| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 117, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.042735042735042736, |
| "grad_norm": 3.711402177810669, |
| "learning_rate": 3.6363636363636366e-06, |
| "loss": 0.2434, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.08547008547008547, |
| "grad_norm": 3.794971227645874, |
| "learning_rate": 8.181818181818183e-06, |
| "loss": 0.1924, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1282051282051282, |
| "grad_norm": 2.4459402561187744, |
| "learning_rate": 9.998079135987437e-06, |
| "loss": 0.174, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.17094017094017094, |
| "grad_norm": 2.0912649631500244, |
| "learning_rate": 9.98634586692894e-06, |
| "loss": 0.1488, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.21367521367521367, |
| "grad_norm": 1.9830565452575684, |
| "learning_rate": 9.963971484502247e-06, |
| "loss": 0.1332, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.2564102564102564, |
| "grad_norm": 1.4833670854568481, |
| "learning_rate": 9.931003736767013e-06, |
| "loss": 0.1146, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.29914529914529914, |
| "grad_norm": 1.437637448310852, |
| "learning_rate": 9.887512978558329e-06, |
| "loss": 0.1175, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.3418803418803419, |
| "grad_norm": 1.591968297958374, |
| "learning_rate": 9.833592021345938e-06, |
| "loss": 0.1114, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.38461538461538464, |
| "grad_norm": 1.383669376373291, |
| "learning_rate": 9.76935593516989e-06, |
| "loss": 0.1092, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.42735042735042733, |
| "grad_norm": 1.2138135433197021, |
| "learning_rate": 9.694941803075285e-06, |
| "loss": 0.1005, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4700854700854701, |
| "grad_norm": 1.317816138267517, |
| "learning_rate": 9.610508428570122e-06, |
| "loss": 0.1079, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.5128205128205128, |
| "grad_norm": 1.1774816513061523, |
| "learning_rate": 9.516235996730645e-06, |
| "loss": 0.1003, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 1.3384287357330322, |
| "learning_rate": 9.41232568967728e-06, |
| "loss": 0.1005, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.5982905982905983, |
| "grad_norm": 1.0372443199157715, |
| "learning_rate": 9.298999257241862e-06, |
| "loss": 0.1029, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6410256410256411, |
| "grad_norm": 1.1703890562057495, |
| "learning_rate": 9.176498543742328e-06, |
| "loss": 0.0988, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.6837606837606838, |
| "grad_norm": 1.1787683963775635, |
| "learning_rate": 9.045084971874738e-06, |
| "loss": 0.0936, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7264957264957265, |
| "grad_norm": 1.180239200592041, |
| "learning_rate": 8.905038984824079e-06, |
| "loss": 0.1036, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 1.1398251056671143, |
| "learning_rate": 8.756659447784367e-06, |
| "loss": 0.1, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.811965811965812, |
| "grad_norm": 1.2935456037521362, |
| "learning_rate": 8.600263010165275e-06, |
| "loss": 0.0956, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.8547008547008547, |
| "grad_norm": 1.1012020111083984, |
| "learning_rate": 8.436183429846314e-06, |
| "loss": 0.1028, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8974358974358975, |
| "grad_norm": 1.0556975603103638, |
| "learning_rate": 8.264770860920722e-06, |
| "loss": 0.1077, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.9401709401709402, |
| "grad_norm": 1.069830298423767, |
| "learning_rate": 8.086391106448965e-06, |
| "loss": 0.0976, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.9829059829059829, |
| "grad_norm": 1.019631028175354, |
| "learning_rate": 7.90142483781658e-06, |
| "loss": 0.1008, |
| "step": 115 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 351, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.139253540605133e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
