| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "global_step": 432, | |
| "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": 1.2026, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 72.19307450157397, | |
| "eval_f1": 75.25003702130245, | |
| "eval_runtime": 3.4782, | |
| "eval_samples_per_second": 2465.906, | |
| "eval_steps_per_second": 7.763, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4771, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 72.21639267809257, | |
| "eval_f1": 75.8717601351557, | |
| "eval_runtime": 3.0887, | |
| "eval_samples_per_second": 2776.861, | |
| "eval_steps_per_second": 8.741, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4296, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_exact_match": 72.77602891453888, | |
| "eval_f1": 75.97727142673193, | |
| "eval_runtime": 3.054, | |
| "eval_samples_per_second": 2808.416, | |
| "eval_steps_per_second": 8.841, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4035, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_exact_match": 72.58948350239011, | |
| "eval_f1": 76.00974757668295, | |
| "eval_runtime": 3.0528, | |
| "eval_samples_per_second": 2809.589, | |
| "eval_steps_per_second": 8.844, | |
| "step": 432 | |
| } | |
| ], | |
| "max_steps": 1080, | |
| "num_train_epochs": 10, | |
| "total_flos": 51701511880704.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |