| { | |
| "best_metric": 2.0671772956848145, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.18744142455482662, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0037488284910965324, | |
| "grad_norm": 0.20465420186519623, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8354, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037488284910965324, | |
| "eval_loss": 2.3435218334198, | |
| "eval_runtime": 7.3235, | |
| "eval_samples_per_second": 61.446, | |
| "eval_steps_per_second": 7.783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007497656982193065, | |
| "grad_norm": 0.1741742640733719, | |
| "learning_rate": 4e-05, | |
| "loss": 1.954, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011246485473289597, | |
| "grad_norm": 0.2319125086069107, | |
| "learning_rate": 6e-05, | |
| "loss": 1.957, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01499531396438613, | |
| "grad_norm": 0.19860558211803436, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9693, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01874414245548266, | |
| "grad_norm": 0.19092042744159698, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9022, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022492970946579195, | |
| "grad_norm": 0.18668273091316223, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.1489, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.026241799437675725, | |
| "grad_norm": 0.1946374922990799, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.8344, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02999062792877226, | |
| "grad_norm": 0.21194031834602356, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.9127, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.033739456419868794, | |
| "grad_norm": 0.22352221608161926, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.9701, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03748828491096532, | |
| "grad_norm": 0.24026735126972198, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.0824, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 0.2265283763408661, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.9292, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04498594189315839, | |
| "grad_norm": 0.25951072573661804, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.036, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04873477038425492, | |
| "grad_norm": 0.23826272785663605, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.8531, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05248359887535145, | |
| "grad_norm": 0.24685098230838776, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.9693, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.056232427366447985, | |
| "grad_norm": 0.31856727600097656, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.9089, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05998125585754452, | |
| "grad_norm": 0.3416077792644501, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.9659, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06373008434864105, | |
| "grad_norm": 0.25727298855781555, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.0328, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06747891283973759, | |
| "grad_norm": 0.2617862820625305, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.0191, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07122774133083412, | |
| "grad_norm": 0.2551460862159729, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.9836, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07497656982193064, | |
| "grad_norm": 0.2661774754524231, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.9065, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07872539831302718, | |
| "grad_norm": 0.2693111300468445, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.9384, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 0.27645257115364075, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.9451, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08622305529522024, | |
| "grad_norm": 0.29583096504211426, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.9816, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08997188378631678, | |
| "grad_norm": 0.2951229214668274, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.9707, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09372071227741331, | |
| "grad_norm": 0.30265846848487854, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.966, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09372071227741331, | |
| "eval_loss": 2.104829788208008, | |
| "eval_runtime": 7.3882, | |
| "eval_samples_per_second": 60.908, | |
| "eval_steps_per_second": 7.715, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09746954076850985, | |
| "grad_norm": 0.3987659811973572, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.0137, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10121836925960637, | |
| "grad_norm": 0.33826690912246704, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.0594, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1049671977507029, | |
| "grad_norm": 0.34245115518569946, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.1526, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10871602624179943, | |
| "grad_norm": 0.35702967643737793, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.0391, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11246485473289597, | |
| "grad_norm": 0.36739176511764526, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.0303, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1162136832239925, | |
| "grad_norm": 0.3986171782016754, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 2.173, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11996251171508904, | |
| "grad_norm": 0.419553279876709, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.2194, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": 0.4767111539840698, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.956, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1274601686972821, | |
| "grad_norm": 0.4549711346626282, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 2.1381, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13120899718837864, | |
| "grad_norm": 0.45940274000167847, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.1526, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13495782567947517, | |
| "grad_norm": 0.5444797873497009, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.1269, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1387066541705717, | |
| "grad_norm": 0.519831120967865, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 2.1167, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14245548266166824, | |
| "grad_norm": 0.5798463225364685, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 2.1214, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14620431115276475, | |
| "grad_norm": 0.5918245911598206, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.1993, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14995313964386128, | |
| "grad_norm": 0.6637012362480164, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.0433, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15370196813495782, | |
| "grad_norm": 0.6506871581077576, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.1465, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15745079662605435, | |
| "grad_norm": 0.6886833310127258, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 2.2776, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.16119962511715089, | |
| "grad_norm": 0.7585076093673706, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 2.2323, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 0.749284029006958, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 2.3017, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.16869728209934395, | |
| "grad_norm": 0.8231189250946045, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 2.1884, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1724461105904405, | |
| "grad_norm": 0.9007522463798523, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.2728, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.17619493908153702, | |
| "grad_norm": 0.9463634490966797, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.4172, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.17994376757263356, | |
| "grad_norm": 1.162490725517273, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.4727, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1836925960637301, | |
| "grad_norm": 1.6514424085617065, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.3781, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18744142455482662, | |
| "grad_norm": 2.209977388381958, | |
| "learning_rate": 0.0, | |
| "loss": 2.7399, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18744142455482662, | |
| "eval_loss": 2.0671772956848145, | |
| "eval_runtime": 7.4249, | |
| "eval_samples_per_second": 60.607, | |
| "eval_steps_per_second": 7.677, | |
| "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": 8520778270113792.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |