| { | |
| "best_metric": 0.3560263514518738, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.032362459546925564, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006472491909385113, | |
| "grad_norm": 12.391196250915527, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1618, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006472491909385113, | |
| "eval_loss": 1.1013591289520264, | |
| "eval_runtime": 105.1712, | |
| "eval_samples_per_second": 24.75, | |
| "eval_steps_per_second": 3.1, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012944983818770227, | |
| "grad_norm": 10.685352325439453, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1263, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001941747572815534, | |
| "grad_norm": 7.642386436462402, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5872, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025889967637540453, | |
| "grad_norm": 12.233989715576172, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5568, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003236245954692557, | |
| "grad_norm": 6.16679048538208, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6063, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003883495145631068, | |
| "grad_norm": 5.216569423675537, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.3087, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004530744336569579, | |
| "grad_norm": 13.939298629760742, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.416, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005177993527508091, | |
| "grad_norm": 7.698254108428955, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.4695, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005825242718446602, | |
| "grad_norm": 4.788593292236328, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.2645, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006472491909385114, | |
| "grad_norm": 7.387963771820068, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.3205, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007119741100323625, | |
| "grad_norm": 5.369454860687256, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.3034, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007766990291262136, | |
| "grad_norm": 5.2790961265563965, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.1894, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008414239482200648, | |
| "grad_norm": 6.785725116729736, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.371, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009061488673139158, | |
| "grad_norm": 5.897602081298828, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.3022, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009708737864077669, | |
| "grad_norm": 6.494931697845459, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.3642, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010355987055016181, | |
| "grad_norm": 4.765385627746582, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.2676, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011003236245954692, | |
| "grad_norm": 5.174181938171387, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.4054, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011650485436893204, | |
| "grad_norm": 4.145316123962402, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.1391, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012297734627831715, | |
| "grad_norm": 5.084649085998535, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.2942, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012944983818770227, | |
| "grad_norm": 4.862823009490967, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1627, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013592233009708738, | |
| "grad_norm": 4.962240695953369, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.1816, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01423948220064725, | |
| "grad_norm": 4.77435827255249, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.2001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01488673139158576, | |
| "grad_norm": 5.3655242919921875, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.3343, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015533980582524271, | |
| "grad_norm": 5.315501689910889, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.3153, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016181229773462782, | |
| "grad_norm": 5.242373943328857, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.2928, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016181229773462782, | |
| "eval_loss": 0.387269526720047, | |
| "eval_runtime": 107.3282, | |
| "eval_samples_per_second": 24.253, | |
| "eval_steps_per_second": 3.037, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016828478964401296, | |
| "grad_norm": 6.530815124511719, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.2529, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.017475728155339806, | |
| "grad_norm": 5.5826096534729, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.3388, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018122977346278317, | |
| "grad_norm": 5.376560211181641, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.2726, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.018770226537216828, | |
| "grad_norm": 5.761511325836182, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.1466, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.019417475728155338, | |
| "grad_norm": 5.3690266609191895, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.1776, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020064724919093852, | |
| "grad_norm": 5.804825305938721, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.322, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.020711974110032363, | |
| "grad_norm": 7.030401229858398, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.3815, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.021359223300970873, | |
| "grad_norm": 6.575643062591553, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.2383, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022006472491909384, | |
| "grad_norm": 7.8663763999938965, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.4263, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.022653721682847898, | |
| "grad_norm": 6.203314781188965, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.283, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02330097087378641, | |
| "grad_norm": 7.10265588760376, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.3987, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02394822006472492, | |
| "grad_norm": 7.17543363571167, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.2639, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02459546925566343, | |
| "grad_norm": 7.629087924957275, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.3724, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02524271844660194, | |
| "grad_norm": 7.922370910644531, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.5521, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.025889967637540454, | |
| "grad_norm": 7.377615928649902, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.2888, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026537216828478965, | |
| "grad_norm": 8.394305229187012, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.2991, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.027184466019417475, | |
| "grad_norm": 7.840498447418213, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.1786, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.027831715210355986, | |
| "grad_norm": 10.578374862670898, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.4825, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0284789644012945, | |
| "grad_norm": 9.716651916503906, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.4621, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02912621359223301, | |
| "grad_norm": 11.308793067932129, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.5274, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02977346278317152, | |
| "grad_norm": 13.435274124145508, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.3785, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.030420711974110032, | |
| "grad_norm": 16.50029182434082, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.6574, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.031067961165048542, | |
| "grad_norm": 11.9188871383667, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.2691, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03171521035598705, | |
| "grad_norm": 47.62702178955078, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.8136, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.032362459546925564, | |
| "grad_norm": 85.18385314941406, | |
| "learning_rate": 0.0, | |
| "loss": 2.0817, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.032362459546925564, | |
| "eval_loss": 0.3560263514518738, | |
| "eval_runtime": 107.2714, | |
| "eval_samples_per_second": 24.266, | |
| "eval_steps_per_second": 3.039, | |
| "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": 5, | |
| "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": 3.917361458656051e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |