Gracefully handle stop > dataset_size with warning

This commit is contained in:
Pyry Takala 2025-11-21 20:04:33 +00:00
parent cd782a1977
commit 85e49943ed

View File

@ -36,12 +36,14 @@ class Task:
start = self.start start = self.start
if self.stop is not None: if self.stop is not None:
num_ex = self.num_examples() num_ex = self.num_examples()
stop = min(self.stop, num_ex) # Gracefully cap at dataset size
if self.stop > num_ex: if self.stop > num_ex:
raise ValueError( import warnings
warnings.warn(
f"Stop parameter ({self.stop}) exceeds dataset size ({num_ex}). " f"Stop parameter ({self.stop}) exceeds dataset size ({num_ex}). "
f"Please use stop <= {num_ex} or remove the stop parameter to use the full dataset." f"Using {num_ex} examples instead.",
UserWarning
) )
stop = self.stop
else: else:
stop = self.num_examples() stop = self.num_examples()
step = self.step step = self.step