| { | |
| "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": 1.4816354816354817e-05, | |
| "loss": 0.6192, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6443305015563965, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.683, | |
| "eval_samples_per_second": 45.982, | |
| "eval_steps_per_second": 5.775, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 7.408177408177408e-06, | |
| "loss": 0.6177, | |
| "step": 4276 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6296011209487915, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.6675, | |
| "eval_samples_per_second": 46.013, | |
| "eval_steps_per_second": 5.779, | |
| "step": 4276 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.6128, | |
| "step": 6414 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6173180341720581, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.6859, | |
| "eval_samples_per_second": 45.976, | |
| "eval_steps_per_second": 5.775, | |
| "step": 6414 | |
| } | |
| ], | |
| "max_steps": 6414, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.6048929796061184e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |