| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 49.08730158730159, | |
| "eval_steps": 500, | |
| "global_step": 550, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 1.1145, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 6.349206349206349e-05, | |
| "loss": 0.5522, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 9.523809523809524e-05, | |
| "loss": 0.36, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 36.03, | |
| "learning_rate": 0.00012698412698412698, | |
| "loss": 0.2707, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 45.04, | |
| "learning_rate": 0.00015873015873015873, | |
| "loss": 0.1626, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 6300, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 3.414361306352845e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |