fix batch size calculation

This commit is contained in:
Wing Lian
2023-05-31 14:11:32 -04:00
parent f94dd626f0
commit 5a631b305b
2 changed files with 6 additions and 3 deletions

View File

@@ -233,6 +233,7 @@ def load_tokenized_prepared_datasets(
datasets.append(ds_wrapper)
else:
logging.error(f"unhandled prompt tokenization strategy: {d.type}")
raise ValueError(f"unhandled prompt tokenization strategy: {d.type}")
logging.info("tokenizing, merging, and shuffling master dataset")
samples: List[int] = []