| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5371393492940454, | |
| "eval_steps": 500, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0009846531614487416, | |
| "loss": 0.5762, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0009693063228974831, | |
| "loss": 0.6042, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0009539594843462247, | |
| "loss": 0.6024, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0009386126457949663, | |
| "loss": 0.6057, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0009232658072437078, | |
| "loss": 0.6143, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0009079189686924494, | |
| "loss": 0.6081, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.000892572130141191, | |
| "loss": 0.611, | |
| "step": 3500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 32580, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 1852812344426496.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |