| { | |
| "best_metric": 0.10270044952630997, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5657708628005658, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011315417256011316, | |
| "grad_norm": 9.686368942260742, | |
| "learning_rate": 5e-05, | |
| "loss": 12.4512, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011315417256011316, | |
| "eval_loss": 12.496306419372559, | |
| "eval_runtime": 15.6369, | |
| "eval_samples_per_second": 38.051, | |
| "eval_steps_per_second": 4.796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02263083451202263, | |
| "grad_norm": 9.485298156738281, | |
| "learning_rate": 0.0001, | |
| "loss": 12.5365, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.033946251768033946, | |
| "grad_norm": 10.219993591308594, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.1397, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04526166902404526, | |
| "grad_norm": 12.514872550964355, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 9.1671, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056577086280056574, | |
| "grad_norm": 12.2258939743042, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.2113, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06789250353606789, | |
| "grad_norm": 14.635221481323242, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.7714, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07920792079207921, | |
| "grad_norm": 11.704349517822266, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5518, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09052333804809053, | |
| "grad_norm": 4.874855041503906, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4791, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10183875530410184, | |
| "grad_norm": 10.435992240905762, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.8347, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11315417256011315, | |
| "grad_norm": 21.458200454711914, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 7.7088, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12446958981612447, | |
| "grad_norm": 19.289995193481445, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.7447, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13578500707213578, | |
| "grad_norm": 11.059289932250977, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.0373, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1471004243281471, | |
| "grad_norm": 6.678143501281738, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1645, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 8.943098068237305, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2441, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16973125884016974, | |
| "grad_norm": 7.194612979888916, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1196, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18104667609618105, | |
| "grad_norm": 2.812526226043701, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0578, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19236209335219237, | |
| "grad_norm": 3.1021275520324707, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1586, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2036775106082037, | |
| "grad_norm": 14.355679512023926, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4559, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.214992927864215, | |
| "grad_norm": 3.471893310546875, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1112, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2263083451202263, | |
| "grad_norm": 4.7540154457092285, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "grad_norm": 1.5422192811965942, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0799, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24893917963224893, | |
| "grad_norm": 5.010796546936035, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4152, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26025459688826025, | |
| "grad_norm": 1.886130452156067, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3529, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.27157001414427157, | |
| "grad_norm": 7.487283706665039, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5008, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2828854314002829, | |
| "grad_norm": 10.072656631469727, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6203, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2828854314002829, | |
| "eval_loss": 0.217138409614563, | |
| "eval_runtime": 15.0374, | |
| "eval_samples_per_second": 39.568, | |
| "eval_steps_per_second": 4.988, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2942008486562942, | |
| "grad_norm": 0.08450052887201309, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0009, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3055162659123055, | |
| "grad_norm": 5.7550835609436035, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0396, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 3.7565834522247314, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0744, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.32814710042432815, | |
| "grad_norm": 1.2026886940002441, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0131, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33946251768033947, | |
| "grad_norm": 0.4069508910179138, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0088, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3507779349363508, | |
| "grad_norm": 0.40454617142677307, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0063, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3620933521923621, | |
| "grad_norm": 4.627459526062012, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0733, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3734087694483734, | |
| "grad_norm": 2.0707437992095947, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0246, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38472418670438474, | |
| "grad_norm": 2.672361373901367, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2179, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": 5.646185874938965, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4478, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4073550212164074, | |
| "grad_norm": 3.170839309692383, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3974, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4186704384724187, | |
| "grad_norm": 3.557582139968872, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4034, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.42998585572843, | |
| "grad_norm": 0.8311156034469604, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1684, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.44130127298444133, | |
| "grad_norm": 0.007551469840109348, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0001, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4526166902404526, | |
| "grad_norm": 0.09443239122629166, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0011, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4639321074964639, | |
| "grad_norm": 0.03768008202314377, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0005, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 0.31332749128341675, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0033, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48656294200848654, | |
| "grad_norm": 1.8230053186416626, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0182, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.49787835926449786, | |
| "grad_norm": 2.7197210788726807, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0416, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5091937765205092, | |
| "grad_norm": 0.6926154494285583, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0082, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5205091937765205, | |
| "grad_norm": 1.0953466892242432, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1237, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5318246110325319, | |
| "grad_norm": 2.7397115230560303, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.325, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5431400282885431, | |
| "grad_norm": 1.0948930978775024, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.345, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5544554455445545, | |
| "grad_norm": 1.4320255517959595, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3015, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5657708628005658, | |
| "grad_norm": 0.5962116122245789, | |
| "learning_rate": 0.0, | |
| "loss": 0.2995, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5657708628005658, | |
| "eval_loss": 0.10270044952630997, | |
| "eval_runtime": 15.0801, | |
| "eval_samples_per_second": 39.456, | |
| "eval_steps_per_second": 4.973, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |