| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.992, | |
| "global_step": 31, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5e-05, | |
| "loss": 13.7576, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.129032258064516e-05, | |
| "loss": 0.761, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.0851829268292683, | |
| "eval_loss": 0.21037571132183075, | |
| "eval_runtime": 1.8873, | |
| "eval_samples_per_second": 52.986, | |
| "eval_steps_per_second": 2.119, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "step": 31, | |
| "total_flos": 938904995758080.0, | |
| "train_loss": 1.0375519144919612, | |
| "train_runtime": 119.5105, | |
| "train_samples_per_second": 8.367, | |
| "train_steps_per_second": 0.259 | |
| } | |
| ], | |
| "max_steps": 31, | |
| "num_train_epochs": 1, | |
| "total_flos": 938904995758080.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |