| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.0, |
| "learning_rate": 5e-05, |
| "loss": 1.9399, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 50, |
| "total_flos": 1307491660988416.0, |
| "train_loss": 1.93986328125, |
| "train_runtime": 84.3125, |
| "train_samples_per_second": 4.744, |
| "train_steps_per_second": 0.593 |
| } |
| ], |
| "max_steps": 50, |
| "num_train_epochs": 2, |
| "total_flos": 1307491660988416.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
