss[loss=0.1662, simple_loss=0.2406, pruned_loss=0.04592, over 4896.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02971, over 973051.07 frames.], batch size: 22, lr: 1.39e-04
+2022-05-08 15:48:36,996 INFO [train.py:715] (3/8) Epoch 16, batch 7300, loss[loss=0.1944, simple_loss=0.2465, pruned_loss=0.07115, over 4813.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03014, over 973263.17 frames.], batch size: 27, lr: 1.39e-04
+2022-05-08 15:49:15,803 INFO [train.py:715] (3/8) Epoch 16, batch 7350, loss[loss=0.1334, simple_loss=0.2178, pruned_loss=0.02451, over 4802.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2074, pruned_loss=0.03035, over 972013.02 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 15:49:55,249 INFO [train.py:715] (3/8) Epoch 16, batch 7400, loss[loss=0.136, simple_loss=0.219, pruned_loss=0.02651, over 4826.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2078, pruned_loss=0.03053, over 972389.90 frames.], batch size: 25, lr: 1.39e-04
+2022-05-08 15:50:34,950 INFO [train.py:715] (3/8) Epoch 16, batch 7450, loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02841, over 4816.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2068, pruned_loss=0.03004, over 972204.23 frames.], batch size: 26, lr: 1.39e-04
+2022-05-08 15:51:14,629 INFO [train.py:715] (3/8) Epoch 16, batch 7500, loss[loss=0.1597, simple_loss=0.2395, pruned_loss=0.03994, over 4926.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.03017, over 972190.59 frames.], batch size: 23, lr: 1.39e-04
+2022-05-08 15:51:53,688 INFO [train.py:715] (3/8) Epoch 16, batch 7550, loss[loss=0.1316, simple_loss=0.2087, pruned_loss=0.02726, over 4766.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03003, over 972323.26 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 15:52:33,702 INFO [train.py:715] (3/8) Epoch 16, batch 7600, loss[loss=0.1276, simple_loss=0.199, pruned_loss=0.02804, over 4851.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02931, over 971330.25 frames.], batch size: 20, lr: 1.39e-04
+2022-05-08 15:53:14,085 INFO [train.py:715] (3/8) Epoch 16, batch 7650, loss[loss=0.157, simple_loss=0.2256, pruned_loss=0.04417, over 4851.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.02947, over 971239.70 frames.], batch size: 30, lr: 1.39e-04
+2022-05-08 15:53:54,226 INFO [train.py:715] (3/8) Epoch 16, batch 7700, loss[loss=0.1316, simple_loss=0.2142, pruned_loss=0.02452, over 4823.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02955, over 971382.61 frames.], batch size: 25, lr: 1.39e-04
+2022-05-08 15:54:33,735 INFO [train.py:715] (3/8) Epoch 16, batch 7750, loss[loss=0.1223, simple_loss=0.1981, pruned_loss=0.02325, over 4944.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02942, over 971479.68 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 15:55:13,928 INFO [train.py:715] (3/8) Epoch 16, batch 7800, loss[loss=0.1525, simple_loss=0.229, pruned_loss=0.03804, over 4832.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02935, over 971838.02 frames.], batch size: 26, lr: 1.39e-04
+2022-05-08 15:55:54,770 INFO [train.py:715] (3/8) Epoch 16, batch 7850, loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02874, over 4785.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02945, over 971428.05 frames.], batch size: 14, lr: 1.39e-04
+2022-05-08 15:56:34,178 INFO [train.py:715] (3/8) Epoch 16, batch 7900, loss[loss=0.09852, simple_loss=0.1694, pruned_loss=0.01381, over 4845.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02923, over 971817.02 frames.], batch size: 12, lr: 1.39e-04
+2022-05-08 15:57:14,067 INFO [train.py:715] (3/8) Epoch 16, batch 7950, loss[loss=0.1321, simple_loss=0.2204, pruned_loss=0.02189, over 4988.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2083, pruned_loss=0.02939, over 972262.02 frames.], batch size: 25, lr: 1.39e-04
+2022-05-08 15:57:54,571 INFO [train.py:715] (3/8) Epoch 16, batch 8000, loss[loss=0.15, simple_loss=0.2277, pruned_loss=0.03613, over 4921.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2083, pruned_loss=0.02933, over 970670.48 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 15:58:34,608 INFO [train.py:715] (3/8) Epoch 16, batch 8050, loss[loss=0.1507, simple_loss=0.2271, pruned_loss=0.03715, over 4977.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02956, over 970765.92 frames.], batch size: 24, lr: 1.39e-04
+2022-05-08 15:59:14,261 INFO [train.py:715] (3/8) Epoch 16, batch 8100, loss[loss=0.1584, simple_loss=0.227, pruned_loss=0.04496, over 4899.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02967, over 970701.47 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 15:59:54,682 INFO [train.py:715] (3/8) Epoch 16, batch 8150, loss[loss=0.1226, simple_loss=0.2017, pruned_loss=0.0217, over 4798.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.0301, over 971867.05 frames.], batch size: 25, lr: 1.39e-04
+2022-05-08 16:00:35,757 INFO [train.py:715] (3/8) Epoch 16, batch 8200, loss[loss=0.1448, simple_loss=0.2199, pruned_loss=0.03483, over 4805.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2089, pruned_loss=0.02993, over 972251.57 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 16:01:15,839 INFO [train.py:715] (3/8) Epoch 16, batch 8250, loss[loss=0.1365, simple_loss=0.2148, pruned_loss=0.02913, over 4954.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.0297, over 972483.83 frames.], batch size: 29, lr: 1.39e-04
+2022-05-08 16:01:55,594 INFO [train.py:715] (3/8) Epoch 16, batch 8300, loss[loss=0.124, simple_loss=0.1877, pruned_loss=0.03017, over 4828.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02943, over 972435.47 frames.], batch size: 13, lr: 1.39e-04
+2022-05-08 16:02:36,305 INFO [train.py:715] (3/8) Epoch 16, batch 8350, loss[loss=0.1281, simple_loss=0.2036, pruned_loss=0.02632, over 4923.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02977, over 972647.01 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 16:03:16,606 INFO [train.py:715] (3/8) Epoch 16, batch 8400, loss[loss=0.1545, simple_loss=0.2278, pruned_loss=0.04062, over 4790.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02955, over 972591.49 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 16:03:55,138 INFO [train.py:715] (3/8) Epoch 16, batch 8450, loss[loss=0.1189, simple_loss=0.195, pruned_loss=0.02145, over 4793.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02945, over 972097.93 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 16:04:34,542 INFO [train.py:715] (3/8) Epoch 16, batch 8500, loss[loss=0.1923, simple_loss=0.2376, pruned_loss=0.07352, over 4757.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02975, over 971413.70 frames.], batch size: 12, lr: 1.39e-04
+2022-05-08 16:05:13,265 INFO [train.py:715] (3/8) Epoch 16, batch 8550, loss[loss=0.1292, simple_loss=0.2064, pruned_loss=0.02601, over 4844.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02981, over 971626.47 frames.], batch size: 20, lr: 1.39e-04
+2022-05-08 16:05:51,581 INFO [train.py:715] (3/8) Epoch 16, batch 8600, loss[loss=0.1347, simple_loss=0.2146, pruned_loss=0.0274, over 4857.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02928, over 971478.79 frames.], batch size: 38, lr: 1.39e-04
+2022-05-08 16:06:29,597 INFO [train.py:715] (3/8) Epoch 16, batch 8650, loss[loss=0.1119, simple_loss=0.1907, pruned_loss=0.01653, over 4828.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02941, over 971852.13 frames.], batch size: 13, lr: 1.39e-04
+2022-05-08 16:07:08,673 INFO [train.py:715] (3/8) Epoch 16, batch 8700, loss[loss=0.1211, simple_loss=0.1992, pruned_loss=0.02145, over 4813.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02979, over 970962.88 frames.], batch size: 26, lr: 1.39e-04
+2022-05-08 16:07:47,716 INFO [train.py:715] (3/8) Epoch 16, batch 8750, loss[loss=0.1172, simple_loss=0.1993, pruned_loss=0.01752, over 4786.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02985, over 971120.67 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 16:08:26,280 INFO [train.py:715] (3/8) Epoch 16, batch 8800, loss[loss=0.1259, simple_loss=0.2004, pruned_loss=0.02568, over 4901.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02946, over 971620.18 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 16:09:04,975 INFO [train.py:715] (3/8) Epoch 16, batch 8850, loss[loss=0.1186, simple_loss=0.2007, pruned_loss=0.01829, over 4977.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02963, over 971750.07 frames.], batch size: 28, lr: 1.39e-04
+2022-05-08 16:09:44,466 INFO [train.py:715] (3/8) Epoch 16, batch 8900, loss[loss=0.1397, simple_loss=0.2064, pruned_loss=0.03654, over 4979.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03039, over 971800.28 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 16:10:22,908 INFO [train.py:715] (3/8) Epoch 16, batch 8950, loss[loss=0.1551, simple_loss=0.2202, pruned_loss=0.045, over 4897.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02996, over 971550.07 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 16:11:01,141 INFO [train.py:715] (3/8) Epoch 16, batch 9000, loss[loss=0.1378, simple_loss=0.2065, pruned_loss=0.03457, over 4948.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02962, over 971742.71 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 16:11:01,142 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 16:11:23,893 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.105, simple_loss=0.1884, pruned_loss=0.01076, over 914524.00 frames.
+2022-05-08 16:12:02,819 INFO [train.py:715] (3/8) Epoch 16, batch 9050, loss[loss=0.1334, simple_loss=0.2043, pruned_loss=0.03127, over 4792.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.02969, over 972493.41 frames.], batch size: 14, lr: 1.39e-04
+2022-05-08 16:12:41,946 INFO [train.py:715] (3/8) Epoch 16, batch 9100, loss[loss=0.1277, simple_loss=0.2029, pruned_loss=0.02622, over 4691.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.0296, over 972641.49 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 16:13:20,956 INFO [train.py:715] (3/8) Epoch 16, batch 9150, loss[loss=0.1659, simple_loss=0.2278, pruned_loss=0.05198, over 4917.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02906, over 971851.65 frames.], batch size: 39, lr: 1.39e-04
+2022-05-08 16:13:58,479 INFO [train.py:715] (3/8) Epoch 16, batch 9200, loss[loss=0.1395, simple_loss=0.2088, pruned_loss=0.03506, over 4953.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02977, over 971893.00 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 16:14:37,128 INFO [train.py:715] (3/8) Epoch 16, batch 9250, loss[loss=0.1151, simple_loss=0.1887, pruned_loss=0.02074, over 4908.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02942, over 972821.56 frames.], batch size: 23, lr: 1.39e-04
+2022-05-08 16:15:16,084 INFO [train.py:715] (3/8) Epoch 16, batch 9300, loss[loss=0.1219, simple_loss=0.1921, pruned_loss=0.02582, over 4865.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02923, over 973447.67 frames.], batch size: 13, lr: 1.39e-04
+2022-05-08 16:15:54,778 INFO [train.py:715] (3/8) Epoch 16, batch 9350, loss[loss=0.1156, simple_loss=0.1914, pruned_loss=0.01986, over 4977.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02927, over 973473.15 frames.], batch size: 33, lr: 1.39e-04
+2022-05-08 16:16:33,102 INFO [train.py:715] (3/8) Epoch 16, batch 9400, loss[loss=0.1516, simple_loss=0.2297, pruned_loss=0.03676, over 4782.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02937, over 972999.98 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 16:17:11,621 INFO [train.py:715] (3/8) Epoch 16, batch 9450, loss[loss=0.1608, simple_loss=0.2361, pruned_loss=0.04275, over 4960.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02969, over 973647.12 frames.], batch size: 35, lr: 1.39e-04
+2022-05-08 16:17:50,527 INFO [train.py:715] (3/8) Epoch 16, batch 9500, loss[loss=0.1274, simple_loss=0.1919, pruned_loss=0.03142, over 4839.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03016, over 973300.29 frames.], batch size: 13, lr: 1.39e-04
+2022-05-08 16:18:28,785 INFO [train.py:715] (3/8) Epoch 16, batch 9550, loss[loss=0.1274, simple_loss=0.2041, pruned_loss=0.02539, over 4854.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.0303, over 972466.35 frames.], batch size: 30, lr: 1.39e-04
+2022-05-08 16:19:08,107 INFO [train.py:715] (3/8) Epoch 16, batch 9600, loss[loss=0.1275, simple_loss=0.1989, pruned_loss=0.02801, over 4860.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2091, pruned_loss=0.0301, over 972649.56 frames.], batch size: 32, lr: 1.39e-04
+2022-05-08 16:19:47,953 INFO [train.py:715] (3/8) Epoch 16, batch 9650, loss[loss=0.1347, simple_loss=0.2139, pruned_loss=0.02774, over 4881.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.02999, over 973057.38 frames.], batch size: 16, lr: 1.39e-04
+2022-05-08 16:20:27,616 INFO [train.py:715] (3/8) Epoch 16, batch 9700, loss[loss=0.1148, simple_loss=0.1931, pruned_loss=0.01826, over 4898.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03036, over 972480.71 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 16:21:08,037 INFO [train.py:715] (3/8) Epoch 16, batch 9750, loss[loss=0.1628, simple_loss=0.2444, pruned_loss=0.0406, over 4915.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2089, pruned_loss=0.03007, over 972719.19 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 16:21:49,087 INFO [train.py:715] (3/8) Epoch 16, batch 9800, loss[loss=0.1087, simple_loss=0.1818, pruned_loss=0.01778, over 4958.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03019, over 972845.53 frames.], batch size: 24, lr: 1.39e-04
+2022-05-08 16:22:29,520 INFO [train.py:715] (3/8) Epoch 16, batch 9850, loss[loss=0.1337, simple_loss=0.2133, pruned_loss=0.02703, over 4962.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02977, over 973206.39 frames.], batch size: 24, lr: 1.39e-04
+2022-05-08 16:23:09,312 INFO [train.py:715] (3/8) Epoch 16, batch 9900, loss[loss=0.1175, simple_loss=0.1986, pruned_loss=0.01823, over 4988.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03024, over 972928.14 frames.], batch size: 20, lr: 1.39e-04
+2022-05-08 16:23:49,494 INFO [train.py:715] (3/8) Epoch 16, batch 9950, loss[loss=0.1217, simple_loss=0.1967, pruned_loss=0.02333, over 4883.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03032, over 973030.50 frames.], batch size: 22, lr: 1.39e-04
+2022-05-08 16:24:30,467 INFO [train.py:715] (3/8) Epoch 16, batch 10000, loss[loss=0.1174, simple_loss=0.2034, pruned_loss=0.01568, over 4978.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03018, over 973479.42 frames.], batch size: 28, lr: 1.39e-04
+2022-05-08 16:25:09,397 INFO [train.py:715] (3/8) Epoch 16, batch 10050, loss[loss=0.1142, simple_loss=0.1834, pruned_loss=0.02253, over 4854.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03001, over 973534.24 frames.], batch size: 30, lr: 1.39e-04
+2022-05-08 16:25:49,623 INFO [train.py:715] (3/8) Epoch 16, batch 10100, loss[loss=0.1209, simple_loss=0.199, pruned_loss=0.0214, over 4903.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.0299, over 973099.94 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 16:26:30,395 INFO [train.py:715] (3/8) Epoch 16, batch 10150, loss[loss=0.1293, simple_loss=0.2135, pruned_loss=0.02252, over 4981.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02949, over 972581.96 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 16:27:10,600 INFO [train.py:715] (3/8) Epoch 16, batch 10200, loss[loss=0.1366, simple_loss=0.209, pruned_loss=0.03213, over 4770.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02968, over 972318.21 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 16:27:49,590 INFO [train.py:715] (3/8) Epoch 16, batch 10250, loss[loss=0.1385, simple_loss=0.2246, pruned_loss=0.02623, over 4752.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02988, over 972763.19 frames.], batch size: 16, lr: 1.39e-04
+2022-05-08 16:28:29,499 INFO [train.py:715] (3/8) Epoch 16, batch 10300, loss[loss=0.1191, simple_loss=0.1911, pruned_loss=0.02356, over 4981.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02993, over 973602.39 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 16:29:09,157 INFO [train.py:715] (3/8) Epoch 16, batch 10350, loss[loss=0.1649, simple_loss=0.2464, pruned_loss=0.04176, over 4775.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03037, over 972681.18 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 16:29:47,476 INFO [train.py:715] (3/8) Epoch 16, batch 10400, loss[loss=0.1479, simple_loss=0.2184, pruned_loss=0.03864, over 4813.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03043, over 972725.69 frames.], batch size: 26, lr: 1.39e-04
+2022-05-08 16:30:26,268 INFO [train.py:715] (3/8) Epoch 16, batch 10450, loss[loss=0.1209, simple_loss=0.1991, pruned_loss=0.02132, over 4809.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03075, over 972712.85 frames.], batch size: 25, lr: 1.39e-04
+2022-05-08 16:31:05,206 INFO [train.py:715] (3/8) Epoch 16, batch 10500, loss[loss=0.1585, simple_loss=0.2338, pruned_loss=0.04159, over 4840.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03085, over 972865.58 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 16:31:44,638 INFO [train.py:715] (3/8) Epoch 16, batch 10550, loss[loss=0.1393, simple_loss=0.2139, pruned_loss=0.03234, over 4905.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03099, over 973359.20 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 16:32:22,616 INFO [train.py:715] (3/8) Epoch 16, batch 10600, loss[loss=0.1303, simple_loss=0.1927, pruned_loss=0.03398, over 4800.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03041, over 973488.84 frames.], batch size: 12, lr: 1.39e-04
+2022-05-08 16:33:01,320 INFO [train.py:715] (3/8) Epoch 16, batch 10650, loss[loss=0.1164, simple_loss=0.1984, pruned_loss=0.01723, over 4936.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03054, over 972998.02 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 16:33:40,769 INFO [train.py:715] (3/8) Epoch 16, batch 10700, loss[loss=0.1307, simple_loss=0.2037, pruned_loss=0.0288, over 4891.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03077, over 972688.38 frames.], batch size: 22, lr: 1.39e-04
+2022-05-08 16:34:19,605 INFO [train.py:715] (3/8) Epoch 16, batch 10750, loss[loss=0.1439, simple_loss=0.2176, pruned_loss=0.03506, over 4875.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2095, pruned_loss=0.03051, over 971985.81 frames.], batch size: 38, lr: 1.39e-04
+2022-05-08 16:34:58,504 INFO [train.py:715] (3/8) Epoch 16, batch 10800, loss[loss=0.1147, simple_loss=0.1983, pruned_loss=0.01554, over 4751.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03, over 972573.82 frames.], batch size: 19, lr: 1.39e-04
+2022-05-08 16:35:37,667 INFO [train.py:715] (3/8) Epoch 16, batch 10850, loss[loss=0.1496, simple_loss=0.2321, pruned_loss=0.03352, over 4893.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03013, over 973096.65 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 16:36:17,327 INFO [train.py:715] (3/8) Epoch 16, batch 10900, loss[loss=0.129, simple_loss=0.2023, pruned_loss=0.02783, over 4912.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02982, over 972628.78 frames.], batch size: 22, lr: 1.39e-04
+2022-05-08 16:36:55,551 INFO [train.py:715] (3/8) Epoch 16, batch 10950, loss[loss=0.1163, simple_loss=0.1984, pruned_loss=0.01714, over 4784.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03019, over 973257.46 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 16:37:34,521 INFO [train.py:715] (3/8) Epoch 16, batch 11000, loss[loss=0.1398, simple_loss=0.2101, pruned_loss=0.03472, over 4753.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02997, over 972787.45 frames.], batch size: 14, lr: 1.39e-04
+2022-05-08 16:38:13,976 INFO [train.py:715] (3/8) Epoch 16, batch 11050, loss[loss=0.1675, simple_loss=0.2354, pruned_loss=0.04982, over 4959.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02983, over 972589.56 frames.], batch size: 14, lr: 1.39e-04
+2022-05-08 16:38:55,222 INFO [train.py:715] (3/8) Epoch 16, batch 11100, loss[loss=0.1194, simple_loss=0.1922, pruned_loss=0.02331, over 4826.00 frames.], tot_loss[loss=0.133, simple_loss=0.2067, pruned_loss=0.02971, over 972823.92 frames.], batch size: 13, lr: 1.39e-04
+2022-05-08 16:39:33,650 INFO [train.py:715] (3/8) Epoch 16, batch 11150, loss[loss=0.1477, simple_loss=0.2237, pruned_loss=0.03584, over 4942.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02945, over 971707.81 frames.], batch size: 35, lr: 1.39e-04
+2022-05-08 16:40:12,899 INFO [train.py:715] (3/8) Epoch 16, batch 11200, loss[loss=0.1674, simple_loss=0.2366, pruned_loss=0.04911, over 4856.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2062, pruned_loss=0.02941, over 971574.97 frames.], batch size: 32, lr: 1.39e-04
+2022-05-08 16:40:51,684 INFO [train.py:715] (3/8) Epoch 16, batch 11250, loss[loss=0.145, simple_loss=0.2044, pruned_loss=0.04277, over 4883.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02986, over 972321.23 frames.], batch size: 32, lr: 1.39e-04
+2022-05-08 16:41:29,876 INFO [train.py:715] (3/8) Epoch 16, batch 11300, loss[loss=0.1267, simple_loss=0.2001, pruned_loss=0.02658, over 4778.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.0296, over 971894.16 frames.], batch size: 18, lr: 1.39e-04
+2022-05-08 16:42:08,150 INFO [train.py:715] (3/8) Epoch 16, batch 11350, loss[loss=0.158, simple_loss=0.2336, pruned_loss=0.0412, over 4980.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02915, over 971991.56 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 16:42:47,130 INFO [train.py:715] (3/8) Epoch 16, batch 11400, loss[loss=0.1348, simple_loss=0.212, pruned_loss=0.02878, over 4987.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02914, over 971644.87 frames.], batch size: 14, lr: 1.39e-04
+2022-05-08 16:43:25,155 INFO [train.py:715] (3/8) Epoch 16, batch 11450, loss[loss=0.1442, simple_loss=0.2252, pruned_loss=0.03159, over 4948.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02922, over 971023.54 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 16:44:03,096 INFO [train.py:715] (3/8) Epoch 16, batch 11500, loss[loss=0.1274, simple_loss=0.2024, pruned_loss=0.02623, over 4837.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2059, pruned_loss=0.02921, over 971280.28 frames.], batch size: 15, lr: 1.39e-04
+2022-05-08 16:44:41,777 INFO [train.py:715] (3/8) Epoch 16, batch 11550, loss[loss=0.1257, simple_loss=0.1994, pruned_loss=0.02602, over 4985.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2062, pruned_loss=0.02928, over 971589.88 frames.], batch size: 28, lr: 1.39e-04
+2022-05-08 16:45:20,368 INFO [train.py:715] (3/8) Epoch 16, batch 11600, loss[loss=0.121, simple_loss=0.1946, pruned_loss=0.02374, over 4946.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2063, pruned_loss=0.0295, over 971453.61 frames.], batch size: 29, lr: 1.39e-04
+2022-05-08 16:45:57,963 INFO [train.py:715] (3/8) Epoch 16, batch 11650, loss[loss=0.1356, simple_loss=0.2024, pruned_loss=0.03436, over 4979.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2063, pruned_loss=0.0296, over 971556.28 frames.], batch size: 28, lr: 1.39e-04
+2022-05-08 16:46:36,441 INFO [train.py:715] (3/8) Epoch 16, batch 11700, loss[loss=0.1341, simple_loss=0.2125, pruned_loss=0.02789, over 4802.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02929, over 971942.84 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 16:47:15,523 INFO [train.py:715] (3/8) Epoch 16, batch 11750, loss[loss=0.1484, simple_loss=0.2276, pruned_loss=0.0346, over 4940.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02943, over 972507.94 frames.], batch size: 21, lr: 1.39e-04
+2022-05-08 16:47:53,674 INFO [train.py:715] (3/8) Epoch 16, batch 11800, loss[loss=0.1392, simple_loss=0.2092, pruned_loss=0.03465, over 4852.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02914, over 972926.76 frames.], batch size: 20, lr: 1.39e-04
+2022-05-08 16:48:31,492 INFO [train.py:715] (3/8) Epoch 16, batch 11850, loss[loss=0.1131, simple_loss=0.1841, pruned_loss=0.02104, over 4783.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.0291, over 972609.28 frames.], batch size: 17, lr: 1.39e-04
+2022-05-08 16:49:10,178 INFO [train.py:715] (3/8) Epoch 16, batch 11900, loss[loss=0.1344, simple_loss=0.2051, pruned_loss=0.03181, over 4971.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02947, over 972832.26 frames.], batch size: 35, lr: 1.39e-04
+2022-05-08 16:49:48,597 INFO [train.py:715] (3/8) Epoch 16, batch 11950, loss[loss=0.1247, simple_loss=0.1964, pruned_loss=0.02651, over 4934.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02915, over 971935.17 frames.], batch size: 23, lr: 1.39e-04
+2022-05-08 16:50:26,416 INFO [train.py:715] (3/8) Epoch 16, batch 12000, loss[loss=0.1193, simple_loss=0.1973, pruned_loss=0.02064, over 4931.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02928, over 972344.75 frames.], batch size: 18, lr: 1.38e-04
+2022-05-08 16:50:26,417 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 16:50:37,200 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.1049, simple_loss=0.1884, pruned_loss=0.01072, over 914524.00 frames.
+2022-05-08 16:51:16,049 INFO [train.py:715] (3/8) Epoch 16, batch 12050, loss[loss=0.1181, simple_loss=0.1897, pruned_loss=0.02323, over 4992.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02944, over 972320.42 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 16:51:55,271 INFO [train.py:715] (3/8) Epoch 16, batch 12100, loss[loss=0.1911, simple_loss=0.2725, pruned_loss=0.05491, over 4858.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02969, over 972234.20 frames.], batch size: 32, lr: 1.38e-04
+2022-05-08 16:52:34,709 INFO [train.py:715] (3/8) Epoch 16, batch 12150, loss[loss=0.1389, simple_loss=0.2164, pruned_loss=0.0307, over 4957.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03002, over 972583.45 frames.], batch size: 35, lr: 1.38e-04
+2022-05-08 16:53:12,374 INFO [train.py:715] (3/8) Epoch 16, batch 12200, loss[loss=0.1073, simple_loss=0.189, pruned_loss=0.01282, over 4880.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02946, over 971466.27 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 16:53:50,655 INFO [train.py:715] (3/8) Epoch 16, batch 12250, loss[loss=0.1113, simple_loss=0.1762, pruned_loss=0.02322, over 4974.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02932, over 971308.31 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 16:54:29,691 INFO [train.py:715] (3/8) Epoch 16, batch 12300, loss[loss=0.1372, simple_loss=0.224, pruned_loss=0.02522, over 4840.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02949, over 972742.46 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 16:55:08,773 INFO [train.py:715] (3/8) Epoch 16, batch 12350, loss[loss=0.1251, simple_loss=0.197, pruned_loss=0.02657, over 4777.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02924, over 973205.26 frames.], batch size: 18, lr: 1.38e-04
+2022-05-08 16:55:47,032 INFO [train.py:715] (3/8) Epoch 16, batch 12400, loss[loss=0.1406, simple_loss=0.2148, pruned_loss=0.0332, over 4927.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03014, over 974256.26 frames.], batch size: 23, lr: 1.38e-04
+2022-05-08 16:56:26,129 INFO [train.py:715] (3/8) Epoch 16, batch 12450, loss[loss=0.1275, simple_loss=0.1872, pruned_loss=0.03384, over 4647.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02963, over 973984.56 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 16:57:05,990 INFO [train.py:715] (3/8) Epoch 16, batch 12500, loss[loss=0.1345, simple_loss=0.209, pruned_loss=0.03005, over 4942.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03023, over 973482.21 frames.], batch size: 39, lr: 1.38e-04
+2022-05-08 16:57:44,599 INFO [train.py:715] (3/8) Epoch 16, batch 12550, loss[loss=0.1287, simple_loss=0.2038, pruned_loss=0.02676, over 4864.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03009, over 973529.75 frames.], batch size: 30, lr: 1.38e-04
+2022-05-08 16:58:23,183 INFO [train.py:715] (3/8) Epoch 16, batch 12600, loss[loss=0.1061, simple_loss=0.1739, pruned_loss=0.01914, over 4980.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02978, over 972221.31 frames.], batch size: 24, lr: 1.38e-04
+2022-05-08 16:59:01,907 INFO [train.py:715] (3/8) Epoch 16, batch 12650, loss[loss=0.1257, simple_loss=0.1905, pruned_loss=0.0304, over 4881.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03014, over 972178.91 frames.], batch size: 22, lr: 1.38e-04
+2022-05-08 16:59:40,540 INFO [train.py:715] (3/8) Epoch 16, batch 12700, loss[loss=0.1329, simple_loss=0.2021, pruned_loss=0.03182, over 4912.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03005, over 971852.93 frames.], batch size: 18, lr: 1.38e-04
+2022-05-08 17:00:18,083 INFO [train.py:715] (3/8) Epoch 16, batch 12750, loss[loss=0.1138, simple_loss=0.186, pruned_loss=0.02079, over 4903.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02961, over 971183.79 frames.], batch size: 17, lr: 1.38e-04
+2022-05-08 17:00:57,707 INFO [train.py:715] (3/8) Epoch 16, batch 12800, loss[loss=0.1176, simple_loss=0.1967, pruned_loss=0.01923, over 4837.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02943, over 971852.29 frames.], batch size: 27, lr: 1.38e-04
+2022-05-08 17:01:36,685 INFO [train.py:715] (3/8) Epoch 16, batch 12850, loss[loss=0.1273, simple_loss=0.2092, pruned_loss=0.02274, over 4765.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02968, over 971843.60 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 17:02:15,047 INFO [train.py:715] (3/8) Epoch 16, batch 12900, loss[loss=0.114, simple_loss=0.1993, pruned_loss=0.01432, over 4939.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02947, over 972780.18 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 17:02:53,760 INFO [train.py:715] (3/8) Epoch 16, batch 12950, loss[loss=0.1245, simple_loss=0.1985, pruned_loss=0.02523, over 4843.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02935, over 972940.40 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 17:03:32,779 INFO [train.py:715] (3/8) Epoch 16, batch 13000, loss[loss=0.1332, simple_loss=0.2125, pruned_loss=0.02696, over 4775.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.0298, over 972286.68 frames.], batch size: 17, lr: 1.38e-04
+2022-05-08 17:04:11,282 INFO [train.py:715] (3/8) Epoch 16, batch 13050, loss[loss=0.1276, simple_loss=0.1964, pruned_loss=0.02942, over 4859.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03013, over 972383.09 frames.], batch size: 12, lr: 1.38e-04
+2022-05-08 17:04:49,803 INFO [train.py:715] (3/8) Epoch 16, batch 13100, loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02978, over 4787.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02981, over 972293.43 frames.], batch size: 17, lr: 1.38e-04
+2022-05-08 17:05:28,954 INFO [train.py:715] (3/8) Epoch 16, batch 13150, loss[loss=0.1261, simple_loss=0.1954, pruned_loss=0.02836, over 4925.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02952, over 971757.77 frames.], batch size: 18, lr: 1.38e-04
+2022-05-08 17:06:08,077 INFO [train.py:715] (3/8) Epoch 16, batch 13200, loss[loss=0.1373, simple_loss=0.2184, pruned_loss=0.02812, over 4835.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02982, over 971981.75 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:06:46,154 INFO [train.py:715] (3/8) Epoch 16, batch 13250, loss[loss=0.1291, simple_loss=0.1994, pruned_loss=0.02943, over 4649.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02993, over 972466.47 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 17:07:25,007 INFO [train.py:715] (3/8) Epoch 16, batch 13300, loss[loss=0.1485, simple_loss=0.2184, pruned_loss=0.03933, over 4744.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02986, over 972876.33 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 17:08:04,361 INFO [train.py:715] (3/8) Epoch 16, batch 13350, loss[loss=0.1473, simple_loss=0.2208, pruned_loss=0.03691, over 4865.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02984, over 972354.63 frames.], batch size: 30, lr: 1.38e-04
+2022-05-08 17:08:42,685 INFO [train.py:715] (3/8) Epoch 16, batch 13400, loss[loss=0.1635, simple_loss=0.2314, pruned_loss=0.04777, over 4988.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02967, over 972361.86 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:09:21,148 INFO [train.py:715] (3/8) Epoch 16, batch 13450, loss[loss=0.1331, simple_loss=0.2098, pruned_loss=0.02818, over 4825.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02973, over 971593.57 frames.], batch size: 26, lr: 1.38e-04
+2022-05-08 17:10:00,908 INFO [train.py:715] (3/8) Epoch 16, batch 13500, loss[loss=0.1391, simple_loss=0.2102, pruned_loss=0.03406, over 4869.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02954, over 970958.29 frames.], batch size: 30, lr: 1.38e-04
+2022-05-08 17:10:39,239 INFO [train.py:715] (3/8) Epoch 16, batch 13550, loss[loss=0.1187, simple_loss=0.2136, pruned_loss=0.01195, over 4777.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02975, over 970813.51 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 17:11:17,352 INFO [train.py:715] (3/8) Epoch 16, batch 13600, loss[loss=0.1401, simple_loss=0.2108, pruned_loss=0.0347, over 4978.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02952, over 970666.15 frames.], batch size: 24, lr: 1.38e-04
+2022-05-08 17:11:56,186 INFO [train.py:715] (3/8) Epoch 16, batch 13650, loss[loss=0.1298, simple_loss=0.2007, pruned_loss=0.02949, over 4816.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02949, over 970873.88 frames.], batch size: 25, lr: 1.38e-04
+2022-05-08 17:12:35,109 INFO [train.py:715] (3/8) Epoch 16, batch 13700, loss[loss=0.1299, simple_loss=0.2111, pruned_loss=0.02436, over 4817.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02946, over 970911.25 frames.], batch size: 25, lr: 1.38e-04
+2022-05-08 17:13:13,500 INFO [train.py:715] (3/8) Epoch 16, batch 13750, loss[loss=0.1508, simple_loss=0.2365, pruned_loss=0.03257, over 4841.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2062, pruned_loss=0.02933, over 970371.13 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:13:52,015 INFO [train.py:715] (3/8) Epoch 16, batch 13800, loss[loss=0.1366, simple_loss=0.2019, pruned_loss=0.03567, over 4778.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02944, over 971074.05 frames.], batch size: 12, lr: 1.38e-04
+2022-05-08 17:14:30,651 INFO [train.py:715] (3/8) Epoch 16, batch 13850, loss[loss=0.1158, simple_loss=0.1841, pruned_loss=0.02377, over 4836.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02929, over 972137.80 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 17:15:08,624 INFO [train.py:715] (3/8) Epoch 16, batch 13900, loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03021, over 4976.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.02961, over 972431.36 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:15:46,310 INFO [train.py:715] (3/8) Epoch 16, batch 13950, loss[loss=0.1496, simple_loss=0.2175, pruned_loss=0.04089, over 4970.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02992, over 973089.62 frames.], batch size: 35, lr: 1.38e-04
+2022-05-08 17:16:24,662 INFO [train.py:715] (3/8) Epoch 16, batch 14000, loss[loss=0.1319, simple_loss=0.2085, pruned_loss=0.02769, over 4881.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03026, over 972964.35 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 17:17:03,285 INFO [train.py:715] (3/8) Epoch 16, batch 14050, loss[loss=0.1282, simple_loss=0.2105, pruned_loss=0.02291, over 4814.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03091, over 972451.79 frames.], batch size: 26, lr: 1.38e-04
+2022-05-08 17:17:41,058 INFO [train.py:715] (3/8) Epoch 16, batch 14100, loss[loss=0.1224, simple_loss=0.2008, pruned_loss=0.02206, over 4810.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03072, over 972603.30 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 17:18:18,777 INFO [train.py:715] (3/8) Epoch 16, batch 14150, loss[loss=0.1308, simple_loss=0.2163, pruned_loss=0.02265, over 4958.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03066, over 973510.82 frames.], batch size: 28, lr: 1.38e-04
+2022-05-08 17:18:57,315 INFO [train.py:715] (3/8) Epoch 16, batch 14200, loss[loss=0.1308, simple_loss=0.2016, pruned_loss=0.02996, over 4811.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03019, over 973051.90 frames.], batch size: 25, lr: 1.38e-04
+2022-05-08 17:19:36,008 INFO [train.py:715] (3/8) Epoch 16, batch 14250, loss[loss=0.1547, simple_loss=0.2257, pruned_loss=0.04182, over 4877.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03031, over 972304.24 frames.], batch size: 20, lr: 1.38e-04
+2022-05-08 17:20:14,627 INFO [train.py:715] (3/8) Epoch 16, batch 14300, loss[loss=0.1169, simple_loss=0.1952, pruned_loss=0.01934, over 4960.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03006, over 973308.11 frames.], batch size: 24, lr: 1.38e-04
+2022-05-08 17:20:53,332 INFO [train.py:715] (3/8) Epoch 16, batch 14350, loss[loss=0.1615, simple_loss=0.2391, pruned_loss=0.04199, over 4794.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02997, over 973554.07 frames.], batch size: 17, lr: 1.38e-04
+2022-05-08 17:21:32,525 INFO [train.py:715] (3/8) Epoch 16, batch 14400, loss[loss=0.1174, simple_loss=0.1928, pruned_loss=0.02103, over 4855.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03001, over 972676.49 frames.], batch size: 20, lr: 1.38e-04
+2022-05-08 17:22:10,262 INFO [train.py:715] (3/8) Epoch 16, batch 14450, loss[loss=0.1107, simple_loss=0.1713, pruned_loss=0.02509, over 4788.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02975, over 972177.52 frames.], batch size: 12, lr: 1.38e-04
+2022-05-08 17:22:49,091 INFO [train.py:715] (3/8) Epoch 16, batch 14500, loss[loss=0.1491, simple_loss=0.2254, pruned_loss=0.03645, over 4900.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.02999, over 971685.02 frames.], batch size: 19, lr: 1.38e-04
+2022-05-08 17:23:28,026 INFO [train.py:715] (3/8) Epoch 16, batch 14550, loss[loss=0.1219, simple_loss=0.1995, pruned_loss=0.0222, over 4982.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02971, over 972318.52 frames.], batch size: 28, lr: 1.38e-04
+2022-05-08 17:24:06,693 INFO [train.py:715] (3/8) Epoch 16, batch 14600, loss[loss=0.1233, simple_loss=0.2013, pruned_loss=0.02266, over 4812.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.02996, over 972254.39 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 17:24:44,965 INFO [train.py:715] (3/8) Epoch 16, batch 14650, loss[loss=0.1527, simple_loss=0.2221, pruned_loss=0.04169, over 4886.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02968, over 972232.40 frames.], batch size: 38, lr: 1.38e-04
+2022-05-08 17:25:23,541 INFO [train.py:715] (3/8) Epoch 16, batch 14700, loss[loss=0.133, simple_loss=0.2115, pruned_loss=0.02718, over 4734.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02977, over 971553.29 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 17:26:02,839 INFO [train.py:715] (3/8) Epoch 16, batch 14750, loss[loss=0.1532, simple_loss=0.2194, pruned_loss=0.04352, over 4839.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03036, over 972090.45 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:26:40,633 INFO [train.py:715] (3/8) Epoch 16, batch 14800, loss[loss=0.1176, simple_loss=0.1886, pruned_loss=0.0233, over 4920.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03003, over 972441.63 frames.], batch size: 29, lr: 1.38e-04
+2022-05-08 17:27:19,699 INFO [train.py:715] (3/8) Epoch 16, batch 14850, loss[loss=0.1233, simple_loss=0.2161, pruned_loss=0.01525, over 4799.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02928, over 972386.78 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 17:27:58,607 INFO [train.py:715] (3/8) Epoch 16, batch 14900, loss[loss=0.1595, simple_loss=0.2223, pruned_loss=0.0483, over 4929.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02983, over 972477.12 frames.], batch size: 23, lr: 1.38e-04
+2022-05-08 17:28:37,059 INFO [train.py:715] (3/8) Epoch 16, batch 14950, loss[loss=0.1152, simple_loss=0.1982, pruned_loss=0.01606, over 4988.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.0298, over 973064.45 frames.], batch size: 25, lr: 1.38e-04
+2022-05-08 17:29:16,120 INFO [train.py:715] (3/8) Epoch 16, batch 15000, loss[loss=0.1393, simple_loss=0.2157, pruned_loss=0.0314, over 4993.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02994, over 972292.06 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 17:29:16,120 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 17:29:25,725 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.1049, simple_loss=0.1884, pruned_loss=0.01069, over 914524.00 frames.
+2022-05-08 17:30:04,000 INFO [train.py:715] (3/8) Epoch 16, batch 15050, loss[loss=0.1406, simple_loss=0.221, pruned_loss=0.03005, over 4761.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03048, over 972121.45 frames.], batch size: 18, lr: 1.38e-04
+2022-05-08 17:30:42,065 INFO [train.py:715] (3/8) Epoch 16, batch 15100, loss[loss=0.1091, simple_loss=0.1772, pruned_loss=0.02047, over 4823.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03012, over 972774.62 frames.], batch size: 27, lr: 1.38e-04
+2022-05-08 17:31:20,870 INFO [train.py:715] (3/8) Epoch 16, batch 15150, loss[loss=0.1253, simple_loss=0.1943, pruned_loss=0.02815, over 4873.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03006, over 972817.70 frames.], batch size: 22, lr: 1.38e-04
+2022-05-08 17:31:58,566 INFO [train.py:715] (3/8) Epoch 16, batch 15200, loss[loss=0.1264, simple_loss=0.2045, pruned_loss=0.02415, over 4806.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03019, over 972232.07 frames.], batch size: 26, lr: 1.38e-04
+2022-05-08 17:32:36,119 INFO [train.py:715] (3/8) Epoch 16, batch 15250, loss[loss=0.1445, simple_loss=0.2159, pruned_loss=0.03654, over 4967.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03016, over 972030.69 frames.], batch size: 28, lr: 1.38e-04
+2022-05-08 17:33:14,310 INFO [train.py:715] (3/8) Epoch 16, batch 15300, loss[loss=0.1324, simple_loss=0.209, pruned_loss=0.02795, over 4951.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03034, over 973196.41 frames.], batch size: 35, lr: 1.38e-04
+2022-05-08 17:33:52,457 INFO [train.py:715] (3/8) Epoch 16, batch 15350, loss[loss=0.1316, simple_loss=0.1983, pruned_loss=0.03247, over 4878.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03031, over 973385.90 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 17:34:30,726 INFO [train.py:715] (3/8) Epoch 16, batch 15400, loss[loss=0.156, simple_loss=0.2288, pruned_loss=0.04156, over 4910.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.03062, over 973364.63 frames.], batch size: 17, lr: 1.38e-04
+2022-05-08 17:35:08,739 INFO [train.py:715] (3/8) Epoch 16, batch 15450, loss[loss=0.1315, simple_loss=0.1972, pruned_loss=0.03292, over 4975.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03062, over 973735.24 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 17:35:47,169 INFO [train.py:715] (3/8) Epoch 16, batch 15500, loss[loss=0.1556, simple_loss=0.2216, pruned_loss=0.04483, over 4641.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03041, over 972916.00 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 17:36:24,799 INFO [train.py:715] (3/8) Epoch 16, batch 15550, loss[loss=0.1443, simple_loss=0.2063, pruned_loss=0.04114, over 4690.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03008, over 971688.78 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:37:02,466 INFO [train.py:715] (3/8) Epoch 16, batch 15600, loss[loss=0.09893, simple_loss=0.1735, pruned_loss=0.01215, over 4943.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03027, over 971871.55 frames.], batch size: 29, lr: 1.38e-04
+2022-05-08 17:37:41,084 INFO [train.py:715] (3/8) Epoch 16, batch 15650, loss[loss=0.1222, simple_loss=0.203, pruned_loss=0.02071, over 4804.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03023, over 972162.75 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 17:38:19,118 INFO [train.py:715] (3/8) Epoch 16, batch 15700, loss[loss=0.1684, simple_loss=0.2184, pruned_loss=0.05925, over 4980.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03055, over 971605.61 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:38:56,853 INFO [train.py:715] (3/8) Epoch 16, batch 15750, loss[loss=0.1351, simple_loss=0.2096, pruned_loss=0.03031, over 4840.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03036, over 971697.75 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:39:34,742 INFO [train.py:715] (3/8) Epoch 16, batch 15800, loss[loss=0.1346, simple_loss=0.2063, pruned_loss=0.03145, over 4880.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02961, over 972101.08 frames.], batch size: 22, lr: 1.38e-04
+2022-05-08 17:40:13,085 INFO [train.py:715] (3/8) Epoch 16, batch 15850, loss[loss=0.1228, simple_loss=0.1951, pruned_loss=0.02525, over 4786.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.02973, over 972370.28 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 17:40:50,712 INFO [train.py:715] (3/8) Epoch 16, batch 15900, loss[loss=0.1482, simple_loss=0.2157, pruned_loss=0.04039, over 4995.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.02997, over 972050.10 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 17:41:28,317 INFO [train.py:715] (3/8) Epoch 16, batch 15950, loss[loss=0.1463, simple_loss=0.2239, pruned_loss=0.03436, over 4934.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03029, over 971879.37 frames.], batch size: 29, lr: 1.38e-04
+2022-05-08 17:42:06,731 INFO [train.py:715] (3/8) Epoch 16, batch 16000, loss[loss=0.1265, simple_loss=0.2004, pruned_loss=0.02631, over 4789.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03001, over 972039.38 frames.], batch size: 17, lr: 1.38e-04
+2022-05-08 17:42:44,835 INFO [train.py:715] (3/8) Epoch 16, batch 16050, loss[loss=0.1077, simple_loss=0.1815, pruned_loss=0.01693, over 4782.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03022, over 971605.42 frames.], batch size: 17, lr: 1.38e-04
+2022-05-08 17:43:22,461 INFO [train.py:715] (3/8) Epoch 16, batch 16100, loss[loss=0.1325, simple_loss=0.2188, pruned_loss=0.02311, over 4971.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03023, over 972299.94 frames.], batch size: 24, lr: 1.38e-04
+2022-05-08 17:43:59,972 INFO [train.py:715] (3/8) Epoch 16, batch 16150, loss[loss=0.1159, simple_loss=0.1929, pruned_loss=0.01941, over 4973.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03031, over 971819.98 frames.], batch size: 24, lr: 1.38e-04
+2022-05-08 17:44:38,352 INFO [train.py:715] (3/8) Epoch 16, batch 16200, loss[loss=0.1643, simple_loss=0.2329, pruned_loss=0.04786, over 4920.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03008, over 971162.18 frames.], batch size: 23, lr: 1.38e-04
+2022-05-08 17:45:15,918 INFO [train.py:715] (3/8) Epoch 16, batch 16250, loss[loss=0.1292, simple_loss=0.2068, pruned_loss=0.02583, over 4793.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02961, over 971265.65 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 17:45:53,547 INFO [train.py:715] (3/8) Epoch 16, batch 16300, loss[loss=0.1679, simple_loss=0.2337, pruned_loss=0.05104, over 4850.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02964, over 971629.49 frames.], batch size: 30, lr: 1.38e-04
+2022-05-08 17:46:31,874 INFO [train.py:715] (3/8) Epoch 16, batch 16350, loss[loss=0.1398, simple_loss=0.2031, pruned_loss=0.03825, over 4988.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02963, over 971500.30 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:47:10,532 INFO [train.py:715] (3/8) Epoch 16, batch 16400, loss[loss=0.1069, simple_loss=0.1811, pruned_loss=0.0163, over 4658.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02975, over 970967.90 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 17:47:47,571 INFO [train.py:715] (3/8) Epoch 16, batch 16450, loss[loss=0.1168, simple_loss=0.1904, pruned_loss=0.02165, over 4759.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02959, over 970821.69 frames.], batch size: 19, lr: 1.38e-04
+2022-05-08 17:48:25,522 INFO [train.py:715] (3/8) Epoch 16, batch 16500, loss[loss=0.1279, simple_loss=0.2084, pruned_loss=0.02375, over 4814.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02957, over 971689.23 frames.], batch size: 26, lr: 1.38e-04
+2022-05-08 17:49:04,093 INFO [train.py:715] (3/8) Epoch 16, batch 16550, loss[loss=0.1344, simple_loss=0.2113, pruned_loss=0.0288, over 4841.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02974, over 972401.73 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:49:41,516 INFO [train.py:715] (3/8) Epoch 16, batch 16600, loss[loss=0.1402, simple_loss=0.2122, pruned_loss=0.03408, over 4853.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02976, over 973092.70 frames.], batch size: 34, lr: 1.38e-04
+2022-05-08 17:50:19,533 INFO [train.py:715] (3/8) Epoch 16, batch 16650, loss[loss=0.1457, simple_loss=0.2308, pruned_loss=0.03036, over 4681.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02956, over 973162.80 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:50:57,796 INFO [train.py:715] (3/8) Epoch 16, batch 16700, loss[loss=0.1229, simple_loss=0.1947, pruned_loss=0.02562, over 4801.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02975, over 972699.58 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 17:51:35,938 INFO [train.py:715] (3/8) Epoch 16, batch 16750, loss[loss=0.1294, simple_loss=0.1986, pruned_loss=0.03007, over 4870.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02941, over 973070.35 frames.], batch size: 32, lr: 1.38e-04
+2022-05-08 17:52:13,453 INFO [train.py:715] (3/8) Epoch 16, batch 16800, loss[loss=0.1252, simple_loss=0.2021, pruned_loss=0.02417, over 4870.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02959, over 972398.72 frames.], batch size: 22, lr: 1.38e-04
+2022-05-08 17:52:51,539 INFO [train.py:715] (3/8) Epoch 16, batch 16850, loss[loss=0.1317, simple_loss=0.1902, pruned_loss=0.03656, over 4839.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.02949, over 971841.56 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 17:53:30,002 INFO [train.py:715] (3/8) Epoch 16, batch 16900, loss[loss=0.1498, simple_loss=0.2185, pruned_loss=0.04052, over 4864.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02948, over 972335.62 frames.], batch size: 32, lr: 1.38e-04
+2022-05-08 17:54:07,594 INFO [train.py:715] (3/8) Epoch 16, batch 16950, loss[loss=0.1542, simple_loss=0.2295, pruned_loss=0.03945, over 4978.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02903, over 971840.67 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 17:54:45,479 INFO [train.py:715] (3/8) Epoch 16, batch 17000, loss[loss=0.1453, simple_loss=0.2214, pruned_loss=0.03458, over 4834.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02901, over 971584.37 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:55:23,675 INFO [train.py:715] (3/8) Epoch 16, batch 17050, loss[loss=0.1262, simple_loss=0.1826, pruned_loss=0.03492, over 4693.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2056, pruned_loss=0.02895, over 971038.00 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:56:02,258 INFO [train.py:715] (3/8) Epoch 16, batch 17100, loss[loss=0.1503, simple_loss=0.2218, pruned_loss=0.03939, over 4971.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2062, pruned_loss=0.02962, over 970320.78 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:56:39,334 INFO [train.py:715] (3/8) Epoch 16, batch 17150, loss[loss=0.1475, simple_loss=0.2198, pruned_loss=0.0376, over 4928.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03037, over 971142.54 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 17:57:17,465 INFO [train.py:715] (3/8) Epoch 16, batch 17200, loss[loss=0.1288, simple_loss=0.1938, pruned_loss=0.03197, over 4770.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03069, over 971299.19 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 17:57:56,362 INFO [train.py:715] (3/8) Epoch 16, batch 17250, loss[loss=0.1423, simple_loss=0.2196, pruned_loss=0.03249, over 4815.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03045, over 971890.46 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 17:58:33,738 INFO [train.py:715] (3/8) Epoch 16, batch 17300, loss[loss=0.1312, simple_loss=0.2135, pruned_loss=0.02449, over 4954.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.0301, over 971385.08 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 17:59:11,267 INFO [train.py:715] (3/8) Epoch 16, batch 17350, loss[loss=0.1569, simple_loss=0.2392, pruned_loss=0.03728, over 4933.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03029, over 970903.38 frames.], batch size: 23, lr: 1.38e-04
+2022-05-08 17:59:49,078 INFO [train.py:715] (3/8) Epoch 16, batch 17400, loss[loss=0.164, simple_loss=0.2258, pruned_loss=0.05111, over 4871.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03019, over 971793.79 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 18:00:27,745 INFO [train.py:715] (3/8) Epoch 16, batch 17450, loss[loss=0.1369, simple_loss=0.2133, pruned_loss=0.03027, over 4813.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03064, over 971856.77 frames.], batch size: 27, lr: 1.38e-04
+2022-05-08 18:01:04,507 INFO [train.py:715] (3/8) Epoch 16, batch 17500, loss[loss=0.1189, simple_loss=0.1866, pruned_loss=0.02557, over 4971.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2075, pruned_loss=0.03017, over 972042.08 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 18:01:42,656 INFO [train.py:715] (3/8) Epoch 16, batch 17550, loss[loss=0.1093, simple_loss=0.1843, pruned_loss=0.01716, over 4842.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02987, over 972075.94 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 18:02:21,341 INFO [train.py:715] (3/8) Epoch 16, batch 17600, loss[loss=0.137, simple_loss=0.2157, pruned_loss=0.0291, over 4652.00 frames.], tot_loss[loss=0.134, simple_loss=0.2074, pruned_loss=0.03028, over 972065.91 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 18:02:58,694 INFO [train.py:715] (3/8) Epoch 16, batch 17650, loss[loss=0.1198, simple_loss=0.1895, pruned_loss=0.02501, over 4956.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2068, pruned_loss=0.02969, over 972688.87 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 18:03:36,638 INFO [train.py:715] (3/8) Epoch 16, batch 17700, loss[loss=0.139, simple_loss=0.2129, pruned_loss=0.03255, over 4825.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.0302, over 972850.46 frames.], batch size: 27, lr: 1.38e-04
+2022-05-08 18:04:15,005 INFO [train.py:715] (3/8) Epoch 16, batch 17750, loss[loss=0.1138, simple_loss=0.1939, pruned_loss=0.0169, over 4828.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2079, pruned_loss=0.03079, over 973472.07 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 18:04:53,069 INFO [train.py:715] (3/8) Epoch 16, batch 17800, loss[loss=0.1525, simple_loss=0.2227, pruned_loss=0.04115, over 4971.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03086, over 973912.81 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 18:05:30,280 INFO [train.py:715] (3/8) Epoch 16, batch 17850, loss[loss=0.1293, simple_loss=0.2031, pruned_loss=0.02773, over 4856.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03085, over 973793.68 frames.], batch size: 32, lr: 1.38e-04
+2022-05-08 18:06:08,450 INFO [train.py:715] (3/8) Epoch 16, batch 17900, loss[loss=0.1456, simple_loss=0.2204, pruned_loss=0.03546, over 4745.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03076, over 973604.02 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 18:06:46,892 INFO [train.py:715] (3/8) Epoch 16, batch 17950, loss[loss=0.1118, simple_loss=0.1883, pruned_loss=0.01764, over 4858.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03028, over 973030.03 frames.], batch size: 20, lr: 1.38e-04
+2022-05-08 18:07:24,274 INFO [train.py:715] (3/8) Epoch 16, batch 18000, loss[loss=0.1331, simple_loss=0.1976, pruned_loss=0.03428, over 4809.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03003, over 973271.05 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 18:07:24,275 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 18:07:33,811 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.105, simple_loss=0.1884, pruned_loss=0.01082, over 914524.00 frames.
+2022-05-08 18:08:11,769 INFO [train.py:715] (3/8) Epoch 16, batch 18050, loss[loss=0.1259, simple_loss=0.1994, pruned_loss=0.02617, over 4896.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02973, over 973599.01 frames.], batch size: 17, lr: 1.38e-04
+2022-05-08 18:08:50,180 INFO [train.py:715] (3/8) Epoch 16, batch 18100, loss[loss=0.1484, simple_loss=0.2193, pruned_loss=0.03879, over 4775.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02943, over 973212.63 frames.], batch size: 18, lr: 1.38e-04
+2022-05-08 18:09:28,826 INFO [train.py:715] (3/8) Epoch 16, batch 18150, loss[loss=0.1199, simple_loss=0.1951, pruned_loss=0.02233, over 4918.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02962, over 973546.16 frames.], batch size: 18, lr: 1.38e-04
+2022-05-08 18:10:07,474 INFO [train.py:715] (3/8) Epoch 16, batch 18200, loss[loss=0.1309, simple_loss=0.2082, pruned_loss=0.02679, over 4821.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.03015, over 974072.26 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 18:10:45,085 INFO [train.py:715] (3/8) Epoch 16, batch 18250, loss[loss=0.1267, simple_loss=0.179, pruned_loss=0.03714, over 4802.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03036, over 973276.63 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 18:11:23,847 INFO [train.py:715] (3/8) Epoch 16, batch 18300, loss[loss=0.1116, simple_loss=0.1807, pruned_loss=0.02119, over 4974.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03017, over 973304.65 frames.], batch size: 28, lr: 1.38e-04
+2022-05-08 18:12:02,949 INFO [train.py:715] (3/8) Epoch 16, batch 18350, loss[loss=0.1216, simple_loss=0.1955, pruned_loss=0.02385, over 4683.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03024, over 973821.42 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 18:12:40,720 INFO [train.py:715] (3/8) Epoch 16, batch 18400, loss[loss=0.1187, simple_loss=0.1914, pruned_loss=0.02295, over 4851.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03062, over 973996.14 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 18:13:19,244 INFO [train.py:715] (3/8) Epoch 16, batch 18450, loss[loss=0.1203, simple_loss=0.1932, pruned_loss=0.02373, over 4767.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2079, pruned_loss=0.03039, over 973223.55 frames.], batch size: 19, lr: 1.38e-04
+2022-05-08 18:13:57,851 INFO [train.py:715] (3/8) Epoch 16, batch 18500, loss[loss=0.1462, simple_loss=0.2142, pruned_loss=0.03914, over 4855.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.0301, over 972607.74 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 18:14:36,373 INFO [train.py:715] (3/8) Epoch 16, batch 18550, loss[loss=0.1157, simple_loss=0.191, pruned_loss=0.02023, over 4759.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02979, over 973016.91 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 18:15:13,856 INFO [train.py:715] (3/8) Epoch 16, batch 18600, loss[loss=0.1255, simple_loss=0.1983, pruned_loss=0.02639, over 4969.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02954, over 972098.81 frames.], batch size: 25, lr: 1.38e-04
+2022-05-08 18:15:52,139 INFO [train.py:715] (3/8) Epoch 16, batch 18650, loss[loss=0.1282, simple_loss=0.2035, pruned_loss=0.02641, over 4974.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02958, over 971879.90 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 18:16:30,643 INFO [train.py:715] (3/8) Epoch 16, batch 18700, loss[loss=0.13, simple_loss=0.2113, pruned_loss=0.0244, over 4636.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.0296, over 971020.93 frames.], batch size: 13, lr: 1.38e-04
+2022-05-08 18:17:08,142 INFO [train.py:715] (3/8) Epoch 16, batch 18750, loss[loss=0.1566, simple_loss=0.2166, pruned_loss=0.04832, over 4870.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.0299, over 971026.91 frames.], batch size: 32, lr: 1.38e-04
+2022-05-08 18:17:45,513 INFO [train.py:715] (3/8) Epoch 16, batch 18800, loss[loss=0.128, simple_loss=0.204, pruned_loss=0.02603, over 4876.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02947, over 971390.14 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 18:18:23,823 INFO [train.py:715] (3/8) Epoch 16, batch 18850, loss[loss=0.1251, simple_loss=0.1871, pruned_loss=0.03152, over 4801.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02979, over 970625.05 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 18:19:02,093 INFO [train.py:715] (3/8) Epoch 16, batch 18900, loss[loss=0.1334, simple_loss=0.1962, pruned_loss=0.03531, over 4793.00 frames.], tot_loss[loss=0.1333, simple_loss=0.207, pruned_loss=0.02982, over 971087.25 frames.], batch size: 24, lr: 1.38e-04
+2022-05-08 18:19:39,523 INFO [train.py:715] (3/8) Epoch 16, batch 18950, loss[loss=0.112, simple_loss=0.1778, pruned_loss=0.02313, over 4931.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03001, over 971447.90 frames.], batch size: 23, lr: 1.38e-04
+2022-05-08 18:20:17,360 INFO [train.py:715] (3/8) Epoch 16, batch 19000, loss[loss=0.1856, simple_loss=0.2452, pruned_loss=0.06301, over 4984.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03003, over 971772.75 frames.], batch size: 31, lr: 1.38e-04
+2022-05-08 18:20:55,967 INFO [train.py:715] (3/8) Epoch 16, batch 19050, loss[loss=0.1319, simple_loss=0.216, pruned_loss=0.02389, over 4942.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02921, over 972045.57 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 18:21:36,430 INFO [train.py:715] (3/8) Epoch 16, batch 19100, loss[loss=0.1152, simple_loss=0.1841, pruned_loss=0.02309, over 4798.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02886, over 971810.15 frames.], batch size: 12, lr: 1.38e-04
+2022-05-08 18:22:14,091 INFO [train.py:715] (3/8) Epoch 16, batch 19150, loss[loss=0.1336, simple_loss=0.2112, pruned_loss=0.02805, over 4986.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02922, over 972149.15 frames.], batch size: 28, lr: 1.38e-04
+2022-05-08 18:22:52,371 INFO [train.py:715] (3/8) Epoch 16, batch 19200, loss[loss=0.1375, simple_loss=0.2023, pruned_loss=0.03638, over 4786.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02903, over 972944.69 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 18:23:31,021 INFO [train.py:715] (3/8) Epoch 16, batch 19250, loss[loss=0.1113, simple_loss=0.1777, pruned_loss=0.02245, over 4708.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.0298, over 971633.90 frames.], batch size: 12, lr: 1.38e-04
+2022-05-08 18:24:08,556 INFO [train.py:715] (3/8) Epoch 16, batch 19300, loss[loss=0.1434, simple_loss=0.2077, pruned_loss=0.03959, over 4842.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02941, over 971848.01 frames.], batch size: 30, lr: 1.38e-04
+2022-05-08 18:24:46,583 INFO [train.py:715] (3/8) Epoch 16, batch 19350, loss[loss=0.1551, simple_loss=0.2232, pruned_loss=0.0435, over 4871.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02941, over 971514.73 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 18:25:25,228 INFO [train.py:715] (3/8) Epoch 16, batch 19400, loss[loss=0.1246, simple_loss=0.2017, pruned_loss=0.02372, over 4897.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2084, pruned_loss=0.02942, over 971464.62 frames.], batch size: 19, lr: 1.38e-04
+2022-05-08 18:26:03,261 INFO [train.py:715] (3/8) Epoch 16, batch 19450, loss[loss=0.1177, simple_loss=0.1945, pruned_loss=0.02045, over 4915.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02947, over 971851.72 frames.], batch size: 19, lr: 1.38e-04
+2022-05-08 18:26:40,801 INFO [train.py:715] (3/8) Epoch 16, batch 19500, loss[loss=0.1242, simple_loss=0.1927, pruned_loss=0.02786, over 4794.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03008, over 972460.43 frames.], batch size: 18, lr: 1.38e-04
+2022-05-08 18:27:18,960 INFO [train.py:715] (3/8) Epoch 16, batch 19550, loss[loss=0.1486, simple_loss=0.2236, pruned_loss=0.03682, over 4855.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02984, over 971968.75 frames.], batch size: 15, lr: 1.38e-04
+2022-05-08 18:27:57,193 INFO [train.py:715] (3/8) Epoch 16, batch 19600, loss[loss=0.1399, simple_loss=0.2264, pruned_loss=0.02676, over 4878.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02988, over 971274.02 frames.], batch size: 16, lr: 1.38e-04
+2022-05-08 18:28:34,602 INFO [train.py:715] (3/8) Epoch 16, batch 19650, loss[loss=0.1645, simple_loss=0.2318, pruned_loss=0.04861, over 4818.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.0298, over 971873.87 frames.], batch size: 26, lr: 1.38e-04
+2022-05-08 18:29:12,877 INFO [train.py:715] (3/8) Epoch 16, batch 19700, loss[loss=0.1418, simple_loss=0.2139, pruned_loss=0.03481, over 4914.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02969, over 972254.49 frames.], batch size: 39, lr: 1.38e-04
+2022-05-08 18:29:51,095 INFO [train.py:715] (3/8) Epoch 16, batch 19750, loss[loss=0.1219, simple_loss=0.2043, pruned_loss=0.01975, over 4940.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02949, over 972382.49 frames.], batch size: 29, lr: 1.38e-04
+2022-05-08 18:30:28,918 INFO [train.py:715] (3/8) Epoch 16, batch 19800, loss[loss=0.146, simple_loss=0.219, pruned_loss=0.03647, over 4965.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02966, over 972724.84 frames.], batch size: 24, lr: 1.38e-04
+2022-05-08 18:31:06,637 INFO [train.py:715] (3/8) Epoch 16, batch 19850, loss[loss=0.1404, simple_loss=0.2149, pruned_loss=0.03295, over 4945.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02989, over 972733.48 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 18:31:44,942 INFO [train.py:715] (3/8) Epoch 16, batch 19900, loss[loss=0.1562, simple_loss=0.2385, pruned_loss=0.03699, over 4792.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02952, over 971994.26 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 18:32:22,973 INFO [train.py:715] (3/8) Epoch 16, batch 19950, loss[loss=0.1212, simple_loss=0.1969, pruned_loss=0.02276, over 4990.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2083, pruned_loss=0.02912, over 972233.70 frames.], batch size: 14, lr: 1.38e-04
+2022-05-08 18:33:00,615 INFO [train.py:715] (3/8) Epoch 16, batch 20000, loss[loss=0.1423, simple_loss=0.2105, pruned_loss=0.0371, over 4987.00 frames.], tot_loss[loss=0.1333, simple_loss=0.208, pruned_loss=0.02927, over 972671.53 frames.], batch size: 31, lr: 1.38e-04
+2022-05-08 18:33:38,892 INFO [train.py:715] (3/8) Epoch 16, batch 20050, loss[loss=0.1138, simple_loss=0.1895, pruned_loss=0.01908, over 4922.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2079, pruned_loss=0.02893, over 972787.05 frames.], batch size: 23, lr: 1.38e-04
+2022-05-08 18:34:17,307 INFO [train.py:715] (3/8) Epoch 16, batch 20100, loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.02828, over 4965.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.0289, over 972860.00 frames.], batch size: 35, lr: 1.38e-04
+2022-05-08 18:34:54,669 INFO [train.py:715] (3/8) Epoch 16, batch 20150, loss[loss=0.1611, simple_loss=0.2411, pruned_loss=0.04048, over 4892.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02952, over 972878.70 frames.], batch size: 19, lr: 1.38e-04
+2022-05-08 18:35:32,577 INFO [train.py:715] (3/8) Epoch 16, batch 20200, loss[loss=0.1385, simple_loss=0.2102, pruned_loss=0.03336, over 4947.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02958, over 972617.40 frames.], batch size: 21, lr: 1.38e-04
+2022-05-08 18:36:10,897 INFO [train.py:715] (3/8) Epoch 16, batch 20250, loss[loss=0.1243, simple_loss=0.1971, pruned_loss=0.02574, over 4944.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02922, over 972735.35 frames.], batch size: 39, lr: 1.38e-04
+2022-05-08 18:36:49,192 INFO [train.py:715] (3/8) Epoch 16, batch 20300, loss[loss=0.1171, simple_loss=0.1908, pruned_loss=0.02168, over 4901.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.0293, over 973103.28 frames.], batch size: 17, lr: 1.38e-04
+2022-05-08 18:37:27,017 INFO [train.py:715] (3/8) Epoch 16, batch 20350, loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02987, over 4864.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02961, over 972806.86 frames.], batch size: 20, lr: 1.37e-04
+2022-05-08 18:38:05,176 INFO [train.py:715] (3/8) Epoch 16, batch 20400, loss[loss=0.1458, simple_loss=0.2242, pruned_loss=0.0337, over 4836.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.0297, over 973286.85 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 18:38:43,166 INFO [train.py:715] (3/8) Epoch 16, batch 20450, loss[loss=0.09869, simple_loss=0.1662, pruned_loss=0.01558, over 4736.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.0291, over 972676.01 frames.], batch size: 12, lr: 1.37e-04
+2022-05-08 18:39:21,073 INFO [train.py:715] (3/8) Epoch 16, batch 20500, loss[loss=0.1287, simple_loss=0.198, pruned_loss=0.02973, over 4688.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02931, over 972772.38 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 18:39:58,717 INFO [train.py:715] (3/8) Epoch 16, batch 20550, loss[loss=0.1205, simple_loss=0.1935, pruned_loss=0.02379, over 4821.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.0297, over 973117.97 frames.], batch size: 12, lr: 1.37e-04
+2022-05-08 18:40:37,508 INFO [train.py:715] (3/8) Epoch 16, batch 20600, loss[loss=0.1166, simple_loss=0.2048, pruned_loss=0.01421, over 4807.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.0298, over 973126.58 frames.], batch size: 25, lr: 1.37e-04
+2022-05-08 18:41:15,475 INFO [train.py:715] (3/8) Epoch 16, batch 20650, loss[loss=0.1617, simple_loss=0.2275, pruned_loss=0.04796, over 4846.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02981, over 973526.95 frames.], batch size: 32, lr: 1.37e-04
+2022-05-08 18:41:52,935 INFO [train.py:715] (3/8) Epoch 16, batch 20700, loss[loss=0.1446, simple_loss=0.2216, pruned_loss=0.03378, over 4773.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02986, over 973250.67 frames.], batch size: 14, lr: 1.37e-04
+2022-05-08 18:42:31,441 INFO [train.py:715] (3/8) Epoch 16, batch 20750, loss[loss=0.1424, simple_loss=0.2014, pruned_loss=0.04167, over 4850.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03009, over 973497.47 frames.], batch size: 30, lr: 1.37e-04
+2022-05-08 18:43:09,457 INFO [train.py:715] (3/8) Epoch 16, batch 20800, loss[loss=0.1125, simple_loss=0.1895, pruned_loss=0.01775, over 4867.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.02972, over 972961.10 frames.], batch size: 20, lr: 1.37e-04
+2022-05-08 18:43:47,990 INFO [train.py:715] (3/8) Epoch 16, batch 20850, loss[loss=0.1779, simple_loss=0.2449, pruned_loss=0.05546, over 4984.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.0301, over 972176.11 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 18:44:25,954 INFO [train.py:715] (3/8) Epoch 16, batch 20900, loss[loss=0.1324, simple_loss=0.208, pruned_loss=0.02841, over 4977.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02944, over 972620.29 frames.], batch size: 24, lr: 1.37e-04
+2022-05-08 18:45:05,225 INFO [train.py:715] (3/8) Epoch 16, batch 20950, loss[loss=0.1093, simple_loss=0.1842, pruned_loss=0.01718, over 4923.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2056, pruned_loss=0.02878, over 972320.98 frames.], batch size: 23, lr: 1.37e-04
+2022-05-08 18:45:43,432 INFO [train.py:715] (3/8) Epoch 16, batch 21000, loss[loss=0.1343, simple_loss=0.2106, pruned_loss=0.02899, over 4911.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02906, over 972555.02 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 18:45:43,432 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 18:45:53,027 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.1047, simple_loss=0.1882, pruned_loss=0.0106, over 914524.00 frames.
+2022-05-08 18:46:31,914 INFO [train.py:715] (3/8) Epoch 16, batch 21050, loss[loss=0.1105, simple_loss=0.1868, pruned_loss=0.01708, over 4821.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02905, over 973223.03 frames.], batch size: 13, lr: 1.37e-04
+2022-05-08 18:47:10,475 INFO [train.py:715] (3/8) Epoch 16, batch 21100, loss[loss=0.1474, simple_loss=0.2296, pruned_loss=0.03261, over 4957.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02928, over 972632.51 frames.], batch size: 39, lr: 1.37e-04
+2022-05-08 18:47:49,072 INFO [train.py:715] (3/8) Epoch 16, batch 21150, loss[loss=0.1172, simple_loss=0.1889, pruned_loss=0.02277, over 4850.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02925, over 972158.56 frames.], batch size: 30, lr: 1.37e-04
+2022-05-08 18:48:27,792 INFO [train.py:715] (3/8) Epoch 16, batch 21200, loss[loss=0.1099, simple_loss=0.1806, pruned_loss=0.01959, over 4835.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.0292, over 971418.60 frames.], batch size: 13, lr: 1.37e-04
+2022-05-08 18:49:06,849 INFO [train.py:715] (3/8) Epoch 16, batch 21250, loss[loss=0.1479, simple_loss=0.2265, pruned_loss=0.0346, over 4987.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.0289, over 972739.23 frames.], batch size: 28, lr: 1.37e-04
+2022-05-08 18:49:44,921 INFO [train.py:715] (3/8) Epoch 16, batch 21300, loss[loss=0.1303, simple_loss=0.2024, pruned_loss=0.02909, over 4772.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2062, pruned_loss=0.02947, over 971626.37 frames.], batch size: 18, lr: 1.37e-04
+2022-05-08 18:50:23,523 INFO [train.py:715] (3/8) Epoch 16, batch 21350, loss[loss=0.1224, simple_loss=0.1963, pruned_loss=0.02424, over 4909.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02956, over 972515.24 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 18:51:01,536 INFO [train.py:715] (3/8) Epoch 16, batch 21400, loss[loss=0.1266, simple_loss=0.2089, pruned_loss=0.0222, over 4793.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02911, over 972116.75 frames.], batch size: 24, lr: 1.37e-04
+2022-05-08 18:51:39,055 INFO [train.py:715] (3/8) Epoch 16, batch 21450, loss[loss=0.129, simple_loss=0.2061, pruned_loss=0.0259, over 4769.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02948, over 972677.04 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 18:52:17,450 INFO [train.py:715] (3/8) Epoch 16, batch 21500, loss[loss=0.1373, simple_loss=0.206, pruned_loss=0.03426, over 4912.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02942, over 972314.65 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 18:52:55,413 INFO [train.py:715] (3/8) Epoch 16, batch 21550, loss[loss=0.1226, simple_loss=0.1934, pruned_loss=0.02593, over 4838.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02893, over 972448.47 frames.], batch size: 30, lr: 1.37e-04
+2022-05-08 18:53:33,005 INFO [train.py:715] (3/8) Epoch 16, batch 21600, loss[loss=0.1191, simple_loss=0.1941, pruned_loss=0.02199, over 4787.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02903, over 971624.40 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 18:54:11,338 INFO [train.py:715] (3/8) Epoch 16, batch 21650, loss[loss=0.1392, simple_loss=0.2116, pruned_loss=0.03338, over 4840.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02876, over 971253.57 frames.], batch size: 30, lr: 1.37e-04
+2022-05-08 18:54:49,123 INFO [train.py:715] (3/8) Epoch 16, batch 21700, loss[loss=0.1425, simple_loss=0.2058, pruned_loss=0.03963, over 4840.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02875, over 970871.79 frames.], batch size: 30, lr: 1.37e-04
+2022-05-08 18:55:27,323 INFO [train.py:715] (3/8) Epoch 16, batch 21750, loss[loss=0.1144, simple_loss=0.1912, pruned_loss=0.01882, over 4968.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02883, over 971370.89 frames.], batch size: 35, lr: 1.37e-04
+2022-05-08 18:56:04,818 INFO [train.py:715] (3/8) Epoch 16, batch 21800, loss[loss=0.1317, simple_loss=0.2045, pruned_loss=0.02943, over 4850.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02934, over 971897.55 frames.], batch size: 13, lr: 1.37e-04
+2022-05-08 18:56:42,921 INFO [train.py:715] (3/8) Epoch 16, batch 21850, loss[loss=0.1219, simple_loss=0.2067, pruned_loss=0.01852, over 4982.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.0296, over 971134.65 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 18:57:20,563 INFO [train.py:715] (3/8) Epoch 16, batch 21900, loss[loss=0.1076, simple_loss=0.1854, pruned_loss=0.01488, over 4971.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02985, over 972238.39 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 18:57:57,980 INFO [train.py:715] (3/8) Epoch 16, batch 21950, loss[loss=0.1305, simple_loss=0.2162, pruned_loss=0.0224, over 4818.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02975, over 971496.51 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 18:58:36,386 INFO [train.py:715] (3/8) Epoch 16, batch 22000, loss[loss=0.1204, simple_loss=0.2112, pruned_loss=0.01477, over 4778.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02969, over 971523.87 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 18:59:13,999 INFO [train.py:715] (3/8) Epoch 16, batch 22050, loss[loss=0.1434, simple_loss=0.2219, pruned_loss=0.03244, over 4853.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03045, over 970771.13 frames.], batch size: 20, lr: 1.37e-04
+2022-05-08 18:59:52,236 INFO [train.py:715] (3/8) Epoch 16, batch 22100, loss[loss=0.1212, simple_loss=0.192, pruned_loss=0.02518, over 4823.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03011, over 971217.10 frames.], batch size: 26, lr: 1.37e-04
+2022-05-08 19:00:29,953 INFO [train.py:715] (3/8) Epoch 16, batch 22150, loss[loss=0.1188, simple_loss=0.1893, pruned_loss=0.02415, over 4818.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.0297, over 971508.46 frames.], batch size: 26, lr: 1.37e-04
+2022-05-08 19:01:08,388 INFO [train.py:715] (3/8) Epoch 16, batch 22200, loss[loss=0.1246, simple_loss=0.2022, pruned_loss=0.02354, over 4980.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02915, over 971545.75 frames.], batch size: 28, lr: 1.37e-04
+2022-05-08 19:01:46,151 INFO [train.py:715] (3/8) Epoch 16, batch 22250, loss[loss=0.1421, simple_loss=0.2154, pruned_loss=0.03441, over 4982.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02942, over 971202.94 frames.], batch size: 33, lr: 1.37e-04
+2022-05-08 19:02:24,238 INFO [train.py:715] (3/8) Epoch 16, batch 22300, loss[loss=0.13, simple_loss=0.1991, pruned_loss=0.03041, over 4853.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02946, over 970899.66 frames.], batch size: 20, lr: 1.37e-04
+2022-05-08 19:03:02,796 INFO [train.py:715] (3/8) Epoch 16, batch 22350, loss[loss=0.1324, simple_loss=0.2149, pruned_loss=0.0249, over 4800.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02945, over 971371.18 frames.], batch size: 21, lr: 1.37e-04
+2022-05-08 19:03:40,845 INFO [train.py:715] (3/8) Epoch 16, batch 22400, loss[loss=0.1676, simple_loss=0.2398, pruned_loss=0.04768, over 4894.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02933, over 971400.55 frames.], batch size: 22, lr: 1.37e-04
+2022-05-08 19:04:19,199 INFO [train.py:715] (3/8) Epoch 16, batch 22450, loss[loss=0.1429, simple_loss=0.212, pruned_loss=0.03685, over 4881.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.0295, over 971435.35 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 19:04:57,329 INFO [train.py:715] (3/8) Epoch 16, batch 22500, loss[loss=0.1283, simple_loss=0.2094, pruned_loss=0.02357, over 4882.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02931, over 972093.75 frames.], batch size: 22, lr: 1.37e-04
+2022-05-08 19:05:35,516 INFO [train.py:715] (3/8) Epoch 16, batch 22550, loss[loss=0.1242, simple_loss=0.1931, pruned_loss=0.02766, over 4922.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02921, over 972417.50 frames.], batch size: 18, lr: 1.37e-04
+2022-05-08 19:06:13,254 INFO [train.py:715] (3/8) Epoch 16, batch 22600, loss[loss=0.127, simple_loss=0.2088, pruned_loss=0.02258, over 4923.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02921, over 972419.44 frames.], batch size: 23, lr: 1.37e-04
+2022-05-08 19:06:50,942 INFO [train.py:715] (3/8) Epoch 16, batch 22650, loss[loss=0.1202, simple_loss=0.1976, pruned_loss=0.02135, over 4919.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02938, over 973217.78 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 19:07:29,635 INFO [train.py:715] (3/8) Epoch 16, batch 22700, loss[loss=0.1145, simple_loss=0.1877, pruned_loss=0.02068, over 4745.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02928, over 972751.93 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 19:08:07,679 INFO [train.py:715] (3/8) Epoch 16, batch 22750, loss[loss=0.1082, simple_loss=0.1856, pruned_loss=0.01539, over 4815.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02936, over 973374.44 frames.], batch size: 25, lr: 1.37e-04
+2022-05-08 19:08:45,791 INFO [train.py:715] (3/8) Epoch 16, batch 22800, loss[loss=0.1272, simple_loss=0.1982, pruned_loss=0.02808, over 4823.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02928, over 972655.01 frames.], batch size: 26, lr: 1.37e-04
+2022-05-08 19:09:23,700 INFO [train.py:715] (3/8) Epoch 16, batch 22850, loss[loss=0.1404, simple_loss=0.2179, pruned_loss=0.0315, over 4918.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02954, over 973873.80 frames.], batch size: 18, lr: 1.37e-04
+2022-05-08 19:10:01,847 INFO [train.py:715] (3/8) Epoch 16, batch 22900, loss[loss=0.1294, simple_loss=0.2168, pruned_loss=0.02098, over 4795.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02971, over 973362.93 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 19:10:39,883 INFO [train.py:715] (3/8) Epoch 16, batch 22950, loss[loss=0.1259, simple_loss=0.2037, pruned_loss=0.02401, over 4841.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02955, over 972857.99 frames.], batch size: 13, lr: 1.37e-04
+2022-05-08 19:11:17,830 INFO [train.py:715] (3/8) Epoch 16, batch 23000, loss[loss=0.1348, simple_loss=0.2017, pruned_loss=0.03395, over 4807.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02934, over 972692.71 frames.], batch size: 14, lr: 1.37e-04
+2022-05-08 19:11:56,368 INFO [train.py:715] (3/8) Epoch 16, batch 23050, loss[loss=0.118, simple_loss=0.2056, pruned_loss=0.01519, over 4838.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02949, over 972787.60 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:12:34,516 INFO [train.py:715] (3/8) Epoch 16, batch 23100, loss[loss=0.1379, simple_loss=0.2087, pruned_loss=0.03352, over 4961.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02944, over 972422.97 frames.], batch size: 24, lr: 1.37e-04
+2022-05-08 19:13:12,453 INFO [train.py:715] (3/8) Epoch 16, batch 23150, loss[loss=0.1319, simple_loss=0.213, pruned_loss=0.02541, over 4921.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02943, over 972472.67 frames.], batch size: 29, lr: 1.37e-04
+2022-05-08 19:13:50,197 INFO [train.py:715] (3/8) Epoch 16, batch 23200, loss[loss=0.1355, simple_loss=0.2122, pruned_loss=0.02943, over 4806.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02934, over 972520.06 frames.], batch size: 25, lr: 1.37e-04
+2022-05-08 19:14:28,511 INFO [train.py:715] (3/8) Epoch 16, batch 23250, loss[loss=0.1082, simple_loss=0.1864, pruned_loss=0.01505, over 4983.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02927, over 972187.92 frames.], batch size: 28, lr: 1.37e-04
+2022-05-08 19:15:06,179 INFO [train.py:715] (3/8) Epoch 16, batch 23300, loss[loss=0.1348, simple_loss=0.2079, pruned_loss=0.03091, over 4947.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02935, over 972494.49 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:15:44,249 INFO [train.py:715] (3/8) Epoch 16, batch 23350, loss[loss=0.139, simple_loss=0.2125, pruned_loss=0.03276, over 4791.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02933, over 972580.32 frames.], batch size: 21, lr: 1.37e-04
+2022-05-08 19:16:21,897 INFO [train.py:715] (3/8) Epoch 16, batch 23400, loss[loss=0.1333, simple_loss=0.2126, pruned_loss=0.02699, over 4942.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2085, pruned_loss=0.02942, over 973292.23 frames.], batch size: 23, lr: 1.37e-04
+2022-05-08 19:16:59,786 INFO [train.py:715] (3/8) Epoch 16, batch 23450, loss[loss=0.1378, simple_loss=0.1988, pruned_loss=0.03844, over 4978.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2082, pruned_loss=0.02931, over 972717.28 frames.], batch size: 31, lr: 1.37e-04
+2022-05-08 19:17:37,691 INFO [train.py:715] (3/8) Epoch 16, batch 23500, loss[loss=0.1474, simple_loss=0.2158, pruned_loss=0.03948, over 4924.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02933, over 972441.42 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 19:18:15,674 INFO [train.py:715] (3/8) Epoch 16, batch 23550, loss[loss=0.1296, simple_loss=0.2121, pruned_loss=0.02351, over 4975.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02956, over 972543.63 frames.], batch size: 25, lr: 1.37e-04
+2022-05-08 19:18:54,224 INFO [train.py:715] (3/8) Epoch 16, batch 23600, loss[loss=0.1457, simple_loss=0.2197, pruned_loss=0.03587, over 4827.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02949, over 972533.88 frames.], batch size: 13, lr: 1.37e-04
+2022-05-08 19:19:31,590 INFO [train.py:715] (3/8) Epoch 16, batch 23650, loss[loss=0.1391, simple_loss=0.213, pruned_loss=0.03264, over 4895.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02955, over 972379.01 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 19:20:09,502 INFO [train.py:715] (3/8) Epoch 16, batch 23700, loss[loss=0.1063, simple_loss=0.1817, pruned_loss=0.01546, over 4974.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02933, over 972478.68 frames.], batch size: 28, lr: 1.37e-04
+2022-05-08 19:20:47,877 INFO [train.py:715] (3/8) Epoch 16, batch 23750, loss[loss=0.1315, simple_loss=0.202, pruned_loss=0.03051, over 4745.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02942, over 971845.09 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 19:21:25,951 INFO [train.py:715] (3/8) Epoch 16, batch 23800, loss[loss=0.1154, simple_loss=0.1926, pruned_loss=0.0191, over 4825.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02906, over 972160.69 frames.], batch size: 26, lr: 1.37e-04
+2022-05-08 19:22:04,208 INFO [train.py:715] (3/8) Epoch 16, batch 23850, loss[loss=0.1316, simple_loss=0.2006, pruned_loss=0.03132, over 4962.00 frames.], tot_loss[loss=0.1333, simple_loss=0.207, pruned_loss=0.02979, over 972363.50 frames.], batch size: 35, lr: 1.37e-04
+2022-05-08 19:22:42,143 INFO [train.py:715] (3/8) Epoch 16, batch 23900, loss[loss=0.1138, simple_loss=0.1839, pruned_loss=0.02189, over 4966.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.0295, over 972174.31 frames.], batch size: 24, lr: 1.37e-04
+2022-05-08 19:23:20,420 INFO [train.py:715] (3/8) Epoch 16, batch 23950, loss[loss=0.1505, simple_loss=0.2213, pruned_loss=0.03986, over 4901.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02934, over 972078.22 frames.], batch size: 39, lr: 1.37e-04
+2022-05-08 19:23:57,820 INFO [train.py:715] (3/8) Epoch 16, batch 24000, loss[loss=0.1597, simple_loss=0.2288, pruned_loss=0.04526, over 4964.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02905, over 972420.19 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:23:57,820 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 19:24:07,634 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.1049, simple_loss=0.1883, pruned_loss=0.01074, over 914524.00 frames.
+2022-05-08 19:24:46,405 INFO [train.py:715] (3/8) Epoch 16, batch 24050, loss[loss=0.1515, simple_loss=0.2261, pruned_loss=0.03842, over 4681.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02927, over 972522.60 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:25:24,730 INFO [train.py:715] (3/8) Epoch 16, batch 24100, loss[loss=0.1237, simple_loss=0.1852, pruned_loss=0.03109, over 4734.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02952, over 973018.46 frames.], batch size: 12, lr: 1.37e-04
+2022-05-08 19:26:03,115 INFO [train.py:715] (3/8) Epoch 16, batch 24150, loss[loss=0.1345, simple_loss=0.212, pruned_loss=0.02843, over 4878.00 frames.], tot_loss[loss=0.1333, simple_loss=0.208, pruned_loss=0.02932, over 973666.65 frames.], batch size: 22, lr: 1.37e-04
+2022-05-08 19:26:40,871 INFO [train.py:715] (3/8) Epoch 16, batch 24200, loss[loss=0.167, simple_loss=0.2266, pruned_loss=0.05367, over 4686.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02923, over 973208.58 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:27:19,230 INFO [train.py:715] (3/8) Epoch 16, batch 24250, loss[loss=0.1488, simple_loss=0.2231, pruned_loss=0.03726, over 4968.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02966, over 973374.05 frames.], batch size: 39, lr: 1.37e-04
+2022-05-08 19:27:57,174 INFO [train.py:715] (3/8) Epoch 16, batch 24300, loss[loss=0.1244, simple_loss=0.2047, pruned_loss=0.02205, over 4824.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02924, over 973955.32 frames.], batch size: 26, lr: 1.37e-04
+2022-05-08 19:28:35,673 INFO [train.py:715] (3/8) Epoch 16, batch 24350, loss[loss=0.1663, simple_loss=0.2458, pruned_loss=0.04343, over 4954.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02942, over 973401.86 frames.], batch size: 35, lr: 1.37e-04
+2022-05-08 19:29:13,225 INFO [train.py:715] (3/8) Epoch 16, batch 24400, loss[loss=0.1246, simple_loss=0.1994, pruned_loss=0.02487, over 4984.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02917, over 973292.96 frames.], batch size: 31, lr: 1.37e-04
+2022-05-08 19:29:50,783 INFO [train.py:715] (3/8) Epoch 16, batch 24450, loss[loss=0.1424, simple_loss=0.2206, pruned_loss=0.03207, over 4882.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02974, over 972874.13 frames.], batch size: 22, lr: 1.37e-04
+2022-05-08 19:30:28,697 INFO [train.py:715] (3/8) Epoch 16, batch 24500, loss[loss=0.1353, simple_loss=0.2108, pruned_loss=0.02991, over 4899.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02978, over 972767.26 frames.], batch size: 39, lr: 1.37e-04
+2022-05-08 19:31:06,548 INFO [train.py:715] (3/8) Epoch 16, batch 24550, loss[loss=0.139, simple_loss=0.2076, pruned_loss=0.03525, over 4841.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03003, over 972301.22 frames.], batch size: 30, lr: 1.37e-04
+2022-05-08 19:31:43,994 INFO [train.py:715] (3/8) Epoch 16, batch 24600, loss[loss=0.126, simple_loss=0.2027, pruned_loss=0.02461, over 4959.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03, over 972445.62 frames.], batch size: 39, lr: 1.37e-04
+2022-05-08 19:32:21,347 INFO [train.py:715] (3/8) Epoch 16, batch 24650, loss[loss=0.1243, simple_loss=0.1987, pruned_loss=0.02497, over 4912.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03047, over 971876.88 frames.], batch size: 23, lr: 1.37e-04
+2022-05-08 19:32:59,496 INFO [train.py:715] (3/8) Epoch 16, batch 24700, loss[loss=0.1269, simple_loss=0.2145, pruned_loss=0.01971, over 4987.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03052, over 971850.08 frames.], batch size: 28, lr: 1.37e-04
+2022-05-08 19:33:37,069 INFO [train.py:715] (3/8) Epoch 16, batch 24750, loss[loss=0.1229, simple_loss=0.1928, pruned_loss=0.02653, over 4831.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03067, over 971563.42 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:34:14,868 INFO [train.py:715] (3/8) Epoch 16, batch 24800, loss[loss=0.1111, simple_loss=0.1757, pruned_loss=0.02322, over 4734.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.0308, over 971612.15 frames.], batch size: 12, lr: 1.37e-04
+2022-05-08 19:34:52,613 INFO [train.py:715] (3/8) Epoch 16, batch 24850, loss[loss=0.1207, simple_loss=0.1979, pruned_loss=0.02178, over 4945.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03073, over 971885.21 frames.], batch size: 21, lr: 1.37e-04
+2022-05-08 19:35:30,370 INFO [train.py:715] (3/8) Epoch 16, batch 24900, loss[loss=0.1367, simple_loss=0.2153, pruned_loss=0.02903, over 4880.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.031, over 971535.45 frames.], batch size: 22, lr: 1.37e-04
+2022-05-08 19:36:08,068 INFO [train.py:715] (3/8) Epoch 16, batch 24950, loss[loss=0.1254, simple_loss=0.2046, pruned_loss=0.02307, over 4759.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03086, over 971406.51 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 19:36:45,487 INFO [train.py:715] (3/8) Epoch 16, batch 25000, loss[loss=0.1205, simple_loss=0.2024, pruned_loss=0.01933, over 4964.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03053, over 971048.78 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:37:23,738 INFO [train.py:715] (3/8) Epoch 16, batch 25050, loss[loss=0.1208, simple_loss=0.1904, pruned_loss=0.02563, over 4928.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2071, pruned_loss=0.02998, over 971415.30 frames.], batch size: 18, lr: 1.37e-04
+2022-05-08 19:38:02,499 INFO [train.py:715] (3/8) Epoch 16, batch 25100, loss[loss=0.1189, simple_loss=0.1971, pruned_loss=0.02039, over 4809.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2071, pruned_loss=0.02993, over 971758.99 frames.], batch size: 13, lr: 1.37e-04
+2022-05-08 19:38:40,223 INFO [train.py:715] (3/8) Epoch 16, batch 25150, loss[loss=0.1249, simple_loss=0.2007, pruned_loss=0.02459, over 4858.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02995, over 972209.54 frames.], batch size: 20, lr: 1.37e-04
+2022-05-08 19:39:18,061 INFO [train.py:715] (3/8) Epoch 16, batch 25200, loss[loss=0.1336, simple_loss=0.2056, pruned_loss=0.03085, over 4755.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2075, pruned_loss=0.03014, over 973130.91 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 19:39:56,035 INFO [train.py:715] (3/8) Epoch 16, batch 25250, loss[loss=0.138, simple_loss=0.208, pruned_loss=0.03397, over 4877.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.02998, over 972501.01 frames.], batch size: 32, lr: 1.37e-04
+2022-05-08 19:40:33,646 INFO [train.py:715] (3/8) Epoch 16, batch 25300, loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03084, over 4985.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.03001, over 973359.74 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:41:10,911 INFO [train.py:715] (3/8) Epoch 16, batch 25350, loss[loss=0.1252, simple_loss=0.1998, pruned_loss=0.02531, over 4991.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03015, over 972197.97 frames.], batch size: 28, lr: 1.37e-04
+2022-05-08 19:41:49,016 INFO [train.py:715] (3/8) Epoch 16, batch 25400, loss[loss=0.1213, simple_loss=0.1956, pruned_loss=0.02344, over 4952.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02998, over 971810.03 frames.], batch size: 29, lr: 1.37e-04
+2022-05-08 19:42:27,350 INFO [train.py:715] (3/8) Epoch 16, batch 25450, loss[loss=0.138, simple_loss=0.2131, pruned_loss=0.03142, over 4777.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03038, over 971993.50 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 19:43:04,844 INFO [train.py:715] (3/8) Epoch 16, batch 25500, loss[loss=0.1489, simple_loss=0.2116, pruned_loss=0.04303, over 4860.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03018, over 972540.94 frames.], batch size: 32, lr: 1.37e-04
+2022-05-08 19:43:42,834 INFO [train.py:715] (3/8) Epoch 16, batch 25550, loss[loss=0.1424, simple_loss=0.2144, pruned_loss=0.03519, over 4737.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02957, over 972138.07 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 19:44:21,345 INFO [train.py:715] (3/8) Epoch 16, batch 25600, loss[loss=0.1308, simple_loss=0.2034, pruned_loss=0.02911, over 4905.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02961, over 971825.43 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 19:45:00,129 INFO [train.py:715] (3/8) Epoch 16, batch 25650, loss[loss=0.1135, simple_loss=0.1844, pruned_loss=0.02133, over 4982.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02958, over 971713.10 frames.], batch size: 14, lr: 1.37e-04
+2022-05-08 19:45:38,355 INFO [train.py:715] (3/8) Epoch 16, batch 25700, loss[loss=0.1219, simple_loss=0.2052, pruned_loss=0.01926, over 4864.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02911, over 971940.38 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 19:46:16,989 INFO [train.py:715] (3/8) Epoch 16, batch 25750, loss[loss=0.1329, simple_loss=0.2103, pruned_loss=0.02771, over 4880.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02898, over 972660.56 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 19:46:55,626 INFO [train.py:715] (3/8) Epoch 16, batch 25800, loss[loss=0.1704, simple_loss=0.2466, pruned_loss=0.04703, over 4777.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02941, over 972503.74 frames.], batch size: 18, lr: 1.37e-04
+2022-05-08 19:47:34,231 INFO [train.py:715] (3/8) Epoch 16, batch 25850, loss[loss=0.1448, simple_loss=0.2229, pruned_loss=0.03334, over 4982.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02967, over 972474.79 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:48:13,052 INFO [train.py:715] (3/8) Epoch 16, batch 25900, loss[loss=0.1076, simple_loss=0.1819, pruned_loss=0.01668, over 4928.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02976, over 972081.25 frames.], batch size: 29, lr: 1.37e-04
+2022-05-08 19:48:52,472 INFO [train.py:715] (3/8) Epoch 16, batch 25950, loss[loss=0.1093, simple_loss=0.1801, pruned_loss=0.01924, over 4699.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02954, over 972000.81 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:49:32,208 INFO [train.py:715] (3/8) Epoch 16, batch 26000, loss[loss=0.1425, simple_loss=0.2179, pruned_loss=0.03353, over 4950.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2081, pruned_loss=0.02924, over 972013.15 frames.], batch size: 35, lr: 1.37e-04
+2022-05-08 19:50:11,558 INFO [train.py:715] (3/8) Epoch 16, batch 26050, loss[loss=0.1307, simple_loss=0.2084, pruned_loss=0.02648, over 4990.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2085, pruned_loss=0.02954, over 972529.39 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:50:50,796 INFO [train.py:715] (3/8) Epoch 16, batch 26100, loss[loss=0.1167, simple_loss=0.1991, pruned_loss=0.01717, over 4902.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.0292, over 972171.30 frames.], batch size: 18, lr: 1.37e-04
+2022-05-08 19:51:30,062 INFO [train.py:715] (3/8) Epoch 16, batch 26150, loss[loss=0.1119, simple_loss=0.1923, pruned_loss=0.01576, over 4708.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.0296, over 972436.16 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 19:52:08,702 INFO [train.py:715] (3/8) Epoch 16, batch 26200, loss[loss=0.1464, simple_loss=0.221, pruned_loss=0.03593, over 4793.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02995, over 972096.67 frames.], batch size: 21, lr: 1.37e-04
+2022-05-08 19:52:48,176 INFO [train.py:715] (3/8) Epoch 16, batch 26250, loss[loss=0.1132, simple_loss=0.1859, pruned_loss=0.02031, over 4955.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03035, over 971491.99 frames.], batch size: 14, lr: 1.37e-04
+2022-05-08 19:53:27,331 INFO [train.py:715] (3/8) Epoch 16, batch 26300, loss[loss=0.1171, simple_loss=0.1951, pruned_loss=0.01957, over 4819.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02996, over 972048.96 frames.], batch size: 13, lr: 1.37e-04
+2022-05-08 19:54:06,987 INFO [train.py:715] (3/8) Epoch 16, batch 26350, loss[loss=0.1166, simple_loss=0.1933, pruned_loss=0.0199, over 4952.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02993, over 971820.71 frames.], batch size: 21, lr: 1.37e-04
+2022-05-08 19:54:46,283 INFO [train.py:715] (3/8) Epoch 16, batch 26400, loss[loss=0.1166, simple_loss=0.1946, pruned_loss=0.01927, over 4754.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03014, over 972424.59 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 19:55:26,170 INFO [train.py:715] (3/8) Epoch 16, batch 26450, loss[loss=0.1037, simple_loss=0.1823, pruned_loss=0.01259, over 4812.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02968, over 972292.45 frames.], batch size: 27, lr: 1.37e-04
+2022-05-08 19:56:05,125 INFO [train.py:715] (3/8) Epoch 16, batch 26500, loss[loss=0.1322, simple_loss=0.2112, pruned_loss=0.02659, over 4976.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02953, over 972770.98 frames.], batch size: 35, lr: 1.37e-04
+2022-05-08 19:56:44,040 INFO [train.py:715] (3/8) Epoch 16, batch 26550, loss[loss=0.1786, simple_loss=0.2555, pruned_loss=0.0508, over 4958.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.0296, over 972932.80 frames.], batch size: 21, lr: 1.37e-04
+2022-05-08 19:57:23,102 INFO [train.py:715] (3/8) Epoch 16, batch 26600, loss[loss=0.1292, simple_loss=0.2111, pruned_loss=0.0237, over 4793.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02895, over 972619.28 frames.], batch size: 14, lr: 1.37e-04
+2022-05-08 19:58:02,096 INFO [train.py:715] (3/8) Epoch 16, batch 26650, loss[loss=0.1557, simple_loss=0.2224, pruned_loss=0.04446, over 4775.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02883, over 972876.44 frames.], batch size: 18, lr: 1.37e-04
+2022-05-08 19:58:41,427 INFO [train.py:715] (3/8) Epoch 16, batch 26700, loss[loss=0.1102, simple_loss=0.191, pruned_loss=0.01468, over 4782.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.0289, over 972987.87 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 19:59:20,661 INFO [train.py:715] (3/8) Epoch 16, batch 26750, loss[loss=0.1156, simple_loss=0.1874, pruned_loss=0.02195, over 4926.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2065, pruned_loss=0.02957, over 972529.81 frames.], batch size: 29, lr: 1.37e-04
+2022-05-08 20:00:00,476 INFO [train.py:715] (3/8) Epoch 16, batch 26800, loss[loss=0.1304, simple_loss=0.2166, pruned_loss=0.02206, over 4991.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02944, over 972918.35 frames.], batch size: 26, lr: 1.37e-04
+2022-05-08 20:00:39,349 INFO [train.py:715] (3/8) Epoch 16, batch 26850, loss[loss=0.1342, simple_loss=0.2059, pruned_loss=0.03123, over 4861.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02939, over 972065.82 frames.], batch size: 32, lr: 1.37e-04
+2022-05-08 20:01:18,829 INFO [train.py:715] (3/8) Epoch 16, batch 26900, loss[loss=0.1497, simple_loss=0.2147, pruned_loss=0.04233, over 4779.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2065, pruned_loss=0.02963, over 971327.55 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 20:01:58,326 INFO [train.py:715] (3/8) Epoch 16, batch 26950, loss[loss=0.1506, simple_loss=0.2111, pruned_loss=0.04504, over 4988.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03019, over 970990.61 frames.], batch size: 14, lr: 1.37e-04
+2022-05-08 20:02:37,505 INFO [train.py:715] (3/8) Epoch 16, batch 27000, loss[loss=0.1189, simple_loss=0.1952, pruned_loss=0.02134, over 4748.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02988, over 971824.15 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 20:02:37,505 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 20:02:47,198 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.1048, simple_loss=0.1883, pruned_loss=0.01067, over 914524.00 frames.
+2022-05-08 20:03:26,299 INFO [train.py:715] (3/8) Epoch 16, batch 27050, loss[loss=0.1217, simple_loss=0.1997, pruned_loss=0.02182, over 4815.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02954, over 971401.34 frames.], batch size: 21, lr: 1.37e-04
+2022-05-08 20:04:08,234 INFO [train.py:715] (3/8) Epoch 16, batch 27100, loss[loss=0.1262, simple_loss=0.2155, pruned_loss=0.01847, over 4940.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02955, over 971248.55 frames.], batch size: 23, lr: 1.37e-04
+2022-05-08 20:04:47,171 INFO [train.py:715] (3/8) Epoch 16, batch 27150, loss[loss=0.1696, simple_loss=0.2447, pruned_loss=0.04723, over 4956.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02927, over 972064.34 frames.], batch size: 39, lr: 1.37e-04
+2022-05-08 20:05:26,606 INFO [train.py:715] (3/8) Epoch 16, batch 27200, loss[loss=0.1477, simple_loss=0.2222, pruned_loss=0.03658, over 4907.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02913, over 971592.22 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 20:06:05,792 INFO [train.py:715] (3/8) Epoch 16, batch 27250, loss[loss=0.128, simple_loss=0.2122, pruned_loss=0.02193, over 4969.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02926, over 972341.88 frames.], batch size: 24, lr: 1.37e-04
+2022-05-08 20:06:45,175 INFO [train.py:715] (3/8) Epoch 16, batch 27300, loss[loss=0.136, simple_loss=0.2144, pruned_loss=0.02882, over 4921.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02976, over 972902.41 frames.], batch size: 18, lr: 1.37e-04
+2022-05-08 20:07:24,246 INFO [train.py:715] (3/8) Epoch 16, batch 27350, loss[loss=0.132, simple_loss=0.2024, pruned_loss=0.03083, over 4761.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02991, over 972641.24 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 20:08:03,613 INFO [train.py:715] (3/8) Epoch 16, batch 27400, loss[loss=0.1173, simple_loss=0.1924, pruned_loss=0.02108, over 4872.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02949, over 973027.70 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 20:08:42,904 INFO [train.py:715] (3/8) Epoch 16, batch 27450, loss[loss=0.1347, simple_loss=0.205, pruned_loss=0.03214, over 4977.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02954, over 973235.88 frames.], batch size: 31, lr: 1.37e-04
+2022-05-08 20:09:21,910 INFO [train.py:715] (3/8) Epoch 16, batch 27500, loss[loss=0.1363, simple_loss=0.2122, pruned_loss=0.03025, over 4802.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02956, over 972831.71 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 20:10:01,268 INFO [train.py:715] (3/8) Epoch 16, batch 27550, loss[loss=0.1348, simple_loss=0.2095, pruned_loss=0.02999, over 4912.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03006, over 973286.82 frames.], batch size: 17, lr: 1.37e-04
+2022-05-08 20:10:41,120 INFO [train.py:715] (3/8) Epoch 16, batch 27600, loss[loss=0.133, simple_loss=0.2053, pruned_loss=0.03039, over 4852.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02939, over 972840.88 frames.], batch size: 32, lr: 1.37e-04
+2022-05-08 20:11:20,148 INFO [train.py:715] (3/8) Epoch 16, batch 27650, loss[loss=0.1494, simple_loss=0.225, pruned_loss=0.03692, over 4925.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.0295, over 973095.66 frames.], batch size: 39, lr: 1.37e-04
+2022-05-08 20:11:59,676 INFO [train.py:715] (3/8) Epoch 16, batch 27700, loss[loss=0.1213, simple_loss=0.1952, pruned_loss=0.02372, over 4879.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02949, over 972290.68 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 20:12:38,977 INFO [train.py:715] (3/8) Epoch 16, batch 27750, loss[loss=0.143, simple_loss=0.2199, pruned_loss=0.03311, over 4865.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2087, pruned_loss=0.02989, over 973037.26 frames.], batch size: 20, lr: 1.37e-04
+2022-05-08 20:13:18,195 INFO [train.py:715] (3/8) Epoch 16, batch 27800, loss[loss=0.1434, simple_loss=0.2248, pruned_loss=0.03098, over 4852.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2088, pruned_loss=0.0299, over 973491.91 frames.], batch size: 20, lr: 1.37e-04
+2022-05-08 20:13:57,554 INFO [train.py:715] (3/8) Epoch 16, batch 27850, loss[loss=0.1352, simple_loss=0.2098, pruned_loss=0.03034, over 4858.00 frames.], tot_loss[loss=0.1344, simple_loss=0.209, pruned_loss=0.02996, over 973605.49 frames.], batch size: 20, lr: 1.37e-04
+2022-05-08 20:14:36,983 INFO [train.py:715] (3/8) Epoch 16, batch 27900, loss[loss=0.1427, simple_loss=0.2218, pruned_loss=0.03178, over 4739.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2085, pruned_loss=0.02947, over 973073.18 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 20:15:16,666 INFO [train.py:715] (3/8) Epoch 16, batch 27950, loss[loss=0.1127, simple_loss=0.1859, pruned_loss=0.01976, over 4804.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02969, over 972365.60 frames.], batch size: 12, lr: 1.37e-04
+2022-05-08 20:15:55,974 INFO [train.py:715] (3/8) Epoch 16, batch 28000, loss[loss=0.1213, simple_loss=0.1962, pruned_loss=0.02317, over 4862.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02939, over 972694.31 frames.], batch size: 32, lr: 1.37e-04
+2022-05-08 20:16:35,540 INFO [train.py:715] (3/8) Epoch 16, batch 28050, loss[loss=0.1418, simple_loss=0.2221, pruned_loss=0.03075, over 4883.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02965, over 973326.07 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 20:17:15,209 INFO [train.py:715] (3/8) Epoch 16, batch 28100, loss[loss=0.1318, simple_loss=0.1938, pruned_loss=0.03497, over 4974.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03013, over 974054.25 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 20:17:54,190 INFO [train.py:715] (3/8) Epoch 16, batch 28150, loss[loss=0.1206, simple_loss=0.1997, pruned_loss=0.0208, over 4741.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02985, over 972961.56 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 20:18:33,944 INFO [train.py:715] (3/8) Epoch 16, batch 28200, loss[loss=0.1172, simple_loss=0.1864, pruned_loss=0.02403, over 4809.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02997, over 972313.77 frames.], batch size: 13, lr: 1.37e-04
+2022-05-08 20:19:13,274 INFO [train.py:715] (3/8) Epoch 16, batch 28250, loss[loss=0.162, simple_loss=0.2351, pruned_loss=0.04444, over 4973.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02986, over 973030.08 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 20:19:51,892 INFO [train.py:715] (3/8) Epoch 16, batch 28300, loss[loss=0.1186, simple_loss=0.1888, pruned_loss=0.02423, over 4691.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03009, over 972794.89 frames.], batch size: 15, lr: 1.37e-04
+2022-05-08 20:20:31,607 INFO [train.py:715] (3/8) Epoch 16, batch 28350, loss[loss=0.1231, simple_loss=0.1961, pruned_loss=0.02502, over 4872.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02975, over 972626.55 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 20:21:11,562 INFO [train.py:715] (3/8) Epoch 16, batch 28400, loss[loss=0.1317, simple_loss=0.208, pruned_loss=0.02771, over 4927.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02977, over 972822.23 frames.], batch size: 23, lr: 1.37e-04
+2022-05-08 20:21:51,019 INFO [train.py:715] (3/8) Epoch 16, batch 28450, loss[loss=0.131, simple_loss=0.208, pruned_loss=0.02704, over 4879.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02952, over 972683.71 frames.], batch size: 16, lr: 1.37e-04
+2022-05-08 20:22:29,722 INFO [train.py:715] (3/8) Epoch 16, batch 28500, loss[loss=0.1357, simple_loss=0.2148, pruned_loss=0.02829, over 4756.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02959, over 971673.70 frames.], batch size: 19, lr: 1.37e-04
+2022-05-08 20:23:09,888 INFO [train.py:715] (3/8) Epoch 16, batch 28550, loss[loss=0.1156, simple_loss=0.1894, pruned_loss=0.02089, over 4943.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02988, over 972211.49 frames.], batch size: 39, lr: 1.37e-04
+2022-05-08 20:23:49,361 INFO [train.py:715] (3/8) Epoch 16, batch 28600, loss[loss=0.1198, simple_loss=0.1949, pruned_loss=0.02232, over 4938.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02996, over 972084.13 frames.], batch size: 39, lr: 1.37e-04
+2022-05-08 20:24:28,946 INFO [train.py:715] (3/8) Epoch 16, batch 28650, loss[loss=0.1196, simple_loss=0.1977, pruned_loss=0.02072, over 4962.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02984, over 972190.58 frames.], batch size: 35, lr: 1.37e-04
+2022-05-08 20:25:08,099 INFO [train.py:715] (3/8) Epoch 16, batch 28700, loss[loss=0.1308, simple_loss=0.202, pruned_loss=0.02979, over 4975.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02958, over 973338.71 frames.], batch size: 24, lr: 1.37e-04
+2022-05-08 20:25:47,667 INFO [train.py:715] (3/8) Epoch 16, batch 28750, loss[loss=0.1229, simple_loss=0.1998, pruned_loss=0.02301, over 4865.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02901, over 973785.90 frames.], batch size: 20, lr: 1.37e-04
+2022-05-08 20:26:27,377 INFO [train.py:715] (3/8) Epoch 16, batch 28800, loss[loss=0.1209, simple_loss=0.1974, pruned_loss=0.02222, over 4880.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02876, over 973374.13 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 20:27:06,536 INFO [train.py:715] (3/8) Epoch 16, batch 28850, loss[loss=0.1212, simple_loss=0.1996, pruned_loss=0.02143, over 4980.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02905, over 972546.54 frames.], batch size: 25, lr: 1.36e-04
+2022-05-08 20:27:46,356 INFO [train.py:715] (3/8) Epoch 16, batch 28900, loss[loss=0.1182, simple_loss=0.1908, pruned_loss=0.02281, over 4992.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.02896, over 971667.39 frames.], batch size: 14, lr: 1.36e-04
+2022-05-08 20:28:25,934 INFO [train.py:715] (3/8) Epoch 16, batch 28950, loss[loss=0.1322, simple_loss=0.2082, pruned_loss=0.02806, over 4741.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02941, over 971881.31 frames.], batch size: 16, lr: 1.36e-04
+2022-05-08 20:29:05,870 INFO [train.py:715] (3/8) Epoch 16, batch 29000, loss[loss=0.1252, simple_loss=0.1939, pruned_loss=0.02822, over 4902.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02955, over 973773.22 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 20:29:45,339 INFO [train.py:715] (3/8) Epoch 16, batch 29050, loss[loss=0.1104, simple_loss=0.192, pruned_loss=0.01437, over 4977.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02971, over 973557.09 frames.], batch size: 25, lr: 1.36e-04
+2022-05-08 20:30:25,182 INFO [train.py:715] (3/8) Epoch 16, batch 29100, loss[loss=0.1513, simple_loss=0.2275, pruned_loss=0.03751, over 4977.00 frames.], tot_loss[loss=0.134, simple_loss=0.2088, pruned_loss=0.02966, over 973366.47 frames.], batch size: 31, lr: 1.36e-04
+2022-05-08 20:31:06,237 INFO [train.py:715] (3/8) Epoch 16, batch 29150, loss[loss=0.1385, simple_loss=0.2239, pruned_loss=0.02655, over 4817.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2085, pruned_loss=0.02957, over 973607.99 frames.], batch size: 27, lr: 1.36e-04
+2022-05-08 20:31:46,268 INFO [train.py:715] (3/8) Epoch 16, batch 29200, loss[loss=0.1564, simple_loss=0.234, pruned_loss=0.03935, over 4799.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02915, over 974009.20 frames.], batch size: 17, lr: 1.36e-04
+2022-05-08 20:32:27,450 INFO [train.py:715] (3/8) Epoch 16, batch 29250, loss[loss=0.131, simple_loss=0.2075, pruned_loss=0.02721, over 4897.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02937, over 972656.19 frames.], batch size: 17, lr: 1.36e-04
+2022-05-08 20:33:08,452 INFO [train.py:715] (3/8) Epoch 16, batch 29300, loss[loss=0.1315, simple_loss=0.2096, pruned_loss=0.0267, over 4911.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02954, over 972379.42 frames.], batch size: 39, lr: 1.36e-04
+2022-05-08 20:33:49,841 INFO [train.py:715] (3/8) Epoch 16, batch 29350, loss[loss=0.1334, simple_loss=0.2137, pruned_loss=0.02652, over 4946.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02957, over 971591.71 frames.], batch size: 29, lr: 1.36e-04
+2022-05-08 20:34:30,966 INFO [train.py:715] (3/8) Epoch 16, batch 29400, loss[loss=0.1269, simple_loss=0.2038, pruned_loss=0.02501, over 4979.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02935, over 971585.02 frames.], batch size: 39, lr: 1.36e-04
+2022-05-08 20:35:12,718 INFO [train.py:715] (3/8) Epoch 16, batch 29450, loss[loss=0.1147, simple_loss=0.1929, pruned_loss=0.01821, over 4970.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02948, over 971118.64 frames.], batch size: 25, lr: 1.36e-04
+2022-05-08 20:35:54,216 INFO [train.py:715] (3/8) Epoch 16, batch 29500, loss[loss=0.1297, simple_loss=0.2019, pruned_loss=0.02868, over 4754.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2064, pruned_loss=0.02959, over 970940.22 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 20:36:36,036 INFO [train.py:715] (3/8) Epoch 16, batch 29550, loss[loss=0.1471, simple_loss=0.2094, pruned_loss=0.04241, over 4869.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02984, over 971159.31 frames.], batch size: 39, lr: 1.36e-04
+2022-05-08 20:37:17,259 INFO [train.py:715] (3/8) Epoch 16, batch 29600, loss[loss=0.1018, simple_loss=0.1726, pruned_loss=0.01547, over 4988.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02936, over 972285.74 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 20:37:59,051 INFO [train.py:715] (3/8) Epoch 16, batch 29650, loss[loss=0.1131, simple_loss=0.1946, pruned_loss=0.01583, over 4819.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.0293, over 972345.85 frames.], batch size: 26, lr: 1.36e-04
+2022-05-08 20:38:40,542 INFO [train.py:715] (3/8) Epoch 16, batch 29700, loss[loss=0.1261, simple_loss=0.2053, pruned_loss=0.02342, over 4811.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2062, pruned_loss=0.02933, over 972822.54 frames.], batch size: 27, lr: 1.36e-04
+2022-05-08 20:39:21,789 INFO [train.py:715] (3/8) Epoch 16, batch 29750, loss[loss=0.1298, simple_loss=0.2044, pruned_loss=0.02757, over 4848.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02951, over 973161.42 frames.], batch size: 20, lr: 1.36e-04
+2022-05-08 20:40:02,896 INFO [train.py:715] (3/8) Epoch 16, batch 29800, loss[loss=0.1581, simple_loss=0.2403, pruned_loss=0.03799, over 4795.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02972, over 972808.73 frames.], batch size: 14, lr: 1.36e-04
+2022-05-08 20:40:44,776 INFO [train.py:715] (3/8) Epoch 16, batch 29850, loss[loss=0.13, simple_loss=0.1975, pruned_loss=0.03121, over 4838.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02931, over 972371.48 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 20:41:26,318 INFO [train.py:715] (3/8) Epoch 16, batch 29900, loss[loss=0.1286, simple_loss=0.2072, pruned_loss=0.02498, over 4968.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02948, over 973347.33 frames.], batch size: 28, lr: 1.36e-04
+2022-05-08 20:42:07,628 INFO [train.py:715] (3/8) Epoch 16, batch 29950, loss[loss=0.135, simple_loss=0.2094, pruned_loss=0.03026, over 4967.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02998, over 973378.31 frames.], batch size: 39, lr: 1.36e-04
+2022-05-08 20:42:50,230 INFO [train.py:715] (3/8) Epoch 16, batch 30000, loss[loss=0.1446, simple_loss=0.2185, pruned_loss=0.03542, over 4792.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02967, over 973035.16 frames.], batch size: 14, lr: 1.36e-04
+2022-05-08 20:42:50,231 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 20:43:01,792 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.1047, simple_loss=0.1883, pruned_loss=0.01058, over 914524.00 frames.
+2022-05-08 20:43:44,304 INFO [train.py:715] (3/8) Epoch 16, batch 30050, loss[loss=0.1427, simple_loss=0.2222, pruned_loss=0.03157, over 4876.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02932, over 973474.97 frames.], batch size: 16, lr: 1.36e-04
+2022-05-08 20:44:26,133 INFO [train.py:715] (3/8) Epoch 16, batch 30100, loss[loss=0.1263, simple_loss=0.2082, pruned_loss=0.02225, over 4789.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02937, over 972608.05 frames.], batch size: 18, lr: 1.36e-04
+2022-05-08 20:45:06,926 INFO [train.py:715] (3/8) Epoch 16, batch 30150, loss[loss=0.1081, simple_loss=0.1822, pruned_loss=0.01695, over 4781.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03013, over 972243.48 frames.], batch size: 14, lr: 1.36e-04
+2022-05-08 20:45:48,621 INFO [train.py:715] (3/8) Epoch 16, batch 30200, loss[loss=0.1208, simple_loss=0.1963, pruned_loss=0.02267, over 4930.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.0305, over 972890.97 frames.], batch size: 21, lr: 1.36e-04
+2022-05-08 20:46:29,885 INFO [train.py:715] (3/8) Epoch 16, batch 30250, loss[loss=0.1356, simple_loss=0.2039, pruned_loss=0.03362, over 4842.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.0307, over 972328.84 frames.], batch size: 30, lr: 1.36e-04
+2022-05-08 20:47:09,988 INFO [train.py:715] (3/8) Epoch 16, batch 30300, loss[loss=0.1301, simple_loss=0.2115, pruned_loss=0.02438, over 4818.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03095, over 972772.23 frames.], batch size: 25, lr: 1.36e-04
+2022-05-08 20:47:50,184 INFO [train.py:715] (3/8) Epoch 16, batch 30350, loss[loss=0.1181, simple_loss=0.195, pruned_loss=0.02059, over 4802.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2079, pruned_loss=0.03057, over 972605.78 frames.], batch size: 14, lr: 1.36e-04
+2022-05-08 20:48:30,611 INFO [train.py:715] (3/8) Epoch 16, batch 30400, loss[loss=0.1847, simple_loss=0.2504, pruned_loss=0.0595, over 4980.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2072, pruned_loss=0.03021, over 971934.27 frames.], batch size: 35, lr: 1.36e-04
+2022-05-08 20:49:10,257 INFO [train.py:715] (3/8) Epoch 16, batch 30450, loss[loss=0.1471, simple_loss=0.2198, pruned_loss=0.03719, over 4878.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2072, pruned_loss=0.03008, over 971988.31 frames.], batch size: 20, lr: 1.36e-04
+2022-05-08 20:49:49,413 INFO [train.py:715] (3/8) Epoch 16, batch 30500, loss[loss=0.1174, simple_loss=0.1938, pruned_loss=0.02044, over 4950.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2079, pruned_loss=0.03049, over 971478.43 frames.], batch size: 21, lr: 1.36e-04
+2022-05-08 20:50:29,338 INFO [train.py:715] (3/8) Epoch 16, batch 30550, loss[loss=0.1477, simple_loss=0.2227, pruned_loss=0.03633, over 4957.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.0302, over 971859.71 frames.], batch size: 21, lr: 1.36e-04
+2022-05-08 20:51:09,801 INFO [train.py:715] (3/8) Epoch 16, batch 30600, loss[loss=0.1349, simple_loss=0.1993, pruned_loss=0.03527, over 4839.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2069, pruned_loss=0.03018, over 971507.01 frames.], batch size: 30, lr: 1.36e-04
+2022-05-08 20:51:49,047 INFO [train.py:715] (3/8) Epoch 16, batch 30650, loss[loss=0.1087, simple_loss=0.1806, pruned_loss=0.01844, over 4850.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2072, pruned_loss=0.03006, over 971913.53 frames.], batch size: 32, lr: 1.36e-04
+2022-05-08 20:52:28,801 INFO [train.py:715] (3/8) Epoch 16, batch 30700, loss[loss=0.1082, simple_loss=0.192, pruned_loss=0.01217, over 4860.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02962, over 971499.39 frames.], batch size: 20, lr: 1.36e-04
+2022-05-08 20:53:10,032 INFO [train.py:715] (3/8) Epoch 16, batch 30750, loss[loss=0.1172, simple_loss=0.1907, pruned_loss=0.0219, over 4836.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02942, over 970710.09 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 20:53:49,622 INFO [train.py:715] (3/8) Epoch 16, batch 30800, loss[loss=0.139, simple_loss=0.2262, pruned_loss=0.02594, over 4825.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02982, over 971126.85 frames.], batch size: 26, lr: 1.36e-04
+2022-05-08 20:54:28,448 INFO [train.py:715] (3/8) Epoch 16, batch 30850, loss[loss=0.1381, simple_loss=0.2083, pruned_loss=0.03395, over 4841.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02966, over 971065.53 frames.], batch size: 30, lr: 1.36e-04
+2022-05-08 20:55:08,444 INFO [train.py:715] (3/8) Epoch 16, batch 30900, loss[loss=0.177, simple_loss=0.2566, pruned_loss=0.04868, over 4955.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02987, over 971888.12 frames.], batch size: 24, lr: 1.36e-04
+2022-05-08 20:55:47,879 INFO [train.py:715] (3/8) Epoch 16, batch 30950, loss[loss=0.1301, simple_loss=0.2053, pruned_loss=0.02746, over 4866.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02982, over 972406.50 frames.], batch size: 20, lr: 1.36e-04
+2022-05-08 20:56:26,904 INFO [train.py:715] (3/8) Epoch 16, batch 31000, loss[loss=0.138, simple_loss=0.2082, pruned_loss=0.03386, over 4741.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.0304, over 971488.62 frames.], batch size: 16, lr: 1.36e-04
+2022-05-08 20:57:06,083 INFO [train.py:715] (3/8) Epoch 16, batch 31050, loss[loss=0.1128, simple_loss=0.1983, pruned_loss=0.01368, over 4922.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03024, over 972341.66 frames.], batch size: 29, lr: 1.36e-04
+2022-05-08 20:57:45,840 INFO [train.py:715] (3/8) Epoch 16, batch 31100, loss[loss=0.1412, simple_loss=0.2204, pruned_loss=0.03105, over 4833.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03019, over 972179.22 frames.], batch size: 13, lr: 1.36e-04
+2022-05-08 20:58:25,690 INFO [train.py:715] (3/8) Epoch 16, batch 31150, loss[loss=0.2141, simple_loss=0.2887, pruned_loss=0.06981, over 4868.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03046, over 971729.30 frames.], batch size: 38, lr: 1.36e-04
+2022-05-08 20:59:04,402 INFO [train.py:715] (3/8) Epoch 16, batch 31200, loss[loss=0.1424, simple_loss=0.2011, pruned_loss=0.04182, over 4826.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03018, over 970927.82 frames.], batch size: 26, lr: 1.36e-04
+2022-05-08 20:59:44,075 INFO [train.py:715] (3/8) Epoch 16, batch 31250, loss[loss=0.1416, simple_loss=0.2045, pruned_loss=0.03933, over 4859.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.02999, over 971186.41 frames.], batch size: 32, lr: 1.36e-04
+2022-05-08 21:00:23,615 INFO [train.py:715] (3/8) Epoch 16, batch 31300, loss[loss=0.1225, simple_loss=0.202, pruned_loss=0.02149, over 4819.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02937, over 971514.23 frames.], batch size: 13, lr: 1.36e-04
+2022-05-08 21:01:03,210 INFO [train.py:715] (3/8) Epoch 16, batch 31350, loss[loss=0.1368, simple_loss=0.2085, pruned_loss=0.03252, over 4765.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02917, over 971490.90 frames.], batch size: 12, lr: 1.36e-04
+2022-05-08 21:01:42,657 INFO [train.py:715] (3/8) Epoch 16, batch 31400, loss[loss=0.1291, simple_loss=0.202, pruned_loss=0.02812, over 4799.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02927, over 972171.23 frames.], batch size: 24, lr: 1.36e-04
+2022-05-08 21:02:22,720 INFO [train.py:715] (3/8) Epoch 16, batch 31450, loss[loss=0.1236, simple_loss=0.1956, pruned_loss=0.02576, over 4901.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02942, over 972617.06 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 21:03:01,698 INFO [train.py:715] (3/8) Epoch 16, batch 31500, loss[loss=0.1243, simple_loss=0.207, pruned_loss=0.0208, over 4705.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02945, over 972611.64 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 21:03:40,542 INFO [train.py:715] (3/8) Epoch 16, batch 31550, loss[loss=0.151, simple_loss=0.2178, pruned_loss=0.04207, over 4910.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03001, over 973027.46 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 21:04:19,805 INFO [train.py:715] (3/8) Epoch 16, batch 31600, loss[loss=0.1257, simple_loss=0.1995, pruned_loss=0.02602, over 4847.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02979, over 972856.51 frames.], batch size: 32, lr: 1.36e-04
+2022-05-08 21:04:58,917 INFO [train.py:715] (3/8) Epoch 16, batch 31650, loss[loss=0.1394, simple_loss=0.2217, pruned_loss=0.02858, over 4872.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02988, over 972600.28 frames.], batch size: 16, lr: 1.36e-04
+2022-05-08 21:05:37,855 INFO [train.py:715] (3/8) Epoch 16, batch 31700, loss[loss=0.1168, simple_loss=0.1912, pruned_loss=0.02123, over 4694.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02934, over 972437.00 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 21:06:17,110 INFO [train.py:715] (3/8) Epoch 16, batch 31750, loss[loss=0.1424, simple_loss=0.2159, pruned_loss=0.03443, over 4850.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.0291, over 972559.67 frames.], batch size: 32, lr: 1.36e-04
+2022-05-08 21:06:56,939 INFO [train.py:715] (3/8) Epoch 16, batch 31800, loss[loss=0.1058, simple_loss=0.1853, pruned_loss=0.01314, over 4986.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02965, over 973440.71 frames.], batch size: 25, lr: 1.36e-04
+2022-05-08 21:07:36,868 INFO [train.py:715] (3/8) Epoch 16, batch 31850, loss[loss=0.1234, simple_loss=0.2009, pruned_loss=0.02293, over 4993.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02949, over 973159.83 frames.], batch size: 16, lr: 1.36e-04
+2022-05-08 21:08:15,873 INFO [train.py:715] (3/8) Epoch 16, batch 31900, loss[loss=0.1334, simple_loss=0.2091, pruned_loss=0.02887, over 4647.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02926, over 972799.35 frames.], batch size: 13, lr: 1.36e-04
+2022-05-08 21:08:55,065 INFO [train.py:715] (3/8) Epoch 16, batch 31950, loss[loss=0.1429, simple_loss=0.2131, pruned_loss=0.03631, over 4977.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02899, over 972302.92 frames.], batch size: 28, lr: 1.36e-04
+2022-05-08 21:09:34,440 INFO [train.py:715] (3/8) Epoch 16, batch 32000, loss[loss=0.1229, simple_loss=0.1996, pruned_loss=0.02316, over 4745.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02969, over 972124.71 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 21:10:13,550 INFO [train.py:715] (3/8) Epoch 16, batch 32050, loss[loss=0.1298, simple_loss=0.2, pruned_loss=0.02981, over 4783.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2067, pruned_loss=0.03, over 972152.27 frames.], batch size: 18, lr: 1.36e-04
+2022-05-08 21:10:53,098 INFO [train.py:715] (3/8) Epoch 16, batch 32100, loss[loss=0.1389, simple_loss=0.2146, pruned_loss=0.03159, over 4852.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2072, pruned_loss=0.03031, over 972003.43 frames.], batch size: 20, lr: 1.36e-04
+2022-05-08 21:11:32,626 INFO [train.py:715] (3/8) Epoch 16, batch 32150, loss[loss=0.1813, simple_loss=0.2372, pruned_loss=0.06268, over 4942.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2067, pruned_loss=0.03008, over 972128.45 frames.], batch size: 21, lr: 1.36e-04
+2022-05-08 21:12:12,708 INFO [train.py:715] (3/8) Epoch 16, batch 32200, loss[loss=0.1436, simple_loss=0.2238, pruned_loss=0.03169, over 4950.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2069, pruned_loss=0.03037, over 971416.40 frames.], batch size: 23, lr: 1.36e-04
+2022-05-08 21:12:51,831 INFO [train.py:715] (3/8) Epoch 16, batch 32250, loss[loss=0.1245, simple_loss=0.1929, pruned_loss=0.02807, over 4698.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2077, pruned_loss=0.03052, over 971750.53 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 21:13:31,328 INFO [train.py:715] (3/8) Epoch 16, batch 32300, loss[loss=0.1362, simple_loss=0.1986, pruned_loss=0.03692, over 4792.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03031, over 971703.06 frames.], batch size: 12, lr: 1.36e-04
+2022-05-08 21:14:11,344 INFO [train.py:715] (3/8) Epoch 16, batch 32350, loss[loss=0.149, simple_loss=0.2223, pruned_loss=0.03781, over 4768.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02988, over 971890.82 frames.], batch size: 16, lr: 1.36e-04
+2022-05-08 21:14:50,975 INFO [train.py:715] (3/8) Epoch 16, batch 32400, loss[loss=0.1539, simple_loss=0.2235, pruned_loss=0.04211, over 4813.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03029, over 971663.91 frames.], batch size: 21, lr: 1.36e-04
+2022-05-08 21:15:30,004 INFO [train.py:715] (3/8) Epoch 16, batch 32450, loss[loss=0.1203, simple_loss=0.196, pruned_loss=0.02231, over 4906.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03016, over 970938.82 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 21:16:10,033 INFO [train.py:715] (3/8) Epoch 16, batch 32500, loss[loss=0.1302, simple_loss=0.2038, pruned_loss=0.02826, over 4767.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03019, over 970244.34 frames.], batch size: 14, lr: 1.36e-04
+2022-05-08 21:16:49,323 INFO [train.py:715] (3/8) Epoch 16, batch 32550, loss[loss=0.1144, simple_loss=0.1938, pruned_loss=0.0175, over 4825.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02981, over 971640.34 frames.], batch size: 27, lr: 1.36e-04
+2022-05-08 21:17:28,288 INFO [train.py:715] (3/8) Epoch 16, batch 32600, loss[loss=0.141, simple_loss=0.2121, pruned_loss=0.03492, over 4686.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02958, over 971990.69 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 21:18:07,200 INFO [train.py:715] (3/8) Epoch 16, batch 32650, loss[loss=0.1309, simple_loss=0.2078, pruned_loss=0.02705, over 4757.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02962, over 971790.32 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 21:18:46,395 INFO [train.py:715] (3/8) Epoch 16, batch 32700, loss[loss=0.1166, simple_loss=0.1853, pruned_loss=0.02391, over 4926.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.0293, over 971886.99 frames.], batch size: 18, lr: 1.36e-04
+2022-05-08 21:19:25,736 INFO [train.py:715] (3/8) Epoch 16, batch 32750, loss[loss=0.1252, simple_loss=0.2, pruned_loss=0.02525, over 4812.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02926, over 971709.82 frames.], batch size: 13, lr: 1.36e-04
+2022-05-08 21:20:05,461 INFO [train.py:715] (3/8) Epoch 16, batch 32800, loss[loss=0.1272, simple_loss=0.2064, pruned_loss=0.02403, over 4928.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02925, over 971149.49 frames.], batch size: 23, lr: 1.36e-04
+2022-05-08 21:20:44,827 INFO [train.py:715] (3/8) Epoch 16, batch 32850, loss[loss=0.1285, simple_loss=0.2026, pruned_loss=0.02721, over 4945.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02971, over 971626.12 frames.], batch size: 21, lr: 1.36e-04
+2022-05-08 21:21:24,458 INFO [train.py:715] (3/8) Epoch 16, batch 32900, loss[loss=0.1399, simple_loss=0.2201, pruned_loss=0.02981, over 4939.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02958, over 972082.04 frames.], batch size: 29, lr: 1.36e-04
+2022-05-08 21:22:03,428 INFO [train.py:715] (3/8) Epoch 16, batch 32950, loss[loss=0.1338, simple_loss=0.1997, pruned_loss=0.03391, over 4633.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02935, over 972363.04 frames.], batch size: 13, lr: 1.36e-04
+2022-05-08 21:22:42,575 INFO [train.py:715] (3/8) Epoch 16, batch 33000, loss[loss=0.1165, simple_loss=0.1901, pruned_loss=0.02141, over 4820.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02943, over 972710.47 frames.], batch size: 26, lr: 1.36e-04
+2022-05-08 21:22:42,576 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 21:22:55,769 INFO [train.py:742] (3/8) Epoch 16, validation: loss=0.105, simple_loss=0.1884, pruned_loss=0.01078, over 914524.00 frames.
+2022-05-08 21:23:35,556 INFO [train.py:715] (3/8) Epoch 16, batch 33050, loss[loss=0.1153, simple_loss=0.1966, pruned_loss=0.01695, over 4977.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02965, over 972488.77 frames.], batch size: 14, lr: 1.36e-04
+2022-05-08 21:24:14,884 INFO [train.py:715] (3/8) Epoch 16, batch 33100, loss[loss=0.1081, simple_loss=0.1763, pruned_loss=0.01996, over 4912.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.0293, over 972996.74 frames.], batch size: 17, lr: 1.36e-04
+2022-05-08 21:24:54,242 INFO [train.py:715] (3/8) Epoch 16, batch 33150, loss[loss=0.12, simple_loss=0.1946, pruned_loss=0.0227, over 4700.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02909, over 972688.77 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 21:25:34,103 INFO [train.py:715] (3/8) Epoch 16, batch 33200, loss[loss=0.1267, simple_loss=0.1969, pruned_loss=0.02825, over 4959.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2075, pruned_loss=0.02894, over 972353.61 frames.], batch size: 14, lr: 1.36e-04
+2022-05-08 21:26:13,844 INFO [train.py:715] (3/8) Epoch 16, batch 33250, loss[loss=0.1221, simple_loss=0.1905, pruned_loss=0.02682, over 4911.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03001, over 971925.50 frames.], batch size: 17, lr: 1.36e-04
+2022-05-08 21:26:53,436 INFO [train.py:715] (3/8) Epoch 16, batch 33300, loss[loss=0.1307, simple_loss=0.2123, pruned_loss=0.02455, over 4909.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03008, over 972591.90 frames.], batch size: 23, lr: 1.36e-04
+2022-05-08 21:27:32,747 INFO [train.py:715] (3/8) Epoch 16, batch 33350, loss[loss=0.1361, simple_loss=0.2124, pruned_loss=0.02993, over 4743.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02963, over 972229.38 frames.], batch size: 16, lr: 1.36e-04
+2022-05-08 21:28:12,219 INFO [train.py:715] (3/8) Epoch 16, batch 33400, loss[loss=0.1451, simple_loss=0.2239, pruned_loss=0.03309, over 4906.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02971, over 972078.02 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 21:28:51,464 INFO [train.py:715] (3/8) Epoch 16, batch 33450, loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03466, over 4967.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02942, over 972639.18 frames.], batch size: 31, lr: 1.36e-04
+2022-05-08 21:29:30,508 INFO [train.py:715] (3/8) Epoch 16, batch 33500, loss[loss=0.1494, simple_loss=0.2243, pruned_loss=0.0373, over 4849.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02942, over 972436.67 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 21:30:09,464 INFO [train.py:715] (3/8) Epoch 16, batch 33550, loss[loss=0.1398, simple_loss=0.2136, pruned_loss=0.03303, over 4791.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02966, over 973008.84 frames.], batch size: 12, lr: 1.36e-04
+2022-05-08 21:30:49,227 INFO [train.py:715] (3/8) Epoch 16, batch 33600, loss[loss=0.1236, simple_loss=0.2005, pruned_loss=0.02333, over 4976.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02949, over 973614.01 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 21:31:28,204 INFO [train.py:715] (3/8) Epoch 16, batch 33650, loss[loss=0.1155, simple_loss=0.1872, pruned_loss=0.02188, over 4956.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02975, over 973940.30 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 21:32:07,847 INFO [train.py:715] (3/8) Epoch 16, batch 33700, loss[loss=0.1096, simple_loss=0.1747, pruned_loss=0.02229, over 4777.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.03004, over 973370.69 frames.], batch size: 12, lr: 1.36e-04
+2022-05-08 21:32:46,798 INFO [train.py:715] (3/8) Epoch 16, batch 33750, loss[loss=0.1263, simple_loss=0.2068, pruned_loss=0.02284, over 4897.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03054, over 974291.74 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 21:33:25,787 INFO [train.py:715] (3/8) Epoch 16, batch 33800, loss[loss=0.1413, simple_loss=0.2136, pruned_loss=0.03446, over 4808.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2099, pruned_loss=0.03051, over 974326.67 frames.], batch size: 21, lr: 1.36e-04
+2022-05-08 21:34:05,045 INFO [train.py:715] (3/8) Epoch 16, batch 33850, loss[loss=0.1468, simple_loss=0.2125, pruned_loss=0.04052, over 4785.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.03069, over 974281.55 frames.], batch size: 18, lr: 1.36e-04
+2022-05-08 21:34:44,271 INFO [train.py:715] (3/8) Epoch 16, batch 33900, loss[loss=0.1286, simple_loss=0.1949, pruned_loss=0.0311, over 4979.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03067, over 973711.27 frames.], batch size: 14, lr: 1.36e-04
+2022-05-08 21:35:24,624 INFO [train.py:715] (3/8) Epoch 16, batch 33950, loss[loss=0.1558, simple_loss=0.2248, pruned_loss=0.04338, over 4836.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03015, over 973779.69 frames.], batch size: 30, lr: 1.36e-04
+2022-05-08 21:36:03,124 INFO [train.py:715] (3/8) Epoch 16, batch 34000, loss[loss=0.1487, simple_loss=0.2359, pruned_loss=0.03072, over 4888.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02977, over 973657.51 frames.], batch size: 22, lr: 1.36e-04
+2022-05-08 21:36:43,153 INFO [train.py:715] (3/8) Epoch 16, batch 34050, loss[loss=0.131, simple_loss=0.1992, pruned_loss=0.03146, over 4930.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02989, over 973106.10 frames.], batch size: 29, lr: 1.36e-04
+2022-05-08 21:37:22,557 INFO [train.py:715] (3/8) Epoch 16, batch 34100, loss[loss=0.1243, simple_loss=0.2016, pruned_loss=0.02352, over 4832.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03002, over 972786.53 frames.], batch size: 26, lr: 1.36e-04
+2022-05-08 21:38:01,718 INFO [train.py:715] (3/8) Epoch 16, batch 34150, loss[loss=0.1713, simple_loss=0.253, pruned_loss=0.04478, over 4870.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02978, over 972000.78 frames.], batch size: 38, lr: 1.36e-04
+2022-05-08 21:38:41,102 INFO [train.py:715] (3/8) Epoch 16, batch 34200, loss[loss=0.1255, simple_loss=0.2015, pruned_loss=0.02473, over 4988.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02975, over 971720.74 frames.], batch size: 25, lr: 1.36e-04
+2022-05-08 21:39:20,449 INFO [train.py:715] (3/8) Epoch 16, batch 34250, loss[loss=0.1356, simple_loss=0.2121, pruned_loss=0.02954, over 4761.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.0294, over 971506.04 frames.], batch size: 16, lr: 1.36e-04
+2022-05-08 21:40:00,529 INFO [train.py:715] (3/8) Epoch 16, batch 34300, loss[loss=0.1129, simple_loss=0.1908, pruned_loss=0.0175, over 4860.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02892, over 971792.14 frames.], batch size: 20, lr: 1.36e-04
+2022-05-08 21:40:39,501 INFO [train.py:715] (3/8) Epoch 16, batch 34350, loss[loss=0.1348, simple_loss=0.208, pruned_loss=0.03083, over 4758.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.0292, over 972170.35 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 21:41:18,851 INFO [train.py:715] (3/8) Epoch 16, batch 34400, loss[loss=0.1167, simple_loss=0.1883, pruned_loss=0.02256, over 4829.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02891, over 971461.76 frames.], batch size: 13, lr: 1.36e-04
+2022-05-08 21:41:58,452 INFO [train.py:715] (3/8) Epoch 16, batch 34450, loss[loss=0.1283, simple_loss=0.2099, pruned_loss=0.02339, over 4885.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2077, pruned_loss=0.02912, over 972304.57 frames.], batch size: 22, lr: 1.36e-04
+2022-05-08 21:42:37,729 INFO [train.py:715] (3/8) Epoch 16, batch 34500, loss[loss=0.112, simple_loss=0.1818, pruned_loss=0.02106, over 4912.00 frames.], tot_loss[loss=0.133, simple_loss=0.2078, pruned_loss=0.02907, over 971591.65 frames.], batch size: 18, lr: 1.36e-04
+2022-05-08 21:43:17,127 INFO [train.py:715] (3/8) Epoch 16, batch 34550, loss[loss=0.1286, simple_loss=0.2119, pruned_loss=0.02269, over 4784.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2083, pruned_loss=0.02921, over 971576.33 frames.], batch size: 17, lr: 1.36e-04
+2022-05-08 21:43:56,247 INFO [train.py:715] (3/8) Epoch 16, batch 34600, loss[loss=0.1513, simple_loss=0.2257, pruned_loss=0.03847, over 4844.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2077, pruned_loss=0.02888, over 971384.76 frames.], batch size: 15, lr: 1.36e-04
+2022-05-08 21:44:36,201 INFO [train.py:715] (3/8) Epoch 16, batch 34650, loss[loss=0.09669, simple_loss=0.1715, pruned_loss=0.01095, over 4797.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02903, over 971210.85 frames.], batch size: 12, lr: 1.36e-04
+2022-05-08 21:45:15,694 INFO [train.py:715] (3/8) Epoch 16, batch 34700, loss[loss=0.1284, simple_loss=0.2063, pruned_loss=0.02527, over 4774.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02905, over 970709.53 frames.], batch size: 14, lr: 1.36e-04
+2022-05-08 21:45:54,803 INFO [train.py:715] (3/8) Epoch 16, batch 34750, loss[loss=0.141, simple_loss=0.2236, pruned_loss=0.02919, over 4761.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02936, over 970751.36 frames.], batch size: 19, lr: 1.36e-04
+2022-05-08 21:46:32,021 INFO [train.py:715] (3/8) Epoch 16, batch 34800, loss[loss=0.1372, simple_loss=0.2156, pruned_loss=0.02943, over 4927.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02976, over 971730.04 frames.], batch size: 23, lr: 1.36e-04
+2022-05-08 21:47:23,861 INFO [train.py:715] (3/8) Epoch 17, batch 0, loss[loss=0.1236, simple_loss=0.2034, pruned_loss=0.02189, over 4954.00 frames.], tot_loss[loss=0.1236, simple_loss=0.2034, pruned_loss=0.02189, over 4954.00 frames.], batch size: 24, lr: 1.32e-04
+2022-05-08 21:48:03,329 INFO [train.py:715] (3/8) Epoch 17, batch 50, loss[loss=0.1152, simple_loss=0.188, pruned_loss=0.0212, over 4983.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03044, over 219117.38 frames.], batch size: 15, lr: 1.32e-04
+2022-05-08 21:48:44,385 INFO [train.py:715] (3/8) Epoch 17, batch 100, loss[loss=0.1179, simple_loss=0.2032, pruned_loss=0.01626, over 4819.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2088, pruned_loss=0.02979, over 385735.51 frames.], batch size: 26, lr: 1.32e-04
+2022-05-08 21:49:25,331 INFO [train.py:715] (3/8) Epoch 17, batch 150, loss[loss=0.1348, simple_loss=0.2044, pruned_loss=0.03264, over 4733.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03018, over 515586.15 frames.], batch size: 16, lr: 1.32e-04
+2022-05-08 21:50:06,393 INFO [train.py:715] (3/8) Epoch 17, batch 200, loss[loss=0.131, simple_loss=0.2008, pruned_loss=0.03056, over 4853.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03012, over 617754.95 frames.], batch size: 20, lr: 1.32e-04
+2022-05-08 21:50:49,388 INFO [train.py:715] (3/8) Epoch 17, batch 250, loss[loss=0.1638, simple_loss=0.2356, pruned_loss=0.046, over 4891.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02996, over 696341.69 frames.], batch size: 17, lr: 1.32e-04
+2022-05-08 21:51:30,987 INFO [train.py:715] (3/8) Epoch 17, batch 300, loss[loss=0.1269, simple_loss=0.1985, pruned_loss=0.02765, over 4815.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03018, over 757882.64 frames.], batch size: 27, lr: 1.32e-04
+2022-05-08 21:52:11,855 INFO [train.py:715] (3/8) Epoch 17, batch 350, loss[loss=0.1349, simple_loss=0.2107, pruned_loss=0.02952, over 4951.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02985, over 806347.49 frames.], batch size: 15, lr: 1.32e-04
+2022-05-08 21:52:52,793 INFO [train.py:715] (3/8) Epoch 17, batch 400, loss[loss=0.1365, simple_loss=0.2117, pruned_loss=0.03066, over 4905.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02972, over 842984.86 frames.], batch size: 17, lr: 1.32e-04
+2022-05-08 21:53:33,714 INFO [train.py:715] (3/8) Epoch 17, batch 450, loss[loss=0.1322, simple_loss=0.213, pruned_loss=0.02567, over 4805.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02967, over 870958.46 frames.], batch size: 15, lr: 1.32e-04
+2022-05-08 21:54:14,771 INFO [train.py:715] (3/8) Epoch 17, batch 500, loss[loss=0.1365, simple_loss=0.2051, pruned_loss=0.0339, over 4810.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02923, over 892940.49 frames.], batch size: 15, lr: 1.32e-04
+2022-05-08 21:54:56,773 INFO [train.py:715] (3/8) Epoch 17, batch 550, loss[loss=0.1247, simple_loss=0.1974, pruned_loss=0.026, over 4758.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02927, over 909662.92 frames.], batch size: 19, lr: 1.32e-04
+2022-05-08 21:55:37,898 INFO [train.py:715] (3/8) Epoch 17, batch 600, loss[loss=0.108, simple_loss=0.182, pruned_loss=0.01704, over 4914.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02941, over 923965.78 frames.], batch size: 18, lr: 1.32e-04
+2022-05-08 21:56:20,089 INFO [train.py:715] (3/8) Epoch 17, batch 650, loss[loss=0.1666, simple_loss=0.2296, pruned_loss=0.05177, over 4854.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02925, over 935074.59 frames.], batch size: 32, lr: 1.32e-04
+2022-05-08 21:57:01,709 INFO [train.py:715] (3/8) Epoch 17, batch 700, loss[loss=0.1342, simple_loss=0.2167, pruned_loss=0.02584, over 4927.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02928, over 943512.33 frames.], batch size: 18, lr: 1.32e-04
+2022-05-08 21:57:42,596 INFO [train.py:715] (3/8) Epoch 17, batch 750, loss[loss=0.1303, simple_loss=0.2139, pruned_loss=0.02337, over 4803.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02961, over 949616.70 frames.], batch size: 25, lr: 1.32e-04
+2022-05-08 21:58:23,380 INFO [train.py:715] (3/8) Epoch 17, batch 800, loss[loss=0.1247, simple_loss=0.1945, pruned_loss=0.02744, over 4755.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02992, over 954533.86 frames.], batch size: 19, lr: 1.32e-04
+2022-05-08 21:59:03,982 INFO [train.py:715] (3/8) Epoch 17, batch 850, loss[loss=0.1111, simple_loss=0.1868, pruned_loss=0.01773, over 4783.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02981, over 958680.46 frames.], batch size: 17, lr: 1.32e-04
+2022-05-08 21:59:45,378 INFO [train.py:715] (3/8) Epoch 17, batch 900, loss[loss=0.1312, simple_loss=0.2087, pruned_loss=0.02679, over 4765.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02965, over 962155.64 frames.], batch size: 19, lr: 1.32e-04
+2022-05-08 22:00:26,263 INFO [train.py:715] (3/8) Epoch 17, batch 950, loss[loss=0.153, simple_loss=0.2353, pruned_loss=0.03531, over 4983.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02978, over 965044.89 frames.], batch size: 15, lr: 1.32e-04
+2022-05-08 22:01:07,643 INFO [train.py:715] (3/8) Epoch 17, batch 1000, loss[loss=0.1181, simple_loss=0.1952, pruned_loss=0.02053, over 4749.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02961, over 965923.15 frames.], batch size: 19, lr: 1.32e-04
+2022-05-08 22:01:48,891 INFO [train.py:715] (3/8) Epoch 17, batch 1050, loss[loss=0.1642, simple_loss=0.2386, pruned_loss=0.04487, over 4963.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.0299, over 967220.27 frames.], batch size: 24, lr: 1.32e-04
+2022-05-08 22:02:29,882 INFO [train.py:715] (3/8) Epoch 17, batch 1100, loss[loss=0.1189, simple_loss=0.1961, pruned_loss=0.02082, over 4774.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2086, pruned_loss=0.02984, over 967531.35 frames.], batch size: 14, lr: 1.32e-04
+2022-05-08 22:03:10,393 INFO [train.py:715] (3/8) Epoch 17, batch 1150, loss[loss=0.1141, simple_loss=0.1883, pruned_loss=0.01993, over 4971.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2083, pruned_loss=0.02946, over 968433.91 frames.], batch size: 15, lr: 1.32e-04
+2022-05-08 22:03:51,865 INFO [train.py:715] (3/8) Epoch 17, batch 1200, loss[loss=0.1197, simple_loss=0.1941, pruned_loss=0.02262, over 4836.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2086, pruned_loss=0.02949, over 969382.36 frames.], batch size: 30, lr: 1.32e-04
+2022-05-08 22:04:32,834 INFO [train.py:715] (3/8) Epoch 17, batch 1250, loss[loss=0.111, simple_loss=0.1949, pruned_loss=0.01357, over 4918.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2077, pruned_loss=0.02867, over 970030.76 frames.], batch size: 29, lr: 1.32e-04
+2022-05-08 22:05:13,884 INFO [train.py:715] (3/8) Epoch 17, batch 1300, loss[loss=0.1169, simple_loss=0.1896, pruned_loss=0.02212, over 4781.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2075, pruned_loss=0.02879, over 970434.77 frames.], batch size: 17, lr: 1.32e-04
+2022-05-08 22:05:55,244 INFO [train.py:715] (3/8) Epoch 17, batch 1350, loss[loss=0.1094, simple_loss=0.1828, pruned_loss=0.01804, over 4929.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02914, over 970673.81 frames.], batch size: 29, lr: 1.32e-04
+2022-05-08 22:06:36,201 INFO [train.py:715] (3/8) Epoch 17, batch 1400, loss[loss=0.1426, simple_loss=0.2226, pruned_loss=0.03126, over 4921.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02969, over 971434.54 frames.], batch size: 29, lr: 1.32e-04
+2022-05-08 22:07:16,805 INFO [train.py:715] (3/8) Epoch 17, batch 1450, loss[loss=0.1537, simple_loss=0.231, pruned_loss=0.03819, over 4799.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02958, over 971162.74 frames.], batch size: 24, lr: 1.32e-04
+2022-05-08 22:07:57,517 INFO [train.py:715] (3/8) Epoch 17, batch 1500, loss[loss=0.1146, simple_loss=0.184, pruned_loss=0.02261, over 4782.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02988, over 971752.34 frames.], batch size: 21, lr: 1.32e-04
+2022-05-08 22:08:39,010 INFO [train.py:715] (3/8) Epoch 17, batch 1550, loss[loss=0.1426, simple_loss=0.2183, pruned_loss=0.03343, over 4960.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03017, over 972055.21 frames.], batch size: 24, lr: 1.32e-04
+2022-05-08 22:09:20,357 INFO [train.py:715] (3/8) Epoch 17, batch 1600, loss[loss=0.1295, simple_loss=0.1982, pruned_loss=0.03036, over 4922.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03013, over 972792.42 frames.], batch size: 18, lr: 1.32e-04
+2022-05-08 22:10:01,032 INFO [train.py:715] (3/8) Epoch 17, batch 1650, loss[loss=0.1345, simple_loss=0.2029, pruned_loss=0.03311, over 4745.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.0298, over 972471.28 frames.], batch size: 16, lr: 1.32e-04
+2022-05-08 22:10:42,368 INFO [train.py:715] (3/8) Epoch 17, batch 1700, loss[loss=0.1129, simple_loss=0.1788, pruned_loss=0.02349, over 4798.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02985, over 972310.90 frames.], batch size: 14, lr: 1.32e-04
+2022-05-08 22:11:23,610 INFO [train.py:715] (3/8) Epoch 17, batch 1750, loss[loss=0.1474, simple_loss=0.217, pruned_loss=0.03896, over 4699.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03032, over 972372.37 frames.], batch size: 15, lr: 1.32e-04
+2022-05-08 22:12:04,540 INFO [train.py:715] (3/8) Epoch 17, batch 1800, loss[loss=0.1464, simple_loss=0.2239, pruned_loss=0.0345, over 4993.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03012, over 972762.20 frames.], batch size: 14, lr: 1.32e-04
+2022-05-08 22:12:45,652 INFO [train.py:715] (3/8) Epoch 17, batch 1850, loss[loss=0.1089, simple_loss=0.1823, pruned_loss=0.01777, over 4831.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02996, over 972817.58 frames.], batch size: 27, lr: 1.32e-04
+2022-05-08 22:13:27,332 INFO [train.py:715] (3/8) Epoch 17, batch 1900, loss[loss=0.1711, simple_loss=0.2361, pruned_loss=0.05304, over 4896.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.03005, over 972909.01 frames.], batch size: 19, lr: 1.32e-04
+2022-05-08 22:14:08,484 INFO [train.py:715] (3/8) Epoch 17, batch 1950, loss[loss=0.1488, simple_loss=0.2162, pruned_loss=0.04071, over 4872.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02957, over 971928.35 frames.], batch size: 16, lr: 1.32e-04
+2022-05-08 22:14:49,365 INFO [train.py:715] (3/8) Epoch 17, batch 2000, loss[loss=0.1264, simple_loss=0.2021, pruned_loss=0.02539, over 4914.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02944, over 972861.25 frames.], batch size: 23, lr: 1.32e-04
+2022-05-08 22:15:30,343 INFO [train.py:715] (3/8) Epoch 17, batch 2050, loss[loss=0.1507, simple_loss=0.2221, pruned_loss=0.03967, over 4949.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02901, over 972421.39 frames.], batch size: 29, lr: 1.32e-04
+2022-05-08 22:16:11,451 INFO [train.py:715] (3/8) Epoch 17, batch 2100, loss[loss=0.1313, simple_loss=0.2121, pruned_loss=0.0252, over 4906.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02953, over 973280.35 frames.], batch size: 17, lr: 1.32e-04
+2022-05-08 22:16:52,788 INFO [train.py:715] (3/8) Epoch 17, batch 2150, loss[loss=0.1237, simple_loss=0.2108, pruned_loss=0.01826, over 4921.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02956, over 973222.07 frames.], batch size: 21, lr: 1.32e-04
+2022-05-08 22:17:34,185 INFO [train.py:715] (3/8) Epoch 17, batch 2200, loss[loss=0.1323, simple_loss=0.1946, pruned_loss=0.03504, over 4967.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02947, over 973029.22 frames.], batch size: 35, lr: 1.32e-04
+2022-05-08 22:18:15,309 INFO [train.py:715] (3/8) Epoch 17, batch 2250, loss[loss=0.1721, simple_loss=0.2343, pruned_loss=0.05495, over 4923.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.02997, over 973174.18 frames.], batch size: 39, lr: 1.32e-04
+2022-05-08 22:18:56,042 INFO [train.py:715] (3/8) Epoch 17, batch 2300, loss[loss=0.1541, simple_loss=0.2195, pruned_loss=0.04432, over 4925.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02953, over 973044.07 frames.], batch size: 18, lr: 1.32e-04
+2022-05-08 22:19:36,479 INFO [train.py:715] (3/8) Epoch 17, batch 2350, loss[loss=0.1262, simple_loss=0.2048, pruned_loss=0.02384, over 4861.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02969, over 972248.07 frames.], batch size: 32, lr: 1.32e-04
+2022-05-08 22:20:17,317 INFO [train.py:715] (3/8) Epoch 17, batch 2400, loss[loss=0.1314, simple_loss=0.208, pruned_loss=0.02745, over 4843.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2069, pruned_loss=0.0296, over 972404.41 frames.], batch size: 20, lr: 1.32e-04
+2022-05-08 22:20:58,225 INFO [train.py:715] (3/8) Epoch 17, batch 2450, loss[loss=0.1165, simple_loss=0.1924, pruned_loss=0.0203, over 4988.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02934, over 972249.17 frames.], batch size: 28, lr: 1.32e-04
+2022-05-08 22:21:39,040 INFO [train.py:715] (3/8) Epoch 17, batch 2500, loss[loss=0.1591, simple_loss=0.2362, pruned_loss=0.041, over 4802.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02999, over 971957.29 frames.], batch size: 13, lr: 1.32e-04
+2022-05-08 22:22:20,009 INFO [train.py:715] (3/8) Epoch 17, batch 2550, loss[loss=0.1359, simple_loss=0.2049, pruned_loss=0.03348, over 4845.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2063, pruned_loss=0.02946, over 971713.96 frames.], batch size: 20, lr: 1.32e-04
+2022-05-08 22:23:00,986 INFO [train.py:715] (3/8) Epoch 17, batch 2600, loss[loss=0.1177, simple_loss=0.195, pruned_loss=0.02025, over 4794.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02917, over 971826.62 frames.], batch size: 21, lr: 1.32e-04
+2022-05-08 22:23:42,209 INFO [train.py:715] (3/8) Epoch 17, batch 2650, loss[loss=0.1315, simple_loss=0.2085, pruned_loss=0.0272, over 4924.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02925, over 971314.39 frames.], batch size: 18, lr: 1.32e-04
+2022-05-08 22:24:22,845 INFO [train.py:715] (3/8) Epoch 17, batch 2700, loss[loss=0.1265, simple_loss=0.2142, pruned_loss=0.0194, over 4802.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02935, over 971911.98 frames.], batch size: 24, lr: 1.32e-04
+2022-05-08 22:25:04,065 INFO [train.py:715] (3/8) Epoch 17, batch 2750, loss[loss=0.1277, simple_loss=0.203, pruned_loss=0.02619, over 4807.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02925, over 972356.22 frames.], batch size: 21, lr: 1.32e-04
+2022-05-08 22:25:44,578 INFO [train.py:715] (3/8) Epoch 17, batch 2800, loss[loss=0.1246, simple_loss=0.2056, pruned_loss=0.02174, over 4755.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02881, over 973368.76 frames.], batch size: 16, lr: 1.32e-04
+2022-05-08 22:26:25,559 INFO [train.py:715] (3/8) Epoch 17, batch 2850, loss[loss=0.1282, simple_loss=0.216, pruned_loss=0.02023, over 4941.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02858, over 973377.05 frames.], batch size: 21, lr: 1.32e-04
+2022-05-08 22:27:06,300 INFO [train.py:715] (3/8) Epoch 17, batch 2900, loss[loss=0.1359, simple_loss=0.2138, pruned_loss=0.02901, over 4820.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02897, over 972768.98 frames.], batch size: 27, lr: 1.32e-04
+2022-05-08 22:27:47,265 INFO [train.py:715] (3/8) Epoch 17, batch 2950, loss[loss=0.1355, simple_loss=0.2153, pruned_loss=0.02788, over 4799.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02981, over 972898.82 frames.], batch size: 24, lr: 1.32e-04
+2022-05-08 22:28:28,420 INFO [train.py:715] (3/8) Epoch 17, batch 3000, loss[loss=0.1357, simple_loss=0.2031, pruned_loss=0.03417, over 4963.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02943, over 972489.20 frames.], batch size: 35, lr: 1.32e-04
+2022-05-08 22:28:28,420 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 22:28:43,492 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1882, pruned_loss=0.01063, over 914524.00 frames.
+2022-05-08 22:29:24,681 INFO [train.py:715] (3/8) Epoch 17, batch 3050, loss[loss=0.1361, simple_loss=0.2052, pruned_loss=0.03348, over 4788.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02917, over 971580.63 frames.], batch size: 18, lr: 1.32e-04
+2022-05-08 22:30:05,288 INFO [train.py:715] (3/8) Epoch 17, batch 3100, loss[loss=0.127, simple_loss=0.2012, pruned_loss=0.02642, over 4822.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02901, over 971459.46 frames.], batch size: 15, lr: 1.32e-04
+2022-05-08 22:30:46,409 INFO [train.py:715] (3/8) Epoch 17, batch 3150, loss[loss=0.1405, simple_loss=0.2203, pruned_loss=0.03037, over 4784.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02945, over 971606.04 frames.], batch size: 18, lr: 1.32e-04
+2022-05-08 22:31:26,340 INFO [train.py:715] (3/8) Epoch 17, batch 3200, loss[loss=0.1138, simple_loss=0.1991, pruned_loss=0.01431, over 4712.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02933, over 971245.04 frames.], batch size: 15, lr: 1.32e-04
+2022-05-08 22:32:07,678 INFO [train.py:715] (3/8) Epoch 17, batch 3250, loss[loss=0.1488, simple_loss=0.2157, pruned_loss=0.04091, over 4965.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02974, over 971363.10 frames.], batch size: 35, lr: 1.32e-04
+2022-05-08 22:32:47,741 INFO [train.py:715] (3/8) Epoch 17, batch 3300, loss[loss=0.1381, simple_loss=0.227, pruned_loss=0.02459, over 4784.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02934, over 971686.04 frames.], batch size: 18, lr: 1.32e-04
+2022-05-08 22:33:28,435 INFO [train.py:715] (3/8) Epoch 17, batch 3350, loss[loss=0.1414, simple_loss=0.2209, pruned_loss=0.03093, over 4779.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.0295, over 971956.51 frames.], batch size: 18, lr: 1.32e-04
+2022-05-08 22:34:09,184 INFO [train.py:715] (3/8) Epoch 17, batch 3400, loss[loss=0.1466, simple_loss=0.2135, pruned_loss=0.03988, over 4939.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02937, over 972439.36 frames.], batch size: 21, lr: 1.32e-04
+2022-05-08 22:34:50,594 INFO [train.py:715] (3/8) Epoch 17, batch 3450, loss[loss=0.1289, simple_loss=0.2052, pruned_loss=0.02627, over 4954.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02888, over 971662.51 frames.], batch size: 35, lr: 1.32e-04
+2022-05-08 22:35:30,943 INFO [train.py:715] (3/8) Epoch 17, batch 3500, loss[loss=0.1449, simple_loss=0.2271, pruned_loss=0.03131, over 4918.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02909, over 972205.83 frames.], batch size: 23, lr: 1.32e-04
+2022-05-08 22:36:11,167 INFO [train.py:715] (3/8) Epoch 17, batch 3550, loss[loss=0.1273, simple_loss=0.2147, pruned_loss=0.01998, over 4980.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02879, over 971741.13 frames.], batch size: 28, lr: 1.32e-04
+2022-05-08 22:36:52,130 INFO [train.py:715] (3/8) Epoch 17, batch 3600, loss[loss=0.1452, simple_loss=0.2268, pruned_loss=0.03177, over 4969.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2079, pruned_loss=0.02926, over 971351.89 frames.], batch size: 24, lr: 1.32e-04
+2022-05-08 22:37:31,757 INFO [train.py:715] (3/8) Epoch 17, batch 3650, loss[loss=0.1307, simple_loss=0.2073, pruned_loss=0.027, over 4782.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2078, pruned_loss=0.02891, over 971339.80 frames.], batch size: 17, lr: 1.32e-04
+2022-05-08 22:38:11,918 INFO [train.py:715] (3/8) Epoch 17, batch 3700, loss[loss=0.1249, simple_loss=0.1973, pruned_loss=0.02628, over 4859.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2065, pruned_loss=0.02822, over 970984.92 frames.], batch size: 20, lr: 1.32e-04
+2022-05-08 22:38:52,846 INFO [train.py:715] (3/8) Epoch 17, batch 3750, loss[loss=0.1364, simple_loss=0.2027, pruned_loss=0.03505, over 4794.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02866, over 970644.47 frames.], batch size: 17, lr: 1.32e-04
+2022-05-08 22:39:33,614 INFO [train.py:715] (3/8) Epoch 17, batch 3800, loss[loss=0.1306, simple_loss=0.2108, pruned_loss=0.0252, over 4846.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02884, over 971030.07 frames.], batch size: 32, lr: 1.32e-04
+2022-05-08 22:40:14,221 INFO [train.py:715] (3/8) Epoch 17, batch 3850, loss[loss=0.1204, simple_loss=0.1891, pruned_loss=0.02587, over 4971.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02909, over 972063.73 frames.], batch size: 35, lr: 1.32e-04
+2022-05-08 22:40:54,282 INFO [train.py:715] (3/8) Epoch 17, batch 3900, loss[loss=0.1465, simple_loss=0.2257, pruned_loss=0.03368, over 4968.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02923, over 971849.39 frames.], batch size: 24, lr: 1.32e-04
+2022-05-08 22:41:35,758 INFO [train.py:715] (3/8) Epoch 17, batch 3950, loss[loss=0.1227, simple_loss=0.1991, pruned_loss=0.02317, over 4739.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02947, over 972273.51 frames.], batch size: 16, lr: 1.32e-04
+2022-05-08 22:42:15,635 INFO [train.py:715] (3/8) Epoch 17, batch 4000, loss[loss=0.1268, simple_loss=0.2048, pruned_loss=0.02439, over 4948.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02926, over 972116.14 frames.], batch size: 21, lr: 1.32e-04
+2022-05-08 22:42:56,133 INFO [train.py:715] (3/8) Epoch 17, batch 4050, loss[loss=0.1556, simple_loss=0.2348, pruned_loss=0.03815, over 4950.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02927, over 972847.85 frames.], batch size: 39, lr: 1.32e-04
+2022-05-08 22:43:36,615 INFO [train.py:715] (3/8) Epoch 17, batch 4100, loss[loss=0.1207, simple_loss=0.1997, pruned_loss=0.02082, over 4828.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02904, over 972955.77 frames.], batch size: 12, lr: 1.32e-04
+2022-05-08 22:44:17,667 INFO [train.py:715] (3/8) Epoch 17, batch 4150, loss[loss=0.1448, simple_loss=0.2118, pruned_loss=0.0389, over 4806.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02937, over 972687.93 frames.], batch size: 14, lr: 1.32e-04
+2022-05-08 22:44:56,903 INFO [train.py:715] (3/8) Epoch 17, batch 4200, loss[loss=0.1311, simple_loss=0.2115, pruned_loss=0.02532, over 4982.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02912, over 972418.82 frames.], batch size: 25, lr: 1.32e-04
+2022-05-08 22:45:36,946 INFO [train.py:715] (3/8) Epoch 17, batch 4250, loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.0309, over 4862.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02937, over 972435.04 frames.], batch size: 20, lr: 1.32e-04
+2022-05-08 22:46:18,118 INFO [train.py:715] (3/8) Epoch 17, batch 4300, loss[loss=0.1279, simple_loss=0.2195, pruned_loss=0.0182, over 4732.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02939, over 973116.43 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 22:46:58,168 INFO [train.py:715] (3/8) Epoch 17, batch 4350, loss[loss=0.123, simple_loss=0.2085, pruned_loss=0.0188, over 4878.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02934, over 973148.53 frames.], batch size: 22, lr: 1.31e-04
+2022-05-08 22:47:38,041 INFO [train.py:715] (3/8) Epoch 17, batch 4400, loss[loss=0.1365, simple_loss=0.2067, pruned_loss=0.03313, over 4968.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02969, over 972901.89 frames.], batch size: 25, lr: 1.31e-04
+2022-05-08 22:48:18,894 INFO [train.py:715] (3/8) Epoch 17, batch 4450, loss[loss=0.1267, simple_loss=0.198, pruned_loss=0.02774, over 4848.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02971, over 973725.85 frames.], batch size: 20, lr: 1.31e-04
+2022-05-08 22:48:59,885 INFO [train.py:715] (3/8) Epoch 17, batch 4500, loss[loss=0.1219, simple_loss=0.2091, pruned_loss=0.01732, over 4766.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02981, over 972943.36 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 22:49:39,759 INFO [train.py:715] (3/8) Epoch 17, batch 4550, loss[loss=0.1318, simple_loss=0.2163, pruned_loss=0.02368, over 4737.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02943, over 972868.07 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 22:50:20,189 INFO [train.py:715] (3/8) Epoch 17, batch 4600, loss[loss=0.1194, simple_loss=0.1994, pruned_loss=0.01968, over 4772.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02909, over 972137.82 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 22:51:01,213 INFO [train.py:715] (3/8) Epoch 17, batch 4650, loss[loss=0.1386, simple_loss=0.2069, pruned_loss=0.03512, over 4849.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02968, over 970928.66 frames.], batch size: 20, lr: 1.31e-04
+2022-05-08 22:51:41,120 INFO [train.py:715] (3/8) Epoch 17, batch 4700, loss[loss=0.1436, simple_loss=0.1983, pruned_loss=0.04441, over 4780.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02944, over 970500.11 frames.], batch size: 12, lr: 1.31e-04
+2022-05-08 22:52:21,064 INFO [train.py:715] (3/8) Epoch 17, batch 4750, loss[loss=0.1242, simple_loss=0.202, pruned_loss=0.0232, over 4935.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02977, over 971035.88 frames.], batch size: 39, lr: 1.31e-04
+2022-05-08 22:53:02,044 INFO [train.py:715] (3/8) Epoch 17, batch 4800, loss[loss=0.1374, simple_loss=0.222, pruned_loss=0.02641, over 4943.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02959, over 971215.31 frames.], batch size: 21, lr: 1.31e-04
+2022-05-08 22:53:42,799 INFO [train.py:715] (3/8) Epoch 17, batch 4850, loss[loss=0.1175, simple_loss=0.1852, pruned_loss=0.02486, over 4874.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02893, over 972141.41 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 22:54:22,666 INFO [train.py:715] (3/8) Epoch 17, batch 4900, loss[loss=0.1189, simple_loss=0.1989, pruned_loss=0.01948, over 4912.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02856, over 973203.60 frames.], batch size: 23, lr: 1.31e-04
+2022-05-08 22:55:03,097 INFO [train.py:715] (3/8) Epoch 17, batch 4950, loss[loss=0.1647, simple_loss=0.2455, pruned_loss=0.04197, over 4791.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02857, over 972333.77 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 22:55:44,143 INFO [train.py:715] (3/8) Epoch 17, batch 5000, loss[loss=0.1317, simple_loss=0.2095, pruned_loss=0.02698, over 4956.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02866, over 972241.74 frames.], batch size: 21, lr: 1.31e-04
+2022-05-08 22:56:24,632 INFO [train.py:715] (3/8) Epoch 17, batch 5050, loss[loss=0.1476, simple_loss=0.2163, pruned_loss=0.03943, over 4923.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.0291, over 972629.49 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 22:57:04,164 INFO [train.py:715] (3/8) Epoch 17, batch 5100, loss[loss=0.1501, simple_loss=0.2182, pruned_loss=0.04097, over 4826.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02935, over 971665.52 frames.], batch size: 26, lr: 1.31e-04
+2022-05-08 22:57:44,985 INFO [train.py:715] (3/8) Epoch 17, batch 5150, loss[loss=0.1194, simple_loss=0.1985, pruned_loss=0.02014, over 4972.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02945, over 972437.15 frames.], batch size: 24, lr: 1.31e-04
+2022-05-08 22:58:26,126 INFO [train.py:715] (3/8) Epoch 17, batch 5200, loss[loss=0.1319, simple_loss=0.1937, pruned_loss=0.03509, over 4816.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2066, pruned_loss=0.0298, over 972469.15 frames.], batch size: 26, lr: 1.31e-04
+2022-05-08 22:59:05,340 INFO [train.py:715] (3/8) Epoch 17, batch 5250, loss[loss=0.1195, simple_loss=0.1886, pruned_loss=0.02517, over 4838.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02886, over 972202.79 frames.], batch size: 26, lr: 1.31e-04
+2022-05-08 22:59:44,889 INFO [train.py:715] (3/8) Epoch 17, batch 5300, loss[loss=0.1114, simple_loss=0.1916, pruned_loss=0.0156, over 4936.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2054, pruned_loss=0.02867, over 971961.81 frames.], batch size: 29, lr: 1.31e-04
+2022-05-08 23:00:25,449 INFO [train.py:715] (3/8) Epoch 17, batch 5350, loss[loss=0.1244, simple_loss=0.2011, pruned_loss=0.02383, over 4982.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02842, over 972544.81 frames.], batch size: 14, lr: 1.31e-04
+2022-05-08 23:01:06,241 INFO [train.py:715] (3/8) Epoch 17, batch 5400, loss[loss=0.1462, simple_loss=0.2181, pruned_loss=0.03712, over 4730.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.0287, over 972470.60 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 23:01:45,350 INFO [train.py:715] (3/8) Epoch 17, batch 5450, loss[loss=0.1298, simple_loss=0.2111, pruned_loss=0.02423, over 4814.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.0286, over 972030.02 frames.], batch size: 25, lr: 1.31e-04
+2022-05-08 23:02:26,550 INFO [train.py:715] (3/8) Epoch 17, batch 5500, loss[loss=0.1581, simple_loss=0.2375, pruned_loss=0.0394, over 4768.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02864, over 971790.46 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 23:03:07,881 INFO [train.py:715] (3/8) Epoch 17, batch 5550, loss[loss=0.1262, simple_loss=0.2102, pruned_loss=0.02111, over 4910.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.0291, over 971363.18 frames.], batch size: 23, lr: 1.31e-04
+2022-05-08 23:03:46,991 INFO [train.py:715] (3/8) Epoch 17, batch 5600, loss[loss=0.1256, simple_loss=0.1952, pruned_loss=0.02797, over 4936.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02955, over 970898.18 frames.], batch size: 23, lr: 1.31e-04
+2022-05-08 23:04:27,249 INFO [train.py:715] (3/8) Epoch 17, batch 5650, loss[loss=0.1314, simple_loss=0.2004, pruned_loss=0.03121, over 4799.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02924, over 971660.79 frames.], batch size: 24, lr: 1.31e-04
+2022-05-08 23:05:08,284 INFO [train.py:715] (3/8) Epoch 17, batch 5700, loss[loss=0.1671, simple_loss=0.2404, pruned_loss=0.04687, over 4876.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2067, pruned_loss=0.02958, over 971605.17 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 23:05:48,476 INFO [train.py:715] (3/8) Epoch 17, batch 5750, loss[loss=0.1489, simple_loss=0.2199, pruned_loss=0.03891, over 4865.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02968, over 971604.59 frames.], batch size: 20, lr: 1.31e-04
+2022-05-08 23:06:27,752 INFO [train.py:715] (3/8) Epoch 17, batch 5800, loss[loss=0.1255, simple_loss=0.1956, pruned_loss=0.02774, over 4708.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02965, over 971689.99 frames.], batch size: 15, lr: 1.31e-04
+2022-05-08 23:07:08,774 INFO [train.py:715] (3/8) Epoch 17, batch 5850, loss[loss=0.1305, simple_loss=0.204, pruned_loss=0.02847, over 4849.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02945, over 972223.11 frames.], batch size: 20, lr: 1.31e-04
+2022-05-08 23:07:49,080 INFO [train.py:715] (3/8) Epoch 17, batch 5900, loss[loss=0.1259, simple_loss=0.1928, pruned_loss=0.02946, over 4776.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02968, over 971994.01 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 23:08:29,709 INFO [train.py:715] (3/8) Epoch 17, batch 5950, loss[loss=0.1208, simple_loss=0.2025, pruned_loss=0.01953, over 4793.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02979, over 972824.19 frames.], batch size: 17, lr: 1.31e-04
+2022-05-08 23:09:09,143 INFO [train.py:715] (3/8) Epoch 17, batch 6000, loss[loss=0.1423, simple_loss=0.2136, pruned_loss=0.03545, over 4931.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02968, over 973164.80 frames.], batch size: 29, lr: 1.31e-04
+2022-05-08 23:09:09,143 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 23:09:23,455 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01069, over 914524.00 frames.
+2022-05-08 23:10:02,836 INFO [train.py:715] (3/8) Epoch 17, batch 6050, loss[loss=0.1184, simple_loss=0.1894, pruned_loss=0.02371, over 4776.00 frames.], tot_loss[loss=0.133, simple_loss=0.2067, pruned_loss=0.02962, over 974035.56 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 23:10:43,309 INFO [train.py:715] (3/8) Epoch 17, batch 6100, loss[loss=0.1239, simple_loss=0.2048, pruned_loss=0.02152, over 4925.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2058, pruned_loss=0.02923, over 972918.61 frames.], batch size: 23, lr: 1.31e-04
+2022-05-08 23:11:22,422 INFO [train.py:715] (3/8) Epoch 17, batch 6150, loss[loss=0.09983, simple_loss=0.1697, pruned_loss=0.01501, over 4845.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02872, over 973167.01 frames.], batch size: 13, lr: 1.31e-04
+2022-05-08 23:12:02,006 INFO [train.py:715] (3/8) Epoch 17, batch 6200, loss[loss=0.1411, simple_loss=0.2108, pruned_loss=0.03572, over 4908.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02885, over 973225.33 frames.], batch size: 19, lr: 1.31e-04
+2022-05-08 23:12:42,482 INFO [train.py:715] (3/8) Epoch 17, batch 6250, loss[loss=0.1041, simple_loss=0.175, pruned_loss=0.01664, over 4830.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.0289, over 972527.65 frames.], batch size: 13, lr: 1.31e-04
+2022-05-08 23:13:22,267 INFO [train.py:715] (3/8) Epoch 17, batch 6300, loss[loss=0.127, simple_loss=0.2015, pruned_loss=0.02624, over 4901.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02931, over 972357.50 frames.], batch size: 17, lr: 1.31e-04
+2022-05-08 23:14:01,680 INFO [train.py:715] (3/8) Epoch 17, batch 6350, loss[loss=0.1225, simple_loss=0.2037, pruned_loss=0.02071, over 4925.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02946, over 972595.65 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 23:14:41,496 INFO [train.py:715] (3/8) Epoch 17, batch 6400, loss[loss=0.09824, simple_loss=0.1641, pruned_loss=0.01622, over 4722.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02955, over 972316.56 frames.], batch size: 12, lr: 1.31e-04
+2022-05-08 23:15:21,778 INFO [train.py:715] (3/8) Epoch 17, batch 6450, loss[loss=0.1196, simple_loss=0.2093, pruned_loss=0.01502, over 4956.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02945, over 972393.91 frames.], batch size: 29, lr: 1.31e-04
+2022-05-08 23:16:01,143 INFO [train.py:715] (3/8) Epoch 17, batch 6500, loss[loss=0.1426, simple_loss=0.2189, pruned_loss=0.03315, over 4908.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02998, over 972160.85 frames.], batch size: 17, lr: 1.31e-04
+2022-05-08 23:16:40,476 INFO [train.py:715] (3/8) Epoch 17, batch 6550, loss[loss=0.1188, simple_loss=0.1959, pruned_loss=0.02089, over 4782.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03013, over 972199.87 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 23:17:20,845 INFO [train.py:715] (3/8) Epoch 17, batch 6600, loss[loss=0.09798, simple_loss=0.1673, pruned_loss=0.01431, over 4771.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02994, over 971772.21 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 23:18:01,038 INFO [train.py:715] (3/8) Epoch 17, batch 6650, loss[loss=0.1773, simple_loss=0.237, pruned_loss=0.05876, over 4830.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02971, over 971452.55 frames.], batch size: 15, lr: 1.31e-04
+2022-05-08 23:18:40,482 INFO [train.py:715] (3/8) Epoch 17, batch 6700, loss[loss=0.1103, simple_loss=0.1858, pruned_loss=0.01742, over 4820.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02968, over 972026.18 frames.], batch size: 26, lr: 1.31e-04
+2022-05-08 23:19:20,728 INFO [train.py:715] (3/8) Epoch 17, batch 6750, loss[loss=0.1644, simple_loss=0.2378, pruned_loss=0.04545, over 4843.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02962, over 972370.63 frames.], batch size: 15, lr: 1.31e-04
+2022-05-08 23:20:00,495 INFO [train.py:715] (3/8) Epoch 17, batch 6800, loss[loss=0.1314, simple_loss=0.2007, pruned_loss=0.0311, over 4933.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02945, over 971929.63 frames.], batch size: 39, lr: 1.31e-04
+2022-05-08 23:20:41,162 INFO [train.py:715] (3/8) Epoch 17, batch 6850, loss[loss=0.1232, simple_loss=0.2064, pruned_loss=0.02, over 4886.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02929, over 971246.30 frames.], batch size: 19, lr: 1.31e-04
+2022-05-08 23:21:20,240 INFO [train.py:715] (3/8) Epoch 17, batch 6900, loss[loss=0.1305, simple_loss=0.2155, pruned_loss=0.02279, over 4933.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02929, over 972249.64 frames.], batch size: 21, lr: 1.31e-04
+2022-05-08 23:22:00,930 INFO [train.py:715] (3/8) Epoch 17, batch 6950, loss[loss=0.1208, simple_loss=0.2011, pruned_loss=0.02029, over 4805.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02921, over 972305.28 frames.], batch size: 21, lr: 1.31e-04
+2022-05-08 23:22:40,663 INFO [train.py:715] (3/8) Epoch 17, batch 7000, loss[loss=0.1425, simple_loss=0.2118, pruned_loss=0.0366, over 4853.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02952, over 972647.45 frames.], batch size: 20, lr: 1.31e-04
+2022-05-08 23:23:20,237 INFO [train.py:715] (3/8) Epoch 17, batch 7050, loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02996, over 4815.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02932, over 971590.69 frames.], batch size: 12, lr: 1.31e-04
+2022-05-08 23:24:00,508 INFO [train.py:715] (3/8) Epoch 17, batch 7100, loss[loss=0.1076, simple_loss=0.1753, pruned_loss=0.01996, over 4858.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02918, over 972239.10 frames.], batch size: 13, lr: 1.31e-04
+2022-05-08 23:24:40,018 INFO [train.py:715] (3/8) Epoch 17, batch 7150, loss[loss=0.163, simple_loss=0.2253, pruned_loss=0.05035, over 4949.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02911, over 972133.74 frames.], batch size: 35, lr: 1.31e-04
+2022-05-08 23:25:19,633 INFO [train.py:715] (3/8) Epoch 17, batch 7200, loss[loss=0.1629, simple_loss=0.2382, pruned_loss=0.04382, over 4806.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02935, over 972157.09 frames.], batch size: 25, lr: 1.31e-04
+2022-05-08 23:25:58,583 INFO [train.py:715] (3/8) Epoch 17, batch 7250, loss[loss=0.1639, simple_loss=0.2303, pruned_loss=0.0488, over 4960.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02931, over 972790.60 frames.], batch size: 35, lr: 1.31e-04
+2022-05-08 23:26:39,073 INFO [train.py:715] (3/8) Epoch 17, batch 7300, loss[loss=0.1256, simple_loss=0.1992, pruned_loss=0.02603, over 4919.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02901, over 972812.91 frames.], batch size: 29, lr: 1.31e-04
+2022-05-08 23:27:18,026 INFO [train.py:715] (3/8) Epoch 17, batch 7350, loss[loss=0.1329, simple_loss=0.2173, pruned_loss=0.0243, over 4940.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.0289, over 972712.66 frames.], batch size: 23, lr: 1.31e-04
+2022-05-08 23:27:56,387 INFO [train.py:715] (3/8) Epoch 17, batch 7400, loss[loss=0.1457, simple_loss=0.2218, pruned_loss=0.03485, over 4734.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02896, over 972719.59 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 23:28:36,427 INFO [train.py:715] (3/8) Epoch 17, batch 7450, loss[loss=0.1487, simple_loss=0.22, pruned_loss=0.03871, over 4858.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02923, over 971667.86 frames.], batch size: 20, lr: 1.31e-04
+2022-05-08 23:29:15,436 INFO [train.py:715] (3/8) Epoch 17, batch 7500, loss[loss=0.1279, simple_loss=0.2093, pruned_loss=0.02328, over 4785.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02893, over 971254.69 frames.], batch size: 21, lr: 1.31e-04
+2022-05-08 23:29:55,165 INFO [train.py:715] (3/8) Epoch 17, batch 7550, loss[loss=0.1295, simple_loss=0.1971, pruned_loss=0.03093, over 4902.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02913, over 972522.88 frames.], batch size: 19, lr: 1.31e-04
+2022-05-08 23:30:34,489 INFO [train.py:715] (3/8) Epoch 17, batch 7600, loss[loss=0.12, simple_loss=0.2016, pruned_loss=0.0192, over 4952.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.0292, over 973276.93 frames.], batch size: 24, lr: 1.31e-04
+2022-05-08 23:31:14,610 INFO [train.py:715] (3/8) Epoch 17, batch 7650, loss[loss=0.1398, simple_loss=0.2247, pruned_loss=0.02749, over 4772.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02921, over 973638.66 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 23:31:54,498 INFO [train.py:715] (3/8) Epoch 17, batch 7700, loss[loss=0.1123, simple_loss=0.183, pruned_loss=0.02082, over 4785.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02924, over 972208.64 frames.], batch size: 14, lr: 1.31e-04
+2022-05-08 23:32:33,790 INFO [train.py:715] (3/8) Epoch 17, batch 7750, loss[loss=0.1561, simple_loss=0.2268, pruned_loss=0.04271, over 4784.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.0294, over 972736.68 frames.], batch size: 17, lr: 1.31e-04
+2022-05-08 23:33:14,388 INFO [train.py:715] (3/8) Epoch 17, batch 7800, loss[loss=0.1192, simple_loss=0.1844, pruned_loss=0.02697, over 4785.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02889, over 972162.87 frames.], batch size: 17, lr: 1.31e-04
+2022-05-08 23:33:54,606 INFO [train.py:715] (3/8) Epoch 17, batch 7850, loss[loss=0.1213, simple_loss=0.2016, pruned_loss=0.02056, over 4953.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02899, over 972666.88 frames.], batch size: 21, lr: 1.31e-04
+2022-05-08 23:34:34,852 INFO [train.py:715] (3/8) Epoch 17, batch 7900, loss[loss=0.1092, simple_loss=0.1857, pruned_loss=0.01632, over 4826.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02942, over 972243.17 frames.], batch size: 27, lr: 1.31e-04
+2022-05-08 23:35:13,816 INFO [train.py:715] (3/8) Epoch 17, batch 7950, loss[loss=0.1527, simple_loss=0.2276, pruned_loss=0.03887, over 4894.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02964, over 972140.18 frames.], batch size: 17, lr: 1.31e-04
+2022-05-08 23:35:53,565 INFO [train.py:715] (3/8) Epoch 17, batch 8000, loss[loss=0.1299, simple_loss=0.2043, pruned_loss=0.02779, over 4685.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.0294, over 971948.93 frames.], batch size: 15, lr: 1.31e-04
+2022-05-08 23:36:33,460 INFO [train.py:715] (3/8) Epoch 17, batch 8050, loss[loss=0.111, simple_loss=0.1895, pruned_loss=0.01624, over 4864.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02937, over 972373.91 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 23:37:12,789 INFO [train.py:715] (3/8) Epoch 17, batch 8100, loss[loss=0.1369, simple_loss=0.2165, pruned_loss=0.02863, over 4973.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02897, over 972419.01 frames.], batch size: 24, lr: 1.31e-04
+2022-05-08 23:37:52,689 INFO [train.py:715] (3/8) Epoch 17, batch 8150, loss[loss=0.1314, simple_loss=0.2122, pruned_loss=0.0253, over 4819.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.02897, over 972189.80 frames.], batch size: 25, lr: 1.31e-04
+2022-05-08 23:38:32,362 INFO [train.py:715] (3/8) Epoch 17, batch 8200, loss[loss=0.1307, simple_loss=0.2074, pruned_loss=0.02706, over 4789.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02923, over 971844.43 frames.], batch size: 12, lr: 1.31e-04
+2022-05-08 23:39:14,692 INFO [train.py:715] (3/8) Epoch 17, batch 8250, loss[loss=0.1432, simple_loss=0.2221, pruned_loss=0.03215, over 4825.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02928, over 972442.06 frames.], batch size: 13, lr: 1.31e-04
+2022-05-08 23:39:53,904 INFO [train.py:715] (3/8) Epoch 17, batch 8300, loss[loss=0.1201, simple_loss=0.2058, pruned_loss=0.01724, over 4943.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02879, over 972325.55 frames.], batch size: 21, lr: 1.31e-04
+2022-05-08 23:40:33,623 INFO [train.py:715] (3/8) Epoch 17, batch 8350, loss[loss=0.1754, simple_loss=0.2441, pruned_loss=0.05337, over 4833.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02917, over 972235.14 frames.], batch size: 15, lr: 1.31e-04
+2022-05-08 23:41:13,219 INFO [train.py:715] (3/8) Epoch 17, batch 8400, loss[loss=0.1266, simple_loss=0.2062, pruned_loss=0.02349, over 4994.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02865, over 972693.58 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 23:41:52,765 INFO [train.py:715] (3/8) Epoch 17, batch 8450, loss[loss=0.1362, simple_loss=0.2108, pruned_loss=0.03079, over 4909.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2062, pruned_loss=0.0281, over 972491.96 frames.], batch size: 23, lr: 1.31e-04
+2022-05-08 23:42:32,333 INFO [train.py:715] (3/8) Epoch 17, batch 8500, loss[loss=0.1232, simple_loss=0.1942, pruned_loss=0.02607, over 4817.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02835, over 973418.82 frames.], batch size: 15, lr: 1.31e-04
+2022-05-08 23:43:12,147 INFO [train.py:715] (3/8) Epoch 17, batch 8550, loss[loss=0.1165, simple_loss=0.1875, pruned_loss=0.02273, over 4847.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02905, over 972955.69 frames.], batch size: 30, lr: 1.31e-04
+2022-05-08 23:43:52,012 INFO [train.py:715] (3/8) Epoch 17, batch 8600, loss[loss=0.1777, simple_loss=0.2466, pruned_loss=0.05437, over 4875.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02935, over 972747.54 frames.], batch size: 39, lr: 1.31e-04
+2022-05-08 23:44:31,015 INFO [train.py:715] (3/8) Epoch 17, batch 8650, loss[loss=0.1043, simple_loss=0.1687, pruned_loss=0.02, over 4811.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02894, over 972328.29 frames.], batch size: 12, lr: 1.31e-04
+2022-05-08 23:45:10,885 INFO [train.py:715] (3/8) Epoch 17, batch 8700, loss[loss=0.1267, simple_loss=0.198, pruned_loss=0.02768, over 4871.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02939, over 972390.63 frames.], batch size: 12, lr: 1.31e-04
+2022-05-08 23:45:50,295 INFO [train.py:715] (3/8) Epoch 17, batch 8750, loss[loss=0.1246, simple_loss=0.2091, pruned_loss=0.0201, over 4989.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02951, over 972821.08 frames.], batch size: 25, lr: 1.31e-04
+2022-05-08 23:46:29,856 INFO [train.py:715] (3/8) Epoch 17, batch 8800, loss[loss=0.1398, simple_loss=0.2112, pruned_loss=0.03417, over 4744.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02958, over 972203.68 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 23:47:09,592 INFO [train.py:715] (3/8) Epoch 17, batch 8850, loss[loss=0.1465, simple_loss=0.2141, pruned_loss=0.03945, over 4807.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02945, over 972007.97 frames.], batch size: 21, lr: 1.31e-04
+2022-05-08 23:47:48,801 INFO [train.py:715] (3/8) Epoch 17, batch 8900, loss[loss=0.1529, simple_loss=0.2272, pruned_loss=0.03932, over 4918.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02944, over 972135.93 frames.], batch size: 19, lr: 1.31e-04
+2022-05-08 23:48:28,445 INFO [train.py:715] (3/8) Epoch 17, batch 8950, loss[loss=0.1571, simple_loss=0.2296, pruned_loss=0.04232, over 4795.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.0294, over 971385.17 frames.], batch size: 21, lr: 1.31e-04
+2022-05-08 23:49:07,470 INFO [train.py:715] (3/8) Epoch 17, batch 9000, loss[loss=0.1088, simple_loss=0.1774, pruned_loss=0.02013, over 4793.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02925, over 971677.05 frames.], batch size: 12, lr: 1.31e-04
+2022-05-08 23:49:07,470 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-08 23:49:17,246 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1048, simple_loss=0.1882, pruned_loss=0.01072, over 914524.00 frames.
+2022-05-08 23:49:56,411 INFO [train.py:715] (3/8) Epoch 17, batch 9050, loss[loss=0.1633, simple_loss=0.2535, pruned_loss=0.03656, over 4967.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2068, pruned_loss=0.02972, over 971971.82 frames.], batch size: 24, lr: 1.31e-04
+2022-05-08 23:50:36,246 INFO [train.py:715] (3/8) Epoch 17, batch 9100, loss[loss=0.1335, simple_loss=0.2149, pruned_loss=0.02601, over 4931.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02929, over 971636.91 frames.], batch size: 29, lr: 1.31e-04
+2022-05-08 23:51:15,867 INFO [train.py:715] (3/8) Epoch 17, batch 9150, loss[loss=0.1319, simple_loss=0.2083, pruned_loss=0.02775, over 4867.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.0291, over 971459.50 frames.], batch size: 20, lr: 1.31e-04
+2022-05-08 23:51:54,747 INFO [train.py:715] (3/8) Epoch 17, batch 9200, loss[loss=0.1503, simple_loss=0.2182, pruned_loss=0.04119, over 4929.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02924, over 971592.47 frames.], batch size: 35, lr: 1.31e-04
+2022-05-08 23:52:34,933 INFO [train.py:715] (3/8) Epoch 17, batch 9250, loss[loss=0.1436, simple_loss=0.22, pruned_loss=0.03362, over 4812.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02906, over 971076.91 frames.], batch size: 26, lr: 1.31e-04
+2022-05-08 23:53:14,616 INFO [train.py:715] (3/8) Epoch 17, batch 9300, loss[loss=0.145, simple_loss=0.2259, pruned_loss=0.03204, over 4943.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02962, over 971174.32 frames.], batch size: 21, lr: 1.31e-04
+2022-05-08 23:53:53,952 INFO [train.py:715] (3/8) Epoch 17, batch 9350, loss[loss=0.1318, simple_loss=0.1985, pruned_loss=0.03257, over 4759.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02957, over 971202.47 frames.], batch size: 19, lr: 1.31e-04
+2022-05-08 23:54:33,280 INFO [train.py:715] (3/8) Epoch 17, batch 9400, loss[loss=0.1166, simple_loss=0.1806, pruned_loss=0.02623, over 4764.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02969, over 970884.38 frames.], batch size: 19, lr: 1.31e-04
+2022-05-08 23:55:13,701 INFO [train.py:715] (3/8) Epoch 17, batch 9450, loss[loss=0.1327, simple_loss=0.2086, pruned_loss=0.02844, over 4857.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02919, over 971325.24 frames.], batch size: 20, lr: 1.31e-04
+2022-05-08 23:55:53,693 INFO [train.py:715] (3/8) Epoch 17, batch 9500, loss[loss=0.1292, simple_loss=0.194, pruned_loss=0.03218, over 4769.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02948, over 971031.03 frames.], batch size: 12, lr: 1.31e-04
+2022-05-08 23:56:32,926 INFO [train.py:715] (3/8) Epoch 17, batch 9550, loss[loss=0.1374, simple_loss=0.2213, pruned_loss=0.02672, over 4883.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.0293, over 971747.18 frames.], batch size: 22, lr: 1.31e-04
+2022-05-08 23:57:12,481 INFO [train.py:715] (3/8) Epoch 17, batch 9600, loss[loss=0.1301, simple_loss=0.2108, pruned_loss=0.02469, over 4929.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.0296, over 971244.14 frames.], batch size: 23, lr: 1.31e-04
+2022-05-08 23:57:52,761 INFO [train.py:715] (3/8) Epoch 17, batch 9650, loss[loss=0.1329, simple_loss=0.212, pruned_loss=0.02694, over 4785.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02981, over 971728.40 frames.], batch size: 18, lr: 1.31e-04
+2022-05-08 23:58:31,950 INFO [train.py:715] (3/8) Epoch 17, batch 9700, loss[loss=0.152, simple_loss=0.2181, pruned_loss=0.04299, over 4860.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02979, over 970674.50 frames.], batch size: 16, lr: 1.31e-04
+2022-05-08 23:59:11,718 INFO [train.py:715] (3/8) Epoch 17, batch 9750, loss[loss=0.1165, simple_loss=0.1964, pruned_loss=0.0183, over 4929.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02927, over 971091.42 frames.], batch size: 23, lr: 1.31e-04
+2022-05-08 23:59:51,459 INFO [train.py:715] (3/8) Epoch 17, batch 9800, loss[loss=0.1252, simple_loss=0.1955, pruned_loss=0.02739, over 4983.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02931, over 971144.92 frames.], batch size: 33, lr: 1.31e-04
+2022-05-09 00:00:31,044 INFO [train.py:715] (3/8) Epoch 17, batch 9850, loss[loss=0.1277, simple_loss=0.2062, pruned_loss=0.0246, over 4842.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02975, over 971917.17 frames.], batch size: 15, lr: 1.31e-04
+2022-05-09 00:01:10,443 INFO [train.py:715] (3/8) Epoch 17, batch 9900, loss[loss=0.132, simple_loss=0.2045, pruned_loss=0.02976, over 4959.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02958, over 972727.79 frames.], batch size: 24, lr: 1.31e-04
+2022-05-09 00:01:49,848 INFO [train.py:715] (3/8) Epoch 17, batch 9950, loss[loss=0.1323, simple_loss=0.2057, pruned_loss=0.02944, over 4860.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02939, over 972587.40 frames.], batch size: 20, lr: 1.31e-04
+2022-05-09 00:02:30,140 INFO [train.py:715] (3/8) Epoch 17, batch 10000, loss[loss=0.113, simple_loss=0.1958, pruned_loss=0.01514, over 4950.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02922, over 971956.76 frames.], batch size: 21, lr: 1.31e-04
+2022-05-09 00:03:09,390 INFO [train.py:715] (3/8) Epoch 17, batch 10050, loss[loss=0.1162, simple_loss=0.189, pruned_loss=0.02171, over 4929.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02946, over 972270.59 frames.], batch size: 18, lr: 1.31e-04
+2022-05-09 00:03:48,276 INFO [train.py:715] (3/8) Epoch 17, batch 10100, loss[loss=0.1717, simple_loss=0.23, pruned_loss=0.05667, over 4860.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02952, over 972083.05 frames.], batch size: 32, lr: 1.31e-04
+2022-05-09 00:04:27,593 INFO [train.py:715] (3/8) Epoch 17, batch 10150, loss[loss=0.1628, simple_loss=0.2271, pruned_loss=0.04921, over 4897.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02922, over 971765.21 frames.], batch size: 39, lr: 1.31e-04
+2022-05-09 00:05:06,927 INFO [train.py:715] (3/8) Epoch 17, batch 10200, loss[loss=0.1288, simple_loss=0.2054, pruned_loss=0.02611, over 4830.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02862, over 971488.68 frames.], batch size: 15, lr: 1.31e-04
+2022-05-09 00:05:44,871 INFO [train.py:715] (3/8) Epoch 17, batch 10250, loss[loss=0.1452, simple_loss=0.2214, pruned_loss=0.03453, over 4908.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02864, over 972336.13 frames.], batch size: 17, lr: 1.31e-04
+2022-05-09 00:06:24,647 INFO [train.py:715] (3/8) Epoch 17, batch 10300, loss[loss=0.1136, simple_loss=0.1913, pruned_loss=0.01795, over 4814.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02884, over 972359.49 frames.], batch size: 27, lr: 1.31e-04
+2022-05-09 00:07:04,572 INFO [train.py:715] (3/8) Epoch 17, batch 10350, loss[loss=0.1433, simple_loss=0.2214, pruned_loss=0.03261, over 4895.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02913, over 972330.70 frames.], batch size: 22, lr: 1.31e-04
+2022-05-09 00:07:43,243 INFO [train.py:715] (3/8) Epoch 17, batch 10400, loss[loss=0.1593, simple_loss=0.2309, pruned_loss=0.04384, over 4823.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2083, pruned_loss=0.02949, over 973073.94 frames.], batch size: 15, lr: 1.31e-04
+2022-05-09 00:08:22,343 INFO [train.py:715] (3/8) Epoch 17, batch 10450, loss[loss=0.1489, simple_loss=0.2169, pruned_loss=0.04044, over 4925.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02931, over 972883.98 frames.], batch size: 21, lr: 1.31e-04
+2022-05-09 00:09:02,375 INFO [train.py:715] (3/8) Epoch 17, batch 10500, loss[loss=0.1097, simple_loss=0.1819, pruned_loss=0.01877, over 4823.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02905, over 973158.53 frames.], batch size: 27, lr: 1.31e-04
+2022-05-09 00:09:41,413 INFO [train.py:715] (3/8) Epoch 17, batch 10550, loss[loss=0.1217, simple_loss=0.1983, pruned_loss=0.02255, over 4790.00 frames.], tot_loss[loss=0.1333, simple_loss=0.208, pruned_loss=0.02929, over 972723.11 frames.], batch size: 14, lr: 1.31e-04
+2022-05-09 00:10:19,760 INFO [train.py:715] (3/8) Epoch 17, batch 10600, loss[loss=0.1079, simple_loss=0.1752, pruned_loss=0.02031, over 4821.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.029, over 972869.24 frames.], batch size: 26, lr: 1.31e-04
+2022-05-09 00:10:59,065 INFO [train.py:715] (3/8) Epoch 17, batch 10650, loss[loss=0.1375, simple_loss=0.2209, pruned_loss=0.02702, over 4777.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02879, over 972197.17 frames.], batch size: 18, lr: 1.31e-04
+2022-05-09 00:11:38,577 INFO [train.py:715] (3/8) Epoch 17, batch 10700, loss[loss=0.1659, simple_loss=0.2432, pruned_loss=0.04433, over 4867.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02934, over 971803.07 frames.], batch size: 32, lr: 1.31e-04
+2022-05-09 00:12:17,257 INFO [train.py:715] (3/8) Epoch 17, batch 10750, loss[loss=0.1423, simple_loss=0.2056, pruned_loss=0.03947, over 4920.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02963, over 972441.00 frames.], batch size: 23, lr: 1.31e-04
+2022-05-09 00:12:56,255 INFO [train.py:715] (3/8) Epoch 17, batch 10800, loss[loss=0.1224, simple_loss=0.1941, pruned_loss=0.02535, over 4936.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02908, over 972598.07 frames.], batch size: 21, lr: 1.31e-04
+2022-05-09 00:13:36,022 INFO [train.py:715] (3/8) Epoch 17, batch 10850, loss[loss=0.1002, simple_loss=0.1713, pruned_loss=0.01461, over 4773.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02936, over 972558.87 frames.], batch size: 12, lr: 1.31e-04
+2022-05-09 00:14:15,589 INFO [train.py:715] (3/8) Epoch 17, batch 10900, loss[loss=0.1278, simple_loss=0.2019, pruned_loss=0.02687, over 4912.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02941, over 972585.62 frames.], batch size: 29, lr: 1.31e-04
+2022-05-09 00:14:53,759 INFO [train.py:715] (3/8) Epoch 17, batch 10950, loss[loss=0.1286, simple_loss=0.1973, pruned_loss=0.02995, over 4894.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02992, over 973068.58 frames.], batch size: 22, lr: 1.31e-04
+2022-05-09 00:15:33,875 INFO [train.py:715] (3/8) Epoch 17, batch 11000, loss[loss=0.1075, simple_loss=0.1666, pruned_loss=0.0242, over 4828.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2082, pruned_loss=0.02929, over 973505.32 frames.], batch size: 12, lr: 1.31e-04
+2022-05-09 00:16:13,746 INFO [train.py:715] (3/8) Epoch 17, batch 11050, loss[loss=0.1539, simple_loss=0.2205, pruned_loss=0.04363, over 4755.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02925, over 972807.25 frames.], batch size: 16, lr: 1.31e-04
+2022-05-09 00:16:52,425 INFO [train.py:715] (3/8) Epoch 17, batch 11100, loss[loss=0.1206, simple_loss=0.2047, pruned_loss=0.01819, over 4898.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02905, over 972944.76 frames.], batch size: 22, lr: 1.31e-04
+2022-05-09 00:17:31,480 INFO [train.py:715] (3/8) Epoch 17, batch 11150, loss[loss=0.1148, simple_loss=0.1957, pruned_loss=0.01693, over 4826.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02884, over 972567.70 frames.], batch size: 27, lr: 1.31e-04
+2022-05-09 00:18:11,487 INFO [train.py:715] (3/8) Epoch 17, batch 11200, loss[loss=0.1385, simple_loss=0.2145, pruned_loss=0.0313, over 4812.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02875, over 972743.22 frames.], batch size: 21, lr: 1.31e-04
+2022-05-09 00:18:51,602 INFO [train.py:715] (3/8) Epoch 17, batch 11250, loss[loss=0.1165, simple_loss=0.1867, pruned_loss=0.02311, over 4757.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02862, over 972308.58 frames.], batch size: 19, lr: 1.31e-04
+2022-05-09 00:19:29,832 INFO [train.py:715] (3/8) Epoch 17, batch 11300, loss[loss=0.1261, simple_loss=0.1936, pruned_loss=0.0293, over 4690.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02893, over 971758.19 frames.], batch size: 15, lr: 1.31e-04
+2022-05-09 00:20:09,301 INFO [train.py:715] (3/8) Epoch 17, batch 11350, loss[loss=0.0981, simple_loss=0.1665, pruned_loss=0.01487, over 4849.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.029, over 972921.43 frames.], batch size: 32, lr: 1.31e-04
+2022-05-09 00:20:49,488 INFO [train.py:715] (3/8) Epoch 17, batch 11400, loss[loss=0.1191, simple_loss=0.1925, pruned_loss=0.02289, over 4861.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.0292, over 972706.51 frames.], batch size: 16, lr: 1.31e-04
+2022-05-09 00:21:28,497 INFO [train.py:715] (3/8) Epoch 17, batch 11450, loss[loss=0.1172, simple_loss=0.1779, pruned_loss=0.0283, over 4856.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02925, over 972639.72 frames.], batch size: 13, lr: 1.31e-04
+2022-05-09 00:22:07,511 INFO [train.py:715] (3/8) Epoch 17, batch 11500, loss[loss=0.1305, simple_loss=0.2052, pruned_loss=0.02793, over 4778.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2062, pruned_loss=0.02933, over 972729.58 frames.], batch size: 18, lr: 1.31e-04
+2022-05-09 00:22:47,221 INFO [train.py:715] (3/8) Epoch 17, batch 11550, loss[loss=0.1305, simple_loss=0.2019, pruned_loss=0.02955, over 4979.00 frames.], tot_loss[loss=0.1321, simple_loss=0.206, pruned_loss=0.02912, over 972574.91 frames.], batch size: 35, lr: 1.31e-04
+2022-05-09 00:23:27,160 INFO [train.py:715] (3/8) Epoch 17, batch 11600, loss[loss=0.1578, simple_loss=0.2312, pruned_loss=0.04225, over 4809.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02872, over 971662.70 frames.], batch size: 15, lr: 1.31e-04
+2022-05-09 00:24:05,129 INFO [train.py:715] (3/8) Epoch 17, batch 11650, loss[loss=0.1249, simple_loss=0.2044, pruned_loss=0.02275, over 4823.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02855, over 971425.65 frames.], batch size: 15, lr: 1.31e-04
+2022-05-09 00:24:44,953 INFO [train.py:715] (3/8) Epoch 17, batch 11700, loss[loss=0.1352, simple_loss=0.2075, pruned_loss=0.03146, over 4798.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02896, over 970926.33 frames.], batch size: 21, lr: 1.31e-04
+2022-05-09 00:25:24,935 INFO [train.py:715] (3/8) Epoch 17, batch 11750, loss[loss=0.1474, simple_loss=0.2164, pruned_loss=0.03922, over 4890.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02908, over 970302.56 frames.], batch size: 19, lr: 1.31e-04
+2022-05-09 00:26:03,878 INFO [train.py:715] (3/8) Epoch 17, batch 11800, loss[loss=0.1284, simple_loss=0.2012, pruned_loss=0.02777, over 4909.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02898, over 971445.37 frames.], batch size: 39, lr: 1.31e-04
+2022-05-09 00:26:42,876 INFO [train.py:715] (3/8) Epoch 17, batch 11850, loss[loss=0.1173, simple_loss=0.1826, pruned_loss=0.02597, over 4782.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02884, over 971899.44 frames.], batch size: 14, lr: 1.31e-04
+2022-05-09 00:27:22,146 INFO [train.py:715] (3/8) Epoch 17, batch 11900, loss[loss=0.1289, simple_loss=0.2067, pruned_loss=0.02558, over 4847.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.02895, over 971958.88 frames.], batch size: 32, lr: 1.31e-04
+2022-05-09 00:28:01,949 INFO [train.py:715] (3/8) Epoch 17, batch 11950, loss[loss=0.1416, simple_loss=0.2245, pruned_loss=0.02936, over 4985.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2053, pruned_loss=0.02885, over 971930.22 frames.], batch size: 25, lr: 1.31e-04
+2022-05-09 00:28:40,962 INFO [train.py:715] (3/8) Epoch 17, batch 12000, loss[loss=0.1284, simple_loss=0.1944, pruned_loss=0.0312, over 4940.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2054, pruned_loss=0.02884, over 972273.88 frames.], batch size: 21, lr: 1.31e-04
+2022-05-09 00:28:40,963 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 00:28:52,718 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1048, simple_loss=0.1882, pruned_loss=0.0107, over 914524.00 frames.
+2022-05-09 00:29:31,827 INFO [train.py:715] (3/8) Epoch 17, batch 12050, loss[loss=0.1743, simple_loss=0.2413, pruned_loss=0.05368, over 4851.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.0285, over 972544.96 frames.], batch size: 32, lr: 1.31e-04
+2022-05-09 00:30:10,919 INFO [train.py:715] (3/8) Epoch 17, batch 12100, loss[loss=0.1244, simple_loss=0.2055, pruned_loss=0.02165, over 4930.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02888, over 973339.55 frames.], batch size: 23, lr: 1.31e-04
+2022-05-09 00:30:50,930 INFO [train.py:715] (3/8) Epoch 17, batch 12150, loss[loss=0.1186, simple_loss=0.1898, pruned_loss=0.02369, over 4985.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02913, over 972705.30 frames.], batch size: 28, lr: 1.31e-04
+2022-05-09 00:31:29,660 INFO [train.py:715] (3/8) Epoch 17, batch 12200, loss[loss=0.1195, simple_loss=0.1965, pruned_loss=0.02124, over 4906.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02942, over 971433.12 frames.], batch size: 19, lr: 1.31e-04
+2022-05-09 00:32:08,194 INFO [train.py:715] (3/8) Epoch 17, batch 12250, loss[loss=0.1196, simple_loss=0.1974, pruned_loss=0.02092, over 4850.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02956, over 971873.70 frames.], batch size: 20, lr: 1.31e-04
+2022-05-09 00:32:47,684 INFO [train.py:715] (3/8) Epoch 17, batch 12300, loss[loss=0.1172, simple_loss=0.1814, pruned_loss=0.02648, over 4852.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.0293, over 971904.79 frames.], batch size: 13, lr: 1.31e-04
+2022-05-09 00:33:26,860 INFO [train.py:715] (3/8) Epoch 17, batch 12350, loss[loss=0.1324, simple_loss=0.1998, pruned_loss=0.03245, over 4845.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02943, over 971063.32 frames.], batch size: 30, lr: 1.31e-04
+2022-05-09 00:34:05,565 INFO [train.py:715] (3/8) Epoch 17, batch 12400, loss[loss=0.1838, simple_loss=0.2547, pruned_loss=0.05647, over 4927.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02954, over 971058.29 frames.], batch size: 23, lr: 1.31e-04
+2022-05-09 00:34:44,617 INFO [train.py:715] (3/8) Epoch 17, batch 12450, loss[loss=0.1448, simple_loss=0.2248, pruned_loss=0.03244, over 4906.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02947, over 971564.34 frames.], batch size: 17, lr: 1.31e-04
+2022-05-09 00:35:24,996 INFO [train.py:715] (3/8) Epoch 17, batch 12500, loss[loss=0.1329, simple_loss=0.21, pruned_loss=0.02792, over 4941.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02949, over 971722.05 frames.], batch size: 39, lr: 1.31e-04
+2022-05-09 00:36:03,578 INFO [train.py:715] (3/8) Epoch 17, batch 12550, loss[loss=0.1258, simple_loss=0.2029, pruned_loss=0.02435, over 4818.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02939, over 972123.76 frames.], batch size: 26, lr: 1.31e-04
+2022-05-09 00:36:42,927 INFO [train.py:715] (3/8) Epoch 17, batch 12600, loss[loss=0.117, simple_loss=0.1913, pruned_loss=0.02132, over 4985.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02949, over 973098.05 frames.], batch size: 25, lr: 1.31e-04
+2022-05-09 00:37:22,862 INFO [train.py:715] (3/8) Epoch 17, batch 12650, loss[loss=0.1158, simple_loss=0.1873, pruned_loss=0.02215, over 4802.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02957, over 973193.04 frames.], batch size: 21, lr: 1.31e-04
+2022-05-09 00:38:02,852 INFO [train.py:715] (3/8) Epoch 17, batch 12700, loss[loss=0.1286, simple_loss=0.2056, pruned_loss=0.02576, over 4971.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.0299, over 972587.15 frames.], batch size: 24, lr: 1.31e-04
+2022-05-09 00:38:42,160 INFO [train.py:715] (3/8) Epoch 17, batch 12750, loss[loss=0.1519, simple_loss=0.237, pruned_loss=0.03338, over 4748.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02962, over 973156.31 frames.], batch size: 19, lr: 1.31e-04
+2022-05-09 00:39:20,963 INFO [train.py:715] (3/8) Epoch 17, batch 12800, loss[loss=0.1536, simple_loss=0.2307, pruned_loss=0.03826, over 4872.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02974, over 973239.91 frames.], batch size: 22, lr: 1.31e-04
+2022-05-09 00:40:00,598 INFO [train.py:715] (3/8) Epoch 17, batch 12850, loss[loss=0.1286, simple_loss=0.2059, pruned_loss=0.02568, over 4812.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02966, over 972648.88 frames.], batch size: 25, lr: 1.31e-04
+2022-05-09 00:40:39,040 INFO [train.py:715] (3/8) Epoch 17, batch 12900, loss[loss=0.1205, simple_loss=0.1909, pruned_loss=0.02505, over 4815.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02898, over 971484.00 frames.], batch size: 13, lr: 1.31e-04
+2022-05-09 00:41:18,425 INFO [train.py:715] (3/8) Epoch 17, batch 12950, loss[loss=0.1579, simple_loss=0.2265, pruned_loss=0.04466, over 4830.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02873, over 971647.77 frames.], batch size: 30, lr: 1.31e-04
+2022-05-09 00:41:57,022 INFO [train.py:715] (3/8) Epoch 17, batch 13000, loss[loss=0.1356, simple_loss=0.212, pruned_loss=0.02955, over 4846.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02876, over 971460.68 frames.], batch size: 13, lr: 1.31e-04
+2022-05-09 00:42:36,102 INFO [train.py:715] (3/8) Epoch 17, batch 13050, loss[loss=0.134, simple_loss=0.2224, pruned_loss=0.0228, over 4857.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02888, over 971505.18 frames.], batch size: 20, lr: 1.31e-04
+2022-05-09 00:43:15,223 INFO [train.py:715] (3/8) Epoch 17, batch 13100, loss[loss=0.1125, simple_loss=0.1866, pruned_loss=0.01916, over 4927.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.029, over 970932.58 frames.], batch size: 23, lr: 1.31e-04
+2022-05-09 00:43:54,022 INFO [train.py:715] (3/8) Epoch 17, batch 13150, loss[loss=0.1198, simple_loss=0.1912, pruned_loss=0.02423, over 4823.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02959, over 970702.63 frames.], batch size: 26, lr: 1.31e-04
+2022-05-09 00:44:33,796 INFO [train.py:715] (3/8) Epoch 17, batch 13200, loss[loss=0.1303, simple_loss=0.1952, pruned_loss=0.03268, over 4809.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02953, over 970760.99 frames.], batch size: 12, lr: 1.31e-04
+2022-05-09 00:45:12,322 INFO [train.py:715] (3/8) Epoch 17, batch 13250, loss[loss=0.1368, simple_loss=0.2063, pruned_loss=0.03366, over 4976.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02939, over 971606.10 frames.], batch size: 39, lr: 1.31e-04
+2022-05-09 00:45:51,624 INFO [train.py:715] (3/8) Epoch 17, batch 13300, loss[loss=0.124, simple_loss=0.1958, pruned_loss=0.02609, over 4941.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2053, pruned_loss=0.0291, over 971832.71 frames.], batch size: 23, lr: 1.31e-04
+2022-05-09 00:46:30,709 INFO [train.py:715] (3/8) Epoch 17, batch 13350, loss[loss=0.1075, simple_loss=0.1757, pruned_loss=0.01959, over 4870.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2048, pruned_loss=0.02882, over 971323.06 frames.], batch size: 12, lr: 1.31e-04
+2022-05-09 00:47:09,939 INFO [train.py:715] (3/8) Epoch 17, batch 13400, loss[loss=0.1288, simple_loss=0.1978, pruned_loss=0.0299, over 4976.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2052, pruned_loss=0.02916, over 971499.93 frames.], batch size: 14, lr: 1.31e-04
+2022-05-09 00:47:49,249 INFO [train.py:715] (3/8) Epoch 17, batch 13450, loss[loss=0.119, simple_loss=0.1935, pruned_loss=0.02227, over 4841.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2057, pruned_loss=0.02945, over 971932.33 frames.], batch size: 30, lr: 1.30e-04
+2022-05-09 00:48:27,711 INFO [train.py:715] (3/8) Epoch 17, batch 13500, loss[loss=0.1288, simple_loss=0.2049, pruned_loss=0.02638, over 4981.00 frames.], tot_loss[loss=0.1324, simple_loss=0.206, pruned_loss=0.02942, over 972905.24 frames.], batch size: 27, lr: 1.30e-04
+2022-05-09 00:49:07,421 INFO [train.py:715] (3/8) Epoch 17, batch 13550, loss[loss=0.1228, simple_loss=0.2009, pruned_loss=0.02238, over 4826.00 frames.], tot_loss[loss=0.1323, simple_loss=0.206, pruned_loss=0.02933, over 973251.54 frames.], batch size: 27, lr: 1.30e-04
+2022-05-09 00:49:45,776 INFO [train.py:715] (3/8) Epoch 17, batch 13600, loss[loss=0.1338, simple_loss=0.2056, pruned_loss=0.03097, over 4928.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02959, over 972984.24 frames.], batch size: 21, lr: 1.30e-04
+2022-05-09 00:50:24,816 INFO [train.py:715] (3/8) Epoch 17, batch 13650, loss[loss=0.09879, simple_loss=0.1712, pruned_loss=0.01317, over 4783.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03009, over 972722.41 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 00:51:04,639 INFO [train.py:715] (3/8) Epoch 17, batch 13700, loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03154, over 4968.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02968, over 973330.31 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 00:51:43,956 INFO [train.py:715] (3/8) Epoch 17, batch 13750, loss[loss=0.1728, simple_loss=0.2556, pruned_loss=0.04499, over 4738.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02956, over 973063.85 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 00:52:24,097 INFO [train.py:715] (3/8) Epoch 17, batch 13800, loss[loss=0.1241, simple_loss=0.2039, pruned_loss=0.02212, over 4811.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.0297, over 973331.33 frames.], batch size: 26, lr: 1.30e-04
+2022-05-09 00:53:03,508 INFO [train.py:715] (3/8) Epoch 17, batch 13850, loss[loss=0.1614, simple_loss=0.2378, pruned_loss=0.04247, over 4846.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.03, over 972700.71 frames.], batch size: 20, lr: 1.30e-04
+2022-05-09 00:53:43,318 INFO [train.py:715] (3/8) Epoch 17, batch 13900, loss[loss=0.1455, simple_loss=0.2127, pruned_loss=0.03914, over 4872.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02966, over 972153.34 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 00:54:22,806 INFO [train.py:715] (3/8) Epoch 17, batch 13950, loss[loss=0.1476, simple_loss=0.2264, pruned_loss=0.03446, over 4748.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02956, over 972549.25 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 00:55:02,839 INFO [train.py:715] (3/8) Epoch 17, batch 14000, loss[loss=0.1469, simple_loss=0.225, pruned_loss=0.03443, over 4896.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02963, over 972280.68 frames.], batch size: 22, lr: 1.30e-04
+2022-05-09 00:55:42,003 INFO [train.py:715] (3/8) Epoch 17, batch 14050, loss[loss=0.1585, simple_loss=0.2257, pruned_loss=0.04568, over 4831.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02976, over 971406.01 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 00:56:21,073 INFO [train.py:715] (3/8) Epoch 17, batch 14100, loss[loss=0.1432, simple_loss=0.2127, pruned_loss=0.03682, over 4962.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03013, over 971404.35 frames.], batch size: 31, lr: 1.30e-04
+2022-05-09 00:57:01,246 INFO [train.py:715] (3/8) Epoch 17, batch 14150, loss[loss=0.1275, simple_loss=0.2065, pruned_loss=0.0243, over 4817.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02942, over 972327.52 frames.], batch size: 21, lr: 1.30e-04
+2022-05-09 00:57:40,319 INFO [train.py:715] (3/8) Epoch 17, batch 14200, loss[loss=0.1232, simple_loss=0.1963, pruned_loss=0.02502, over 4783.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02952, over 971321.31 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 00:58:19,830 INFO [train.py:715] (3/8) Epoch 17, batch 14250, loss[loss=0.132, simple_loss=0.2025, pruned_loss=0.03073, over 4820.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02993, over 971264.77 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 00:58:58,999 INFO [train.py:715] (3/8) Epoch 17, batch 14300, loss[loss=0.1286, simple_loss=0.2048, pruned_loss=0.02623, over 4933.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.0302, over 970530.32 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 00:59:38,854 INFO [train.py:715] (3/8) Epoch 17, batch 14350, loss[loss=0.1328, simple_loss=0.2111, pruned_loss=0.02728, over 4953.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02984, over 971193.92 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 01:00:17,888 INFO [train.py:715] (3/8) Epoch 17, batch 14400, loss[loss=0.164, simple_loss=0.2329, pruned_loss=0.04754, over 4750.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02992, over 972343.48 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 01:00:56,578 INFO [train.py:715] (3/8) Epoch 17, batch 14450, loss[loss=0.11, simple_loss=0.188, pruned_loss=0.01595, over 4987.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02976, over 972159.78 frames.], batch size: 25, lr: 1.30e-04
+2022-05-09 01:01:36,312 INFO [train.py:715] (3/8) Epoch 17, batch 14500, loss[loss=0.1271, simple_loss=0.1958, pruned_loss=0.02925, over 4940.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03028, over 972397.53 frames.], batch size: 29, lr: 1.30e-04
+2022-05-09 01:02:15,671 INFO [train.py:715] (3/8) Epoch 17, batch 14550, loss[loss=0.1087, simple_loss=0.1912, pruned_loss=0.01313, over 4982.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.0297, over 971905.47 frames.], batch size: 28, lr: 1.30e-04
+2022-05-09 01:02:54,148 INFO [train.py:715] (3/8) Epoch 17, batch 14600, loss[loss=0.1189, simple_loss=0.1882, pruned_loss=0.02482, over 4926.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02927, over 972599.29 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 01:03:33,788 INFO [train.py:715] (3/8) Epoch 17, batch 14650, loss[loss=0.1385, simple_loss=0.2168, pruned_loss=0.03006, over 4832.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02883, over 972767.73 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:04:13,439 INFO [train.py:715] (3/8) Epoch 17, batch 14700, loss[loss=0.1415, simple_loss=0.2188, pruned_loss=0.0321, over 4868.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02849, over 972824.16 frames.], batch size: 30, lr: 1.30e-04
+2022-05-09 01:04:52,652 INFO [train.py:715] (3/8) Epoch 17, batch 14750, loss[loss=0.1437, simple_loss=0.219, pruned_loss=0.03421, over 4934.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02821, over 972272.41 frames.], batch size: 29, lr: 1.30e-04
+2022-05-09 01:05:31,536 INFO [train.py:715] (3/8) Epoch 17, batch 14800, loss[loss=0.1228, simple_loss=0.2016, pruned_loss=0.02207, over 4804.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.0287, over 972692.22 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 01:06:11,602 INFO [train.py:715] (3/8) Epoch 17, batch 14850, loss[loss=0.1525, simple_loss=0.2276, pruned_loss=0.03872, over 4684.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02858, over 971986.97 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:06:50,381 INFO [train.py:715] (3/8) Epoch 17, batch 14900, loss[loss=0.1295, simple_loss=0.2087, pruned_loss=0.02513, over 4870.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02873, over 971225.92 frames.], batch size: 20, lr: 1.30e-04
+2022-05-09 01:07:29,330 INFO [train.py:715] (3/8) Epoch 17, batch 14950, loss[loss=0.144, simple_loss=0.2092, pruned_loss=0.0394, over 4708.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02868, over 972388.61 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:08:09,015 INFO [train.py:715] (3/8) Epoch 17, batch 15000, loss[loss=0.1354, simple_loss=0.197, pruned_loss=0.03694, over 4698.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.0287, over 972970.27 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:08:09,016 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 01:08:19,081 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1046, simple_loss=0.1881, pruned_loss=0.01059, over 914524.00 frames.
+2022-05-09 01:08:59,146 INFO [train.py:715] (3/8) Epoch 17, batch 15050, loss[loss=0.1261, simple_loss=0.2048, pruned_loss=0.02372, over 4800.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02911, over 972628.07 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 01:09:38,652 INFO [train.py:715] (3/8) Epoch 17, batch 15100, loss[loss=0.1106, simple_loss=0.1846, pruned_loss=0.01829, over 4800.00 frames.], tot_loss[loss=0.132, simple_loss=0.2059, pruned_loss=0.02908, over 972220.03 frames.], batch size: 25, lr: 1.30e-04
+2022-05-09 01:10:17,572 INFO [train.py:715] (3/8) Epoch 17, batch 15150, loss[loss=0.1083, simple_loss=0.1898, pruned_loss=0.01342, over 4934.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02896, over 972257.23 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 01:10:56,610 INFO [train.py:715] (3/8) Epoch 17, batch 15200, loss[loss=0.1186, simple_loss=0.1987, pruned_loss=0.01923, over 4961.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02871, over 971629.15 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 01:11:36,237 INFO [train.py:715] (3/8) Epoch 17, batch 15250, loss[loss=0.1599, simple_loss=0.2273, pruned_loss=0.04623, over 4906.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02921, over 971745.12 frames.], batch size: 39, lr: 1.30e-04
+2022-05-09 01:12:15,601 INFO [train.py:715] (3/8) Epoch 17, batch 15300, loss[loss=0.1286, simple_loss=0.2048, pruned_loss=0.02615, over 4846.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02916, over 971565.95 frames.], batch size: 13, lr: 1.30e-04
+2022-05-09 01:12:53,858 INFO [train.py:715] (3/8) Epoch 17, batch 15350, loss[loss=0.1318, simple_loss=0.2076, pruned_loss=0.028, over 4957.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02935, over 972635.59 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:13:33,402 INFO [train.py:715] (3/8) Epoch 17, batch 15400, loss[loss=0.1454, simple_loss=0.2077, pruned_loss=0.04151, over 4698.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02935, over 972051.80 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:14:12,475 INFO [train.py:715] (3/8) Epoch 17, batch 15450, loss[loss=0.1317, simple_loss=0.2084, pruned_loss=0.02753, over 4776.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02905, over 971679.08 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 01:14:51,820 INFO [train.py:715] (3/8) Epoch 17, batch 15500, loss[loss=0.1344, simple_loss=0.2148, pruned_loss=0.02696, over 4819.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.0293, over 971022.44 frames.], batch size: 25, lr: 1.30e-04
+2022-05-09 01:15:30,648 INFO [train.py:715] (3/8) Epoch 17, batch 15550, loss[loss=0.1139, simple_loss=0.1925, pruned_loss=0.01764, over 4809.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02917, over 971228.13 frames.], batch size: 25, lr: 1.30e-04
+2022-05-09 01:16:10,371 INFO [train.py:715] (3/8) Epoch 17, batch 15600, loss[loss=0.1199, simple_loss=0.195, pruned_loss=0.0224, over 4905.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02959, over 971717.12 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 01:16:49,789 INFO [train.py:715] (3/8) Epoch 17, batch 15650, loss[loss=0.1389, simple_loss=0.2219, pruned_loss=0.02801, over 4900.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02968, over 972260.35 frames.], batch size: 19, lr: 1.30e-04
+2022-05-09 01:17:27,916 INFO [train.py:715] (3/8) Epoch 17, batch 15700, loss[loss=0.1223, simple_loss=0.1831, pruned_loss=0.03075, over 4906.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02985, over 971871.03 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 01:18:07,729 INFO [train.py:715] (3/8) Epoch 17, batch 15750, loss[loss=0.1351, simple_loss=0.1982, pruned_loss=0.03594, over 4787.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02924, over 971147.26 frames.], batch size: 12, lr: 1.30e-04
+2022-05-09 01:18:47,135 INFO [train.py:715] (3/8) Epoch 17, batch 15800, loss[loss=0.1337, simple_loss=0.1973, pruned_loss=0.03507, over 4917.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02924, over 971624.86 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 01:19:26,082 INFO [train.py:715] (3/8) Epoch 17, batch 15850, loss[loss=0.112, simple_loss=0.188, pruned_loss=0.018, over 4939.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02965, over 970868.49 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 01:20:04,719 INFO [train.py:715] (3/8) Epoch 17, batch 15900, loss[loss=0.1625, simple_loss=0.2434, pruned_loss=0.04078, over 4844.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02931, over 971184.32 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:20:44,128 INFO [train.py:715] (3/8) Epoch 17, batch 15950, loss[loss=0.1239, simple_loss=0.1965, pruned_loss=0.0257, over 4842.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02941, over 970952.77 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:21:23,630 INFO [train.py:715] (3/8) Epoch 17, batch 16000, loss[loss=0.1363, simple_loss=0.1993, pruned_loss=0.03665, over 4790.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02951, over 969796.26 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 01:22:02,020 INFO [train.py:715] (3/8) Epoch 17, batch 16050, loss[loss=0.1498, simple_loss=0.2108, pruned_loss=0.04447, over 4878.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02989, over 969722.18 frames.], batch size: 30, lr: 1.30e-04
+2022-05-09 01:22:42,058 INFO [train.py:715] (3/8) Epoch 17, batch 16100, loss[loss=0.1502, simple_loss=0.2143, pruned_loss=0.04306, over 4984.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02978, over 969833.12 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:23:21,959 INFO [train.py:715] (3/8) Epoch 17, batch 16150, loss[loss=0.1101, simple_loss=0.1945, pruned_loss=0.01283, over 4791.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02926, over 969739.65 frames.], batch size: 13, lr: 1.30e-04
+2022-05-09 01:24:01,719 INFO [train.py:715] (3/8) Epoch 17, batch 16200, loss[loss=0.1659, simple_loss=0.2427, pruned_loss=0.04455, over 4986.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.0296, over 970002.11 frames.], batch size: 25, lr: 1.30e-04
+2022-05-09 01:24:43,130 INFO [train.py:715] (3/8) Epoch 17, batch 16250, loss[loss=0.1023, simple_loss=0.1755, pruned_loss=0.01456, over 4972.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02972, over 970849.43 frames.], batch size: 14, lr: 1.30e-04
+2022-05-09 01:25:23,141 INFO [train.py:715] (3/8) Epoch 17, batch 16300, loss[loss=0.133, simple_loss=0.2137, pruned_loss=0.02618, over 4889.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02924, over 971850.74 frames.], batch size: 22, lr: 1.30e-04
+2022-05-09 01:26:02,217 INFO [train.py:715] (3/8) Epoch 17, batch 16350, loss[loss=0.1634, simple_loss=0.2291, pruned_loss=0.04884, over 4956.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02939, over 972490.10 frames.], batch size: 35, lr: 1.30e-04
+2022-05-09 01:26:40,872 INFO [train.py:715] (3/8) Epoch 17, batch 16400, loss[loss=0.1328, simple_loss=0.2035, pruned_loss=0.03105, over 4828.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02892, over 971777.37 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:27:20,588 INFO [train.py:715] (3/8) Epoch 17, batch 16450, loss[loss=0.1141, simple_loss=0.2051, pruned_loss=0.01154, over 4783.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02905, over 971339.41 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 01:28:00,552 INFO [train.py:715] (3/8) Epoch 17, batch 16500, loss[loss=0.1179, simple_loss=0.199, pruned_loss=0.01833, over 4831.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02938, over 971016.48 frames.], batch size: 27, lr: 1.30e-04
+2022-05-09 01:28:39,574 INFO [train.py:715] (3/8) Epoch 17, batch 16550, loss[loss=0.1382, simple_loss=0.2103, pruned_loss=0.03303, over 4930.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02956, over 970815.31 frames.], batch size: 39, lr: 1.30e-04
+2022-05-09 01:29:18,073 INFO [train.py:715] (3/8) Epoch 17, batch 16600, loss[loss=0.1259, simple_loss=0.2041, pruned_loss=0.02386, over 4776.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02895, over 971804.02 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 01:29:58,264 INFO [train.py:715] (3/8) Epoch 17, batch 16650, loss[loss=0.1226, simple_loss=0.2018, pruned_loss=0.02168, over 4921.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02849, over 972679.55 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 01:30:38,044 INFO [train.py:715] (3/8) Epoch 17, batch 16700, loss[loss=0.14, simple_loss=0.2197, pruned_loss=0.0301, over 4780.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.0283, over 973371.48 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 01:31:16,490 INFO [train.py:715] (3/8) Epoch 17, batch 16750, loss[loss=0.1473, simple_loss=0.2283, pruned_loss=0.03313, over 4938.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.0287, over 973013.55 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 01:31:56,310 INFO [train.py:715] (3/8) Epoch 17, batch 16800, loss[loss=0.1145, simple_loss=0.1868, pruned_loss=0.02113, over 4831.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02901, over 973398.24 frames.], batch size: 13, lr: 1.30e-04
+2022-05-09 01:32:35,733 INFO [train.py:715] (3/8) Epoch 17, batch 16850, loss[loss=0.1436, simple_loss=0.217, pruned_loss=0.03508, over 4855.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.0292, over 973595.97 frames.], batch size: 32, lr: 1.30e-04
+2022-05-09 01:33:15,640 INFO [train.py:715] (3/8) Epoch 17, batch 16900, loss[loss=0.1104, simple_loss=0.1853, pruned_loss=0.01776, over 4750.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.0287, over 973131.87 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 01:33:53,866 INFO [train.py:715] (3/8) Epoch 17, batch 16950, loss[loss=0.1258, simple_loss=0.208, pruned_loss=0.02185, over 4988.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02859, over 973105.48 frames.], batch size: 28, lr: 1.30e-04
+2022-05-09 01:34:33,424 INFO [train.py:715] (3/8) Epoch 17, batch 17000, loss[loss=0.1434, simple_loss=0.2097, pruned_loss=0.03859, over 4847.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02944, over 973505.59 frames.], batch size: 30, lr: 1.30e-04
+2022-05-09 01:35:12,911 INFO [train.py:715] (3/8) Epoch 17, batch 17050, loss[loss=0.1445, simple_loss=0.2069, pruned_loss=0.04106, over 4838.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.0302, over 973293.34 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:35:51,175 INFO [train.py:715] (3/8) Epoch 17, batch 17100, loss[loss=0.1556, simple_loss=0.2345, pruned_loss=0.03832, over 4937.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03015, over 972802.90 frames.], batch size: 21, lr: 1.30e-04
+2022-05-09 01:36:30,680 INFO [train.py:715] (3/8) Epoch 17, batch 17150, loss[loss=0.1541, simple_loss=0.232, pruned_loss=0.0381, over 4784.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03012, over 973485.58 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 01:37:10,049 INFO [train.py:715] (3/8) Epoch 17, batch 17200, loss[loss=0.1139, simple_loss=0.1784, pruned_loss=0.02469, over 4747.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2082, pruned_loss=0.02946, over 974303.20 frames.], batch size: 12, lr: 1.30e-04
+2022-05-09 01:37:48,555 INFO [train.py:715] (3/8) Epoch 17, batch 17250, loss[loss=0.1146, simple_loss=0.1868, pruned_loss=0.02116, over 4864.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02933, over 973391.53 frames.], batch size: 13, lr: 1.30e-04
+2022-05-09 01:38:26,822 INFO [train.py:715] (3/8) Epoch 17, batch 17300, loss[loss=0.152, simple_loss=0.2305, pruned_loss=0.03678, over 4969.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02921, over 973043.70 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:39:06,138 INFO [train.py:715] (3/8) Epoch 17, batch 17350, loss[loss=0.1285, simple_loss=0.2058, pruned_loss=0.0256, over 4745.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02919, over 973364.18 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 01:39:45,335 INFO [train.py:715] (3/8) Epoch 17, batch 17400, loss[loss=0.1382, simple_loss=0.2209, pruned_loss=0.02774, over 4933.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2087, pruned_loss=0.02969, over 972208.10 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 01:40:23,322 INFO [train.py:715] (3/8) Epoch 17, batch 17450, loss[loss=0.121, simple_loss=0.1838, pruned_loss=0.02907, over 4789.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02957, over 971873.05 frames.], batch size: 14, lr: 1.30e-04
+2022-05-09 01:41:03,008 INFO [train.py:715] (3/8) Epoch 17, batch 17500, loss[loss=0.1513, simple_loss=0.2334, pruned_loss=0.03457, over 4958.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.02942, over 972485.75 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 01:41:42,132 INFO [train.py:715] (3/8) Epoch 17, batch 17550, loss[loss=0.1347, simple_loss=0.2141, pruned_loss=0.02765, over 4977.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2089, pruned_loss=0.02984, over 972247.35 frames.], batch size: 35, lr: 1.30e-04
+2022-05-09 01:42:20,891 INFO [train.py:715] (3/8) Epoch 17, batch 17600, loss[loss=0.1617, simple_loss=0.2468, pruned_loss=0.03828, over 4961.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2088, pruned_loss=0.02976, over 971731.03 frames.], batch size: 21, lr: 1.30e-04
+2022-05-09 01:42:59,400 INFO [train.py:715] (3/8) Epoch 17, batch 17650, loss[loss=0.1161, simple_loss=0.19, pruned_loss=0.02111, over 4687.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02967, over 971089.90 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:43:38,885 INFO [train.py:715] (3/8) Epoch 17, batch 17700, loss[loss=0.1357, simple_loss=0.2075, pruned_loss=0.03197, over 4832.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02938, over 971409.14 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:44:17,597 INFO [train.py:715] (3/8) Epoch 17, batch 17750, loss[loss=0.1372, simple_loss=0.2069, pruned_loss=0.03373, over 4854.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02972, over 971620.60 frames.], batch size: 32, lr: 1.30e-04
+2022-05-09 01:44:56,093 INFO [train.py:715] (3/8) Epoch 17, batch 17800, loss[loss=0.1215, simple_loss=0.1991, pruned_loss=0.02197, over 4932.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02938, over 971729.28 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 01:45:35,676 INFO [train.py:715] (3/8) Epoch 17, batch 17850, loss[loss=0.1384, simple_loss=0.2178, pruned_loss=0.02953, over 4951.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02959, over 972197.81 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:46:14,673 INFO [train.py:715] (3/8) Epoch 17, batch 17900, loss[loss=0.1194, simple_loss=0.197, pruned_loss=0.02092, over 4915.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02978, over 971910.19 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 01:46:54,014 INFO [train.py:715] (3/8) Epoch 17, batch 17950, loss[loss=0.129, simple_loss=0.1973, pruned_loss=0.03031, over 4982.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03029, over 973301.34 frames.], batch size: 33, lr: 1.30e-04
+2022-05-09 01:47:32,275 INFO [train.py:715] (3/8) Epoch 17, batch 18000, loss[loss=0.128, simple_loss=0.2097, pruned_loss=0.02317, over 4975.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03019, over 974014.84 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 01:47:32,276 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 01:47:42,061 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01066, over 914524.00 frames.
+2022-05-09 01:48:20,782 INFO [train.py:715] (3/8) Epoch 17, batch 18050, loss[loss=0.1203, simple_loss=0.2017, pruned_loss=0.01949, over 4913.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02996, over 973799.80 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 01:49:00,410 INFO [train.py:715] (3/8) Epoch 17, batch 18100, loss[loss=0.1602, simple_loss=0.2341, pruned_loss=0.0431, over 4775.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.0297, over 973828.22 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 01:49:39,796 INFO [train.py:715] (3/8) Epoch 17, batch 18150, loss[loss=0.1483, simple_loss=0.2264, pruned_loss=0.03505, over 4701.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.0297, over 972394.53 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:50:17,779 INFO [train.py:715] (3/8) Epoch 17, batch 18200, loss[loss=0.1024, simple_loss=0.1794, pruned_loss=0.01265, over 4806.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02938, over 972291.65 frames.], batch size: 25, lr: 1.30e-04
+2022-05-09 01:50:57,531 INFO [train.py:715] (3/8) Epoch 17, batch 18250, loss[loss=0.1132, simple_loss=0.1853, pruned_loss=0.02058, over 4966.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02971, over 972122.80 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:51:37,061 INFO [train.py:715] (3/8) Epoch 17, batch 18300, loss[loss=0.115, simple_loss=0.1941, pruned_loss=0.01789, over 4978.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02965, over 972058.59 frames.], batch size: 28, lr: 1.30e-04
+2022-05-09 01:52:15,574 INFO [train.py:715] (3/8) Epoch 17, batch 18350, loss[loss=0.106, simple_loss=0.1779, pruned_loss=0.01709, over 4973.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02971, over 972082.32 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 01:52:55,002 INFO [train.py:715] (3/8) Epoch 17, batch 18400, loss[loss=0.1239, simple_loss=0.1938, pruned_loss=0.02702, over 4796.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02919, over 972669.14 frames.], batch size: 13, lr: 1.30e-04
+2022-05-09 01:53:33,898 INFO [train.py:715] (3/8) Epoch 17, batch 18450, loss[loss=0.1351, simple_loss=0.207, pruned_loss=0.03155, over 4846.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02911, over 972099.82 frames.], batch size: 34, lr: 1.30e-04
+2022-05-09 01:54:13,086 INFO [train.py:715] (3/8) Epoch 17, batch 18500, loss[loss=0.1318, simple_loss=0.2049, pruned_loss=0.02933, over 4938.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02869, over 973140.43 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 01:54:51,416 INFO [train.py:715] (3/8) Epoch 17, batch 18550, loss[loss=0.139, simple_loss=0.2142, pruned_loss=0.03188, over 4855.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02915, over 972442.76 frames.], batch size: 32, lr: 1.30e-04
+2022-05-09 01:55:30,372 INFO [train.py:715] (3/8) Epoch 17, batch 18600, loss[loss=0.1465, simple_loss=0.2146, pruned_loss=0.03923, over 4929.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02915, over 971993.15 frames.], batch size: 39, lr: 1.30e-04
+2022-05-09 01:56:09,530 INFO [train.py:715] (3/8) Epoch 17, batch 18650, loss[loss=0.1398, simple_loss=0.2074, pruned_loss=0.03611, over 4778.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02965, over 972823.52 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 01:56:47,376 INFO [train.py:715] (3/8) Epoch 17, batch 18700, loss[loss=0.1235, simple_loss=0.1938, pruned_loss=0.0266, over 4964.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02931, over 973141.93 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 01:57:27,055 INFO [train.py:715] (3/8) Epoch 17, batch 18750, loss[loss=0.1154, simple_loss=0.1928, pruned_loss=0.019, over 4864.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02903, over 972352.03 frames.], batch size: 20, lr: 1.30e-04
+2022-05-09 01:58:06,644 INFO [train.py:715] (3/8) Epoch 17, batch 18800, loss[loss=0.1749, simple_loss=0.2616, pruned_loss=0.04412, over 4834.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02925, over 972984.59 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 01:58:45,348 INFO [train.py:715] (3/8) Epoch 17, batch 18850, loss[loss=0.1647, simple_loss=0.2302, pruned_loss=0.0496, over 4925.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02894, over 973414.23 frames.], batch size: 39, lr: 1.30e-04
+2022-05-09 01:59:23,454 INFO [train.py:715] (3/8) Epoch 17, batch 18900, loss[loss=0.1754, simple_loss=0.2322, pruned_loss=0.05934, over 4869.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.0292, over 973305.30 frames.], batch size: 32, lr: 1.30e-04
+2022-05-09 02:00:02,551 INFO [train.py:715] (3/8) Epoch 17, batch 18950, loss[loss=0.114, simple_loss=0.1965, pruned_loss=0.01571, over 4860.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02876, over 973434.56 frames.], batch size: 22, lr: 1.30e-04
+2022-05-09 02:00:41,836 INFO [train.py:715] (3/8) Epoch 17, batch 19000, loss[loss=0.11, simple_loss=0.1926, pruned_loss=0.01369, over 4923.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02898, over 973124.41 frames.], batch size: 29, lr: 1.30e-04
+2022-05-09 02:01:20,326 INFO [train.py:715] (3/8) Epoch 17, batch 19050, loss[loss=0.1358, simple_loss=0.2077, pruned_loss=0.03194, over 4991.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02904, over 972604.96 frames.], batch size: 14, lr: 1.30e-04
+2022-05-09 02:01:59,754 INFO [train.py:715] (3/8) Epoch 17, batch 19100, loss[loss=0.1397, simple_loss=0.2122, pruned_loss=0.03362, over 4841.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02891, over 972799.61 frames.], batch size: 32, lr: 1.30e-04
+2022-05-09 02:02:38,885 INFO [train.py:715] (3/8) Epoch 17, batch 19150, loss[loss=0.1239, simple_loss=0.2096, pruned_loss=0.01914, over 4740.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02854, over 972067.73 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 02:03:17,328 INFO [train.py:715] (3/8) Epoch 17, batch 19200, loss[loss=0.12, simple_loss=0.1984, pruned_loss=0.02084, over 4990.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02874, over 971931.65 frames.], batch size: 14, lr: 1.30e-04
+2022-05-09 02:03:56,164 INFO [train.py:715] (3/8) Epoch 17, batch 19250, loss[loss=0.1155, simple_loss=0.1946, pruned_loss=0.01824, over 4966.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02839, over 972266.71 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 02:04:35,742 INFO [train.py:715] (3/8) Epoch 17, batch 19300, loss[loss=0.1279, simple_loss=0.1964, pruned_loss=0.02971, over 4910.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02851, over 971983.63 frames.], batch size: 19, lr: 1.30e-04
+2022-05-09 02:05:15,463 INFO [train.py:715] (3/8) Epoch 17, batch 19350, loss[loss=0.1496, simple_loss=0.2214, pruned_loss=0.0389, over 4703.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02857, over 972294.42 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 02:05:54,626 INFO [train.py:715] (3/8) Epoch 17, batch 19400, loss[loss=0.1168, simple_loss=0.1974, pruned_loss=0.01807, over 4915.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02882, over 972112.17 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 02:06:34,193 INFO [train.py:715] (3/8) Epoch 17, batch 19450, loss[loss=0.1253, simple_loss=0.2012, pruned_loss=0.0247, over 4916.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02909, over 972551.74 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 02:07:13,757 INFO [train.py:715] (3/8) Epoch 17, batch 19500, loss[loss=0.1457, simple_loss=0.2249, pruned_loss=0.03321, over 4871.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.0293, over 972774.84 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 02:07:53,345 INFO [train.py:715] (3/8) Epoch 17, batch 19550, loss[loss=0.1209, simple_loss=0.1946, pruned_loss=0.02363, over 4778.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02952, over 973506.77 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 02:08:31,622 INFO [train.py:715] (3/8) Epoch 17, batch 19600, loss[loss=0.1569, simple_loss=0.2192, pruned_loss=0.0473, over 4950.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02921, over 972692.04 frames.], batch size: 39, lr: 1.30e-04
+2022-05-09 02:09:11,586 INFO [train.py:715] (3/8) Epoch 17, batch 19650, loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02894, over 4950.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02939, over 972444.79 frames.], batch size: 21, lr: 1.30e-04
+2022-05-09 02:09:51,452 INFO [train.py:715] (3/8) Epoch 17, batch 19700, loss[loss=0.1129, simple_loss=0.182, pruned_loss=0.02193, over 4840.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02942, over 972661.48 frames.], batch size: 30, lr: 1.30e-04
+2022-05-09 02:10:30,059 INFO [train.py:715] (3/8) Epoch 17, batch 19750, loss[loss=0.1189, simple_loss=0.193, pruned_loss=0.02239, over 4806.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02934, over 972902.47 frames.], batch size: 25, lr: 1.30e-04
+2022-05-09 02:11:09,369 INFO [train.py:715] (3/8) Epoch 17, batch 19800, loss[loss=0.1403, simple_loss=0.2175, pruned_loss=0.0315, over 4780.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02959, over 972374.49 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 02:11:47,959 INFO [train.py:715] (3/8) Epoch 17, batch 19850, loss[loss=0.1508, simple_loss=0.2267, pruned_loss=0.03744, over 4789.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02983, over 972404.17 frames.], batch size: 14, lr: 1.30e-04
+2022-05-09 02:12:26,931 INFO [train.py:715] (3/8) Epoch 17, batch 19900, loss[loss=0.1115, simple_loss=0.1912, pruned_loss=0.01583, over 4795.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02948, over 972580.38 frames.], batch size: 21, lr: 1.30e-04
+2022-05-09 02:13:05,188 INFO [train.py:715] (3/8) Epoch 17, batch 19950, loss[loss=0.1003, simple_loss=0.1667, pruned_loss=0.01695, over 4734.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02955, over 971956.54 frames.], batch size: 12, lr: 1.30e-04
+2022-05-09 02:13:44,431 INFO [train.py:715] (3/8) Epoch 17, batch 20000, loss[loss=0.1155, simple_loss=0.1862, pruned_loss=0.0224, over 4797.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02959, over 972020.12 frames.], batch size: 12, lr: 1.30e-04
+2022-05-09 02:14:24,055 INFO [train.py:715] (3/8) Epoch 17, batch 20050, loss[loss=0.1229, simple_loss=0.2022, pruned_loss=0.02181, over 4911.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.0296, over 972023.99 frames.], batch size: 22, lr: 1.30e-04
+2022-05-09 02:15:03,201 INFO [train.py:715] (3/8) Epoch 17, batch 20100, loss[loss=0.1421, simple_loss=0.2129, pruned_loss=0.03568, over 4843.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02911, over 973091.89 frames.], batch size: 30, lr: 1.30e-04
+2022-05-09 02:15:42,009 INFO [train.py:715] (3/8) Epoch 17, batch 20150, loss[loss=0.1545, simple_loss=0.2352, pruned_loss=0.03688, over 4823.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02914, over 972436.41 frames.], batch size: 25, lr: 1.30e-04
+2022-05-09 02:16:22,284 INFO [train.py:715] (3/8) Epoch 17, batch 20200, loss[loss=0.1179, simple_loss=0.1961, pruned_loss=0.01981, over 4864.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02889, over 972052.96 frames.], batch size: 32, lr: 1.30e-04
+2022-05-09 02:17:02,701 INFO [train.py:715] (3/8) Epoch 17, batch 20250, loss[loss=0.09803, simple_loss=0.163, pruned_loss=0.01653, over 4837.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.0287, over 972133.59 frames.], batch size: 12, lr: 1.30e-04
+2022-05-09 02:17:40,776 INFO [train.py:715] (3/8) Epoch 17, batch 20300, loss[loss=0.1107, simple_loss=0.1816, pruned_loss=0.01984, over 4939.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.0283, over 971897.07 frames.], batch size: 29, lr: 1.30e-04
+2022-05-09 02:18:20,508 INFO [train.py:715] (3/8) Epoch 17, batch 20350, loss[loss=0.1628, simple_loss=0.2333, pruned_loss=0.04613, over 4746.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02841, over 971513.77 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 02:19:00,633 INFO [train.py:715] (3/8) Epoch 17, batch 20400, loss[loss=0.1157, simple_loss=0.1995, pruned_loss=0.01592, over 4936.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02812, over 972399.51 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 02:19:39,222 INFO [train.py:715] (3/8) Epoch 17, batch 20450, loss[loss=0.159, simple_loss=0.229, pruned_loss=0.04456, over 4905.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.0283, over 972727.15 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 02:20:17,924 INFO [train.py:715] (3/8) Epoch 17, batch 20500, loss[loss=0.1235, simple_loss=0.2035, pruned_loss=0.02172, over 4658.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2058, pruned_loss=0.0279, over 972667.10 frames.], batch size: 13, lr: 1.30e-04
+2022-05-09 02:20:57,776 INFO [train.py:715] (3/8) Epoch 17, batch 20550, loss[loss=0.166, simple_loss=0.2309, pruned_loss=0.05048, over 4883.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02835, over 972507.38 frames.], batch size: 22, lr: 1.30e-04
+2022-05-09 02:21:36,912 INFO [train.py:715] (3/8) Epoch 17, batch 20600, loss[loss=0.1402, simple_loss=0.2077, pruned_loss=0.03637, over 4961.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02863, over 971869.14 frames.], batch size: 14, lr: 1.30e-04
+2022-05-09 02:22:15,099 INFO [train.py:715] (3/8) Epoch 17, batch 20650, loss[loss=0.1667, simple_loss=0.241, pruned_loss=0.04622, over 4803.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02901, over 972011.49 frames.], batch size: 21, lr: 1.30e-04
+2022-05-09 02:22:54,071 INFO [train.py:715] (3/8) Epoch 17, batch 20700, loss[loss=0.1229, simple_loss=0.1888, pruned_loss=0.0285, over 4775.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02882, over 972591.95 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 02:23:33,733 INFO [train.py:715] (3/8) Epoch 17, batch 20750, loss[loss=0.1369, simple_loss=0.2177, pruned_loss=0.02806, over 4981.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02892, over 972914.63 frames.], batch size: 14, lr: 1.30e-04
+2022-05-09 02:24:12,679 INFO [train.py:715] (3/8) Epoch 17, batch 20800, loss[loss=0.1491, simple_loss=0.224, pruned_loss=0.03707, over 4771.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.0293, over 972192.86 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 02:24:51,253 INFO [train.py:715] (3/8) Epoch 17, batch 20850, loss[loss=0.14, simple_loss=0.2275, pruned_loss=0.02621, over 4789.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02879, over 972679.25 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 02:25:30,262 INFO [train.py:715] (3/8) Epoch 17, batch 20900, loss[loss=0.1176, simple_loss=0.1882, pruned_loss=0.02353, over 4865.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2053, pruned_loss=0.02881, over 972614.23 frames.], batch size: 32, lr: 1.30e-04
+2022-05-09 02:26:10,247 INFO [train.py:715] (3/8) Epoch 17, batch 20950, loss[loss=0.1281, simple_loss=0.2048, pruned_loss=0.02572, over 4871.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2053, pruned_loss=0.02878, over 971374.87 frames.], batch size: 30, lr: 1.30e-04
+2022-05-09 02:26:48,267 INFO [train.py:715] (3/8) Epoch 17, batch 21000, loss[loss=0.1378, simple_loss=0.2163, pruned_loss=0.02971, over 4875.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02885, over 971220.87 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 02:26:48,268 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 02:27:00,911 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1049, simple_loss=0.1882, pruned_loss=0.01077, over 914524.00 frames.
+2022-05-09 02:27:38,928 INFO [train.py:715] (3/8) Epoch 17, batch 21050, loss[loss=0.137, simple_loss=0.2138, pruned_loss=0.0301, over 4947.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02892, over 971719.35 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 02:28:18,321 INFO [train.py:715] (3/8) Epoch 17, batch 21100, loss[loss=0.1195, simple_loss=0.1934, pruned_loss=0.02285, over 4884.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02894, over 972639.36 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 02:28:58,367 INFO [train.py:715] (3/8) Epoch 17, batch 21150, loss[loss=0.1449, simple_loss=0.2167, pruned_loss=0.03657, over 4749.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02923, over 971586.06 frames.], batch size: 19, lr: 1.30e-04
+2022-05-09 02:29:37,030 INFO [train.py:715] (3/8) Epoch 17, batch 21200, loss[loss=0.1405, simple_loss=0.2096, pruned_loss=0.03565, over 4698.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02904, over 971316.65 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 02:30:15,712 INFO [train.py:715] (3/8) Epoch 17, batch 21250, loss[loss=0.1259, simple_loss=0.1987, pruned_loss=0.02654, over 4921.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02924, over 971798.70 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 02:30:55,577 INFO [train.py:715] (3/8) Epoch 17, batch 21300, loss[loss=0.121, simple_loss=0.1929, pruned_loss=0.02457, over 4739.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2052, pruned_loss=0.02873, over 972488.92 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 02:31:35,366 INFO [train.py:715] (3/8) Epoch 17, batch 21350, loss[loss=0.12, simple_loss=0.1966, pruned_loss=0.02171, over 4832.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.02857, over 972950.37 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 02:32:13,590 INFO [train.py:715] (3/8) Epoch 17, batch 21400, loss[loss=0.1287, simple_loss=0.2085, pruned_loss=0.02448, over 4824.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02846, over 973461.10 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 02:32:53,761 INFO [train.py:715] (3/8) Epoch 17, batch 21450, loss[loss=0.1611, simple_loss=0.2454, pruned_loss=0.03837, over 4839.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02835, over 973799.56 frames.], batch size: 20, lr: 1.30e-04
+2022-05-09 02:33:33,551 INFO [train.py:715] (3/8) Epoch 17, batch 21500, loss[loss=0.1402, simple_loss=0.2297, pruned_loss=0.02539, over 4782.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02847, over 974383.79 frames.], batch size: 19, lr: 1.30e-04
+2022-05-09 02:34:12,047 INFO [train.py:715] (3/8) Epoch 17, batch 21550, loss[loss=0.1282, simple_loss=0.2016, pruned_loss=0.02738, over 4843.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2054, pruned_loss=0.02868, over 973497.44 frames.], batch size: 32, lr: 1.30e-04
+2022-05-09 02:34:51,493 INFO [train.py:715] (3/8) Epoch 17, batch 21600, loss[loss=0.1296, simple_loss=0.2048, pruned_loss=0.0272, over 4928.00 frames.], tot_loss[loss=0.132, simple_loss=0.2058, pruned_loss=0.02908, over 973816.18 frames.], batch size: 29, lr: 1.30e-04
+2022-05-09 02:35:31,960 INFO [train.py:715] (3/8) Epoch 17, batch 21650, loss[loss=0.1186, simple_loss=0.197, pruned_loss=0.02015, over 4922.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02887, over 974285.28 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 02:36:11,047 INFO [train.py:715] (3/8) Epoch 17, batch 21700, loss[loss=0.1691, simple_loss=0.2311, pruned_loss=0.05358, over 4852.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02921, over 974288.29 frames.], batch size: 20, lr: 1.30e-04
+2022-05-09 02:36:49,698 INFO [train.py:715] (3/8) Epoch 17, batch 21750, loss[loss=0.118, simple_loss=0.1879, pruned_loss=0.0241, over 4867.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2062, pruned_loss=0.02917, over 974404.47 frames.], batch size: 32, lr: 1.30e-04
+2022-05-09 02:37:29,250 INFO [train.py:715] (3/8) Epoch 17, batch 21800, loss[loss=0.1466, simple_loss=0.2229, pruned_loss=0.03517, over 4911.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2061, pruned_loss=0.0292, over 974086.22 frames.], batch size: 19, lr: 1.30e-04
+2022-05-09 02:38:08,213 INFO [train.py:715] (3/8) Epoch 17, batch 21850, loss[loss=0.1312, simple_loss=0.2035, pruned_loss=0.02945, over 4826.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02928, over 973927.79 frames.], batch size: 20, lr: 1.30e-04
+2022-05-09 02:38:47,460 INFO [train.py:715] (3/8) Epoch 17, batch 21900, loss[loss=0.1515, simple_loss=0.2206, pruned_loss=0.04116, over 4948.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02929, over 973877.22 frames.], batch size: 24, lr: 1.30e-04
+2022-05-09 02:39:25,953 INFO [train.py:715] (3/8) Epoch 17, batch 21950, loss[loss=0.1257, simple_loss=0.1872, pruned_loss=0.0321, over 4920.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02909, over 972635.13 frames.], batch size: 17, lr: 1.30e-04
+2022-05-09 02:40:05,670 INFO [train.py:715] (3/8) Epoch 17, batch 22000, loss[loss=0.1253, simple_loss=0.1963, pruned_loss=0.02716, over 4882.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.0293, over 972232.12 frames.], batch size: 22, lr: 1.30e-04
+2022-05-09 02:40:45,438 INFO [train.py:715] (3/8) Epoch 17, batch 22050, loss[loss=0.1339, simple_loss=0.2248, pruned_loss=0.02152, over 4809.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02888, over 972283.09 frames.], batch size: 21, lr: 1.30e-04
+2022-05-09 02:41:23,862 INFO [train.py:715] (3/8) Epoch 17, batch 22100, loss[loss=0.1271, simple_loss=0.2024, pruned_loss=0.02589, over 4685.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02892, over 972046.02 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 02:42:03,598 INFO [train.py:715] (3/8) Epoch 17, batch 22150, loss[loss=0.1441, simple_loss=0.2204, pruned_loss=0.0339, over 4927.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02884, over 972832.81 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 02:42:43,494 INFO [train.py:715] (3/8) Epoch 17, batch 22200, loss[loss=0.1678, simple_loss=0.2301, pruned_loss=0.05274, over 4742.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02915, over 972686.08 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 02:43:22,389 INFO [train.py:715] (3/8) Epoch 17, batch 22250, loss[loss=0.1303, simple_loss=0.2126, pruned_loss=0.02399, over 4928.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.0291, over 972790.41 frames.], batch size: 29, lr: 1.30e-04
+2022-05-09 02:44:01,342 INFO [train.py:715] (3/8) Epoch 17, batch 22300, loss[loss=0.1337, simple_loss=0.2057, pruned_loss=0.03088, over 4692.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.029, over 972150.27 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 02:44:41,264 INFO [train.py:715] (3/8) Epoch 17, batch 22350, loss[loss=0.1301, simple_loss=0.205, pruned_loss=0.02764, over 4710.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02932, over 972306.16 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 02:45:20,836 INFO [train.py:715] (3/8) Epoch 17, batch 22400, loss[loss=0.1386, simple_loss=0.2153, pruned_loss=0.03096, over 4925.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02922, over 971940.29 frames.], batch size: 23, lr: 1.30e-04
+2022-05-09 02:45:59,651 INFO [train.py:715] (3/8) Epoch 17, batch 22450, loss[loss=0.1125, simple_loss=0.184, pruned_loss=0.0205, over 4989.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02969, over 972379.03 frames.], batch size: 25, lr: 1.30e-04
+2022-05-09 02:46:38,625 INFO [train.py:715] (3/8) Epoch 17, batch 22500, loss[loss=0.1345, simple_loss=0.2024, pruned_loss=0.03325, over 4935.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02963, over 972282.46 frames.], batch size: 21, lr: 1.30e-04
+2022-05-09 02:47:18,397 INFO [train.py:715] (3/8) Epoch 17, batch 22550, loss[loss=0.1386, simple_loss=0.1922, pruned_loss=0.04252, over 4919.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02956, over 972175.58 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 02:47:56,727 INFO [train.py:715] (3/8) Epoch 17, batch 22600, loss[loss=0.1227, simple_loss=0.1931, pruned_loss=0.02621, over 4789.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02963, over 972037.20 frames.], batch size: 12, lr: 1.30e-04
+2022-05-09 02:48:36,266 INFO [train.py:715] (3/8) Epoch 17, batch 22650, loss[loss=0.1194, simple_loss=0.1887, pruned_loss=0.02499, over 4753.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02968, over 972634.46 frames.], batch size: 16, lr: 1.30e-04
+2022-05-09 02:49:15,731 INFO [train.py:715] (3/8) Epoch 17, batch 22700, loss[loss=0.1052, simple_loss=0.1826, pruned_loss=0.01396, over 4775.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02937, over 972180.13 frames.], batch size: 18, lr: 1.30e-04
+2022-05-09 02:49:54,664 INFO [train.py:715] (3/8) Epoch 17, batch 22750, loss[loss=0.1229, simple_loss=0.1961, pruned_loss=0.02484, over 4897.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02911, over 972620.74 frames.], batch size: 19, lr: 1.30e-04
+2022-05-09 02:50:33,048 INFO [train.py:715] (3/8) Epoch 17, batch 22800, loss[loss=0.1221, simple_loss=0.1976, pruned_loss=0.02334, over 4843.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.0289, over 972705.09 frames.], batch size: 15, lr: 1.30e-04
+2022-05-09 02:51:12,444 INFO [train.py:715] (3/8) Epoch 17, batch 22850, loss[loss=0.1464, simple_loss=0.2153, pruned_loss=0.03871, over 4975.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02905, over 973491.90 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 02:51:52,341 INFO [train.py:715] (3/8) Epoch 17, batch 22900, loss[loss=0.1222, simple_loss=0.1914, pruned_loss=0.02647, over 4750.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02866, over 973186.79 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 02:52:30,190 INFO [train.py:715] (3/8) Epoch 17, batch 22950, loss[loss=0.1303, simple_loss=0.2078, pruned_loss=0.02639, over 4932.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02925, over 973787.72 frames.], batch size: 29, lr: 1.29e-04
+2022-05-09 02:53:10,087 INFO [train.py:715] (3/8) Epoch 17, batch 23000, loss[loss=0.1208, simple_loss=0.1984, pruned_loss=0.02158, over 4801.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02944, over 972885.67 frames.], batch size: 24, lr: 1.29e-04
+2022-05-09 02:53:50,347 INFO [train.py:715] (3/8) Epoch 17, batch 23050, loss[loss=0.1505, simple_loss=0.2186, pruned_loss=0.04114, over 4903.00 frames.], tot_loss[loss=0.1332, simple_loss=0.208, pruned_loss=0.02922, over 973446.09 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 02:54:29,512 INFO [train.py:715] (3/8) Epoch 17, batch 23100, loss[loss=0.1122, simple_loss=0.1854, pruned_loss=0.01951, over 4987.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2072, pruned_loss=0.02862, over 972925.62 frames.], batch size: 28, lr: 1.29e-04
+2022-05-09 02:55:07,926 INFO [train.py:715] (3/8) Epoch 17, batch 23150, loss[loss=0.1285, simple_loss=0.188, pruned_loss=0.03455, over 4814.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02876, over 972970.49 frames.], batch size: 13, lr: 1.29e-04
+2022-05-09 02:55:47,705 INFO [train.py:715] (3/8) Epoch 17, batch 23200, loss[loss=0.1666, simple_loss=0.2372, pruned_loss=0.04798, over 4990.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02851, over 972841.60 frames.], batch size: 28, lr: 1.29e-04
+2022-05-09 02:56:27,704 INFO [train.py:715] (3/8) Epoch 17, batch 23250, loss[loss=0.1204, simple_loss=0.1918, pruned_loss=0.02446, over 4794.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02883, over 973323.79 frames.], batch size: 21, lr: 1.29e-04
+2022-05-09 02:57:05,639 INFO [train.py:715] (3/8) Epoch 17, batch 23300, loss[loss=0.1276, simple_loss=0.1971, pruned_loss=0.02907, over 4838.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02891, over 973260.79 frames.], batch size: 32, lr: 1.29e-04
+2022-05-09 02:57:44,993 INFO [train.py:715] (3/8) Epoch 17, batch 23350, loss[loss=0.1372, simple_loss=0.2078, pruned_loss=0.03332, over 4918.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02848, over 974063.07 frames.], batch size: 23, lr: 1.29e-04
+2022-05-09 02:58:25,087 INFO [train.py:715] (3/8) Epoch 17, batch 23400, loss[loss=0.1337, simple_loss=0.2038, pruned_loss=0.03186, over 4867.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02864, over 974303.86 frames.], batch size: 16, lr: 1.29e-04
+2022-05-09 02:59:03,869 INFO [train.py:715] (3/8) Epoch 17, batch 23450, loss[loss=0.1442, simple_loss=0.2217, pruned_loss=0.03331, over 4799.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02885, over 974840.11 frames.], batch size: 21, lr: 1.29e-04
+2022-05-09 02:59:42,963 INFO [train.py:715] (3/8) Epoch 17, batch 23500, loss[loss=0.1502, simple_loss=0.2158, pruned_loss=0.0423, over 4759.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2074, pruned_loss=0.02872, over 973932.04 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 03:00:22,279 INFO [train.py:715] (3/8) Epoch 17, batch 23550, loss[loss=0.1143, simple_loss=0.1906, pruned_loss=0.01896, over 4825.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02899, over 973166.04 frames.], batch size: 25, lr: 1.29e-04
+2022-05-09 03:01:01,965 INFO [train.py:715] (3/8) Epoch 17, batch 23600, loss[loss=0.1369, simple_loss=0.2019, pruned_loss=0.03591, over 4779.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02893, over 973248.46 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 03:01:40,306 INFO [train.py:715] (3/8) Epoch 17, batch 23650, loss[loss=0.1206, simple_loss=0.1844, pruned_loss=0.02834, over 4779.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02861, over 973527.67 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 03:02:19,918 INFO [train.py:715] (3/8) Epoch 17, batch 23700, loss[loss=0.1334, simple_loss=0.2069, pruned_loss=0.02997, over 4830.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02889, over 972734.56 frames.], batch size: 26, lr: 1.29e-04
+2022-05-09 03:02:59,508 INFO [train.py:715] (3/8) Epoch 17, batch 23750, loss[loss=0.1401, simple_loss=0.2186, pruned_loss=0.03076, over 4704.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2075, pruned_loss=0.02883, over 972979.82 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 03:03:38,384 INFO [train.py:715] (3/8) Epoch 17, batch 23800, loss[loss=0.1353, simple_loss=0.215, pruned_loss=0.02774, over 4879.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2083, pruned_loss=0.02922, over 972966.45 frames.], batch size: 22, lr: 1.29e-04
+2022-05-09 03:04:16,664 INFO [train.py:715] (3/8) Epoch 17, batch 23850, loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.031, over 4896.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2087, pruned_loss=0.02973, over 972851.30 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 03:04:56,707 INFO [train.py:715] (3/8) Epoch 17, batch 23900, loss[loss=0.1113, simple_loss=0.1868, pruned_loss=0.01793, over 4836.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02959, over 972139.84 frames.], batch size: 26, lr: 1.29e-04
+2022-05-09 03:05:35,869 INFO [train.py:715] (3/8) Epoch 17, batch 23950, loss[loss=0.118, simple_loss=0.19, pruned_loss=0.02302, over 4982.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02941, over 971934.67 frames.], batch size: 25, lr: 1.29e-04
+2022-05-09 03:06:14,199 INFO [train.py:715] (3/8) Epoch 17, batch 24000, loss[loss=0.1049, simple_loss=0.1887, pruned_loss=0.01057, over 4909.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02913, over 972254.17 frames.], batch size: 23, lr: 1.29e-04
+2022-05-09 03:06:14,200 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 03:06:24,067 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01067, over 914524.00 frames.
+2022-05-09 03:07:02,580 INFO [train.py:715] (3/8) Epoch 17, batch 24050, loss[loss=0.1378, simple_loss=0.2016, pruned_loss=0.03701, over 4778.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02923, over 971615.75 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 03:07:41,976 INFO [train.py:715] (3/8) Epoch 17, batch 24100, loss[loss=0.146, simple_loss=0.23, pruned_loss=0.03102, over 4768.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2075, pruned_loss=0.02899, over 972020.23 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 03:08:22,154 INFO [train.py:715] (3/8) Epoch 17, batch 24150, loss[loss=0.1622, simple_loss=0.2365, pruned_loss=0.04394, over 4801.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02913, over 971201.60 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 03:09:00,903 INFO [train.py:715] (3/8) Epoch 17, batch 24200, loss[loss=0.1183, simple_loss=0.1946, pruned_loss=0.02098, over 4943.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02909, over 971449.20 frames.], batch size: 23, lr: 1.29e-04
+2022-05-09 03:09:42,454 INFO [train.py:715] (3/8) Epoch 17, batch 24250, loss[loss=0.1146, simple_loss=0.1946, pruned_loss=0.01727, over 4831.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02901, over 971494.76 frames.], batch size: 26, lr: 1.29e-04
+2022-05-09 03:10:23,060 INFO [train.py:715] (3/8) Epoch 17, batch 24300, loss[loss=0.122, simple_loss=0.192, pruned_loss=0.02595, over 4854.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02913, over 971190.47 frames.], batch size: 32, lr: 1.29e-04
+2022-05-09 03:11:02,612 INFO [train.py:715] (3/8) Epoch 17, batch 24350, loss[loss=0.1325, simple_loss=0.2015, pruned_loss=0.03176, over 4755.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02912, over 971645.25 frames.], batch size: 16, lr: 1.29e-04
+2022-05-09 03:11:41,991 INFO [train.py:715] (3/8) Epoch 17, batch 24400, loss[loss=0.1363, simple_loss=0.2121, pruned_loss=0.03022, over 4796.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02868, over 971566.27 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 03:12:21,141 INFO [train.py:715] (3/8) Epoch 17, batch 24450, loss[loss=0.144, simple_loss=0.2193, pruned_loss=0.03433, over 4801.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2054, pruned_loss=0.02873, over 972023.28 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 03:13:01,330 INFO [train.py:715] (3/8) Epoch 17, batch 24500, loss[loss=0.1379, simple_loss=0.2199, pruned_loss=0.02799, over 4813.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.02845, over 971791.81 frames.], batch size: 25, lr: 1.29e-04
+2022-05-09 03:13:40,456 INFO [train.py:715] (3/8) Epoch 17, batch 24550, loss[loss=0.2015, simple_loss=0.2557, pruned_loss=0.0737, over 4792.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02878, over 972327.79 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 03:14:19,286 INFO [train.py:715] (3/8) Epoch 17, batch 24600, loss[loss=0.1438, simple_loss=0.2085, pruned_loss=0.03953, over 4898.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02888, over 973038.20 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 03:14:59,438 INFO [train.py:715] (3/8) Epoch 17, batch 24650, loss[loss=0.1216, simple_loss=0.1919, pruned_loss=0.02562, over 4986.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02855, over 973380.33 frames.], batch size: 28, lr: 1.29e-04
+2022-05-09 03:15:39,739 INFO [train.py:715] (3/8) Epoch 17, batch 24700, loss[loss=0.1252, simple_loss=0.1993, pruned_loss=0.02559, over 4981.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2055, pruned_loss=0.02866, over 973637.62 frames.], batch size: 28, lr: 1.29e-04
+2022-05-09 03:16:18,261 INFO [train.py:715] (3/8) Epoch 17, batch 24750, loss[loss=0.112, simple_loss=0.1869, pruned_loss=0.01856, over 4941.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02897, over 974010.75 frames.], batch size: 29, lr: 1.29e-04
+2022-05-09 03:16:58,095 INFO [train.py:715] (3/8) Epoch 17, batch 24800, loss[loss=0.1085, simple_loss=0.1788, pruned_loss=0.01912, over 4857.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2055, pruned_loss=0.02859, over 973219.16 frames.], batch size: 13, lr: 1.29e-04
+2022-05-09 03:17:37,936 INFO [train.py:715] (3/8) Epoch 17, batch 24850, loss[loss=0.1278, simple_loss=0.2074, pruned_loss=0.02405, over 4881.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.0286, over 973388.13 frames.], batch size: 16, lr: 1.29e-04
+2022-05-09 03:18:17,564 INFO [train.py:715] (3/8) Epoch 17, batch 24900, loss[loss=0.1321, simple_loss=0.2033, pruned_loss=0.03039, over 4699.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2047, pruned_loss=0.02827, over 971787.49 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 03:18:56,114 INFO [train.py:715] (3/8) Epoch 17, batch 24950, loss[loss=0.1263, simple_loss=0.1971, pruned_loss=0.02773, over 4853.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2047, pruned_loss=0.028, over 972921.12 frames.], batch size: 30, lr: 1.29e-04
+2022-05-09 03:19:35,619 INFO [train.py:715] (3/8) Epoch 17, batch 25000, loss[loss=0.1174, simple_loss=0.1983, pruned_loss=0.01824, over 4982.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2048, pruned_loss=0.02818, over 973485.72 frames.], batch size: 25, lr: 1.29e-04
+2022-05-09 03:20:14,001 INFO [train.py:715] (3/8) Epoch 17, batch 25050, loss[loss=0.1383, simple_loss=0.2135, pruned_loss=0.03148, over 4830.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02841, over 973952.47 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 03:20:53,000 INFO [train.py:715] (3/8) Epoch 17, batch 25100, loss[loss=0.168, simple_loss=0.2345, pruned_loss=0.05081, over 4909.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02888, over 973431.88 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 03:21:32,981 INFO [train.py:715] (3/8) Epoch 17, batch 25150, loss[loss=0.1145, simple_loss=0.1945, pruned_loss=0.01732, over 4795.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.0288, over 973440.97 frames.], batch size: 24, lr: 1.29e-04
+2022-05-09 03:22:12,874 INFO [train.py:715] (3/8) Epoch 17, batch 25200, loss[loss=0.1318, simple_loss=0.2105, pruned_loss=0.02654, over 4866.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02891, over 973429.65 frames.], batch size: 16, lr: 1.29e-04
+2022-05-09 03:22:51,916 INFO [train.py:715] (3/8) Epoch 17, batch 25250, loss[loss=0.1497, simple_loss=0.2329, pruned_loss=0.03327, over 4929.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02887, over 973532.63 frames.], batch size: 39, lr: 1.29e-04
+2022-05-09 03:23:31,034 INFO [train.py:715] (3/8) Epoch 17, batch 25300, loss[loss=0.1222, simple_loss=0.1987, pruned_loss=0.02288, over 4869.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02912, over 973035.45 frames.], batch size: 32, lr: 1.29e-04
+2022-05-09 03:24:11,041 INFO [train.py:715] (3/8) Epoch 17, batch 25350, loss[loss=0.1291, simple_loss=0.1964, pruned_loss=0.03088, over 4848.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02927, over 973617.03 frames.], batch size: 30, lr: 1.29e-04
+2022-05-09 03:24:49,785 INFO [train.py:715] (3/8) Epoch 17, batch 25400, loss[loss=0.1337, simple_loss=0.2198, pruned_loss=0.0238, over 4790.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.0287, over 972593.45 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 03:25:28,941 INFO [train.py:715] (3/8) Epoch 17, batch 25450, loss[loss=0.1283, simple_loss=0.2107, pruned_loss=0.02288, over 4779.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02883, over 972554.48 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 03:26:08,065 INFO [train.py:715] (3/8) Epoch 17, batch 25500, loss[loss=0.09696, simple_loss=0.1646, pruned_loss=0.01468, over 4773.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02869, over 972922.81 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 03:26:47,843 INFO [train.py:715] (3/8) Epoch 17, batch 25550, loss[loss=0.1324, simple_loss=0.2183, pruned_loss=0.02322, over 4832.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02891, over 972234.95 frames.], batch size: 26, lr: 1.29e-04
+2022-05-09 03:27:26,924 INFO [train.py:715] (3/8) Epoch 17, batch 25600, loss[loss=0.1204, simple_loss=0.1988, pruned_loss=0.021, over 4783.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02858, over 972614.28 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 03:28:05,428 INFO [train.py:715] (3/8) Epoch 17, batch 25650, loss[loss=0.1152, simple_loss=0.1857, pruned_loss=0.02235, over 4753.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.0287, over 972779.34 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 03:28:45,199 INFO [train.py:715] (3/8) Epoch 17, batch 25700, loss[loss=0.1229, simple_loss=0.2073, pruned_loss=0.01927, over 4916.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02871, over 971905.28 frames.], batch size: 39, lr: 1.29e-04
+2022-05-09 03:29:24,289 INFO [train.py:715] (3/8) Epoch 17, batch 25750, loss[loss=0.1279, simple_loss=0.2063, pruned_loss=0.02477, over 4689.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02931, over 970735.34 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 03:30:03,680 INFO [train.py:715] (3/8) Epoch 17, batch 25800, loss[loss=0.1321, simple_loss=0.2055, pruned_loss=0.02936, over 4955.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02993, over 971529.43 frames.], batch size: 35, lr: 1.29e-04
+2022-05-09 03:30:43,162 INFO [train.py:715] (3/8) Epoch 17, batch 25850, loss[loss=0.1163, simple_loss=0.1918, pruned_loss=0.02038, over 4793.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03012, over 971408.96 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 03:31:22,524 INFO [train.py:715] (3/8) Epoch 17, batch 25900, loss[loss=0.1286, simple_loss=0.2004, pruned_loss=0.02833, over 4832.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02984, over 971927.96 frames.], batch size: 26, lr: 1.29e-04
+2022-05-09 03:32:01,049 INFO [train.py:715] (3/8) Epoch 17, batch 25950, loss[loss=0.1372, simple_loss=0.2089, pruned_loss=0.03272, over 4800.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02976, over 972265.44 frames.], batch size: 24, lr: 1.29e-04
+2022-05-09 03:32:39,481 INFO [train.py:715] (3/8) Epoch 17, batch 26000, loss[loss=0.09862, simple_loss=0.1713, pruned_loss=0.01298, over 4790.00 frames.], tot_loss[loss=0.1333, simple_loss=0.207, pruned_loss=0.02973, over 971664.21 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 03:33:19,120 INFO [train.py:715] (3/8) Epoch 17, batch 26050, loss[loss=0.149, simple_loss=0.2255, pruned_loss=0.0363, over 4815.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02948, over 972241.11 frames.], batch size: 26, lr: 1.29e-04
+2022-05-09 03:33:57,728 INFO [train.py:715] (3/8) Epoch 17, batch 26100, loss[loss=0.1027, simple_loss=0.1761, pruned_loss=0.01466, over 4847.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02888, over 971401.48 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 03:34:37,125 INFO [train.py:715] (3/8) Epoch 17, batch 26150, loss[loss=0.1238, simple_loss=0.1994, pruned_loss=0.02414, over 4846.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02895, over 971286.07 frames.], batch size: 32, lr: 1.29e-04
+2022-05-09 03:35:16,510 INFO [train.py:715] (3/8) Epoch 17, batch 26200, loss[loss=0.1271, simple_loss=0.2047, pruned_loss=0.02481, over 4852.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02919, over 971899.41 frames.], batch size: 20, lr: 1.29e-04
+2022-05-09 03:35:56,481 INFO [train.py:715] (3/8) Epoch 17, batch 26250, loss[loss=0.1527, simple_loss=0.2239, pruned_loss=0.04069, over 4746.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02932, over 971519.01 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 03:36:35,145 INFO [train.py:715] (3/8) Epoch 17, batch 26300, loss[loss=0.1247, simple_loss=0.1976, pruned_loss=0.02588, over 4979.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02972, over 971576.87 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 03:37:13,924 INFO [train.py:715] (3/8) Epoch 17, batch 26350, loss[loss=0.122, simple_loss=0.1979, pruned_loss=0.02299, over 4822.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02915, over 970947.13 frames.], batch size: 25, lr: 1.29e-04
+2022-05-09 03:37:53,865 INFO [train.py:715] (3/8) Epoch 17, batch 26400, loss[loss=0.1298, simple_loss=0.2115, pruned_loss=0.02404, over 4870.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02937, over 970944.11 frames.], batch size: 22, lr: 1.29e-04
+2022-05-09 03:38:32,579 INFO [train.py:715] (3/8) Epoch 17, batch 26450, loss[loss=0.1135, simple_loss=0.1874, pruned_loss=0.01979, over 4974.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02957, over 971998.25 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 03:39:11,788 INFO [train.py:715] (3/8) Epoch 17, batch 26500, loss[loss=0.1564, simple_loss=0.2233, pruned_loss=0.04476, over 4920.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02965, over 972093.25 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 03:39:51,010 INFO [train.py:715] (3/8) Epoch 17, batch 26550, loss[loss=0.1307, simple_loss=0.2076, pruned_loss=0.02687, over 4871.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02937, over 971564.19 frames.], batch size: 22, lr: 1.29e-04
+2022-05-09 03:40:29,942 INFO [train.py:715] (3/8) Epoch 17, batch 26600, loss[loss=0.1149, simple_loss=0.1984, pruned_loss=0.01574, over 4933.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02893, over 971430.12 frames.], batch size: 23, lr: 1.29e-04
+2022-05-09 03:41:08,351 INFO [train.py:715] (3/8) Epoch 17, batch 26650, loss[loss=0.1447, simple_loss=0.2209, pruned_loss=0.0343, over 4852.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02902, over 971677.24 frames.], batch size: 20, lr: 1.29e-04
+2022-05-09 03:41:47,384 INFO [train.py:715] (3/8) Epoch 17, batch 26700, loss[loss=0.1304, simple_loss=0.2099, pruned_loss=0.02544, over 4820.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02863, over 970977.65 frames.], batch size: 25, lr: 1.29e-04
+2022-05-09 03:42:26,788 INFO [train.py:715] (3/8) Epoch 17, batch 26750, loss[loss=0.1318, simple_loss=0.199, pruned_loss=0.03228, over 4792.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02863, over 970937.75 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 03:43:05,135 INFO [train.py:715] (3/8) Epoch 17, batch 26800, loss[loss=0.121, simple_loss=0.194, pruned_loss=0.02402, over 4872.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.0287, over 971772.04 frames.], batch size: 22, lr: 1.29e-04
+2022-05-09 03:43:43,935 INFO [train.py:715] (3/8) Epoch 17, batch 26850, loss[loss=0.1196, simple_loss=0.2069, pruned_loss=0.01612, over 4765.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02875, over 972305.88 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 03:44:23,812 INFO [train.py:715] (3/8) Epoch 17, batch 26900, loss[loss=0.1272, simple_loss=0.2062, pruned_loss=0.02408, over 4970.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02862, over 972487.60 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 03:45:02,979 INFO [train.py:715] (3/8) Epoch 17, batch 26950, loss[loss=0.1249, simple_loss=0.2034, pruned_loss=0.02318, over 4990.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02849, over 972749.10 frames.], batch size: 28, lr: 1.29e-04
+2022-05-09 03:45:41,692 INFO [train.py:715] (3/8) Epoch 17, batch 27000, loss[loss=0.1434, simple_loss=0.2245, pruned_loss=0.0312, over 4959.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02841, over 972552.28 frames.], batch size: 39, lr: 1.29e-04
+2022-05-09 03:45:41,692 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 03:45:51,479 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.0107, over 914524.00 frames.
+2022-05-09 03:46:30,446 INFO [train.py:715] (3/8) Epoch 17, batch 27050, loss[loss=0.1161, simple_loss=0.1958, pruned_loss=0.01817, over 4815.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02878, over 972512.26 frames.], batch size: 21, lr: 1.29e-04
+2022-05-09 03:47:09,965 INFO [train.py:715] (3/8) Epoch 17, batch 27100, loss[loss=0.1093, simple_loss=0.1843, pruned_loss=0.01713, over 4777.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2061, pruned_loss=0.02912, over 973057.41 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 03:47:49,461 INFO [train.py:715] (3/8) Epoch 17, batch 27150, loss[loss=0.1623, simple_loss=0.2254, pruned_loss=0.04957, over 4787.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2062, pruned_loss=0.02941, over 973102.29 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 03:48:27,666 INFO [train.py:715] (3/8) Epoch 17, batch 27200, loss[loss=0.1455, simple_loss=0.2148, pruned_loss=0.03811, over 4762.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2057, pruned_loss=0.02924, over 972554.22 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 03:49:06,449 INFO [train.py:715] (3/8) Epoch 17, batch 27250, loss[loss=0.14, simple_loss=0.2084, pruned_loss=0.03582, over 4773.00 frames.], tot_loss[loss=0.1326, simple_loss=0.206, pruned_loss=0.02956, over 972379.54 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 03:49:46,075 INFO [train.py:715] (3/8) Epoch 17, batch 27300, loss[loss=0.1055, simple_loss=0.1758, pruned_loss=0.01761, over 4934.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02902, over 971906.29 frames.], batch size: 21, lr: 1.29e-04
+2022-05-09 03:50:25,158 INFO [train.py:715] (3/8) Epoch 17, batch 27350, loss[loss=0.1461, simple_loss=0.2122, pruned_loss=0.03999, over 4858.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02913, over 972760.09 frames.], batch size: 20, lr: 1.29e-04
+2022-05-09 03:51:04,595 INFO [train.py:715] (3/8) Epoch 17, batch 27400, loss[loss=0.1157, simple_loss=0.1875, pruned_loss=0.02191, over 4837.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02894, over 972581.63 frames.], batch size: 13, lr: 1.29e-04
+2022-05-09 03:51:43,498 INFO [train.py:715] (3/8) Epoch 17, batch 27450, loss[loss=0.1382, simple_loss=0.2138, pruned_loss=0.03134, over 4911.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02879, over 972457.44 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 03:52:23,143 INFO [train.py:715] (3/8) Epoch 17, batch 27500, loss[loss=0.1283, simple_loss=0.2065, pruned_loss=0.02508, over 4992.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02841, over 972680.55 frames.], batch size: 16, lr: 1.29e-04
+2022-05-09 03:53:01,812 INFO [train.py:715] (3/8) Epoch 17, batch 27550, loss[loss=0.1299, simple_loss=0.2124, pruned_loss=0.02372, over 4867.00 frames.], tot_loss[loss=0.132, simple_loss=0.207, pruned_loss=0.02852, over 972779.63 frames.], batch size: 20, lr: 1.29e-04
+2022-05-09 03:53:40,305 INFO [train.py:715] (3/8) Epoch 17, batch 27600, loss[loss=0.1439, simple_loss=0.2217, pruned_loss=0.03303, over 4764.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2073, pruned_loss=0.02854, over 972375.53 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 03:54:19,258 INFO [train.py:715] (3/8) Epoch 17, batch 27650, loss[loss=0.1122, simple_loss=0.1876, pruned_loss=0.01843, over 4842.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02882, over 972355.45 frames.], batch size: 30, lr: 1.29e-04
+2022-05-09 03:54:57,851 INFO [train.py:715] (3/8) Epoch 17, batch 27700, loss[loss=0.1211, simple_loss=0.2018, pruned_loss=0.0202, over 4983.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02867, over 972951.20 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 03:55:37,178 INFO [train.py:715] (3/8) Epoch 17, batch 27750, loss[loss=0.1125, simple_loss=0.1899, pruned_loss=0.01758, over 4830.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02871, over 972130.10 frames.], batch size: 26, lr: 1.29e-04
+2022-05-09 03:56:16,913 INFO [train.py:715] (3/8) Epoch 17, batch 27800, loss[loss=0.1399, simple_loss=0.2155, pruned_loss=0.03216, over 4778.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02869, over 972137.02 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 03:56:57,480 INFO [train.py:715] (3/8) Epoch 17, batch 27850, loss[loss=0.1544, simple_loss=0.2184, pruned_loss=0.04515, over 4790.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02939, over 971631.31 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 03:57:37,276 INFO [train.py:715] (3/8) Epoch 17, batch 27900, loss[loss=0.1594, simple_loss=0.2343, pruned_loss=0.0423, over 4943.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02941, over 972282.98 frames.], batch size: 23, lr: 1.29e-04
+2022-05-09 03:58:16,551 INFO [train.py:715] (3/8) Epoch 17, batch 27950, loss[loss=0.1187, simple_loss=0.1908, pruned_loss=0.02328, over 4925.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.0288, over 971236.08 frames.], batch size: 23, lr: 1.29e-04
+2022-05-09 03:58:56,515 INFO [train.py:715] (3/8) Epoch 17, batch 28000, loss[loss=0.1164, simple_loss=0.1947, pruned_loss=0.019, over 4892.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2076, pruned_loss=0.02892, over 971883.67 frames.], batch size: 22, lr: 1.29e-04
+2022-05-09 03:59:36,521 INFO [train.py:715] (3/8) Epoch 17, batch 28050, loss[loss=0.1235, simple_loss=0.1913, pruned_loss=0.02782, over 4987.00 frames.], tot_loss[loss=0.133, simple_loss=0.2081, pruned_loss=0.02899, over 972470.18 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 04:00:15,250 INFO [train.py:715] (3/8) Epoch 17, batch 28100, loss[loss=0.1527, simple_loss=0.2287, pruned_loss=0.03834, over 4959.00 frames.], tot_loss[loss=0.134, simple_loss=0.2087, pruned_loss=0.02964, over 973033.21 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:00:54,613 INFO [train.py:715] (3/8) Epoch 17, batch 28150, loss[loss=0.1164, simple_loss=0.1835, pruned_loss=0.02463, over 4805.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02932, over 972043.13 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 04:01:33,615 INFO [train.py:715] (3/8) Epoch 17, batch 28200, loss[loss=0.1209, simple_loss=0.1979, pruned_loss=0.0219, over 4957.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02936, over 972541.24 frames.], batch size: 35, lr: 1.29e-04
+2022-05-09 04:02:12,001 INFO [train.py:715] (3/8) Epoch 17, batch 28250, loss[loss=0.1447, simple_loss=0.217, pruned_loss=0.03619, over 4771.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02971, over 972755.93 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 04:02:50,450 INFO [train.py:715] (3/8) Epoch 17, batch 28300, loss[loss=0.1195, simple_loss=0.1998, pruned_loss=0.01954, over 4952.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2087, pruned_loss=0.02987, over 973012.01 frames.], batch size: 24, lr: 1.29e-04
+2022-05-09 04:03:29,617 INFO [train.py:715] (3/8) Epoch 17, batch 28350, loss[loss=0.1303, simple_loss=0.2073, pruned_loss=0.02664, over 4804.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.0302, over 973079.56 frames.], batch size: 21, lr: 1.29e-04
+2022-05-09 04:04:09,194 INFO [train.py:715] (3/8) Epoch 17, batch 28400, loss[loss=0.1248, simple_loss=0.198, pruned_loss=0.02582, over 4815.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02973, over 972940.57 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 04:04:48,215 INFO [train.py:715] (3/8) Epoch 17, batch 28450, loss[loss=0.1574, simple_loss=0.2263, pruned_loss=0.04426, over 4918.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02963, over 972469.02 frames.], batch size: 21, lr: 1.29e-04
+2022-05-09 04:05:26,443 INFO [train.py:715] (3/8) Epoch 17, batch 28500, loss[loss=0.1336, simple_loss=0.2128, pruned_loss=0.02721, over 4954.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02965, over 972812.39 frames.], batch size: 21, lr: 1.29e-04
+2022-05-09 04:06:06,461 INFO [train.py:715] (3/8) Epoch 17, batch 28550, loss[loss=0.1202, simple_loss=0.1958, pruned_loss=0.02227, over 4873.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02897, over 973247.44 frames.], batch size: 22, lr: 1.29e-04
+2022-05-09 04:06:45,100 INFO [train.py:715] (3/8) Epoch 17, batch 28600, loss[loss=0.1161, simple_loss=0.1938, pruned_loss=0.01925, over 4968.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02888, over 972597.49 frames.], batch size: 35, lr: 1.29e-04
+2022-05-09 04:07:23,872 INFO [train.py:715] (3/8) Epoch 17, batch 28650, loss[loss=0.1488, simple_loss=0.2221, pruned_loss=0.03776, over 4759.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02864, over 973269.85 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 04:08:02,257 INFO [train.py:715] (3/8) Epoch 17, batch 28700, loss[loss=0.1365, simple_loss=0.2095, pruned_loss=0.03177, over 4957.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02893, over 972991.54 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 04:08:41,576 INFO [train.py:715] (3/8) Epoch 17, batch 28750, loss[loss=0.1415, simple_loss=0.2141, pruned_loss=0.03448, over 4911.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02873, over 971890.99 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 04:09:20,209 INFO [train.py:715] (3/8) Epoch 17, batch 28800, loss[loss=0.1304, simple_loss=0.207, pruned_loss=0.02693, over 4693.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02853, over 971482.55 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:09:58,905 INFO [train.py:715] (3/8) Epoch 17, batch 28850, loss[loss=0.1329, simple_loss=0.2152, pruned_loss=0.02527, over 4982.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02846, over 971294.96 frames.], batch size: 25, lr: 1.29e-04
+2022-05-09 04:10:37,992 INFO [train.py:715] (3/8) Epoch 17, batch 28900, loss[loss=0.1313, simple_loss=0.212, pruned_loss=0.02533, over 4921.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02849, over 972047.68 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 04:11:16,521 INFO [train.py:715] (3/8) Epoch 17, batch 28950, loss[loss=0.09688, simple_loss=0.1611, pruned_loss=0.01635, over 4756.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.02856, over 972015.29 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 04:11:54,924 INFO [train.py:715] (3/8) Epoch 17, batch 29000, loss[loss=0.1313, simple_loss=0.2129, pruned_loss=0.02484, over 4910.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02854, over 972372.85 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 04:12:33,661 INFO [train.py:715] (3/8) Epoch 17, batch 29050, loss[loss=0.1264, simple_loss=0.2018, pruned_loss=0.02554, over 4862.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02822, over 971655.80 frames.], batch size: 38, lr: 1.29e-04
+2022-05-09 04:13:13,014 INFO [train.py:715] (3/8) Epoch 17, batch 29100, loss[loss=0.1521, simple_loss=0.2209, pruned_loss=0.04163, over 4810.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02838, over 972141.04 frames.], batch size: 24, lr: 1.29e-04
+2022-05-09 04:13:51,908 INFO [train.py:715] (3/8) Epoch 17, batch 29150, loss[loss=0.1254, simple_loss=0.2008, pruned_loss=0.02503, over 4974.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02878, over 971877.49 frames.], batch size: 25, lr: 1.29e-04
+2022-05-09 04:14:30,015 INFO [train.py:715] (3/8) Epoch 17, batch 29200, loss[loss=0.1089, simple_loss=0.1754, pruned_loss=0.02124, over 4972.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02869, over 972144.34 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:15:09,521 INFO [train.py:715] (3/8) Epoch 17, batch 29250, loss[loss=0.1358, simple_loss=0.2119, pruned_loss=0.02983, over 4986.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02899, over 972583.78 frames.], batch size: 27, lr: 1.29e-04
+2022-05-09 04:15:49,145 INFO [train.py:715] (3/8) Epoch 17, batch 29300, loss[loss=0.1021, simple_loss=0.1714, pruned_loss=0.01634, over 4801.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02955, over 972162.93 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 04:16:27,570 INFO [train.py:715] (3/8) Epoch 17, batch 29350, loss[loss=0.1322, simple_loss=0.1956, pruned_loss=0.03439, over 4865.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02952, over 971600.37 frames.], batch size: 32, lr: 1.29e-04
+2022-05-09 04:17:06,158 INFO [train.py:715] (3/8) Epoch 17, batch 29400, loss[loss=0.148, simple_loss=0.2213, pruned_loss=0.0374, over 4875.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02976, over 971340.16 frames.], batch size: 22, lr: 1.29e-04
+2022-05-09 04:17:45,841 INFO [train.py:715] (3/8) Epoch 17, batch 29450, loss[loss=0.1155, simple_loss=0.1929, pruned_loss=0.01904, over 4939.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.0297, over 971792.59 frames.], batch size: 23, lr: 1.29e-04
+2022-05-09 04:18:24,965 INFO [train.py:715] (3/8) Epoch 17, batch 29500, loss[loss=0.1519, simple_loss=0.2217, pruned_loss=0.04107, over 4783.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02928, over 972399.77 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 04:19:03,884 INFO [train.py:715] (3/8) Epoch 17, batch 29550, loss[loss=0.1372, simple_loss=0.2036, pruned_loss=0.03541, over 4777.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02908, over 972565.55 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 04:19:43,165 INFO [train.py:715] (3/8) Epoch 17, batch 29600, loss[loss=0.1097, simple_loss=0.1815, pruned_loss=0.01897, over 4804.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02887, over 972930.34 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 04:20:22,740 INFO [train.py:715] (3/8) Epoch 17, batch 29650, loss[loss=0.1073, simple_loss=0.1837, pruned_loss=0.01541, over 4932.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02871, over 972174.78 frames.], batch size: 21, lr: 1.29e-04
+2022-05-09 04:21:01,517 INFO [train.py:715] (3/8) Epoch 17, batch 29700, loss[loss=0.1295, simple_loss=0.2034, pruned_loss=0.02786, over 4918.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02843, over 971747.68 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 04:21:40,465 INFO [train.py:715] (3/8) Epoch 17, batch 29750, loss[loss=0.1312, simple_loss=0.2017, pruned_loss=0.03031, over 4776.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02881, over 971230.76 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 04:22:20,623 INFO [train.py:715] (3/8) Epoch 17, batch 29800, loss[loss=0.1474, simple_loss=0.2274, pruned_loss=0.03367, over 4823.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02917, over 971576.88 frames.], batch size: 26, lr: 1.29e-04
+2022-05-09 04:22:59,615 INFO [train.py:715] (3/8) Epoch 17, batch 29850, loss[loss=0.1458, simple_loss=0.21, pruned_loss=0.04078, over 4830.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02905, over 972726.72 frames.], batch size: 30, lr: 1.29e-04
+2022-05-09 04:23:38,911 INFO [train.py:715] (3/8) Epoch 17, batch 29900, loss[loss=0.1611, simple_loss=0.2371, pruned_loss=0.04253, over 4984.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02908, over 972760.87 frames.], batch size: 24, lr: 1.29e-04
+2022-05-09 04:24:18,621 INFO [train.py:715] (3/8) Epoch 17, batch 29950, loss[loss=0.1174, simple_loss=0.2009, pruned_loss=0.01698, over 4691.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02923, over 973125.98 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:24:58,025 INFO [train.py:715] (3/8) Epoch 17, batch 30000, loss[loss=0.1165, simple_loss=0.185, pruned_loss=0.024, over 4798.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02968, over 973080.58 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 04:24:58,026 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 04:25:08,260 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.01065, over 914524.00 frames.
+2022-05-09 04:25:48,089 INFO [train.py:715] (3/8) Epoch 17, batch 30050, loss[loss=0.1324, simple_loss=0.1993, pruned_loss=0.03274, over 4921.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.0297, over 973155.56 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 04:26:27,726 INFO [train.py:715] (3/8) Epoch 17, batch 30100, loss[loss=0.1439, simple_loss=0.2129, pruned_loss=0.03746, over 4780.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02919, over 972418.97 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 04:27:06,814 INFO [train.py:715] (3/8) Epoch 17, batch 30150, loss[loss=0.1133, simple_loss=0.1877, pruned_loss=0.01949, over 4877.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02937, over 973147.35 frames.], batch size: 16, lr: 1.29e-04
+2022-05-09 04:27:46,315 INFO [train.py:715] (3/8) Epoch 17, batch 30200, loss[loss=0.1587, simple_loss=0.229, pruned_loss=0.04425, over 4846.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02952, over 972247.61 frames.], batch size: 30, lr: 1.29e-04
+2022-05-09 04:28:25,427 INFO [train.py:715] (3/8) Epoch 17, batch 30250, loss[loss=0.1168, simple_loss=0.2027, pruned_loss=0.01546, over 4978.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02949, over 972186.31 frames.], batch size: 24, lr: 1.29e-04
+2022-05-09 04:29:04,419 INFO [train.py:715] (3/8) Epoch 17, batch 30300, loss[loss=0.12, simple_loss=0.1922, pruned_loss=0.02394, over 4908.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02905, over 972655.52 frames.], batch size: 29, lr: 1.29e-04
+2022-05-09 04:29:44,186 INFO [train.py:715] (3/8) Epoch 17, batch 30350, loss[loss=0.1201, simple_loss=0.1912, pruned_loss=0.02455, over 4994.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02875, over 972710.49 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 04:30:23,369 INFO [train.py:715] (3/8) Epoch 17, batch 30400, loss[loss=0.1594, simple_loss=0.2228, pruned_loss=0.04796, over 4880.00 frames.], tot_loss[loss=0.132, simple_loss=0.2059, pruned_loss=0.02903, over 971614.13 frames.], batch size: 22, lr: 1.29e-04
+2022-05-09 04:31:02,093 INFO [train.py:715] (3/8) Epoch 17, batch 30450, loss[loss=0.1145, simple_loss=0.1867, pruned_loss=0.02114, over 4907.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2054, pruned_loss=0.02886, over 971863.93 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 04:31:41,825 INFO [train.py:715] (3/8) Epoch 17, batch 30500, loss[loss=0.132, simple_loss=0.198, pruned_loss=0.03302, over 4974.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02867, over 972220.29 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:32:21,635 INFO [train.py:715] (3/8) Epoch 17, batch 30550, loss[loss=0.1489, simple_loss=0.2175, pruned_loss=0.04018, over 4857.00 frames.], tot_loss[loss=0.1313, simple_loss=0.205, pruned_loss=0.0288, over 971963.25 frames.], batch size: 20, lr: 1.29e-04
+2022-05-09 04:33:01,421 INFO [train.py:715] (3/8) Epoch 17, batch 30600, loss[loss=0.1287, simple_loss=0.2087, pruned_loss=0.02433, over 4766.00 frames.], tot_loss[loss=0.131, simple_loss=0.205, pruned_loss=0.02847, over 971350.24 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 04:33:40,316 INFO [train.py:715] (3/8) Epoch 17, batch 30650, loss[loss=0.1078, simple_loss=0.1804, pruned_loss=0.01758, over 4770.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02851, over 971404.21 frames.], batch size: 12, lr: 1.29e-04
+2022-05-09 04:34:20,059 INFO [train.py:715] (3/8) Epoch 17, batch 30700, loss[loss=0.1198, simple_loss=0.1895, pruned_loss=0.02508, over 4760.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2042, pruned_loss=0.02808, over 971197.55 frames.], batch size: 16, lr: 1.29e-04
+2022-05-09 04:34:59,087 INFO [train.py:715] (3/8) Epoch 17, batch 30750, loss[loss=0.134, simple_loss=0.2041, pruned_loss=0.032, over 4743.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2048, pruned_loss=0.02855, over 971675.18 frames.], batch size: 16, lr: 1.29e-04
+2022-05-09 04:35:38,913 INFO [train.py:715] (3/8) Epoch 17, batch 30800, loss[loss=0.1488, simple_loss=0.2323, pruned_loss=0.0327, over 4790.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2048, pruned_loss=0.02836, over 971643.13 frames.], batch size: 24, lr: 1.29e-04
+2022-05-09 04:36:18,142 INFO [train.py:715] (3/8) Epoch 17, batch 30850, loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03357, over 4971.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02826, over 971980.99 frames.], batch size: 39, lr: 1.29e-04
+2022-05-09 04:36:58,384 INFO [train.py:715] (3/8) Epoch 17, batch 30900, loss[loss=0.1162, simple_loss=0.194, pruned_loss=0.01919, over 4867.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02825, over 972010.56 frames.], batch size: 20, lr: 1.29e-04
+2022-05-09 04:37:38,031 INFO [train.py:715] (3/8) Epoch 17, batch 30950, loss[loss=0.1162, simple_loss=0.1832, pruned_loss=0.02462, over 4769.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02832, over 972522.01 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 04:38:17,301 INFO [train.py:715] (3/8) Epoch 17, batch 31000, loss[loss=0.1529, simple_loss=0.2339, pruned_loss=0.03594, over 4968.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02907, over 972171.85 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:38:57,010 INFO [train.py:715] (3/8) Epoch 17, batch 31050, loss[loss=0.128, simple_loss=0.2011, pruned_loss=0.02747, over 4929.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02923, over 972531.37 frames.], batch size: 29, lr: 1.29e-04
+2022-05-09 04:39:36,078 INFO [train.py:715] (3/8) Epoch 17, batch 31100, loss[loss=0.1378, simple_loss=0.2137, pruned_loss=0.03096, over 4702.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02963, over 972191.39 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:40:15,213 INFO [train.py:715] (3/8) Epoch 17, batch 31150, loss[loss=0.1573, simple_loss=0.2344, pruned_loss=0.04007, over 4969.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02943, over 972435.05 frames.], batch size: 24, lr: 1.29e-04
+2022-05-09 04:40:54,497 INFO [train.py:715] (3/8) Epoch 17, batch 31200, loss[loss=0.1432, simple_loss=0.226, pruned_loss=0.03025, over 4917.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02877, over 972133.69 frames.], batch size: 23, lr: 1.29e-04
+2022-05-09 04:41:34,596 INFO [train.py:715] (3/8) Epoch 17, batch 31250, loss[loss=0.1469, simple_loss=0.2363, pruned_loss=0.02874, over 4814.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02926, over 972510.69 frames.], batch size: 27, lr: 1.29e-04
+2022-05-09 04:42:13,893 INFO [train.py:715] (3/8) Epoch 17, batch 31300, loss[loss=0.1261, simple_loss=0.2027, pruned_loss=0.02477, over 4870.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.0289, over 972918.78 frames.], batch size: 30, lr: 1.29e-04
+2022-05-09 04:42:53,280 INFO [train.py:715] (3/8) Epoch 17, batch 31350, loss[loss=0.1173, simple_loss=0.1875, pruned_loss=0.0235, over 4869.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02942, over 973269.90 frames.], batch size: 20, lr: 1.29e-04
+2022-05-09 04:43:32,645 INFO [train.py:715] (3/8) Epoch 17, batch 31400, loss[loss=0.1399, simple_loss=0.2192, pruned_loss=0.03028, over 4799.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02968, over 973211.89 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 04:44:11,255 INFO [train.py:715] (3/8) Epoch 17, batch 31450, loss[loss=0.1172, simple_loss=0.1951, pruned_loss=0.01967, over 4760.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.0294, over 973488.46 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 04:44:51,214 INFO [train.py:715] (3/8) Epoch 17, batch 31500, loss[loss=0.1254, simple_loss=0.1989, pruned_loss=0.02595, over 4834.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02912, over 973636.47 frames.], batch size: 26, lr: 1.29e-04
+2022-05-09 04:45:29,939 INFO [train.py:715] (3/8) Epoch 17, batch 31550, loss[loss=0.1255, simple_loss=0.203, pruned_loss=0.02396, over 4985.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02907, over 973705.39 frames.], batch size: 25, lr: 1.29e-04
+2022-05-09 04:46:09,493 INFO [train.py:715] (3/8) Epoch 17, batch 31600, loss[loss=0.1675, simple_loss=0.2295, pruned_loss=0.05274, over 4969.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02904, over 972546.22 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:46:48,901 INFO [train.py:715] (3/8) Epoch 17, batch 31650, loss[loss=0.1581, simple_loss=0.2216, pruned_loss=0.04736, over 4832.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02893, over 973297.01 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:47:28,182 INFO [train.py:715] (3/8) Epoch 17, batch 31700, loss[loss=0.1317, simple_loss=0.2121, pruned_loss=0.02562, over 4885.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02889, over 972922.23 frames.], batch size: 22, lr: 1.29e-04
+2022-05-09 04:48:07,939 INFO [train.py:715] (3/8) Epoch 17, batch 31750, loss[loss=0.1875, simple_loss=0.2687, pruned_loss=0.05311, over 4768.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02903, over 972341.10 frames.], batch size: 17, lr: 1.29e-04
+2022-05-09 04:48:47,177 INFO [train.py:715] (3/8) Epoch 17, batch 31800, loss[loss=0.1152, simple_loss=0.1972, pruned_loss=0.01662, over 4890.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02929, over 972877.50 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 04:49:27,378 INFO [train.py:715] (3/8) Epoch 17, batch 31850, loss[loss=0.1514, simple_loss=0.2197, pruned_loss=0.04153, over 4750.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02962, over 972524.75 frames.], batch size: 16, lr: 1.29e-04
+2022-05-09 04:50:06,508 INFO [train.py:715] (3/8) Epoch 17, batch 31900, loss[loss=0.1356, simple_loss=0.2062, pruned_loss=0.03249, over 4758.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02925, over 972655.13 frames.], batch size: 19, lr: 1.29e-04
+2022-05-09 04:50:45,988 INFO [train.py:715] (3/8) Epoch 17, batch 31950, loss[loss=0.1211, simple_loss=0.1994, pruned_loss=0.02136, over 4843.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02907, over 972024.03 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:51:25,762 INFO [train.py:715] (3/8) Epoch 17, batch 32000, loss[loss=0.1476, simple_loss=0.2258, pruned_loss=0.03466, over 4928.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.0295, over 972187.90 frames.], batch size: 23, lr: 1.29e-04
+2022-05-09 04:52:04,649 INFO [train.py:715] (3/8) Epoch 17, batch 32050, loss[loss=0.1637, simple_loss=0.2422, pruned_loss=0.04266, over 4865.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2082, pruned_loss=0.0295, over 971759.50 frames.], batch size: 20, lr: 1.29e-04
+2022-05-09 04:52:44,370 INFO [train.py:715] (3/8) Epoch 17, batch 32100, loss[loss=0.1256, simple_loss=0.2058, pruned_loss=0.02272, over 4847.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02971, over 972307.96 frames.], batch size: 13, lr: 1.29e-04
+2022-05-09 04:53:23,404 INFO [train.py:715] (3/8) Epoch 17, batch 32150, loss[loss=0.1594, simple_loss=0.2352, pruned_loss=0.04177, over 4955.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02989, over 972730.03 frames.], batch size: 39, lr: 1.29e-04
+2022-05-09 04:54:02,757 INFO [train.py:715] (3/8) Epoch 17, batch 32200, loss[loss=0.1504, simple_loss=0.2288, pruned_loss=0.03596, over 4919.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02951, over 972057.99 frames.], batch size: 23, lr: 1.29e-04
+2022-05-09 04:54:45,063 INFO [train.py:715] (3/8) Epoch 17, batch 32250, loss[loss=0.1058, simple_loss=0.1781, pruned_loss=0.01673, over 4974.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02962, over 971447.94 frames.], batch size: 14, lr: 1.29e-04
+2022-05-09 04:55:24,425 INFO [train.py:715] (3/8) Epoch 17, batch 32300, loss[loss=0.1442, simple_loss=0.2233, pruned_loss=0.03252, over 4813.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02983, over 970903.70 frames.], batch size: 25, lr: 1.29e-04
+2022-05-09 04:56:04,350 INFO [train.py:715] (3/8) Epoch 17, batch 32350, loss[loss=0.1443, simple_loss=0.2249, pruned_loss=0.03186, over 4836.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.03, over 971164.63 frames.], batch size: 15, lr: 1.29e-04
+2022-05-09 04:56:43,384 INFO [train.py:715] (3/8) Epoch 17, batch 32400, loss[loss=0.1279, simple_loss=0.2056, pruned_loss=0.0251, over 4797.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02913, over 971102.61 frames.], batch size: 18, lr: 1.29e-04
+2022-05-09 04:57:22,533 INFO [train.py:715] (3/8) Epoch 17, batch 32450, loss[loss=0.1533, simple_loss=0.2262, pruned_loss=0.0402, over 4982.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02932, over 972602.80 frames.], batch size: 14, lr: 1.28e-04
+2022-05-09 04:58:02,559 INFO [train.py:715] (3/8) Epoch 17, batch 32500, loss[loss=0.1376, simple_loss=0.2071, pruned_loss=0.03407, over 4862.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02926, over 972986.46 frames.], batch size: 32, lr: 1.28e-04
+2022-05-09 04:58:41,968 INFO [train.py:715] (3/8) Epoch 17, batch 32550, loss[loss=0.1156, simple_loss=0.1883, pruned_loss=0.02146, over 4915.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.029, over 972531.33 frames.], batch size: 39, lr: 1.28e-04
+2022-05-09 04:59:21,559 INFO [train.py:715] (3/8) Epoch 17, batch 32600, loss[loss=0.1223, simple_loss=0.2017, pruned_loss=0.02146, over 4644.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02908, over 970662.15 frames.], batch size: 13, lr: 1.28e-04
+2022-05-09 05:00:01,072 INFO [train.py:715] (3/8) Epoch 17, batch 32650, loss[loss=0.1309, simple_loss=0.2024, pruned_loss=0.02966, over 4896.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02869, over 971383.47 frames.], batch size: 22, lr: 1.28e-04
+2022-05-09 05:00:39,806 INFO [train.py:715] (3/8) Epoch 17, batch 32700, loss[loss=0.1309, simple_loss=0.2037, pruned_loss=0.02908, over 4868.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2072, pruned_loss=0.02873, over 971432.00 frames.], batch size: 32, lr: 1.28e-04
+2022-05-09 05:01:19,988 INFO [train.py:715] (3/8) Epoch 17, batch 32750, loss[loss=0.1142, simple_loss=0.1903, pruned_loss=0.01899, over 4882.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02856, over 971699.39 frames.], batch size: 22, lr: 1.28e-04
+2022-05-09 05:01:59,336 INFO [train.py:715] (3/8) Epoch 17, batch 32800, loss[loss=0.1346, simple_loss=0.201, pruned_loss=0.03411, over 4902.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.0282, over 971647.20 frames.], batch size: 17, lr: 1.28e-04
+2022-05-09 05:02:38,972 INFO [train.py:715] (3/8) Epoch 17, batch 32850, loss[loss=0.1328, simple_loss=0.209, pruned_loss=0.02829, over 4968.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02836, over 971721.93 frames.], batch size: 24, lr: 1.28e-04
+2022-05-09 05:03:18,521 INFO [train.py:715] (3/8) Epoch 17, batch 32900, loss[loss=0.1316, simple_loss=0.2104, pruned_loss=0.02646, over 4948.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02816, over 972576.84 frames.], batch size: 21, lr: 1.28e-04
+2022-05-09 05:03:58,027 INFO [train.py:715] (3/8) Epoch 17, batch 32950, loss[loss=0.1453, simple_loss=0.2289, pruned_loss=0.03083, over 4865.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.028, over 972258.88 frames.], batch size: 16, lr: 1.28e-04
+2022-05-09 05:04:36,961 INFO [train.py:715] (3/8) Epoch 17, batch 33000, loss[loss=0.1201, simple_loss=0.1933, pruned_loss=0.02349, over 4930.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02807, over 971957.02 frames.], batch size: 18, lr: 1.28e-04
+2022-05-09 05:04:36,961 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 05:04:49,645 INFO [train.py:742] (3/8) Epoch 17, validation: loss=0.1049, simple_loss=0.1881, pruned_loss=0.0108, over 914524.00 frames.
+2022-05-09 05:05:28,989 INFO [train.py:715] (3/8) Epoch 17, batch 33050, loss[loss=0.1285, simple_loss=0.2088, pruned_loss=0.02413, over 4837.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02832, over 972667.71 frames.], batch size: 13, lr: 1.28e-04
+2022-05-09 05:06:08,146 INFO [train.py:715] (3/8) Epoch 17, batch 33100, loss[loss=0.1208, simple_loss=0.1843, pruned_loss=0.02868, over 4836.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02867, over 973613.80 frames.], batch size: 13, lr: 1.28e-04
+2022-05-09 05:06:47,450 INFO [train.py:715] (3/8) Epoch 17, batch 33150, loss[loss=0.1357, simple_loss=0.2055, pruned_loss=0.03297, over 4790.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02868, over 973021.12 frames.], batch size: 24, lr: 1.28e-04
+2022-05-09 05:07:27,184 INFO [train.py:715] (3/8) Epoch 17, batch 33200, loss[loss=0.1495, simple_loss=0.2128, pruned_loss=0.04313, over 4963.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02912, over 973414.77 frames.], batch size: 24, lr: 1.28e-04
+2022-05-09 05:08:06,794 INFO [train.py:715] (3/8) Epoch 17, batch 33250, loss[loss=0.1401, simple_loss=0.2244, pruned_loss=0.02791, over 4821.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02866, over 973230.64 frames.], batch size: 26, lr: 1.28e-04
+2022-05-09 05:08:46,105 INFO [train.py:715] (3/8) Epoch 17, batch 33300, loss[loss=0.1349, simple_loss=0.1975, pruned_loss=0.0362, over 4693.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02939, over 972012.30 frames.], batch size: 15, lr: 1.28e-04
+2022-05-09 05:09:25,687 INFO [train.py:715] (3/8) Epoch 17, batch 33350, loss[loss=0.1444, simple_loss=0.2186, pruned_loss=0.03516, over 4939.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02926, over 971876.61 frames.], batch size: 24, lr: 1.28e-04
+2022-05-09 05:10:05,483 INFO [train.py:715] (3/8) Epoch 17, batch 33400, loss[loss=0.1167, simple_loss=0.1913, pruned_loss=0.02107, over 4804.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02934, over 972210.82 frames.], batch size: 12, lr: 1.28e-04
+2022-05-09 05:10:44,825 INFO [train.py:715] (3/8) Epoch 17, batch 33450, loss[loss=0.1216, simple_loss=0.2019, pruned_loss=0.02067, over 4920.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2075, pruned_loss=0.02889, over 972293.20 frames.], batch size: 18, lr: 1.28e-04
+2022-05-09 05:11:24,375 INFO [train.py:715] (3/8) Epoch 17, batch 33500, loss[loss=0.171, simple_loss=0.2328, pruned_loss=0.05454, over 4957.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02915, over 972465.45 frames.], batch size: 35, lr: 1.28e-04
+2022-05-09 05:12:04,588 INFO [train.py:715] (3/8) Epoch 17, batch 33550, loss[loss=0.1023, simple_loss=0.1752, pruned_loss=0.0147, over 4927.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02891, over 972899.80 frames.], batch size: 23, lr: 1.28e-04
+2022-05-09 05:12:44,745 INFO [train.py:715] (3/8) Epoch 17, batch 33600, loss[loss=0.1254, simple_loss=0.1934, pruned_loss=0.02873, over 4790.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.029, over 972603.22 frames.], batch size: 14, lr: 1.28e-04
+2022-05-09 05:13:23,722 INFO [train.py:715] (3/8) Epoch 17, batch 33650, loss[loss=0.1238, simple_loss=0.2, pruned_loss=0.02382, over 4943.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02933, over 972720.26 frames.], batch size: 29, lr: 1.28e-04
+2022-05-09 05:14:03,358 INFO [train.py:715] (3/8) Epoch 17, batch 33700, loss[loss=0.1387, simple_loss=0.2155, pruned_loss=0.03096, over 4796.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02903, over 972661.87 frames.], batch size: 24, lr: 1.28e-04
+2022-05-09 05:14:42,577 INFO [train.py:715] (3/8) Epoch 17, batch 33750, loss[loss=0.1346, simple_loss=0.2038, pruned_loss=0.03267, over 4968.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.0295, over 972498.33 frames.], batch size: 15, lr: 1.28e-04
+2022-05-09 05:15:21,395 INFO [train.py:715] (3/8) Epoch 17, batch 33800, loss[loss=0.1367, simple_loss=0.2207, pruned_loss=0.02638, over 4923.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02951, over 971809.15 frames.], batch size: 18, lr: 1.28e-04
+2022-05-09 05:16:01,528 INFO [train.py:715] (3/8) Epoch 17, batch 33850, loss[loss=0.1273, simple_loss=0.206, pruned_loss=0.02435, over 4766.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02908, over 971528.09 frames.], batch size: 19, lr: 1.28e-04
+2022-05-09 05:16:41,836 INFO [train.py:715] (3/8) Epoch 17, batch 33900, loss[loss=0.1522, simple_loss=0.2328, pruned_loss=0.03577, over 4809.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02941, over 971607.94 frames.], batch size: 25, lr: 1.28e-04
+2022-05-09 05:17:21,090 INFO [train.py:715] (3/8) Epoch 17, batch 33950, loss[loss=0.1529, simple_loss=0.23, pruned_loss=0.03788, over 4776.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02941, over 971710.10 frames.], batch size: 18, lr: 1.28e-04
+2022-05-09 05:18:00,095 INFO [train.py:715] (3/8) Epoch 17, batch 34000, loss[loss=0.119, simple_loss=0.1947, pruned_loss=0.02161, over 4926.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02941, over 973223.68 frames.], batch size: 21, lr: 1.28e-04
+2022-05-09 05:18:39,509 INFO [train.py:715] (3/8) Epoch 17, batch 34050, loss[loss=0.1469, simple_loss=0.2274, pruned_loss=0.03318, over 4812.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02991, over 972828.07 frames.], batch size: 26, lr: 1.28e-04
+2022-05-09 05:19:19,505 INFO [train.py:715] (3/8) Epoch 17, batch 34100, loss[loss=0.1289, simple_loss=0.2076, pruned_loss=0.02506, over 4862.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02951, over 973775.80 frames.], batch size: 20, lr: 1.28e-04
+2022-05-09 05:19:58,309 INFO [train.py:715] (3/8) Epoch 17, batch 34150, loss[loss=0.1354, simple_loss=0.2099, pruned_loss=0.03048, over 4941.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02918, over 973323.57 frames.], batch size: 21, lr: 1.28e-04
+2022-05-09 05:20:37,450 INFO [train.py:715] (3/8) Epoch 17, batch 34200, loss[loss=0.1137, simple_loss=0.1851, pruned_loss=0.0211, over 4798.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02909, over 972795.34 frames.], batch size: 12, lr: 1.28e-04
+2022-05-09 05:21:16,560 INFO [train.py:715] (3/8) Epoch 17, batch 34250, loss[loss=0.1259, simple_loss=0.2087, pruned_loss=0.02154, over 4936.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02914, over 973340.20 frames.], batch size: 39, lr: 1.28e-04
+2022-05-09 05:21:55,281 INFO [train.py:715] (3/8) Epoch 17, batch 34300, loss[loss=0.1254, simple_loss=0.1982, pruned_loss=0.02628, over 4749.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02939, over 973452.02 frames.], batch size: 19, lr: 1.28e-04
+2022-05-09 05:22:34,167 INFO [train.py:715] (3/8) Epoch 17, batch 34350, loss[loss=0.1271, simple_loss=0.2058, pruned_loss=0.02422, over 4968.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02901, over 973198.02 frames.], batch size: 24, lr: 1.28e-04
+2022-05-09 05:23:13,526 INFO [train.py:715] (3/8) Epoch 17, batch 34400, loss[loss=0.1122, simple_loss=0.1788, pruned_loss=0.02281, over 4860.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02858, over 972302.96 frames.], batch size: 20, lr: 1.28e-04
+2022-05-09 05:23:52,516 INFO [train.py:715] (3/8) Epoch 17, batch 34450, loss[loss=0.1254, simple_loss=0.1905, pruned_loss=0.03011, over 4925.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02884, over 972094.25 frames.], batch size: 18, lr: 1.28e-04
+2022-05-09 05:24:30,968 INFO [train.py:715] (3/8) Epoch 17, batch 34500, loss[loss=0.1363, simple_loss=0.2114, pruned_loss=0.03065, over 4982.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02881, over 972003.01 frames.], batch size: 33, lr: 1.28e-04
+2022-05-09 05:25:09,845 INFO [train.py:715] (3/8) Epoch 17, batch 34550, loss[loss=0.1446, simple_loss=0.2145, pruned_loss=0.03736, over 4844.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02885, over 971871.24 frames.], batch size: 32, lr: 1.28e-04
+2022-05-09 05:25:48,994 INFO [train.py:715] (3/8) Epoch 17, batch 34600, loss[loss=0.1347, simple_loss=0.2092, pruned_loss=0.03011, over 4932.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.0288, over 971778.30 frames.], batch size: 18, lr: 1.28e-04
+2022-05-09 05:26:27,693 INFO [train.py:715] (3/8) Epoch 17, batch 34650, loss[loss=0.1234, simple_loss=0.1946, pruned_loss=0.02615, over 4948.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02877, over 972310.69 frames.], batch size: 29, lr: 1.28e-04
+2022-05-09 05:27:06,961 INFO [train.py:715] (3/8) Epoch 17, batch 34700, loss[loss=0.1375, simple_loss=0.2133, pruned_loss=0.03085, over 4824.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02967, over 972003.78 frames.], batch size: 15, lr: 1.28e-04
+2022-05-09 05:27:45,507 INFO [train.py:715] (3/8) Epoch 17, batch 34750, loss[loss=0.1321, simple_loss=0.2048, pruned_loss=0.02973, over 4946.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02951, over 972151.80 frames.], batch size: 29, lr: 1.28e-04
+2022-05-09 05:28:22,197 INFO [train.py:715] (3/8) Epoch 17, batch 34800, loss[loss=0.1294, simple_loss=0.1988, pruned_loss=0.02998, over 4762.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02914, over 971703.33 frames.], batch size: 12, lr: 1.28e-04
+2022-05-09 05:29:12,357 INFO [train.py:715] (3/8) Epoch 18, batch 0, loss[loss=0.1278, simple_loss=0.2052, pruned_loss=0.02521, over 4865.00 frames.], tot_loss[loss=0.1278, simple_loss=0.2052, pruned_loss=0.02521, over 4865.00 frames.], batch size: 20, lr: 1.25e-04
+2022-05-09 05:29:51,058 INFO [train.py:715] (3/8) Epoch 18, batch 50, loss[loss=0.1568, simple_loss=0.2244, pruned_loss=0.04461, over 4979.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02936, over 219512.27 frames.], batch size: 39, lr: 1.25e-04
+2022-05-09 05:30:31,043 INFO [train.py:715] (3/8) Epoch 18, batch 100, loss[loss=0.1251, simple_loss=0.2046, pruned_loss=0.02282, over 4747.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02935, over 386828.60 frames.], batch size: 16, lr: 1.25e-04
+2022-05-09 05:31:10,960 INFO [train.py:715] (3/8) Epoch 18, batch 150, loss[loss=0.1359, simple_loss=0.2196, pruned_loss=0.02611, over 4949.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02836, over 517312.67 frames.], batch size: 21, lr: 1.25e-04
+2022-05-09 05:31:50,260 INFO [train.py:715] (3/8) Epoch 18, batch 200, loss[loss=0.1323, simple_loss=0.2058, pruned_loss=0.02942, over 4828.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02811, over 618981.09 frames.], batch size: 15, lr: 1.25e-04
+2022-05-09 05:32:29,109 INFO [train.py:715] (3/8) Epoch 18, batch 250, loss[loss=0.1204, simple_loss=0.1979, pruned_loss=0.02145, over 4704.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.0283, over 696943.39 frames.], batch size: 15, lr: 1.25e-04
+2022-05-09 05:33:08,564 INFO [train.py:715] (3/8) Epoch 18, batch 300, loss[loss=0.1157, simple_loss=0.1909, pruned_loss=0.02028, over 4771.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02946, over 757574.97 frames.], batch size: 14, lr: 1.25e-04
+2022-05-09 05:33:48,415 INFO [train.py:715] (3/8) Epoch 18, batch 350, loss[loss=0.2061, simple_loss=0.2807, pruned_loss=0.06577, over 4793.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02922, over 805159.35 frames.], batch size: 14, lr: 1.25e-04
+2022-05-09 05:34:27,358 INFO [train.py:715] (3/8) Epoch 18, batch 400, loss[loss=0.1264, simple_loss=0.1948, pruned_loss=0.02903, over 4892.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02946, over 841871.44 frames.], batch size: 19, lr: 1.25e-04
+2022-05-09 05:35:07,143 INFO [train.py:715] (3/8) Epoch 18, batch 450, loss[loss=0.1291, simple_loss=0.1984, pruned_loss=0.02992, over 4809.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02932, over 870741.86 frames.], batch size: 21, lr: 1.25e-04
+2022-05-09 05:35:47,325 INFO [train.py:715] (3/8) Epoch 18, batch 500, loss[loss=0.12, simple_loss=0.1965, pruned_loss=0.02174, over 4805.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02926, over 892645.86 frames.], batch size: 26, lr: 1.25e-04
+2022-05-09 05:36:27,093 INFO [train.py:715] (3/8) Epoch 18, batch 550, loss[loss=0.1409, simple_loss=0.2088, pruned_loss=0.03651, over 4979.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02978, over 909889.32 frames.], batch size: 14, lr: 1.25e-04
+2022-05-09 05:37:06,105 INFO [train.py:715] (3/8) Epoch 18, batch 600, loss[loss=0.1391, simple_loss=0.214, pruned_loss=0.03203, over 4976.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.0299, over 923331.75 frames.], batch size: 39, lr: 1.25e-04
+2022-05-09 05:37:45,638 INFO [train.py:715] (3/8) Epoch 18, batch 650, loss[loss=0.149, simple_loss=0.2233, pruned_loss=0.03732, over 4902.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02922, over 934071.00 frames.], batch size: 17, lr: 1.25e-04
+2022-05-09 05:38:25,477 INFO [train.py:715] (3/8) Epoch 18, batch 700, loss[loss=0.1301, simple_loss=0.2077, pruned_loss=0.02622, over 4762.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02909, over 941994.89 frames.], batch size: 19, lr: 1.25e-04
+2022-05-09 05:39:04,428 INFO [train.py:715] (3/8) Epoch 18, batch 750, loss[loss=0.1156, simple_loss=0.1969, pruned_loss=0.01716, over 4938.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02889, over 949323.23 frames.], batch size: 21, lr: 1.25e-04
+2022-05-09 05:39:43,256 INFO [train.py:715] (3/8) Epoch 18, batch 800, loss[loss=0.121, simple_loss=0.2036, pruned_loss=0.01916, over 4818.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02893, over 954933.19 frames.], batch size: 25, lr: 1.25e-04
+2022-05-09 05:40:22,749 INFO [train.py:715] (3/8) Epoch 18, batch 850, loss[loss=0.1098, simple_loss=0.1761, pruned_loss=0.02168, over 4821.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02862, over 959319.79 frames.], batch size: 12, lr: 1.25e-04
+2022-05-09 05:41:02,301 INFO [train.py:715] (3/8) Epoch 18, batch 900, loss[loss=0.1165, simple_loss=0.1903, pruned_loss=0.02141, over 4966.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02887, over 961470.08 frames.], batch size: 24, lr: 1.25e-04
+2022-05-09 05:41:41,276 INFO [train.py:715] (3/8) Epoch 18, batch 950, loss[loss=0.1208, simple_loss=0.205, pruned_loss=0.01829, over 4873.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02945, over 964093.73 frames.], batch size: 16, lr: 1.25e-04
+2022-05-09 05:42:20,889 INFO [train.py:715] (3/8) Epoch 18, batch 1000, loss[loss=0.1303, simple_loss=0.2075, pruned_loss=0.0266, over 4929.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02936, over 965885.88 frames.], batch size: 18, lr: 1.25e-04
+2022-05-09 05:43:00,529 INFO [train.py:715] (3/8) Epoch 18, batch 1050, loss[loss=0.1542, simple_loss=0.2357, pruned_loss=0.03631, over 4979.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02944, over 966757.14 frames.], batch size: 39, lr: 1.25e-04
+2022-05-09 05:43:39,933 INFO [train.py:715] (3/8) Epoch 18, batch 1100, loss[loss=0.1268, simple_loss=0.2025, pruned_loss=0.02554, over 4956.00 frames.], tot_loss[loss=0.133, simple_loss=0.2066, pruned_loss=0.0297, over 967241.37 frames.], batch size: 15, lr: 1.25e-04
+2022-05-09 05:44:18,725 INFO [train.py:715] (3/8) Epoch 18, batch 1150, loss[loss=0.1364, simple_loss=0.2205, pruned_loss=0.02612, over 4798.00 frames.], tot_loss[loss=0.133, simple_loss=0.2063, pruned_loss=0.02987, over 968061.03 frames.], batch size: 24, lr: 1.25e-04
+2022-05-09 05:44:58,552 INFO [train.py:715] (3/8) Epoch 18, batch 1200, loss[loss=0.1325, simple_loss=0.1982, pruned_loss=0.03337, over 4940.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02957, over 969242.09 frames.], batch size: 39, lr: 1.25e-04
+2022-05-09 05:45:38,537 INFO [train.py:715] (3/8) Epoch 18, batch 1250, loss[loss=0.1383, simple_loss=0.2213, pruned_loss=0.0276, over 4884.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02948, over 970039.86 frames.], batch size: 22, lr: 1.25e-04
+2022-05-09 05:46:17,552 INFO [train.py:715] (3/8) Epoch 18, batch 1300, loss[loss=0.1294, simple_loss=0.2019, pruned_loss=0.02846, over 4976.00 frames.], tot_loss[loss=0.133, simple_loss=0.2067, pruned_loss=0.02963, over 970383.52 frames.], batch size: 25, lr: 1.25e-04
+2022-05-09 05:46:56,373 INFO [train.py:715] (3/8) Epoch 18, batch 1350, loss[loss=0.1686, simple_loss=0.2407, pruned_loss=0.04826, over 4980.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.0295, over 969978.09 frames.], batch size: 26, lr: 1.25e-04
+2022-05-09 05:47:35,781 INFO [train.py:715] (3/8) Epoch 18, batch 1400, loss[loss=0.1131, simple_loss=0.1894, pruned_loss=0.0184, over 4888.00 frames.], tot_loss[loss=0.132, simple_loss=0.2057, pruned_loss=0.02919, over 970264.68 frames.], batch size: 22, lr: 1.25e-04
+2022-05-09 05:48:15,007 INFO [train.py:715] (3/8) Epoch 18, batch 1450, loss[loss=0.1604, simple_loss=0.2213, pruned_loss=0.04976, over 4977.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2053, pruned_loss=0.02883, over 970175.40 frames.], batch size: 15, lr: 1.25e-04
+2022-05-09 05:48:53,402 INFO [train.py:715] (3/8) Epoch 18, batch 1500, loss[loss=0.1226, simple_loss=0.1918, pruned_loss=0.02673, over 4786.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02908, over 970966.28 frames.], batch size: 17, lr: 1.25e-04
+2022-05-09 05:49:32,907 INFO [train.py:715] (3/8) Epoch 18, batch 1550, loss[loss=0.1374, simple_loss=0.2104, pruned_loss=0.03227, over 4786.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02928, over 970919.33 frames.], batch size: 21, lr: 1.25e-04
+2022-05-09 05:50:12,322 INFO [train.py:715] (3/8) Epoch 18, batch 1600, loss[loss=0.116, simple_loss=0.1935, pruned_loss=0.01922, over 4792.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02962, over 971561.22 frames.], batch size: 24, lr: 1.25e-04
+2022-05-09 05:50:51,525 INFO [train.py:715] (3/8) Epoch 18, batch 1650, loss[loss=0.1323, simple_loss=0.205, pruned_loss=0.02978, over 4987.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02943, over 972567.73 frames.], batch size: 14, lr: 1.25e-04
+2022-05-09 05:51:30,468 INFO [train.py:715] (3/8) Epoch 18, batch 1700, loss[loss=0.1547, simple_loss=0.2218, pruned_loss=0.04378, over 4847.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02902, over 972481.84 frames.], batch size: 34, lr: 1.25e-04
+2022-05-09 05:52:09,887 INFO [train.py:715] (3/8) Epoch 18, batch 1750, loss[loss=0.1191, simple_loss=0.1916, pruned_loss=0.02327, over 4764.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02885, over 972749.01 frames.], batch size: 19, lr: 1.25e-04
+2022-05-09 05:52:49,169 INFO [train.py:715] (3/8) Epoch 18, batch 1800, loss[loss=0.1376, simple_loss=0.2177, pruned_loss=0.02874, over 4976.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.0288, over 972376.24 frames.], batch size: 15, lr: 1.25e-04
+2022-05-09 05:53:27,454 INFO [train.py:715] (3/8) Epoch 18, batch 1850, loss[loss=0.1074, simple_loss=0.1733, pruned_loss=0.0208, over 4854.00 frames.], tot_loss[loss=0.1322, simple_loss=0.206, pruned_loss=0.02923, over 972029.78 frames.], batch size: 13, lr: 1.25e-04
+2022-05-09 05:54:06,243 INFO [train.py:715] (3/8) Epoch 18, batch 1900, loss[loss=0.1555, simple_loss=0.2276, pruned_loss=0.04168, over 4821.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2064, pruned_loss=0.02946, over 972249.20 frames.], batch size: 25, lr: 1.25e-04
+2022-05-09 05:54:45,621 INFO [train.py:715] (3/8) Epoch 18, batch 1950, loss[loss=0.133, simple_loss=0.2109, pruned_loss=0.02754, over 4971.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02932, over 972310.05 frames.], batch size: 24, lr: 1.25e-04
+2022-05-09 05:55:24,353 INFO [train.py:715] (3/8) Epoch 18, batch 2000, loss[loss=0.119, simple_loss=0.1915, pruned_loss=0.02322, over 4870.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02927, over 972492.75 frames.], batch size: 22, lr: 1.25e-04
+2022-05-09 05:56:02,841 INFO [train.py:715] (3/8) Epoch 18, batch 2050, loss[loss=0.1277, simple_loss=0.2059, pruned_loss=0.0248, over 4839.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02951, over 971230.04 frames.], batch size: 26, lr: 1.25e-04
+2022-05-09 05:56:42,078 INFO [train.py:715] (3/8) Epoch 18, batch 2100, loss[loss=0.1295, simple_loss=0.2001, pruned_loss=0.02944, over 4958.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02933, over 971483.04 frames.], batch size: 35, lr: 1.25e-04
+2022-05-09 05:57:21,525 INFO [train.py:715] (3/8) Epoch 18, batch 2150, loss[loss=0.1457, simple_loss=0.2091, pruned_loss=0.04119, over 4651.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02908, over 971660.65 frames.], batch size: 13, lr: 1.25e-04
+2022-05-09 05:57:59,832 INFO [train.py:715] (3/8) Epoch 18, batch 2200, loss[loss=0.1581, simple_loss=0.2308, pruned_loss=0.04267, over 4863.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02888, over 972149.16 frames.], batch size: 30, lr: 1.25e-04
+2022-05-09 05:58:39,481 INFO [train.py:715] (3/8) Epoch 18, batch 2250, loss[loss=0.1317, simple_loss=0.2003, pruned_loss=0.03156, over 4862.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02861, over 972392.61 frames.], batch size: 32, lr: 1.25e-04
+2022-05-09 05:59:18,830 INFO [train.py:715] (3/8) Epoch 18, batch 2300, loss[loss=0.1202, simple_loss=0.1998, pruned_loss=0.02027, over 4848.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02856, over 972191.23 frames.], batch size: 20, lr: 1.25e-04
+2022-05-09 05:59:57,621 INFO [train.py:715] (3/8) Epoch 18, batch 2350, loss[loss=0.1438, simple_loss=0.2284, pruned_loss=0.02964, over 4890.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.02856, over 971887.34 frames.], batch size: 22, lr: 1.25e-04
+2022-05-09 06:00:36,233 INFO [train.py:715] (3/8) Epoch 18, batch 2400, loss[loss=0.134, simple_loss=0.2175, pruned_loss=0.02531, over 4826.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2051, pruned_loss=0.02836, over 972059.40 frames.], batch size: 30, lr: 1.25e-04
+2022-05-09 06:01:15,696 INFO [train.py:715] (3/8) Epoch 18, batch 2450, loss[loss=0.1129, simple_loss=0.1914, pruned_loss=0.01719, over 4702.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02818, over 973072.64 frames.], batch size: 15, lr: 1.25e-04
+2022-05-09 06:01:55,088 INFO [train.py:715] (3/8) Epoch 18, batch 2500, loss[loss=0.1521, simple_loss=0.2257, pruned_loss=0.03927, over 4911.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02798, over 972917.63 frames.], batch size: 17, lr: 1.25e-04
+2022-05-09 06:02:33,098 INFO [train.py:715] (3/8) Epoch 18, batch 2550, loss[loss=0.1412, simple_loss=0.2176, pruned_loss=0.0324, over 4892.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02887, over 973256.96 frames.], batch size: 22, lr: 1.25e-04
+2022-05-09 06:03:11,867 INFO [train.py:715] (3/8) Epoch 18, batch 2600, loss[loss=0.1346, simple_loss=0.2121, pruned_loss=0.02858, over 4888.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02896, over 972382.99 frames.], batch size: 19, lr: 1.25e-04
+2022-05-09 06:03:51,790 INFO [train.py:715] (3/8) Epoch 18, batch 2650, loss[loss=0.1357, simple_loss=0.2034, pruned_loss=0.034, over 4795.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02923, over 971815.59 frames.], batch size: 14, lr: 1.25e-04
+2022-05-09 06:04:30,527 INFO [train.py:715] (3/8) Epoch 18, batch 2700, loss[loss=0.1171, simple_loss=0.1943, pruned_loss=0.01996, over 4897.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.02964, over 972036.75 frames.], batch size: 19, lr: 1.25e-04
+2022-05-09 06:05:08,889 INFO [train.py:715] (3/8) Epoch 18, batch 2750, loss[loss=0.137, simple_loss=0.206, pruned_loss=0.03398, over 4820.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.0289, over 972436.79 frames.], batch size: 27, lr: 1.25e-04
+2022-05-09 06:05:47,975 INFO [train.py:715] (3/8) Epoch 18, batch 2800, loss[loss=0.1214, simple_loss=0.2066, pruned_loss=0.01806, over 4764.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02901, over 973322.92 frames.], batch size: 18, lr: 1.25e-04
+2022-05-09 06:06:27,519 INFO [train.py:715] (3/8) Epoch 18, batch 2850, loss[loss=0.1042, simple_loss=0.1798, pruned_loss=0.0143, over 4982.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02911, over 973150.15 frames.], batch size: 15, lr: 1.25e-04
+2022-05-09 06:07:06,091 INFO [train.py:715] (3/8) Epoch 18, batch 2900, loss[loss=0.1262, simple_loss=0.2107, pruned_loss=0.02085, over 4816.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02924, over 973572.25 frames.], batch size: 26, lr: 1.25e-04
+2022-05-09 06:07:44,918 INFO [train.py:715] (3/8) Epoch 18, batch 2950, loss[loss=0.1245, simple_loss=0.2039, pruned_loss=0.02251, over 4946.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02949, over 973258.90 frames.], batch size: 23, lr: 1.25e-04
+2022-05-09 06:08:24,282 INFO [train.py:715] (3/8) Epoch 18, batch 3000, loss[loss=0.143, simple_loss=0.205, pruned_loss=0.04052, over 4773.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02964, over 972754.77 frames.], batch size: 12, lr: 1.25e-04
+2022-05-09 06:08:24,282 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 06:08:34,096 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01065, over 914524.00 frames.
+2022-05-09 06:09:14,110 INFO [train.py:715] (3/8) Epoch 18, batch 3050, loss[loss=0.1639, simple_loss=0.2301, pruned_loss=0.04885, over 4870.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02969, over 973135.05 frames.], batch size: 16, lr: 1.25e-04
+2022-05-09 06:09:52,623 INFO [train.py:715] (3/8) Epoch 18, batch 3100, loss[loss=0.1139, simple_loss=0.1851, pruned_loss=0.0213, over 4802.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02953, over 972698.71 frames.], batch size: 13, lr: 1.25e-04
+2022-05-09 06:10:31,510 INFO [train.py:715] (3/8) Epoch 18, batch 3150, loss[loss=0.1243, simple_loss=0.1946, pruned_loss=0.02704, over 4952.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02907, over 972541.59 frames.], batch size: 35, lr: 1.25e-04
+2022-05-09 06:11:10,547 INFO [train.py:715] (3/8) Epoch 18, batch 3200, loss[loss=0.1585, simple_loss=0.2302, pruned_loss=0.04344, over 4752.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02922, over 971826.73 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 06:11:50,029 INFO [train.py:715] (3/8) Epoch 18, batch 3250, loss[loss=0.1424, simple_loss=0.2126, pruned_loss=0.03613, over 4992.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02929, over 972063.17 frames.], batch size: 20, lr: 1.24e-04
+2022-05-09 06:12:28,191 INFO [train.py:715] (3/8) Epoch 18, batch 3300, loss[loss=0.1271, simple_loss=0.1966, pruned_loss=0.02878, over 4827.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02956, over 971061.42 frames.], batch size: 26, lr: 1.24e-04
+2022-05-09 06:13:07,649 INFO [train.py:715] (3/8) Epoch 18, batch 3350, loss[loss=0.1463, simple_loss=0.2258, pruned_loss=0.03337, over 4919.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2087, pruned_loss=0.02987, over 971414.46 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 06:13:47,789 INFO [train.py:715] (3/8) Epoch 18, batch 3400, loss[loss=0.1019, simple_loss=0.1749, pruned_loss=0.0144, over 4842.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02929, over 971829.37 frames.], batch size: 12, lr: 1.24e-04
+2022-05-09 06:14:26,392 INFO [train.py:715] (3/8) Epoch 18, batch 3450, loss[loss=0.1146, simple_loss=0.1971, pruned_loss=0.01603, over 4799.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02903, over 970776.01 frames.], batch size: 25, lr: 1.24e-04
+2022-05-09 06:15:05,249 INFO [train.py:715] (3/8) Epoch 18, batch 3500, loss[loss=0.1302, simple_loss=0.1995, pruned_loss=0.03043, over 4953.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02925, over 971267.31 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 06:15:45,335 INFO [train.py:715] (3/8) Epoch 18, batch 3550, loss[loss=0.1477, simple_loss=0.2301, pruned_loss=0.03264, over 4945.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02877, over 971779.39 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 06:16:24,512 INFO [train.py:715] (3/8) Epoch 18, batch 3600, loss[loss=0.1616, simple_loss=0.2422, pruned_loss=0.04051, over 4842.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02869, over 973117.56 frames.], batch size: 12, lr: 1.24e-04
+2022-05-09 06:17:03,259 INFO [train.py:715] (3/8) Epoch 18, batch 3650, loss[loss=0.1039, simple_loss=0.1793, pruned_loss=0.01424, over 4796.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02862, over 972996.37 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 06:17:42,728 INFO [train.py:715] (3/8) Epoch 18, batch 3700, loss[loss=0.1304, simple_loss=0.1959, pruned_loss=0.03247, over 4699.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02833, over 972569.89 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 06:18:22,001 INFO [train.py:715] (3/8) Epoch 18, batch 3750, loss[loss=0.1274, simple_loss=0.2155, pruned_loss=0.01968, over 4885.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02857, over 972945.19 frames.], batch size: 39, lr: 1.24e-04
+2022-05-09 06:18:59,954 INFO [train.py:715] (3/8) Epoch 18, batch 3800, loss[loss=0.164, simple_loss=0.2451, pruned_loss=0.04144, over 4903.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2064, pruned_loss=0.02834, over 972742.41 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 06:19:39,328 INFO [train.py:715] (3/8) Epoch 18, batch 3850, loss[loss=0.1571, simple_loss=0.2343, pruned_loss=0.03997, over 4775.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02891, over 973015.18 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 06:20:19,350 INFO [train.py:715] (3/8) Epoch 18, batch 3900, loss[loss=0.1465, simple_loss=0.2185, pruned_loss=0.0373, over 4911.00 frames.], tot_loss[loss=0.1332, simple_loss=0.208, pruned_loss=0.02927, over 972850.15 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 06:20:57,827 INFO [train.py:715] (3/8) Epoch 18, batch 3950, loss[loss=0.1219, simple_loss=0.1975, pruned_loss=0.02316, over 4860.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2084, pruned_loss=0.02947, over 972258.48 frames.], batch size: 30, lr: 1.24e-04
+2022-05-09 06:21:37,238 INFO [train.py:715] (3/8) Epoch 18, batch 4000, loss[loss=0.1241, simple_loss=0.2004, pruned_loss=0.0239, over 4984.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.0293, over 972694.21 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 06:22:16,734 INFO [train.py:715] (3/8) Epoch 18, batch 4050, loss[loss=0.1301, simple_loss=0.1985, pruned_loss=0.0309, over 4842.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02906, over 973003.64 frames.], batch size: 30, lr: 1.24e-04
+2022-05-09 06:22:56,014 INFO [train.py:715] (3/8) Epoch 18, batch 4100, loss[loss=0.1541, simple_loss=0.2351, pruned_loss=0.03652, over 4759.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.0294, over 972394.71 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 06:23:34,761 INFO [train.py:715] (3/8) Epoch 18, batch 4150, loss[loss=0.126, simple_loss=0.2045, pruned_loss=0.0237, over 4765.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02902, over 972236.82 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 06:24:14,198 INFO [train.py:715] (3/8) Epoch 18, batch 4200, loss[loss=0.1317, simple_loss=0.2106, pruned_loss=0.02637, over 4820.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02876, over 972480.32 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 06:24:53,580 INFO [train.py:715] (3/8) Epoch 18, batch 4250, loss[loss=0.1513, simple_loss=0.2257, pruned_loss=0.0385, over 4694.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02858, over 972230.19 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 06:25:32,491 INFO [train.py:715] (3/8) Epoch 18, batch 4300, loss[loss=0.1227, simple_loss=0.1992, pruned_loss=0.0231, over 4754.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02831, over 973072.49 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 06:26:12,602 INFO [train.py:715] (3/8) Epoch 18, batch 4350, loss[loss=0.1258, simple_loss=0.2031, pruned_loss=0.02428, over 4869.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02845, over 973264.96 frames.], batch size: 22, lr: 1.24e-04
+2022-05-09 06:26:52,060 INFO [train.py:715] (3/8) Epoch 18, batch 4400, loss[loss=0.1368, simple_loss=0.219, pruned_loss=0.02724, over 4890.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02896, over 972888.40 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 06:27:31,549 INFO [train.py:715] (3/8) Epoch 18, batch 4450, loss[loss=0.1249, simple_loss=0.198, pruned_loss=0.02583, over 4947.00 frames.], tot_loss[loss=0.132, simple_loss=0.2059, pruned_loss=0.02903, over 973101.57 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 06:28:09,902 INFO [train.py:715] (3/8) Epoch 18, batch 4500, loss[loss=0.122, simple_loss=0.1998, pruned_loss=0.0221, over 4842.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02922, over 972470.20 frames.], batch size: 20, lr: 1.24e-04
+2022-05-09 06:28:49,168 INFO [train.py:715] (3/8) Epoch 18, batch 4550, loss[loss=0.1519, simple_loss=0.2331, pruned_loss=0.03535, over 4732.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02896, over 971916.67 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 06:29:29,015 INFO [train.py:715] (3/8) Epoch 18, batch 4600, loss[loss=0.1196, simple_loss=0.1926, pruned_loss=0.02324, over 4760.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02874, over 972602.22 frames.], batch size: 12, lr: 1.24e-04
+2022-05-09 06:30:07,896 INFO [train.py:715] (3/8) Epoch 18, batch 4650, loss[loss=0.1463, simple_loss=0.2195, pruned_loss=0.03657, over 4974.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02909, over 972825.92 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 06:30:47,011 INFO [train.py:715] (3/8) Epoch 18, batch 4700, loss[loss=0.1016, simple_loss=0.1754, pruned_loss=0.01384, over 4792.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.0295, over 973222.72 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 06:31:26,064 INFO [train.py:715] (3/8) Epoch 18, batch 4750, loss[loss=0.1432, simple_loss=0.2148, pruned_loss=0.03583, over 4907.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02961, over 972679.76 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 06:32:06,182 INFO [train.py:715] (3/8) Epoch 18, batch 4800, loss[loss=0.1113, simple_loss=0.197, pruned_loss=0.01281, over 4957.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.0293, over 972793.06 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 06:32:44,916 INFO [train.py:715] (3/8) Epoch 18, batch 4850, loss[loss=0.1518, simple_loss=0.2249, pruned_loss=0.03937, over 4750.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02943, over 972132.09 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 06:33:24,374 INFO [train.py:715] (3/8) Epoch 18, batch 4900, loss[loss=0.1254, simple_loss=0.203, pruned_loss=0.02394, over 4973.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02984, over 972706.69 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 06:34:04,561 INFO [train.py:715] (3/8) Epoch 18, batch 4950, loss[loss=0.1274, simple_loss=0.2022, pruned_loss=0.02632, over 4804.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02962, over 972166.56 frames.], batch size: 26, lr: 1.24e-04
+2022-05-09 06:34:43,674 INFO [train.py:715] (3/8) Epoch 18, batch 5000, loss[loss=0.13, simple_loss=0.1972, pruned_loss=0.03136, over 4766.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.0292, over 972453.73 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 06:35:22,355 INFO [train.py:715] (3/8) Epoch 18, batch 5050, loss[loss=0.1136, simple_loss=0.192, pruned_loss=0.01764, over 4961.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02912, over 972553.89 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 06:36:01,524 INFO [train.py:715] (3/8) Epoch 18, batch 5100, loss[loss=0.1333, simple_loss=0.2049, pruned_loss=0.03083, over 4919.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02939, over 972025.94 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 06:36:41,089 INFO [train.py:715] (3/8) Epoch 18, batch 5150, loss[loss=0.133, simple_loss=0.2008, pruned_loss=0.03264, over 4883.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02923, over 972260.18 frames.], batch size: 13, lr: 1.24e-04
+2022-05-09 06:37:19,649 INFO [train.py:715] (3/8) Epoch 18, batch 5200, loss[loss=0.1494, simple_loss=0.2146, pruned_loss=0.04217, over 4967.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.0288, over 971213.63 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 06:37:59,018 INFO [train.py:715] (3/8) Epoch 18, batch 5250, loss[loss=0.1179, simple_loss=0.1951, pruned_loss=0.02032, over 4908.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02877, over 971977.42 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 06:38:38,938 INFO [train.py:715] (3/8) Epoch 18, batch 5300, loss[loss=0.1322, simple_loss=0.1934, pruned_loss=0.03548, over 4829.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02875, over 972052.55 frames.], batch size: 12, lr: 1.24e-04
+2022-05-09 06:39:18,964 INFO [train.py:715] (3/8) Epoch 18, batch 5350, loss[loss=0.1384, simple_loss=0.2166, pruned_loss=0.03008, over 4772.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02875, over 972776.25 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 06:39:57,060 INFO [train.py:715] (3/8) Epoch 18, batch 5400, loss[loss=0.1464, simple_loss=0.2224, pruned_loss=0.03517, over 4792.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02853, over 973030.33 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 06:40:38,718 INFO [train.py:715] (3/8) Epoch 18, batch 5450, loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.0289, over 4881.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02912, over 972227.41 frames.], batch size: 22, lr: 1.24e-04
+2022-05-09 06:41:19,098 INFO [train.py:715] (3/8) Epoch 18, batch 5500, loss[loss=0.1195, simple_loss=0.2019, pruned_loss=0.01858, over 4802.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2085, pruned_loss=0.02949, over 972845.78 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 06:41:58,078 INFO [train.py:715] (3/8) Epoch 18, batch 5550, loss[loss=0.1098, simple_loss=0.1821, pruned_loss=0.01872, over 4777.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02944, over 972357.79 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 06:42:36,882 INFO [train.py:715] (3/8) Epoch 18, batch 5600, loss[loss=0.1428, simple_loss=0.2133, pruned_loss=0.03614, over 4913.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02953, over 971883.74 frames.], batch size: 17, lr: 1.24e-04
+2022-05-09 06:43:15,923 INFO [train.py:715] (3/8) Epoch 18, batch 5650, loss[loss=0.1232, simple_loss=0.18, pruned_loss=0.03324, over 4827.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02893, over 972560.82 frames.], batch size: 13, lr: 1.24e-04
+2022-05-09 06:43:55,546 INFO [train.py:715] (3/8) Epoch 18, batch 5700, loss[loss=0.164, simple_loss=0.2338, pruned_loss=0.04704, over 4899.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02898, over 973450.15 frames.], batch size: 17, lr: 1.24e-04
+2022-05-09 06:44:33,666 INFO [train.py:715] (3/8) Epoch 18, batch 5750, loss[loss=0.1305, simple_loss=0.2002, pruned_loss=0.03036, over 4981.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02907, over 972438.68 frames.], batch size: 31, lr: 1.24e-04
+2022-05-09 06:45:12,597 INFO [train.py:715] (3/8) Epoch 18, batch 5800, loss[loss=0.1718, simple_loss=0.2454, pruned_loss=0.04907, over 4886.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.029, over 973482.00 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 06:45:52,340 INFO [train.py:715] (3/8) Epoch 18, batch 5850, loss[loss=0.1493, simple_loss=0.2142, pruned_loss=0.04224, over 4786.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02955, over 972782.52 frames.], batch size: 17, lr: 1.24e-04
+2022-05-09 06:46:31,448 INFO [train.py:715] (3/8) Epoch 18, batch 5900, loss[loss=0.1325, simple_loss=0.2158, pruned_loss=0.02458, over 4894.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02901, over 971668.81 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 06:47:10,143 INFO [train.py:715] (3/8) Epoch 18, batch 5950, loss[loss=0.1103, simple_loss=0.1879, pruned_loss=0.01639, over 4787.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02877, over 972222.27 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 06:47:49,550 INFO [train.py:715] (3/8) Epoch 18, batch 6000, loss[loss=0.1245, simple_loss=0.2097, pruned_loss=0.0197, over 4810.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02902, over 972302.54 frames.], batch size: 25, lr: 1.24e-04
+2022-05-09 06:47:49,551 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 06:47:59,475 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.01075, over 914524.00 frames.
+2022-05-09 06:48:39,113 INFO [train.py:715] (3/8) Epoch 18, batch 6050, loss[loss=0.1592, simple_loss=0.2446, pruned_loss=0.03685, over 4965.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02935, over 972612.55 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 06:49:18,284 INFO [train.py:715] (3/8) Epoch 18, batch 6100, loss[loss=0.1642, simple_loss=0.2328, pruned_loss=0.04783, over 4970.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02921, over 971459.77 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 06:49:56,627 INFO [train.py:715] (3/8) Epoch 18, batch 6150, loss[loss=0.1155, simple_loss=0.2005, pruned_loss=0.01524, over 4893.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02884, over 971217.29 frames.], batch size: 22, lr: 1.24e-04
+2022-05-09 06:50:35,919 INFO [train.py:715] (3/8) Epoch 18, batch 6200, loss[loss=0.1471, simple_loss=0.2132, pruned_loss=0.04054, over 4832.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02858, over 971073.12 frames.], batch size: 30, lr: 1.24e-04
+2022-05-09 06:51:15,500 INFO [train.py:715] (3/8) Epoch 18, batch 6250, loss[loss=0.1278, simple_loss=0.2076, pruned_loss=0.02398, over 4974.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.02809, over 970814.00 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 06:51:54,531 INFO [train.py:715] (3/8) Epoch 18, batch 6300, loss[loss=0.1354, simple_loss=0.2226, pruned_loss=0.02411, over 4973.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2049, pruned_loss=0.02812, over 971906.47 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 06:52:33,701 INFO [train.py:715] (3/8) Epoch 18, batch 6350, loss[loss=0.1359, simple_loss=0.2088, pruned_loss=0.03148, over 4957.00 frames.], tot_loss[loss=0.1305, simple_loss=0.205, pruned_loss=0.02798, over 972148.83 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 06:53:12,891 INFO [train.py:715] (3/8) Epoch 18, batch 6400, loss[loss=0.1161, simple_loss=0.1955, pruned_loss=0.01838, over 4755.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2043, pruned_loss=0.02755, over 970918.06 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 06:53:52,077 INFO [train.py:715] (3/8) Epoch 18, batch 6450, loss[loss=0.1252, simple_loss=0.2008, pruned_loss=0.02484, over 4927.00 frames.], tot_loss[loss=0.13, simple_loss=0.2044, pruned_loss=0.0278, over 971250.64 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 06:54:30,357 INFO [train.py:715] (3/8) Epoch 18, batch 6500, loss[loss=0.1434, simple_loss=0.2182, pruned_loss=0.03434, over 4760.00 frames.], tot_loss[loss=0.1297, simple_loss=0.204, pruned_loss=0.02772, over 971374.82 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 06:55:08,639 INFO [train.py:715] (3/8) Epoch 18, batch 6550, loss[loss=0.1252, simple_loss=0.2124, pruned_loss=0.01903, over 4939.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2042, pruned_loss=0.02796, over 971938.52 frames.], batch size: 39, lr: 1.24e-04
+2022-05-09 06:55:48,101 INFO [train.py:715] (3/8) Epoch 18, batch 6600, loss[loss=0.1286, simple_loss=0.206, pruned_loss=0.02554, over 4932.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2049, pruned_loss=0.02819, over 972873.54 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 06:56:27,457 INFO [train.py:715] (3/8) Epoch 18, batch 6650, loss[loss=0.1419, simple_loss=0.2203, pruned_loss=0.03173, over 4867.00 frames.], tot_loss[loss=0.1311, simple_loss=0.205, pruned_loss=0.02862, over 972732.93 frames.], batch size: 32, lr: 1.24e-04
+2022-05-09 06:57:05,504 INFO [train.py:715] (3/8) Epoch 18, batch 6700, loss[loss=0.1464, simple_loss=0.2367, pruned_loss=0.02806, over 4885.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2059, pruned_loss=0.02923, over 972731.85 frames.], batch size: 22, lr: 1.24e-04
+2022-05-09 06:57:44,486 INFO [train.py:715] (3/8) Epoch 18, batch 6750, loss[loss=0.1448, simple_loss=0.2234, pruned_loss=0.0331, over 4989.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02975, over 972962.92 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 06:58:23,843 INFO [train.py:715] (3/8) Epoch 18, batch 6800, loss[loss=0.1436, simple_loss=0.2263, pruned_loss=0.03049, over 4952.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02943, over 972605.89 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 06:59:02,551 INFO [train.py:715] (3/8) Epoch 18, batch 6850, loss[loss=0.1402, simple_loss=0.2248, pruned_loss=0.02777, over 4821.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02962, over 973053.45 frames.], batch size: 26, lr: 1.24e-04
+2022-05-09 06:59:40,722 INFO [train.py:715] (3/8) Epoch 18, batch 6900, loss[loss=0.154, simple_loss=0.2156, pruned_loss=0.04617, over 4862.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02973, over 972550.82 frames.], batch size: 32, lr: 1.24e-04
+2022-05-09 07:00:20,315 INFO [train.py:715] (3/8) Epoch 18, batch 6950, loss[loss=0.1098, simple_loss=0.1836, pruned_loss=0.01798, over 4755.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02911, over 972852.24 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 07:00:59,041 INFO [train.py:715] (3/8) Epoch 18, batch 7000, loss[loss=0.1312, simple_loss=0.1992, pruned_loss=0.03165, over 4685.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02877, over 971620.32 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 07:01:37,419 INFO [train.py:715] (3/8) Epoch 18, batch 7050, loss[loss=0.1284, simple_loss=0.1945, pruned_loss=0.03118, over 4903.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02925, over 971799.74 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 07:02:16,626 INFO [train.py:715] (3/8) Epoch 18, batch 7100, loss[loss=0.1248, simple_loss=0.1968, pruned_loss=0.02643, over 4845.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2059, pruned_loss=0.02914, over 971361.22 frames.], batch size: 34, lr: 1.24e-04
+2022-05-09 07:02:56,206 INFO [train.py:715] (3/8) Epoch 18, batch 7150, loss[loss=0.1368, simple_loss=0.2182, pruned_loss=0.02769, over 4864.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02926, over 971148.82 frames.], batch size: 20, lr: 1.24e-04
+2022-05-09 07:03:34,829 INFO [train.py:715] (3/8) Epoch 18, batch 7200, loss[loss=0.1283, simple_loss=0.2076, pruned_loss=0.02456, over 4886.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02909, over 971343.80 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 07:04:13,061 INFO [train.py:715] (3/8) Epoch 18, batch 7250, loss[loss=0.1261, simple_loss=0.1926, pruned_loss=0.02984, over 4978.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02895, over 971827.98 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 07:04:52,162 INFO [train.py:715] (3/8) Epoch 18, batch 7300, loss[loss=0.1197, simple_loss=0.1945, pruned_loss=0.02239, over 4775.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2055, pruned_loss=0.0286, over 972069.53 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 07:05:31,286 INFO [train.py:715] (3/8) Epoch 18, batch 7350, loss[loss=0.1404, simple_loss=0.2155, pruned_loss=0.03266, over 4786.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2048, pruned_loss=0.02835, over 971822.21 frames.], batch size: 17, lr: 1.24e-04
+2022-05-09 07:06:09,357 INFO [train.py:715] (3/8) Epoch 18, batch 7400, loss[loss=0.205, simple_loss=0.2794, pruned_loss=0.06527, over 4979.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2056, pruned_loss=0.02886, over 972027.47 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 07:06:48,514 INFO [train.py:715] (3/8) Epoch 18, batch 7450, loss[loss=0.164, simple_loss=0.2377, pruned_loss=0.04512, over 4872.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02893, over 971726.35 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 07:07:27,762 INFO [train.py:715] (3/8) Epoch 18, batch 7500, loss[loss=0.129, simple_loss=0.1888, pruned_loss=0.03463, over 4941.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02892, over 971618.26 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 07:08:05,377 INFO [train.py:715] (3/8) Epoch 18, batch 7550, loss[loss=0.1084, simple_loss=0.1769, pruned_loss=0.01991, over 4828.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02895, over 972477.96 frames.], batch size: 26, lr: 1.24e-04
+2022-05-09 07:08:43,907 INFO [train.py:715] (3/8) Epoch 18, batch 7600, loss[loss=0.1089, simple_loss=0.1866, pruned_loss=0.01557, over 4946.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02845, over 972649.37 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 07:09:23,638 INFO [train.py:715] (3/8) Epoch 18, batch 7650, loss[loss=0.1228, simple_loss=0.2045, pruned_loss=0.02056, over 4878.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.0288, over 971337.50 frames.], batch size: 22, lr: 1.24e-04
+2022-05-09 07:10:02,904 INFO [train.py:715] (3/8) Epoch 18, batch 7700, loss[loss=0.153, simple_loss=0.2282, pruned_loss=0.03886, over 4866.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02899, over 972139.50 frames.], batch size: 32, lr: 1.24e-04
+2022-05-09 07:10:41,610 INFO [train.py:715] (3/8) Epoch 18, batch 7750, loss[loss=0.1567, simple_loss=0.2344, pruned_loss=0.03947, over 4883.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02943, over 971609.67 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 07:11:21,215 INFO [train.py:715] (3/8) Epoch 18, batch 7800, loss[loss=0.1155, simple_loss=0.1865, pruned_loss=0.02221, over 4945.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02949, over 970967.01 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 07:12:01,095 INFO [train.py:715] (3/8) Epoch 18, batch 7850, loss[loss=0.1276, simple_loss=0.2004, pruned_loss=0.02742, over 4953.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02869, over 970282.43 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 07:12:40,477 INFO [train.py:715] (3/8) Epoch 18, batch 7900, loss[loss=0.1506, simple_loss=0.2299, pruned_loss=0.03565, over 4948.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02874, over 969810.83 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 07:13:19,676 INFO [train.py:715] (3/8) Epoch 18, batch 7950, loss[loss=0.1218, simple_loss=0.1948, pruned_loss=0.02443, over 4822.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02862, over 970400.56 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 07:13:59,116 INFO [train.py:715] (3/8) Epoch 18, batch 8000, loss[loss=0.1206, simple_loss=0.1906, pruned_loss=0.02533, over 4826.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02918, over 970189.56 frames.], batch size: 30, lr: 1.24e-04
+2022-05-09 07:14:38,128 INFO [train.py:715] (3/8) Epoch 18, batch 8050, loss[loss=0.136, simple_loss=0.2088, pruned_loss=0.03158, over 4751.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02949, over 970961.42 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 07:15:16,608 INFO [train.py:715] (3/8) Epoch 18, batch 8100, loss[loss=0.1644, simple_loss=0.2301, pruned_loss=0.04941, over 4975.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02922, over 971283.80 frames.], batch size: 40, lr: 1.24e-04
+2022-05-09 07:15:55,248 INFO [train.py:715] (3/8) Epoch 18, batch 8150, loss[loss=0.1437, simple_loss=0.2257, pruned_loss=0.03082, over 4887.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02956, over 971239.97 frames.], batch size: 22, lr: 1.24e-04
+2022-05-09 07:16:34,307 INFO [train.py:715] (3/8) Epoch 18, batch 8200, loss[loss=0.1205, simple_loss=0.1963, pruned_loss=0.02236, over 4808.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02924, over 972039.97 frames.], batch size: 26, lr: 1.24e-04
+2022-05-09 07:17:12,928 INFO [train.py:715] (3/8) Epoch 18, batch 8250, loss[loss=0.1289, simple_loss=0.2023, pruned_loss=0.02775, over 4860.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02872, over 972099.11 frames.], batch size: 20, lr: 1.24e-04
+2022-05-09 07:17:51,219 INFO [train.py:715] (3/8) Epoch 18, batch 8300, loss[loss=0.1342, simple_loss=0.2131, pruned_loss=0.02767, over 4791.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02837, over 972551.58 frames.], batch size: 17, lr: 1.24e-04
+2022-05-09 07:18:31,284 INFO [train.py:715] (3/8) Epoch 18, batch 8350, loss[loss=0.1233, simple_loss=0.1991, pruned_loss=0.02377, over 4878.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02892, over 973536.00 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 07:19:10,481 INFO [train.py:715] (3/8) Epoch 18, batch 8400, loss[loss=0.1412, simple_loss=0.2031, pruned_loss=0.03963, over 4889.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02885, over 972707.55 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 07:19:48,919 INFO [train.py:715] (3/8) Epoch 18, batch 8450, loss[loss=0.1503, simple_loss=0.2211, pruned_loss=0.03976, over 4850.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02859, over 972709.74 frames.], batch size: 34, lr: 1.24e-04
+2022-05-09 07:20:28,156 INFO [train.py:715] (3/8) Epoch 18, batch 8500, loss[loss=0.1224, simple_loss=0.2028, pruned_loss=0.02102, over 4924.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02793, over 972958.44 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 07:21:07,334 INFO [train.py:715] (3/8) Epoch 18, batch 8550, loss[loss=0.1175, simple_loss=0.1893, pruned_loss=0.02281, over 4801.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02848, over 971997.86 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 07:21:46,036 INFO [train.py:715] (3/8) Epoch 18, batch 8600, loss[loss=0.1276, simple_loss=0.2033, pruned_loss=0.02597, over 4976.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.0286, over 972857.69 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 07:22:24,240 INFO [train.py:715] (3/8) Epoch 18, batch 8650, loss[loss=0.1371, simple_loss=0.2198, pruned_loss=0.02717, over 4982.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02865, over 973194.51 frames.], batch size: 28, lr: 1.24e-04
+2022-05-09 07:23:03,808 INFO [train.py:715] (3/8) Epoch 18, batch 8700, loss[loss=0.1121, simple_loss=0.1866, pruned_loss=0.01881, over 4766.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02865, over 972730.07 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 07:23:43,634 INFO [train.py:715] (3/8) Epoch 18, batch 8750, loss[loss=0.1195, simple_loss=0.2043, pruned_loss=0.01731, over 4698.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02894, over 973499.26 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 07:24:23,137 INFO [train.py:715] (3/8) Epoch 18, batch 8800, loss[loss=0.1209, simple_loss=0.1967, pruned_loss=0.02261, over 4936.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02897, over 973829.07 frames.], batch size: 29, lr: 1.24e-04
+2022-05-09 07:25:01,505 INFO [train.py:715] (3/8) Epoch 18, batch 8850, loss[loss=0.1189, simple_loss=0.1968, pruned_loss=0.02049, over 4793.00 frames.], tot_loss[loss=0.131, simple_loss=0.2049, pruned_loss=0.02851, over 972767.05 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 07:25:41,124 INFO [train.py:715] (3/8) Epoch 18, batch 8900, loss[loss=0.1465, simple_loss=0.2169, pruned_loss=0.03809, over 4935.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2056, pruned_loss=0.02896, over 972722.71 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 07:26:19,640 INFO [train.py:715] (3/8) Epoch 18, batch 8950, loss[loss=0.1352, simple_loss=0.2079, pruned_loss=0.03121, over 4816.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02872, over 972466.03 frames.], batch size: 13, lr: 1.24e-04
+2022-05-09 07:26:58,103 INFO [train.py:715] (3/8) Epoch 18, batch 9000, loss[loss=0.1097, simple_loss=0.1806, pruned_loss=0.01943, over 4767.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2052, pruned_loss=0.02863, over 972251.96 frames.], batch size: 17, lr: 1.24e-04
+2022-05-09 07:26:58,103 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 07:27:08,040 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1045, simple_loss=0.1879, pruned_loss=0.01057, over 914524.00 frames.
+2022-05-09 07:27:46,932 INFO [train.py:715] (3/8) Epoch 18, batch 9050, loss[loss=0.127, simple_loss=0.2023, pruned_loss=0.02588, over 4880.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02898, over 972026.39 frames.], batch size: 22, lr: 1.24e-04
+2022-05-09 07:28:26,538 INFO [train.py:715] (3/8) Epoch 18, batch 9100, loss[loss=0.1157, simple_loss=0.1929, pruned_loss=0.01927, over 4766.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02946, over 971598.09 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 07:29:05,674 INFO [train.py:715] (3/8) Epoch 18, batch 9150, loss[loss=0.1165, simple_loss=0.195, pruned_loss=0.01901, over 4769.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02897, over 971228.73 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 07:29:43,362 INFO [train.py:715] (3/8) Epoch 18, batch 9200, loss[loss=0.1214, simple_loss=0.1839, pruned_loss=0.02943, over 4985.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02935, over 971438.62 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 07:30:22,560 INFO [train.py:715] (3/8) Epoch 18, batch 9250, loss[loss=0.1729, simple_loss=0.2325, pruned_loss=0.05664, over 4877.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.0297, over 970649.71 frames.], batch size: 22, lr: 1.24e-04
+2022-05-09 07:31:01,722 INFO [train.py:715] (3/8) Epoch 18, batch 9300, loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03275, over 4924.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.0297, over 971742.66 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 07:31:39,925 INFO [train.py:715] (3/8) Epoch 18, batch 9350, loss[loss=0.1347, simple_loss=0.2027, pruned_loss=0.03338, over 4973.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02919, over 972390.72 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 07:32:18,513 INFO [train.py:715] (3/8) Epoch 18, batch 9400, loss[loss=0.1605, simple_loss=0.2235, pruned_loss=0.04879, over 4932.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.0289, over 972771.90 frames.], batch size: 39, lr: 1.24e-04
+2022-05-09 07:32:58,077 INFO [train.py:715] (3/8) Epoch 18, batch 9450, loss[loss=0.1264, simple_loss=0.1985, pruned_loss=0.02715, over 4778.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02884, over 971739.37 frames.], batch size: 12, lr: 1.24e-04
+2022-05-09 07:33:36,481 INFO [train.py:715] (3/8) Epoch 18, batch 9500, loss[loss=0.127, simple_loss=0.2023, pruned_loss=0.02579, over 4907.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02872, over 971949.14 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 07:34:14,737 INFO [train.py:715] (3/8) Epoch 18, batch 9550, loss[loss=0.1306, simple_loss=0.2031, pruned_loss=0.02903, over 4925.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02898, over 972435.82 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 07:34:53,873 INFO [train.py:715] (3/8) Epoch 18, batch 9600, loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03274, over 4887.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.02854, over 972549.72 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 07:35:33,430 INFO [train.py:715] (3/8) Epoch 18, batch 9650, loss[loss=0.1348, simple_loss=0.206, pruned_loss=0.03181, over 4974.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02875, over 972502.55 frames.], batch size: 39, lr: 1.24e-04
+2022-05-09 07:36:12,261 INFO [train.py:715] (3/8) Epoch 18, batch 9700, loss[loss=0.125, simple_loss=0.1943, pruned_loss=0.02786, over 4982.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02888, over 972435.44 frames.], batch size: 35, lr: 1.24e-04
+2022-05-09 07:36:50,932 INFO [train.py:715] (3/8) Epoch 18, batch 9750, loss[loss=0.1369, simple_loss=0.2149, pruned_loss=0.02945, over 4777.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.0285, over 972751.76 frames.], batch size: 17, lr: 1.24e-04
+2022-05-09 07:37:31,028 INFO [train.py:715] (3/8) Epoch 18, batch 9800, loss[loss=0.1213, simple_loss=0.1899, pruned_loss=0.02633, over 4816.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02873, over 972228.09 frames.], batch size: 25, lr: 1.24e-04
+2022-05-09 07:38:09,633 INFO [train.py:715] (3/8) Epoch 18, batch 9850, loss[loss=0.1249, simple_loss=0.199, pruned_loss=0.02537, over 4969.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02848, over 972232.66 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 07:38:47,994 INFO [train.py:715] (3/8) Epoch 18, batch 9900, loss[loss=0.128, simple_loss=0.1902, pruned_loss=0.03293, over 4839.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2048, pruned_loss=0.02827, over 972514.36 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 07:39:27,319 INFO [train.py:715] (3/8) Epoch 18, batch 9950, loss[loss=0.1278, simple_loss=0.1981, pruned_loss=0.0287, over 4762.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2049, pruned_loss=0.02805, over 972599.12 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 07:40:06,407 INFO [train.py:715] (3/8) Epoch 18, batch 10000, loss[loss=0.1127, simple_loss=0.1993, pruned_loss=0.01299, over 4978.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02826, over 972466.45 frames.], batch size: 28, lr: 1.24e-04
+2022-05-09 07:40:45,256 INFO [train.py:715] (3/8) Epoch 18, batch 10050, loss[loss=0.1129, simple_loss=0.1824, pruned_loss=0.02175, over 4869.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2046, pruned_loss=0.02797, over 971550.31 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 07:41:23,498 INFO [train.py:715] (3/8) Epoch 18, batch 10100, loss[loss=0.1251, simple_loss=0.1997, pruned_loss=0.02531, over 4776.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02827, over 971355.50 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 07:42:02,487 INFO [train.py:715] (3/8) Epoch 18, batch 10150, loss[loss=0.1114, simple_loss=0.1793, pruned_loss=0.02176, over 4837.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.0287, over 971195.11 frames.], batch size: 30, lr: 1.24e-04
+2022-05-09 07:42:41,662 INFO [train.py:715] (3/8) Epoch 18, batch 10200, loss[loss=0.1671, simple_loss=0.2282, pruned_loss=0.05301, over 4972.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02924, over 971491.61 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 07:43:20,197 INFO [train.py:715] (3/8) Epoch 18, batch 10250, loss[loss=0.1662, simple_loss=0.2219, pruned_loss=0.0552, over 4987.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02954, over 972227.66 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 07:43:59,314 INFO [train.py:715] (3/8) Epoch 18, batch 10300, loss[loss=0.1228, simple_loss=0.2078, pruned_loss=0.01893, over 4844.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02929, over 971711.89 frames.], batch size: 20, lr: 1.24e-04
+2022-05-09 07:44:39,640 INFO [train.py:715] (3/8) Epoch 18, batch 10350, loss[loss=0.1042, simple_loss=0.1808, pruned_loss=0.01379, over 4808.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02935, over 971708.03 frames.], batch size: 26, lr: 1.24e-04
+2022-05-09 07:45:18,121 INFO [train.py:715] (3/8) Epoch 18, batch 10400, loss[loss=0.1132, simple_loss=0.1902, pruned_loss=0.01807, over 4934.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02946, over 972205.28 frames.], batch size: 29, lr: 1.24e-04
+2022-05-09 07:45:56,568 INFO [train.py:715] (3/8) Epoch 18, batch 10450, loss[loss=0.121, simple_loss=0.2039, pruned_loss=0.01904, over 4937.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02981, over 972234.64 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 07:46:36,302 INFO [train.py:715] (3/8) Epoch 18, batch 10500, loss[loss=0.1544, simple_loss=0.2225, pruned_loss=0.04317, over 4937.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02958, over 971963.15 frames.], batch size: 29, lr: 1.24e-04
+2022-05-09 07:47:15,165 INFO [train.py:715] (3/8) Epoch 18, batch 10550, loss[loss=0.1464, simple_loss=0.2159, pruned_loss=0.03851, over 4812.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2088, pruned_loss=0.02951, over 971936.94 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 07:47:53,899 INFO [train.py:715] (3/8) Epoch 18, batch 10600, loss[loss=0.1403, simple_loss=0.2159, pruned_loss=0.03231, over 4966.00 frames.], tot_loss[loss=0.1331, simple_loss=0.208, pruned_loss=0.02909, over 972792.00 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 07:48:33,500 INFO [train.py:715] (3/8) Epoch 18, batch 10650, loss[loss=0.1141, simple_loss=0.1979, pruned_loss=0.01517, over 4813.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2071, pruned_loss=0.02856, over 972380.83 frames.], batch size: 27, lr: 1.24e-04
+2022-05-09 07:49:13,191 INFO [train.py:715] (3/8) Epoch 18, batch 10700, loss[loss=0.1188, simple_loss=0.1946, pruned_loss=0.02149, over 4807.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02824, over 971920.94 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 07:49:52,112 INFO [train.py:715] (3/8) Epoch 18, batch 10750, loss[loss=0.1068, simple_loss=0.1788, pruned_loss=0.01742, over 4816.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02878, over 971958.16 frames.], batch size: 25, lr: 1.24e-04
+2022-05-09 07:50:31,124 INFO [train.py:715] (3/8) Epoch 18, batch 10800, loss[loss=0.129, simple_loss=0.1999, pruned_loss=0.02908, over 4971.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02883, over 972514.06 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 07:51:10,554 INFO [train.py:715] (3/8) Epoch 18, batch 10850, loss[loss=0.128, simple_loss=0.2049, pruned_loss=0.02553, over 4874.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02857, over 973540.18 frames.], batch size: 32, lr: 1.24e-04
+2022-05-09 07:51:49,055 INFO [train.py:715] (3/8) Epoch 18, batch 10900, loss[loss=0.1397, simple_loss=0.2032, pruned_loss=0.03811, over 4991.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02828, over 973391.45 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 07:52:27,638 INFO [train.py:715] (3/8) Epoch 18, batch 10950, loss[loss=0.1364, simple_loss=0.2046, pruned_loss=0.03405, over 4828.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2053, pruned_loss=0.02792, over 972906.42 frames.], batch size: 13, lr: 1.24e-04
+2022-05-09 07:53:07,688 INFO [train.py:715] (3/8) Epoch 18, batch 11000, loss[loss=0.175, simple_loss=0.2226, pruned_loss=0.0637, over 4781.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02834, over 972405.23 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 07:53:46,746 INFO [train.py:715] (3/8) Epoch 18, batch 11050, loss[loss=0.1488, simple_loss=0.2136, pruned_loss=0.04197, over 4852.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02887, over 972091.89 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 07:54:26,302 INFO [train.py:715] (3/8) Epoch 18, batch 11100, loss[loss=0.1257, simple_loss=0.1975, pruned_loss=0.02695, over 4938.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02827, over 971766.79 frames.], batch size: 29, lr: 1.24e-04
+2022-05-09 07:55:05,197 INFO [train.py:715] (3/8) Epoch 18, batch 11150, loss[loss=0.1518, simple_loss=0.2238, pruned_loss=0.03989, over 4734.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02848, over 971830.39 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 07:55:44,748 INFO [train.py:715] (3/8) Epoch 18, batch 11200, loss[loss=0.1512, simple_loss=0.2335, pruned_loss=0.03447, over 4759.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02893, over 971349.86 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 07:56:23,192 INFO [train.py:715] (3/8) Epoch 18, batch 11250, loss[loss=0.1208, simple_loss=0.195, pruned_loss=0.02333, over 4823.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02881, over 971819.14 frames.], batch size: 13, lr: 1.24e-04
+2022-05-09 07:57:01,929 INFO [train.py:715] (3/8) Epoch 18, batch 11300, loss[loss=0.1597, simple_loss=0.241, pruned_loss=0.03921, over 4781.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02871, over 971948.27 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 07:57:41,022 INFO [train.py:715] (3/8) Epoch 18, batch 11350, loss[loss=0.1416, simple_loss=0.2115, pruned_loss=0.03581, over 4827.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02917, over 972511.70 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 07:58:20,188 INFO [train.py:715] (3/8) Epoch 18, batch 11400, loss[loss=0.1349, simple_loss=0.2124, pruned_loss=0.02872, over 4967.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02874, over 973735.11 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 07:58:59,553 INFO [train.py:715] (3/8) Epoch 18, batch 11450, loss[loss=0.1105, simple_loss=0.1925, pruned_loss=0.01425, over 4903.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02869, over 974331.28 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 07:59:38,058 INFO [train.py:715] (3/8) Epoch 18, batch 11500, loss[loss=0.1661, simple_loss=0.2456, pruned_loss=0.04335, over 4922.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02881, over 973276.79 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 08:00:17,724 INFO [train.py:715] (3/8) Epoch 18, batch 11550, loss[loss=0.1486, simple_loss=0.2198, pruned_loss=0.03868, over 4827.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02955, over 973751.20 frames.], batch size: 30, lr: 1.24e-04
+2022-05-09 08:00:57,123 INFO [train.py:715] (3/8) Epoch 18, batch 11600, loss[loss=0.1384, simple_loss=0.2232, pruned_loss=0.02678, over 4821.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02937, over 973409.80 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 08:01:35,950 INFO [train.py:715] (3/8) Epoch 18, batch 11650, loss[loss=0.1329, simple_loss=0.204, pruned_loss=0.03093, over 4918.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02912, over 972832.79 frames.], batch size: 39, lr: 1.24e-04
+2022-05-09 08:02:15,655 INFO [train.py:715] (3/8) Epoch 18, batch 11700, loss[loss=0.1228, simple_loss=0.192, pruned_loss=0.02684, over 4892.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02887, over 972238.05 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 08:02:54,932 INFO [train.py:715] (3/8) Epoch 18, batch 11750, loss[loss=0.14, simple_loss=0.2074, pruned_loss=0.03631, over 4902.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02965, over 972797.27 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 08:03:34,977 INFO [train.py:715] (3/8) Epoch 18, batch 11800, loss[loss=0.1316, simple_loss=0.1955, pruned_loss=0.03386, over 4894.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03002, over 973487.74 frames.], batch size: 22, lr: 1.24e-04
+2022-05-09 08:04:13,542 INFO [train.py:715] (3/8) Epoch 18, batch 11850, loss[loss=0.1234, simple_loss=0.2045, pruned_loss=0.02114, over 4929.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02954, over 973527.90 frames.], batch size: 29, lr: 1.24e-04
+2022-05-09 08:04:53,376 INFO [train.py:715] (3/8) Epoch 18, batch 11900, loss[loss=0.1156, simple_loss=0.191, pruned_loss=0.02012, over 4929.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.0292, over 973275.93 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 08:05:32,230 INFO [train.py:715] (3/8) Epoch 18, batch 11950, loss[loss=0.1192, simple_loss=0.1969, pruned_loss=0.02078, over 4798.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02933, over 972925.76 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 08:06:10,824 INFO [train.py:715] (3/8) Epoch 18, batch 12000, loss[loss=0.1316, simple_loss=0.2082, pruned_loss=0.02755, over 4945.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02894, over 972984.27 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 08:06:10,824 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 08:06:20,737 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1046, simple_loss=0.188, pruned_loss=0.01063, over 914524.00 frames.
+2022-05-09 08:07:00,010 INFO [train.py:715] (3/8) Epoch 18, batch 12050, loss[loss=0.1433, simple_loss=0.2177, pruned_loss=0.03448, over 4872.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02881, over 972529.45 frames.], batch size: 32, lr: 1.24e-04
+2022-05-09 08:07:39,521 INFO [train.py:715] (3/8) Epoch 18, batch 12100, loss[loss=0.1191, simple_loss=0.2014, pruned_loss=0.01845, over 4969.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02909, over 973375.90 frames.], batch size: 28, lr: 1.24e-04
+2022-05-09 08:08:19,049 INFO [train.py:715] (3/8) Epoch 18, batch 12150, loss[loss=0.1224, simple_loss=0.198, pruned_loss=0.02334, over 4769.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02854, over 972808.03 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 08:08:59,343 INFO [train.py:715] (3/8) Epoch 18, batch 12200, loss[loss=0.126, simple_loss=0.2016, pruned_loss=0.02517, over 4920.00 frames.], tot_loss[loss=0.131, simple_loss=0.205, pruned_loss=0.02851, over 972198.24 frames.], batch size: 18, lr: 1.24e-04
+2022-05-09 08:09:38,277 INFO [train.py:715] (3/8) Epoch 18, batch 12250, loss[loss=0.1354, simple_loss=0.2153, pruned_loss=0.02775, over 4753.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2048, pruned_loss=0.02837, over 972651.88 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 08:10:18,808 INFO [train.py:715] (3/8) Epoch 18, batch 12300, loss[loss=0.1322, simple_loss=0.2077, pruned_loss=0.02836, over 4890.00 frames.], tot_loss[loss=0.131, simple_loss=0.2049, pruned_loss=0.02862, over 971932.89 frames.], batch size: 16, lr: 1.24e-04
+2022-05-09 08:10:58,226 INFO [train.py:715] (3/8) Epoch 18, batch 12350, loss[loss=0.1516, simple_loss=0.2271, pruned_loss=0.03804, over 4803.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.02846, over 972250.93 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 08:11:37,142 INFO [train.py:715] (3/8) Epoch 18, batch 12400, loss[loss=0.1279, simple_loss=0.2034, pruned_loss=0.02622, over 4936.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02845, over 973024.17 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 08:12:16,684 INFO [train.py:715] (3/8) Epoch 18, batch 12450, loss[loss=0.1169, simple_loss=0.1918, pruned_loss=0.02104, over 4927.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02862, over 974259.67 frames.], batch size: 23, lr: 1.24e-04
+2022-05-09 08:12:55,937 INFO [train.py:715] (3/8) Epoch 18, batch 12500, loss[loss=0.1074, simple_loss=0.1849, pruned_loss=0.01495, over 4977.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02851, over 972998.81 frames.], batch size: 26, lr: 1.24e-04
+2022-05-09 08:13:36,319 INFO [train.py:715] (3/8) Epoch 18, batch 12550, loss[loss=0.1274, simple_loss=0.1911, pruned_loss=0.0318, over 4865.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02889, over 972925.14 frames.], batch size: 34, lr: 1.24e-04
+2022-05-09 08:14:14,824 INFO [train.py:715] (3/8) Epoch 18, batch 12600, loss[loss=0.1284, simple_loss=0.2076, pruned_loss=0.02465, over 4956.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02877, over 972780.38 frames.], batch size: 14, lr: 1.24e-04
+2022-05-09 08:14:54,513 INFO [train.py:715] (3/8) Epoch 18, batch 12650, loss[loss=0.124, simple_loss=0.1974, pruned_loss=0.02535, over 4827.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02888, over 972205.10 frames.], batch size: 13, lr: 1.24e-04
+2022-05-09 08:15:33,311 INFO [train.py:715] (3/8) Epoch 18, batch 12700, loss[loss=0.1531, simple_loss=0.2201, pruned_loss=0.04306, over 4867.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02874, over 972074.41 frames.], batch size: 39, lr: 1.24e-04
+2022-05-09 08:16:12,931 INFO [train.py:715] (3/8) Epoch 18, batch 12750, loss[loss=0.1039, simple_loss=0.1764, pruned_loss=0.01567, over 4909.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02851, over 971808.04 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 08:16:52,481 INFO [train.py:715] (3/8) Epoch 18, batch 12800, loss[loss=0.1222, simple_loss=0.1923, pruned_loss=0.02601, over 4856.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2045, pruned_loss=0.02817, over 972561.80 frames.], batch size: 20, lr: 1.24e-04
+2022-05-09 08:17:31,837 INFO [train.py:715] (3/8) Epoch 18, batch 12850, loss[loss=0.1232, simple_loss=0.2047, pruned_loss=0.02079, over 4871.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02806, over 972145.68 frames.], batch size: 22, lr: 1.24e-04
+2022-05-09 08:18:11,707 INFO [train.py:715] (3/8) Epoch 18, batch 12900, loss[loss=0.1295, simple_loss=0.2078, pruned_loss=0.02557, over 4912.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02811, over 971346.16 frames.], batch size: 17, lr: 1.24e-04
+2022-05-09 08:18:50,195 INFO [train.py:715] (3/8) Epoch 18, batch 12950, loss[loss=0.1504, simple_loss=0.2328, pruned_loss=0.03397, over 4952.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02825, over 971970.27 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 08:19:30,194 INFO [train.py:715] (3/8) Epoch 18, batch 13000, loss[loss=0.1229, simple_loss=0.1996, pruned_loss=0.02311, over 4949.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2052, pruned_loss=0.02786, over 971513.20 frames.], batch size: 21, lr: 1.24e-04
+2022-05-09 08:20:09,527 INFO [train.py:715] (3/8) Epoch 18, batch 13050, loss[loss=0.1164, simple_loss=0.1932, pruned_loss=0.01985, over 4987.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2043, pruned_loss=0.02745, over 971276.30 frames.], batch size: 25, lr: 1.24e-04
+2022-05-09 08:20:48,614 INFO [train.py:715] (3/8) Epoch 18, batch 13100, loss[loss=0.1672, simple_loss=0.2412, pruned_loss=0.04664, over 4864.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02828, over 971472.59 frames.], batch size: 20, lr: 1.24e-04
+2022-05-09 08:21:28,136 INFO [train.py:715] (3/8) Epoch 18, batch 13150, loss[loss=0.1267, simple_loss=0.2021, pruned_loss=0.02566, over 4829.00 frames.], tot_loss[loss=0.1311, simple_loss=0.206, pruned_loss=0.0281, over 972366.09 frames.], batch size: 12, lr: 1.24e-04
+2022-05-09 08:22:07,409 INFO [train.py:715] (3/8) Epoch 18, batch 13200, loss[loss=0.1453, simple_loss=0.2107, pruned_loss=0.03995, over 4960.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02804, over 971688.24 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 08:22:47,221 INFO [train.py:715] (3/8) Epoch 18, batch 13250, loss[loss=0.1254, simple_loss=0.1963, pruned_loss=0.02726, over 4807.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02823, over 971888.50 frames.], batch size: 25, lr: 1.24e-04
+2022-05-09 08:23:25,811 INFO [train.py:715] (3/8) Epoch 18, batch 13300, loss[loss=0.1501, simple_loss=0.2116, pruned_loss=0.04429, over 4822.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02853, over 971861.24 frames.], batch size: 15, lr: 1.24e-04
+2022-05-09 08:24:05,551 INFO [train.py:715] (3/8) Epoch 18, batch 13350, loss[loss=0.1602, simple_loss=0.2215, pruned_loss=0.04942, over 4981.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02869, over 971773.12 frames.], batch size: 24, lr: 1.24e-04
+2022-05-09 08:24:44,553 INFO [train.py:715] (3/8) Epoch 18, batch 13400, loss[loss=0.1332, simple_loss=0.2032, pruned_loss=0.03162, over 4749.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02865, over 972691.08 frames.], batch size: 19, lr: 1.24e-04
+2022-05-09 08:25:25,445 INFO [train.py:715] (3/8) Epoch 18, batch 13450, loss[loss=0.1347, simple_loss=0.207, pruned_loss=0.03119, over 4983.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02818, over 972660.96 frames.], batch size: 33, lr: 1.23e-04
+2022-05-09 08:26:05,138 INFO [train.py:715] (3/8) Epoch 18, batch 13500, loss[loss=0.1185, simple_loss=0.1971, pruned_loss=0.0199, over 4944.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2043, pruned_loss=0.02772, over 973019.00 frames.], batch size: 29, lr: 1.23e-04
+2022-05-09 08:26:44,083 INFO [train.py:715] (3/8) Epoch 18, batch 13550, loss[loss=0.1358, simple_loss=0.2167, pruned_loss=0.02742, over 4977.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2045, pruned_loss=0.02781, over 973536.75 frames.], batch size: 25, lr: 1.23e-04
+2022-05-09 08:27:23,342 INFO [train.py:715] (3/8) Epoch 18, batch 13600, loss[loss=0.1133, simple_loss=0.1896, pruned_loss=0.01846, over 4832.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2041, pruned_loss=0.02755, over 973274.39 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 08:28:02,156 INFO [train.py:715] (3/8) Epoch 18, batch 13650, loss[loss=0.131, simple_loss=0.1971, pruned_loss=0.03244, over 4971.00 frames.], tot_loss[loss=0.1306, simple_loss=0.205, pruned_loss=0.0281, over 972933.80 frames.], batch size: 35, lr: 1.23e-04
+2022-05-09 08:28:41,564 INFO [train.py:715] (3/8) Epoch 18, batch 13700, loss[loss=0.1305, simple_loss=0.2105, pruned_loss=0.02524, over 4793.00 frames.], tot_loss[loss=0.131, simple_loss=0.205, pruned_loss=0.02853, over 972517.52 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 08:29:20,647 INFO [train.py:715] (3/8) Epoch 18, batch 13750, loss[loss=0.1169, simple_loss=0.1871, pruned_loss=0.02331, over 4769.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2047, pruned_loss=0.02876, over 971869.91 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 08:29:59,713 INFO [train.py:715] (3/8) Epoch 18, batch 13800, loss[loss=0.1384, simple_loss=0.2102, pruned_loss=0.03334, over 4840.00 frames.], tot_loss[loss=0.131, simple_loss=0.2047, pruned_loss=0.02866, over 971976.22 frames.], batch size: 32, lr: 1.23e-04
+2022-05-09 08:30:39,482 INFO [train.py:715] (3/8) Epoch 18, batch 13850, loss[loss=0.1531, simple_loss=0.2346, pruned_loss=0.03583, over 4813.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2047, pruned_loss=0.0283, over 971571.69 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 08:31:18,291 INFO [train.py:715] (3/8) Epoch 18, batch 13900, loss[loss=0.1069, simple_loss=0.187, pruned_loss=0.0134, over 4951.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02805, over 972022.79 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 08:31:57,754 INFO [train.py:715] (3/8) Epoch 18, batch 13950, loss[loss=0.1622, simple_loss=0.2376, pruned_loss=0.04342, over 4736.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2045, pruned_loss=0.02797, over 971484.78 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 08:32:37,349 INFO [train.py:715] (3/8) Epoch 18, batch 14000, loss[loss=0.1254, simple_loss=0.2041, pruned_loss=0.02337, over 4879.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2049, pruned_loss=0.02819, over 971131.80 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 08:33:17,110 INFO [train.py:715] (3/8) Epoch 18, batch 14050, loss[loss=0.1363, simple_loss=0.2163, pruned_loss=0.02816, over 4792.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.0286, over 971949.50 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 08:33:56,295 INFO [train.py:715] (3/8) Epoch 18, batch 14100, loss[loss=0.1189, simple_loss=0.196, pruned_loss=0.02097, over 4854.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02877, over 972988.38 frames.], batch size: 13, lr: 1.23e-04
+2022-05-09 08:34:35,396 INFO [train.py:715] (3/8) Epoch 18, batch 14150, loss[loss=0.1089, simple_loss=0.1885, pruned_loss=0.01468, over 4969.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2061, pruned_loss=0.02913, over 972337.38 frames.], batch size: 28, lr: 1.23e-04
+2022-05-09 08:35:14,783 INFO [train.py:715] (3/8) Epoch 18, batch 14200, loss[loss=0.143, simple_loss=0.2237, pruned_loss=0.03117, over 4864.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02861, over 972379.70 frames.], batch size: 20, lr: 1.23e-04
+2022-05-09 08:35:54,059 INFO [train.py:715] (3/8) Epoch 18, batch 14250, loss[loss=0.1315, simple_loss=0.2017, pruned_loss=0.03063, over 4757.00 frames.], tot_loss[loss=0.131, simple_loss=0.2051, pruned_loss=0.02843, over 971988.20 frames.], batch size: 19, lr: 1.23e-04
+2022-05-09 08:36:33,986 INFO [train.py:715] (3/8) Epoch 18, batch 14300, loss[loss=0.1327, simple_loss=0.2082, pruned_loss=0.02863, over 4746.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02874, over 971390.03 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 08:37:13,314 INFO [train.py:715] (3/8) Epoch 18, batch 14350, loss[loss=0.1256, simple_loss=0.2007, pruned_loss=0.02527, over 4983.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02861, over 971509.75 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 08:37:52,856 INFO [train.py:715] (3/8) Epoch 18, batch 14400, loss[loss=0.1053, simple_loss=0.1735, pruned_loss=0.01851, over 4749.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02875, over 971468.02 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 08:38:32,503 INFO [train.py:715] (3/8) Epoch 18, batch 14450, loss[loss=0.1423, simple_loss=0.2138, pruned_loss=0.03539, over 4939.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.0288, over 972567.07 frames.], batch size: 29, lr: 1.23e-04
+2022-05-09 08:39:11,247 INFO [train.py:715] (3/8) Epoch 18, batch 14500, loss[loss=0.1378, simple_loss=0.212, pruned_loss=0.03185, over 4874.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02815, over 973189.70 frames.], batch size: 32, lr: 1.23e-04
+2022-05-09 08:39:50,391 INFO [train.py:715] (3/8) Epoch 18, batch 14550, loss[loss=0.1335, simple_loss=0.2085, pruned_loss=0.02924, over 4955.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02861, over 972900.77 frames.], batch size: 35, lr: 1.23e-04
+2022-05-09 08:40:29,523 INFO [train.py:715] (3/8) Epoch 18, batch 14600, loss[loss=0.1376, simple_loss=0.214, pruned_loss=0.03057, over 4761.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2067, pruned_loss=0.02834, over 972537.08 frames.], batch size: 19, lr: 1.23e-04
+2022-05-09 08:41:09,222 INFO [train.py:715] (3/8) Epoch 18, batch 14650, loss[loss=0.112, simple_loss=0.1895, pruned_loss=0.01722, over 4895.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2059, pruned_loss=0.02794, over 971364.50 frames.], batch size: 22, lr: 1.23e-04
+2022-05-09 08:41:48,678 INFO [train.py:715] (3/8) Epoch 18, batch 14700, loss[loss=0.1244, simple_loss=0.1827, pruned_loss=0.03305, over 4812.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02809, over 971196.73 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 08:42:28,035 INFO [train.py:715] (3/8) Epoch 18, batch 14750, loss[loss=0.1454, simple_loss=0.2221, pruned_loss=0.03438, over 4981.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02814, over 971664.30 frames.], batch size: 40, lr: 1.23e-04
+2022-05-09 08:43:07,464 INFO [train.py:715] (3/8) Epoch 18, batch 14800, loss[loss=0.1241, simple_loss=0.2048, pruned_loss=0.02172, over 4807.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2054, pruned_loss=0.02775, over 971228.82 frames.], batch size: 25, lr: 1.23e-04
+2022-05-09 08:43:46,222 INFO [train.py:715] (3/8) Epoch 18, batch 14850, loss[loss=0.1397, simple_loss=0.2152, pruned_loss=0.03213, over 4989.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02814, over 971974.84 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 08:44:25,878 INFO [train.py:715] (3/8) Epoch 18, batch 14900, loss[loss=0.1428, simple_loss=0.2134, pruned_loss=0.03614, over 4822.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02835, over 972600.94 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 08:45:05,548 INFO [train.py:715] (3/8) Epoch 18, batch 14950, loss[loss=0.135, simple_loss=0.1995, pruned_loss=0.03525, over 4799.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02893, over 972624.96 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 08:45:44,812 INFO [train.py:715] (3/8) Epoch 18, batch 15000, loss[loss=0.1391, simple_loss=0.2087, pruned_loss=0.0347, over 4852.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02908, over 972600.84 frames.], batch size: 30, lr: 1.23e-04
+2022-05-09 08:45:44,813 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 08:45:54,765 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1048, simple_loss=0.1881, pruned_loss=0.01071, over 914524.00 frames.
+2022-05-09 08:46:34,348 INFO [train.py:715] (3/8) Epoch 18, batch 15050, loss[loss=0.1424, simple_loss=0.21, pruned_loss=0.03743, over 4975.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02929, over 971943.82 frames.], batch size: 35, lr: 1.23e-04
+2022-05-09 08:47:13,524 INFO [train.py:715] (3/8) Epoch 18, batch 15100, loss[loss=0.09462, simple_loss=0.1737, pruned_loss=0.007761, over 4822.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2077, pruned_loss=0.02893, over 971822.09 frames.], batch size: 27, lr: 1.23e-04
+2022-05-09 08:47:53,255 INFO [train.py:715] (3/8) Epoch 18, batch 15150, loss[loss=0.132, simple_loss=0.2042, pruned_loss=0.02985, over 4895.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02935, over 973131.90 frames.], batch size: 19, lr: 1.23e-04
+2022-05-09 08:48:32,386 INFO [train.py:715] (3/8) Epoch 18, batch 15200, loss[loss=0.1337, simple_loss=0.2047, pruned_loss=0.03133, over 4861.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02931, over 973663.90 frames.], batch size: 20, lr: 1.23e-04
+2022-05-09 08:49:11,928 INFO [train.py:715] (3/8) Epoch 18, batch 15250, loss[loss=0.1121, simple_loss=0.1847, pruned_loss=0.01981, over 4852.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02926, over 973542.72 frames.], batch size: 13, lr: 1.23e-04
+2022-05-09 08:49:51,791 INFO [train.py:715] (3/8) Epoch 18, batch 15300, loss[loss=0.1185, simple_loss=0.1922, pruned_loss=0.02234, over 4872.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.02895, over 973124.13 frames.], batch size: 22, lr: 1.23e-04
+2022-05-09 08:50:31,162 INFO [train.py:715] (3/8) Epoch 18, batch 15350, loss[loss=0.1243, simple_loss=0.1947, pruned_loss=0.02701, over 4970.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2077, pruned_loss=0.02884, over 972888.07 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 08:51:10,082 INFO [train.py:715] (3/8) Epoch 18, batch 15400, loss[loss=0.1306, simple_loss=0.2039, pruned_loss=0.02865, over 4905.00 frames.], tot_loss[loss=0.1327, simple_loss=0.208, pruned_loss=0.0287, over 972665.81 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 08:51:49,371 INFO [train.py:715] (3/8) Epoch 18, batch 15450, loss[loss=0.1442, simple_loss=0.2219, pruned_loss=0.03329, over 4863.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02909, over 972624.42 frames.], batch size: 20, lr: 1.23e-04
+2022-05-09 08:52:28,996 INFO [train.py:715] (3/8) Epoch 18, batch 15500, loss[loss=0.1418, simple_loss=0.2069, pruned_loss=0.03834, over 4841.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.0293, over 972938.38 frames.], batch size: 30, lr: 1.23e-04
+2022-05-09 08:53:08,161 INFO [train.py:715] (3/8) Epoch 18, batch 15550, loss[loss=0.1264, simple_loss=0.21, pruned_loss=0.02138, over 4904.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02967, over 972448.84 frames.], batch size: 19, lr: 1.23e-04
+2022-05-09 08:53:47,889 INFO [train.py:715] (3/8) Epoch 18, batch 15600, loss[loss=0.1328, simple_loss=0.2131, pruned_loss=0.02624, over 4930.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02976, over 973463.00 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 08:54:28,013 INFO [train.py:715] (3/8) Epoch 18, batch 15650, loss[loss=0.1405, simple_loss=0.2103, pruned_loss=0.03538, over 4720.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02933, over 973235.02 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 08:55:07,612 INFO [train.py:715] (3/8) Epoch 18, batch 15700, loss[loss=0.1774, simple_loss=0.2644, pruned_loss=0.0452, over 4814.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02894, over 973575.35 frames.], batch size: 25, lr: 1.23e-04
+2022-05-09 08:55:46,518 INFO [train.py:715] (3/8) Epoch 18, batch 15750, loss[loss=0.111, simple_loss=0.1953, pruned_loss=0.01331, over 4812.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.02799, over 972314.43 frames.], batch size: 26, lr: 1.23e-04
+2022-05-09 08:56:25,957 INFO [train.py:715] (3/8) Epoch 18, batch 15800, loss[loss=0.1882, simple_loss=0.2577, pruned_loss=0.05937, over 4835.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02843, over 971826.11 frames.], batch size: 30, lr: 1.23e-04
+2022-05-09 08:57:05,871 INFO [train.py:715] (3/8) Epoch 18, batch 15850, loss[loss=0.1178, simple_loss=0.1918, pruned_loss=0.02187, over 4950.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02882, over 971971.57 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 08:57:45,103 INFO [train.py:715] (3/8) Epoch 18, batch 15900, loss[loss=0.1645, simple_loss=0.2443, pruned_loss=0.04236, over 4850.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.0291, over 971885.09 frames.], batch size: 32, lr: 1.23e-04
+2022-05-09 08:58:24,414 INFO [train.py:715] (3/8) Epoch 18, batch 15950, loss[loss=0.1384, simple_loss=0.2205, pruned_loss=0.02811, over 4962.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.0288, over 972374.85 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 08:59:04,888 INFO [train.py:715] (3/8) Epoch 18, batch 16000, loss[loss=0.132, simple_loss=0.213, pruned_loss=0.02549, over 4807.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02922, over 972444.64 frames.], batch size: 25, lr: 1.23e-04
+2022-05-09 08:59:45,381 INFO [train.py:715] (3/8) Epoch 18, batch 16050, loss[loss=0.137, simple_loss=0.2169, pruned_loss=0.02859, over 4979.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02912, over 972491.13 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 09:00:24,420 INFO [train.py:715] (3/8) Epoch 18, batch 16100, loss[loss=0.1282, simple_loss=0.2051, pruned_loss=0.02569, over 4769.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02922, over 972525.86 frames.], batch size: 19, lr: 1.23e-04
+2022-05-09 09:01:03,602 INFO [train.py:715] (3/8) Epoch 18, batch 16150, loss[loss=0.1316, simple_loss=0.2053, pruned_loss=0.02896, over 4971.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2078, pruned_loss=0.02902, over 972910.85 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 09:01:43,696 INFO [train.py:715] (3/8) Epoch 18, batch 16200, loss[loss=0.129, simple_loss=0.2036, pruned_loss=0.02718, over 4771.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2079, pruned_loss=0.02922, over 972013.61 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 09:02:22,641 INFO [train.py:715] (3/8) Epoch 18, batch 16250, loss[loss=0.1406, simple_loss=0.2081, pruned_loss=0.03658, over 4838.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02951, over 972023.36 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 09:03:01,672 INFO [train.py:715] (3/8) Epoch 18, batch 16300, loss[loss=0.1409, simple_loss=0.2107, pruned_loss=0.0356, over 4795.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02931, over 972607.47 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 09:03:41,213 INFO [train.py:715] (3/8) Epoch 18, batch 16350, loss[loss=0.1413, simple_loss=0.216, pruned_loss=0.03337, over 4915.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02926, over 972350.38 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 09:04:20,329 INFO [train.py:715] (3/8) Epoch 18, batch 16400, loss[loss=0.1391, simple_loss=0.2192, pruned_loss=0.02954, over 4805.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02921, over 972935.21 frames.], batch size: 26, lr: 1.23e-04
+2022-05-09 09:04:59,288 INFO [train.py:715] (3/8) Epoch 18, batch 16450, loss[loss=0.1469, simple_loss=0.2183, pruned_loss=0.03778, over 4878.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02901, over 973575.71 frames.], batch size: 39, lr: 1.23e-04
+2022-05-09 09:05:38,805 INFO [train.py:715] (3/8) Epoch 18, batch 16500, loss[loss=0.1315, simple_loss=0.2006, pruned_loss=0.0312, over 4795.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.0287, over 972883.15 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 09:06:18,646 INFO [train.py:715] (3/8) Epoch 18, batch 16550, loss[loss=0.1277, simple_loss=0.1992, pruned_loss=0.0281, over 4987.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02912, over 972598.25 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 09:06:57,075 INFO [train.py:715] (3/8) Epoch 18, batch 16600, loss[loss=0.145, simple_loss=0.2148, pruned_loss=0.03763, over 4841.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02906, over 972295.65 frames.], batch size: 32, lr: 1.23e-04
+2022-05-09 09:07:36,513 INFO [train.py:715] (3/8) Epoch 18, batch 16650, loss[loss=0.1335, simple_loss=0.2153, pruned_loss=0.02581, over 4924.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.0288, over 972552.38 frames.], batch size: 23, lr: 1.23e-04
+2022-05-09 09:08:15,859 INFO [train.py:715] (3/8) Epoch 18, batch 16700, loss[loss=0.1218, simple_loss=0.1962, pruned_loss=0.02375, over 4859.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02897, over 971584.82 frames.], batch size: 20, lr: 1.23e-04
+2022-05-09 09:08:55,198 INFO [train.py:715] (3/8) Epoch 18, batch 16750, loss[loss=0.1095, simple_loss=0.1752, pruned_loss=0.02191, over 4988.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02944, over 972240.59 frames.], batch size: 33, lr: 1.23e-04
+2022-05-09 09:09:34,646 INFO [train.py:715] (3/8) Epoch 18, batch 16800, loss[loss=0.1121, simple_loss=0.193, pruned_loss=0.01563, over 4884.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2064, pruned_loss=0.0296, over 973067.43 frames.], batch size: 22, lr: 1.23e-04
+2022-05-09 09:10:13,851 INFO [train.py:715] (3/8) Epoch 18, batch 16850, loss[loss=0.1333, simple_loss=0.2137, pruned_loss=0.02648, over 4909.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2067, pruned_loss=0.02961, over 972556.81 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 09:10:53,310 INFO [train.py:715] (3/8) Epoch 18, batch 16900, loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03299, over 4897.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02963, over 972146.20 frames.], batch size: 19, lr: 1.23e-04
+2022-05-09 09:11:32,155 INFO [train.py:715] (3/8) Epoch 18, batch 16950, loss[loss=0.103, simple_loss=0.1688, pruned_loss=0.01863, over 4842.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.0292, over 972748.86 frames.], batch size: 13, lr: 1.23e-04
+2022-05-09 09:12:11,613 INFO [train.py:715] (3/8) Epoch 18, batch 17000, loss[loss=0.1389, simple_loss=0.2149, pruned_loss=0.03146, over 4843.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02922, over 972121.01 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 09:12:51,062 INFO [train.py:715] (3/8) Epoch 18, batch 17050, loss[loss=0.1359, simple_loss=0.2204, pruned_loss=0.02565, over 4983.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.0292, over 972238.53 frames.], batch size: 28, lr: 1.23e-04
+2022-05-09 09:13:30,535 INFO [train.py:715] (3/8) Epoch 18, batch 17100, loss[loss=0.1227, simple_loss=0.199, pruned_loss=0.02318, over 4819.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02864, over 972239.51 frames.], batch size: 27, lr: 1.23e-04
+2022-05-09 09:14:10,117 INFO [train.py:715] (3/8) Epoch 18, batch 17150, loss[loss=0.1109, simple_loss=0.1803, pruned_loss=0.02079, over 4763.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.028, over 972685.67 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 09:14:49,240 INFO [train.py:715] (3/8) Epoch 18, batch 17200, loss[loss=0.1421, simple_loss=0.2101, pruned_loss=0.03708, over 4949.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02832, over 973436.28 frames.], batch size: 35, lr: 1.23e-04
+2022-05-09 09:15:28,960 INFO [train.py:715] (3/8) Epoch 18, batch 17250, loss[loss=0.1582, simple_loss=0.2407, pruned_loss=0.03787, over 4830.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02823, over 973259.24 frames.], batch size: 30, lr: 1.23e-04
+2022-05-09 09:16:08,223 INFO [train.py:715] (3/8) Epoch 18, batch 17300, loss[loss=0.1198, simple_loss=0.2069, pruned_loss=0.01635, over 4803.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02814, over 973183.19 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 09:16:48,154 INFO [train.py:715] (3/8) Epoch 18, batch 17350, loss[loss=0.1009, simple_loss=0.1741, pruned_loss=0.01386, over 4819.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02837, over 972842.99 frames.], batch size: 26, lr: 1.23e-04
+2022-05-09 09:17:27,215 INFO [train.py:715] (3/8) Epoch 18, batch 17400, loss[loss=0.1151, simple_loss=0.1899, pruned_loss=0.02015, over 4859.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02836, over 972420.99 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 09:18:07,007 INFO [train.py:715] (3/8) Epoch 18, batch 17450, loss[loss=0.1474, simple_loss=0.2149, pruned_loss=0.03992, over 4834.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02873, over 972099.70 frames.], batch size: 30, lr: 1.23e-04
+2022-05-09 09:18:46,084 INFO [train.py:715] (3/8) Epoch 18, batch 17500, loss[loss=0.1429, simple_loss=0.2114, pruned_loss=0.03717, over 4853.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02876, over 971680.82 frames.], batch size: 32, lr: 1.23e-04
+2022-05-09 09:19:24,713 INFO [train.py:715] (3/8) Epoch 18, batch 17550, loss[loss=0.1193, simple_loss=0.1968, pruned_loss=0.02086, over 4850.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02842, over 971344.92 frames.], batch size: 20, lr: 1.23e-04
+2022-05-09 09:20:04,281 INFO [train.py:715] (3/8) Epoch 18, batch 17600, loss[loss=0.132, simple_loss=0.2205, pruned_loss=0.02174, over 4899.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02867, over 970363.86 frames.], batch size: 22, lr: 1.23e-04
+2022-05-09 09:20:43,548 INFO [train.py:715] (3/8) Epoch 18, batch 17650, loss[loss=0.1169, simple_loss=0.1931, pruned_loss=0.02035, over 4788.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02855, over 970772.61 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 09:21:22,850 INFO [train.py:715] (3/8) Epoch 18, batch 17700, loss[loss=0.1213, simple_loss=0.1952, pruned_loss=0.02373, over 4850.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02855, over 970953.90 frames.], batch size: 30, lr: 1.23e-04
+2022-05-09 09:22:01,950 INFO [train.py:715] (3/8) Epoch 18, batch 17750, loss[loss=0.1207, simple_loss=0.1975, pruned_loss=0.02198, over 4831.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02875, over 971313.04 frames.], batch size: 13, lr: 1.23e-04
+2022-05-09 09:22:41,550 INFO [train.py:715] (3/8) Epoch 18, batch 17800, loss[loss=0.1169, simple_loss=0.1956, pruned_loss=0.01907, over 4922.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2059, pruned_loss=0.02813, over 971398.08 frames.], batch size: 29, lr: 1.23e-04
+2022-05-09 09:23:20,834 INFO [train.py:715] (3/8) Epoch 18, batch 17850, loss[loss=0.1301, simple_loss=0.2121, pruned_loss=0.02409, over 4773.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02847, over 971414.48 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 09:23:59,346 INFO [train.py:715] (3/8) Epoch 18, batch 17900, loss[loss=0.128, simple_loss=0.1917, pruned_loss=0.03218, over 4730.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02846, over 971420.29 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 09:24:39,458 INFO [train.py:715] (3/8) Epoch 18, batch 17950, loss[loss=0.1163, simple_loss=0.1746, pruned_loss=0.02896, over 4781.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.0286, over 972511.86 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 09:25:18,520 INFO [train.py:715] (3/8) Epoch 18, batch 18000, loss[loss=0.1041, simple_loss=0.1763, pruned_loss=0.0159, over 4918.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02859, over 973099.25 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 09:25:18,521 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 09:25:28,382 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01063, over 914524.00 frames.
+2022-05-09 09:26:07,769 INFO [train.py:715] (3/8) Epoch 18, batch 18050, loss[loss=0.1472, simple_loss=0.2117, pruned_loss=0.04133, over 4748.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2055, pruned_loss=0.02858, over 973444.48 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 09:26:47,166 INFO [train.py:715] (3/8) Epoch 18, batch 18100, loss[loss=0.1461, simple_loss=0.2201, pruned_loss=0.03608, over 4904.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2049, pruned_loss=0.02849, over 973351.19 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 09:27:26,271 INFO [train.py:715] (3/8) Epoch 18, batch 18150, loss[loss=0.1394, simple_loss=0.2059, pruned_loss=0.0365, over 4768.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2052, pruned_loss=0.02868, over 973371.54 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 09:28:06,059 INFO [train.py:715] (3/8) Epoch 18, batch 18200, loss[loss=0.1207, simple_loss=0.1929, pruned_loss=0.02419, over 4990.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2055, pruned_loss=0.02864, over 973599.71 frames.], batch size: 25, lr: 1.23e-04
+2022-05-09 09:28:45,753 INFO [train.py:715] (3/8) Epoch 18, batch 18250, loss[loss=0.1354, simple_loss=0.2057, pruned_loss=0.03259, over 4868.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2059, pruned_loss=0.02913, over 973371.75 frames.], batch size: 22, lr: 1.23e-04
+2022-05-09 09:29:24,153 INFO [train.py:715] (3/8) Epoch 18, batch 18300, loss[loss=0.1655, simple_loss=0.2425, pruned_loss=0.04426, over 4879.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02924, over 972667.41 frames.], batch size: 39, lr: 1.23e-04
+2022-05-09 09:30:03,825 INFO [train.py:715] (3/8) Epoch 18, batch 18350, loss[loss=0.1307, simple_loss=0.1973, pruned_loss=0.03202, over 4840.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02937, over 971635.24 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 09:30:43,382 INFO [train.py:715] (3/8) Epoch 18, batch 18400, loss[loss=0.1607, simple_loss=0.2315, pruned_loss=0.04499, over 4816.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.03001, over 972575.42 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 09:31:22,381 INFO [train.py:715] (3/8) Epoch 18, batch 18450, loss[loss=0.1356, simple_loss=0.2126, pruned_loss=0.02926, over 4829.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02956, over 972690.85 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 09:32:01,512 INFO [train.py:715] (3/8) Epoch 18, batch 18500, loss[loss=0.1769, simple_loss=0.2459, pruned_loss=0.05396, over 4775.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02889, over 972918.99 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 09:32:40,865 INFO [train.py:715] (3/8) Epoch 18, batch 18550, loss[loss=0.1553, simple_loss=0.2349, pruned_loss=0.03779, over 4968.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02888, over 972758.55 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 09:33:20,074 INFO [train.py:715] (3/8) Epoch 18, batch 18600, loss[loss=0.1449, simple_loss=0.2099, pruned_loss=0.03995, over 4774.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02847, over 973146.77 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 09:33:58,713 INFO [train.py:715] (3/8) Epoch 18, batch 18650, loss[loss=0.1303, simple_loss=0.1981, pruned_loss=0.03121, over 4880.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.0286, over 972996.18 frames.], batch size: 22, lr: 1.23e-04
+2022-05-09 09:34:38,208 INFO [train.py:715] (3/8) Epoch 18, batch 18700, loss[loss=0.1413, simple_loss=0.2091, pruned_loss=0.03674, over 4803.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02863, over 973299.23 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 09:35:17,421 INFO [train.py:715] (3/8) Epoch 18, batch 18750, loss[loss=0.1559, simple_loss=0.2233, pruned_loss=0.04424, over 4842.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02928, over 973680.20 frames.], batch size: 34, lr: 1.23e-04
+2022-05-09 09:35:56,633 INFO [train.py:715] (3/8) Epoch 18, batch 18800, loss[loss=0.1425, simple_loss=0.2074, pruned_loss=0.03882, over 4640.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02909, over 973804.71 frames.], batch size: 13, lr: 1.23e-04
+2022-05-09 09:36:35,997 INFO [train.py:715] (3/8) Epoch 18, batch 18850, loss[loss=0.107, simple_loss=0.1772, pruned_loss=0.01838, over 4800.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02871, over 972843.66 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 09:37:15,848 INFO [train.py:715] (3/8) Epoch 18, batch 18900, loss[loss=0.1387, simple_loss=0.2164, pruned_loss=0.0305, over 4906.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02872, over 972921.56 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 09:37:54,909 INFO [train.py:715] (3/8) Epoch 18, batch 18950, loss[loss=0.1219, simple_loss=0.2117, pruned_loss=0.01605, over 4834.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02886, over 971920.08 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 09:38:33,357 INFO [train.py:715] (3/8) Epoch 18, batch 19000, loss[loss=0.1269, simple_loss=0.1988, pruned_loss=0.02751, over 4875.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02892, over 972233.31 frames.], batch size: 20, lr: 1.23e-04
+2022-05-09 09:39:12,865 INFO [train.py:715] (3/8) Epoch 18, batch 19050, loss[loss=0.1111, simple_loss=0.1843, pruned_loss=0.01898, over 4825.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02922, over 972217.19 frames.], batch size: 25, lr: 1.23e-04
+2022-05-09 09:39:51,874 INFO [train.py:715] (3/8) Epoch 18, batch 19100, loss[loss=0.126, simple_loss=0.2007, pruned_loss=0.02569, over 4814.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02897, over 971440.63 frames.], batch size: 25, lr: 1.23e-04
+2022-05-09 09:40:31,188 INFO [train.py:715] (3/8) Epoch 18, batch 19150, loss[loss=0.1488, simple_loss=0.2177, pruned_loss=0.03996, over 4701.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02922, over 971406.00 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 09:41:11,057 INFO [train.py:715] (3/8) Epoch 18, batch 19200, loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02864, over 4789.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.0289, over 972487.58 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 09:41:50,579 INFO [train.py:715] (3/8) Epoch 18, batch 19250, loss[loss=0.1373, simple_loss=0.2129, pruned_loss=0.03091, over 4952.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02875, over 972440.64 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 09:42:29,653 INFO [train.py:715] (3/8) Epoch 18, batch 19300, loss[loss=0.1051, simple_loss=0.1788, pruned_loss=0.01572, over 4928.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02837, over 972435.27 frames.], batch size: 29, lr: 1.23e-04
+2022-05-09 09:43:08,117 INFO [train.py:715] (3/8) Epoch 18, batch 19350, loss[loss=0.105, simple_loss=0.175, pruned_loss=0.01745, over 4662.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2052, pruned_loss=0.02762, over 972499.93 frames.], batch size: 13, lr: 1.23e-04
+2022-05-09 09:43:47,526 INFO [train.py:715] (3/8) Epoch 18, batch 19400, loss[loss=0.1258, simple_loss=0.1998, pruned_loss=0.02593, over 4770.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2055, pruned_loss=0.02769, over 972139.12 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 09:44:26,733 INFO [train.py:715] (3/8) Epoch 18, batch 19450, loss[loss=0.1396, simple_loss=0.2161, pruned_loss=0.03161, over 4946.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2053, pruned_loss=0.02771, over 971935.03 frames.], batch size: 23, lr: 1.23e-04
+2022-05-09 09:45:05,482 INFO [train.py:715] (3/8) Epoch 18, batch 19500, loss[loss=0.1114, simple_loss=0.19, pruned_loss=0.01637, over 4806.00 frames.], tot_loss[loss=0.1302, simple_loss=0.205, pruned_loss=0.02771, over 972218.88 frames.], batch size: 25, lr: 1.23e-04
+2022-05-09 09:45:44,653 INFO [train.py:715] (3/8) Epoch 18, batch 19550, loss[loss=0.1625, simple_loss=0.2288, pruned_loss=0.04811, over 4799.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02797, over 971778.61 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 09:46:24,060 INFO [train.py:715] (3/8) Epoch 18, batch 19600, loss[loss=0.1337, simple_loss=0.2016, pruned_loss=0.03284, over 4831.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02867, over 972119.29 frames.], batch size: 30, lr: 1.23e-04
+2022-05-09 09:47:02,886 INFO [train.py:715] (3/8) Epoch 18, batch 19650, loss[loss=0.1786, simple_loss=0.2614, pruned_loss=0.04791, over 4860.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02913, over 971978.47 frames.], batch size: 32, lr: 1.23e-04
+2022-05-09 09:47:41,710 INFO [train.py:715] (3/8) Epoch 18, batch 19700, loss[loss=0.1472, simple_loss=0.2323, pruned_loss=0.03102, over 4859.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02884, over 972503.56 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 09:48:21,728 INFO [train.py:715] (3/8) Epoch 18, batch 19750, loss[loss=0.1205, simple_loss=0.1971, pruned_loss=0.02194, over 4775.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02881, over 972837.34 frames.], batch size: 19, lr: 1.23e-04
+2022-05-09 09:49:01,596 INFO [train.py:715] (3/8) Epoch 18, batch 19800, loss[loss=0.141, simple_loss=0.2151, pruned_loss=0.03347, over 4963.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02887, over 971921.07 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 09:49:40,676 INFO [train.py:715] (3/8) Epoch 18, batch 19850, loss[loss=0.1516, simple_loss=0.2238, pruned_loss=0.03972, over 4902.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02885, over 972252.62 frames.], batch size: 19, lr: 1.23e-04
+2022-05-09 09:50:20,123 INFO [train.py:715] (3/8) Epoch 18, batch 19900, loss[loss=0.1121, simple_loss=0.193, pruned_loss=0.01556, over 4991.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02838, over 973055.78 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 09:50:59,802 INFO [train.py:715] (3/8) Epoch 18, batch 19950, loss[loss=0.1251, simple_loss=0.207, pruned_loss=0.02161, over 4808.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02857, over 972925.48 frames.], batch size: 26, lr: 1.23e-04
+2022-05-09 09:51:39,046 INFO [train.py:715] (3/8) Epoch 18, batch 20000, loss[loss=0.1272, simple_loss=0.2019, pruned_loss=0.02625, over 4981.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02834, over 973029.53 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 09:52:18,799 INFO [train.py:715] (3/8) Epoch 18, batch 20050, loss[loss=0.1354, simple_loss=0.2169, pruned_loss=0.02691, over 4861.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2063, pruned_loss=0.02814, over 973076.33 frames.], batch size: 38, lr: 1.23e-04
+2022-05-09 09:52:59,021 INFO [train.py:715] (3/8) Epoch 18, batch 20100, loss[loss=0.1322, simple_loss=0.2174, pruned_loss=0.02349, over 4935.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2056, pruned_loss=0.02794, over 973004.08 frames.], batch size: 29, lr: 1.23e-04
+2022-05-09 09:53:39,145 INFO [train.py:715] (3/8) Epoch 18, batch 20150, loss[loss=0.1185, simple_loss=0.1962, pruned_loss=0.02039, over 4830.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02816, over 972176.83 frames.], batch size: 26, lr: 1.23e-04
+2022-05-09 09:54:18,209 INFO [train.py:715] (3/8) Epoch 18, batch 20200, loss[loss=0.1287, simple_loss=0.2079, pruned_loss=0.02472, over 4913.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02846, over 972141.36 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 09:54:57,194 INFO [train.py:715] (3/8) Epoch 18, batch 20250, loss[loss=0.1361, simple_loss=0.213, pruned_loss=0.02953, over 4689.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.0284, over 972266.97 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 09:55:36,875 INFO [train.py:715] (3/8) Epoch 18, batch 20300, loss[loss=0.1435, simple_loss=0.2273, pruned_loss=0.02987, over 4782.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2067, pruned_loss=0.02839, over 972287.00 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 09:56:16,003 INFO [train.py:715] (3/8) Epoch 18, batch 20350, loss[loss=0.1275, simple_loss=0.2098, pruned_loss=0.02264, over 4891.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02834, over 971602.64 frames.], batch size: 19, lr: 1.23e-04
+2022-05-09 09:56:55,261 INFO [train.py:715] (3/8) Epoch 18, batch 20400, loss[loss=0.1153, simple_loss=0.1838, pruned_loss=0.02341, over 4995.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.0286, over 971894.92 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 09:57:34,098 INFO [train.py:715] (3/8) Epoch 18, batch 20450, loss[loss=0.1528, simple_loss=0.2226, pruned_loss=0.04152, over 4921.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02908, over 971941.54 frames.], batch size: 39, lr: 1.23e-04
+2022-05-09 09:58:14,210 INFO [train.py:715] (3/8) Epoch 18, batch 20500, loss[loss=0.1453, simple_loss=0.229, pruned_loss=0.03083, over 4802.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02918, over 972099.95 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 09:58:52,923 INFO [train.py:715] (3/8) Epoch 18, batch 20550, loss[loss=0.1479, simple_loss=0.2306, pruned_loss=0.03259, over 4949.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02923, over 972285.42 frames.], batch size: 39, lr: 1.23e-04
+2022-05-09 09:59:31,853 INFO [train.py:715] (3/8) Epoch 18, batch 20600, loss[loss=0.1416, simple_loss=0.211, pruned_loss=0.03615, over 4762.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.02936, over 972491.61 frames.], batch size: 19, lr: 1.23e-04
+2022-05-09 10:00:10,869 INFO [train.py:715] (3/8) Epoch 18, batch 20650, loss[loss=0.1335, simple_loss=0.2009, pruned_loss=0.03305, over 4843.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02904, over 972503.28 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 10:00:50,419 INFO [train.py:715] (3/8) Epoch 18, batch 20700, loss[loss=0.1246, simple_loss=0.1809, pruned_loss=0.03413, over 4904.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02933, over 972519.85 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 10:01:28,861 INFO [train.py:715] (3/8) Epoch 18, batch 20750, loss[loss=0.1499, simple_loss=0.2233, pruned_loss=0.03827, over 4922.00 frames.], tot_loss[loss=0.1332, simple_loss=0.208, pruned_loss=0.02918, over 972291.27 frames.], batch size: 23, lr: 1.23e-04
+2022-05-09 10:02:08,332 INFO [train.py:715] (3/8) Epoch 18, batch 20800, loss[loss=0.1079, simple_loss=0.1879, pruned_loss=0.01395, over 4910.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02917, over 972541.45 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 10:02:47,765 INFO [train.py:715] (3/8) Epoch 18, batch 20850, loss[loss=0.1505, simple_loss=0.2213, pruned_loss=0.03986, over 4985.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02898, over 972944.61 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 10:03:26,623 INFO [train.py:715] (3/8) Epoch 18, batch 20900, loss[loss=0.1019, simple_loss=0.1817, pruned_loss=0.01103, over 4961.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02847, over 972853.26 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 10:04:05,321 INFO [train.py:715] (3/8) Epoch 18, batch 20950, loss[loss=0.1204, simple_loss=0.1972, pruned_loss=0.02181, over 4868.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2072, pruned_loss=0.02876, over 973774.40 frames.], batch size: 20, lr: 1.23e-04
+2022-05-09 10:04:44,841 INFO [train.py:715] (3/8) Epoch 18, batch 21000, loss[loss=0.1374, simple_loss=0.2064, pruned_loss=0.03419, over 4870.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02851, over 973267.73 frames.], batch size: 30, lr: 1.23e-04
+2022-05-09 10:04:44,841 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 10:04:54,815 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1046, simple_loss=0.1879, pruned_loss=0.01059, over 914524.00 frames.
+2022-05-09 10:05:34,567 INFO [train.py:715] (3/8) Epoch 18, batch 21050, loss[loss=0.1514, simple_loss=0.2275, pruned_loss=0.03769, over 4914.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02836, over 973575.15 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 10:06:14,356 INFO [train.py:715] (3/8) Epoch 18, batch 21100, loss[loss=0.1274, simple_loss=0.209, pruned_loss=0.02293, over 4929.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02879, over 973129.61 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 10:06:53,523 INFO [train.py:715] (3/8) Epoch 18, batch 21150, loss[loss=0.1229, simple_loss=0.1957, pruned_loss=0.02498, over 4839.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2076, pruned_loss=0.02891, over 973049.66 frames.], batch size: 30, lr: 1.23e-04
+2022-05-09 10:07:33,003 INFO [train.py:715] (3/8) Epoch 18, batch 21200, loss[loss=0.1655, simple_loss=0.2377, pruned_loss=0.04661, over 4810.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2075, pruned_loss=0.029, over 973558.71 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 10:08:12,709 INFO [train.py:715] (3/8) Epoch 18, batch 21250, loss[loss=0.1574, simple_loss=0.2231, pruned_loss=0.0458, over 4878.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02871, over 973769.09 frames.], batch size: 39, lr: 1.23e-04
+2022-05-09 10:08:51,643 INFO [train.py:715] (3/8) Epoch 18, batch 21300, loss[loss=0.1105, simple_loss=0.1868, pruned_loss=0.01708, over 4822.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02861, over 972546.67 frames.], batch size: 26, lr: 1.23e-04
+2022-05-09 10:09:30,194 INFO [train.py:715] (3/8) Epoch 18, batch 21350, loss[loss=0.1329, simple_loss=0.2128, pruned_loss=0.02652, over 4886.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02858, over 972218.49 frames.], batch size: 22, lr: 1.23e-04
+2022-05-09 10:10:09,583 INFO [train.py:715] (3/8) Epoch 18, batch 21400, loss[loss=0.1444, simple_loss=0.2147, pruned_loss=0.03711, over 4949.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02829, over 973056.34 frames.], batch size: 35, lr: 1.23e-04
+2022-05-09 10:10:51,763 INFO [train.py:715] (3/8) Epoch 18, batch 21450, loss[loss=0.09564, simple_loss=0.1585, pruned_loss=0.01641, over 4810.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02827, over 972959.45 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 10:11:30,944 INFO [train.py:715] (3/8) Epoch 18, batch 21500, loss[loss=0.133, simple_loss=0.2115, pruned_loss=0.02727, over 4921.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02868, over 972317.94 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 10:12:09,694 INFO [train.py:715] (3/8) Epoch 18, batch 21550, loss[loss=0.1095, simple_loss=0.1866, pruned_loss=0.01624, over 4988.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2062, pruned_loss=0.02914, over 972597.66 frames.], batch size: 28, lr: 1.23e-04
+2022-05-09 10:12:49,089 INFO [train.py:715] (3/8) Epoch 18, batch 21600, loss[loss=0.111, simple_loss=0.1833, pruned_loss=0.01929, over 4813.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02948, over 972492.94 frames.], batch size: 26, lr: 1.23e-04
+2022-05-09 10:13:28,301 INFO [train.py:715] (3/8) Epoch 18, batch 21650, loss[loss=0.1228, simple_loss=0.1985, pruned_loss=0.02356, over 4781.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02911, over 972758.08 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 10:14:06,695 INFO [train.py:715] (3/8) Epoch 18, batch 21700, loss[loss=0.1426, simple_loss=0.2146, pruned_loss=0.03527, over 4872.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02933, over 972188.97 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 10:14:45,679 INFO [train.py:715] (3/8) Epoch 18, batch 21750, loss[loss=0.1381, simple_loss=0.2227, pruned_loss=0.02671, over 4839.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02891, over 972511.13 frames.], batch size: 26, lr: 1.23e-04
+2022-05-09 10:15:24,823 INFO [train.py:715] (3/8) Epoch 18, batch 21800, loss[loss=0.1154, simple_loss=0.1791, pruned_loss=0.02583, over 4748.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.0289, over 973322.24 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 10:16:04,132 INFO [train.py:715] (3/8) Epoch 18, batch 21850, loss[loss=0.1051, simple_loss=0.1774, pruned_loss=0.01643, over 4860.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02907, over 972679.56 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 10:16:43,561 INFO [train.py:715] (3/8) Epoch 18, batch 21900, loss[loss=0.1401, simple_loss=0.21, pruned_loss=0.03508, over 4940.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02945, over 972730.35 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 10:17:23,081 INFO [train.py:715] (3/8) Epoch 18, batch 21950, loss[loss=0.1406, simple_loss=0.2239, pruned_loss=0.02866, over 4778.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02946, over 972997.85 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 10:18:02,135 INFO [train.py:715] (3/8) Epoch 18, batch 22000, loss[loss=0.1328, simple_loss=0.2087, pruned_loss=0.02845, over 4877.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02904, over 972502.00 frames.], batch size: 22, lr: 1.23e-04
+2022-05-09 10:18:41,239 INFO [train.py:715] (3/8) Epoch 18, batch 22050, loss[loss=0.09837, simple_loss=0.1718, pruned_loss=0.01249, over 4814.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02891, over 972459.55 frames.], batch size: 27, lr: 1.23e-04
+2022-05-09 10:19:20,732 INFO [train.py:715] (3/8) Epoch 18, batch 22100, loss[loss=0.1206, simple_loss=0.2001, pruned_loss=0.02051, over 4834.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02896, over 972369.26 frames.], batch size: 26, lr: 1.23e-04
+2022-05-09 10:19:59,606 INFO [train.py:715] (3/8) Epoch 18, batch 22150, loss[loss=0.1354, simple_loss=0.2021, pruned_loss=0.03429, over 4703.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02888, over 973233.31 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 10:20:39,096 INFO [train.py:715] (3/8) Epoch 18, batch 22200, loss[loss=0.121, simple_loss=0.1988, pruned_loss=0.02162, over 4940.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02848, over 972414.79 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 10:21:17,773 INFO [train.py:715] (3/8) Epoch 18, batch 22250, loss[loss=0.1413, simple_loss=0.2173, pruned_loss=0.03263, over 4983.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02827, over 973609.70 frames.], batch size: 28, lr: 1.23e-04
+2022-05-09 10:21:57,023 INFO [train.py:715] (3/8) Epoch 18, batch 22300, loss[loss=0.1172, simple_loss=0.1923, pruned_loss=0.02099, over 4808.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02864, over 973550.40 frames.], batch size: 26, lr: 1.23e-04
+2022-05-09 10:22:35,718 INFO [train.py:715] (3/8) Epoch 18, batch 22350, loss[loss=0.121, simple_loss=0.1981, pruned_loss=0.02198, over 4801.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02888, over 973567.32 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 10:23:14,496 INFO [train.py:715] (3/8) Epoch 18, batch 22400, loss[loss=0.1447, simple_loss=0.2185, pruned_loss=0.03549, over 4800.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.0288, over 972611.75 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 10:23:53,398 INFO [train.py:715] (3/8) Epoch 18, batch 22450, loss[loss=0.1589, simple_loss=0.2292, pruned_loss=0.04433, over 4873.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02877, over 972859.08 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 10:24:32,485 INFO [train.py:715] (3/8) Epoch 18, batch 22500, loss[loss=0.1151, simple_loss=0.1923, pruned_loss=0.01898, over 4925.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02881, over 972519.69 frames.], batch size: 29, lr: 1.23e-04
+2022-05-09 10:25:11,263 INFO [train.py:715] (3/8) Epoch 18, batch 22550, loss[loss=0.1313, simple_loss=0.1989, pruned_loss=0.03187, over 4832.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02931, over 970981.43 frames.], batch size: 13, lr: 1.23e-04
+2022-05-09 10:25:50,058 INFO [train.py:715] (3/8) Epoch 18, batch 22600, loss[loss=0.1182, simple_loss=0.1935, pruned_loss=0.02143, over 4900.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02955, over 971287.15 frames.], batch size: 22, lr: 1.23e-04
+2022-05-09 10:26:29,079 INFO [train.py:715] (3/8) Epoch 18, batch 22650, loss[loss=0.1207, simple_loss=0.19, pruned_loss=0.02569, over 4788.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02957, over 971117.89 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 10:27:07,866 INFO [train.py:715] (3/8) Epoch 18, batch 22700, loss[loss=0.1165, simple_loss=0.1966, pruned_loss=0.0182, over 4916.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02937, over 971148.36 frames.], batch size: 18, lr: 1.23e-04
+2022-05-09 10:27:46,837 INFO [train.py:715] (3/8) Epoch 18, batch 22750, loss[loss=0.1206, simple_loss=0.1858, pruned_loss=0.02775, over 4993.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02962, over 971535.72 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 10:28:26,216 INFO [train.py:715] (3/8) Epoch 18, batch 22800, loss[loss=0.1597, simple_loss=0.2428, pruned_loss=0.03826, over 4800.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02913, over 970992.36 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 10:29:04,923 INFO [train.py:715] (3/8) Epoch 18, batch 22850, loss[loss=0.1474, simple_loss=0.2163, pruned_loss=0.03926, over 4847.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.02863, over 971670.80 frames.], batch size: 20, lr: 1.23e-04
+2022-05-09 10:29:43,880 INFO [train.py:715] (3/8) Epoch 18, batch 22900, loss[loss=0.1314, simple_loss=0.2085, pruned_loss=0.02715, over 4808.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02879, over 971551.62 frames.], batch size: 25, lr: 1.23e-04
+2022-05-09 10:30:22,780 INFO [train.py:715] (3/8) Epoch 18, batch 22950, loss[loss=0.1247, simple_loss=0.2096, pruned_loss=0.01985, over 4767.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02842, over 972213.71 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 10:31:02,203 INFO [train.py:715] (3/8) Epoch 18, batch 23000, loss[loss=0.1838, simple_loss=0.2465, pruned_loss=0.06058, over 4814.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02852, over 971881.35 frames.], batch size: 25, lr: 1.23e-04
+2022-05-09 10:31:40,968 INFO [train.py:715] (3/8) Epoch 18, batch 23050, loss[loss=0.1329, simple_loss=0.195, pruned_loss=0.0354, over 4765.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02913, over 972078.57 frames.], batch size: 12, lr: 1.23e-04
+2022-05-09 10:32:20,093 INFO [train.py:715] (3/8) Epoch 18, batch 23100, loss[loss=0.1458, simple_loss=0.2134, pruned_loss=0.03912, over 4972.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02925, over 972204.11 frames.], batch size: 35, lr: 1.23e-04
+2022-05-09 10:32:59,659 INFO [train.py:715] (3/8) Epoch 18, batch 23150, loss[loss=0.1405, simple_loss=0.2173, pruned_loss=0.03185, over 4901.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02867, over 972066.82 frames.], batch size: 22, lr: 1.23e-04
+2022-05-09 10:33:38,765 INFO [train.py:715] (3/8) Epoch 18, batch 23200, loss[loss=0.1243, simple_loss=0.2017, pruned_loss=0.02349, over 4937.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02863, over 972407.44 frames.], batch size: 23, lr: 1.23e-04
+2022-05-09 10:34:17,632 INFO [train.py:715] (3/8) Epoch 18, batch 23250, loss[loss=0.113, simple_loss=0.1865, pruned_loss=0.01978, over 4794.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02854, over 972398.64 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 10:34:56,936 INFO [train.py:715] (3/8) Epoch 18, batch 23300, loss[loss=0.1451, simple_loss=0.2182, pruned_loss=0.03597, over 4831.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02858, over 972340.51 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 10:35:36,583 INFO [train.py:715] (3/8) Epoch 18, batch 23350, loss[loss=0.1273, simple_loss=0.202, pruned_loss=0.02633, over 4953.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02871, over 972697.94 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 10:36:15,528 INFO [train.py:715] (3/8) Epoch 18, batch 23400, loss[loss=0.1213, simple_loss=0.1994, pruned_loss=0.0216, over 4827.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02826, over 972429.81 frames.], batch size: 27, lr: 1.23e-04
+2022-05-09 10:36:54,046 INFO [train.py:715] (3/8) Epoch 18, batch 23450, loss[loss=0.1408, simple_loss=0.2125, pruned_loss=0.0345, over 4957.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02828, over 972226.96 frames.], batch size: 24, lr: 1.23e-04
+2022-05-09 10:37:33,552 INFO [train.py:715] (3/8) Epoch 18, batch 23500, loss[loss=0.1208, simple_loss=0.2062, pruned_loss=0.01773, over 4934.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02812, over 971789.43 frames.], batch size: 29, lr: 1.23e-04
+2022-05-09 10:38:12,434 INFO [train.py:715] (3/8) Epoch 18, batch 23550, loss[loss=0.147, simple_loss=0.223, pruned_loss=0.03549, over 4778.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02844, over 971534.39 frames.], batch size: 14, lr: 1.23e-04
+2022-05-09 10:38:51,086 INFO [train.py:715] (3/8) Epoch 18, batch 23600, loss[loss=0.1465, simple_loss=0.2236, pruned_loss=0.03466, over 4873.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02874, over 971230.42 frames.], batch size: 16, lr: 1.23e-04
+2022-05-09 10:39:30,022 INFO [train.py:715] (3/8) Epoch 18, batch 23650, loss[loss=0.1683, simple_loss=0.2328, pruned_loss=0.05191, over 4900.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02882, over 971354.21 frames.], batch size: 17, lr: 1.23e-04
+2022-05-09 10:40:08,661 INFO [train.py:715] (3/8) Epoch 18, batch 23700, loss[loss=0.167, simple_loss=0.2412, pruned_loss=0.04637, over 4828.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02918, over 970690.13 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 10:40:47,465 INFO [train.py:715] (3/8) Epoch 18, batch 23750, loss[loss=0.1169, simple_loss=0.1909, pruned_loss=0.02145, over 4844.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02943, over 971107.82 frames.], batch size: 15, lr: 1.23e-04
+2022-05-09 10:41:26,883 INFO [train.py:715] (3/8) Epoch 18, batch 23800, loss[loss=0.1592, simple_loss=0.2279, pruned_loss=0.04522, over 4931.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02926, over 972183.82 frames.], batch size: 39, lr: 1.23e-04
+2022-05-09 10:42:06,531 INFO [train.py:715] (3/8) Epoch 18, batch 23850, loss[loss=0.1571, simple_loss=0.2319, pruned_loss=0.04115, over 4807.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02895, over 972337.84 frames.], batch size: 21, lr: 1.23e-04
+2022-05-09 10:42:45,350 INFO [train.py:715] (3/8) Epoch 18, batch 23900, loss[loss=0.1446, simple_loss=0.2199, pruned_loss=0.03464, over 4970.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02891, over 972671.05 frames.], batch size: 28, lr: 1.23e-04
+2022-05-09 10:43:24,102 INFO [train.py:715] (3/8) Epoch 18, batch 23950, loss[loss=0.1116, simple_loss=0.1853, pruned_loss=0.01894, over 4951.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02879, over 973547.35 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 10:44:03,427 INFO [train.py:715] (3/8) Epoch 18, batch 24000, loss[loss=0.1315, simple_loss=0.2162, pruned_loss=0.02339, over 4746.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02894, over 973075.55 frames.], batch size: 16, lr: 1.22e-04
+2022-05-09 10:44:03,428 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 10:44:13,350 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1045, simple_loss=0.1878, pruned_loss=0.01057, over 914524.00 frames.
+2022-05-09 10:44:52,998 INFO [train.py:715] (3/8) Epoch 18, batch 24050, loss[loss=0.1011, simple_loss=0.1742, pruned_loss=0.014, over 4824.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02896, over 972675.76 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 10:45:31,814 INFO [train.py:715] (3/8) Epoch 18, batch 24100, loss[loss=0.1274, simple_loss=0.1972, pruned_loss=0.02879, over 4964.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02896, over 972065.62 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 10:46:10,745 INFO [train.py:715] (3/8) Epoch 18, batch 24150, loss[loss=0.1098, simple_loss=0.1851, pruned_loss=0.01725, over 4808.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02886, over 971726.30 frames.], batch size: 26, lr: 1.22e-04
+2022-05-09 10:46:50,171 INFO [train.py:715] (3/8) Epoch 18, batch 24200, loss[loss=0.1583, simple_loss=0.2263, pruned_loss=0.04513, over 4761.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02907, over 971049.81 frames.], batch size: 16, lr: 1.22e-04
+2022-05-09 10:47:29,227 INFO [train.py:715] (3/8) Epoch 18, batch 24250, loss[loss=0.1244, simple_loss=0.19, pruned_loss=0.02937, over 4923.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02893, over 971044.44 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 10:48:08,105 INFO [train.py:715] (3/8) Epoch 18, batch 24300, loss[loss=0.1341, simple_loss=0.2127, pruned_loss=0.0277, over 4834.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02914, over 971298.24 frames.], batch size: 26, lr: 1.22e-04
+2022-05-09 10:48:46,579 INFO [train.py:715] (3/8) Epoch 18, batch 24350, loss[loss=0.1514, simple_loss=0.2189, pruned_loss=0.04195, over 4961.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02896, over 972261.20 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 10:49:25,639 INFO [train.py:715] (3/8) Epoch 18, batch 24400, loss[loss=0.1374, simple_loss=0.2029, pruned_loss=0.03592, over 4971.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02936, over 972608.66 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 10:50:04,247 INFO [train.py:715] (3/8) Epoch 18, batch 24450, loss[loss=0.1398, simple_loss=0.2183, pruned_loss=0.03058, over 4914.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02923, over 971961.53 frames.], batch size: 23, lr: 1.22e-04
+2022-05-09 10:50:42,847 INFO [train.py:715] (3/8) Epoch 18, batch 24500, loss[loss=0.1386, simple_loss=0.2179, pruned_loss=0.02963, over 4802.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02877, over 972340.05 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 10:51:22,303 INFO [train.py:715] (3/8) Epoch 18, batch 24550, loss[loss=0.1264, simple_loss=0.1893, pruned_loss=0.03173, over 4965.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02913, over 972453.51 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 10:52:01,508 INFO [train.py:715] (3/8) Epoch 18, batch 24600, loss[loss=0.1342, simple_loss=0.2047, pruned_loss=0.03187, over 4913.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02904, over 971550.58 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 10:52:40,235 INFO [train.py:715] (3/8) Epoch 18, batch 24650, loss[loss=0.1455, simple_loss=0.2122, pruned_loss=0.03941, over 4976.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02902, over 972443.51 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 10:53:18,840 INFO [train.py:715] (3/8) Epoch 18, batch 24700, loss[loss=0.1349, simple_loss=0.2168, pruned_loss=0.02656, over 4929.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02897, over 972534.18 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 10:53:58,061 INFO [train.py:715] (3/8) Epoch 18, batch 24750, loss[loss=0.1471, simple_loss=0.2312, pruned_loss=0.03153, over 4950.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02864, over 972896.36 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 10:54:37,027 INFO [train.py:715] (3/8) Epoch 18, batch 24800, loss[loss=0.1366, simple_loss=0.2071, pruned_loss=0.03307, over 4974.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02898, over 971651.60 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 10:55:16,442 INFO [train.py:715] (3/8) Epoch 18, batch 24850, loss[loss=0.1099, simple_loss=0.1881, pruned_loss=0.01585, over 4761.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02874, over 971130.46 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 10:55:55,501 INFO [train.py:715] (3/8) Epoch 18, batch 24900, loss[loss=0.1342, simple_loss=0.217, pruned_loss=0.02575, over 4823.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02874, over 972228.73 frames.], batch size: 25, lr: 1.22e-04
+2022-05-09 10:56:35,062 INFO [train.py:715] (3/8) Epoch 18, batch 24950, loss[loss=0.1489, simple_loss=0.2242, pruned_loss=0.03682, over 4816.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02838, over 972906.49 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 10:57:14,187 INFO [train.py:715] (3/8) Epoch 18, batch 25000, loss[loss=0.1173, simple_loss=0.1887, pruned_loss=0.02294, over 4886.00 frames.], tot_loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.02839, over 973169.14 frames.], batch size: 22, lr: 1.22e-04
+2022-05-09 10:57:52,842 INFO [train.py:715] (3/8) Epoch 18, batch 25050, loss[loss=0.1056, simple_loss=0.1874, pruned_loss=0.01195, over 4794.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02842, over 972394.14 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 10:58:32,137 INFO [train.py:715] (3/8) Epoch 18, batch 25100, loss[loss=0.09958, simple_loss=0.1701, pruned_loss=0.01454, over 4823.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02837, over 973008.77 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 10:59:11,692 INFO [train.py:715] (3/8) Epoch 18, batch 25150, loss[loss=0.1491, simple_loss=0.2308, pruned_loss=0.03365, over 4815.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02827, over 972484.40 frames.], batch size: 26, lr: 1.22e-04
+2022-05-09 10:59:50,261 INFO [train.py:715] (3/8) Epoch 18, batch 25200, loss[loss=0.1184, simple_loss=0.1924, pruned_loss=0.02222, over 4696.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02868, over 972249.98 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 11:00:29,822 INFO [train.py:715] (3/8) Epoch 18, batch 25250, loss[loss=0.1545, simple_loss=0.2364, pruned_loss=0.03629, over 4926.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02853, over 971656.97 frames.], batch size: 29, lr: 1.22e-04
+2022-05-09 11:01:09,549 INFO [train.py:715] (3/8) Epoch 18, batch 25300, loss[loss=0.1246, simple_loss=0.1979, pruned_loss=0.02561, over 4953.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02811, over 971916.30 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 11:01:48,680 INFO [train.py:715] (3/8) Epoch 18, batch 25350, loss[loss=0.1107, simple_loss=0.1875, pruned_loss=0.01697, over 4941.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2048, pruned_loss=0.02779, over 971542.68 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 11:02:27,383 INFO [train.py:715] (3/8) Epoch 18, batch 25400, loss[loss=0.1492, simple_loss=0.2223, pruned_loss=0.03802, over 4901.00 frames.], tot_loss[loss=0.1311, simple_loss=0.206, pruned_loss=0.02809, over 971962.36 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 11:03:06,964 INFO [train.py:715] (3/8) Epoch 18, batch 25450, loss[loss=0.127, simple_loss=0.2026, pruned_loss=0.02574, over 4941.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02833, over 971991.09 frames.], batch size: 39, lr: 1.22e-04
+2022-05-09 11:03:45,937 INFO [train.py:715] (3/8) Epoch 18, batch 25500, loss[loss=0.1217, simple_loss=0.1836, pruned_loss=0.02989, over 4802.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02881, over 972051.47 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:04:24,925 INFO [train.py:715] (3/8) Epoch 18, batch 25550, loss[loss=0.1359, simple_loss=0.2085, pruned_loss=0.03166, over 4810.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02944, over 970929.77 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 11:05:04,556 INFO [train.py:715] (3/8) Epoch 18, batch 25600, loss[loss=0.1387, simple_loss=0.2162, pruned_loss=0.03061, over 4957.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02932, over 971218.34 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 11:05:44,105 INFO [train.py:715] (3/8) Epoch 18, batch 25650, loss[loss=0.1275, simple_loss=0.2076, pruned_loss=0.02369, over 4923.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02878, over 971742.30 frames.], batch size: 23, lr: 1.22e-04
+2022-05-09 11:06:23,311 INFO [train.py:715] (3/8) Epoch 18, batch 25700, loss[loss=0.1391, simple_loss=0.2185, pruned_loss=0.02991, over 4899.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.0287, over 971114.56 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 11:07:02,567 INFO [train.py:715] (3/8) Epoch 18, batch 25750, loss[loss=0.1292, simple_loss=0.2036, pruned_loss=0.02738, over 4789.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.0291, over 971857.16 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 11:07:41,971 INFO [train.py:715] (3/8) Epoch 18, batch 25800, loss[loss=0.1292, simple_loss=0.2081, pruned_loss=0.02513, over 4867.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02909, over 972151.97 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:08:20,794 INFO [train.py:715] (3/8) Epoch 18, batch 25850, loss[loss=0.1195, simple_loss=0.1962, pruned_loss=0.02139, over 4917.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02875, over 972718.12 frames.], batch size: 23, lr: 1.22e-04
+2022-05-09 11:08:59,116 INFO [train.py:715] (3/8) Epoch 18, batch 25900, loss[loss=0.1407, simple_loss=0.2153, pruned_loss=0.03306, over 4862.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02882, over 973242.95 frames.], batch size: 38, lr: 1.22e-04
+2022-05-09 11:09:38,437 INFO [train.py:715] (3/8) Epoch 18, batch 25950, loss[loss=0.1559, simple_loss=0.2258, pruned_loss=0.04303, over 4832.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.0291, over 972737.48 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:10:17,515 INFO [train.py:715] (3/8) Epoch 18, batch 26000, loss[loss=0.1268, simple_loss=0.2114, pruned_loss=0.02106, over 4833.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02908, over 972380.23 frames.], batch size: 30, lr: 1.22e-04
+2022-05-09 11:10:56,984 INFO [train.py:715] (3/8) Epoch 18, batch 26050, loss[loss=0.1188, simple_loss=0.1997, pruned_loss=0.01894, over 4863.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02894, over 972252.74 frames.], batch size: 38, lr: 1.22e-04
+2022-05-09 11:11:36,115 INFO [train.py:715] (3/8) Epoch 18, batch 26100, loss[loss=0.1205, simple_loss=0.1876, pruned_loss=0.02672, over 4944.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02845, over 972359.81 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 11:12:15,690 INFO [train.py:715] (3/8) Epoch 18, batch 26150, loss[loss=0.1293, simple_loss=0.2029, pruned_loss=0.02785, over 4980.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02819, over 972650.56 frames.], batch size: 31, lr: 1.22e-04
+2022-05-09 11:12:54,904 INFO [train.py:715] (3/8) Epoch 18, batch 26200, loss[loss=0.1349, simple_loss=0.2195, pruned_loss=0.02512, over 4785.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02846, over 972017.98 frames.], batch size: 17, lr: 1.22e-04
+2022-05-09 11:13:33,237 INFO [train.py:715] (3/8) Epoch 18, batch 26250, loss[loss=0.165, simple_loss=0.2497, pruned_loss=0.04017, over 4890.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02891, over 971717.76 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 11:14:12,859 INFO [train.py:715] (3/8) Epoch 18, batch 26300, loss[loss=0.1116, simple_loss=0.1933, pruned_loss=0.01492, over 4988.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02872, over 971431.40 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 11:14:51,545 INFO [train.py:715] (3/8) Epoch 18, batch 26350, loss[loss=0.1296, simple_loss=0.2066, pruned_loss=0.02634, over 4688.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02869, over 971191.76 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 11:15:30,591 INFO [train.py:715] (3/8) Epoch 18, batch 26400, loss[loss=0.1108, simple_loss=0.1891, pruned_loss=0.01619, over 4839.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02902, over 971581.96 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:16:09,485 INFO [train.py:715] (3/8) Epoch 18, batch 26450, loss[loss=0.1223, simple_loss=0.1997, pruned_loss=0.02245, over 4984.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02954, over 971561.40 frames.], batch size: 25, lr: 1.22e-04
+2022-05-09 11:16:49,038 INFO [train.py:715] (3/8) Epoch 18, batch 26500, loss[loss=0.1211, simple_loss=0.1957, pruned_loss=0.02325, over 4973.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02905, over 972393.73 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 11:17:28,072 INFO [train.py:715] (3/8) Epoch 18, batch 26550, loss[loss=0.1404, simple_loss=0.2189, pruned_loss=0.031, over 4761.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.029, over 972383.47 frames.], batch size: 12, lr: 1.22e-04
+2022-05-09 11:18:06,865 INFO [train.py:715] (3/8) Epoch 18, batch 26600, loss[loss=0.1262, simple_loss=0.2046, pruned_loss=0.02389, over 4980.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.0289, over 973164.95 frames.], batch size: 28, lr: 1.22e-04
+2022-05-09 11:18:46,128 INFO [train.py:715] (3/8) Epoch 18, batch 26650, loss[loss=0.1008, simple_loss=0.1653, pruned_loss=0.01813, over 4830.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02906, over 971812.43 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:19:25,270 INFO [train.py:715] (3/8) Epoch 18, batch 26700, loss[loss=0.1665, simple_loss=0.2372, pruned_loss=0.04791, over 4926.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02956, over 971369.84 frames.], batch size: 39, lr: 1.22e-04
+2022-05-09 11:20:05,262 INFO [train.py:715] (3/8) Epoch 18, batch 26750, loss[loss=0.1533, simple_loss=0.2233, pruned_loss=0.04164, over 4832.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02896, over 972148.42 frames.], batch size: 30, lr: 1.22e-04
+2022-05-09 11:20:43,659 INFO [train.py:715] (3/8) Epoch 18, batch 26800, loss[loss=0.1132, simple_loss=0.1881, pruned_loss=0.01914, over 4950.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.029, over 972440.14 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 11:21:23,699 INFO [train.py:715] (3/8) Epoch 18, batch 26850, loss[loss=0.1389, simple_loss=0.2237, pruned_loss=0.02704, over 4869.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.0289, over 972666.33 frames.], batch size: 20, lr: 1.22e-04
+2022-05-09 11:22:03,380 INFO [train.py:715] (3/8) Epoch 18, batch 26900, loss[loss=0.1218, simple_loss=0.1981, pruned_loss=0.02279, over 4849.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02894, over 971824.69 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:22:41,420 INFO [train.py:715] (3/8) Epoch 18, batch 26950, loss[loss=0.1322, simple_loss=0.1983, pruned_loss=0.03307, over 4823.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02917, over 972177.07 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:23:20,807 INFO [train.py:715] (3/8) Epoch 18, batch 27000, loss[loss=0.126, simple_loss=0.1952, pruned_loss=0.02842, over 4888.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2054, pruned_loss=0.02918, over 972211.48 frames.], batch size: 22, lr: 1.22e-04
+2022-05-09 11:23:20,808 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 11:23:30,796 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1044, simple_loss=0.1877, pruned_loss=0.01055, over 914524.00 frames.
+2022-05-09 11:24:11,110 INFO [train.py:715] (3/8) Epoch 18, batch 27050, loss[loss=0.1086, simple_loss=0.1845, pruned_loss=0.01633, over 4751.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02904, over 972632.08 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 11:24:50,012 INFO [train.py:715] (3/8) Epoch 18, batch 27100, loss[loss=0.1552, simple_loss=0.2357, pruned_loss=0.03738, over 4918.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02911, over 972052.91 frames.], batch size: 17, lr: 1.22e-04
+2022-05-09 11:25:29,322 INFO [train.py:715] (3/8) Epoch 18, batch 27150, loss[loss=0.1259, simple_loss=0.216, pruned_loss=0.01788, over 4754.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.0287, over 972588.98 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 11:26:08,686 INFO [train.py:715] (3/8) Epoch 18, batch 27200, loss[loss=0.1378, simple_loss=0.2133, pruned_loss=0.03112, over 4828.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02844, over 972176.38 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 11:26:47,916 INFO [train.py:715] (3/8) Epoch 18, batch 27250, loss[loss=0.136, simple_loss=0.2108, pruned_loss=0.03058, over 4975.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02844, over 972184.58 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 11:27:26,983 INFO [train.py:715] (3/8) Epoch 18, batch 27300, loss[loss=0.1362, simple_loss=0.2022, pruned_loss=0.03507, over 4757.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02845, over 972622.39 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 11:28:05,824 INFO [train.py:715] (3/8) Epoch 18, batch 27350, loss[loss=0.133, simple_loss=0.2171, pruned_loss=0.02445, over 4878.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02849, over 972817.61 frames.], batch size: 22, lr: 1.22e-04
+2022-05-09 11:28:46,005 INFO [train.py:715] (3/8) Epoch 18, batch 27400, loss[loss=0.1257, simple_loss=0.2032, pruned_loss=0.02405, over 4635.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02835, over 972480.48 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:29:25,409 INFO [train.py:715] (3/8) Epoch 18, batch 27450, loss[loss=0.1246, simple_loss=0.1992, pruned_loss=0.02503, over 4818.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02889, over 972187.65 frames.], batch size: 25, lr: 1.22e-04
+2022-05-09 11:30:04,446 INFO [train.py:715] (3/8) Epoch 18, batch 27500, loss[loss=0.1344, simple_loss=0.2006, pruned_loss=0.03414, over 4921.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02941, over 971944.02 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 11:30:44,162 INFO [train.py:715] (3/8) Epoch 18, batch 27550, loss[loss=0.1235, simple_loss=0.207, pruned_loss=0.01999, over 4962.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02917, over 971732.68 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 11:31:23,281 INFO [train.py:715] (3/8) Epoch 18, batch 27600, loss[loss=0.126, simple_loss=0.1949, pruned_loss=0.02858, over 4974.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.0295, over 971741.40 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 11:32:01,948 INFO [train.py:715] (3/8) Epoch 18, batch 27650, loss[loss=0.1216, simple_loss=0.1961, pruned_loss=0.02356, over 4794.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2064, pruned_loss=0.02951, over 971736.79 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 11:32:40,860 INFO [train.py:715] (3/8) Epoch 18, batch 27700, loss[loss=0.1454, simple_loss=0.2226, pruned_loss=0.03408, over 4838.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03004, over 971209.81 frames.], batch size: 30, lr: 1.22e-04
+2022-05-09 11:33:20,158 INFO [train.py:715] (3/8) Epoch 18, batch 27750, loss[loss=0.1245, simple_loss=0.2017, pruned_loss=0.02366, over 4983.00 frames.], tot_loss[loss=0.1325, simple_loss=0.206, pruned_loss=0.02954, over 971152.50 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 11:33:59,617 INFO [train.py:715] (3/8) Epoch 18, batch 27800, loss[loss=0.1306, simple_loss=0.1955, pruned_loss=0.03283, over 4965.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2062, pruned_loss=0.02981, over 971477.95 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 11:34:38,868 INFO [train.py:715] (3/8) Epoch 18, batch 27850, loss[loss=0.1503, simple_loss=0.2247, pruned_loss=0.03797, over 4838.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2064, pruned_loss=0.02971, over 971627.49 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:35:18,480 INFO [train.py:715] (3/8) Epoch 18, batch 27900, loss[loss=0.1057, simple_loss=0.1786, pruned_loss=0.01645, over 4825.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.0293, over 971147.50 frames.], batch size: 26, lr: 1.22e-04
+2022-05-09 11:35:57,740 INFO [train.py:715] (3/8) Epoch 18, batch 27950, loss[loss=0.1249, simple_loss=0.186, pruned_loss=0.03195, over 4978.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2064, pruned_loss=0.02945, over 971518.61 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 11:36:36,983 INFO [train.py:715] (3/8) Epoch 18, batch 28000, loss[loss=0.1599, simple_loss=0.2243, pruned_loss=0.04774, over 4804.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02909, over 972552.50 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 11:37:16,533 INFO [train.py:715] (3/8) Epoch 18, batch 28050, loss[loss=0.1041, simple_loss=0.1775, pruned_loss=0.01541, over 4783.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02914, over 971889.88 frames.], batch size: 12, lr: 1.22e-04
+2022-05-09 11:37:56,319 INFO [train.py:715] (3/8) Epoch 18, batch 28100, loss[loss=0.1287, simple_loss=0.203, pruned_loss=0.02717, over 4809.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02915, over 970979.97 frames.], batch size: 25, lr: 1.22e-04
+2022-05-09 11:38:35,509 INFO [train.py:715] (3/8) Epoch 18, batch 28150, loss[loss=0.1137, simple_loss=0.1964, pruned_loss=0.01555, over 4833.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02884, over 971065.18 frames.], batch size: 26, lr: 1.22e-04
+2022-05-09 11:39:13,845 INFO [train.py:715] (3/8) Epoch 18, batch 28200, loss[loss=0.1297, simple_loss=0.2005, pruned_loss=0.02952, over 4852.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02928, over 971809.52 frames.], batch size: 20, lr: 1.22e-04
+2022-05-09 11:39:53,467 INFO [train.py:715] (3/8) Epoch 18, batch 28250, loss[loss=0.1353, simple_loss=0.2028, pruned_loss=0.03387, over 4942.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.02874, over 971321.31 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 11:40:32,293 INFO [train.py:715] (3/8) Epoch 18, batch 28300, loss[loss=0.1478, simple_loss=0.2129, pruned_loss=0.04137, over 4956.00 frames.], tot_loss[loss=0.132, simple_loss=0.2059, pruned_loss=0.02908, over 971210.43 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 11:41:11,198 INFO [train.py:715] (3/8) Epoch 18, batch 28350, loss[loss=0.1503, simple_loss=0.2164, pruned_loss=0.04205, over 4843.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2057, pruned_loss=0.02921, over 971586.42 frames.], batch size: 32, lr: 1.22e-04
+2022-05-09 11:41:50,495 INFO [train.py:715] (3/8) Epoch 18, batch 28400, loss[loss=0.1289, simple_loss=0.205, pruned_loss=0.02635, over 4783.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2056, pruned_loss=0.02909, over 972153.27 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 11:42:29,771 INFO [train.py:715] (3/8) Epoch 18, batch 28450, loss[loss=0.1148, simple_loss=0.1889, pruned_loss=0.02037, over 4815.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02873, over 972427.13 frames.], batch size: 12, lr: 1.22e-04
+2022-05-09 11:43:08,846 INFO [train.py:715] (3/8) Epoch 18, batch 28500, loss[loss=0.1074, simple_loss=0.185, pruned_loss=0.01493, over 4971.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02892, over 972603.28 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 11:43:47,954 INFO [train.py:715] (3/8) Epoch 18, batch 28550, loss[loss=0.1381, simple_loss=0.2152, pruned_loss=0.03043, over 4883.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02878, over 973245.04 frames.], batch size: 22, lr: 1.22e-04
+2022-05-09 11:44:27,959 INFO [train.py:715] (3/8) Epoch 18, batch 28600, loss[loss=0.1544, simple_loss=0.2309, pruned_loss=0.03897, over 4772.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02889, over 972379.51 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 11:45:06,661 INFO [train.py:715] (3/8) Epoch 18, batch 28650, loss[loss=0.1244, simple_loss=0.2107, pruned_loss=0.01907, over 4912.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02876, over 972657.56 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 11:45:45,609 INFO [train.py:715] (3/8) Epoch 18, batch 28700, loss[loss=0.1408, simple_loss=0.2132, pruned_loss=0.03415, over 4938.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02908, over 973854.89 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 11:46:25,176 INFO [train.py:715] (3/8) Epoch 18, batch 28750, loss[loss=0.1434, simple_loss=0.2056, pruned_loss=0.04057, over 4883.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02892, over 974694.48 frames.], batch size: 22, lr: 1.22e-04
+2022-05-09 11:47:04,222 INFO [train.py:715] (3/8) Epoch 18, batch 28800, loss[loss=0.12, simple_loss=0.1908, pruned_loss=0.02465, over 4656.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02883, over 973593.31 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:47:43,078 INFO [train.py:715] (3/8) Epoch 18, batch 28850, loss[loss=0.1216, simple_loss=0.1939, pruned_loss=0.02467, over 4685.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02873, over 972645.14 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 11:48:21,620 INFO [train.py:715] (3/8) Epoch 18, batch 28900, loss[loss=0.1204, simple_loss=0.2063, pruned_loss=0.01721, over 4831.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02914, over 972531.16 frames.], batch size: 26, lr: 1.22e-04
+2022-05-09 11:49:01,745 INFO [train.py:715] (3/8) Epoch 18, batch 28950, loss[loss=0.1189, simple_loss=0.2028, pruned_loss=0.01752, over 4953.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02865, over 972132.76 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 11:49:40,558 INFO [train.py:715] (3/8) Epoch 18, batch 29000, loss[loss=0.1095, simple_loss=0.1884, pruned_loss=0.01526, over 4829.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02865, over 971989.36 frames.], batch size: 26, lr: 1.22e-04
+2022-05-09 11:50:19,734 INFO [train.py:715] (3/8) Epoch 18, batch 29050, loss[loss=0.1427, simple_loss=0.2103, pruned_loss=0.03757, over 4939.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02874, over 971970.89 frames.], batch size: 23, lr: 1.22e-04
+2022-05-09 11:50:59,124 INFO [train.py:715] (3/8) Epoch 18, batch 29100, loss[loss=0.1224, simple_loss=0.1926, pruned_loss=0.02609, over 4950.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.0287, over 972461.05 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 11:51:38,414 INFO [train.py:715] (3/8) Epoch 18, batch 29150, loss[loss=0.1398, simple_loss=0.2105, pruned_loss=0.03452, over 4699.00 frames.], tot_loss[loss=0.131, simple_loss=0.2058, pruned_loss=0.02814, over 971353.24 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 11:52:17,128 INFO [train.py:715] (3/8) Epoch 18, batch 29200, loss[loss=0.1241, simple_loss=0.1913, pruned_loss=0.02848, over 4961.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2067, pruned_loss=0.02827, over 971559.79 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 11:52:55,643 INFO [train.py:715] (3/8) Epoch 18, batch 29250, loss[loss=0.1239, simple_loss=0.2019, pruned_loss=0.02296, over 4897.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02835, over 972189.55 frames.], batch size: 17, lr: 1.22e-04
+2022-05-09 11:53:35,211 INFO [train.py:715] (3/8) Epoch 18, batch 29300, loss[loss=0.1474, simple_loss=0.2117, pruned_loss=0.04159, over 4973.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02813, over 972201.09 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 11:54:13,911 INFO [train.py:715] (3/8) Epoch 18, batch 29350, loss[loss=0.1224, simple_loss=0.1958, pruned_loss=0.02453, over 4978.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2049, pruned_loss=0.02791, over 971997.64 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 11:54:52,609 INFO [train.py:715] (3/8) Epoch 18, batch 29400, loss[loss=0.1201, simple_loss=0.1909, pruned_loss=0.02458, over 4911.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02798, over 971759.20 frames.], batch size: 23, lr: 1.22e-04
+2022-05-09 11:55:33,955 INFO [train.py:715] (3/8) Epoch 18, batch 29450, loss[loss=0.1267, simple_loss=0.1973, pruned_loss=0.02808, over 4802.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02798, over 971762.70 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 11:56:12,979 INFO [train.py:715] (3/8) Epoch 18, batch 29500, loss[loss=0.1443, simple_loss=0.2029, pruned_loss=0.04287, over 4874.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2049, pruned_loss=0.02811, over 972289.33 frames.], batch size: 16, lr: 1.22e-04
+2022-05-09 11:56:52,073 INFO [train.py:715] (3/8) Epoch 18, batch 29550, loss[loss=0.1469, simple_loss=0.23, pruned_loss=0.03193, over 4923.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02821, over 972557.88 frames.], batch size: 29, lr: 1.22e-04
+2022-05-09 11:57:30,050 INFO [train.py:715] (3/8) Epoch 18, batch 29600, loss[loss=0.1394, simple_loss=0.2112, pruned_loss=0.03383, over 4924.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.0286, over 972628.81 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 11:58:09,259 INFO [train.py:715] (3/8) Epoch 18, batch 29650, loss[loss=0.1407, simple_loss=0.2071, pruned_loss=0.03713, over 4806.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02844, over 972480.81 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 11:58:48,234 INFO [train.py:715] (3/8) Epoch 18, batch 29700, loss[loss=0.1459, simple_loss=0.2206, pruned_loss=0.03558, over 4883.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02851, over 972523.80 frames.], batch size: 32, lr: 1.22e-04
+2022-05-09 11:59:26,598 INFO [train.py:715] (3/8) Epoch 18, batch 29750, loss[loss=0.1357, simple_loss=0.2102, pruned_loss=0.03056, over 4975.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2071, pruned_loss=0.02855, over 971962.39 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 12:00:05,913 INFO [train.py:715] (3/8) Epoch 18, batch 29800, loss[loss=0.1132, simple_loss=0.1935, pruned_loss=0.0165, over 4859.00 frames.], tot_loss[loss=0.1319, simple_loss=0.207, pruned_loss=0.02843, over 971935.62 frames.], batch size: 20, lr: 1.22e-04
+2022-05-09 12:00:45,627 INFO [train.py:715] (3/8) Epoch 18, batch 29850, loss[loss=0.1118, simple_loss=0.1924, pruned_loss=0.0156, over 4751.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02844, over 971469.72 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 12:01:24,706 INFO [train.py:715] (3/8) Epoch 18, batch 29900, loss[loss=0.1301, simple_loss=0.2004, pruned_loss=0.02985, over 4759.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2064, pruned_loss=0.02805, over 972103.11 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 12:02:03,296 INFO [train.py:715] (3/8) Epoch 18, batch 29950, loss[loss=0.1258, simple_loss=0.1984, pruned_loss=0.02658, over 4934.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2064, pruned_loss=0.02825, over 972137.17 frames.], batch size: 39, lr: 1.22e-04
+2022-05-09 12:02:43,063 INFO [train.py:715] (3/8) Epoch 18, batch 30000, loss[loss=0.1127, simple_loss=0.197, pruned_loss=0.01417, over 4855.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02871, over 972227.65 frames.], batch size: 20, lr: 1.22e-04
+2022-05-09 12:02:43,064 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 12:02:52,967 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.01071, over 914524.00 frames.
+2022-05-09 12:03:33,191 INFO [train.py:715] (3/8) Epoch 18, batch 30050, loss[loss=0.1235, simple_loss=0.2, pruned_loss=0.02348, over 4982.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02895, over 973453.44 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 12:04:12,321 INFO [train.py:715] (3/8) Epoch 18, batch 30100, loss[loss=0.1289, simple_loss=0.2065, pruned_loss=0.02565, over 4987.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2073, pruned_loss=0.02876, over 973167.48 frames.], batch size: 25, lr: 1.22e-04
+2022-05-09 12:04:50,500 INFO [train.py:715] (3/8) Epoch 18, batch 30150, loss[loss=0.1153, simple_loss=0.1931, pruned_loss=0.01874, over 4969.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02873, over 973056.88 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 12:05:29,935 INFO [train.py:715] (3/8) Epoch 18, batch 30200, loss[loss=0.1232, simple_loss=0.2009, pruned_loss=0.02274, over 4992.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2078, pruned_loss=0.02885, over 972785.14 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 12:06:09,181 INFO [train.py:715] (3/8) Epoch 18, batch 30250, loss[loss=0.1098, simple_loss=0.1879, pruned_loss=0.01582, over 4804.00 frames.], tot_loss[loss=0.1331, simple_loss=0.208, pruned_loss=0.02913, over 972843.80 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 12:06:48,872 INFO [train.py:715] (3/8) Epoch 18, batch 30300, loss[loss=0.1508, simple_loss=0.2186, pruned_loss=0.04154, over 4865.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.029, over 973706.94 frames.], batch size: 32, lr: 1.22e-04
+2022-05-09 12:07:27,508 INFO [train.py:715] (3/8) Epoch 18, batch 30350, loss[loss=0.1355, simple_loss=0.2073, pruned_loss=0.03181, over 4847.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02886, over 971948.79 frames.], batch size: 32, lr: 1.22e-04
+2022-05-09 12:08:07,406 INFO [train.py:715] (3/8) Epoch 18, batch 30400, loss[loss=0.127, simple_loss=0.2015, pruned_loss=0.02625, over 4939.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02895, over 971893.08 frames.], batch size: 23, lr: 1.22e-04
+2022-05-09 12:08:46,434 INFO [train.py:715] (3/8) Epoch 18, batch 30450, loss[loss=0.1477, simple_loss=0.2131, pruned_loss=0.04115, over 4748.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02903, over 972048.35 frames.], batch size: 16, lr: 1.22e-04
+2022-05-09 12:09:24,922 INFO [train.py:715] (3/8) Epoch 18, batch 30500, loss[loss=0.1274, simple_loss=0.2071, pruned_loss=0.02391, over 4870.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.029, over 972324.28 frames.], batch size: 32, lr: 1.22e-04
+2022-05-09 12:10:04,134 INFO [train.py:715] (3/8) Epoch 18, batch 30550, loss[loss=0.1135, simple_loss=0.1938, pruned_loss=0.0166, over 4926.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02866, over 972107.13 frames.], batch size: 23, lr: 1.22e-04
+2022-05-09 12:10:42,816 INFO [train.py:715] (3/8) Epoch 18, batch 30600, loss[loss=0.1195, simple_loss=0.187, pruned_loss=0.02604, over 4764.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02848, over 971517.92 frames.], batch size: 12, lr: 1.22e-04
+2022-05-09 12:11:21,483 INFO [train.py:715] (3/8) Epoch 18, batch 30650, loss[loss=0.1541, simple_loss=0.2205, pruned_loss=0.04391, over 4857.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02846, over 971521.54 frames.], batch size: 20, lr: 1.22e-04
+2022-05-09 12:12:00,154 INFO [train.py:715] (3/8) Epoch 18, batch 30700, loss[loss=0.1022, simple_loss=0.1826, pruned_loss=0.01089, over 4981.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2057, pruned_loss=0.02781, over 973333.29 frames.], batch size: 28, lr: 1.22e-04
+2022-05-09 12:12:39,281 INFO [train.py:715] (3/8) Epoch 18, batch 30750, loss[loss=0.1123, simple_loss=0.1919, pruned_loss=0.0163, over 4756.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2059, pruned_loss=0.02781, over 972964.80 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 12:13:18,035 INFO [train.py:715] (3/8) Epoch 18, batch 30800, loss[loss=0.1136, simple_loss=0.1911, pruned_loss=0.01805, over 4801.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2059, pruned_loss=0.0279, over 972666.39 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 12:13:56,473 INFO [train.py:715] (3/8) Epoch 18, batch 30850, loss[loss=0.1481, simple_loss=0.2262, pruned_loss=0.03499, over 4803.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2059, pruned_loss=0.02794, over 971719.87 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 12:14:35,508 INFO [train.py:715] (3/8) Epoch 18, batch 30900, loss[loss=0.1421, simple_loss=0.2127, pruned_loss=0.0357, over 4982.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02801, over 972379.51 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 12:15:14,126 INFO [train.py:715] (3/8) Epoch 18, batch 30950, loss[loss=0.1297, simple_loss=0.2061, pruned_loss=0.02664, over 4928.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2064, pruned_loss=0.02814, over 972900.57 frames.], batch size: 29, lr: 1.22e-04
+2022-05-09 12:15:52,437 INFO [train.py:715] (3/8) Epoch 18, batch 31000, loss[loss=0.13, simple_loss=0.2087, pruned_loss=0.02569, over 4784.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2064, pruned_loss=0.02813, over 972388.45 frames.], batch size: 17, lr: 1.22e-04
+2022-05-09 12:16:31,405 INFO [train.py:715] (3/8) Epoch 18, batch 31050, loss[loss=0.1212, simple_loss=0.2053, pruned_loss=0.01851, over 4962.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.0287, over 972089.88 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 12:17:10,960 INFO [train.py:715] (3/8) Epoch 18, batch 31100, loss[loss=0.1351, simple_loss=0.2222, pruned_loss=0.02404, over 4786.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02888, over 971611.39 frames.], batch size: 17, lr: 1.22e-04
+2022-05-09 12:17:49,896 INFO [train.py:715] (3/8) Epoch 18, batch 31150, loss[loss=0.1189, simple_loss=0.1899, pruned_loss=0.02395, over 4831.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02893, over 972100.88 frames.], batch size: 30, lr: 1.22e-04
+2022-05-09 12:18:28,837 INFO [train.py:715] (3/8) Epoch 18, batch 31200, loss[loss=0.1303, simple_loss=0.2075, pruned_loss=0.02656, over 4961.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02905, over 972419.53 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 12:19:08,214 INFO [train.py:715] (3/8) Epoch 18, batch 31250, loss[loss=0.1227, simple_loss=0.1939, pruned_loss=0.02579, over 4797.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02842, over 971953.41 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 12:19:47,257 INFO [train.py:715] (3/8) Epoch 18, batch 31300, loss[loss=0.1168, simple_loss=0.2035, pruned_loss=0.01504, over 4941.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02841, over 971353.40 frames.], batch size: 29, lr: 1.22e-04
+2022-05-09 12:20:25,876 INFO [train.py:715] (3/8) Epoch 18, batch 31350, loss[loss=0.1429, simple_loss=0.2107, pruned_loss=0.03754, over 4985.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.0282, over 971274.98 frames.], batch size: 31, lr: 1.22e-04
+2022-05-09 12:21:05,051 INFO [train.py:715] (3/8) Epoch 18, batch 31400, loss[loss=0.1344, simple_loss=0.2136, pruned_loss=0.02755, over 4751.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02842, over 971513.03 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 12:21:44,555 INFO [train.py:715] (3/8) Epoch 18, batch 31450, loss[loss=0.1422, simple_loss=0.221, pruned_loss=0.03168, over 4856.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02865, over 971287.60 frames.], batch size: 32, lr: 1.22e-04
+2022-05-09 12:22:23,387 INFO [train.py:715] (3/8) Epoch 18, batch 31500, loss[loss=0.1207, simple_loss=0.1887, pruned_loss=0.02635, over 4869.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02887, over 971876.05 frames.], batch size: 22, lr: 1.22e-04
+2022-05-09 12:23:01,623 INFO [train.py:715] (3/8) Epoch 18, batch 31550, loss[loss=0.1266, simple_loss=0.2033, pruned_loss=0.02496, over 4791.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02832, over 971289.80 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 12:23:41,440 INFO [train.py:715] (3/8) Epoch 18, batch 31600, loss[loss=0.1329, simple_loss=0.2094, pruned_loss=0.02815, over 4796.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.0285, over 971722.17 frames.], batch size: 17, lr: 1.22e-04
+2022-05-09 12:24:20,708 INFO [train.py:715] (3/8) Epoch 18, batch 31650, loss[loss=0.1488, simple_loss=0.2141, pruned_loss=0.04177, over 4845.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02861, over 972401.82 frames.], batch size: 30, lr: 1.22e-04
+2022-05-09 12:24:59,687 INFO [train.py:715] (3/8) Epoch 18, batch 31700, loss[loss=0.138, simple_loss=0.2229, pruned_loss=0.02655, over 4873.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02862, over 972051.95 frames.], batch size: 39, lr: 1.22e-04
+2022-05-09 12:25:38,808 INFO [train.py:715] (3/8) Epoch 18, batch 31750, loss[loss=0.136, simple_loss=0.2111, pruned_loss=0.03046, over 4973.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02887, over 972203.95 frames.], batch size: 35, lr: 1.22e-04
+2022-05-09 12:26:18,650 INFO [train.py:715] (3/8) Epoch 18, batch 31800, loss[loss=0.1204, simple_loss=0.1939, pruned_loss=0.02346, over 4679.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2049, pruned_loss=0.02815, over 972269.65 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 12:26:58,018 INFO [train.py:715] (3/8) Epoch 18, batch 31850, loss[loss=0.1357, simple_loss=0.2074, pruned_loss=0.03197, over 4855.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02877, over 972325.55 frames.], batch size: 32, lr: 1.22e-04
+2022-05-09 12:27:36,975 INFO [train.py:715] (3/8) Epoch 18, batch 31900, loss[loss=0.132, simple_loss=0.216, pruned_loss=0.02398, over 4865.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02884, over 972624.73 frames.], batch size: 38, lr: 1.22e-04
+2022-05-09 12:28:16,147 INFO [train.py:715] (3/8) Epoch 18, batch 31950, loss[loss=0.13, simple_loss=0.2029, pruned_loss=0.02856, over 4835.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02926, over 972409.85 frames.], batch size: 30, lr: 1.22e-04
+2022-05-09 12:28:54,459 INFO [train.py:715] (3/8) Epoch 18, batch 32000, loss[loss=0.1332, simple_loss=0.2127, pruned_loss=0.02688, over 4809.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02899, over 972352.92 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 12:29:32,617 INFO [train.py:715] (3/8) Epoch 18, batch 32050, loss[loss=0.1262, simple_loss=0.1994, pruned_loss=0.02652, over 4900.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.02895, over 972553.88 frames.], batch size: 17, lr: 1.22e-04
+2022-05-09 12:30:11,877 INFO [train.py:715] (3/8) Epoch 18, batch 32100, loss[loss=0.1178, simple_loss=0.1918, pruned_loss=0.02192, over 4886.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2056, pruned_loss=0.02901, over 972102.20 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 12:30:51,372 INFO [train.py:715] (3/8) Epoch 18, batch 32150, loss[loss=0.1253, simple_loss=0.2014, pruned_loss=0.02464, over 4888.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.0291, over 972155.02 frames.], batch size: 16, lr: 1.22e-04
+2022-05-09 12:31:30,533 INFO [train.py:715] (3/8) Epoch 18, batch 32200, loss[loss=0.1334, simple_loss=0.2008, pruned_loss=0.03295, over 4971.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02894, over 972309.03 frames.], batch size: 25, lr: 1.22e-04
+2022-05-09 12:32:08,908 INFO [train.py:715] (3/8) Epoch 18, batch 32250, loss[loss=0.1112, simple_loss=0.1899, pruned_loss=0.01629, over 4923.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02917, over 971955.28 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 12:32:48,158 INFO [train.py:715] (3/8) Epoch 18, batch 32300, loss[loss=0.1521, simple_loss=0.2304, pruned_loss=0.0369, over 4795.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02878, over 971833.20 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 12:33:26,714 INFO [train.py:715] (3/8) Epoch 18, batch 32350, loss[loss=0.127, simple_loss=0.2001, pruned_loss=0.02691, over 4782.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02893, over 972233.64 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 12:34:05,358 INFO [train.py:715] (3/8) Epoch 18, batch 32400, loss[loss=0.1274, simple_loss=0.204, pruned_loss=0.02537, over 4972.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02897, over 972098.76 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 12:34:44,781 INFO [train.py:715] (3/8) Epoch 18, batch 32450, loss[loss=0.1362, simple_loss=0.2132, pruned_loss=0.0296, over 4774.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02917, over 971572.12 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 12:35:23,649 INFO [train.py:715] (3/8) Epoch 18, batch 32500, loss[loss=0.1329, simple_loss=0.2099, pruned_loss=0.02792, over 4886.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02934, over 971888.93 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 12:36:02,853 INFO [train.py:715] (3/8) Epoch 18, batch 32550, loss[loss=0.1244, simple_loss=0.2043, pruned_loss=0.02226, over 4859.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02905, over 971963.61 frames.], batch size: 20, lr: 1.22e-04
+2022-05-09 12:36:42,025 INFO [train.py:715] (3/8) Epoch 18, batch 32600, loss[loss=0.1389, simple_loss=0.2165, pruned_loss=0.0307, over 4986.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02894, over 971265.15 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 12:37:21,455 INFO [train.py:715] (3/8) Epoch 18, batch 32650, loss[loss=0.1302, simple_loss=0.2118, pruned_loss=0.0243, over 4796.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02856, over 971517.86 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 12:37:59,895 INFO [train.py:715] (3/8) Epoch 18, batch 32700, loss[loss=0.1283, simple_loss=0.2086, pruned_loss=0.02404, over 4882.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02844, over 971526.55 frames.], batch size: 22, lr: 1.22e-04
+2022-05-09 12:38:38,643 INFO [train.py:715] (3/8) Epoch 18, batch 32750, loss[loss=0.1198, simple_loss=0.1975, pruned_loss=0.02104, over 4757.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02859, over 971336.42 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 12:39:17,960 INFO [train.py:715] (3/8) Epoch 18, batch 32800, loss[loss=0.1294, simple_loss=0.2047, pruned_loss=0.02702, over 4803.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02821, over 971635.75 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 12:39:57,150 INFO [train.py:715] (3/8) Epoch 18, batch 32850, loss[loss=0.1643, simple_loss=0.2351, pruned_loss=0.04675, over 4705.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02803, over 971007.78 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 12:40:35,664 INFO [train.py:715] (3/8) Epoch 18, batch 32900, loss[loss=0.1202, simple_loss=0.201, pruned_loss=0.01972, over 4834.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02805, over 971488.14 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 12:41:14,763 INFO [train.py:715] (3/8) Epoch 18, batch 32950, loss[loss=0.1308, simple_loss=0.2012, pruned_loss=0.03019, over 4826.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.02804, over 971539.99 frames.], batch size: 26, lr: 1.22e-04
+2022-05-09 12:41:53,957 INFO [train.py:715] (3/8) Epoch 18, batch 33000, loss[loss=0.1638, simple_loss=0.2434, pruned_loss=0.04211, over 4851.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02804, over 972021.79 frames.], batch size: 20, lr: 1.22e-04
+2022-05-09 12:41:53,958 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 12:42:03,826 INFO [train.py:742] (3/8) Epoch 18, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01068, over 914524.00 frames.
+2022-05-09 12:42:43,656 INFO [train.py:715] (3/8) Epoch 18, batch 33050, loss[loss=0.1205, simple_loss=0.1952, pruned_loss=0.02292, over 4959.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02856, over 972520.67 frames.], batch size: 24, lr: 1.22e-04
+2022-05-09 12:43:22,619 INFO [train.py:715] (3/8) Epoch 18, batch 33100, loss[loss=0.134, simple_loss=0.2124, pruned_loss=0.0278, over 4945.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02859, over 972390.53 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 12:44:02,106 INFO [train.py:715] (3/8) Epoch 18, batch 33150, loss[loss=0.146, simple_loss=0.2283, pruned_loss=0.0318, over 4954.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02897, over 972452.77 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 12:44:41,945 INFO [train.py:715] (3/8) Epoch 18, batch 33200, loss[loss=0.1131, simple_loss=0.1929, pruned_loss=0.01664, over 4829.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02895, over 972438.18 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 12:45:20,898 INFO [train.py:715] (3/8) Epoch 18, batch 33250, loss[loss=0.1272, simple_loss=0.2019, pruned_loss=0.0263, over 4983.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02898, over 973141.34 frames.], batch size: 31, lr: 1.22e-04
+2022-05-09 12:45:59,530 INFO [train.py:715] (3/8) Epoch 18, batch 33300, loss[loss=0.1595, simple_loss=0.2267, pruned_loss=0.04612, over 4781.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02889, over 973237.51 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 12:46:38,975 INFO [train.py:715] (3/8) Epoch 18, batch 33350, loss[loss=0.1049, simple_loss=0.1788, pruned_loss=0.0155, over 4820.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.0287, over 973158.48 frames.], batch size: 25, lr: 1.22e-04
+2022-05-09 12:47:18,353 INFO [train.py:715] (3/8) Epoch 18, batch 33400, loss[loss=0.1152, simple_loss=0.1861, pruned_loss=0.02217, over 4851.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02876, over 973212.28 frames.], batch size: 20, lr: 1.22e-04
+2022-05-09 12:47:57,080 INFO [train.py:715] (3/8) Epoch 18, batch 33450, loss[loss=0.1171, simple_loss=0.1833, pruned_loss=0.02548, over 4927.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02828, over 973486.08 frames.], batch size: 23, lr: 1.22e-04
+2022-05-09 12:48:36,023 INFO [train.py:715] (3/8) Epoch 18, batch 33500, loss[loss=0.1447, simple_loss=0.2222, pruned_loss=0.03363, over 4688.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2064, pruned_loss=0.02829, over 973436.75 frames.], batch size: 15, lr: 1.22e-04
+2022-05-09 12:49:15,396 INFO [train.py:715] (3/8) Epoch 18, batch 33550, loss[loss=0.1425, simple_loss=0.2155, pruned_loss=0.03473, over 4886.00 frames.], tot_loss[loss=0.131, simple_loss=0.2058, pruned_loss=0.02808, over 972341.79 frames.], batch size: 22, lr: 1.22e-04
+2022-05-09 12:49:54,439 INFO [train.py:715] (3/8) Epoch 18, batch 33600, loss[loss=0.1271, simple_loss=0.2099, pruned_loss=0.0222, over 4915.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02835, over 972116.54 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 12:50:32,502 INFO [train.py:715] (3/8) Epoch 18, batch 33650, loss[loss=0.1403, simple_loss=0.2072, pruned_loss=0.03672, over 4808.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02844, over 972007.75 frames.], batch size: 25, lr: 1.22e-04
+2022-05-09 12:51:11,947 INFO [train.py:715] (3/8) Epoch 18, batch 33700, loss[loss=0.1196, simple_loss=0.1918, pruned_loss=0.0237, over 4776.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02868, over 971491.21 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 12:51:51,116 INFO [train.py:715] (3/8) Epoch 18, batch 33750, loss[loss=0.09087, simple_loss=0.1677, pruned_loss=0.007028, over 4837.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02879, over 971760.31 frames.], batch size: 26, lr: 1.22e-04
+2022-05-09 12:52:30,431 INFO [train.py:715] (3/8) Epoch 18, batch 33800, loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03155, over 4848.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02893, over 972417.58 frames.], batch size: 32, lr: 1.22e-04
+2022-05-09 12:53:09,707 INFO [train.py:715] (3/8) Epoch 18, batch 33850, loss[loss=0.1105, simple_loss=0.1761, pruned_loss=0.02242, over 4894.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02849, over 972684.59 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 12:53:49,535 INFO [train.py:715] (3/8) Epoch 18, batch 33900, loss[loss=0.1319, simple_loss=0.2159, pruned_loss=0.02396, over 4779.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02807, over 973043.58 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 12:54:28,738 INFO [train.py:715] (3/8) Epoch 18, batch 33950, loss[loss=0.1742, simple_loss=0.2427, pruned_loss=0.05287, over 4925.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02783, over 972530.70 frames.], batch size: 39, lr: 1.22e-04
+2022-05-09 12:55:07,057 INFO [train.py:715] (3/8) Epoch 18, batch 34000, loss[loss=0.1138, simple_loss=0.1938, pruned_loss=0.01694, over 4882.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2066, pruned_loss=0.02826, over 972781.90 frames.], batch size: 16, lr: 1.22e-04
+2022-05-09 12:55:46,476 INFO [train.py:715] (3/8) Epoch 18, batch 34050, loss[loss=0.1155, simple_loss=0.1945, pruned_loss=0.01827, over 4919.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2068, pruned_loss=0.02844, over 972205.75 frames.], batch size: 18, lr: 1.22e-04
+2022-05-09 12:56:25,890 INFO [train.py:715] (3/8) Epoch 18, batch 34100, loss[loss=0.1409, simple_loss=0.2094, pruned_loss=0.03618, over 4948.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2061, pruned_loss=0.02804, over 972307.58 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 12:57:05,034 INFO [train.py:715] (3/8) Epoch 18, batch 34150, loss[loss=0.1287, simple_loss=0.2072, pruned_loss=0.02513, over 4810.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02815, over 973378.45 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 12:57:44,078 INFO [train.py:715] (3/8) Epoch 18, batch 34200, loss[loss=0.1256, simple_loss=0.199, pruned_loss=0.02613, over 4950.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02803, over 972596.12 frames.], batch size: 29, lr: 1.22e-04
+2022-05-09 12:58:23,225 INFO [train.py:715] (3/8) Epoch 18, batch 34250, loss[loss=0.1688, simple_loss=0.23, pruned_loss=0.05378, over 4774.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.0289, over 972788.57 frames.], batch size: 17, lr: 1.22e-04
+2022-05-09 12:59:02,033 INFO [train.py:715] (3/8) Epoch 18, batch 34300, loss[loss=0.1207, simple_loss=0.201, pruned_loss=0.02017, over 4802.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02891, over 972109.77 frames.], batch size: 21, lr: 1.22e-04
+2022-05-09 12:59:40,333 INFO [train.py:715] (3/8) Epoch 18, batch 34350, loss[loss=0.1735, simple_loss=0.2447, pruned_loss=0.05113, over 4758.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02908, over 972013.17 frames.], batch size: 16, lr: 1.22e-04
+2022-05-09 13:00:19,860 INFO [train.py:715] (3/8) Epoch 18, batch 34400, loss[loss=0.1421, simple_loss=0.2057, pruned_loss=0.03924, over 4635.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02946, over 972274.06 frames.], batch size: 13, lr: 1.22e-04
+2022-05-09 13:00:59,442 INFO [train.py:715] (3/8) Epoch 18, batch 34450, loss[loss=0.1199, simple_loss=0.1925, pruned_loss=0.02369, over 4911.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02907, over 973190.53 frames.], batch size: 19, lr: 1.22e-04
+2022-05-09 13:01:39,372 INFO [train.py:715] (3/8) Epoch 18, batch 34500, loss[loss=0.1148, simple_loss=0.1851, pruned_loss=0.02222, over 4783.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02926, over 972804.71 frames.], batch size: 14, lr: 1.22e-04
+2022-05-09 13:02:18,895 INFO [train.py:715] (3/8) Epoch 18, batch 34550, loss[loss=0.1096, simple_loss=0.1823, pruned_loss=0.01842, over 4945.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02903, over 972205.02 frames.], batch size: 29, lr: 1.22e-04
+2022-05-09 13:02:58,575 INFO [train.py:715] (3/8) Epoch 18, batch 34600, loss[loss=0.09227, simple_loss=0.161, pruned_loss=0.01179, over 4823.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02928, over 971850.63 frames.], batch size: 12, lr: 1.22e-04
+2022-05-09 13:03:37,758 INFO [train.py:715] (3/8) Epoch 18, batch 34650, loss[loss=0.1583, simple_loss=0.216, pruned_loss=0.05029, over 4783.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02905, over 972149.29 frames.], batch size: 12, lr: 1.22e-04
+2022-05-09 13:04:17,382 INFO [train.py:715] (3/8) Epoch 18, batch 34700, loss[loss=0.111, simple_loss=0.1917, pruned_loss=0.01512, over 4752.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02842, over 972369.07 frames.], batch size: 19, lr: 1.21e-04
+2022-05-09 13:04:56,520 INFO [train.py:715] (3/8) Epoch 18, batch 34750, loss[loss=0.1311, simple_loss=0.2087, pruned_loss=0.02673, over 4901.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02844, over 971850.14 frames.], batch size: 19, lr: 1.21e-04
+2022-05-09 13:05:34,143 INFO [train.py:715] (3/8) Epoch 18, batch 34800, loss[loss=0.1231, simple_loss=0.1908, pruned_loss=0.02769, over 4837.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02849, over 970744.75 frames.], batch size: 12, lr: 1.21e-04
+2022-05-09 13:06:24,915 INFO [train.py:715] (3/8) Epoch 19, batch 0, loss[loss=0.137, simple_loss=0.2076, pruned_loss=0.03316, over 4869.00 frames.], tot_loss[loss=0.137, simple_loss=0.2076, pruned_loss=0.03316, over 4869.00 frames.], batch size: 13, lr: 1.18e-04
+2022-05-09 13:07:03,499 INFO [train.py:715] (3/8) Epoch 19, batch 50, loss[loss=0.1482, simple_loss=0.2132, pruned_loss=0.04165, over 4897.00 frames.], tot_loss[loss=0.1313, simple_loss=0.205, pruned_loss=0.02875, over 219648.30 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 13:07:43,523 INFO [train.py:715] (3/8) Epoch 19, batch 100, loss[loss=0.1301, simple_loss=0.2023, pruned_loss=0.02892, over 4746.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2044, pruned_loss=0.02826, over 386823.80 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 13:08:23,945 INFO [train.py:715] (3/8) Epoch 19, batch 150, loss[loss=0.1236, simple_loss=0.1961, pruned_loss=0.0255, over 4849.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2044, pruned_loss=0.02854, over 516886.29 frames.], batch size: 30, lr: 1.18e-04
+2022-05-09 13:09:04,145 INFO [train.py:715] (3/8) Epoch 19, batch 200, loss[loss=0.1463, simple_loss=0.2293, pruned_loss=0.03163, over 4961.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2055, pruned_loss=0.02861, over 618315.62 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 13:09:44,076 INFO [train.py:715] (3/8) Epoch 19, batch 250, loss[loss=0.1367, simple_loss=0.2127, pruned_loss=0.03036, over 4992.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02848, over 697200.60 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 13:10:24,217 INFO [train.py:715] (3/8) Epoch 19, batch 300, loss[loss=0.1385, simple_loss=0.2268, pruned_loss=0.02515, over 4850.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02875, over 757533.14 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 13:11:04,673 INFO [train.py:715] (3/8) Epoch 19, batch 350, loss[loss=0.126, simple_loss=0.1935, pruned_loss=0.02926, over 4960.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02835, over 805713.17 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 13:11:43,719 INFO [train.py:715] (3/8) Epoch 19, batch 400, loss[loss=0.1373, simple_loss=0.2067, pruned_loss=0.03392, over 4853.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02884, over 843213.16 frames.], batch size: 32, lr: 1.18e-04
+2022-05-09 13:12:24,046 INFO [train.py:715] (3/8) Epoch 19, batch 450, loss[loss=0.1498, simple_loss=0.2143, pruned_loss=0.04259, over 4847.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02882, over 871759.49 frames.], batch size: 30, lr: 1.18e-04
+2022-05-09 13:13:04,619 INFO [train.py:715] (3/8) Epoch 19, batch 500, loss[loss=0.1385, simple_loss=0.213, pruned_loss=0.03198, over 4954.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02911, over 894248.46 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 13:13:44,281 INFO [train.py:715] (3/8) Epoch 19, batch 550, loss[loss=0.1166, simple_loss=0.1932, pruned_loss=0.01999, over 4781.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.0287, over 911663.41 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 13:14:24,234 INFO [train.py:715] (3/8) Epoch 19, batch 600, loss[loss=0.1751, simple_loss=0.2476, pruned_loss=0.0513, over 4775.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02887, over 925178.12 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 13:15:04,546 INFO [train.py:715] (3/8) Epoch 19, batch 650, loss[loss=0.1175, simple_loss=0.2021, pruned_loss=0.01642, over 4798.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.029, over 936392.76 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 13:15:44,874 INFO [train.py:715] (3/8) Epoch 19, batch 700, loss[loss=0.1441, simple_loss=0.22, pruned_loss=0.03408, over 4834.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02898, over 943115.99 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 13:16:24,135 INFO [train.py:715] (3/8) Epoch 19, batch 750, loss[loss=0.1022, simple_loss=0.1694, pruned_loss=0.01751, over 4972.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.0293, over 949892.38 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 13:17:03,941 INFO [train.py:715] (3/8) Epoch 19, batch 800, loss[loss=0.15, simple_loss=0.2287, pruned_loss=0.03567, over 4944.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.0293, over 954888.95 frames.], batch size: 35, lr: 1.18e-04
+2022-05-09 13:17:44,205 INFO [train.py:715] (3/8) Epoch 19, batch 850, loss[loss=0.1359, simple_loss=0.2149, pruned_loss=0.02839, over 4939.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02913, over 959080.31 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 13:18:24,381 INFO [train.py:715] (3/8) Epoch 19, batch 900, loss[loss=0.1202, simple_loss=0.1953, pruned_loss=0.02259, over 4794.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02863, over 961111.93 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 13:19:03,893 INFO [train.py:715] (3/8) Epoch 19, batch 950, loss[loss=0.1356, simple_loss=0.208, pruned_loss=0.03155, over 4753.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02867, over 963601.11 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 13:19:43,254 INFO [train.py:715] (3/8) Epoch 19, batch 1000, loss[loss=0.1646, simple_loss=0.2446, pruned_loss=0.04233, over 4787.00 frames.], tot_loss[loss=0.131, simple_loss=0.205, pruned_loss=0.02846, over 965366.06 frames.], batch size: 13, lr: 1.18e-04
+2022-05-09 13:20:23,194 INFO [train.py:715] (3/8) Epoch 19, batch 1050, loss[loss=0.1477, simple_loss=0.2252, pruned_loss=0.03508, over 4821.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2047, pruned_loss=0.02847, over 966380.47 frames.], batch size: 26, lr: 1.18e-04
+2022-05-09 13:21:02,192 INFO [train.py:715] (3/8) Epoch 19, batch 1100, loss[loss=0.1319, simple_loss=0.2053, pruned_loss=0.02928, over 4994.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.0282, over 967807.24 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 13:21:42,017 INFO [train.py:715] (3/8) Epoch 19, batch 1150, loss[loss=0.1276, simple_loss=0.2075, pruned_loss=0.02381, over 4752.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2047, pruned_loss=0.02798, over 969649.93 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 13:22:21,962 INFO [train.py:715] (3/8) Epoch 19, batch 1200, loss[loss=0.133, simple_loss=0.2042, pruned_loss=0.0309, over 4874.00 frames.], tot_loss[loss=0.1297, simple_loss=0.204, pruned_loss=0.02766, over 969533.58 frames.], batch size: 22, lr: 1.18e-04
+2022-05-09 13:23:01,718 INFO [train.py:715] (3/8) Epoch 19, batch 1250, loss[loss=0.1219, simple_loss=0.2016, pruned_loss=0.02109, over 4937.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2041, pruned_loss=0.02764, over 969549.82 frames.], batch size: 29, lr: 1.18e-04
+2022-05-09 13:23:41,057 INFO [train.py:715] (3/8) Epoch 19, batch 1300, loss[loss=0.1556, simple_loss=0.228, pruned_loss=0.0416, over 4817.00 frames.], tot_loss[loss=0.13, simple_loss=0.2046, pruned_loss=0.02771, over 969628.33 frames.], batch size: 25, lr: 1.18e-04
+2022-05-09 13:24:20,596 INFO [train.py:715] (3/8) Epoch 19, batch 1350, loss[loss=0.1362, simple_loss=0.2112, pruned_loss=0.0306, over 4987.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2049, pruned_loss=0.02783, over 970226.46 frames.], batch size: 28, lr: 1.18e-04
+2022-05-09 13:25:00,618 INFO [train.py:715] (3/8) Epoch 19, batch 1400, loss[loss=0.1248, simple_loss=0.1962, pruned_loss=0.0267, over 4980.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2049, pruned_loss=0.02787, over 969959.16 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 13:25:39,919 INFO [train.py:715] (3/8) Epoch 19, batch 1450, loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03121, over 4945.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02795, over 970364.73 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 13:26:20,231 INFO [train.py:715] (3/8) Epoch 19, batch 1500, loss[loss=0.1344, simple_loss=0.217, pruned_loss=0.02589, over 4932.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.0281, over 971434.71 frames.], batch size: 29, lr: 1.18e-04
+2022-05-09 13:27:00,283 INFO [train.py:715] (3/8) Epoch 19, batch 1550, loss[loss=0.1339, simple_loss=0.209, pruned_loss=0.0294, over 4864.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02806, over 971402.41 frames.], batch size: 20, lr: 1.18e-04
+2022-05-09 13:27:40,367 INFO [train.py:715] (3/8) Epoch 19, batch 1600, loss[loss=0.1512, simple_loss=0.2252, pruned_loss=0.03862, over 4924.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02864, over 971629.01 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 13:28:19,707 INFO [train.py:715] (3/8) Epoch 19, batch 1650, loss[loss=0.1253, simple_loss=0.1914, pruned_loss=0.02956, over 4764.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02859, over 971314.09 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 13:28:59,072 INFO [train.py:715] (3/8) Epoch 19, batch 1700, loss[loss=0.1468, simple_loss=0.2298, pruned_loss=0.03193, over 4750.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02865, over 970762.82 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 13:29:39,055 INFO [train.py:715] (3/8) Epoch 19, batch 1750, loss[loss=0.1215, simple_loss=0.2064, pruned_loss=0.01833, over 4774.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2055, pruned_loss=0.02857, over 971680.68 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 13:30:18,171 INFO [train.py:715] (3/8) Epoch 19, batch 1800, loss[loss=0.1439, simple_loss=0.2105, pruned_loss=0.03869, over 4706.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2047, pruned_loss=0.02875, over 971840.62 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 13:30:57,612 INFO [train.py:715] (3/8) Epoch 19, batch 1850, loss[loss=0.1142, simple_loss=0.198, pruned_loss=0.01518, over 4983.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2048, pruned_loss=0.02874, over 971796.25 frames.], batch size: 25, lr: 1.18e-04
+2022-05-09 13:31:36,858 INFO [train.py:715] (3/8) Epoch 19, batch 1900, loss[loss=0.1356, simple_loss=0.2131, pruned_loss=0.02902, over 4941.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2051, pruned_loss=0.02915, over 971549.49 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 13:32:16,777 INFO [train.py:715] (3/8) Epoch 19, batch 1950, loss[loss=0.14, simple_loss=0.2195, pruned_loss=0.03026, over 4927.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2052, pruned_loss=0.02909, over 971672.45 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 13:32:55,075 INFO [train.py:715] (3/8) Epoch 19, batch 2000, loss[loss=0.1271, simple_loss=0.1871, pruned_loss=0.03353, over 4775.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2045, pruned_loss=0.02842, over 971808.97 frames.], batch size: 12, lr: 1.18e-04
+2022-05-09 13:33:34,211 INFO [train.py:715] (3/8) Epoch 19, batch 2050, loss[loss=0.1603, simple_loss=0.2291, pruned_loss=0.04575, over 4839.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02834, over 971778.55 frames.], batch size: 30, lr: 1.18e-04
+2022-05-09 13:34:13,315 INFO [train.py:715] (3/8) Epoch 19, batch 2100, loss[loss=0.1189, simple_loss=0.1884, pruned_loss=0.02469, over 4854.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02865, over 972679.44 frames.], batch size: 32, lr: 1.18e-04
+2022-05-09 13:34:52,133 INFO [train.py:715] (3/8) Epoch 19, batch 2150, loss[loss=0.1305, simple_loss=0.2127, pruned_loss=0.02418, over 4864.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02918, over 972354.57 frames.], batch size: 20, lr: 1.18e-04
+2022-05-09 13:35:31,127 INFO [train.py:715] (3/8) Epoch 19, batch 2200, loss[loss=0.1164, simple_loss=0.1982, pruned_loss=0.01725, over 4950.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02919, over 972314.32 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 13:36:09,823 INFO [train.py:715] (3/8) Epoch 19, batch 2250, loss[loss=0.1384, simple_loss=0.2181, pruned_loss=0.02931, over 4799.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02986, over 972225.42 frames.], batch size: 25, lr: 1.18e-04
+2022-05-09 13:36:49,415 INFO [train.py:715] (3/8) Epoch 19, batch 2300, loss[loss=0.1241, simple_loss=0.199, pruned_loss=0.02459, over 4913.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.02962, over 972656.62 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 13:37:28,007 INFO [train.py:715] (3/8) Epoch 19, batch 2350, loss[loss=0.127, simple_loss=0.2022, pruned_loss=0.02592, over 4800.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02933, over 972304.41 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 13:38:07,165 INFO [train.py:715] (3/8) Epoch 19, batch 2400, loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.035, over 4891.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.029, over 973361.80 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 13:38:46,614 INFO [train.py:715] (3/8) Epoch 19, batch 2450, loss[loss=0.1267, simple_loss=0.1916, pruned_loss=0.03086, over 4899.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02883, over 973614.39 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 13:39:25,449 INFO [train.py:715] (3/8) Epoch 19, batch 2500, loss[loss=0.106, simple_loss=0.1846, pruned_loss=0.01374, over 4918.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2056, pruned_loss=0.02889, over 973002.14 frames.], batch size: 23, lr: 1.18e-04
+2022-05-09 13:40:04,476 INFO [train.py:715] (3/8) Epoch 19, batch 2550, loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03325, over 4832.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2056, pruned_loss=0.02887, over 972737.95 frames.], batch size: 26, lr: 1.18e-04
+2022-05-09 13:40:44,008 INFO [train.py:715] (3/8) Epoch 19, batch 2600, loss[loss=0.1516, simple_loss=0.2212, pruned_loss=0.04103, over 4907.00 frames.], tot_loss[loss=0.131, simple_loss=0.2049, pruned_loss=0.02854, over 972712.20 frames.], batch size: 39, lr: 1.18e-04
+2022-05-09 13:41:26,470 INFO [train.py:715] (3/8) Epoch 19, batch 2650, loss[loss=0.1334, simple_loss=0.216, pruned_loss=0.02534, over 4944.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2046, pruned_loss=0.0282, over 973180.44 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 13:42:05,376 INFO [train.py:715] (3/8) Epoch 19, batch 2700, loss[loss=0.116, simple_loss=0.1892, pruned_loss=0.0214, over 4827.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2049, pruned_loss=0.02814, over 973037.58 frames.], batch size: 30, lr: 1.18e-04
+2022-05-09 13:42:44,051 INFO [train.py:715] (3/8) Epoch 19, batch 2750, loss[loss=0.1464, simple_loss=0.2221, pruned_loss=0.03533, over 4777.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02886, over 972969.92 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 13:43:23,788 INFO [train.py:715] (3/8) Epoch 19, batch 2800, loss[loss=0.1433, simple_loss=0.2185, pruned_loss=0.03406, over 4800.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02855, over 972786.78 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 13:44:03,072 INFO [train.py:715] (3/8) Epoch 19, batch 2850, loss[loss=0.1288, simple_loss=0.207, pruned_loss=0.02528, over 4753.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02837, over 972224.68 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 13:44:42,003 INFO [train.py:715] (3/8) Epoch 19, batch 2900, loss[loss=0.1056, simple_loss=0.1789, pruned_loss=0.01612, over 4920.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02839, over 972614.10 frames.], batch size: 23, lr: 1.18e-04
+2022-05-09 13:45:20,761 INFO [train.py:715] (3/8) Epoch 19, batch 2950, loss[loss=0.1072, simple_loss=0.1902, pruned_loss=0.01212, over 4982.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02822, over 972776.75 frames.], batch size: 28, lr: 1.18e-04
+2022-05-09 13:46:00,074 INFO [train.py:715] (3/8) Epoch 19, batch 3000, loss[loss=0.1359, simple_loss=0.2091, pruned_loss=0.03131, over 4986.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02815, over 973708.79 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 13:46:00,075 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 13:46:10,050 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1877, pruned_loss=0.01062, over 914524.00 frames.
+2022-05-09 13:46:50,340 INFO [train.py:715] (3/8) Epoch 19, batch 3050, loss[loss=0.1242, simple_loss=0.2067, pruned_loss=0.02087, over 4930.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02798, over 973239.24 frames.], batch size: 29, lr: 1.18e-04
+2022-05-09 13:47:29,687 INFO [train.py:715] (3/8) Epoch 19, batch 3100, loss[loss=0.1294, simple_loss=0.1946, pruned_loss=0.03208, over 4958.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02837, over 972680.78 frames.], batch size: 35, lr: 1.18e-04
+2022-05-09 13:48:08,831 INFO [train.py:715] (3/8) Epoch 19, batch 3150, loss[loss=0.1416, simple_loss=0.2187, pruned_loss=0.03226, over 4888.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02852, over 973663.38 frames.], batch size: 22, lr: 1.18e-04
+2022-05-09 13:48:48,670 INFO [train.py:715] (3/8) Epoch 19, batch 3200, loss[loss=0.1243, simple_loss=0.1961, pruned_loss=0.02624, over 4962.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02861, over 973575.64 frames.], batch size: 35, lr: 1.18e-04
+2022-05-09 13:49:27,689 INFO [train.py:715] (3/8) Epoch 19, batch 3250, loss[loss=0.1183, simple_loss=0.1947, pruned_loss=0.02092, over 4880.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02933, over 973146.56 frames.], batch size: 22, lr: 1.18e-04
+2022-05-09 13:50:07,131 INFO [train.py:715] (3/8) Epoch 19, batch 3300, loss[loss=0.1283, simple_loss=0.2031, pruned_loss=0.02673, over 4935.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02901, over 972706.12 frames.], batch size: 29, lr: 1.18e-04
+2022-05-09 13:50:46,361 INFO [train.py:715] (3/8) Epoch 19, batch 3350, loss[loss=0.1287, simple_loss=0.1992, pruned_loss=0.02906, over 4843.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02948, over 972782.56 frames.], batch size: 30, lr: 1.18e-04
+2022-05-09 13:51:26,507 INFO [train.py:715] (3/8) Epoch 19, batch 3400, loss[loss=0.1414, simple_loss=0.2102, pruned_loss=0.03629, over 4900.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02893, over 972838.17 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 13:52:05,356 INFO [train.py:715] (3/8) Epoch 19, batch 3450, loss[loss=0.1099, simple_loss=0.1751, pruned_loss=0.02236, over 4699.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02882, over 972297.82 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 13:52:44,614 INFO [train.py:715] (3/8) Epoch 19, batch 3500, loss[loss=0.1144, simple_loss=0.1946, pruned_loss=0.01714, over 4951.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02837, over 972234.18 frames.], batch size: 29, lr: 1.18e-04
+2022-05-09 13:53:23,732 INFO [train.py:715] (3/8) Epoch 19, batch 3550, loss[loss=0.128, simple_loss=0.1966, pruned_loss=0.02971, over 4777.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.0284, over 971772.81 frames.], batch size: 12, lr: 1.18e-04
+2022-05-09 13:54:02,619 INFO [train.py:715] (3/8) Epoch 19, batch 3600, loss[loss=0.1516, simple_loss=0.2228, pruned_loss=0.04018, over 4844.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.0285, over 971662.03 frames.], batch size: 30, lr: 1.18e-04
+2022-05-09 13:54:42,248 INFO [train.py:715] (3/8) Epoch 19, batch 3650, loss[loss=0.1487, simple_loss=0.2332, pruned_loss=0.03213, over 4959.00 frames.], tot_loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.0284, over 971515.15 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 13:55:21,394 INFO [train.py:715] (3/8) Epoch 19, batch 3700, loss[loss=0.144, simple_loss=0.2076, pruned_loss=0.04019, over 4870.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02827, over 972009.65 frames.], batch size: 32, lr: 1.18e-04
+2022-05-09 13:56:01,852 INFO [train.py:715] (3/8) Epoch 19, batch 3750, loss[loss=0.1095, simple_loss=0.1868, pruned_loss=0.01609, over 4979.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02825, over 972048.43 frames.], batch size: 28, lr: 1.18e-04
+2022-05-09 13:56:40,837 INFO [train.py:715] (3/8) Epoch 19, batch 3800, loss[loss=0.1333, simple_loss=0.2105, pruned_loss=0.028, over 4796.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02812, over 972615.91 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 13:57:19,814 INFO [train.py:715] (3/8) Epoch 19, batch 3850, loss[loss=0.1146, simple_loss=0.1964, pruned_loss=0.01635, over 4905.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.028, over 972628.27 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 13:57:59,511 INFO [train.py:715] (3/8) Epoch 19, batch 3900, loss[loss=0.1653, simple_loss=0.2324, pruned_loss=0.04908, over 4775.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02862, over 973054.12 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 13:58:38,560 INFO [train.py:715] (3/8) Epoch 19, batch 3950, loss[loss=0.1359, simple_loss=0.215, pruned_loss=0.0284, over 4696.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02838, over 972184.34 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 13:59:17,193 INFO [train.py:715] (3/8) Epoch 19, batch 4000, loss[loss=0.1268, simple_loss=0.1988, pruned_loss=0.0274, over 4940.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2066, pruned_loss=0.02832, over 972539.28 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 13:59:56,646 INFO [train.py:715] (3/8) Epoch 19, batch 4050, loss[loss=0.128, simple_loss=0.1996, pruned_loss=0.0282, over 4858.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02837, over 972347.60 frames.], batch size: 32, lr: 1.18e-04
+2022-05-09 14:00:36,779 INFO [train.py:715] (3/8) Epoch 19, batch 4100, loss[loss=0.1312, simple_loss=0.2069, pruned_loss=0.02771, over 4745.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2072, pruned_loss=0.02868, over 972337.27 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 14:01:15,966 INFO [train.py:715] (3/8) Epoch 19, batch 4150, loss[loss=0.1444, simple_loss=0.2195, pruned_loss=0.03468, over 4858.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2063, pruned_loss=0.02816, over 971886.38 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 14:01:54,739 INFO [train.py:715] (3/8) Epoch 19, batch 4200, loss[loss=0.1184, simple_loss=0.2119, pruned_loss=0.01252, over 4960.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02814, over 972215.45 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 14:02:34,000 INFO [train.py:715] (3/8) Epoch 19, batch 4250, loss[loss=0.1374, simple_loss=0.2219, pruned_loss=0.02639, over 4964.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2056, pruned_loss=0.02788, over 972869.82 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 14:03:13,061 INFO [train.py:715] (3/8) Epoch 19, batch 4300, loss[loss=0.1151, simple_loss=0.1939, pruned_loss=0.01815, over 4921.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2054, pruned_loss=0.02794, over 972040.21 frames.], batch size: 23, lr: 1.18e-04
+2022-05-09 14:03:52,547 INFO [train.py:715] (3/8) Epoch 19, batch 4350, loss[loss=0.1329, simple_loss=0.1991, pruned_loss=0.03332, over 4837.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02798, over 972211.69 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:04:31,613 INFO [train.py:715] (3/8) Epoch 19, batch 4400, loss[loss=0.1166, simple_loss=0.1897, pruned_loss=0.02173, over 4925.00 frames.], tot_loss[loss=0.1306, simple_loss=0.205, pruned_loss=0.02812, over 972579.04 frames.], batch size: 29, lr: 1.18e-04
+2022-05-09 14:05:11,663 INFO [train.py:715] (3/8) Epoch 19, batch 4450, loss[loss=0.116, simple_loss=0.1927, pruned_loss=0.0196, over 4934.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.02825, over 971597.43 frames.], batch size: 23, lr: 1.18e-04
+2022-05-09 14:05:50,510 INFO [train.py:715] (3/8) Epoch 19, batch 4500, loss[loss=0.121, simple_loss=0.1922, pruned_loss=0.02494, over 4764.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02856, over 970993.42 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 14:06:29,204 INFO [train.py:715] (3/8) Epoch 19, batch 4550, loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03544, over 4940.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02837, over 972071.08 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 14:07:08,891 INFO [train.py:715] (3/8) Epoch 19, batch 4600, loss[loss=0.1348, simple_loss=0.2053, pruned_loss=0.03212, over 4966.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.02869, over 971762.87 frames.], batch size: 35, lr: 1.18e-04
+2022-05-09 14:07:48,136 INFO [train.py:715] (3/8) Epoch 19, batch 4650, loss[loss=0.1305, simple_loss=0.2053, pruned_loss=0.02785, over 4873.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.0288, over 971824.41 frames.], batch size: 32, lr: 1.18e-04
+2022-05-09 14:08:27,121 INFO [train.py:715] (3/8) Epoch 19, batch 4700, loss[loss=0.1433, simple_loss=0.22, pruned_loss=0.03326, over 4700.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02885, over 971448.55 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:09:06,334 INFO [train.py:715] (3/8) Epoch 19, batch 4750, loss[loss=0.1451, simple_loss=0.2147, pruned_loss=0.03774, over 4768.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.0284, over 971575.24 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 14:09:46,296 INFO [train.py:715] (3/8) Epoch 19, batch 4800, loss[loss=0.1304, simple_loss=0.2149, pruned_loss=0.0229, over 4982.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02847, over 972915.12 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 14:10:25,679 INFO [train.py:715] (3/8) Epoch 19, batch 4850, loss[loss=0.1584, simple_loss=0.2323, pruned_loss=0.04228, over 4843.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02875, over 973474.65 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:11:04,336 INFO [train.py:715] (3/8) Epoch 19, batch 4900, loss[loss=0.1253, simple_loss=0.2059, pruned_loss=0.02231, over 4983.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02842, over 973407.36 frames.], batch size: 25, lr: 1.18e-04
+2022-05-09 14:11:44,091 INFO [train.py:715] (3/8) Epoch 19, batch 4950, loss[loss=0.1502, simple_loss=0.2244, pruned_loss=0.038, over 4833.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.0288, over 972869.65 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:12:23,741 INFO [train.py:715] (3/8) Epoch 19, batch 5000, loss[loss=0.1683, simple_loss=0.2259, pruned_loss=0.05531, over 4787.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02916, over 973107.72 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 14:13:02,750 INFO [train.py:715] (3/8) Epoch 19, batch 5050, loss[loss=0.1197, simple_loss=0.1979, pruned_loss=0.02076, over 4753.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02902, over 973062.47 frames.], batch size: 12, lr: 1.18e-04
+2022-05-09 14:13:41,115 INFO [train.py:715] (3/8) Epoch 19, batch 5100, loss[loss=0.1336, simple_loss=0.195, pruned_loss=0.0361, over 4991.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02926, over 973523.44 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 14:14:21,160 INFO [train.py:715] (3/8) Epoch 19, batch 5150, loss[loss=0.1427, simple_loss=0.2125, pruned_loss=0.03645, over 4760.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02906, over 972766.30 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 14:15:00,187 INFO [train.py:715] (3/8) Epoch 19, batch 5200, loss[loss=0.1367, simple_loss=0.2033, pruned_loss=0.03508, over 4797.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.0291, over 972563.33 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 14:15:38,852 INFO [train.py:715] (3/8) Epoch 19, batch 5250, loss[loss=0.1248, simple_loss=0.2074, pruned_loss=0.02107, over 4980.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02877, over 971716.04 frames.], batch size: 28, lr: 1.18e-04
+2022-05-09 14:16:18,534 INFO [train.py:715] (3/8) Epoch 19, batch 5300, loss[loss=0.1631, simple_loss=0.24, pruned_loss=0.04308, over 4915.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02903, over 971953.47 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 14:16:58,482 INFO [train.py:715] (3/8) Epoch 19, batch 5350, loss[loss=0.1204, simple_loss=0.1987, pruned_loss=0.02105, over 4823.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.0285, over 972200.61 frames.], batch size: 25, lr: 1.18e-04
+2022-05-09 14:17:38,564 INFO [train.py:715] (3/8) Epoch 19, batch 5400, loss[loss=0.1232, simple_loss=0.1981, pruned_loss=0.02416, over 4929.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02906, over 972354.16 frames.], batch size: 23, lr: 1.18e-04
+2022-05-09 14:18:17,827 INFO [train.py:715] (3/8) Epoch 19, batch 5450, loss[loss=0.1095, simple_loss=0.189, pruned_loss=0.01496, over 4828.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02907, over 972683.02 frames.], batch size: 26, lr: 1.18e-04
+2022-05-09 14:18:58,016 INFO [train.py:715] (3/8) Epoch 19, batch 5500, loss[loss=0.12, simple_loss=0.1854, pruned_loss=0.02724, over 4760.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.0289, over 973227.37 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 14:19:37,204 INFO [train.py:715] (3/8) Epoch 19, batch 5550, loss[loss=0.0999, simple_loss=0.1691, pruned_loss=0.01534, over 4821.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02907, over 972810.21 frames.], batch size: 13, lr: 1.18e-04
+2022-05-09 14:20:16,793 INFO [train.py:715] (3/8) Epoch 19, batch 5600, loss[loss=0.1287, simple_loss=0.2049, pruned_loss=0.02629, over 4818.00 frames.], tot_loss[loss=0.1314, simple_loss=0.205, pruned_loss=0.02891, over 972378.07 frames.], batch size: 27, lr: 1.18e-04
+2022-05-09 14:20:56,103 INFO [train.py:715] (3/8) Epoch 19, batch 5650, loss[loss=0.1144, simple_loss=0.19, pruned_loss=0.01945, over 4794.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2048, pruned_loss=0.02867, over 971753.08 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 14:21:35,827 INFO [train.py:715] (3/8) Epoch 19, batch 5700, loss[loss=0.1247, simple_loss=0.1956, pruned_loss=0.02694, over 4787.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2053, pruned_loss=0.02877, over 972915.92 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 14:22:15,333 INFO [train.py:715] (3/8) Epoch 19, batch 5750, loss[loss=0.1252, simple_loss=0.205, pruned_loss=0.02269, over 4773.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2051, pruned_loss=0.02897, over 973075.41 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 14:22:53,919 INFO [train.py:715] (3/8) Epoch 19, batch 5800, loss[loss=0.1311, simple_loss=0.2025, pruned_loss=0.02984, over 4874.00 frames.], tot_loss[loss=0.1327, simple_loss=0.206, pruned_loss=0.02965, over 972497.65 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 14:23:33,193 INFO [train.py:715] (3/8) Epoch 19, batch 5850, loss[loss=0.1326, simple_loss=0.2133, pruned_loss=0.0259, over 4821.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2059, pruned_loss=0.0292, over 973049.43 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:24:11,658 INFO [train.py:715] (3/8) Epoch 19, batch 5900, loss[loss=0.1085, simple_loss=0.1792, pruned_loss=0.01893, over 4865.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2052, pruned_loss=0.02899, over 972441.01 frames.], batch size: 32, lr: 1.18e-04
+2022-05-09 14:24:51,080 INFO [train.py:715] (3/8) Epoch 19, batch 5950, loss[loss=0.1398, simple_loss=0.2056, pruned_loss=0.03699, over 4894.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2051, pruned_loss=0.02884, over 971790.70 frames.], batch size: 32, lr: 1.18e-04
+2022-05-09 14:25:30,282 INFO [train.py:715] (3/8) Epoch 19, batch 6000, loss[loss=0.1375, simple_loss=0.2101, pruned_loss=0.03244, over 4867.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02872, over 972326.48 frames.], batch size: 32, lr: 1.18e-04
+2022-05-09 14:25:30,282 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 14:25:40,195 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01067, over 914524.00 frames.
+2022-05-09 14:26:19,488 INFO [train.py:715] (3/8) Epoch 19, batch 6050, loss[loss=0.1391, simple_loss=0.2195, pruned_loss=0.02934, over 4973.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02864, over 972395.48 frames.], batch size: 25, lr: 1.18e-04
+2022-05-09 14:26:58,346 INFO [train.py:715] (3/8) Epoch 19, batch 6100, loss[loss=0.1101, simple_loss=0.1851, pruned_loss=0.0175, over 4833.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02855, over 972210.21 frames.], batch size: 13, lr: 1.18e-04
+2022-05-09 14:27:37,412 INFO [train.py:715] (3/8) Epoch 19, batch 6150, loss[loss=0.1151, simple_loss=0.1915, pruned_loss=0.01935, over 4926.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02869, over 972571.70 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 14:28:15,610 INFO [train.py:715] (3/8) Epoch 19, batch 6200, loss[loss=0.1371, simple_loss=0.2184, pruned_loss=0.02791, over 4814.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02903, over 972817.10 frames.], batch size: 27, lr: 1.18e-04
+2022-05-09 14:28:55,855 INFO [train.py:715] (3/8) Epoch 19, batch 6250, loss[loss=0.1198, simple_loss=0.1998, pruned_loss=0.01986, over 4799.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.0284, over 972230.79 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 14:29:35,038 INFO [train.py:715] (3/8) Epoch 19, batch 6300, loss[loss=0.1275, simple_loss=0.2005, pruned_loss=0.0273, over 4794.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02824, over 971980.10 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 14:30:14,721 INFO [train.py:715] (3/8) Epoch 19, batch 6350, loss[loss=0.1138, simple_loss=0.1798, pruned_loss=0.02396, over 4772.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02827, over 972626.94 frames.], batch size: 12, lr: 1.18e-04
+2022-05-09 14:30:54,199 INFO [train.py:715] (3/8) Epoch 19, batch 6400, loss[loss=0.126, simple_loss=0.2052, pruned_loss=0.02337, over 4746.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2047, pruned_loss=0.02803, over 972865.52 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 14:31:33,476 INFO [train.py:715] (3/8) Epoch 19, batch 6450, loss[loss=0.1299, simple_loss=0.2076, pruned_loss=0.02615, over 4759.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02832, over 972090.50 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 14:32:12,982 INFO [train.py:715] (3/8) Epoch 19, batch 6500, loss[loss=0.1142, simple_loss=0.1892, pruned_loss=0.0196, over 4802.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02828, over 973206.80 frames.], batch size: 25, lr: 1.18e-04
+2022-05-09 14:32:51,556 INFO [train.py:715] (3/8) Epoch 19, batch 6550, loss[loss=0.119, simple_loss=0.1921, pruned_loss=0.02302, over 4702.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02817, over 973350.38 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:33:31,043 INFO [train.py:715] (3/8) Epoch 19, batch 6600, loss[loss=0.1211, simple_loss=0.2007, pruned_loss=0.02071, over 4931.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02829, over 973192.39 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 14:34:10,193 INFO [train.py:715] (3/8) Epoch 19, batch 6650, loss[loss=0.1202, simple_loss=0.1896, pruned_loss=0.02535, over 4819.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.02875, over 973273.37 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:34:48,935 INFO [train.py:715] (3/8) Epoch 19, batch 6700, loss[loss=0.1341, simple_loss=0.203, pruned_loss=0.03262, over 4830.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02868, over 973081.34 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:35:28,067 INFO [train.py:715] (3/8) Epoch 19, batch 6750, loss[loss=0.1335, simple_loss=0.2061, pruned_loss=0.03049, over 4786.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02844, over 972640.30 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 14:36:07,536 INFO [train.py:715] (3/8) Epoch 19, batch 6800, loss[loss=0.1115, simple_loss=0.1779, pruned_loss=0.02253, over 4848.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.0289, over 972213.26 frames.], batch size: 13, lr: 1.18e-04
+2022-05-09 14:36:46,928 INFO [train.py:715] (3/8) Epoch 19, batch 6850, loss[loss=0.1467, simple_loss=0.2207, pruned_loss=0.03633, over 4818.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2082, pruned_loss=0.02903, over 971774.23 frames.], batch size: 27, lr: 1.18e-04
+2022-05-09 14:37:25,088 INFO [train.py:715] (3/8) Epoch 19, batch 6900, loss[loss=0.105, simple_loss=0.1807, pruned_loss=0.01466, over 4965.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02872, over 972124.23 frames.], batch size: 28, lr: 1.18e-04
+2022-05-09 14:38:04,132 INFO [train.py:715] (3/8) Epoch 19, batch 6950, loss[loss=0.1382, simple_loss=0.2242, pruned_loss=0.0261, over 4837.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02843, over 972335.40 frames.], batch size: 30, lr: 1.18e-04
+2022-05-09 14:38:43,599 INFO [train.py:715] (3/8) Epoch 19, batch 7000, loss[loss=0.115, simple_loss=0.186, pruned_loss=0.02199, over 4977.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02894, over 972072.63 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 14:39:22,852 INFO [train.py:715] (3/8) Epoch 19, batch 7050, loss[loss=0.1217, simple_loss=0.1957, pruned_loss=0.02386, over 4804.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02853, over 972743.02 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 14:40:02,434 INFO [train.py:715] (3/8) Epoch 19, batch 7100, loss[loss=0.1497, simple_loss=0.2104, pruned_loss=0.04455, over 4831.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02868, over 972676.22 frames.], batch size: 30, lr: 1.18e-04
+2022-05-09 14:40:42,073 INFO [train.py:715] (3/8) Epoch 19, batch 7150, loss[loss=0.1267, simple_loss=0.2052, pruned_loss=0.02408, over 4839.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02823, over 972841.35 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:41:20,980 INFO [train.py:715] (3/8) Epoch 19, batch 7200, loss[loss=0.1465, simple_loss=0.2222, pruned_loss=0.03544, over 4955.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02857, over 973135.73 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 14:41:59,732 INFO [train.py:715] (3/8) Epoch 19, batch 7250, loss[loss=0.1409, simple_loss=0.217, pruned_loss=0.03237, over 4978.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02829, over 972805.05 frames.], batch size: 39, lr: 1.18e-04
+2022-05-09 14:42:39,095 INFO [train.py:715] (3/8) Epoch 19, batch 7300, loss[loss=0.1088, simple_loss=0.183, pruned_loss=0.01726, over 4826.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02834, over 973122.60 frames.], batch size: 26, lr: 1.18e-04
+2022-05-09 14:43:18,258 INFO [train.py:715] (3/8) Epoch 19, batch 7350, loss[loss=0.1434, simple_loss=0.2252, pruned_loss=0.03086, over 4807.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02886, over 972934.27 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 14:43:57,162 INFO [train.py:715] (3/8) Epoch 19, batch 7400, loss[loss=0.1358, simple_loss=0.2037, pruned_loss=0.034, over 4843.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02887, over 973036.46 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:44:37,623 INFO [train.py:715] (3/8) Epoch 19, batch 7450, loss[loss=0.1352, simple_loss=0.2168, pruned_loss=0.02677, over 4936.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02899, over 973739.50 frames.], batch size: 23, lr: 1.18e-04
+2022-05-09 14:45:17,478 INFO [train.py:715] (3/8) Epoch 19, batch 7500, loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.03073, over 4982.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.0289, over 974166.74 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 14:45:56,701 INFO [train.py:715] (3/8) Epoch 19, batch 7550, loss[loss=0.1552, simple_loss=0.227, pruned_loss=0.04169, over 4907.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02899, over 973242.91 frames.], batch size: 39, lr: 1.18e-04
+2022-05-09 14:46:36,053 INFO [train.py:715] (3/8) Epoch 19, batch 7600, loss[loss=0.1248, simple_loss=0.2057, pruned_loss=0.022, over 4752.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.029, over 972730.79 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 14:47:16,834 INFO [train.py:715] (3/8) Epoch 19, batch 7650, loss[loss=0.1454, simple_loss=0.2178, pruned_loss=0.03649, over 4835.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02895, over 972371.82 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:47:56,151 INFO [train.py:715] (3/8) Epoch 19, batch 7700, loss[loss=0.1143, simple_loss=0.1885, pruned_loss=0.02002, over 4787.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02936, over 972272.40 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 14:48:34,961 INFO [train.py:715] (3/8) Epoch 19, batch 7750, loss[loss=0.143, simple_loss=0.2223, pruned_loss=0.03188, over 4820.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02931, over 971972.30 frames.], batch size: 25, lr: 1.18e-04
+2022-05-09 14:49:14,658 INFO [train.py:715] (3/8) Epoch 19, batch 7800, loss[loss=0.1092, simple_loss=0.1823, pruned_loss=0.01804, over 4789.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02925, over 973062.18 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 14:49:54,091 INFO [train.py:715] (3/8) Epoch 19, batch 7850, loss[loss=0.13, simple_loss=0.2086, pruned_loss=0.02576, over 4898.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02952, over 972656.20 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 14:50:33,359 INFO [train.py:715] (3/8) Epoch 19, batch 7900, loss[loss=0.1219, simple_loss=0.1933, pruned_loss=0.0253, over 4903.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02939, over 971861.08 frames.], batch size: 19, lr: 1.18e-04
+2022-05-09 14:51:11,761 INFO [train.py:715] (3/8) Epoch 19, batch 7950, loss[loss=0.1316, simple_loss=0.2048, pruned_loss=0.02925, over 4974.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02997, over 971938.02 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 14:51:51,087 INFO [train.py:715] (3/8) Epoch 19, batch 8000, loss[loss=0.1377, simple_loss=0.2004, pruned_loss=0.03754, over 4928.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.03, over 971779.66 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 14:52:30,290 INFO [train.py:715] (3/8) Epoch 19, batch 8050, loss[loss=0.1225, simple_loss=0.2025, pruned_loss=0.02119, over 4940.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02978, over 972414.02 frames.], batch size: 23, lr: 1.18e-04
+2022-05-09 14:53:08,820 INFO [train.py:715] (3/8) Epoch 19, batch 8100, loss[loss=0.1096, simple_loss=0.1875, pruned_loss=0.01591, over 4977.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2068, pruned_loss=0.02969, over 972617.00 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 14:53:48,275 INFO [train.py:715] (3/8) Epoch 19, batch 8150, loss[loss=0.1158, simple_loss=0.1997, pruned_loss=0.01593, over 4897.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02948, over 972060.97 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 14:54:27,922 INFO [train.py:715] (3/8) Epoch 19, batch 8200, loss[loss=0.1257, simple_loss=0.2073, pruned_loss=0.02207, over 4992.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02897, over 971610.21 frames.], batch size: 20, lr: 1.18e-04
+2022-05-09 14:55:06,907 INFO [train.py:715] (3/8) Epoch 19, batch 8250, loss[loss=0.1075, simple_loss=0.1749, pruned_loss=0.02005, over 4928.00 frames.], tot_loss[loss=0.131, simple_loss=0.2051, pruned_loss=0.02845, over 971597.10 frames.], batch size: 23, lr: 1.18e-04
+2022-05-09 14:55:45,535 INFO [train.py:715] (3/8) Epoch 19, batch 8300, loss[loss=0.1533, simple_loss=0.2398, pruned_loss=0.03337, over 4930.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2048, pruned_loss=0.02819, over 971917.83 frames.], batch size: 29, lr: 1.18e-04
+2022-05-09 14:56:25,223 INFO [train.py:715] (3/8) Epoch 19, batch 8350, loss[loss=0.1316, simple_loss=0.201, pruned_loss=0.03115, over 4990.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2042, pruned_loss=0.0278, over 972051.46 frames.], batch size: 27, lr: 1.18e-04
+2022-05-09 14:57:04,446 INFO [train.py:715] (3/8) Epoch 19, batch 8400, loss[loss=0.1341, simple_loss=0.2025, pruned_loss=0.03286, over 4842.00 frames.], tot_loss[loss=0.1298, simple_loss=0.204, pruned_loss=0.02783, over 972499.52 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 14:57:43,452 INFO [train.py:715] (3/8) Epoch 19, batch 8450, loss[loss=0.1161, simple_loss=0.1912, pruned_loss=0.02051, over 4926.00 frames.], tot_loss[loss=0.1296, simple_loss=0.204, pruned_loss=0.0276, over 972883.92 frames.], batch size: 29, lr: 1.18e-04
+2022-05-09 14:58:23,230 INFO [train.py:715] (3/8) Epoch 19, batch 8500, loss[loss=0.1459, simple_loss=0.2299, pruned_loss=0.03101, over 4802.00 frames.], tot_loss[loss=0.1294, simple_loss=0.2039, pruned_loss=0.02744, over 972766.28 frames.], batch size: 25, lr: 1.18e-04
+2022-05-09 14:59:01,924 INFO [train.py:715] (3/8) Epoch 19, batch 8550, loss[loss=0.1095, simple_loss=0.1829, pruned_loss=0.01804, over 4883.00 frames.], tot_loss[loss=0.13, simple_loss=0.2046, pruned_loss=0.02773, over 973236.20 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 14:59:41,019 INFO [train.py:715] (3/8) Epoch 19, batch 8600, loss[loss=0.1476, simple_loss=0.2113, pruned_loss=0.04198, over 4830.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.0282, over 972845.90 frames.], batch size: 15, lr: 1.18e-04
+2022-05-09 15:00:20,522 INFO [train.py:715] (3/8) Epoch 19, batch 8650, loss[loss=0.1212, simple_loss=0.2038, pruned_loss=0.01929, over 4861.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02842, over 973271.38 frames.], batch size: 39, lr: 1.18e-04
+2022-05-09 15:01:00,041 INFO [train.py:715] (3/8) Epoch 19, batch 8700, loss[loss=0.1457, simple_loss=0.2222, pruned_loss=0.03454, over 4963.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02814, over 973061.32 frames.], batch size: 24, lr: 1.18e-04
+2022-05-09 15:01:39,201 INFO [train.py:715] (3/8) Epoch 19, batch 8750, loss[loss=0.1652, simple_loss=0.2372, pruned_loss=0.04658, over 4965.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02859, over 972698.56 frames.], batch size: 35, lr: 1.18e-04
+2022-05-09 15:02:17,954 INFO [train.py:715] (3/8) Epoch 19, batch 8800, loss[loss=0.1312, simple_loss=0.1939, pruned_loss=0.03426, over 4975.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02876, over 973659.06 frames.], batch size: 35, lr: 1.18e-04
+2022-05-09 15:02:57,606 INFO [train.py:715] (3/8) Epoch 19, batch 8850, loss[loss=0.1479, simple_loss=0.2158, pruned_loss=0.03997, over 4935.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02914, over 973353.25 frames.], batch size: 23, lr: 1.18e-04
+2022-05-09 15:03:36,662 INFO [train.py:715] (3/8) Epoch 19, batch 8900, loss[loss=0.1241, simple_loss=0.1969, pruned_loss=0.02561, over 4807.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02907, over 972342.50 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 15:04:16,006 INFO [train.py:715] (3/8) Epoch 19, batch 8950, loss[loss=0.1075, simple_loss=0.178, pruned_loss=0.01847, over 4859.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02892, over 971348.84 frames.], batch size: 13, lr: 1.18e-04
+2022-05-09 15:04:54,902 INFO [train.py:715] (3/8) Epoch 19, batch 9000, loss[loss=0.13, simple_loss=0.2051, pruned_loss=0.0275, over 4913.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02876, over 971554.15 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 15:04:54,902 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 15:05:04,818 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1047, simple_loss=0.1879, pruned_loss=0.01072, over 914524.00 frames.
+2022-05-09 15:05:44,267 INFO [train.py:715] (3/8) Epoch 19, batch 9050, loss[loss=0.122, simple_loss=0.1934, pruned_loss=0.02524, over 4870.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.0294, over 972117.55 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 15:06:23,988 INFO [train.py:715] (3/8) Epoch 19, batch 9100, loss[loss=0.1182, simple_loss=0.1931, pruned_loss=0.02161, over 4806.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02912, over 972679.51 frames.], batch size: 26, lr: 1.18e-04
+2022-05-09 15:07:03,252 INFO [train.py:715] (3/8) Epoch 19, batch 9150, loss[loss=0.1488, simple_loss=0.2206, pruned_loss=0.03845, over 4820.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.0288, over 971727.89 frames.], batch size: 26, lr: 1.18e-04
+2022-05-09 15:07:42,032 INFO [train.py:715] (3/8) Epoch 19, batch 9200, loss[loss=0.1409, simple_loss=0.2058, pruned_loss=0.03799, over 4916.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02835, over 971530.75 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 15:08:21,756 INFO [train.py:715] (3/8) Epoch 19, batch 9250, loss[loss=0.1217, simple_loss=0.1928, pruned_loss=0.02527, over 4837.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02846, over 972134.36 frames.], batch size: 30, lr: 1.18e-04
+2022-05-09 15:09:00,950 INFO [train.py:715] (3/8) Epoch 19, batch 9300, loss[loss=0.1249, simple_loss=0.1951, pruned_loss=0.02734, over 4851.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02832, over 972180.39 frames.], batch size: 32, lr: 1.18e-04
+2022-05-09 15:09:39,864 INFO [train.py:715] (3/8) Epoch 19, batch 9350, loss[loss=0.151, simple_loss=0.2205, pruned_loss=0.0408, over 4899.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02859, over 972622.95 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 15:10:19,955 INFO [train.py:715] (3/8) Epoch 19, batch 9400, loss[loss=0.1468, simple_loss=0.2303, pruned_loss=0.03166, over 4818.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02849, over 972746.05 frames.], batch size: 27, lr: 1.18e-04
+2022-05-09 15:11:00,060 INFO [train.py:715] (3/8) Epoch 19, batch 9450, loss[loss=0.1147, simple_loss=0.1773, pruned_loss=0.02611, over 4975.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02855, over 973535.37 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 15:11:38,884 INFO [train.py:715] (3/8) Epoch 19, batch 9500, loss[loss=0.1222, simple_loss=0.1968, pruned_loss=0.0238, over 4980.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.0286, over 973595.57 frames.], batch size: 28, lr: 1.18e-04
+2022-05-09 15:12:18,094 INFO [train.py:715] (3/8) Epoch 19, batch 9550, loss[loss=0.1329, simple_loss=0.2198, pruned_loss=0.02297, over 4879.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.0284, over 973870.88 frames.], batch size: 16, lr: 1.18e-04
+2022-05-09 15:12:57,474 INFO [train.py:715] (3/8) Epoch 19, batch 9600, loss[loss=0.1586, simple_loss=0.226, pruned_loss=0.04561, over 4970.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.0282, over 973706.82 frames.], batch size: 21, lr: 1.18e-04
+2022-05-09 15:13:36,649 INFO [train.py:715] (3/8) Epoch 19, batch 9650, loss[loss=0.1093, simple_loss=0.1865, pruned_loss=0.0161, over 4791.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2048, pruned_loss=0.02783, over 973449.44 frames.], batch size: 12, lr: 1.18e-04
+2022-05-09 15:14:14,975 INFO [train.py:715] (3/8) Epoch 19, batch 9700, loss[loss=0.1487, simple_loss=0.2304, pruned_loss=0.03347, over 4913.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02806, over 972970.93 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 15:14:54,704 INFO [train.py:715] (3/8) Epoch 19, batch 9750, loss[loss=0.1183, simple_loss=0.1948, pruned_loss=0.02094, over 4850.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2053, pruned_loss=0.02794, over 973202.12 frames.], batch size: 20, lr: 1.18e-04
+2022-05-09 15:15:34,783 INFO [train.py:715] (3/8) Epoch 19, batch 9800, loss[loss=0.09821, simple_loss=0.1701, pruned_loss=0.01318, over 4746.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.02809, over 973218.76 frames.], batch size: 12, lr: 1.18e-04
+2022-05-09 15:16:14,505 INFO [train.py:715] (3/8) Epoch 19, batch 9850, loss[loss=0.1597, simple_loss=0.2316, pruned_loss=0.04389, over 4813.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02818, over 973163.96 frames.], batch size: 25, lr: 1.18e-04
+2022-05-09 15:16:53,381 INFO [train.py:715] (3/8) Epoch 19, batch 9900, loss[loss=0.1176, simple_loss=0.191, pruned_loss=0.02208, over 4953.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02859, over 973204.34 frames.], batch size: 14, lr: 1.18e-04
+2022-05-09 15:17:33,334 INFO [train.py:715] (3/8) Epoch 19, batch 9950, loss[loss=0.1246, simple_loss=0.1993, pruned_loss=0.02492, over 4888.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02885, over 972805.68 frames.], batch size: 17, lr: 1.18e-04
+2022-05-09 15:18:12,861 INFO [train.py:715] (3/8) Epoch 19, batch 10000, loss[loss=0.1094, simple_loss=0.1878, pruned_loss=0.0155, over 4781.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02839, over 972844.91 frames.], batch size: 18, lr: 1.18e-04
+2022-05-09 15:18:51,542 INFO [train.py:715] (3/8) Epoch 19, batch 10050, loss[loss=0.1401, simple_loss=0.2198, pruned_loss=0.03023, over 4959.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02881, over 973077.39 frames.], batch size: 35, lr: 1.18e-04
+2022-05-09 15:19:31,277 INFO [train.py:715] (3/8) Epoch 19, batch 10100, loss[loss=0.1218, simple_loss=0.1917, pruned_loss=0.02592, over 4680.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02871, over 972038.50 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 15:20:10,774 INFO [train.py:715] (3/8) Epoch 19, batch 10150, loss[loss=0.1382, simple_loss=0.2027, pruned_loss=0.03684, over 4981.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02874, over 972684.53 frames.], batch size: 28, lr: 1.17e-04
+2022-05-09 15:20:49,758 INFO [train.py:715] (3/8) Epoch 19, batch 10200, loss[loss=0.153, simple_loss=0.2339, pruned_loss=0.03611, over 4797.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.0287, over 971914.44 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 15:21:29,137 INFO [train.py:715] (3/8) Epoch 19, batch 10250, loss[loss=0.1308, simple_loss=0.2022, pruned_loss=0.0297, over 4791.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.0285, over 972644.15 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 15:22:09,268 INFO [train.py:715] (3/8) Epoch 19, batch 10300, loss[loss=0.115, simple_loss=0.1966, pruned_loss=0.0167, over 4788.00 frames.], tot_loss[loss=0.131, simple_loss=0.206, pruned_loss=0.02799, over 972850.32 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 15:22:48,849 INFO [train.py:715] (3/8) Epoch 19, batch 10350, loss[loss=0.1129, simple_loss=0.1891, pruned_loss=0.01839, over 4938.00 frames.], tot_loss[loss=0.132, simple_loss=0.207, pruned_loss=0.02847, over 972507.13 frames.], batch size: 35, lr: 1.17e-04
+2022-05-09 15:23:27,533 INFO [train.py:715] (3/8) Epoch 19, batch 10400, loss[loss=0.1185, simple_loss=0.1966, pruned_loss=0.02016, over 4804.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2069, pruned_loss=0.02809, over 972205.43 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 15:24:07,291 INFO [train.py:715] (3/8) Epoch 19, batch 10450, loss[loss=0.1215, simple_loss=0.1861, pruned_loss=0.02842, over 4867.00 frames.], tot_loss[loss=0.1318, simple_loss=0.207, pruned_loss=0.02837, over 971708.00 frames.], batch size: 22, lr: 1.17e-04
+2022-05-09 15:24:47,015 INFO [train.py:715] (3/8) Epoch 19, batch 10500, loss[loss=0.1263, simple_loss=0.2055, pruned_loss=0.02357, over 4966.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2075, pruned_loss=0.02883, over 971356.45 frames.], batch size: 28, lr: 1.17e-04
+2022-05-09 15:25:25,926 INFO [train.py:715] (3/8) Epoch 19, batch 10550, loss[loss=0.1569, simple_loss=0.2369, pruned_loss=0.03843, over 4976.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2069, pruned_loss=0.02851, over 971528.90 frames.], batch size: 31, lr: 1.17e-04
+2022-05-09 15:26:04,898 INFO [train.py:715] (3/8) Epoch 19, batch 10600, loss[loss=0.1179, simple_loss=0.1947, pruned_loss=0.0205, over 4936.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02853, over 972339.41 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 15:26:47,171 INFO [train.py:715] (3/8) Epoch 19, batch 10650, loss[loss=0.1441, simple_loss=0.2088, pruned_loss=0.03971, over 4854.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.0282, over 972231.85 frames.], batch size: 30, lr: 1.17e-04
+2022-05-09 15:27:26,345 INFO [train.py:715] (3/8) Epoch 19, batch 10700, loss[loss=0.1139, simple_loss=0.199, pruned_loss=0.0144, over 4916.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02839, over 972557.96 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 15:28:05,704 INFO [train.py:715] (3/8) Epoch 19, batch 10750, loss[loss=0.1286, simple_loss=0.2089, pruned_loss=0.02413, over 4796.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.02821, over 973334.91 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 15:28:45,281 INFO [train.py:715] (3/8) Epoch 19, batch 10800, loss[loss=0.1345, simple_loss=0.2157, pruned_loss=0.02662, over 4785.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2053, pruned_loss=0.02793, over 972743.04 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 15:29:25,029 INFO [train.py:715] (3/8) Epoch 19, batch 10850, loss[loss=0.1601, simple_loss=0.2361, pruned_loss=0.04209, over 4879.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02805, over 972843.99 frames.], batch size: 22, lr: 1.17e-04
+2022-05-09 15:30:03,632 INFO [train.py:715] (3/8) Epoch 19, batch 10900, loss[loss=0.1326, simple_loss=0.204, pruned_loss=0.03057, over 4778.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02805, over 973200.52 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 15:30:42,650 INFO [train.py:715] (3/8) Epoch 19, batch 10950, loss[loss=0.1261, simple_loss=0.2013, pruned_loss=0.02547, over 4897.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2052, pruned_loss=0.02747, over 973287.15 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 15:31:22,352 INFO [train.py:715] (3/8) Epoch 19, batch 11000, loss[loss=0.1244, simple_loss=0.2062, pruned_loss=0.0213, over 4917.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2059, pruned_loss=0.02751, over 973278.13 frames.], batch size: 29, lr: 1.17e-04
+2022-05-09 15:32:02,209 INFO [train.py:715] (3/8) Epoch 19, batch 11050, loss[loss=0.1493, simple_loss=0.2304, pruned_loss=0.03405, over 4807.00 frames.], tot_loss[loss=0.1299, simple_loss=0.205, pruned_loss=0.02737, over 972462.29 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 15:32:40,677 INFO [train.py:715] (3/8) Epoch 19, batch 11100, loss[loss=0.1434, simple_loss=0.2244, pruned_loss=0.03119, over 4972.00 frames.], tot_loss[loss=0.1305, simple_loss=0.205, pruned_loss=0.02801, over 971739.18 frames.], batch size: 28, lr: 1.17e-04
+2022-05-09 15:33:20,041 INFO [train.py:715] (3/8) Epoch 19, batch 11150, loss[loss=0.159, simple_loss=0.2318, pruned_loss=0.04313, over 4813.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2062, pruned_loss=0.02815, over 971152.06 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 15:33:59,453 INFO [train.py:715] (3/8) Epoch 19, batch 11200, loss[loss=0.1167, simple_loss=0.2018, pruned_loss=0.01577, over 4792.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2061, pruned_loss=0.02777, over 970551.07 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 15:34:38,834 INFO [train.py:715] (3/8) Epoch 19, batch 11250, loss[loss=0.1157, simple_loss=0.1954, pruned_loss=0.01802, over 4826.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2064, pruned_loss=0.02772, over 971531.82 frames.], batch size: 26, lr: 1.17e-04
+2022-05-09 15:35:18,204 INFO [train.py:715] (3/8) Epoch 19, batch 11300, loss[loss=0.1208, simple_loss=0.191, pruned_loss=0.02531, over 4770.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2058, pruned_loss=0.02746, over 971698.24 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 15:35:56,987 INFO [train.py:715] (3/8) Epoch 19, batch 11350, loss[loss=0.1329, simple_loss=0.2167, pruned_loss=0.02452, over 4817.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2062, pruned_loss=0.02804, over 972058.10 frames.], batch size: 27, lr: 1.17e-04
+2022-05-09 15:36:36,601 INFO [train.py:715] (3/8) Epoch 19, batch 11400, loss[loss=0.1369, simple_loss=0.2057, pruned_loss=0.03404, over 4798.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02807, over 971652.76 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 15:37:16,207 INFO [train.py:715] (3/8) Epoch 19, batch 11450, loss[loss=0.1343, simple_loss=0.2022, pruned_loss=0.03322, over 4972.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02786, over 971425.56 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 15:37:56,154 INFO [train.py:715] (3/8) Epoch 19, batch 11500, loss[loss=0.1013, simple_loss=0.1749, pruned_loss=0.01392, over 4725.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2044, pruned_loss=0.02792, over 971425.81 frames.], batch size: 12, lr: 1.17e-04
+2022-05-09 15:38:35,580 INFO [train.py:715] (3/8) Epoch 19, batch 11550, loss[loss=0.1073, simple_loss=0.1831, pruned_loss=0.01579, over 4813.00 frames.], tot_loss[loss=0.1294, simple_loss=0.2037, pruned_loss=0.0275, over 972612.01 frames.], batch size: 25, lr: 1.17e-04
+2022-05-09 15:39:14,556 INFO [train.py:715] (3/8) Epoch 19, batch 11600, loss[loss=0.1115, simple_loss=0.1771, pruned_loss=0.02293, over 4963.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2046, pruned_loss=0.02803, over 972085.89 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 15:39:54,374 INFO [train.py:715] (3/8) Epoch 19, batch 11650, loss[loss=0.1218, simple_loss=0.1947, pruned_loss=0.02446, over 4915.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2044, pruned_loss=0.02801, over 971562.37 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 15:40:33,464 INFO [train.py:715] (3/8) Epoch 19, batch 11700, loss[loss=0.1268, simple_loss=0.2066, pruned_loss=0.02345, over 4801.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2052, pruned_loss=0.02872, over 971267.30 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 15:41:13,004 INFO [train.py:715] (3/8) Epoch 19, batch 11750, loss[loss=0.1603, simple_loss=0.2394, pruned_loss=0.04058, over 4910.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.0286, over 970940.69 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 15:41:52,543 INFO [train.py:715] (3/8) Epoch 19, batch 11800, loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03235, over 4810.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02861, over 972694.77 frames.], batch size: 25, lr: 1.17e-04
+2022-05-09 15:42:32,203 INFO [train.py:715] (3/8) Epoch 19, batch 11850, loss[loss=0.1324, simple_loss=0.2124, pruned_loss=0.02615, over 4848.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02852, over 973153.80 frames.], batch size: 20, lr: 1.17e-04
+2022-05-09 15:43:11,792 INFO [train.py:715] (3/8) Epoch 19, batch 11900, loss[loss=0.1314, simple_loss=0.2168, pruned_loss=0.02297, over 4750.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02841, over 972927.70 frames.], batch size: 16, lr: 1.17e-04
+2022-05-09 15:43:51,289 INFO [train.py:715] (3/8) Epoch 19, batch 11950, loss[loss=0.1359, simple_loss=0.2163, pruned_loss=0.02775, over 4774.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.0286, over 971726.38 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 15:44:30,454 INFO [train.py:715] (3/8) Epoch 19, batch 12000, loss[loss=0.1455, simple_loss=0.2288, pruned_loss=0.03109, over 4811.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02835, over 972057.08 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 15:44:30,455 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 15:44:40,310 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1044, simple_loss=0.1877, pruned_loss=0.01054, over 914524.00 frames.
+2022-05-09 15:45:20,291 INFO [train.py:715] (3/8) Epoch 19, batch 12050, loss[loss=0.1339, simple_loss=0.213, pruned_loss=0.02739, over 4811.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02816, over 972153.94 frames.], batch size: 26, lr: 1.17e-04
+2022-05-09 15:46:00,177 INFO [train.py:715] (3/8) Epoch 19, batch 12100, loss[loss=0.139, simple_loss=0.2087, pruned_loss=0.03464, over 4842.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02833, over 972185.37 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 15:46:39,302 INFO [train.py:715] (3/8) Epoch 19, batch 12150, loss[loss=0.1208, simple_loss=0.1759, pruned_loss=0.03288, over 4870.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02906, over 972476.36 frames.], batch size: 13, lr: 1.17e-04
+2022-05-09 15:47:18,768 INFO [train.py:715] (3/8) Epoch 19, batch 12200, loss[loss=0.117, simple_loss=0.1974, pruned_loss=0.01828, over 4896.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02922, over 973616.97 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 15:47:58,231 INFO [train.py:715] (3/8) Epoch 19, batch 12250, loss[loss=0.1262, simple_loss=0.199, pruned_loss=0.02668, over 4958.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02864, over 973637.89 frames.], batch size: 35, lr: 1.17e-04
+2022-05-09 15:48:37,869 INFO [train.py:715] (3/8) Epoch 19, batch 12300, loss[loss=0.1446, simple_loss=0.2205, pruned_loss=0.03431, over 4980.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02882, over 973733.14 frames.], batch size: 31, lr: 1.17e-04
+2022-05-09 15:49:17,548 INFO [train.py:715] (3/8) Epoch 19, batch 12350, loss[loss=0.1237, simple_loss=0.2117, pruned_loss=0.01788, over 4746.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02881, over 973016.26 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 15:49:56,106 INFO [train.py:715] (3/8) Epoch 19, batch 12400, loss[loss=0.1299, simple_loss=0.2067, pruned_loss=0.02661, over 4979.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.0285, over 972261.14 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 15:50:35,578 INFO [train.py:715] (3/8) Epoch 19, batch 12450, loss[loss=0.1322, simple_loss=0.2049, pruned_loss=0.02976, over 4969.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02863, over 972140.30 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 15:51:14,299 INFO [train.py:715] (3/8) Epoch 19, batch 12500, loss[loss=0.1088, simple_loss=0.1814, pruned_loss=0.01809, over 4890.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02902, over 971720.02 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 15:51:53,639 INFO [train.py:715] (3/8) Epoch 19, batch 12550, loss[loss=0.1392, simple_loss=0.2219, pruned_loss=0.02822, over 4883.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02859, over 971862.15 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 15:52:33,121 INFO [train.py:715] (3/8) Epoch 19, batch 12600, loss[loss=0.1397, simple_loss=0.2233, pruned_loss=0.0281, over 4797.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02847, over 971999.62 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 15:53:12,607 INFO [train.py:715] (3/8) Epoch 19, batch 12650, loss[loss=0.1171, simple_loss=0.203, pruned_loss=0.01555, over 4986.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.0282, over 972399.10 frames.], batch size: 28, lr: 1.17e-04
+2022-05-09 15:53:51,566 INFO [train.py:715] (3/8) Epoch 19, batch 12700, loss[loss=0.1235, simple_loss=0.1933, pruned_loss=0.02683, over 4992.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02865, over 972337.52 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 15:54:30,744 INFO [train.py:715] (3/8) Epoch 19, batch 12750, loss[loss=0.1216, simple_loss=0.1905, pruned_loss=0.02632, over 4957.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02853, over 972665.10 frames.], batch size: 35, lr: 1.17e-04
+2022-05-09 15:55:10,389 INFO [train.py:715] (3/8) Epoch 19, batch 12800, loss[loss=0.1218, simple_loss=0.1949, pruned_loss=0.02431, over 4886.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02826, over 972733.94 frames.], batch size: 32, lr: 1.17e-04
+2022-05-09 15:55:49,790 INFO [train.py:715] (3/8) Epoch 19, batch 12850, loss[loss=0.1202, simple_loss=0.1922, pruned_loss=0.02403, over 4856.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02804, over 971869.01 frames.], batch size: 20, lr: 1.17e-04
+2022-05-09 15:56:28,727 INFO [train.py:715] (3/8) Epoch 19, batch 12900, loss[loss=0.1044, simple_loss=0.1709, pruned_loss=0.0189, over 4895.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02807, over 972299.73 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 15:57:08,292 INFO [train.py:715] (3/8) Epoch 19, batch 12950, loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03008, over 4854.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02825, over 972662.62 frames.], batch size: 20, lr: 1.17e-04
+2022-05-09 15:57:47,532 INFO [train.py:715] (3/8) Epoch 19, batch 13000, loss[loss=0.16, simple_loss=0.2258, pruned_loss=0.04708, over 4941.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2054, pruned_loss=0.02794, over 973593.11 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 15:58:26,680 INFO [train.py:715] (3/8) Epoch 19, batch 13050, loss[loss=0.1203, simple_loss=0.2002, pruned_loss=0.02019, over 4781.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02857, over 973187.97 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 15:59:05,570 INFO [train.py:715] (3/8) Epoch 19, batch 13100, loss[loss=0.1707, simple_loss=0.2358, pruned_loss=0.05284, over 4753.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02865, over 973170.50 frames.], batch size: 16, lr: 1.17e-04
+2022-05-09 15:59:44,830 INFO [train.py:715] (3/8) Epoch 19, batch 13150, loss[loss=0.1516, simple_loss=0.2305, pruned_loss=0.03637, over 4829.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.02845, over 972950.82 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:00:24,453 INFO [train.py:715] (3/8) Epoch 19, batch 13200, loss[loss=0.1118, simple_loss=0.1869, pruned_loss=0.01829, over 4838.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02864, over 973014.50 frames.], batch size: 26, lr: 1.17e-04
+2022-05-09 16:01:03,676 INFO [train.py:715] (3/8) Epoch 19, batch 13250, loss[loss=0.1723, simple_loss=0.2421, pruned_loss=0.05126, over 4922.00 frames.], tot_loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.02842, over 971932.09 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 16:01:42,978 INFO [train.py:715] (3/8) Epoch 19, batch 13300, loss[loss=0.111, simple_loss=0.1861, pruned_loss=0.0179, over 4895.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02854, over 971944.05 frames.], batch size: 22, lr: 1.17e-04
+2022-05-09 16:02:22,612 INFO [train.py:715] (3/8) Epoch 19, batch 13350, loss[loss=0.1564, simple_loss=0.227, pruned_loss=0.04289, over 4984.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02849, over 971593.31 frames.], batch size: 28, lr: 1.17e-04
+2022-05-09 16:03:01,276 INFO [train.py:715] (3/8) Epoch 19, batch 13400, loss[loss=0.1156, simple_loss=0.1879, pruned_loss=0.02165, over 4841.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02839, over 971653.18 frames.], batch size: 13, lr: 1.17e-04
+2022-05-09 16:03:40,772 INFO [train.py:715] (3/8) Epoch 19, batch 13450, loss[loss=0.1162, simple_loss=0.1939, pruned_loss=0.01922, over 4930.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02824, over 972101.02 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 16:04:20,049 INFO [train.py:715] (3/8) Epoch 19, batch 13500, loss[loss=0.138, simple_loss=0.2052, pruned_loss=0.03537, over 4867.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02832, over 972362.14 frames.], batch size: 39, lr: 1.17e-04
+2022-05-09 16:04:59,473 INFO [train.py:715] (3/8) Epoch 19, batch 13550, loss[loss=0.1196, simple_loss=0.1981, pruned_loss=0.02054, over 4846.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02821, over 972388.02 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:05:38,407 INFO [train.py:715] (3/8) Epoch 19, batch 13600, loss[loss=0.1119, simple_loss=0.1913, pruned_loss=0.01624, over 4925.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02824, over 972693.70 frames.], batch size: 23, lr: 1.17e-04
+2022-05-09 16:06:17,570 INFO [train.py:715] (3/8) Epoch 19, batch 13650, loss[loss=0.1354, simple_loss=0.2137, pruned_loss=0.02854, over 4885.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02833, over 971524.36 frames.], batch size: 32, lr: 1.17e-04
+2022-05-09 16:06:57,012 INFO [train.py:715] (3/8) Epoch 19, batch 13700, loss[loss=0.1496, simple_loss=0.2209, pruned_loss=0.03914, over 4924.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02817, over 971318.06 frames.], batch size: 23, lr: 1.17e-04
+2022-05-09 16:07:35,732 INFO [train.py:715] (3/8) Epoch 19, batch 13750, loss[loss=0.1331, simple_loss=0.2154, pruned_loss=0.02538, over 4772.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02852, over 971960.33 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 16:08:14,998 INFO [train.py:715] (3/8) Epoch 19, batch 13800, loss[loss=0.1222, simple_loss=0.1947, pruned_loss=0.02491, over 4930.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02859, over 971979.19 frames.], batch size: 29, lr: 1.17e-04
+2022-05-09 16:08:55,060 INFO [train.py:715] (3/8) Epoch 19, batch 13850, loss[loss=0.1349, simple_loss=0.2048, pruned_loss=0.0325, over 4769.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02869, over 972292.18 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 16:09:34,678 INFO [train.py:715] (3/8) Epoch 19, batch 13900, loss[loss=0.1243, simple_loss=0.2073, pruned_loss=0.02069, over 4950.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02889, over 973272.69 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 16:10:14,443 INFO [train.py:715] (3/8) Epoch 19, batch 13950, loss[loss=0.1583, simple_loss=0.2357, pruned_loss=0.04044, over 4850.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02852, over 973448.60 frames.], batch size: 20, lr: 1.17e-04
+2022-05-09 16:10:53,216 INFO [train.py:715] (3/8) Epoch 19, batch 14000, loss[loss=0.1308, simple_loss=0.2086, pruned_loss=0.02653, over 4792.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02841, over 972114.99 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 16:11:32,643 INFO [train.py:715] (3/8) Epoch 19, batch 14050, loss[loss=0.1395, simple_loss=0.2214, pruned_loss=0.02874, over 4938.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.02805, over 972716.24 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 16:12:11,842 INFO [train.py:715] (3/8) Epoch 19, batch 14100, loss[loss=0.158, simple_loss=0.2234, pruned_loss=0.04631, over 4777.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2066, pruned_loss=0.02834, over 972443.65 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 16:12:51,005 INFO [train.py:715] (3/8) Epoch 19, batch 14150, loss[loss=0.1253, simple_loss=0.1955, pruned_loss=0.02754, over 4958.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02831, over 972537.86 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 16:13:30,123 INFO [train.py:715] (3/8) Epoch 19, batch 14200, loss[loss=0.1296, simple_loss=0.2085, pruned_loss=0.02535, over 4703.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2067, pruned_loss=0.02836, over 973160.43 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:14:08,939 INFO [train.py:715] (3/8) Epoch 19, batch 14250, loss[loss=0.1112, simple_loss=0.1864, pruned_loss=0.01794, over 4921.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02835, over 973061.58 frames.], batch size: 23, lr: 1.17e-04
+2022-05-09 16:14:48,113 INFO [train.py:715] (3/8) Epoch 19, batch 14300, loss[loss=0.1109, simple_loss=0.1866, pruned_loss=0.01761, over 4899.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2072, pruned_loss=0.02858, over 972555.87 frames.], batch size: 22, lr: 1.17e-04
+2022-05-09 16:15:27,232 INFO [train.py:715] (3/8) Epoch 19, batch 14350, loss[loss=0.1267, simple_loss=0.2065, pruned_loss=0.02348, over 4869.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2069, pruned_loss=0.02836, over 972531.48 frames.], batch size: 32, lr: 1.17e-04
+2022-05-09 16:16:06,785 INFO [train.py:715] (3/8) Epoch 19, batch 14400, loss[loss=0.1778, simple_loss=0.249, pruned_loss=0.05332, over 4953.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02862, over 971790.21 frames.], batch size: 39, lr: 1.17e-04
+2022-05-09 16:16:45,667 INFO [train.py:715] (3/8) Epoch 19, batch 14450, loss[loss=0.1382, simple_loss=0.2095, pruned_loss=0.03346, over 4940.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2069, pruned_loss=0.02841, over 971474.71 frames.], batch size: 23, lr: 1.17e-04
+2022-05-09 16:17:24,668 INFO [train.py:715] (3/8) Epoch 19, batch 14500, loss[loss=0.1266, simple_loss=0.1944, pruned_loss=0.02939, over 4965.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2063, pruned_loss=0.02805, over 971861.57 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:18:03,481 INFO [train.py:715] (3/8) Epoch 19, batch 14550, loss[loss=0.1513, simple_loss=0.212, pruned_loss=0.04531, over 4844.00 frames.], tot_loss[loss=0.131, simple_loss=0.206, pruned_loss=0.02801, over 972055.22 frames.], batch size: 30, lr: 1.17e-04
+2022-05-09 16:18:43,153 INFO [train.py:715] (3/8) Epoch 19, batch 14600, loss[loss=0.1195, simple_loss=0.1942, pruned_loss=0.02244, over 4947.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02833, over 972246.56 frames.], batch size: 39, lr: 1.17e-04
+2022-05-09 16:19:22,223 INFO [train.py:715] (3/8) Epoch 19, batch 14650, loss[loss=0.1285, simple_loss=0.2054, pruned_loss=0.02583, over 4801.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2064, pruned_loss=0.02834, over 972931.55 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 16:20:01,161 INFO [train.py:715] (3/8) Epoch 19, batch 14700, loss[loss=0.1158, simple_loss=0.1878, pruned_loss=0.02194, over 4790.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02835, over 971729.72 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 16:20:40,519 INFO [train.py:715] (3/8) Epoch 19, batch 14750, loss[loss=0.1287, simple_loss=0.2111, pruned_loss=0.0231, over 4756.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.0281, over 970921.54 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 16:21:19,782 INFO [train.py:715] (3/8) Epoch 19, batch 14800, loss[loss=0.1338, simple_loss=0.2121, pruned_loss=0.02778, over 4934.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02815, over 971456.33 frames.], batch size: 29, lr: 1.17e-04
+2022-05-09 16:21:58,084 INFO [train.py:715] (3/8) Epoch 19, batch 14850, loss[loss=0.1325, simple_loss=0.1998, pruned_loss=0.0326, over 4780.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02793, over 971248.49 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 16:22:37,372 INFO [train.py:715] (3/8) Epoch 19, batch 14900, loss[loss=0.1182, simple_loss=0.1931, pruned_loss=0.02165, over 4701.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2053, pruned_loss=0.02799, over 970893.33 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:23:16,322 INFO [train.py:715] (3/8) Epoch 19, batch 14950, loss[loss=0.1452, simple_loss=0.2066, pruned_loss=0.04189, over 4742.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02801, over 970617.24 frames.], batch size: 16, lr: 1.17e-04
+2022-05-09 16:23:55,095 INFO [train.py:715] (3/8) Epoch 19, batch 15000, loss[loss=0.1436, simple_loss=0.2077, pruned_loss=0.03977, over 4862.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02805, over 971713.29 frames.], batch size: 32, lr: 1.17e-04
+2022-05-09 16:23:55,096 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 16:24:07,487 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1877, pruned_loss=0.01064, over 914524.00 frames.
+2022-05-09 16:24:46,703 INFO [train.py:715] (3/8) Epoch 19, batch 15050, loss[loss=0.1622, simple_loss=0.228, pruned_loss=0.0482, over 4643.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02835, over 971976.71 frames.], batch size: 13, lr: 1.17e-04
+2022-05-09 16:25:26,174 INFO [train.py:715] (3/8) Epoch 19, batch 15100, loss[loss=0.1684, simple_loss=0.2444, pruned_loss=0.04625, over 4800.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02841, over 971955.54 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 16:26:05,807 INFO [train.py:715] (3/8) Epoch 19, batch 15150, loss[loss=0.125, simple_loss=0.1963, pruned_loss=0.02685, over 4979.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02862, over 972736.53 frames.], batch size: 28, lr: 1.17e-04
+2022-05-09 16:26:45,270 INFO [train.py:715] (3/8) Epoch 19, batch 15200, loss[loss=0.1323, simple_loss=0.2176, pruned_loss=0.02343, over 4819.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02834, over 972805.18 frames.], batch size: 13, lr: 1.17e-04
+2022-05-09 16:27:24,250 INFO [train.py:715] (3/8) Epoch 19, batch 15250, loss[loss=0.1175, simple_loss=0.1858, pruned_loss=0.02458, over 4918.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02827, over 972011.66 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 16:28:04,172 INFO [train.py:715] (3/8) Epoch 19, batch 15300, loss[loss=0.1411, simple_loss=0.2145, pruned_loss=0.03385, over 4965.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.0285, over 973058.24 frames.], batch size: 35, lr: 1.17e-04
+2022-05-09 16:28:43,720 INFO [train.py:715] (3/8) Epoch 19, batch 15350, loss[loss=0.1288, simple_loss=0.2112, pruned_loss=0.02322, over 4897.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2064, pruned_loss=0.02797, over 973062.33 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 16:29:23,530 INFO [train.py:715] (3/8) Epoch 19, batch 15400, loss[loss=0.137, simple_loss=0.2085, pruned_loss=0.03279, over 4983.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2066, pruned_loss=0.02795, over 972908.51 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:30:03,012 INFO [train.py:715] (3/8) Epoch 19, batch 15450, loss[loss=0.121, simple_loss=0.1951, pruned_loss=0.02343, over 4843.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2065, pruned_loss=0.02807, over 972962.56 frames.], batch size: 30, lr: 1.17e-04
+2022-05-09 16:30:42,453 INFO [train.py:715] (3/8) Epoch 19, batch 15500, loss[loss=0.1282, simple_loss=0.2066, pruned_loss=0.02487, over 4794.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2075, pruned_loss=0.0285, over 971786.39 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 16:31:21,336 INFO [train.py:715] (3/8) Epoch 19, batch 15550, loss[loss=0.1208, simple_loss=0.1933, pruned_loss=0.02414, over 4750.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2073, pruned_loss=0.02841, over 971669.56 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 16:32:00,419 INFO [train.py:715] (3/8) Epoch 19, batch 15600, loss[loss=0.1248, simple_loss=0.2048, pruned_loss=0.02237, over 4811.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2076, pruned_loss=0.02876, over 971913.09 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 16:32:40,088 INFO [train.py:715] (3/8) Epoch 19, batch 15650, loss[loss=0.135, simple_loss=0.207, pruned_loss=0.03143, over 4985.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02892, over 971258.98 frames.], batch size: 26, lr: 1.17e-04
+2022-05-09 16:33:19,038 INFO [train.py:715] (3/8) Epoch 19, batch 15700, loss[loss=0.1314, simple_loss=0.2021, pruned_loss=0.03038, over 4884.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02891, over 971319.01 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 16:33:59,138 INFO [train.py:715] (3/8) Epoch 19, batch 15750, loss[loss=0.1232, simple_loss=0.1933, pruned_loss=0.02657, over 4914.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02887, over 971805.85 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 16:34:38,393 INFO [train.py:715] (3/8) Epoch 19, batch 15800, loss[loss=0.1234, simple_loss=0.1884, pruned_loss=0.02921, over 4778.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02905, over 971577.96 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 16:35:17,528 INFO [train.py:715] (3/8) Epoch 19, batch 15850, loss[loss=0.1208, simple_loss=0.1958, pruned_loss=0.0229, over 4968.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02832, over 972467.05 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:35:56,471 INFO [train.py:715] (3/8) Epoch 19, batch 15900, loss[loss=0.136, simple_loss=0.2161, pruned_loss=0.02796, over 4806.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02826, over 972329.10 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 16:36:35,618 INFO [train.py:715] (3/8) Epoch 19, batch 15950, loss[loss=0.1321, simple_loss=0.2072, pruned_loss=0.02845, over 4925.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2063, pruned_loss=0.02807, over 971246.65 frames.], batch size: 23, lr: 1.17e-04
+2022-05-09 16:37:15,272 INFO [train.py:715] (3/8) Epoch 19, batch 16000, loss[loss=0.1393, simple_loss=0.2159, pruned_loss=0.0314, over 4966.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2067, pruned_loss=0.02834, over 971192.58 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:37:53,933 INFO [train.py:715] (3/8) Epoch 19, batch 16050, loss[loss=0.1209, simple_loss=0.1909, pruned_loss=0.02542, over 4790.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02837, over 970599.60 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 16:38:33,244 INFO [train.py:715] (3/8) Epoch 19, batch 16100, loss[loss=0.1509, simple_loss=0.2391, pruned_loss=0.03137, over 4956.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02837, over 971187.37 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:39:12,542 INFO [train.py:715] (3/8) Epoch 19, batch 16150, loss[loss=0.1392, simple_loss=0.2164, pruned_loss=0.03099, over 4927.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02834, over 971801.74 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 16:39:51,600 INFO [train.py:715] (3/8) Epoch 19, batch 16200, loss[loss=0.1236, simple_loss=0.1944, pruned_loss=0.0264, over 4820.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02804, over 972005.82 frames.], batch size: 13, lr: 1.17e-04
+2022-05-09 16:40:29,891 INFO [train.py:715] (3/8) Epoch 19, batch 16250, loss[loss=0.1059, simple_loss=0.1779, pruned_loss=0.01695, over 4855.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02835, over 971664.30 frames.], batch size: 20, lr: 1.17e-04
+2022-05-09 16:41:08,934 INFO [train.py:715] (3/8) Epoch 19, batch 16300, loss[loss=0.152, simple_loss=0.2232, pruned_loss=0.04039, over 4877.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.02864, over 972048.03 frames.], batch size: 32, lr: 1.17e-04
+2022-05-09 16:41:48,391 INFO [train.py:715] (3/8) Epoch 19, batch 16350, loss[loss=0.113, simple_loss=0.1868, pruned_loss=0.01958, over 4800.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2068, pruned_loss=0.02846, over 971502.88 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 16:42:26,932 INFO [train.py:715] (3/8) Epoch 19, batch 16400, loss[loss=0.09984, simple_loss=0.1772, pruned_loss=0.01126, over 4780.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2063, pruned_loss=0.02794, over 971581.62 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 16:43:05,777 INFO [train.py:715] (3/8) Epoch 19, batch 16450, loss[loss=0.1223, simple_loss=0.2042, pruned_loss=0.02026, over 4834.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2058, pruned_loss=0.02793, over 971524.95 frames.], batch size: 26, lr: 1.17e-04
+2022-05-09 16:43:44,323 INFO [train.py:715] (3/8) Epoch 19, batch 16500, loss[loss=0.1545, simple_loss=0.2278, pruned_loss=0.04061, over 4927.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2056, pruned_loss=0.02761, over 971089.52 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 16:44:23,744 INFO [train.py:715] (3/8) Epoch 19, batch 16550, loss[loss=0.1224, simple_loss=0.1934, pruned_loss=0.0257, over 4747.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2056, pruned_loss=0.02758, over 970806.16 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 16:45:02,747 INFO [train.py:715] (3/8) Epoch 19, batch 16600, loss[loss=0.1245, simple_loss=0.1902, pruned_loss=0.02943, over 4983.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2054, pruned_loss=0.02772, over 970691.87 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 16:45:41,762 INFO [train.py:715] (3/8) Epoch 19, batch 16650, loss[loss=0.1173, simple_loss=0.1971, pruned_loss=0.0188, over 4956.00 frames.], tot_loss[loss=0.13, simple_loss=0.2045, pruned_loss=0.02779, over 970413.24 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 16:46:21,734 INFO [train.py:715] (3/8) Epoch 19, batch 16700, loss[loss=0.1212, simple_loss=0.196, pruned_loss=0.02317, over 4981.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2046, pruned_loss=0.02806, over 970605.60 frames.], batch size: 28, lr: 1.17e-04
+2022-05-09 16:47:00,843 INFO [train.py:715] (3/8) Epoch 19, batch 16750, loss[loss=0.1455, simple_loss=0.2241, pruned_loss=0.03344, over 4965.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2046, pruned_loss=0.02805, over 971259.24 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 16:47:40,567 INFO [train.py:715] (3/8) Epoch 19, batch 16800, loss[loss=0.1287, simple_loss=0.2038, pruned_loss=0.02683, over 4988.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2043, pruned_loss=0.02816, over 972078.00 frames.], batch size: 31, lr: 1.17e-04
+2022-05-09 16:48:19,964 INFO [train.py:715] (3/8) Epoch 19, batch 16850, loss[loss=0.1444, simple_loss=0.2136, pruned_loss=0.03755, over 4942.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2044, pruned_loss=0.0281, over 972341.31 frames.], batch size: 23, lr: 1.17e-04
+2022-05-09 16:48:59,492 INFO [train.py:715] (3/8) Epoch 19, batch 16900, loss[loss=0.1455, simple_loss=0.2163, pruned_loss=0.03739, over 4915.00 frames.], tot_loss[loss=0.131, simple_loss=0.2051, pruned_loss=0.0284, over 972813.73 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 16:49:38,108 INFO [train.py:715] (3/8) Epoch 19, batch 16950, loss[loss=0.1169, simple_loss=0.194, pruned_loss=0.01985, over 4790.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02857, over 972547.16 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 16:50:17,671 INFO [train.py:715] (3/8) Epoch 19, batch 17000, loss[loss=0.191, simple_loss=0.2428, pruned_loss=0.06961, over 4926.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.0286, over 972569.55 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 16:50:57,094 INFO [train.py:715] (3/8) Epoch 19, batch 17050, loss[loss=0.142, simple_loss=0.2215, pruned_loss=0.03124, over 4877.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02862, over 972181.83 frames.], batch size: 22, lr: 1.17e-04
+2022-05-09 16:51:36,156 INFO [train.py:715] (3/8) Epoch 19, batch 17100, loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.03265, over 4845.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02867, over 972177.18 frames.], batch size: 13, lr: 1.17e-04
+2022-05-09 16:52:15,338 INFO [train.py:715] (3/8) Epoch 19, batch 17150, loss[loss=0.1581, simple_loss=0.2261, pruned_loss=0.04499, over 4790.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02861, over 972240.58 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 16:52:54,352 INFO [train.py:715] (3/8) Epoch 19, batch 17200, loss[loss=0.1321, simple_loss=0.2101, pruned_loss=0.027, over 4944.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.0287, over 972412.19 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 16:53:33,089 INFO [train.py:715] (3/8) Epoch 19, batch 17250, loss[loss=0.1187, simple_loss=0.1954, pruned_loss=0.02106, over 4822.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02822, over 972193.45 frames.], batch size: 25, lr: 1.17e-04
+2022-05-09 16:54:12,078 INFO [train.py:715] (3/8) Epoch 19, batch 17300, loss[loss=0.1405, simple_loss=0.2207, pruned_loss=0.03014, over 4705.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02817, over 971967.38 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:54:51,728 INFO [train.py:715] (3/8) Epoch 19, batch 17350, loss[loss=0.134, simple_loss=0.2105, pruned_loss=0.02874, over 4975.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2053, pruned_loss=0.02799, over 972833.14 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:55:31,274 INFO [train.py:715] (3/8) Epoch 19, batch 17400, loss[loss=0.1369, simple_loss=0.2124, pruned_loss=0.03069, over 4712.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02849, over 972375.33 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:56:10,520 INFO [train.py:715] (3/8) Epoch 19, batch 17450, loss[loss=0.1432, simple_loss=0.2001, pruned_loss=0.0431, over 4930.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02846, over 972665.87 frames.], batch size: 29, lr: 1.17e-04
+2022-05-09 16:56:49,866 INFO [train.py:715] (3/8) Epoch 19, batch 17500, loss[loss=0.1249, simple_loss=0.1951, pruned_loss=0.02731, over 4753.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02873, over 972463.31 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 16:57:29,146 INFO [train.py:715] (3/8) Epoch 19, batch 17550, loss[loss=0.1281, simple_loss=0.2003, pruned_loss=0.02801, over 4957.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2053, pruned_loss=0.02797, over 972846.63 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 16:58:08,752 INFO [train.py:715] (3/8) Epoch 19, batch 17600, loss[loss=0.1484, simple_loss=0.2162, pruned_loss=0.04025, over 4838.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02795, over 972575.58 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 16:58:47,927 INFO [train.py:715] (3/8) Epoch 19, batch 17650, loss[loss=0.1195, simple_loss=0.194, pruned_loss=0.02248, over 4985.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02825, over 972207.92 frames.], batch size: 28, lr: 1.17e-04
+2022-05-09 16:59:27,075 INFO [train.py:715] (3/8) Epoch 19, batch 17700, loss[loss=0.1309, simple_loss=0.2127, pruned_loss=0.02455, over 4934.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02807, over 971329.87 frames.], batch size: 29, lr: 1.17e-04
+2022-05-09 17:00:06,647 INFO [train.py:715] (3/8) Epoch 19, batch 17750, loss[loss=0.1596, simple_loss=0.218, pruned_loss=0.05056, over 4971.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02833, over 972307.90 frames.], batch size: 35, lr: 1.17e-04
+2022-05-09 17:00:45,237 INFO [train.py:715] (3/8) Epoch 19, batch 17800, loss[loss=0.127, simple_loss=0.1968, pruned_loss=0.02861, over 4801.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02814, over 972482.68 frames.], batch size: 12, lr: 1.17e-04
+2022-05-09 17:01:24,011 INFO [train.py:715] (3/8) Epoch 19, batch 17850, loss[loss=0.1182, simple_loss=0.1906, pruned_loss=0.02292, over 4861.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02846, over 972218.64 frames.], batch size: 32, lr: 1.17e-04
+2022-05-09 17:02:03,485 INFO [train.py:715] (3/8) Epoch 19, batch 17900, loss[loss=0.1599, simple_loss=0.2317, pruned_loss=0.0441, over 4893.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02818, over 972599.36 frames.], batch size: 39, lr: 1.17e-04
+2022-05-09 17:02:41,970 INFO [train.py:715] (3/8) Epoch 19, batch 17950, loss[loss=0.1273, simple_loss=0.1926, pruned_loss=0.03105, over 4991.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02883, over 972689.14 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 17:03:21,256 INFO [train.py:715] (3/8) Epoch 19, batch 18000, loss[loss=0.141, simple_loss=0.2088, pruned_loss=0.0366, over 4977.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02881, over 973073.29 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 17:03:21,256 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 17:03:31,128 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1046, simple_loss=0.1877, pruned_loss=0.01074, over 914524.00 frames.
+2022-05-09 17:04:10,641 INFO [train.py:715] (3/8) Epoch 19, batch 18050, loss[loss=0.1304, simple_loss=0.199, pruned_loss=0.03092, over 4833.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02894, over 972854.96 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 17:04:50,209 INFO [train.py:715] (3/8) Epoch 19, batch 18100, loss[loss=0.1741, simple_loss=0.2504, pruned_loss=0.04888, over 4800.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02892, over 973282.74 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 17:05:30,065 INFO [train.py:715] (3/8) Epoch 19, batch 18150, loss[loss=0.149, simple_loss=0.2159, pruned_loss=0.04109, over 4963.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02867, over 973014.82 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 17:06:09,190 INFO [train.py:715] (3/8) Epoch 19, batch 18200, loss[loss=0.134, simple_loss=0.2114, pruned_loss=0.0283, over 4961.00 frames.], tot_loss[loss=0.132, simple_loss=0.2059, pruned_loss=0.02902, over 973841.64 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 17:06:48,111 INFO [train.py:715] (3/8) Epoch 19, batch 18250, loss[loss=0.1431, simple_loss=0.22, pruned_loss=0.03314, over 4967.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02901, over 973777.51 frames.], batch size: 35, lr: 1.17e-04
+2022-05-09 17:07:28,073 INFO [train.py:715] (3/8) Epoch 19, batch 18300, loss[loss=0.1193, simple_loss=0.1904, pruned_loss=0.02409, over 4963.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02897, over 974226.29 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 17:08:07,531 INFO [train.py:715] (3/8) Epoch 19, batch 18350, loss[loss=0.1302, simple_loss=0.2106, pruned_loss=0.02487, over 4944.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02878, over 973717.90 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 17:08:47,421 INFO [train.py:715] (3/8) Epoch 19, batch 18400, loss[loss=0.1269, simple_loss=0.2021, pruned_loss=0.02591, over 4756.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02878, over 973703.89 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 17:09:26,676 INFO [train.py:715] (3/8) Epoch 19, batch 18450, loss[loss=0.141, simple_loss=0.2164, pruned_loss=0.03285, over 4790.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.0286, over 973487.29 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 17:10:06,109 INFO [train.py:715] (3/8) Epoch 19, batch 18500, loss[loss=0.1199, simple_loss=0.1926, pruned_loss=0.02357, over 4972.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02844, over 972245.18 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 17:10:45,347 INFO [train.py:715] (3/8) Epoch 19, batch 18550, loss[loss=0.1405, simple_loss=0.2227, pruned_loss=0.02911, over 4915.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02864, over 972121.99 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 17:11:24,401 INFO [train.py:715] (3/8) Epoch 19, batch 18600, loss[loss=0.09521, simple_loss=0.1682, pruned_loss=0.01111, over 4928.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02828, over 972440.95 frames.], batch size: 23, lr: 1.17e-04
+2022-05-09 17:12:06,303 INFO [train.py:715] (3/8) Epoch 19, batch 18650, loss[loss=0.1106, simple_loss=0.1793, pruned_loss=0.02094, over 4784.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02878, over 972261.36 frames.], batch size: 12, lr: 1.17e-04
+2022-05-09 17:12:45,148 INFO [train.py:715] (3/8) Epoch 19, batch 18700, loss[loss=0.1285, simple_loss=0.2138, pruned_loss=0.02156, over 4710.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2074, pruned_loss=0.02852, over 972600.45 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 17:13:24,440 INFO [train.py:715] (3/8) Epoch 19, batch 18750, loss[loss=0.1228, simple_loss=0.1948, pruned_loss=0.02542, over 4957.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2065, pruned_loss=0.02821, over 973113.21 frames.], batch size: 29, lr: 1.17e-04
+2022-05-09 17:14:04,381 INFO [train.py:715] (3/8) Epoch 19, batch 18800, loss[loss=0.1258, simple_loss=0.2013, pruned_loss=0.02519, over 4807.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02862, over 973237.09 frames.], batch size: 25, lr: 1.17e-04
+2022-05-09 17:14:44,262 INFO [train.py:715] (3/8) Epoch 19, batch 18850, loss[loss=0.1255, simple_loss=0.2059, pruned_loss=0.02251, over 4827.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02893, over 973194.69 frames.], batch size: 26, lr: 1.17e-04
+2022-05-09 17:15:23,449 INFO [train.py:715] (3/8) Epoch 19, batch 18900, loss[loss=0.1207, simple_loss=0.1928, pruned_loss=0.02426, over 4816.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.0288, over 973509.83 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 17:16:02,832 INFO [train.py:715] (3/8) Epoch 19, batch 18950, loss[loss=0.1133, simple_loss=0.1868, pruned_loss=0.01989, over 4926.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.0287, over 972152.04 frames.], batch size: 23, lr: 1.17e-04
+2022-05-09 17:16:42,871 INFO [train.py:715] (3/8) Epoch 19, batch 19000, loss[loss=0.1431, simple_loss=0.2199, pruned_loss=0.03316, over 4964.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02902, over 972011.73 frames.], batch size: 40, lr: 1.17e-04
+2022-05-09 17:17:22,370 INFO [train.py:715] (3/8) Epoch 19, batch 19050, loss[loss=0.129, simple_loss=0.1999, pruned_loss=0.02906, over 4925.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02865, over 971318.72 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 17:18:01,437 INFO [train.py:715] (3/8) Epoch 19, batch 19100, loss[loss=0.1401, simple_loss=0.2077, pruned_loss=0.03625, over 4932.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.0288, over 971383.56 frames.], batch size: 29, lr: 1.17e-04
+2022-05-09 17:18:41,051 INFO [train.py:715] (3/8) Epoch 19, batch 19150, loss[loss=0.1491, simple_loss=0.223, pruned_loss=0.03762, over 4968.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02864, over 971847.54 frames.], batch size: 28, lr: 1.17e-04
+2022-05-09 17:19:20,393 INFO [train.py:715] (3/8) Epoch 19, batch 19200, loss[loss=0.1382, simple_loss=0.2123, pruned_loss=0.03209, over 4968.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02844, over 971084.26 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 17:19:59,881 INFO [train.py:715] (3/8) Epoch 19, batch 19250, loss[loss=0.162, simple_loss=0.2298, pruned_loss=0.0471, over 4954.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02865, over 971439.74 frames.], batch size: 35, lr: 1.17e-04
+2022-05-09 17:20:39,159 INFO [train.py:715] (3/8) Epoch 19, batch 19300, loss[loss=0.141, simple_loss=0.2177, pruned_loss=0.03211, over 4961.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02839, over 971781.83 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 17:21:19,522 INFO [train.py:715] (3/8) Epoch 19, batch 19350, loss[loss=0.1538, simple_loss=0.2131, pruned_loss=0.04721, over 4814.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02883, over 971160.98 frames.], batch size: 13, lr: 1.17e-04
+2022-05-09 17:21:58,944 INFO [train.py:715] (3/8) Epoch 19, batch 19400, loss[loss=0.1539, simple_loss=0.2269, pruned_loss=0.04049, over 4962.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02882, over 970729.58 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 17:22:38,649 INFO [train.py:715] (3/8) Epoch 19, batch 19450, loss[loss=0.133, simple_loss=0.2025, pruned_loss=0.03173, over 4901.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02893, over 970507.56 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 17:23:18,392 INFO [train.py:715] (3/8) Epoch 19, batch 19500, loss[loss=0.1257, simple_loss=0.2051, pruned_loss=0.02311, over 4805.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.02895, over 970776.01 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 17:23:57,782 INFO [train.py:715] (3/8) Epoch 19, batch 19550, loss[loss=0.126, simple_loss=0.1995, pruned_loss=0.02622, over 4878.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02918, over 970380.24 frames.], batch size: 16, lr: 1.17e-04
+2022-05-09 17:24:36,950 INFO [train.py:715] (3/8) Epoch 19, batch 19600, loss[loss=0.1615, simple_loss=0.2355, pruned_loss=0.04374, over 4931.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02897, over 970641.41 frames.], batch size: 39, lr: 1.17e-04
+2022-05-09 17:25:17,642 INFO [train.py:715] (3/8) Epoch 19, batch 19650, loss[loss=0.1245, simple_loss=0.2091, pruned_loss=0.01991, over 4901.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02895, over 971547.15 frames.], batch size: 29, lr: 1.17e-04
+2022-05-09 17:25:56,966 INFO [train.py:715] (3/8) Epoch 19, batch 19700, loss[loss=0.1435, simple_loss=0.22, pruned_loss=0.03347, over 4923.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02883, over 972051.92 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 17:26:35,805 INFO [train.py:715] (3/8) Epoch 19, batch 19750, loss[loss=0.1246, simple_loss=0.192, pruned_loss=0.02861, over 4910.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02911, over 972434.20 frames.], batch size: 23, lr: 1.17e-04
+2022-05-09 17:27:16,060 INFO [train.py:715] (3/8) Epoch 19, batch 19800, loss[loss=0.1319, simple_loss=0.1924, pruned_loss=0.03574, over 4642.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02907, over 972364.47 frames.], batch size: 13, lr: 1.17e-04
+2022-05-09 17:27:55,916 INFO [train.py:715] (3/8) Epoch 19, batch 19850, loss[loss=0.1377, simple_loss=0.2201, pruned_loss=0.02761, over 4811.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02904, over 972283.34 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 17:28:35,201 INFO [train.py:715] (3/8) Epoch 19, batch 19900, loss[loss=0.1327, simple_loss=0.2094, pruned_loss=0.02803, over 4972.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02899, over 971674.61 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 17:29:13,881 INFO [train.py:715] (3/8) Epoch 19, batch 19950, loss[loss=0.1282, simple_loss=0.1994, pruned_loss=0.02855, over 4694.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02863, over 971540.83 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 17:29:53,616 INFO [train.py:715] (3/8) Epoch 19, batch 20000, loss[loss=0.1417, simple_loss=0.2091, pruned_loss=0.0372, over 4774.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02828, over 971578.75 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 17:30:33,007 INFO [train.py:715] (3/8) Epoch 19, batch 20050, loss[loss=0.118, simple_loss=0.1982, pruned_loss=0.01887, over 4938.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.02807, over 972752.81 frames.], batch size: 23, lr: 1.17e-04
+2022-05-09 17:31:12,642 INFO [train.py:715] (3/8) Epoch 19, batch 20100, loss[loss=0.1342, simple_loss=0.1912, pruned_loss=0.03853, over 4814.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02863, over 973011.99 frames.], batch size: 13, lr: 1.17e-04
+2022-05-09 17:31:52,174 INFO [train.py:715] (3/8) Epoch 19, batch 20150, loss[loss=0.1204, simple_loss=0.1967, pruned_loss=0.02207, over 4904.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.0287, over 973105.51 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 17:32:31,819 INFO [train.py:715] (3/8) Epoch 19, batch 20200, loss[loss=0.1117, simple_loss=0.191, pruned_loss=0.01622, over 4926.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02822, over 972183.51 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 17:33:11,345 INFO [train.py:715] (3/8) Epoch 19, batch 20250, loss[loss=0.1412, simple_loss=0.2181, pruned_loss=0.03215, over 4832.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02813, over 971905.30 frames.], batch size: 26, lr: 1.17e-04
+2022-05-09 17:33:50,681 INFO [train.py:715] (3/8) Epoch 19, batch 20300, loss[loss=0.1289, simple_loss=0.1958, pruned_loss=0.03095, over 4772.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02867, over 971637.75 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 17:34:30,223 INFO [train.py:715] (3/8) Epoch 19, batch 20350, loss[loss=0.1386, simple_loss=0.209, pruned_loss=0.03413, over 4963.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.0286, over 971408.69 frames.], batch size: 35, lr: 1.17e-04
+2022-05-09 17:35:09,432 INFO [train.py:715] (3/8) Epoch 19, batch 20400, loss[loss=0.12, simple_loss=0.2016, pruned_loss=0.01916, over 4775.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02834, over 972772.57 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 17:35:48,299 INFO [train.py:715] (3/8) Epoch 19, batch 20450, loss[loss=0.1478, simple_loss=0.2238, pruned_loss=0.03595, over 4992.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.0283, over 972625.96 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 17:36:28,041 INFO [train.py:715] (3/8) Epoch 19, batch 20500, loss[loss=0.13, simple_loss=0.1995, pruned_loss=0.03026, over 4793.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02851, over 972884.29 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 17:37:07,746 INFO [train.py:715] (3/8) Epoch 19, batch 20550, loss[loss=0.1655, simple_loss=0.2382, pruned_loss=0.04644, over 4774.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02836, over 972615.36 frames.], batch size: 19, lr: 1.17e-04
+2022-05-09 17:37:46,564 INFO [train.py:715] (3/8) Epoch 19, batch 20600, loss[loss=0.113, simple_loss=0.1898, pruned_loss=0.01812, over 4782.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02868, over 972006.31 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 17:38:26,012 INFO [train.py:715] (3/8) Epoch 19, batch 20650, loss[loss=0.1341, simple_loss=0.205, pruned_loss=0.03155, over 4806.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02874, over 972488.69 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 17:39:05,345 INFO [train.py:715] (3/8) Epoch 19, batch 20700, loss[loss=0.1265, simple_loss=0.2046, pruned_loss=0.02418, over 4913.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02845, over 971362.80 frames.], batch size: 17, lr: 1.17e-04
+2022-05-09 17:39:44,823 INFO [train.py:715] (3/8) Epoch 19, batch 20750, loss[loss=0.1388, simple_loss=0.2174, pruned_loss=0.03012, over 4802.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2067, pruned_loss=0.02821, over 971897.04 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 17:40:23,537 INFO [train.py:715] (3/8) Epoch 19, batch 20800, loss[loss=0.1357, simple_loss=0.2061, pruned_loss=0.0326, over 4831.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02823, over 972990.59 frames.], batch size: 30, lr: 1.17e-04
+2022-05-09 17:41:02,812 INFO [train.py:715] (3/8) Epoch 19, batch 20850, loss[loss=0.1432, simple_loss=0.2127, pruned_loss=0.03685, over 4905.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02818, over 972845.75 frames.], batch size: 18, lr: 1.17e-04
+2022-05-09 17:41:42,481 INFO [train.py:715] (3/8) Epoch 19, batch 20900, loss[loss=0.1245, simple_loss=0.2029, pruned_loss=0.02305, over 4828.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2054, pruned_loss=0.02796, over 973135.28 frames.], batch size: 13, lr: 1.17e-04
+2022-05-09 17:42:21,286 INFO [train.py:715] (3/8) Epoch 19, batch 20950, loss[loss=0.1465, simple_loss=0.2158, pruned_loss=0.03857, over 4690.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2057, pruned_loss=0.02788, over 972706.50 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 17:43:01,036 INFO [train.py:715] (3/8) Epoch 19, batch 21000, loss[loss=0.1218, simple_loss=0.1834, pruned_loss=0.03011, over 4891.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02805, over 973176.62 frames.], batch size: 16, lr: 1.17e-04
+2022-05-09 17:43:01,037 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 17:43:11,504 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1878, pruned_loss=0.01062, over 914524.00 frames.
+2022-05-09 17:43:51,338 INFO [train.py:715] (3/8) Epoch 19, batch 21050, loss[loss=0.1304, simple_loss=0.205, pruned_loss=0.02788, over 4990.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02805, over 972761.67 frames.], batch size: 14, lr: 1.17e-04
+2022-05-09 17:44:31,303 INFO [train.py:715] (3/8) Epoch 19, batch 21100, loss[loss=0.1289, simple_loss=0.2041, pruned_loss=0.02682, over 4817.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02791, over 973667.19 frames.], batch size: 26, lr: 1.17e-04
+2022-05-09 17:45:10,120 INFO [train.py:715] (3/8) Epoch 19, batch 21150, loss[loss=0.1329, simple_loss=0.2184, pruned_loss=0.02371, over 4862.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.02798, over 973586.77 frames.], batch size: 20, lr: 1.17e-04
+2022-05-09 17:45:49,701 INFO [train.py:715] (3/8) Epoch 19, batch 21200, loss[loss=0.1392, simple_loss=0.2096, pruned_loss=0.03439, over 4979.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.0282, over 973488.05 frames.], batch size: 31, lr: 1.17e-04
+2022-05-09 17:46:28,952 INFO [train.py:715] (3/8) Epoch 19, batch 21250, loss[loss=0.1123, simple_loss=0.1895, pruned_loss=0.0175, over 4900.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02825, over 972996.79 frames.], batch size: 22, lr: 1.17e-04
+2022-05-09 17:47:07,993 INFO [train.py:715] (3/8) Epoch 19, batch 21300, loss[loss=0.1425, simple_loss=0.2126, pruned_loss=0.03615, over 4882.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02819, over 972473.81 frames.], batch size: 16, lr: 1.17e-04
+2022-05-09 17:47:46,808 INFO [train.py:715] (3/8) Epoch 19, batch 21350, loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02782, over 4968.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02843, over 972910.50 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 17:48:26,342 INFO [train.py:715] (3/8) Epoch 19, batch 21400, loss[loss=0.1576, simple_loss=0.2471, pruned_loss=0.0341, over 4953.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02881, over 972496.76 frames.], batch size: 24, lr: 1.17e-04
+2022-05-09 17:49:05,855 INFO [train.py:715] (3/8) Epoch 19, batch 21450, loss[loss=0.1731, simple_loss=0.2512, pruned_loss=0.0475, over 4976.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02882, over 971974.85 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 17:49:44,647 INFO [train.py:715] (3/8) Epoch 19, batch 21500, loss[loss=0.1113, simple_loss=0.1821, pruned_loss=0.0203, over 4931.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02917, over 972626.82 frames.], batch size: 29, lr: 1.17e-04
+2022-05-09 17:50:24,357 INFO [train.py:715] (3/8) Epoch 19, batch 21550, loss[loss=0.1163, simple_loss=0.1864, pruned_loss=0.02309, over 4804.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02894, over 973340.43 frames.], batch size: 21, lr: 1.17e-04
+2022-05-09 17:51:04,079 INFO [train.py:715] (3/8) Epoch 19, batch 21600, loss[loss=0.1663, simple_loss=0.2319, pruned_loss=0.05038, over 4698.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02872, over 972447.33 frames.], batch size: 15, lr: 1.17e-04
+2022-05-09 17:51:43,838 INFO [train.py:715] (3/8) Epoch 19, batch 21650, loss[loss=0.143, simple_loss=0.2135, pruned_loss=0.03626, over 4817.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02898, over 972978.85 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 17:52:22,733 INFO [train.py:715] (3/8) Epoch 19, batch 21700, loss[loss=0.1123, simple_loss=0.1861, pruned_loss=0.0193, over 4762.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02889, over 972664.69 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 17:53:02,146 INFO [train.py:715] (3/8) Epoch 19, batch 21750, loss[loss=0.1308, simple_loss=0.2082, pruned_loss=0.02673, over 4867.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02876, over 972359.74 frames.], batch size: 20, lr: 1.16e-04
+2022-05-09 17:53:43,112 INFO [train.py:715] (3/8) Epoch 19, batch 21800, loss[loss=0.1365, simple_loss=0.2148, pruned_loss=0.02905, over 4874.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02809, over 973236.95 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 17:54:22,935 INFO [train.py:715] (3/8) Epoch 19, batch 21850, loss[loss=0.1756, simple_loss=0.2372, pruned_loss=0.05702, over 4871.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2051, pruned_loss=0.02776, over 972824.76 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 17:55:03,314 INFO [train.py:715] (3/8) Epoch 19, batch 21900, loss[loss=0.1257, simple_loss=0.2081, pruned_loss=0.02161, over 4876.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02817, over 973719.87 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 17:55:43,306 INFO [train.py:715] (3/8) Epoch 19, batch 21950, loss[loss=0.1128, simple_loss=0.1883, pruned_loss=0.01861, over 4883.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02795, over 973674.32 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 17:56:22,525 INFO [train.py:715] (3/8) Epoch 19, batch 22000, loss[loss=0.1152, simple_loss=0.1907, pruned_loss=0.01983, over 4873.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2043, pruned_loss=0.02763, over 973645.96 frames.], batch size: 22, lr: 1.16e-04
+2022-05-09 17:57:01,818 INFO [train.py:715] (3/8) Epoch 19, batch 22050, loss[loss=0.1175, simple_loss=0.184, pruned_loss=0.02551, over 4918.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02847, over 973833.41 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 17:57:41,390 INFO [train.py:715] (3/8) Epoch 19, batch 22100, loss[loss=0.1308, simple_loss=0.2013, pruned_loss=0.03019, over 4784.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02809, over 973133.48 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 17:58:21,389 INFO [train.py:715] (3/8) Epoch 19, batch 22150, loss[loss=0.1285, simple_loss=0.1856, pruned_loss=0.03573, over 4774.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2047, pruned_loss=0.02795, over 972739.94 frames.], batch size: 12, lr: 1.16e-04
+2022-05-09 17:59:00,691 INFO [train.py:715] (3/8) Epoch 19, batch 22200, loss[loss=0.1378, simple_loss=0.2123, pruned_loss=0.0317, over 4784.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2047, pruned_loss=0.02779, over 972651.06 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 17:59:40,597 INFO [train.py:715] (3/8) Epoch 19, batch 22250, loss[loss=0.1369, simple_loss=0.2044, pruned_loss=0.03472, over 4774.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2045, pruned_loss=0.02789, over 972178.57 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 18:00:20,344 INFO [train.py:715] (3/8) Epoch 19, batch 22300, loss[loss=0.1228, simple_loss=0.203, pruned_loss=0.02131, over 4826.00 frames.], tot_loss[loss=0.1298, simple_loss=0.204, pruned_loss=0.02776, over 972133.79 frames.], batch size: 27, lr: 1.16e-04
+2022-05-09 18:00:59,301 INFO [train.py:715] (3/8) Epoch 19, batch 22350, loss[loss=0.1333, simple_loss=0.195, pruned_loss=0.0358, over 4844.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2041, pruned_loss=0.02768, over 971500.15 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 18:01:38,320 INFO [train.py:715] (3/8) Epoch 19, batch 22400, loss[loss=0.1342, simple_loss=0.2054, pruned_loss=0.03152, over 4867.00 frames.], tot_loss[loss=0.1298, simple_loss=0.204, pruned_loss=0.02778, over 972017.21 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 18:02:17,607 INFO [train.py:715] (3/8) Epoch 19, batch 22450, loss[loss=0.1368, simple_loss=0.2053, pruned_loss=0.03415, over 4835.00 frames.], tot_loss[loss=0.1291, simple_loss=0.2037, pruned_loss=0.02727, over 971694.90 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:02:57,544 INFO [train.py:715] (3/8) Epoch 19, batch 22500, loss[loss=0.1464, simple_loss=0.2156, pruned_loss=0.03862, over 4854.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2043, pruned_loss=0.02739, over 971649.81 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 18:03:36,398 INFO [train.py:715] (3/8) Epoch 19, batch 22550, loss[loss=0.1372, simple_loss=0.2169, pruned_loss=0.02869, over 4923.00 frames.], tot_loss[loss=0.129, simple_loss=0.2043, pruned_loss=0.02683, over 972213.59 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 18:04:16,060 INFO [train.py:715] (3/8) Epoch 19, batch 22600, loss[loss=0.1311, simple_loss=0.2068, pruned_loss=0.02771, over 4707.00 frames.], tot_loss[loss=0.129, simple_loss=0.2039, pruned_loss=0.02708, over 971993.71 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:04:55,710 INFO [train.py:715] (3/8) Epoch 19, batch 22650, loss[loss=0.1158, simple_loss=0.1922, pruned_loss=0.01969, over 4777.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2048, pruned_loss=0.02749, over 971904.32 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 18:05:34,683 INFO [train.py:715] (3/8) Epoch 19, batch 22700, loss[loss=0.1341, simple_loss=0.2174, pruned_loss=0.02544, over 4774.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02791, over 971986.63 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 18:06:13,671 INFO [train.py:715] (3/8) Epoch 19, batch 22750, loss[loss=0.1316, simple_loss=0.2046, pruned_loss=0.02935, over 4906.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2053, pruned_loss=0.0277, over 971939.34 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 18:06:53,391 INFO [train.py:715] (3/8) Epoch 19, batch 22800, loss[loss=0.1241, simple_loss=0.2113, pruned_loss=0.01845, over 4882.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2055, pruned_loss=0.02775, over 972621.25 frames.], batch size: 20, lr: 1.16e-04
+2022-05-09 18:07:33,732 INFO [train.py:715] (3/8) Epoch 19, batch 22850, loss[loss=0.1497, simple_loss=0.2358, pruned_loss=0.03182, over 4837.00 frames.], tot_loss[loss=0.131, simple_loss=0.2061, pruned_loss=0.02789, over 972107.78 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:08:11,771 INFO [train.py:715] (3/8) Epoch 19, batch 22900, loss[loss=0.1379, simple_loss=0.2084, pruned_loss=0.03367, over 4988.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02842, over 972597.38 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 18:08:51,143 INFO [train.py:715] (3/8) Epoch 19, batch 22950, loss[loss=0.1214, simple_loss=0.1982, pruned_loss=0.02228, over 4838.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02844, over 972277.82 frames.], batch size: 27, lr: 1.16e-04
+2022-05-09 18:09:31,741 INFO [train.py:715] (3/8) Epoch 19, batch 23000, loss[loss=0.1642, simple_loss=0.2235, pruned_loss=0.0525, over 4859.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02852, over 971956.70 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 18:10:12,245 INFO [train.py:715] (3/8) Epoch 19, batch 23050, loss[loss=0.1274, simple_loss=0.2064, pruned_loss=0.02418, over 4905.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02915, over 971946.40 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 18:10:52,465 INFO [train.py:715] (3/8) Epoch 19, batch 23100, loss[loss=0.111, simple_loss=0.1778, pruned_loss=0.02211, over 4831.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02897, over 972058.89 frames.], batch size: 13, lr: 1.16e-04
+2022-05-09 18:11:33,197 INFO [train.py:715] (3/8) Epoch 19, batch 23150, loss[loss=0.1638, simple_loss=0.2421, pruned_loss=0.04268, over 4876.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02871, over 972107.80 frames.], batch size: 22, lr: 1.16e-04
+2022-05-09 18:12:14,188 INFO [train.py:715] (3/8) Epoch 19, batch 23200, loss[loss=0.1223, simple_loss=0.1992, pruned_loss=0.02277, over 4898.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.028, over 972147.29 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 18:12:53,607 INFO [train.py:715] (3/8) Epoch 19, batch 23250, loss[loss=0.1211, simple_loss=0.1952, pruned_loss=0.02347, over 4829.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02802, over 971717.54 frames.], batch size: 26, lr: 1.16e-04
+2022-05-09 18:13:34,362 INFO [train.py:715] (3/8) Epoch 19, batch 23300, loss[loss=0.1565, simple_loss=0.231, pruned_loss=0.04095, over 4758.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02861, over 971854.26 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 18:14:16,101 INFO [train.py:715] (3/8) Epoch 19, batch 23350, loss[loss=0.1348, simple_loss=0.215, pruned_loss=0.02728, over 4893.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.0287, over 972753.22 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 18:14:56,712 INFO [train.py:715] (3/8) Epoch 19, batch 23400, loss[loss=0.1366, simple_loss=0.2062, pruned_loss=0.03351, over 4808.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02925, over 971879.53 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 18:15:37,871 INFO [train.py:715] (3/8) Epoch 19, batch 23450, loss[loss=0.1444, simple_loss=0.2153, pruned_loss=0.03673, over 4834.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02878, over 972894.75 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 18:16:19,142 INFO [train.py:715] (3/8) Epoch 19, batch 23500, loss[loss=0.1667, simple_loss=0.2359, pruned_loss=0.04876, over 4848.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02847, over 972351.76 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 18:17:00,519 INFO [train.py:715] (3/8) Epoch 19, batch 23550, loss[loss=0.133, simple_loss=0.2098, pruned_loss=0.02805, over 4710.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02815, over 971611.53 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:17:41,324 INFO [train.py:715] (3/8) Epoch 19, batch 23600, loss[loss=0.1265, simple_loss=0.1988, pruned_loss=0.02708, over 4685.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02846, over 970821.88 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:18:22,141 INFO [train.py:715] (3/8) Epoch 19, batch 23650, loss[loss=0.139, simple_loss=0.2135, pruned_loss=0.03224, over 4917.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02844, over 970707.39 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 18:19:04,126 INFO [train.py:715] (3/8) Epoch 19, batch 23700, loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.03501, over 4708.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02854, over 970930.67 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:19:44,516 INFO [train.py:715] (3/8) Epoch 19, batch 23750, loss[loss=0.1544, simple_loss=0.2354, pruned_loss=0.03669, over 4782.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2051, pruned_loss=0.02853, over 971626.31 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 18:20:24,719 INFO [train.py:715] (3/8) Epoch 19, batch 23800, loss[loss=0.1143, simple_loss=0.2001, pruned_loss=0.01425, over 4814.00 frames.], tot_loss[loss=0.131, simple_loss=0.2049, pruned_loss=0.02856, over 971836.42 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 18:21:05,133 INFO [train.py:715] (3/8) Epoch 19, batch 23850, loss[loss=0.1058, simple_loss=0.1843, pruned_loss=0.01368, over 4919.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02829, over 971411.30 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 18:21:45,590 INFO [train.py:715] (3/8) Epoch 19, batch 23900, loss[loss=0.1237, simple_loss=0.1989, pruned_loss=0.0242, over 4782.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02828, over 971206.68 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 18:22:24,879 INFO [train.py:715] (3/8) Epoch 19, batch 23950, loss[loss=0.1563, simple_loss=0.2351, pruned_loss=0.03879, over 4901.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02832, over 971105.86 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 18:23:05,247 INFO [train.py:715] (3/8) Epoch 19, batch 24000, loss[loss=0.1452, simple_loss=0.2273, pruned_loss=0.03152, over 4816.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2047, pruned_loss=0.02813, over 971043.09 frames.], batch size: 26, lr: 1.16e-04
+2022-05-09 18:23:05,248 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 18:23:15,157 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01073, over 914524.00 frames.
+2022-05-09 18:23:55,485 INFO [train.py:715] (3/8) Epoch 19, batch 24050, loss[loss=0.1159, simple_loss=0.1862, pruned_loss=0.02284, over 4960.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2043, pruned_loss=0.0282, over 971401.65 frames.], batch size: 24, lr: 1.16e-04
+2022-05-09 18:24:36,271 INFO [train.py:715] (3/8) Epoch 19, batch 24100, loss[loss=0.1117, simple_loss=0.1934, pruned_loss=0.015, over 4804.00 frames.], tot_loss[loss=0.1289, simple_loss=0.2031, pruned_loss=0.02735, over 971140.00 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 18:25:16,110 INFO [train.py:715] (3/8) Epoch 19, batch 24150, loss[loss=0.1309, simple_loss=0.202, pruned_loss=0.02991, over 4909.00 frames.], tot_loss[loss=0.1294, simple_loss=0.2039, pruned_loss=0.02746, over 971248.31 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 18:25:56,276 INFO [train.py:715] (3/8) Epoch 19, batch 24200, loss[loss=0.1181, simple_loss=0.2015, pruned_loss=0.01739, over 4945.00 frames.], tot_loss[loss=0.1289, simple_loss=0.2034, pruned_loss=0.02724, over 970609.88 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 18:26:36,611 INFO [train.py:715] (3/8) Epoch 19, batch 24250, loss[loss=0.1546, simple_loss=0.2344, pruned_loss=0.03744, over 4839.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02821, over 971813.06 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:27:17,346 INFO [train.py:715] (3/8) Epoch 19, batch 24300, loss[loss=0.127, simple_loss=0.204, pruned_loss=0.02499, over 4771.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02847, over 971694.35 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 18:27:56,392 INFO [train.py:715] (3/8) Epoch 19, batch 24350, loss[loss=0.1059, simple_loss=0.1836, pruned_loss=0.01404, over 4791.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02837, over 971734.48 frames.], batch size: 12, lr: 1.16e-04
+2022-05-09 18:28:36,035 INFO [train.py:715] (3/8) Epoch 19, batch 24400, loss[loss=0.1167, simple_loss=0.1877, pruned_loss=0.0228, over 4817.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02862, over 971827.77 frames.], batch size: 13, lr: 1.16e-04
+2022-05-09 18:29:16,437 INFO [train.py:715] (3/8) Epoch 19, batch 24450, loss[loss=0.1501, simple_loss=0.2257, pruned_loss=0.03724, over 4891.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02818, over 971414.71 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 18:29:55,850 INFO [train.py:715] (3/8) Epoch 19, batch 24500, loss[loss=0.1501, simple_loss=0.216, pruned_loss=0.0421, over 4850.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2044, pruned_loss=0.02751, over 971719.84 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 18:30:34,370 INFO [train.py:715] (3/8) Epoch 19, batch 24550, loss[loss=0.1406, simple_loss=0.2199, pruned_loss=0.03068, over 4960.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2054, pruned_loss=0.02774, over 971039.24 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:31:13,262 INFO [train.py:715] (3/8) Epoch 19, batch 24600, loss[loss=0.1377, simple_loss=0.1972, pruned_loss=0.03909, over 4861.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02856, over 972016.79 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 18:31:52,757 INFO [train.py:715] (3/8) Epoch 19, batch 24650, loss[loss=0.1564, simple_loss=0.219, pruned_loss=0.04691, over 4846.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02865, over 971776.80 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 18:32:31,485 INFO [train.py:715] (3/8) Epoch 19, batch 24700, loss[loss=0.1275, simple_loss=0.2082, pruned_loss=0.02341, over 4814.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02859, over 971751.67 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 18:33:10,028 INFO [train.py:715] (3/8) Epoch 19, batch 24750, loss[loss=0.1237, simple_loss=0.2034, pruned_loss=0.02202, over 4807.00 frames.], tot_loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.02841, over 971708.84 frames.], batch size: 25, lr: 1.16e-04
+2022-05-09 18:33:50,380 INFO [train.py:715] (3/8) Epoch 19, batch 24800, loss[loss=0.1266, simple_loss=0.1928, pruned_loss=0.03016, over 4928.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2049, pruned_loss=0.02806, over 971384.79 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 18:34:30,018 INFO [train.py:715] (3/8) Epoch 19, batch 24850, loss[loss=0.126, simple_loss=0.2123, pruned_loss=0.01983, over 4823.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2045, pruned_loss=0.02784, over 971431.75 frames.], batch size: 27, lr: 1.16e-04
+2022-05-09 18:35:09,084 INFO [train.py:715] (3/8) Epoch 19, batch 24900, loss[loss=0.1435, simple_loss=0.2199, pruned_loss=0.03358, over 4829.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02819, over 972344.84 frames.], batch size: 26, lr: 1.16e-04
+2022-05-09 18:35:48,550 INFO [train.py:715] (3/8) Epoch 19, batch 24950, loss[loss=0.151, simple_loss=0.2215, pruned_loss=0.04025, over 4909.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02843, over 973450.72 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 18:36:28,350 INFO [train.py:715] (3/8) Epoch 19, batch 25000, loss[loss=0.1161, simple_loss=0.1904, pruned_loss=0.02084, over 4740.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02868, over 974078.22 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 18:37:07,182 INFO [train.py:715] (3/8) Epoch 19, batch 25050, loss[loss=0.1235, simple_loss=0.1916, pruned_loss=0.02768, over 4801.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02844, over 973639.10 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 18:37:46,486 INFO [train.py:715] (3/8) Epoch 19, batch 25100, loss[loss=0.1173, simple_loss=0.1961, pruned_loss=0.01924, over 4928.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02826, over 973945.42 frames.], batch size: 23, lr: 1.16e-04
+2022-05-09 18:38:26,082 INFO [train.py:715] (3/8) Epoch 19, batch 25150, loss[loss=0.1398, simple_loss=0.2205, pruned_loss=0.02949, over 4912.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02859, over 973391.40 frames.], batch size: 39, lr: 1.16e-04
+2022-05-09 18:39:05,717 INFO [train.py:715] (3/8) Epoch 19, batch 25200, loss[loss=0.1227, simple_loss=0.2017, pruned_loss=0.0218, over 4798.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02862, over 973104.83 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 18:39:44,332 INFO [train.py:715] (3/8) Epoch 19, batch 25250, loss[loss=0.1185, simple_loss=0.1944, pruned_loss=0.02124, over 4792.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02882, over 972544.57 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 18:40:23,572 INFO [train.py:715] (3/8) Epoch 19, batch 25300, loss[loss=0.1484, simple_loss=0.216, pruned_loss=0.04035, over 4863.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02847, over 972227.73 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 18:41:03,216 INFO [train.py:715] (3/8) Epoch 19, batch 25350, loss[loss=0.1413, simple_loss=0.2273, pruned_loss=0.02763, over 4861.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02876, over 971897.32 frames.], batch size: 20, lr: 1.16e-04
+2022-05-09 18:41:42,428 INFO [train.py:715] (3/8) Epoch 19, batch 25400, loss[loss=0.1317, simple_loss=0.1971, pruned_loss=0.03318, over 4879.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2064, pruned_loss=0.02832, over 971782.39 frames.], batch size: 22, lr: 1.16e-04
+2022-05-09 18:42:21,494 INFO [train.py:715] (3/8) Epoch 19, batch 25450, loss[loss=0.1203, simple_loss=0.1991, pruned_loss=0.02069, over 4822.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02833, over 972743.24 frames.], batch size: 26, lr: 1.16e-04
+2022-05-09 18:43:00,714 INFO [train.py:715] (3/8) Epoch 19, batch 25500, loss[loss=0.1501, simple_loss=0.2276, pruned_loss=0.03627, over 4888.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.0285, over 972828.84 frames.], batch size: 22, lr: 1.16e-04
+2022-05-09 18:43:39,821 INFO [train.py:715] (3/8) Epoch 19, batch 25550, loss[loss=0.12, simple_loss=0.1918, pruned_loss=0.02415, over 4811.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2073, pruned_loss=0.02869, over 973204.51 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 18:44:18,031 INFO [train.py:715] (3/8) Epoch 19, batch 25600, loss[loss=0.1454, simple_loss=0.2214, pruned_loss=0.03471, over 4949.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02861, over 972711.69 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 18:44:56,958 INFO [train.py:715] (3/8) Epoch 19, batch 25650, loss[loss=0.1347, simple_loss=0.2139, pruned_loss=0.02774, over 4917.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02876, over 973132.27 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 18:45:36,003 INFO [train.py:715] (3/8) Epoch 19, batch 25700, loss[loss=0.1061, simple_loss=0.1775, pruned_loss=0.01734, over 4733.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02856, over 972778.85 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 18:46:14,565 INFO [train.py:715] (3/8) Epoch 19, batch 25750, loss[loss=0.1405, simple_loss=0.2138, pruned_loss=0.03354, over 4765.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02867, over 972547.80 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 18:46:53,571 INFO [train.py:715] (3/8) Epoch 19, batch 25800, loss[loss=0.133, simple_loss=0.2042, pruned_loss=0.0309, over 4988.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02815, over 971734.02 frames.], batch size: 31, lr: 1.16e-04
+2022-05-09 18:47:32,967 INFO [train.py:715] (3/8) Epoch 19, batch 25850, loss[loss=0.121, simple_loss=0.1917, pruned_loss=0.02513, over 4851.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.02802, over 972176.29 frames.], batch size: 20, lr: 1.16e-04
+2022-05-09 18:48:12,299 INFO [train.py:715] (3/8) Epoch 19, batch 25900, loss[loss=0.1141, simple_loss=0.192, pruned_loss=0.01813, over 4867.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02821, over 971461.81 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 18:48:50,877 INFO [train.py:715] (3/8) Epoch 19, batch 25950, loss[loss=0.176, simple_loss=0.2597, pruned_loss=0.04612, over 4969.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02881, over 971186.44 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 18:49:30,499 INFO [train.py:715] (3/8) Epoch 19, batch 26000, loss[loss=0.1505, simple_loss=0.2252, pruned_loss=0.03797, over 4702.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2047, pruned_loss=0.02813, over 971171.17 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:50:10,476 INFO [train.py:715] (3/8) Epoch 19, batch 26050, loss[loss=0.1563, simple_loss=0.2256, pruned_loss=0.04351, over 4858.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02869, over 971434.18 frames.], batch size: 20, lr: 1.16e-04
+2022-05-09 18:50:49,157 INFO [train.py:715] (3/8) Epoch 19, batch 26100, loss[loss=0.1376, simple_loss=0.2167, pruned_loss=0.02927, over 4757.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.0285, over 971786.68 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 18:51:28,555 INFO [train.py:715] (3/8) Epoch 19, batch 26150, loss[loss=0.1139, simple_loss=0.1868, pruned_loss=0.02047, over 4862.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02872, over 971729.65 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 18:52:07,554 INFO [train.py:715] (3/8) Epoch 19, batch 26200, loss[loss=0.1644, simple_loss=0.2421, pruned_loss=0.04333, over 4985.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02879, over 972227.98 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 18:52:47,075 INFO [train.py:715] (3/8) Epoch 19, batch 26250, loss[loss=0.1306, simple_loss=0.2015, pruned_loss=0.02989, over 4799.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2054, pruned_loss=0.02879, over 972541.52 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 18:53:25,456 INFO [train.py:715] (3/8) Epoch 19, batch 26300, loss[loss=0.1321, simple_loss=0.2095, pruned_loss=0.02741, over 4977.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02849, over 973307.97 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:54:04,838 INFO [train.py:715] (3/8) Epoch 19, batch 26350, loss[loss=0.1289, simple_loss=0.2061, pruned_loss=0.02581, over 4838.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2046, pruned_loss=0.02784, over 973541.45 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:54:44,060 INFO [train.py:715] (3/8) Epoch 19, batch 26400, loss[loss=0.1627, simple_loss=0.2317, pruned_loss=0.04684, over 4892.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02826, over 973094.27 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 18:55:23,156 INFO [train.py:715] (3/8) Epoch 19, batch 26450, loss[loss=0.1316, simple_loss=0.2046, pruned_loss=0.02931, over 4901.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02819, over 972358.48 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 18:56:02,216 INFO [train.py:715] (3/8) Epoch 19, batch 26500, loss[loss=0.1308, simple_loss=0.2081, pruned_loss=0.02674, over 4838.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02838, over 972172.04 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 18:56:40,881 INFO [train.py:715] (3/8) Epoch 19, batch 26550, loss[loss=0.1509, simple_loss=0.2287, pruned_loss=0.03654, over 4743.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.0283, over 971679.92 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 18:57:21,641 INFO [train.py:715] (3/8) Epoch 19, batch 26600, loss[loss=0.1247, simple_loss=0.2016, pruned_loss=0.02387, over 4901.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2067, pruned_loss=0.02831, over 971753.75 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 18:58:02,781 INFO [train.py:715] (3/8) Epoch 19, batch 26650, loss[loss=0.1104, simple_loss=0.1887, pruned_loss=0.0161, over 4795.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02856, over 971736.65 frames.], batch size: 24, lr: 1.16e-04
+2022-05-09 18:58:41,694 INFO [train.py:715] (3/8) Epoch 19, batch 26700, loss[loss=0.1377, simple_loss=0.2059, pruned_loss=0.03472, over 4824.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02814, over 971052.95 frames.], batch size: 26, lr: 1.16e-04
+2022-05-09 18:59:21,011 INFO [train.py:715] (3/8) Epoch 19, batch 26750, loss[loss=0.1673, simple_loss=0.2335, pruned_loss=0.05049, over 4907.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2069, pruned_loss=0.02841, over 971057.65 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 19:00:00,954 INFO [train.py:715] (3/8) Epoch 19, batch 26800, loss[loss=0.1248, simple_loss=0.1847, pruned_loss=0.03243, over 4783.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.0286, over 970700.53 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 19:00:41,175 INFO [train.py:715] (3/8) Epoch 19, batch 26850, loss[loss=0.1128, simple_loss=0.1864, pruned_loss=0.01955, over 4914.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2065, pruned_loss=0.02817, over 972034.41 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 19:01:20,366 INFO [train.py:715] (3/8) Epoch 19, batch 26900, loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02886, over 4897.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2063, pruned_loss=0.0281, over 972056.98 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 19:02:00,250 INFO [train.py:715] (3/8) Epoch 19, batch 26950, loss[loss=0.1363, simple_loss=0.2086, pruned_loss=0.03202, over 4768.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02842, over 972447.21 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 19:02:39,714 INFO [train.py:715] (3/8) Epoch 19, batch 27000, loss[loss=0.1468, simple_loss=0.2148, pruned_loss=0.03938, over 4750.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02875, over 971889.77 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 19:02:39,714 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 19:02:49,598 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1047, simple_loss=0.1878, pruned_loss=0.0108, over 914524.00 frames.
+2022-05-09 19:03:29,468 INFO [train.py:715] (3/8) Epoch 19, batch 27050, loss[loss=0.16, simple_loss=0.2395, pruned_loss=0.04028, over 4902.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02924, over 971410.89 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 19:04:09,792 INFO [train.py:715] (3/8) Epoch 19, batch 27100, loss[loss=0.1301, simple_loss=0.1891, pruned_loss=0.03556, over 4989.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02903, over 970956.64 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 19:04:50,658 INFO [train.py:715] (3/8) Epoch 19, batch 27150, loss[loss=0.1085, simple_loss=0.1788, pruned_loss=0.01912, over 4928.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02934, over 971504.24 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 19:05:30,590 INFO [train.py:715] (3/8) Epoch 19, batch 27200, loss[loss=0.1514, simple_loss=0.2282, pruned_loss=0.03736, over 4877.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02901, over 970964.10 frames.], batch size: 22, lr: 1.16e-04
+2022-05-09 19:06:11,127 INFO [train.py:715] (3/8) Epoch 19, batch 27250, loss[loss=0.1284, simple_loss=0.2112, pruned_loss=0.02277, over 4944.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02899, over 971053.92 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 19:06:52,923 INFO [train.py:715] (3/8) Epoch 19, batch 27300, loss[loss=0.1392, simple_loss=0.2157, pruned_loss=0.0314, over 4813.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02886, over 971817.04 frames.], batch size: 25, lr: 1.16e-04
+2022-05-09 19:07:33,647 INFO [train.py:715] (3/8) Epoch 19, batch 27350, loss[loss=0.1462, simple_loss=0.2273, pruned_loss=0.03259, over 4874.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02916, over 971942.56 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 19:08:14,910 INFO [train.py:715] (3/8) Epoch 19, batch 27400, loss[loss=0.1283, simple_loss=0.1972, pruned_loss=0.02969, over 4913.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.0288, over 972682.84 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 19:08:54,852 INFO [train.py:715] (3/8) Epoch 19, batch 27450, loss[loss=0.1288, simple_loss=0.2041, pruned_loss=0.02679, over 4963.00 frames.], tot_loss[loss=0.132, simple_loss=0.2069, pruned_loss=0.02854, over 972428.21 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 19:09:36,479 INFO [train.py:715] (3/8) Epoch 19, batch 27500, loss[loss=0.1234, simple_loss=0.2063, pruned_loss=0.02022, over 4918.00 frames.], tot_loss[loss=0.1319, simple_loss=0.207, pruned_loss=0.02843, over 972642.19 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 19:10:17,082 INFO [train.py:715] (3/8) Epoch 19, batch 27550, loss[loss=0.1526, simple_loss=0.2354, pruned_loss=0.03484, over 4759.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02869, over 973013.63 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 19:10:57,700 INFO [train.py:715] (3/8) Epoch 19, batch 27600, loss[loss=0.1188, simple_loss=0.1934, pruned_loss=0.02213, over 4942.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02866, over 973479.04 frames.], batch size: 23, lr: 1.16e-04
+2022-05-09 19:11:38,777 INFO [train.py:715] (3/8) Epoch 19, batch 27650, loss[loss=0.1523, simple_loss=0.2223, pruned_loss=0.04113, over 4790.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2073, pruned_loss=0.02869, over 973099.23 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 19:12:19,403 INFO [train.py:715] (3/8) Epoch 19, batch 27700, loss[loss=0.137, simple_loss=0.2075, pruned_loss=0.03324, over 4887.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2059, pruned_loss=0.02812, over 973067.08 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 19:13:00,035 INFO [train.py:715] (3/8) Epoch 19, batch 27750, loss[loss=0.122, simple_loss=0.1996, pruned_loss=0.02222, over 4990.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2052, pruned_loss=0.02785, over 973201.33 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 19:13:40,112 INFO [train.py:715] (3/8) Epoch 19, batch 27800, loss[loss=0.1298, simple_loss=0.198, pruned_loss=0.03078, over 4992.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2049, pruned_loss=0.02783, over 973485.80 frames.], batch size: 31, lr: 1.16e-04
+2022-05-09 19:14:21,133 INFO [train.py:715] (3/8) Epoch 19, batch 27850, loss[loss=0.1074, simple_loss=0.1784, pruned_loss=0.01817, over 4663.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02832, over 972302.23 frames.], batch size: 13, lr: 1.16e-04
+2022-05-09 19:15:01,163 INFO [train.py:715] (3/8) Epoch 19, batch 27900, loss[loss=0.1429, simple_loss=0.2209, pruned_loss=0.03245, over 4782.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02835, over 972040.11 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 19:15:41,282 INFO [train.py:715] (3/8) Epoch 19, batch 27950, loss[loss=0.1308, simple_loss=0.206, pruned_loss=0.02777, over 4867.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02837, over 971272.07 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 19:16:21,259 INFO [train.py:715] (3/8) Epoch 19, batch 28000, loss[loss=0.144, simple_loss=0.2084, pruned_loss=0.03983, over 4876.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02831, over 971696.29 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 19:17:02,093 INFO [train.py:715] (3/8) Epoch 19, batch 28050, loss[loss=0.1364, simple_loss=0.2135, pruned_loss=0.02964, over 4982.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02803, over 971574.24 frames.], batch size: 28, lr: 1.16e-04
+2022-05-09 19:17:42,532 INFO [train.py:715] (3/8) Epoch 19, batch 28100, loss[loss=0.1189, simple_loss=0.1899, pruned_loss=0.02398, over 4935.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02861, over 972465.39 frames.], batch size: 23, lr: 1.16e-04
+2022-05-09 19:18:22,476 INFO [train.py:715] (3/8) Epoch 19, batch 28150, loss[loss=0.1121, simple_loss=0.1805, pruned_loss=0.02187, over 4645.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02843, over 972762.17 frames.], batch size: 13, lr: 1.16e-04
+2022-05-09 19:19:02,903 INFO [train.py:715] (3/8) Epoch 19, batch 28200, loss[loss=0.1425, simple_loss=0.2086, pruned_loss=0.03817, over 4843.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02879, over 971485.21 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 19:19:42,612 INFO [train.py:715] (3/8) Epoch 19, batch 28250, loss[loss=0.146, simple_loss=0.2161, pruned_loss=0.0379, over 4965.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02891, over 971515.51 frames.], batch size: 24, lr: 1.16e-04
+2022-05-09 19:20:22,517 INFO [train.py:715] (3/8) Epoch 19, batch 28300, loss[loss=0.1405, simple_loss=0.213, pruned_loss=0.03394, over 4800.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02859, over 972011.87 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 19:21:02,196 INFO [train.py:715] (3/8) Epoch 19, batch 28350, loss[loss=0.1407, simple_loss=0.2114, pruned_loss=0.03501, over 4855.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02852, over 972437.56 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 19:21:42,213 INFO [train.py:715] (3/8) Epoch 19, batch 28400, loss[loss=0.1399, simple_loss=0.2142, pruned_loss=0.03284, over 4934.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02848, over 972588.75 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 19:22:22,332 INFO [train.py:715] (3/8) Epoch 19, batch 28450, loss[loss=0.1241, simple_loss=0.2095, pruned_loss=0.01933, over 4879.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02842, over 972652.18 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 19:23:02,155 INFO [train.py:715] (3/8) Epoch 19, batch 28500, loss[loss=0.1366, simple_loss=0.2182, pruned_loss=0.02747, over 4875.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2072, pruned_loss=0.02872, over 973166.79 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 19:23:42,829 INFO [train.py:715] (3/8) Epoch 19, batch 28550, loss[loss=0.1084, simple_loss=0.1749, pruned_loss=0.02098, over 4805.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02857, over 972746.13 frames.], batch size: 13, lr: 1.16e-04
+2022-05-09 19:24:22,312 INFO [train.py:715] (3/8) Epoch 19, batch 28600, loss[loss=0.1187, simple_loss=0.2002, pruned_loss=0.01862, over 4803.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02859, over 972757.00 frames.], batch size: 13, lr: 1.16e-04
+2022-05-09 19:25:02,350 INFO [train.py:715] (3/8) Epoch 19, batch 28650, loss[loss=0.1405, simple_loss=0.2106, pruned_loss=0.03522, over 4817.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2077, pruned_loss=0.02911, over 973557.58 frames.], batch size: 26, lr: 1.16e-04
+2022-05-09 19:25:43,119 INFO [train.py:715] (3/8) Epoch 19, batch 28700, loss[loss=0.1285, simple_loss=0.1961, pruned_loss=0.03047, over 4855.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02848, over 974688.45 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 19:26:22,653 INFO [train.py:715] (3/8) Epoch 19, batch 28750, loss[loss=0.1345, simple_loss=0.211, pruned_loss=0.02902, over 4974.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02833, over 975053.37 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 19:27:02,563 INFO [train.py:715] (3/8) Epoch 19, batch 28800, loss[loss=0.1399, simple_loss=0.2087, pruned_loss=0.03556, over 4981.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.0285, over 974379.52 frames.], batch size: 39, lr: 1.16e-04
+2022-05-09 19:27:41,940 INFO [train.py:715] (3/8) Epoch 19, batch 28850, loss[loss=0.1134, simple_loss=0.1924, pruned_loss=0.01722, over 4974.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.0285, over 973801.98 frames.], batch size: 24, lr: 1.16e-04
+2022-05-09 19:28:21,325 INFO [train.py:715] (3/8) Epoch 19, batch 28900, loss[loss=0.1533, simple_loss=0.2219, pruned_loss=0.0423, over 4935.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02817, over 973053.45 frames.], batch size: 35, lr: 1.16e-04
+2022-05-09 19:28:59,435 INFO [train.py:715] (3/8) Epoch 19, batch 28950, loss[loss=0.1446, simple_loss=0.2142, pruned_loss=0.03753, over 4850.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.0283, over 973421.27 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 19:29:38,325 INFO [train.py:715] (3/8) Epoch 19, batch 29000, loss[loss=0.1273, simple_loss=0.1999, pruned_loss=0.02731, over 4879.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02822, over 972833.58 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 19:30:17,557 INFO [train.py:715] (3/8) Epoch 19, batch 29050, loss[loss=0.1439, simple_loss=0.2244, pruned_loss=0.03172, over 4808.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02827, over 972837.97 frames.], batch size: 25, lr: 1.16e-04
+2022-05-09 19:30:56,438 INFO [train.py:715] (3/8) Epoch 19, batch 29100, loss[loss=0.1351, simple_loss=0.2098, pruned_loss=0.03018, over 4931.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.0283, over 973163.87 frames.], batch size: 23, lr: 1.16e-04
+2022-05-09 19:31:35,383 INFO [train.py:715] (3/8) Epoch 19, batch 29150, loss[loss=0.1479, simple_loss=0.2154, pruned_loss=0.04021, over 4786.00 frames.], tot_loss[loss=0.1299, simple_loss=0.204, pruned_loss=0.02785, over 972509.35 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 19:32:14,167 INFO [train.py:715] (3/8) Epoch 19, batch 29200, loss[loss=0.1414, simple_loss=0.2119, pruned_loss=0.03547, over 4855.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2038, pruned_loss=0.02768, over 972135.25 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 19:32:53,530 INFO [train.py:715] (3/8) Epoch 19, batch 29250, loss[loss=0.1407, simple_loss=0.2124, pruned_loss=0.03447, over 4897.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2039, pruned_loss=0.02771, over 972389.03 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 19:33:32,160 INFO [train.py:715] (3/8) Epoch 19, batch 29300, loss[loss=0.1389, simple_loss=0.2252, pruned_loss=0.02637, over 4980.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2047, pruned_loss=0.02805, over 973112.67 frames.], batch size: 25, lr: 1.16e-04
+2022-05-09 19:34:11,674 INFO [train.py:715] (3/8) Epoch 19, batch 29350, loss[loss=0.1158, simple_loss=0.1908, pruned_loss=0.02039, over 4980.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2047, pruned_loss=0.02788, over 973061.80 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 19:34:50,605 INFO [train.py:715] (3/8) Epoch 19, batch 29400, loss[loss=0.1675, simple_loss=0.241, pruned_loss=0.04695, over 4841.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2044, pruned_loss=0.02816, over 972388.26 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 19:35:29,742 INFO [train.py:715] (3/8) Epoch 19, batch 29450, loss[loss=0.1234, simple_loss=0.2117, pruned_loss=0.0176, over 4987.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2049, pruned_loss=0.02825, over 972875.36 frames.], batch size: 28, lr: 1.16e-04
+2022-05-09 19:36:09,169 INFO [train.py:715] (3/8) Epoch 19, batch 29500, loss[loss=0.1069, simple_loss=0.1854, pruned_loss=0.01413, over 4811.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02855, over 972411.87 frames.], batch size: 25, lr: 1.16e-04
+2022-05-09 19:36:48,559 INFO [train.py:715] (3/8) Epoch 19, batch 29550, loss[loss=0.1235, simple_loss=0.1909, pruned_loss=0.02808, over 4915.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02845, over 971574.37 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 19:37:28,170 INFO [train.py:715] (3/8) Epoch 19, batch 29600, loss[loss=0.1408, simple_loss=0.2127, pruned_loss=0.03448, over 4773.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02894, over 971209.35 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 19:38:07,302 INFO [train.py:715] (3/8) Epoch 19, batch 29650, loss[loss=0.1573, simple_loss=0.2335, pruned_loss=0.04051, over 4903.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02881, over 970961.71 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 19:38:47,452 INFO [train.py:715] (3/8) Epoch 19, batch 29700, loss[loss=0.1307, simple_loss=0.2036, pruned_loss=0.02891, over 4820.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.0286, over 972005.74 frames.], batch size: 12, lr: 1.16e-04
+2022-05-09 19:39:26,744 INFO [train.py:715] (3/8) Epoch 19, batch 29750, loss[loss=0.141, simple_loss=0.2036, pruned_loss=0.03922, over 4689.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02829, over 971798.87 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 19:40:06,089 INFO [train.py:715] (3/8) Epoch 19, batch 29800, loss[loss=0.1236, simple_loss=0.2024, pruned_loss=0.02244, over 4790.00 frames.], tot_loss[loss=0.131, simple_loss=0.206, pruned_loss=0.02807, over 971952.63 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 19:40:45,393 INFO [train.py:715] (3/8) Epoch 19, batch 29850, loss[loss=0.1463, simple_loss=0.2275, pruned_loss=0.03252, over 4879.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02838, over 971166.57 frames.], batch size: 22, lr: 1.16e-04
+2022-05-09 19:41:24,808 INFO [train.py:715] (3/8) Epoch 19, batch 29900, loss[loss=0.1438, simple_loss=0.2188, pruned_loss=0.03436, over 4820.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02857, over 972172.37 frames.], batch size: 25, lr: 1.16e-04
+2022-05-09 19:42:04,769 INFO [train.py:715] (3/8) Epoch 19, batch 29950, loss[loss=0.09904, simple_loss=0.1729, pruned_loss=0.01256, over 4914.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2068, pruned_loss=0.0283, over 972462.80 frames.], batch size: 23, lr: 1.16e-04
+2022-05-09 19:42:43,616 INFO [train.py:715] (3/8) Epoch 19, batch 30000, loss[loss=0.1277, simple_loss=0.1989, pruned_loss=0.02821, over 4737.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02809, over 972410.95 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 19:42:43,617 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 19:42:53,507 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1877, pruned_loss=0.01067, over 914524.00 frames.
+2022-05-09 19:43:32,627 INFO [train.py:715] (3/8) Epoch 19, batch 30050, loss[loss=0.1447, simple_loss=0.222, pruned_loss=0.03367, over 4922.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02846, over 972677.05 frames.], batch size: 23, lr: 1.16e-04
+2022-05-09 19:44:12,190 INFO [train.py:715] (3/8) Epoch 19, batch 30100, loss[loss=0.1253, simple_loss=0.2062, pruned_loss=0.02225, over 4818.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02851, over 972957.03 frames.], batch size: 27, lr: 1.16e-04
+2022-05-09 19:44:51,310 INFO [train.py:715] (3/8) Epoch 19, batch 30150, loss[loss=0.1337, simple_loss=0.2013, pruned_loss=0.033, over 4832.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02851, over 973601.80 frames.], batch size: 30, lr: 1.16e-04
+2022-05-09 19:45:31,085 INFO [train.py:715] (3/8) Epoch 19, batch 30200, loss[loss=0.1445, simple_loss=0.2183, pruned_loss=0.03538, over 4878.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02886, over 972862.79 frames.], batch size: 20, lr: 1.16e-04
+2022-05-09 19:46:09,574 INFO [train.py:715] (3/8) Epoch 19, batch 30250, loss[loss=0.1278, simple_loss=0.2051, pruned_loss=0.02525, over 4927.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02895, over 973109.07 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 19:46:48,894 INFO [train.py:715] (3/8) Epoch 19, batch 30300, loss[loss=0.148, simple_loss=0.2159, pruned_loss=0.0401, over 4983.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02892, over 972915.49 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 19:47:28,482 INFO [train.py:715] (3/8) Epoch 19, batch 30350, loss[loss=0.1202, simple_loss=0.197, pruned_loss=0.02173, over 4888.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02861, over 972619.25 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 19:48:08,093 INFO [train.py:715] (3/8) Epoch 19, batch 30400, loss[loss=0.1151, simple_loss=0.1845, pruned_loss=0.02281, over 4901.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02862, over 973070.57 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 19:48:47,854 INFO [train.py:715] (3/8) Epoch 19, batch 30450, loss[loss=0.1327, simple_loss=0.2081, pruned_loss=0.02859, over 4875.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02904, over 972702.85 frames.], batch size: 22, lr: 1.16e-04
+2022-05-09 19:49:26,660 INFO [train.py:715] (3/8) Epoch 19, batch 30500, loss[loss=0.116, simple_loss=0.2007, pruned_loss=0.01568, over 4790.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02883, over 971801.79 frames.], batch size: 24, lr: 1.16e-04
+2022-05-09 19:50:06,593 INFO [train.py:715] (3/8) Epoch 19, batch 30550, loss[loss=0.1428, simple_loss=0.2233, pruned_loss=0.03117, over 4870.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02876, over 971604.88 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 19:50:45,746 INFO [train.py:715] (3/8) Epoch 19, batch 30600, loss[loss=0.1322, simple_loss=0.208, pruned_loss=0.02819, over 4916.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02876, over 972396.36 frames.], batch size: 23, lr: 1.16e-04
+2022-05-09 19:51:25,827 INFO [train.py:715] (3/8) Epoch 19, batch 30650, loss[loss=0.1293, simple_loss=0.2037, pruned_loss=0.02741, over 4699.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02863, over 972127.76 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 19:52:05,614 INFO [train.py:715] (3/8) Epoch 19, batch 30700, loss[loss=0.1295, simple_loss=0.2141, pruned_loss=0.0224, over 4805.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.0281, over 971648.83 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 19:52:45,190 INFO [train.py:715] (3/8) Epoch 19, batch 30750, loss[loss=0.1268, simple_loss=0.2006, pruned_loss=0.02649, over 4849.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2058, pruned_loss=0.02789, over 971729.26 frames.], batch size: 34, lr: 1.16e-04
+2022-05-09 19:53:25,712 INFO [train.py:715] (3/8) Epoch 19, batch 30800, loss[loss=0.1191, simple_loss=0.1983, pruned_loss=0.01993, over 4901.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2057, pruned_loss=0.02793, over 971551.92 frames.], batch size: 22, lr: 1.16e-04
+2022-05-09 19:54:05,656 INFO [train.py:715] (3/8) Epoch 19, batch 30850, loss[loss=0.1306, simple_loss=0.2018, pruned_loss=0.0297, over 4778.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2057, pruned_loss=0.02772, over 971439.17 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 19:54:46,448 INFO [train.py:715] (3/8) Epoch 19, batch 30900, loss[loss=0.1251, simple_loss=0.1989, pruned_loss=0.02569, over 4799.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.02802, over 971522.47 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 19:55:26,512 INFO [train.py:715] (3/8) Epoch 19, batch 30950, loss[loss=0.1433, simple_loss=0.2183, pruned_loss=0.03411, over 4748.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.0279, over 972019.06 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 19:56:07,122 INFO [train.py:715] (3/8) Epoch 19, batch 31000, loss[loss=0.1113, simple_loss=0.1887, pruned_loss=0.01695, over 4792.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2049, pruned_loss=0.02787, over 971681.21 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 19:56:47,789 INFO [train.py:715] (3/8) Epoch 19, batch 31050, loss[loss=0.1244, simple_loss=0.2021, pruned_loss=0.02329, over 4982.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02799, over 972054.14 frames.], batch size: 14, lr: 1.16e-04
+2022-05-09 19:57:28,117 INFO [train.py:715] (3/8) Epoch 19, batch 31100, loss[loss=0.1374, simple_loss=0.217, pruned_loss=0.02889, over 4893.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02804, over 972147.26 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 19:58:08,817 INFO [train.py:715] (3/8) Epoch 19, batch 31150, loss[loss=0.1268, simple_loss=0.2012, pruned_loss=0.02618, over 4751.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02838, over 971470.48 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 19:58:49,192 INFO [train.py:715] (3/8) Epoch 19, batch 31200, loss[loss=0.1355, simple_loss=0.2113, pruned_loss=0.02987, over 4770.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02849, over 971295.69 frames.], batch size: 12, lr: 1.16e-04
+2022-05-09 19:59:30,189 INFO [train.py:715] (3/8) Epoch 19, batch 31250, loss[loss=0.1036, simple_loss=0.1814, pruned_loss=0.01295, over 4851.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02865, over 971515.42 frames.], batch size: 20, lr: 1.16e-04
+2022-05-09 20:00:09,924 INFO [train.py:715] (3/8) Epoch 19, batch 31300, loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02865, over 4965.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02852, over 972375.13 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 20:00:50,568 INFO [train.py:715] (3/8) Epoch 19, batch 31350, loss[loss=0.1202, simple_loss=0.1955, pruned_loss=0.02246, over 4944.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02838, over 971039.29 frames.], batch size: 29, lr: 1.16e-04
+2022-05-09 20:01:31,162 INFO [train.py:715] (3/8) Epoch 19, batch 31400, loss[loss=0.1174, simple_loss=0.2045, pruned_loss=0.01518, over 4985.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02866, over 971817.54 frames.], batch size: 26, lr: 1.16e-04
+2022-05-09 20:02:11,466 INFO [train.py:715] (3/8) Epoch 19, batch 31450, loss[loss=0.1359, simple_loss=0.2131, pruned_loss=0.02931, over 4783.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02852, over 971937.70 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 20:02:52,731 INFO [train.py:715] (3/8) Epoch 19, batch 31500, loss[loss=0.1599, simple_loss=0.2271, pruned_loss=0.04636, over 4925.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02881, over 972319.27 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 20:03:32,848 INFO [train.py:715] (3/8) Epoch 19, batch 31550, loss[loss=0.1245, simple_loss=0.206, pruned_loss=0.02148, over 4810.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02853, over 971995.41 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 20:04:13,427 INFO [train.py:715] (3/8) Epoch 19, batch 31600, loss[loss=0.1294, simple_loss=0.2046, pruned_loss=0.02715, over 4773.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02869, over 971632.52 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 20:04:53,553 INFO [train.py:715] (3/8) Epoch 19, batch 31650, loss[loss=0.1246, simple_loss=0.2079, pruned_loss=0.02068, over 4791.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02923, over 972185.47 frames.], batch size: 21, lr: 1.16e-04
+2022-05-09 20:05:33,936 INFO [train.py:715] (3/8) Epoch 19, batch 31700, loss[loss=0.1256, simple_loss=0.1987, pruned_loss=0.02631, over 4899.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02886, over 972454.44 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 20:06:14,404 INFO [train.py:715] (3/8) Epoch 19, batch 31750, loss[loss=0.1911, simple_loss=0.2534, pruned_loss=0.06438, over 4776.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02891, over 971822.62 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 20:06:54,583 INFO [train.py:715] (3/8) Epoch 19, batch 31800, loss[loss=0.1501, simple_loss=0.2169, pruned_loss=0.04164, over 4887.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.02872, over 972715.08 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 20:07:35,677 INFO [train.py:715] (3/8) Epoch 19, batch 31850, loss[loss=0.1547, simple_loss=0.2253, pruned_loss=0.04201, over 4910.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2053, pruned_loss=0.0287, over 973132.57 frames.], batch size: 23, lr: 1.16e-04
+2022-05-09 20:08:15,979 INFO [train.py:715] (3/8) Epoch 19, batch 31900, loss[loss=0.1217, simple_loss=0.1867, pruned_loss=0.02838, over 4871.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2041, pruned_loss=0.02779, over 973616.94 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 20:08:56,574 INFO [train.py:715] (3/8) Epoch 19, batch 31950, loss[loss=0.1147, simple_loss=0.1946, pruned_loss=0.01739, over 4948.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2049, pruned_loss=0.02796, over 973556.36 frames.], batch size: 24, lr: 1.16e-04
+2022-05-09 20:09:36,643 INFO [train.py:715] (3/8) Epoch 19, batch 32000, loss[loss=0.1277, simple_loss=0.2005, pruned_loss=0.02742, over 4754.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.02796, over 973678.28 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 20:10:16,975 INFO [train.py:715] (3/8) Epoch 19, batch 32050, loss[loss=0.1341, simple_loss=0.1981, pruned_loss=0.0351, over 4759.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2049, pruned_loss=0.02787, over 973123.92 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 20:10:57,300 INFO [train.py:715] (3/8) Epoch 19, batch 32100, loss[loss=0.1365, simple_loss=0.2036, pruned_loss=0.0347, over 4957.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2049, pruned_loss=0.02808, over 973718.24 frames.], batch size: 35, lr: 1.16e-04
+2022-05-09 20:11:37,103 INFO [train.py:715] (3/8) Epoch 19, batch 32150, loss[loss=0.1329, simple_loss=0.2023, pruned_loss=0.03172, over 4844.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02866, over 973227.91 frames.], batch size: 13, lr: 1.16e-04
+2022-05-09 20:12:18,365 INFO [train.py:715] (3/8) Epoch 19, batch 32200, loss[loss=0.1381, simple_loss=0.2029, pruned_loss=0.03669, over 4974.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.02826, over 973259.36 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 20:12:58,104 INFO [train.py:715] (3/8) Epoch 19, batch 32250, loss[loss=0.1243, simple_loss=0.2028, pruned_loss=0.02288, over 4891.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02855, over 972177.16 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 20:13:38,489 INFO [train.py:715] (3/8) Epoch 19, batch 32300, loss[loss=0.1141, simple_loss=0.191, pruned_loss=0.01856, over 4804.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2045, pruned_loss=0.02806, over 971833.03 frames.], batch size: 25, lr: 1.16e-04
+2022-05-09 20:14:19,672 INFO [train.py:715] (3/8) Epoch 19, batch 32350, loss[loss=0.1114, simple_loss=0.1897, pruned_loss=0.01657, over 4831.00 frames.], tot_loss[loss=0.13, simple_loss=0.2042, pruned_loss=0.02795, over 972215.84 frames.], batch size: 15, lr: 1.16e-04
+2022-05-09 20:15:00,205 INFO [train.py:715] (3/8) Epoch 19, batch 32400, loss[loss=0.124, simple_loss=0.1935, pruned_loss=0.02727, over 4847.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2044, pruned_loss=0.028, over 972294.04 frames.], batch size: 13, lr: 1.16e-04
+2022-05-09 20:15:40,800 INFO [train.py:715] (3/8) Epoch 19, batch 32450, loss[loss=0.1228, simple_loss=0.1961, pruned_loss=0.02478, over 4963.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02853, over 972408.83 frames.], batch size: 25, lr: 1.16e-04
+2022-05-09 20:16:20,798 INFO [train.py:715] (3/8) Epoch 19, batch 32500, loss[loss=0.1395, simple_loss=0.2061, pruned_loss=0.03647, over 4868.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.0282, over 972509.03 frames.], batch size: 13, lr: 1.16e-04
+2022-05-09 20:17:01,569 INFO [train.py:715] (3/8) Epoch 19, batch 32550, loss[loss=0.131, simple_loss=0.2122, pruned_loss=0.0249, over 4736.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02859, over 972282.38 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 20:17:41,585 INFO [train.py:715] (3/8) Epoch 19, batch 32600, loss[loss=0.1193, simple_loss=0.1844, pruned_loss=0.02716, over 4888.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2052, pruned_loss=0.0278, over 972311.80 frames.], batch size: 17, lr: 1.16e-04
+2022-05-09 20:18:21,659 INFO [train.py:715] (3/8) Epoch 19, batch 32650, loss[loss=0.1377, simple_loss=0.2153, pruned_loss=0.03007, over 4944.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2054, pruned_loss=0.02768, over 972210.22 frames.], batch size: 39, lr: 1.16e-04
+2022-05-09 20:19:02,301 INFO [train.py:715] (3/8) Epoch 19, batch 32700, loss[loss=0.149, simple_loss=0.2205, pruned_loss=0.03876, over 4875.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.028, over 972400.19 frames.], batch size: 20, lr: 1.16e-04
+2022-05-09 20:19:42,121 INFO [train.py:715] (3/8) Epoch 19, batch 32750, loss[loss=0.124, simple_loss=0.2017, pruned_loss=0.02313, over 4854.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.0281, over 971829.31 frames.], batch size: 20, lr: 1.16e-04
+2022-05-09 20:20:21,840 INFO [train.py:715] (3/8) Epoch 19, batch 32800, loss[loss=0.1368, simple_loss=0.2169, pruned_loss=0.02841, over 4907.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2063, pruned_loss=0.02816, over 972245.95 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 20:21:00,655 INFO [train.py:715] (3/8) Epoch 19, batch 32850, loss[loss=0.1351, simple_loss=0.2156, pruned_loss=0.02732, over 4925.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2067, pruned_loss=0.02834, over 972361.63 frames.], batch size: 23, lr: 1.16e-04
+2022-05-09 20:21:39,681 INFO [train.py:715] (3/8) Epoch 19, batch 32900, loss[loss=0.1028, simple_loss=0.188, pruned_loss=0.00878, over 4955.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02813, over 972536.31 frames.], batch size: 24, lr: 1.16e-04
+2022-05-09 20:22:18,347 INFO [train.py:715] (3/8) Epoch 19, batch 32950, loss[loss=0.1264, simple_loss=0.2011, pruned_loss=0.02583, over 4755.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02837, over 972884.60 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 20:22:57,661 INFO [train.py:715] (3/8) Epoch 19, batch 33000, loss[loss=0.1419, simple_loss=0.2192, pruned_loss=0.03223, over 4841.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02862, over 972812.85 frames.], batch size: 20, lr: 1.16e-04
+2022-05-09 20:22:57,662 INFO [train.py:733] (3/8) Computing validation loss
+2022-05-09 20:23:07,491 INFO [train.py:742] (3/8) Epoch 19, validation: loss=0.1048, simple_loss=0.1878, pruned_loss=0.01088, over 914524.00 frames.
+2022-05-09 20:23:46,770 INFO [train.py:715] (3/8) Epoch 19, batch 33050, loss[loss=0.1425, simple_loss=0.2146, pruned_loss=0.03517, over 4837.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02902, over 972944.76 frames.], batch size: 13, lr: 1.16e-04
+2022-05-09 20:24:26,213 INFO [train.py:715] (3/8) Epoch 19, batch 33100, loss[loss=0.1439, simple_loss=0.216, pruned_loss=0.03591, over 4896.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.0289, over 972697.94 frames.], batch size: 22, lr: 1.16e-04
+2022-05-09 20:25:05,028 INFO [train.py:715] (3/8) Epoch 19, batch 33150, loss[loss=0.139, simple_loss=0.2154, pruned_loss=0.03135, over 4943.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.0286, over 972403.44 frames.], batch size: 35, lr: 1.16e-04
+2022-05-09 20:25:44,210 INFO [train.py:715] (3/8) Epoch 19, batch 33200, loss[loss=0.1298, simple_loss=0.2146, pruned_loss=0.02251, over 4878.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02875, over 972018.45 frames.], batch size: 22, lr: 1.16e-04
+2022-05-09 20:26:23,766 INFO [train.py:715] (3/8) Epoch 19, batch 33250, loss[loss=0.1323, simple_loss=0.2035, pruned_loss=0.03056, over 4854.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02894, over 972070.32 frames.], batch size: 32, lr: 1.16e-04
+2022-05-09 20:27:03,192 INFO [train.py:715] (3/8) Epoch 19, batch 33300, loss[loss=0.1476, simple_loss=0.2144, pruned_loss=0.04039, over 4954.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02894, over 973101.92 frames.], batch size: 35, lr: 1.16e-04
+2022-05-09 20:27:42,909 INFO [train.py:715] (3/8) Epoch 19, batch 33350, loss[loss=0.1152, simple_loss=0.1911, pruned_loss=0.0197, over 4819.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02904, over 971807.52 frames.], batch size: 25, lr: 1.16e-04
+2022-05-09 20:28:22,076 INFO [train.py:715] (3/8) Epoch 19, batch 33400, loss[loss=0.09827, simple_loss=0.1716, pruned_loss=0.01245, over 4762.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02832, over 972232.93 frames.], batch size: 19, lr: 1.16e-04
+2022-05-09 20:29:01,054 INFO [train.py:715] (3/8) Epoch 19, batch 33450, loss[loss=0.1162, simple_loss=0.1893, pruned_loss=0.02153, over 4754.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02836, over 971070.20 frames.], batch size: 16, lr: 1.16e-04
+2022-05-09 20:29:40,020 INFO [train.py:715] (3/8) Epoch 19, batch 33500, loss[loss=0.1372, simple_loss=0.215, pruned_loss=0.02966, over 4911.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02855, over 971072.53 frames.], batch size: 18, lr: 1.16e-04
+2022-05-09 20:30:18,903 INFO [train.py:715] (3/8) Epoch 19, batch 33550, loss[loss=0.1378, simple_loss=0.2158, pruned_loss=0.02991, over 4898.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02839, over 971666.58 frames.], batch size: 39, lr: 1.15e-04
+2022-05-09 20:30:58,231 INFO [train.py:715] (3/8) Epoch 19, batch 33600, loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03616, over 4934.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2076, pruned_loss=0.02892, over 972268.46 frames.], batch size: 29, lr: 1.15e-04
+2022-05-09 20:31:37,215 INFO [train.py:715] (3/8) Epoch 19, batch 33650, loss[loss=0.1373, simple_loss=0.2093, pruned_loss=0.03271, over 4901.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2077, pruned_loss=0.02897, over 972445.40 frames.], batch size: 19, lr: 1.15e-04
+2022-05-09 20:32:16,616 INFO [train.py:715] (3/8) Epoch 19, batch 33700, loss[loss=0.1201, simple_loss=0.1945, pruned_loss=0.0229, over 4947.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02919, over 972445.91 frames.], batch size: 21, lr: 1.15e-04
+2022-05-09 20:32:55,331 INFO [train.py:715] (3/8) Epoch 19, batch 33750, loss[loss=0.1334, simple_loss=0.2149, pruned_loss=0.02597, over 4930.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02855, over 971955.73 frames.], batch size: 23, lr: 1.15e-04
+2022-05-09 20:33:34,124 INFO [train.py:715] (3/8) Epoch 19, batch 33800, loss[loss=0.1424, simple_loss=0.2106, pruned_loss=0.03712, over 4776.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2041, pruned_loss=0.02776, over 972015.66 frames.], batch size: 17, lr: 1.15e-04
+2022-05-09 20:34:12,733 INFO [train.py:715] (3/8) Epoch 19, batch 33850, loss[loss=0.1163, simple_loss=0.1889, pruned_loss=0.02184, over 4799.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2042, pruned_loss=0.02782, over 972100.51 frames.], batch size: 24, lr: 1.15e-04
+2022-05-09 20:34:51,527 INFO [train.py:715] (3/8) Epoch 19, batch 33900, loss[loss=0.1131, simple_loss=0.185, pruned_loss=0.02059, over 4986.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2042, pruned_loss=0.02773, over 972583.50 frames.], batch size: 15, lr: 1.15e-04
+2022-05-09 20:35:31,244 INFO [train.py:715] (3/8) Epoch 19, batch 33950, loss[loss=0.192, simple_loss=0.251, pruned_loss=0.06652, over 4954.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02812, over 972033.06 frames.], batch size: 39, lr: 1.15e-04
+2022-05-09 20:36:10,890 INFO [train.py:715] (3/8) Epoch 19, batch 34000, loss[loss=0.1275, simple_loss=0.2125, pruned_loss=0.02127, over 4802.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02815, over 971945.72 frames.], batch size: 21, lr: 1.15e-04
+2022-05-09 20:36:50,181 INFO [train.py:715] (3/8) Epoch 19, batch 34050, loss[loss=0.1527, simple_loss=0.2225, pruned_loss=0.04145, over 4831.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02848, over 973042.22 frames.], batch size: 15, lr: 1.15e-04
+2022-05-09 20:37:28,970 INFO [train.py:715] (3/8) Epoch 19, batch 34100, loss[loss=0.1317, simple_loss=0.2177, pruned_loss=0.02282, over 4915.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02835, over 972743.58 frames.], batch size: 17, lr: 1.15e-04
+2022-05-09 20:38:08,482 INFO [train.py:715] (3/8) Epoch 19, batch 34150, loss[loss=0.1364, simple_loss=0.2239, pruned_loss=0.02449, over 4789.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02844, over 973186.13 frames.], batch size: 18, lr: 1.15e-04
+2022-05-09 20:38:48,057 INFO [train.py:715] (3/8) Epoch 19, batch 34200, loss[loss=0.1148, simple_loss=0.1906, pruned_loss=0.01949, over 4817.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02842, over 973256.28 frames.], batch size: 26, lr: 1.15e-04
+2022-05-09 20:39:27,597 INFO [train.py:715] (3/8) Epoch 19, batch 34250, loss[loss=0.1182, simple_loss=0.1961, pruned_loss=0.02009, over 4778.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2047, pruned_loss=0.0279, over 972918.13 frames.], batch size: 17, lr: 1.15e-04
+2022-05-09 20:40:06,926 INFO [train.py:715] (3/8) Epoch 19, batch 34300, loss[loss=0.1347, simple_loss=0.2128, pruned_loss=0.02825, over 4866.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02797, over 972869.20 frames.], batch size: 16, lr: 1.15e-04
+2022-05-09 20:40:46,126 INFO [train.py:715] (3/8) Epoch 19, batch 34350, loss[loss=0.1289, simple_loss=0.2017, pruned_loss=0.02801, over 4939.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02819, over 973077.46 frames.], batch size: 29, lr: 1.15e-04
+2022-05-09 20:41:25,882 INFO [train.py:715] (3/8) Epoch 19, batch 34400, loss[loss=0.1403, simple_loss=0.2178, pruned_loss=0.03139, over 4932.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.0285, over 973075.40 frames.], batch size: 29, lr: 1.15e-04
+2022-05-09 20:42:05,038 INFO [train.py:715] (3/8) Epoch 19, batch 34450, loss[loss=0.1376, simple_loss=0.2069, pruned_loss=0.03415, over 4914.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02817, over 973720.86 frames.], batch size: 18, lr: 1.15e-04
+2022-05-09 20:42:44,560 INFO [train.py:715] (3/8) Epoch 19, batch 34500, loss[loss=0.1174, simple_loss=0.1934, pruned_loss=0.0207, over 4839.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02819, over 973700.01 frames.], batch size: 26, lr: 1.15e-04
+2022-05-09 20:43:24,266 INFO [train.py:715] (3/8) Epoch 19, batch 34550, loss[loss=0.1288, simple_loss=0.2168, pruned_loss=0.02043, over 4836.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02833, over 972744.62 frames.], batch size: 25, lr: 1.15e-04
+2022-05-09 20:44:03,126 INFO [train.py:715] (3/8) Epoch 19, batch 34600, loss[loss=0.1296, simple_loss=0.2058, pruned_loss=0.02664, over 4968.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02832, over 972928.46 frames.], batch size: 24, lr: 1.15e-04
+2022-05-09 20:44:45,165 INFO [train.py:715] (3/8) Epoch 19, batch 34650, loss[loss=0.1754, simple_loss=0.2354, pruned_loss=0.05773, over 4634.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.02803, over 972590.98 frames.], batch size: 13, lr: 1.15e-04
+2022-05-09 20:45:24,629 INFO [train.py:715] (3/8) Epoch 19, batch 34700, loss[loss=0.1325, simple_loss=0.2122, pruned_loss=0.02644, over 4877.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02796, over 971834.14 frames.], batch size: 16, lr: 1.15e-04
+2022-05-09 20:46:02,679 INFO [train.py:715] (3/8) Epoch 19, batch 34750, loss[loss=0.13, simple_loss=0.2037, pruned_loss=0.02812, over 4962.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02844, over 971183.57 frames.], batch size: 15, lr: 1.15e-04
+2022-05-09 20:46:39,960 INFO [train.py:715] (3/8) Epoch 19, batch 34800, loss[loss=0.1236, simple_loss=0.1999, pruned_loss=0.02363, over 4912.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02813, over 971086.38 frames.], batch size: 18, lr: 1.15e-04
+2022-05-09 20:46:48,547 INFO [train.py:915] (3/8) Done!