| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "global_step": 732, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9538461538461539, |
| "eval_loss": 0.5094375014305115, |
| "eval_runtime": 15.142, |
| "eval_samples_per_second": 64.39, |
| "eval_steps_per_second": 8.057, |
| "step": 366 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 6.338797814207651e-06, |
| "loss": 1.3158, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.961025641025641, |
| "eval_loss": 0.31403589248657227, |
| "eval_runtime": 15.5001, |
| "eval_samples_per_second": 62.903, |
| "eval_steps_per_second": 7.871, |
| "step": 732 |
| } |
| ], |
| "max_steps": 732, |
| "num_train_epochs": 2, |
| "total_flos": 774873285313920.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
