| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "global_step": 548, |
| "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": 1.4855, |
| "step": 274 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 72.56616532587152, |
| "eval_f1": 76.19648264629018, |
| "eval_runtime": 3.3219, |
| "eval_samples_per_second": 2581.933, |
| "eval_steps_per_second": 8.128, |
| "step": 274 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.7957, |
| "step": 548 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 73.06750612102134, |
| "eval_f1": 76.60875533208507, |
| "eval_runtime": 2.9408, |
| "eval_samples_per_second": 2916.565, |
| "eval_steps_per_second": 9.181, |
| "step": 548 |
| } |
| ], |
| "max_steps": 2740, |
| "num_train_epochs": 10, |
| "total_flos": 66076463333376.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
