| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "global_step": 216, |
| "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": 0.8824, |
| "step": 108 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 71.31864288212662, |
| "eval_f1": 76.04683751043017, |
| "eval_runtime": 8.1741, |
| "eval_samples_per_second": 1049.295, |
| "eval_steps_per_second": 3.303, |
| "step": 108 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4402, |
| "step": 216 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 73.8719832109129, |
| "eval_f1": 76.89260705612574, |
| "eval_runtime": 7.5361, |
| "eval_samples_per_second": 1138.128, |
| "eval_steps_per_second": 3.583, |
| "step": 216 |
| } |
| ], |
| "max_steps": 1080, |
| "num_train_epochs": 10, |
| "total_flos": 67913918709760.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
