| { | |
| "best_metric": 1.5995488166809082, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6218422075398368, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012436844150796735, | |
| "grad_norm": 4.070582389831543, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012436844150796735, | |
| "eval_loss": 6.697080135345459, | |
| "eval_runtime": 4.2989, | |
| "eval_samples_per_second": 11.631, | |
| "eval_steps_per_second": 3.024, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02487368830159347, | |
| "grad_norm": 4.343489646911621, | |
| "learning_rate": 0.0001, | |
| "loss": 4.86, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03731053245239021, | |
| "grad_norm": 4.6962361335754395, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.8283, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04974737660318694, | |
| "grad_norm": 4.616434097290039, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.0479, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06218422075398368, | |
| "grad_norm": 4.6326904296875, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.208, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07462106490478042, | |
| "grad_norm": 3.4674623012542725, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.7493, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08705790905557714, | |
| "grad_norm": 3.225517749786377, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.5875, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09949475320637388, | |
| "grad_norm": 3.2241368293762207, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4383, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11193159735717062, | |
| "grad_norm": 3.3204712867736816, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.211, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12436844150796736, | |
| "grad_norm": 2.812617301940918, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.0978, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1368052856587641, | |
| "grad_norm": 2.866771936416626, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.8688, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14924212980956084, | |
| "grad_norm": 6.981631755828857, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.6069, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16167897396035755, | |
| "grad_norm": 10.564940452575684, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.8817, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17411581811115429, | |
| "grad_norm": 8.371127128601074, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.7034, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18655266226195102, | |
| "grad_norm": 3.5405235290527344, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.462, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19898950641274776, | |
| "grad_norm": 2.1815154552459717, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.2772, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2114263505635445, | |
| "grad_norm": 2.2907159328460693, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.1571, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.22386319471434124, | |
| "grad_norm": 2.2352960109710693, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.1092, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23630003886513798, | |
| "grad_norm": 2.1429026126861572, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.1112, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24873688301593472, | |
| "grad_norm": 2.0608441829681396, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.9141, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26117372716673143, | |
| "grad_norm": 1.994292974472046, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.7083, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2736105713175282, | |
| "grad_norm": 1.7245221138000488, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.7911, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2860474154683249, | |
| "grad_norm": 1.8327735662460327, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.6479, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2984842596191217, | |
| "grad_norm": 1.897107720375061, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.3578, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3109211037699184, | |
| "grad_norm": 7.827093124389648, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.7274, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3109211037699184, | |
| "eval_loss": 1.8228825330734253, | |
| "eval_runtime": 4.3671, | |
| "eval_samples_per_second": 11.449, | |
| "eval_steps_per_second": 2.977, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3233579479207151, | |
| "grad_norm": 3.0982296466827393, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.3577, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.33579479207151186, | |
| "grad_norm": 2.92927885055542, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.2911, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.34823163622230857, | |
| "grad_norm": 2.458441972732544, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.0293, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.36066848037310534, | |
| "grad_norm": 2.1433932781219482, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.0705, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.37310532452390205, | |
| "grad_norm": 1.8144245147705078, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.8359, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": 1.615573525428772, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.8279, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3979790128254955, | |
| "grad_norm": 1.7636524438858032, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.9141, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4104158569762923, | |
| "grad_norm": 1.6936835050582886, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.9035, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.422852701127089, | |
| "grad_norm": 1.7628343105316162, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.5598, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4352895452778857, | |
| "grad_norm": 2.0483028888702393, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.6121, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4477263894286825, | |
| "grad_norm": 2.3952748775482178, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.2943, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4601632335794792, | |
| "grad_norm": 2.835444211959839, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.9927, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.47260007773027596, | |
| "grad_norm": 1.7717387676239014, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.8088, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.48503692188107267, | |
| "grad_norm": 1.5801821947097778, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.074, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.49747376603186944, | |
| "grad_norm": 1.5096017122268677, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.9525, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5099106101826661, | |
| "grad_norm": 1.5900380611419678, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.7708, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5223474543334629, | |
| "grad_norm": 1.4869619607925415, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.9034, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5347842984842596, | |
| "grad_norm": 1.295594573020935, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.8161, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5472211426350564, | |
| "grad_norm": 1.4549026489257812, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.7517, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5596579867858531, | |
| "grad_norm": 1.751529335975647, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.7905, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5720948309366498, | |
| "grad_norm": 1.6213444471359253, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.5946, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5845316750874465, | |
| "grad_norm": 1.8312252759933472, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.5736, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5969685192382433, | |
| "grad_norm": 1.7476670742034912, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.4217, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6094053633890401, | |
| "grad_norm": 1.5351223945617676, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.9661, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6218422075398368, | |
| "grad_norm": 1.8565118312835693, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4582, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6218422075398368, | |
| "eval_loss": 1.5995488166809082, | |
| "eval_runtime": 4.3433, | |
| "eval_samples_per_second": 11.512, | |
| "eval_steps_per_second": 2.993, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |