| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 6414, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.6195, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6526795029640198, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.8335, | |
| "eval_samples_per_second": 45.678, | |
| "eval_steps_per_second": 5.737, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6168, | |
| "step": 4276 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6258916258811951, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.7299, | |
| "eval_samples_per_second": 45.887, | |
| "eval_steps_per_second": 5.763, | |
| "step": 4276 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.616, | |
| "step": 6414 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.624345064163208, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.7295, | |
| "eval_samples_per_second": 45.888, | |
| "eval_steps_per_second": 5.763, | |
| "step": 6414 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 6414, | |
| "total_flos": 1.6048929796061184e+16, | |
| "train_loss": 0.0, | |
| "train_runtime": 0.0199, | |
| "train_samples_per_second": 1287840.29, | |
| "train_steps_per_second": 321997.724 | |
| } | |
| ], | |
| "max_steps": 6414, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.6048929796061184e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |