| { | |
| "best_metric": 10.373420715332031, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.12610340479192939, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025220680958385876, | |
| "grad_norm": 0.027054335922002792, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3787, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025220680958385876, | |
| "eval_loss": 10.378507614135742, | |
| "eval_runtime": 2.8338, | |
| "eval_samples_per_second": 942.898, | |
| "eval_steps_per_second": 117.862, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005044136191677175, | |
| "grad_norm": 0.023505287244915962, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3786, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007566204287515763, | |
| "grad_norm": 0.026017118245363235, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3786, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01008827238335435, | |
| "grad_norm": 0.0248271394520998, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3781, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012610340479192938, | |
| "grad_norm": 0.0254810843616724, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3779, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015132408575031526, | |
| "grad_norm": 0.02538875676691532, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3781, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017654476670870115, | |
| "grad_norm": 0.025415387004613876, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3776, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0201765447667087, | |
| "grad_norm": 0.029065122827887535, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3779, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02269861286254729, | |
| "grad_norm": 0.02831706777215004, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3786, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025220680958385876, | |
| "grad_norm": 0.0291791670024395, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027742749054224466, | |
| "grad_norm": 0.030690718442201614, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3765, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03026481715006305, | |
| "grad_norm": 0.032121799886226654, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.377, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03278688524590164, | |
| "grad_norm": 0.028205260634422302, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3775, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03530895334174023, | |
| "grad_norm": 0.030245285481214523, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3778, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03783102143757881, | |
| "grad_norm": 0.030657567083835602, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3769, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0403530895334174, | |
| "grad_norm": 0.033357568085193634, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3752, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04287515762925599, | |
| "grad_norm": 0.03190469369292259, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3769, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04539722572509458, | |
| "grad_norm": 0.03442990407347679, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3761, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04791929382093316, | |
| "grad_norm": 0.03860880061984062, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3755, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05044136191677175, | |
| "grad_norm": 0.03901612013578415, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3758, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05296343001261034, | |
| "grad_norm": 0.039788056164979935, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3746, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05548549810844893, | |
| "grad_norm": 0.04064761474728584, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3759, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.058007566204287514, | |
| "grad_norm": 0.04556358978152275, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.376, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0605296343001261, | |
| "grad_norm": 0.050544317811727524, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3747, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06305170239596469, | |
| "grad_norm": 0.05241914466023445, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3745, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06305170239596469, | |
| "eval_loss": 10.375017166137695, | |
| "eval_runtime": 2.8388, | |
| "eval_samples_per_second": 941.231, | |
| "eval_steps_per_second": 117.654, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 0.04510338976979256, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3746, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06809583858764187, | |
| "grad_norm": 0.045711468905210495, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3747, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07061790668348046, | |
| "grad_norm": 0.04386696591973305, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3759, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07313997477931904, | |
| "grad_norm": 0.045891132205724716, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3753, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07566204287515763, | |
| "grad_norm": 0.04793156683444977, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.374, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07818411097099622, | |
| "grad_norm": 0.05221310257911682, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3743, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0807061790668348, | |
| "grad_norm": 0.051459524780511856, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3736, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0832282471626734, | |
| "grad_norm": 0.05057171732187271, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3746, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08575031525851198, | |
| "grad_norm": 0.05461611598730087, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3743, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08827238335435057, | |
| "grad_norm": 0.05995216593146324, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3727, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09079445145018916, | |
| "grad_norm": 0.061333104968070984, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3725, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09331651954602774, | |
| "grad_norm": 0.07217469811439514, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3731, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09583858764186633, | |
| "grad_norm": 0.05127323046326637, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3735, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09836065573770492, | |
| "grad_norm": 0.04944981634616852, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3738, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1008827238335435, | |
| "grad_norm": 0.05343186855316162, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3733, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1034047919293821, | |
| "grad_norm": 0.05616803839802742, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3744, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10592686002522068, | |
| "grad_norm": 0.0577423982322216, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3737, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10844892812105927, | |
| "grad_norm": 0.06030035391449928, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3739, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11097099621689786, | |
| "grad_norm": 0.05783156305551529, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3731, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11349306431273644, | |
| "grad_norm": 0.06098296493291855, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3737, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11601513240857503, | |
| "grad_norm": 0.06156492978334427, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.372, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11853720050441362, | |
| "grad_norm": 0.06359221786260605, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3731, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1210592686002522, | |
| "grad_norm": 0.06486078351736069, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3731, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1235813366960908, | |
| "grad_norm": 0.0683504045009613, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.3725, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12610340479192939, | |
| "grad_norm": 0.07451239973306656, | |
| "learning_rate": 0.0, | |
| "loss": 10.3729, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12610340479192939, | |
| "eval_loss": 10.373420715332031, | |
| "eval_runtime": 2.8358, | |
| "eval_samples_per_second": 942.245, | |
| "eval_steps_per_second": 117.781, | |
| "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": 42888344764416.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |