| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9643564356435643, | |
| "eval_steps": 500, | |
| "global_step": 62, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 3.087754011154175, | |
| "learning_rate": 0.00019853538358476932, | |
| "loss": 1.3203, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": 2.311302900314331, | |
| "learning_rate": 0.0001736741137876405, | |
| "loss": 0.4199, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": 1.8357369899749756, | |
| "learning_rate": 0.0001362807705350641, | |
| "loss": 0.3195, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2673267326732673, | |
| "grad_norm": 1.4744713306427002, | |
| "learning_rate": 8.014095333542548e-05, | |
| "loss": 0.2549, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5841584158415842, | |
| "grad_norm": 1.1155927181243896, | |
| "learning_rate": 3.030624313447067e-05, | |
| "loss": 0.2176, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.900990099009901, | |
| "grad_norm": 2.092095136642456, | |
| "learning_rate": 2.5988083057666533e-06, | |
| "loss": 0.1992, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 62, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4959013881077760.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |