| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 8427, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.911000355998576e-05, | |
| "loss": 2.0667, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.822000711997152e-05, | |
| "loss": 1.382, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.733001067995728e-05, | |
| "loss": 1.2498, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.644001423994304e-05, | |
| "loss": 1.1809, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.55500177999288e-05, | |
| "loss": 1.1255, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 76.79280983916746, | |
| "eval_f1": 85.50356159934326, | |
| "step": 2809 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.4660021359914563e-05, | |
| "loss": 1.0414, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.3770024919900323e-05, | |
| "loss": 0.8871, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.2880028479886081e-05, | |
| "loss": 0.908, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.1990032039871841e-05, | |
| "loss": 0.864, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.1100035599857601e-05, | |
| "loss": 0.868, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.0210039159843361e-05, | |
| "loss": 0.8678, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 79.16745506149479, | |
| "eval_f1": 86.76959997899563, | |
| "step": 5618 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.320042719829121e-06, | |
| "loss": 0.7097, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 8.430046279814883e-06, | |
| "loss": 0.6732, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.540049839800642e-06, | |
| "loss": 0.6801, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.650053399786402e-06, | |
| "loss": 0.6832, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.7600569597721615e-06, | |
| "loss": 0.678, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_exact_match": 79.65941343424787, | |
| "eval_f1": 87.43123506757227, | |
| "step": 8427 | |
| } | |
| ], | |
| "max_steps": 11236, | |
| "num_train_epochs": 4, | |
| "total_flos": 5.284674541505741e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |