| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.17135023989033585, |
| "eval_steps": 100, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 8.993468091981983e-06, |
| "loss": 0.6658, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 8.973891330515647e-06, |
| "loss": 0.4496, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 8.941326548314408e-06, |
| "loss": 0.3875, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 8.895868283228027e-06, |
| "loss": 0.3646, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 8.837648503792598e-06, |
| "loss": 0.3664, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 8.766836226116608e-06, |
| "loss": 0.3676, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 8.683637023215312e-06, |
| "loss": 0.3075, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 8.588292428217834e-06, |
| "loss": 0.2945, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 8.481079233179522e-06, |
| "loss": 0.3539, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 8.362308685535184e-06, |
| "loss": 0.2699, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.17, |
| "eval_accuracy": 0.0, |
| "eval_loss": 0.27337193489074707, |
| "eval_runtime": 53.8814, |
| "eval_samples_per_second": 72.214, |
| "eval_steps_per_second": 12.045, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 583, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "total_flos": 0.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
