| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "global_step": 488, |
| "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": 1.12, |
| "step": 122 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 68.46447354852016, |
| "eval_f1": 72.17371786060637, |
| "eval_runtime": 9.344, |
| "eval_samples_per_second": 1037.781, |
| "eval_steps_per_second": 3.318, |
| "step": 122 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.5279, |
| "step": 244 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 69.71228214911828, |
| "eval_f1": 72.82528738140188, |
| "eval_runtime": 8.584, |
| "eval_samples_per_second": 1129.657, |
| "eval_steps_per_second": 3.611, |
| "step": 244 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4649, |
| "step": 366 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 70.83634113643394, |
| "eval_f1": 73.46335152671074, |
| "eval_runtime": 8.5652, |
| "eval_samples_per_second": 1132.142, |
| "eval_steps_per_second": 3.619, |
| "step": 366 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4205, |
| "step": 488 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_exact_match": 71.46540167061978, |
| "eval_f1": 74.07958546885926, |
| "eval_runtime": 8.561, |
| "eval_samples_per_second": 1132.691, |
| "eval_steps_per_second": 3.621, |
| "step": 488 |
| } |
| ], |
| "max_steps": 1220, |
| "num_train_epochs": 10, |
| "total_flos": 153959423541248.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
