| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.1, |
| "global_step": 2500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 2.97e-05, |
| "loss": 8.3052, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 2.94e-05, |
| "loss": 3.639, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 2.91e-05, |
| "loss": 2.9626, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 2.88e-05, |
| "loss": 2.5033, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 2.8499999999999998e-05, |
| "loss": 2.1567, |
| "step": 2500 |
| } |
| ], |
| "max_steps": 50000, |
| "num_train_epochs": 2, |
| "total_flos": 8992845987840000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
