| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.1130899376669634, |
| "global_step": 2500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.22, |
| "learning_rate": 5e-05, |
| "loss": 1.3082, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 4.37374749498998e-05, |
| "loss": 1.0848, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 3.74749498997996e-05, |
| "loss": 1.0004, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 3.12124248496994e-05, |
| "loss": 0.9697, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 2.49498997995992e-05, |
| "loss": 0.9269, |
| "step": 2500 |
| } |
| ], |
| "max_steps": 4492, |
| "num_train_epochs": 2, |
| "total_flos": 955872881915904.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
