fix reward bug

2025-03-13 19:18:56 +00:00
parent ff85cb7f1e
commit 118c6e7361
1 changed files with 1 additions and 1 deletions
--- a/verl/trainer/main_ppo.py
+++ b/verl/trainer/main_ppo.py
@@ -23,7 +23,7 @@ import re
 import numpy as np

 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
    else:
        raise NotImplementedError