| { | |
| "best_metric": 0.18060417473316193, | |
| "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/kwsylgen/bart/bart-finetuned-kwsylgen-64-simple_input_BARTlarge/checkpoint-6500", | |
| "epoch": 2.3322569070685324, | |
| "eval_steps": 500, | |
| "global_step": 6500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.9277993440628052, | |
| "learning_rate": 1.8815931108719056e-05, | |
| "loss": 2.0641, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.24505409598350525, | |
| "eval_runtime": 128.1235, | |
| "eval_samples_per_second": 184.845, | |
| "eval_steps_per_second": 2.896, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 1.0129226446151733, | |
| "learning_rate": 1.7619901925606986e-05, | |
| "loss": 0.2194, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.22281154990196228, | |
| "eval_runtime": 128.9637, | |
| "eval_samples_per_second": 183.641, | |
| "eval_steps_per_second": 2.877, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 1.0302517414093018, | |
| "learning_rate": 1.6423872742494916e-05, | |
| "loss": 0.1989, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.20858530700206757, | |
| "eval_runtime": 129.0216, | |
| "eval_samples_per_second": 183.558, | |
| "eval_steps_per_second": 2.875, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 176.42080688476562, | |
| "learning_rate": 1.5227843559382852e-05, | |
| "loss": 0.1888, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.20265720784664154, | |
| "eval_runtime": 129.0285, | |
| "eval_samples_per_second": 183.549, | |
| "eval_steps_per_second": 2.875, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.7003317475318909, | |
| "learning_rate": 1.4031814376270783e-05, | |
| "loss": 0.177, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.19755715131759644, | |
| "eval_runtime": 129.1437, | |
| "eval_samples_per_second": 183.385, | |
| "eval_steps_per_second": 2.873, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.9357886910438538, | |
| "learning_rate": 1.2835785193158714e-05, | |
| "loss": 0.1703, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 0.19327057898044586, | |
| "eval_runtime": 128.8805, | |
| "eval_samples_per_second": 183.759, | |
| "eval_steps_per_second": 2.879, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.7597601413726807, | |
| "learning_rate": 1.1639756010046645e-05, | |
| "loss": 0.1647, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 0.19279009103775024, | |
| "eval_runtime": 130.5884, | |
| "eval_samples_per_second": 181.356, | |
| "eval_steps_per_second": 2.841, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.7547380924224854, | |
| "learning_rate": 1.0443726826934577e-05, | |
| "loss": 0.159, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.1890030950307846, | |
| "eval_runtime": 130.7667, | |
| "eval_samples_per_second": 181.109, | |
| "eval_steps_per_second": 2.837, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 1.0234203338623047, | |
| "learning_rate": 9.24769764382251e-06, | |
| "loss": 0.1538, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.18637944757938385, | |
| "eval_runtime": 129.4971, | |
| "eval_samples_per_second": 182.884, | |
| "eval_steps_per_second": 2.865, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.8639469742774963, | |
| "learning_rate": 8.051668460710443e-06, | |
| "loss": 0.151, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.18570180237293243, | |
| "eval_runtime": 130.9952, | |
| "eval_samples_per_second": 180.793, | |
| "eval_steps_per_second": 2.832, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 1.0679283142089844, | |
| "learning_rate": 6.855639277598374e-06, | |
| "loss": 0.1471, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.1828351765871048, | |
| "eval_runtime": 130.7048, | |
| "eval_samples_per_second": 181.195, | |
| "eval_steps_per_second": 2.838, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 0.7938817143440247, | |
| "learning_rate": 5.6596100944863066e-06, | |
| "loss": 0.1436, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 0.18144695460796356, | |
| "eval_runtime": 129.7461, | |
| "eval_samples_per_second": 182.533, | |
| "eval_steps_per_second": 2.859, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 0.6742356419563293, | |
| "learning_rate": 4.463580911374238e-06, | |
| "loss": 0.1435, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 0.18060417473316193, | |
| "eval_runtime": 128.241, | |
| "eval_samples_per_second": 184.676, | |
| "eval_steps_per_second": 2.893, | |
| "step": 6500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8361, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 5.63409272218583e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |