| { | |
| "best_metric": 3.2145681381225586, | |
| "best_model_checkpoint": "output/mc-ride/checkpoint-32", | |
| "epoch": 1.0, | |
| "global_step": 32, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012909979873429716, | |
| "loss": 3.7047, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010671211798514472, | |
| "loss": 3.5465, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.532397582660788e-05, | |
| "loss": 3.6064, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 3.4545, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.557148289931624e-05, | |
| "loss": 3.4447, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3181297643383925e-06, | |
| "loss": 3.3188, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.2145681381225586, | |
| "eval_runtime": 2.2812, | |
| "eval_samples_per_second": 21.042, | |
| "eval_steps_per_second": 2.63, | |
| "step": 32 | |
| } | |
| ], | |
| "max_steps": 32, | |
| "num_train_epochs": 1, | |
| "total_flos": 33314734080000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |