| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 2436, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.3842364532019706e-05, | |
| "loss": 1.6283, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.7684729064039407e-05, | |
| "loss": 1.4531, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.1527093596059112e-05, | |
| "loss": 1.1524, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.369458128078818e-06, | |
| "loss": 0.9436, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 2436, | |
| "total_flos": 7632935533582848.0, | |
| "train_loss": 1.2240433465866816, | |
| "train_runtime": 1087.7277, | |
| "train_samples_per_second": 35.808, | |
| "train_steps_per_second": 2.24 | |
| } | |
| ], | |
| "max_steps": 2436, | |
| "num_train_epochs": 3, | |
| "total_flos": 7632935533582848.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |