| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.573394495412844, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.0538990825688075e-05, | |
| "loss": 3.6812, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_cer": 0.8057585825027685, | |
| "eval_loss": 2.628359079360962, | |
| "eval_runtime": 29.7335, | |
| "eval_samples_per_second": 3.363, | |
| "eval_steps_per_second": 0.437, | |
| "step": 500 | |
| } | |
| ], | |
| "max_steps": 2616, | |
| "num_train_epochs": 3, | |
| "total_flos": 4.78498749677568e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |