| { | |
| "best_metric": 11.910809516906738, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.4916512059369202, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029684601113172542, | |
| "grad_norm": 0.07854124903678894, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9231, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029684601113172542, | |
| "eval_loss": 11.920661926269531, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 300.827, | |
| "eval_steps_per_second": 78.215, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.059369202226345084, | |
| "grad_norm": 0.06692206114530563, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9261, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08905380333951762, | |
| "grad_norm": 0.0733456239104271, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9269, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11873840445269017, | |
| "grad_norm": 0.08705615997314453, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9222, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14842300556586271, | |
| "grad_norm": 0.08946333825588226, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9286, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17810760667903525, | |
| "grad_norm": 0.08612839132547379, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9341, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 0.10323967784643173, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9302, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.23747680890538034, | |
| "grad_norm": 0.10682009905576706, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9299, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.26716141001855287, | |
| "grad_norm": 0.07031102478504181, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9248, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.29684601113172543, | |
| "grad_norm": 0.042968425899744034, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9318, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.06182645261287689, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9299, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3562152133580705, | |
| "grad_norm": 0.061960361897945404, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9277, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.38589981447124305, | |
| "grad_norm": 0.07849795371294022, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9238, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4155844155844156, | |
| "grad_norm": 0.09162940829992294, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9264, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4452690166975881, | |
| "grad_norm": 0.09380555152893066, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4749536178107607, | |
| "grad_norm": 0.10168056190013885, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9273, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5046382189239332, | |
| "grad_norm": 0.0702374204993248, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9267, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5343228200371057, | |
| "grad_norm": 0.05303334444761276, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.925, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5640074211502782, | |
| "grad_norm": 0.07480276376008987, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9222, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5936920222634509, | |
| "grad_norm": 0.05803615599870682, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9215, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6233766233766234, | |
| "grad_norm": 0.09139496088027954, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9298, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 0.08935210108757019, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9281, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6827458256029685, | |
| "grad_norm": 0.10482572019100189, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9257, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.712430426716141, | |
| "grad_norm": 0.11235759407281876, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9329, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7421150278293135, | |
| "grad_norm": 0.09789710491895676, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9338, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7421150278293135, | |
| "eval_loss": 11.914202690124512, | |
| "eval_runtime": 0.1702, | |
| "eval_samples_per_second": 293.777, | |
| "eval_steps_per_second": 76.382, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7717996289424861, | |
| "grad_norm": 0.05901161581277847, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9242, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8014842300556586, | |
| "grad_norm": 0.06706172227859497, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.9231, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8311688311688312, | |
| "grad_norm": 0.07833290100097656, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9237, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8608534322820037, | |
| "grad_norm": 0.091151162981987, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.9266, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8905380333951762, | |
| "grad_norm": 0.11896399408578873, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.929, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9202226345083488, | |
| "grad_norm": 0.11437124013900757, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9297, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9499072356215214, | |
| "grad_norm": 0.13641905784606934, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9235, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 0.15378476679325104, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9242, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0166975881261595, | |
| "grad_norm": 0.13144145905971527, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 17.6087, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0463821892393321, | |
| "grad_norm": 0.07724036276340485, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 13.2434, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0760667903525047, | |
| "grad_norm": 0.0806306004524231, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.7137, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1057513914656771, | |
| "grad_norm": 0.09000066667795181, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 12.1179, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1354359925788498, | |
| "grad_norm": 0.12084916979074478, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.5785, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1651205936920221, | |
| "grad_norm": 0.12375957518815994, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.8553, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.1948051948051948, | |
| "grad_norm": 0.1317008137702942, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.8129, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2244897959183674, | |
| "grad_norm": 0.14589351415634155, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9896, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.25417439703154, | |
| "grad_norm": 0.10819032043218613, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.9097, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.2838589981447124, | |
| "grad_norm": 0.08235201239585876, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 13.3787, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.313543599257885, | |
| "grad_norm": 0.08341158926486969, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.532, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.3432282003710574, | |
| "grad_norm": 0.09403184056282043, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.4107, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.37291280148423, | |
| "grad_norm": 0.09566580504179001, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 13.2582, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4025974025974026, | |
| "grad_norm": 0.12213481962680817, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.283, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.4322820037105752, | |
| "grad_norm": 0.11991226673126221, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 12.1191, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.4619666048237476, | |
| "grad_norm": 0.15538115799427032, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 12.0205, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.4916512059369202, | |
| "grad_norm": 0.13172012567520142, | |
| "learning_rate": 1e-05, | |
| "loss": 10.5414, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4916512059369202, | |
| "eval_loss": 11.910809516906738, | |
| "eval_runtime": 0.1853, | |
| "eval_samples_per_second": 269.832, | |
| "eval_steps_per_second": 70.156, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |