testing config

environments/gsm8k_server.py

@@ -368,8 +368,9 @@ class GSM8kEnv(BaseEnv):
                         percentage_of_range = min(percentage_of_range, 1.0)
                         # Apply linear penalty scaling from 1.0 down to 0.0
                         scores["scores"].append(1.0 - percentage_of_range)
-            if all([scores["scores"][0] == score for score in scores["scores"]]):
-                return None  # If all the same, we return None
+            # NOTE: identical-score filter disabled for testing.
+            # if all([scores["scores"][0] == score for score in scores["scores"]]):
+            #     return None
             return scores
         else:
             # If the gold solution is not parseable, we return None