| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.06576783952647156, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013153567905294311, | |
| "grad_norm": 4.305715084075928, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013153567905294311, | |
| "eval_loss": NaN, | |
| "eval_runtime": 154.6996, | |
| "eval_samples_per_second": 33.109, | |
| "eval_steps_per_second": 4.144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026307135810588623, | |
| "grad_norm": 4.98206901550293, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8066, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003946070371588293, | |
| "grad_norm": 4.7236738204956055, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.712, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005261427162117725, | |
| "grad_norm": 5.148580074310303, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.9262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006576783952647156, | |
| "grad_norm": 6.657264232635498, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.3766, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007892140743176587, | |
| "grad_norm": 3.452958345413208, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9662, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009207497533706017, | |
| "grad_norm": 3.356189489364624, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.5367, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01052285432423545, | |
| "grad_norm": 2.3280153274536133, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.478, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01183821111476488, | |
| "grad_norm": 2.648228406906128, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.4201, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013153567905294311, | |
| "grad_norm": 5.471138954162598, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.3108, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014468924695823742, | |
| "grad_norm": 2.8087058067321777, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.0655, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015784281486353174, | |
| "grad_norm": 7.201243877410889, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.0358, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017099638276882604, | |
| "grad_norm": 3.615448236465454, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.5537, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018414995067412034, | |
| "grad_norm": 4.010716438293457, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.806, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019730351857941468, | |
| "grad_norm": 2.0730106830596924, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.6445, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0210457086484709, | |
| "grad_norm": 1.6707302331924438, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.4386, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02236106543900033, | |
| "grad_norm": 1.6326355934143066, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.3879, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02367642222952976, | |
| "grad_norm": 1.5959230661392212, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3075, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024991779020059193, | |
| "grad_norm": 1.9072798490524292, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.3008, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.026307135810588623, | |
| "grad_norm": 1.344789981842041, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.2003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027622492601118053, | |
| "grad_norm": 1.4146466255187988, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.2142, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028937849391647483, | |
| "grad_norm": 1.3578002452850342, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.9889, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.030253206182176917, | |
| "grad_norm": 1.4287495613098145, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.9253, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03156856297270635, | |
| "grad_norm": 1.527700424194336, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.8363, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03288391976323578, | |
| "grad_norm": 1.7608954906463623, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.5056, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03288391976323578, | |
| "eval_loss": NaN, | |
| "eval_runtime": 154.8596, | |
| "eval_samples_per_second": 33.075, | |
| "eval_steps_per_second": 4.139, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03419927655376521, | |
| "grad_norm": 3.8425331115722656, | |
| "learning_rate": 5e-05, | |
| "loss": 2.646, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03551463334429464, | |
| "grad_norm": 3.500214099884033, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.5897, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03682999013482407, | |
| "grad_norm": 2.8640339374542236, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.4347, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0381453469253535, | |
| "grad_norm": 2.1953330039978027, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.3318, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.039460703715882936, | |
| "grad_norm": 1.360359787940979, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.3259, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.040776060506412366, | |
| "grad_norm": 1.5449228286743164, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.1774, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0420914172969418, | |
| "grad_norm": 1.6351491212844849, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.1532, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04340677408747123, | |
| "grad_norm": 2.0852408409118652, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.1224, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04472213087800066, | |
| "grad_norm": 1.954745888710022, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.1098, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04603748766853009, | |
| "grad_norm": 1.9391647577285767, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.0364, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04735284445905952, | |
| "grad_norm": 2.2001044750213623, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.91, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04866820124958895, | |
| "grad_norm": 2.463000535964966, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.664, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.049983558040118385, | |
| "grad_norm": 1.6193251609802246, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3198, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.051298914830647815, | |
| "grad_norm": 1.781665563583374, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.4016, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.052614271621177246, | |
| "grad_norm": 1.9119794368743896, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2973, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.053929628411706676, | |
| "grad_norm": 1.837246060371399, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.2067, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.055244985202236106, | |
| "grad_norm": 1.520390510559082, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.2404, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05656034199276554, | |
| "grad_norm": 1.44670569896698, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.225, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05787569878329497, | |
| "grad_norm": 1.3467217683792114, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1485, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0591910555738244, | |
| "grad_norm": 1.2551240921020508, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.0337, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.060506412364353834, | |
| "grad_norm": 1.223370909690857, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.9589, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.061821769154883265, | |
| "grad_norm": 1.1751079559326172, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.0722, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0631371259454127, | |
| "grad_norm": 1.4985276460647583, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.9858, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06445248273594212, | |
| "grad_norm": 1.7056043148040771, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.7523, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06576783952647156, | |
| "grad_norm": 2.749437093734741, | |
| "learning_rate": 0.0, | |
| "loss": 1.7858, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06576783952647156, | |
| "eval_loss": NaN, | |
| "eval_runtime": 154.9001, | |
| "eval_samples_per_second": 33.066, | |
| "eval_steps_per_second": 4.138, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |