| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 2103, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.811222063718498e-05, | |
| "loss": 2.1783, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.6224441274369948e-05, | |
| "loss": 1.5465, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.433666191155492e-05, | |
| "loss": 1.3387, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.4488825487398953e-06, | |
| "loss": 1.1576, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 2103, | |
| "total_flos": 601278409310208.0, | |
| "train_loss": 1.535128086904543, | |
| "train_runtime": 406.2688, | |
| "train_samples_per_second": 20.706, | |
| "train_steps_per_second": 5.176 | |
| } | |
| ], | |
| "max_steps": 2103, | |
| "num_train_epochs": 3, | |
| "total_flos": 601278409310208.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |