| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.440922190201729, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.3976945244956775e-05, | |
| "loss": 5.6847, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_bleu1_score": 0.1655, | |
| "eval_bleu2_score": 0.128, | |
| "eval_bleu3_score": 0.1077, | |
| "eval_bleu4_score": 0.0992, | |
| "eval_loss": 5.288726329803467, | |
| "eval_rouge2_fmeasure": 0.082, | |
| "eval_rouge2_precision": 0.0851, | |
| "eval_rouge2_recall": 0.0812, | |
| "eval_runtime": 18.2887, | |
| "eval_samples_per_second": 14.052, | |
| "step": 500 | |
| } | |
| ], | |
| "max_steps": 694, | |
| "num_train_epochs": 2, | |
| "total_flos": 1243649361208320, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |