| { |
| "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": 1.5332, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 52.60580622595313, |
| "eval_f1": 62.3070838425992, |
| "eval_runtime": 8.5312, |
| "eval_samples_per_second": 1005.367, |
| "eval_steps_per_second": 3.165, |
| "step": 275 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.8065, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 54.69278302436749, |
| "eval_f1": 63.26903650858902, |
| "eval_runtime": 7.4659, |
| "eval_samples_per_second": 1148.831, |
| "eval_steps_per_second": 3.616, |
| "step": 550 |
| } |
| ], |
| "max_steps": 2750, |
| "num_train_epochs": 10, |
| "total_flos": 174079118147584.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
