| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8852985115918773, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.5595923792645104e-05, | |
| "loss": 0.1166, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1165263624280018e-05, | |
| "loss": 0.0882, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.734603455914932e-06, | |
| "loss": 0.0775, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.303943287549845e-06, | |
| "loss": 0.0677, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 2259, | |
| "num_train_epochs": 1, | |
| "total_flos": 3597528092114944.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |