open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-28 17:29:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix chain sum veRL example for latest veRL (#371)

Browse source 
* fixes for latest verl

* add balance_batch cofg

* 1 -> 2 gpu

* tweaks

* also add raw ids to server script
This commit is contained in:
Oliver Stanley 2025-03-14 19:15:54 +00:00 • committed by GitHub
parent 8a0cacc054
commit bd13b1b92a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 11 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/veRL/chain_sum/main_ppo_custom_reward.py
View file

@ -70,6 +70,7 @@ class ReasoningGymDataset(Dataset):
row_dict["input_ids"] = input_ids[0]
row_dict["attention_mask"] = attention_mask[0]
row_dict["position_ids"] = position_ids[0]
row_dict["raw_prompt_ids"] = self.tokenizer.encode(prompt, add_special_tokens=False)
# encode prompts without chat template
if self.return_raw_chat: