| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9846153846153847, | |
| "eval_steps": 500, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.975000000000002e-06, | |
| "loss": 12.7837, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.950000000000001e-06, | |
| "loss": 12.4595, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.925e-06, | |
| "loss": 11.9117, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.9e-06, | |
| "loss": 11.662, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.875000000000001e-06, | |
| "loss": 11.4278, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.85e-06, | |
| "loss": 11.1398, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.825000000000002e-06, | |
| "loss": 10.9135, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.800000000000001e-06, | |
| "loss": 10.8274, | |
| "step": 8 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 400, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 539703011966976.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |