| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.847380410022779, | |
| "global_step": 2500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.6203492786636296e-05, | |
| "loss": 0.3026, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9689652127847431, | |
| "eval_f1": 0.8772689578918271, | |
| "eval_loss": 0.10503004491329193, | |
| "eval_precision": 0.8721260419529174, | |
| "eval_recall": 0.8824728890536657, | |
| "eval_runtime": 13.1957, | |
| "eval_samples_per_second": 246.292, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.240698557327259e-05, | |
| "loss": 0.1276, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.610478359908885e-06, | |
| "loss": 0.0892, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9735858496674319, | |
| "eval_f1": 0.8989136438961518, | |
| "eval_loss": 0.0925988033413887, | |
| "eval_precision": 0.8929126657521719, | |
| "eval_recall": 0.9049958290851794, | |
| "eval_runtime": 13.204, | |
| "eval_samples_per_second": 246.138, | |
| "step": 1756 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 4.8139711465451785e-06, | |
| "loss": 0.0672, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.0174639331814731e-06, | |
| "loss": 0.0536, | |
| "step": 2500 | |
| } | |
| ], | |
| "max_steps": 2634, | |
| "num_train_epochs": 3, | |
| "total_flos": 1334617302236400, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |