Arguments related to the training process itself. For all parameters, see: https://huggingface.co/docs/transformers/v4.26.1/en/main_classes/trainer#transformers.TrainingArguments
| 110 | |
| 111 | @dataclass |
| 112 | class TrainingArguments(transformers.TrainingArguments): |
| 113 | """ |
| 114 | Arguments related to the training process itself. For all parameters, see: https://huggingface.co/docs/transformers/v4.26.1/en/main_classes/trainer#transformers.TrainingArguments |
| 115 | """ |
| 116 | |
| 117 | logging_first_step: Optional[bool] = field( |
| 118 | default=True, |
| 119 | metadata={"help": ("Whether to log and evaluate the first global_step or not.")}, |
| 120 | ) |
| 121 | optim: Optional[str] = field(default="adamw_torch") |