Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@



# torchtune

[![Unit Test](https://github.com/pytorch/torchtune/actions/workflows/unit_test.yaml/badge.svg?branch=main)](https://github.com/pytorch/torchtune/actions/workflows/unit_test.yaml)
Expand Down
8 changes: 0 additions & 8 deletions torchtune/dev/rl/rewards.py
Original file line number Diff line number Diff line change
Expand Up @@ -296,21 +296,13 @@ def batched_rewards(
metadata = {"func_names": [f.__name__ for f in reward_funcs]}

for b in range(batch_size):

for g in range(grpo_size):

answer = answers[b][g]

text_completion = tokenizer.decode(completions[b, g].tolist())

cot, potential_answer = extract_tags(f"<think>{text_completion}")

for rw_idx, reward_func in enumerate(reward_funcs):

reward, success = reward_func(cot, answer, potential_answer)

rewards_tensor[b, g, rw_idx] += reward

successes_tensor[b, g, rw_idx] += success

return rewards_tensor, successes_tensor, metadata
Loading