| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 324, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 3e-05, |
| "loss": 0.9233, |
| "step": 108 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 73.02086976798414, |
| "eval_f1": 76.57325510432632, |
| "eval_runtime": 8.0744, |
| "eval_samples_per_second": 1062.241, |
| "eval_steps_per_second": 3.344, |
| "step": 108 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4382, |
| "step": 216 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 72.61280167890871, |
| "eval_f1": 76.40311241593459, |
| "eval_runtime": 7.4311, |
| "eval_samples_per_second": 1154.198, |
| "eval_steps_per_second": 3.633, |
| "step": 216 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.402, |
| "step": 324 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 74.04686953480238, |
| "eval_f1": 76.91032003827833, |
| "eval_runtime": 7.4536, |
| "eval_samples_per_second": 1150.726, |
| "eval_steps_per_second": 3.622, |
| "step": 324 |
| } |
| ], |
| "max_steps": 1080, |
| "num_train_epochs": 10, |
| "total_flos": 102029926072320.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
