| { | |
| "best_metric": 10.364799499511719, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11341083073433512, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022682166146867026, | |
| "grad_norm": 0.1346822828054428, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3842, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022682166146867026, | |
| "eval_loss": 10.386616706848145, | |
| "eval_runtime": 3.0546, | |
| "eval_samples_per_second": 972.312, | |
| "eval_steps_per_second": 121.784, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004536433229373405, | |
| "grad_norm": 0.13732023537158966, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3876, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006804649844060108, | |
| "grad_norm": 0.14120781421661377, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3875, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00907286645874681, | |
| "grad_norm": 0.1419186294078827, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3854, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011341083073433513, | |
| "grad_norm": 0.14743481576442719, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3863, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013609299688120215, | |
| "grad_norm": 0.1470358669757843, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3842, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01587751630280692, | |
| "grad_norm": 0.1487945318222046, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3833, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01814573291749362, | |
| "grad_norm": 0.13862915337085724, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3862, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020413949532180325, | |
| "grad_norm": 0.14534485340118408, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.385, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022682166146867026, | |
| "grad_norm": 0.14452332258224487, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.384, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02495038276155373, | |
| "grad_norm": 0.13165196776390076, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3834, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02721859937624043, | |
| "grad_norm": 0.14375360310077667, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3852, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029486815990927135, | |
| "grad_norm": 0.16815604269504547, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3775, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03175503260561384, | |
| "grad_norm": 0.16887976229190826, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3798, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03402324922030054, | |
| "grad_norm": 0.17802490293979645, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3792, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03629146583498724, | |
| "grad_norm": 0.1856260597705841, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3768, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03855968244967394, | |
| "grad_norm": 0.1794416904449463, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3793, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04082789906436065, | |
| "grad_norm": 0.17807826399803162, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3762, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04309611567904735, | |
| "grad_norm": 0.182838574051857, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3777, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04536433229373405, | |
| "grad_norm": 0.18508730828762054, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3753, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04763254890842075, | |
| "grad_norm": 0.19818346202373505, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3759, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04990076552310746, | |
| "grad_norm": 0.17286446690559387, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.375, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05216898213779416, | |
| "grad_norm": 0.17338807880878448, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3757, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05443719875248086, | |
| "grad_norm": 0.18380731344223022, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3751, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05670541536716756, | |
| "grad_norm": 0.19529420137405396, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3706, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05670541536716756, | |
| "eval_loss": 10.371033668518066, | |
| "eval_runtime": 3.0382, | |
| "eval_samples_per_second": 977.536, | |
| "eval_steps_per_second": 122.439, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05897363198185427, | |
| "grad_norm": 0.20476947724819183, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3699, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06124184859654097, | |
| "grad_norm": 0.23112817108631134, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3707, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06351006521122768, | |
| "grad_norm": 0.23180252313613892, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3711, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06577828182591437, | |
| "grad_norm": 0.22128894925117493, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3708, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06804649844060108, | |
| "grad_norm": 0.2330835610628128, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3695, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07031471505528777, | |
| "grad_norm": 0.2294759452342987, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3689, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07258293166997448, | |
| "grad_norm": 0.23074816167354584, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3672, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07485114828466119, | |
| "grad_norm": 0.2303849160671234, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3683, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07711936489934788, | |
| "grad_norm": 0.22095413506031036, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3697, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07938758151403459, | |
| "grad_norm": 0.2163832187652588, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3694, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0816557981287213, | |
| "grad_norm": 0.20412799715995789, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3699, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08392401474340799, | |
| "grad_norm": 0.21430176496505737, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3699, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0861922313580947, | |
| "grad_norm": 0.240758016705513, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3665, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0884604479727814, | |
| "grad_norm": 0.24734526872634888, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3648, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0907286645874681, | |
| "grad_norm": 0.25556033849716187, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09299688120215481, | |
| "grad_norm": 0.25022992491722107, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3659, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0952650978168415, | |
| "grad_norm": 0.2543710768222809, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3659, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09753331443152821, | |
| "grad_norm": 0.2404075562953949, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3647, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09980153104621492, | |
| "grad_norm": 0.24763478338718414, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.365, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10206974766090161, | |
| "grad_norm": 0.2456260770559311, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3668, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10433796427558832, | |
| "grad_norm": 0.23241014778614044, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3673, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10660618089027502, | |
| "grad_norm": 0.2225053906440735, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3674, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10887439750496172, | |
| "grad_norm": 0.21233010292053223, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3674, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11114261411964843, | |
| "grad_norm": 0.21536342799663544, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.369, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11341083073433512, | |
| "grad_norm": 0.2400255799293518, | |
| "learning_rate": 0.0, | |
| "loss": 10.3672, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11341083073433512, | |
| "eval_loss": 10.364799499511719, | |
| "eval_runtime": 3.032, | |
| "eval_samples_per_second": 979.564, | |
| "eval_steps_per_second": 122.693, | |
| "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": 42781424615424.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |