| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "global_step": 550, |
| "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": 1.8579, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 53.16544246239944, |
| "eval_f1": 61.777650329112305, |
| "eval_runtime": 3.7887, |
| "eval_samples_per_second": 2263.858, |
| "eval_steps_per_second": 7.127, |
| "step": 275 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 1.0254, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 54.517896700478026, |
| "eval_f1": 62.363125553309885, |
| "eval_runtime": 3.0652, |
| "eval_samples_per_second": 2798.226, |
| "eval_steps_per_second": 8.809, |
| "step": 550 |
| } |
| ], |
| "max_steps": 2750, |
| "num_train_epochs": 10, |
| "total_flos": 66106662322176.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
