| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3e-05, | |
| "loss": 2.9848, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3e-05, | |
| "loss": 3.393, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.625e-05, | |
| "loss": 3.6617, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.25e-05, | |
| "loss": 2.8843, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 3.5456, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.9694, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.125e-05, | |
| "loss": 3.4113, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 7.5e-06, | |
| "loss": 2.6773, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.75e-06, | |
| "loss": 2.9026, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 9, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 787135888097280.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |