| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.4925373134328357, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1963, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3e-05, | |
| "loss": 0.136, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1295, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0863, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0, | |
| "loss": 0.0649, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 1000, | |
| "num_train_epochs": 2, | |
| "save_steps": 200, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |