allow non-packing pretraining

Former-commit-id: 3fee5cc5a3db9ce874ad90f2500ec092d904bd4e
This commit is contained in:
hiyouga
2024-03-09 22:21:46 +08:00
parent c631799f5d
commit 4881f4e631
22 changed files with 64 additions and 67 deletions

View File

@@ -78,9 +78,11 @@ class DataArguments:
default=0.0,
metadata={"help": "Size of the development set, should be an integer or a float in range `[0,1)`."},
)
sft_packing: bool = field(
default=False,
metadata={"help": "Packing the questions and answers in the supervised fine-tuning stage."},
packing: Optional[bool] = field(
default=None,
metadata={
"help": "Whether or not to pack the sequences in training. Will automatically enable in pre-training."
},
)
cache_path: Optional[str] = field(
default=None,