| { | |
| "best_metric": 2.407135248184204, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.013550135501355014, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005420054200542005, | |
| "grad_norm": 26.37570571899414, | |
| "learning_rate": 2e-05, | |
| "loss": 8.8942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005420054200542005, | |
| "eval_loss": 2.610739231109619, | |
| "eval_runtime": 99.1947, | |
| "eval_samples_per_second": 7.833, | |
| "eval_steps_per_second": 3.922, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001084010840108401, | |
| "grad_norm": 20.89866828918457, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9083, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016260162601626016, | |
| "grad_norm": 25.650644302368164, | |
| "learning_rate": 6e-05, | |
| "loss": 8.0859, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002168021680216802, | |
| "grad_norm": 36.12504196166992, | |
| "learning_rate": 8e-05, | |
| "loss": 12.1335, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0027100271002710027, | |
| "grad_norm": 34.003334045410156, | |
| "learning_rate": 0.0001, | |
| "loss": 12.2915, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0027100271002710027, | |
| "eval_loss": 2.595651865005493, | |
| "eval_runtime": 92.9256, | |
| "eval_samples_per_second": 8.362, | |
| "eval_steps_per_second": 4.186, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032520325203252032, | |
| "grad_norm": 25.100780487060547, | |
| "learning_rate": 0.00012, | |
| "loss": 9.5278, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003794037940379404, | |
| "grad_norm": 30.90632438659668, | |
| "learning_rate": 0.00014, | |
| "loss": 11.0581, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004336043360433604, | |
| "grad_norm": 31.816679000854492, | |
| "learning_rate": 0.00016, | |
| "loss": 10.076, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004878048780487805, | |
| "grad_norm": 23.059032440185547, | |
| "learning_rate": 0.00018, | |
| "loss": 9.7569, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005420054200542005, | |
| "grad_norm": 28.870441436767578, | |
| "learning_rate": 0.0002, | |
| "loss": 9.1119, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005420054200542005, | |
| "eval_loss": 2.5213193893432617, | |
| "eval_runtime": 92.8251, | |
| "eval_samples_per_second": 8.371, | |
| "eval_steps_per_second": 4.191, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005962059620596206, | |
| "grad_norm": 26.181333541870117, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 9.8918, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0065040650406504065, | |
| "grad_norm": 24.101024627685547, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 8.1502, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007046070460704607, | |
| "grad_norm": 34.53730010986328, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 9.925, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007588075880758808, | |
| "grad_norm": 29.023534774780273, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 9.7495, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008130081300813009, | |
| "grad_norm": 40.96164321899414, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 10.4518, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008130081300813009, | |
| "eval_loss": 2.4435627460479736, | |
| "eval_runtime": 94.0323, | |
| "eval_samples_per_second": 8.263, | |
| "eval_steps_per_second": 4.137, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008672086720867209, | |
| "grad_norm": 32.43494415283203, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.5567, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00921409214092141, | |
| "grad_norm": 32.65191650390625, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 8.9572, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00975609756097561, | |
| "grad_norm": 50.91588592529297, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 10.5949, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010298102981029811, | |
| "grad_norm": 35.54926681518555, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 6.8794, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01084010840108401, | |
| "grad_norm": 28.28718376159668, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 7.4647, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01084010840108401, | |
| "eval_loss": 2.413238525390625, | |
| "eval_runtime": 91.443, | |
| "eval_samples_per_second": 8.497, | |
| "eval_steps_per_second": 4.254, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011382113821138212, | |
| "grad_norm": 35.49647903442383, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 9.9151, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011924119241192412, | |
| "grad_norm": 31.30296516418457, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 7.5294, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.012466124661246613, | |
| "grad_norm": 51.738033294677734, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 8.7387, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.013008130081300813, | |
| "grad_norm": 46.668582916259766, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 11.1315, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013550135501355014, | |
| "grad_norm": 33.56441879272461, | |
| "learning_rate": 0.0, | |
| "loss": 9.0747, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013550135501355014, | |
| "eval_loss": 2.407135248184204, | |
| "eval_runtime": 90.3932, | |
| "eval_samples_per_second": 8.596, | |
| "eval_steps_per_second": 4.303, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 307049980231680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |