| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 520, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.5821785926818848, | |
| "learning_rate": 2.6987179487179488e-05, | |
| "loss": 2.7105, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "grad_norm": 0.6891746520996094, | |
| "learning_rate": 2.057692307692308e-05, | |
| "loss": 2.1701, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "grad_norm": 0.574246883392334, | |
| "learning_rate": 1.4166666666666666e-05, | |
| "loss": 2.0303, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "grad_norm": 0.604869544506073, | |
| "learning_rate": 7.756410256410258e-06, | |
| "loss": 1.9826, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "grad_norm": 0.5710687637329102, | |
| "learning_rate": 1.3461538461538462e-06, | |
| "loss": 1.9492, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 520, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 558562761768960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |