separate benchmark / app eval

This commit is contained in:
Xi Yan 2024-11-05 16:54:31 -08:00
parent 979cd4cd44
commit 4a64f98c82
2 changed files with 10 additions and 18 deletions

View file

@ -17,7 +17,7 @@ class EvalTaskDef(BaseModel):
scoring_functions: List[str]
metadata: Dict[str, Any] = Field(
default_factory=dict,
description="Metadata for this evaluation task (e.g. from GECO)",
description="Metadata for this evaluation task",
)