| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 3.6542, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.009247481060283e-05, | |
| "loss": 3.2898, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00013197813593027427, | |
| "loss": 3.0885, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.860000000000001e-05, | |
| "loss": 2.9368, | |
| "step": 20 | |
| } | |
| ], | |
| "max_steps": 24, | |
| "num_train_epochs": 3, | |
| "total_flos": 22732406784000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |