| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.12793858947705103, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025587717895410203, | |
| "grad_norm": 8.105547904968262, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6052, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025587717895410203, | |
| "eval_loss": NaN, | |
| "eval_runtime": 34.1539, | |
| "eval_samples_per_second": 77.092, | |
| "eval_steps_per_second": 9.662, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005117543579082041, | |
| "grad_norm": 10.676786422729492, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3579, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007676315368623061, | |
| "grad_norm": 7.778765678405762, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.1817, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010235087158164081, | |
| "grad_norm": 7.556909561157227, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.4221, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012793858947705102, | |
| "grad_norm": 8.060060501098633, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.6974, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015352630737246123, | |
| "grad_norm": 6.9193572998046875, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.0536, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01791140252678714, | |
| "grad_norm": 5.16635799407959, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.5565, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020470174316328162, | |
| "grad_norm": 7.898144721984863, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4027, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023028946105869183, | |
| "grad_norm": 2.9443695545196533, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1935, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025587717895410204, | |
| "grad_norm": 5.086276531219482, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.2233, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028146489684951224, | |
| "grad_norm": 2.406510353088379, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1276, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.030705261474492245, | |
| "grad_norm": 2.1311497688293457, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1066, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.033264033264033266, | |
| "grad_norm": 4.07924747467041, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3409, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03582280505357428, | |
| "grad_norm": 2.831731081008911, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1882, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03838157684311531, | |
| "grad_norm": 1.6757906675338745, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1248, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.040940348632656325, | |
| "grad_norm": 2.234086275100708, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1363, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04349912042219734, | |
| "grad_norm": 1.2191581726074219, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1268, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.046057892211738366, | |
| "grad_norm": 0.8200116157531738, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0743, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04861666400127938, | |
| "grad_norm": 2.0941131114959717, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0736, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05117543579082041, | |
| "grad_norm": 1.5826663970947266, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0923, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.053734207580361425, | |
| "grad_norm": 1.1381422281265259, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0719, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05629297936990245, | |
| "grad_norm": 1.930910587310791, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1141, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.058851751159443466, | |
| "grad_norm": 1.5791821479797363, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0665, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06141052294898449, | |
| "grad_norm": 1.1263339519500732, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0407, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06396929473852551, | |
| "grad_norm": 1.92032790184021, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.059, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06396929473852551, | |
| "eval_loss": NaN, | |
| "eval_runtime": 34.1606, | |
| "eval_samples_per_second": 77.077, | |
| "eval_steps_per_second": 9.66, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06652806652806653, | |
| "grad_norm": 1.8097161054611206, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06908683831760755, | |
| "grad_norm": 0.7914613485336304, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.103, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07164561010714857, | |
| "grad_norm": 0.8462138772010803, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0943, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07420438189668958, | |
| "grad_norm": 1.8287194967269897, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0764, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07676315368623061, | |
| "grad_norm": 1.483808994293213, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0589, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07932192547577163, | |
| "grad_norm": 1.5596754550933838, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0551, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08188069726531265, | |
| "grad_norm": 0.7599142789840698, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0638, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08443946905485367, | |
| "grad_norm": 1.0001721382141113, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0772, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08699824084439468, | |
| "grad_norm": 1.0733184814453125, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1038, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08955701263393571, | |
| "grad_norm": 0.7661743760108948, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0452, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09211578442347673, | |
| "grad_norm": 0.7713401913642883, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0806, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09467455621301775, | |
| "grad_norm": 1.0687928199768066, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0932, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09723332800255877, | |
| "grad_norm": 1.8803575038909912, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1912, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0997920997920998, | |
| "grad_norm": 1.3063056468963623, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0888, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10235087158164081, | |
| "grad_norm": 0.8238579630851746, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0557, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10490964337118183, | |
| "grad_norm": 0.6661612391471863, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0588, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10746841516072285, | |
| "grad_norm": 0.940695583820343, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0567, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11002718695026387, | |
| "grad_norm": 0.8477737903594971, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0428, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1125859587398049, | |
| "grad_norm": 0.5933483839035034, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0646, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11514473052934592, | |
| "grad_norm": 1.623978614807129, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0878, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11770350231888693, | |
| "grad_norm": 0.909454882144928, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0792, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12026227410842795, | |
| "grad_norm": 0.8963677287101746, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0255, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12282104589796898, | |
| "grad_norm": 0.762410581111908, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0719, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12537981768751, | |
| "grad_norm": 0.7860987782478333, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0594, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12793858947705103, | |
| "grad_norm": 1.0392541885375977, | |
| "learning_rate": 0.0, | |
| "loss": 0.0517, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12793858947705103, | |
| "eval_loss": NaN, | |
| "eval_runtime": 34.1551, | |
| "eval_samples_per_second": 77.089, | |
| "eval_steps_per_second": 9.662, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |