| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9955555555555555, | |
| "global_step": 112, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 1.5179, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 112, | |
| "total_flos": 2.2375521021350707e+17, | |
| "train_loss": 1.532381568636213, | |
| "train_runtime": 408.5144, | |
| "train_samples_per_second": 17.595, | |
| "train_steps_per_second": 0.274 | |
| } | |
| ], | |
| "max_steps": 112, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.2375521021350707e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |