| { | |
| "best_metric": 0.23411691188812256, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11627906976744186, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002325581395348837, | |
| "grad_norm": 480.875244140625, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2283, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002325581395348837, | |
| "eval_loss": 3.548891544342041, | |
| "eval_runtime": 84.6742, | |
| "eval_samples_per_second": 34.213, | |
| "eval_steps_per_second": 4.287, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004651162790697674, | |
| "grad_norm": 461.0716247558594, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3606, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0069767441860465115, | |
| "grad_norm": 380.3354187011719, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.2033, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009302325581395349, | |
| "grad_norm": 243.8723907470703, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.3104, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011627906976744186, | |
| "grad_norm": 559.4659423828125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0377, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013953488372093023, | |
| "grad_norm": 292.1619567871094, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7272, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01627906976744186, | |
| "grad_norm": 700.7692260742188, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5149, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018604651162790697, | |
| "grad_norm": 259.9952392578125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6226, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020930232558139535, | |
| "grad_norm": 169.6724395751953, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6372, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023255813953488372, | |
| "grad_norm": 195.54771423339844, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4816, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02558139534883721, | |
| "grad_norm": 112.20954895019531, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.4465, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027906976744186046, | |
| "grad_norm": 140.589111328125, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4026, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.030232558139534883, | |
| "grad_norm": 99.36078643798828, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3726, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03255813953488372, | |
| "grad_norm": 103.61114501953125, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3657, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03488372093023256, | |
| "grad_norm": 125.44934844970703, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3889, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.037209302325581395, | |
| "grad_norm": 110.65096282958984, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.374, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03953488372093023, | |
| "grad_norm": 69.39531707763672, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3473, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04186046511627907, | |
| "grad_norm": 85.2568588256836, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3667, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.044186046511627906, | |
| "grad_norm": 59.08995056152344, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3262, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.046511627906976744, | |
| "grad_norm": 53.15679168701172, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2325, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04883720930232558, | |
| "grad_norm": 88.6565933227539, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3123, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05116279069767442, | |
| "grad_norm": 63.372840881347656, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2454, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.053488372093023255, | |
| "grad_norm": 61.798309326171875, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2687, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05581395348837209, | |
| "grad_norm": 57.89033889770508, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2881, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05813953488372093, | |
| "grad_norm": 68.68138122558594, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3239, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05813953488372093, | |
| "eval_loss": 0.3628028333187103, | |
| "eval_runtime": 84.9333, | |
| "eval_samples_per_second": 34.109, | |
| "eval_steps_per_second": 4.274, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06046511627906977, | |
| "grad_norm": 88.96664428710938, | |
| "learning_rate": 5e-05, | |
| "loss": 0.396, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06279069767441861, | |
| "grad_norm": 82.79183197021484, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3057, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06511627906976744, | |
| "grad_norm": 61.08711242675781, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2818, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06744186046511629, | |
| "grad_norm": 70.03043365478516, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2947, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06976744186046512, | |
| "grad_norm": 64.4678955078125, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2746, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07209302325581396, | |
| "grad_norm": 58.500099182128906, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2671, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07441860465116279, | |
| "grad_norm": 59.845664978027344, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2728, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07674418604651163, | |
| "grad_norm": 56.12503433227539, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3234, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07906976744186046, | |
| "grad_norm": 58.79863357543945, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2889, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08139534883720931, | |
| "grad_norm": 59.2402229309082, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.328, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08372093023255814, | |
| "grad_norm": 46.734561920166016, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3102, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08604651162790698, | |
| "grad_norm": 48.9833869934082, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.2495, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08837209302325581, | |
| "grad_norm": 49.06808853149414, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3149, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09069767441860466, | |
| "grad_norm": 66.39009094238281, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2584, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09302325581395349, | |
| "grad_norm": 46.767024993896484, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2119, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09534883720930233, | |
| "grad_norm": 43.55037307739258, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2359, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09767441860465116, | |
| "grad_norm": 51.920928955078125, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2567, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 51.2324333190918, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.3273, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10232558139534884, | |
| "grad_norm": 41.81425094604492, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2583, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10465116279069768, | |
| "grad_norm": 35.66553497314453, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1697, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10697674418604651, | |
| "grad_norm": 47.469024658203125, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2617, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10930232558139535, | |
| "grad_norm": 52.34221649169922, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3625, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11162790697674418, | |
| "grad_norm": 40.48112869262695, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2194, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11395348837209303, | |
| "grad_norm": 44.73693084716797, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2252, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11627906976744186, | |
| "grad_norm": 57.12425994873047, | |
| "learning_rate": 0.0, | |
| "loss": 0.2006, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11627906976744186, | |
| "eval_loss": 0.23411691188812256, | |
| "eval_runtime": 84.9204, | |
| "eval_samples_per_second": 34.114, | |
| "eval_steps_per_second": 4.275, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658027780734976e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |