diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py index 6987b2321a..e3831d3980 100644 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -256,6 +256,8 @@ def grpo_trainer__generate_and_score_completions(function_name, function): replace_part, spacing = found[0] removed_comments = re.sub(r"\#[^\n]{1,}", "", replace_part) splits = removed_comments.split("\n") + print(splits) + print(len(spacing)) print(sum(re.match(rf"{spacing}[^\s]", x) is not None for x in splits)) if sum(re.match(rf"{spacing}[^\s]", x) is not None for x in splits) == 2 and len(spacing) == 8: