| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 3045, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.4532019704433497e-05, | |
| "loss": 1.6412, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.522167487684729e-05, | |
| "loss": 0.7311, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.9064039408866997e-05, | |
| "loss": 0.5043, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.2918719211822661e-05, | |
| "loss": 0.4708, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 6.7610837438423645e-06, | |
| "loss": 0.2924, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.03448275862069e-07, | |
| "loss": 0.2632, | |
| "step": 3000 | |
| } | |
| ], | |
| "max_steps": 3045, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.303221952809243e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |