| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 825, |
| "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": 1.3978, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 53.445260580622595, |
| "eval_f1": 62.83720520244014, |
| "eval_runtime": 8.3325, |
| "eval_samples_per_second": 1029.342, |
| "eval_steps_per_second": 3.24, |
| "step": 275 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.7654, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 54.91430570129416, |
| "eval_f1": 63.90078167100805, |
| "eval_runtime": 7.5502, |
| "eval_samples_per_second": 1135.994, |
| "eval_steps_per_second": 3.576, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.5677, |
| "step": 825 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 55.077532936924335, |
| "eval_f1": 64.05674326781359, |
| "eval_runtime": 7.5583, |
| "eval_samples_per_second": 1134.785, |
| "eval_steps_per_second": 3.572, |
| "step": 825 |
| } |
| ], |
| "max_steps": 2750, |
| "num_train_epochs": 10, |
| "total_flos": 261397011234816.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
