| { | |
| "best_metric": 11.931137084960938, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2669336002669336, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005338672005338672, | |
| "grad_norm": 0.010944690555334091, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9321, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005338672005338672, | |
| "eval_loss": 11.932465553283691, | |
| "eval_runtime": 3.2895, | |
| "eval_samples_per_second": 383.642, | |
| "eval_steps_per_second": 48.031, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010677344010677344, | |
| "grad_norm": 0.011320938356220722, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9326, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016016016016016016, | |
| "grad_norm": 0.011404898948967457, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9319, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02135468802135469, | |
| "grad_norm": 0.0110051603987813, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9328, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02669336002669336, | |
| "grad_norm": 0.011356206610798836, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9323, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03203203203203203, | |
| "grad_norm": 0.011060361750423908, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9323, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0373707040373707, | |
| "grad_norm": 0.010736605152487755, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9322, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04270937604270938, | |
| "grad_norm": 0.01069414708763361, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9327, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04804804804804805, | |
| "grad_norm": 0.012905471958220005, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9324, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05338672005338672, | |
| "grad_norm": 0.013225181959569454, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9326, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.058725392058725394, | |
| "grad_norm": 0.012276624329388142, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9325, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06406406406406406, | |
| "grad_norm": 0.012049563229084015, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9328, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06940273606940274, | |
| "grad_norm": 0.012281198985874653, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9327, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0747414080747414, | |
| "grad_norm": 0.013785919174551964, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9319, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08008008008008008, | |
| "grad_norm": 0.01462618075311184, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08541875208541876, | |
| "grad_norm": 0.014857230708003044, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9314, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09075742409075742, | |
| "grad_norm": 0.014654548838734627, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9322, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0960960960960961, | |
| "grad_norm": 0.013729645870625973, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9322, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10143476810143477, | |
| "grad_norm": 0.016921019181609154, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.932, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10677344010677343, | |
| "grad_norm": 0.01694069430232048, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9317, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11211211211211211, | |
| "grad_norm": 0.019150249660015106, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9316, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11745078411745079, | |
| "grad_norm": 0.019771084189414978, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9317, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12278945612278945, | |
| "grad_norm": 0.01873360387980938, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9319, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12812812812812813, | |
| "grad_norm": 0.0185577142983675, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9322, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1334668001334668, | |
| "grad_norm": 0.019920753315091133, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9321, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1334668001334668, | |
| "eval_loss": 11.931558609008789, | |
| "eval_runtime": 3.3225, | |
| "eval_samples_per_second": 379.831, | |
| "eval_steps_per_second": 47.554, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13880547213880548, | |
| "grad_norm": 0.020508192479610443, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9312, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 0.02420317381620407, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9317, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1494828161494828, | |
| "grad_norm": 0.023656731471419334, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9307, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1548214881548215, | |
| "grad_norm": 0.02386278659105301, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9311, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.16016016016016016, | |
| "grad_norm": 0.022931382060050964, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9318, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16549883216549882, | |
| "grad_norm": 0.022951658815145493, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9314, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1708375041708375, | |
| "grad_norm": 0.02454853057861328, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9315, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.17617617617617617, | |
| "grad_norm": 0.023593643680214882, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.9313, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.18151484818151484, | |
| "grad_norm": 0.025214286521077156, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9313, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.18685352018685353, | |
| "grad_norm": 0.02529080957174301, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9315, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1921921921921922, | |
| "grad_norm": 0.026581237092614174, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.9314, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.02596159279346466, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.9312, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.20286953620286954, | |
| "grad_norm": 0.025232110172510147, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.931, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2082082082082082, | |
| "grad_norm": 0.03222332522273064, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.93, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.21354688021354687, | |
| "grad_norm": 0.028676046058535576, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.9311, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21888555221888556, | |
| "grad_norm": 0.02865523286163807, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.9302, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.22422422422422422, | |
| "grad_norm": 0.029142210260033607, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9309, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.22956289622956288, | |
| "grad_norm": 0.028110573068261147, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9313, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.23490156823490158, | |
| "grad_norm": 0.025929946452379227, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.931, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.24024024024024024, | |
| "grad_norm": 0.03023443929851055, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9303, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2455789122455789, | |
| "grad_norm": 0.029193932190537453, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.9314, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2509175842509176, | |
| "grad_norm": 0.027724456042051315, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.9312, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.25625625625625625, | |
| "grad_norm": 0.026069508865475655, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9313, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2615949282615949, | |
| "grad_norm": 0.026789134368300438, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.9321, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2669336002669336, | |
| "grad_norm": 0.02489320933818817, | |
| "learning_rate": 0.0, | |
| "loss": 11.9326, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2669336002669336, | |
| "eval_loss": 11.931137084960938, | |
| "eval_runtime": 3.2883, | |
| "eval_samples_per_second": 383.781, | |
| "eval_steps_per_second": 48.049, | |
| "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": 1044123156480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |