| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "global_step": 40, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 0.5591, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.0001, |
| "loss": 0.1207, |
| "step": 20 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 5e-05, |
| "loss": 0.0467, |
| "step": 30 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 0.0, |
| "loss": 0.0115, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 40, |
| "total_flos": 1.7531787511332864e+17, |
| "train_loss": 0.1845165841281414, |
| "train_runtime": 21.0041, |
| "train_samples_per_second": 30.47, |
| "train_steps_per_second": 1.904 |
| } |
| ], |
| "max_steps": 40, |
| "num_train_epochs": 4, |
| "total_flos": 1.7531787511332864e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
