yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-10-14 17:52:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Testing

Browse Source
This commit is contained in:
Jake Poznanski 2025-08-21 17:17:43 +00:00
parent 892429965a
commit 5556e204cf
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
olmocr/train/grpo_train.py
View File

@ -170,10 +170,11 @@ class OlmOCRDataset(Dataset):
# Return None if processing fails # Return None if processing fails
return None return None
def simple_length_reward(completions_ids, **kwargs): def simple_length_reward(**kwargs):
"""Reward function that assigns higher scores to longer completions (in terms of token count).""" """Reward function that assigns higher scores to longer completions (in terms of token count)."""
logger.info(f"Reward function called {kwargs}") logger.info(f"Reward function called {kwargs}")
return [float(len(ids)) for ids in completions_ids] # return [float(len(ids)) for ids in completions_ids]
return random.choice([0.1, 0.5])
def main(): def main():