| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 4276, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.5566666666666666e-05, | |
| "loss": 0.6212, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6539720296859741, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.7284, | |
| "eval_samples_per_second": 45.89, | |
| "eval_steps_per_second": 5.764, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.6700000000000002e-05, | |
| "loss": 0.62, | |
| "step": 4276 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6409146785736084, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 22.7182, | |
| "eval_samples_per_second": 45.91, | |
| "eval_steps_per_second": 5.766, | |
| "step": 4276 | |
| } | |
| ], | |
| "max_steps": 10690, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.0699286530707456e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |