| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.995850622406639, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 3.33, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.9021, |
| "step": 100 |
| }, |
| { |
| "epoch": 6.66, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.5015, |
| "step": 200 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.0, |
| "loss": 0.3757, |
| "step": 300 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 300, |
| "total_flos": 1317332914237440.0, |
| "train_loss": 0.5930885314941406, |
| "train_runtime": 183.6839, |
| "train_samples_per_second": 26.241, |
| "train_steps_per_second": 1.633 |
| } |
| ], |
| "max_steps": 300, |
| "num_train_epochs": 10, |
| "total_flos": 1317332914237440.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
