| { |
| "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": 1.0794, |
| "step": 108 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 71.20205199953364, |
| "eval_f1": 75.31695248222917, |
| "eval_runtime": 3.5361, |
| "eval_samples_per_second": 2425.525, |
| "eval_steps_per_second": 7.635, |
| "step": 108 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.467, |
| "step": 216 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 72.30966538416696, |
| "eval_f1": 76.08255800934496, |
| "eval_runtime": 3.0269, |
| "eval_samples_per_second": 2833.594, |
| "eval_steps_per_second": 8.92, |
| "step": 216 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4226, |
| "step": 324 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 72.57782441413082, |
| "eval_f1": 76.43131088381374, |
| "eval_runtime": 3.0154, |
| "eval_samples_per_second": 2844.398, |
| "eval_steps_per_second": 8.954, |
| "step": 324 |
| } |
| ], |
| "max_steps": 1080, |
| "num_train_epochs": 10, |
| "total_flos": 38745933873152.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
