| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.4005602240896358, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.5331465919701216e-05, | |
| "loss": 2.5689, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.0662931839402428e-05, | |
| "loss": 2.5293, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.3891727924346924, | |
| "eval_runtime": 1945.2107, | |
| "eval_samples_per_second": 0.551, | |
| "eval_steps_per_second": 0.138, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.994397759103642e-06, | |
| "loss": 2.4758, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 2142, | |
| "num_train_epochs": 2, | |
| "total_flos": 3135504384000000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |