| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.228, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9846984698469847, | |
| "eval_f1": 0.9792429792429792, | |
| "eval_loss": 0.06820278614759445, | |
| "eval_precision": 0.9901234567901235, | |
| "eval_recall": 0.9685990338164251, | |
| "eval_runtime": 21.3752, | |
| "eval_samples_per_second": 51.976, | |
| "eval_steps_per_second": 6.503, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0644, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9963996399639964, | |
| "eval_f1": 0.9951573849878934, | |
| "eval_loss": 0.020056167617440224, | |
| "eval_precision": 0.9975728155339806, | |
| "eval_recall": 0.9927536231884058, | |
| "eval_runtime": 13.8433, | |
| "eval_samples_per_second": 80.256, | |
| "eval_steps_per_second": 10.041, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0193, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 1500, | |
| "num_train_epochs": 3, | |
| "total_flos": 3157332664320000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |