| { | |
| "best_metric": 1.8351699113845825, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.13805004314063848, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027610008628127696, | |
| "grad_norm": 121.57788848876953, | |
| "learning_rate": 5e-05, | |
| "loss": 13.5104, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027610008628127696, | |
| "eval_loss": 13.60006046295166, | |
| "eval_runtime": 22.1692, | |
| "eval_samples_per_second": 110.063, | |
| "eval_steps_per_second": 13.758, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005522001725625539, | |
| "grad_norm": 120.4114761352539, | |
| "learning_rate": 0.0001, | |
| "loss": 13.5466, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00828300258843831, | |
| "grad_norm": 189.47218322753906, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 13.0268, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011044003451251078, | |
| "grad_norm": 74.05614471435547, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.1214, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013805004314063849, | |
| "grad_norm": 65.40906524658203, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.8602, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01656600517687662, | |
| "grad_norm": 49.65504455566406, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.3736, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019327006039689388, | |
| "grad_norm": 75.54695892333984, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.7208, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.022088006902502157, | |
| "grad_norm": 32.32862854003906, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0733, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024849007765314925, | |
| "grad_norm": 13.67139720916748, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.6005, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027610008628127698, | |
| "grad_norm": 19.72774887084961, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.4848, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.030371009490940466, | |
| "grad_norm": 26.92169952392578, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.2381, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03313201035375324, | |
| "grad_norm": 63.783424377441406, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.0044, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.035893011216566004, | |
| "grad_norm": 27.033920288085938, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 4.1015, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.038654012079378776, | |
| "grad_norm": 25.252769470214844, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2373, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04141501294219154, | |
| "grad_norm": 15.015902519226074, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.966, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04417601380500431, | |
| "grad_norm": 11.274029731750488, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.8608, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.046937014667817085, | |
| "grad_norm": 6.833890914916992, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8622, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04969801553062985, | |
| "grad_norm": 4.205880641937256, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.7259, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05245901639344262, | |
| "grad_norm": 8.309425354003906, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.8331, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.055220017256255395, | |
| "grad_norm": 1.8611191511154175, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.7104, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05798101811906816, | |
| "grad_norm": 3.5068414211273193, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.6505, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06074201898188093, | |
| "grad_norm": 6.320912837982178, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.6542, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0635030198446937, | |
| "grad_norm": 3.254844903945923, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.6272, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06626402070750648, | |
| "grad_norm": 20.136241912841797, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.3386, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06902502157031924, | |
| "grad_norm": 39.7511100769043, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.4797, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06902502157031924, | |
| "eval_loss": 1.9534236192703247, | |
| "eval_runtime": 22.1838, | |
| "eval_samples_per_second": 109.99, | |
| "eval_steps_per_second": 13.749, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07178602243313201, | |
| "grad_norm": 11.875720024108887, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4916, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07454702329594479, | |
| "grad_norm": 5.627650260925293, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.7081, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07730802415875755, | |
| "grad_norm": 4.874751567840576, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.6722, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08006902502157032, | |
| "grad_norm": 4.535109043121338, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.6553, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08283002588438308, | |
| "grad_norm": 3.0000500679016113, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6382, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08559102674719586, | |
| "grad_norm": 0.9891252517700195, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.6092, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08835202761000863, | |
| "grad_norm": 3.292105197906494, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.5993, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09111302847282139, | |
| "grad_norm": 2.8137319087982178, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.6062, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09387402933563417, | |
| "grad_norm": 0.6060113906860352, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.5763, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09663503019844694, | |
| "grad_norm": 1.3685656785964966, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.5971, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0993960310612597, | |
| "grad_norm": 3.1901323795318604, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.6005, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10215703192407248, | |
| "grad_norm": 27.733556747436523, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.9088, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10491803278688525, | |
| "grad_norm": 16.257993698120117, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.3302, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10767903364969801, | |
| "grad_norm": 2.6833341121673584, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.6092, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11044003451251079, | |
| "grad_norm": 2.7292048931121826, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5974, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11320103537532356, | |
| "grad_norm": 1.0176692008972168, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.5762, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11596203623813632, | |
| "grad_norm": 2.5920333862304688, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.5751, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1187230371009491, | |
| "grad_norm": 2.3291893005371094, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.5899, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12148403796376187, | |
| "grad_norm": 0.8562758564949036, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5714, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12424503882657463, | |
| "grad_norm": 3.0587594509124756, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.5834, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1270060396893874, | |
| "grad_norm": 0.6108625531196594, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.5768, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12976704055220017, | |
| "grad_norm": 0.5593339800834656, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.5774, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.13252804141501295, | |
| "grad_norm": 0.6090744733810425, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.5771, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1352890422778257, | |
| "grad_norm": 14.088340759277344, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.6429, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13805004314063848, | |
| "grad_norm": 26.365188598632812, | |
| "learning_rate": 0.0, | |
| "loss": 3.5791, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13805004314063848, | |
| "eval_loss": 1.8351699113845825, | |
| "eval_runtime": 22.1791, | |
| "eval_samples_per_second": 110.013, | |
| "eval_steps_per_second": 13.752, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |