| { | |
| "best_metric": 0.14495012164115906, | |
| "best_model_checkpoint": "./test-small-bert-with-loss-weight/checkpoint-1500", | |
| "epoch": 1.4763779527559056, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.1797900262467194e-05, | |
| "loss": 0.1546, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.8429757067519668, | |
| "eval_f1": 0.27041574613376174, | |
| "eval_loss": 0.14738939702510834, | |
| "eval_precision": 0.8877752868257945, | |
| "eval_recall": 0.1594996090695856, | |
| "eval_runtime": 8.7195, | |
| "eval_samples_per_second": 1128.732, | |
| "eval_steps_per_second": 4.473, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.3595800524934386e-05, | |
| "loss": 0.1506, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_accuracy": 0.8417091726463214, | |
| "eval_f1": 0.2548480963718129, | |
| "eval_loss": 0.14584653079509735, | |
| "eval_precision": 0.9028258362168397, | |
| "eval_recall": 0.14836401544767455, | |
| "eval_runtime": 8.6401, | |
| "eval_samples_per_second": 1139.107, | |
| "eval_steps_per_second": 4.514, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.5393700787401574e-05, | |
| "loss": 0.1485, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_accuracy": 0.8470173770208351, | |
| "eval_f1": 0.30824260667305176, | |
| "eval_loss": 0.14495012164115906, | |
| "eval_precision": 0.8806120169756534, | |
| "eval_recall": 0.18681735257184828, | |
| "eval_runtime": 8.8318, | |
| "eval_samples_per_second": 1114.387, | |
| "eval_steps_per_second": 4.416, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 3048, | |
| "num_train_epochs": 3, | |
| "total_flos": 465852985957632.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |