| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "global_step": 4000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5, |
| "learning_rate": 4.605263157894737e-05, |
| "loss": 3.9918, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 3.9473684210526316e-05, |
| "loss": 3.7733, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 3.289473684210527e-05, |
| "loss": 3.4872, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 2.6315789473684212e-05, |
| "loss": 3.4665, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 1.9736842105263158e-05, |
| "loss": 3.2853, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 1.3157894736842106e-05, |
| "loss": 3.2903, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.5, |
| "learning_rate": 6.578947368421053e-06, |
| "loss": 3.1943, |
| "step": 3500 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 0.0, |
| "loss": 3.1584, |
| "step": 4000 |
| } |
| ], |
| "max_steps": 4000, |
| "num_train_epochs": 4, |
| "total_flos": 1516563449856000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
