tangger/Search-R1
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix reward bug

Browse Source
This commit is contained in:
PeterGriffinJin
2025-03-13 19:18:56 +00:00
parent ff85cb7f1e
commit 118c6e7361
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
verl/trainer/main_ppo.py
View File

@@ -23,7 +23,7 @@ import re
import numpy as np import numpy as np
def _select_rm_score_fn(data_source): def _select_rm_score_fn(data_source):
if "nq" in data_source: if data_source in ['nq', 'triviaqa', 'popqa', 'hotpotqa', '2wikimultihopqa', 'musique', 'bamboogle']:
return qa_em.compute_score_em return qa_em.compute_score_em
else: else:
raise NotImplementedError raise NotImplementedError