reward weighting update

opentensor · Aug 23, 2023 · e0eeb05 · e0eeb05
1 parent 4d9ef17
commit e0eeb05
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/openvalidators/reward/config.py b/openvalidators/reward/config.py
@@ -36,8 +36,8 @@ class DefaultRewardFrameworkConfig:
     """Reward framework default configuration.
     Note: All the weights should add up to 1.0.
     """
-    dpo_model_weight: float = 0.2
+    dpo_model_weight: float = 0.4
     rlhf_model_weight: float = 0.4
-    reciprocate_model_weight: float = 0.4
+    reciprocate_model_weight: float = 0.2
     dahoas_model_weight: float = 0
     prompt_model_weight: float = 0