From 65b6519447d12affc4bf4027b59b1d9af244df0c Mon Sep 17 00:00:00 2001
From: Salman Mohammadi <salman.mohammadi@outlook.com>
Date: Wed, 5 Feb 2025 18:13:05 +0000
Subject: [PATCH] adding 'reward_processing_classes'

---
 src/axolotl/core/trainers/grpo/__init__.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/axolotl/core/trainers/grpo/__init__.py b/src/axolotl/core/trainers/grpo/__init__.py
index b04373a95..0a7a22f2d 100644
--- a/src/axolotl/core/trainers/grpo/__init__.py
+++ b/src/axolotl/core/trainers/grpo/__init__.py
@@ -53,6 +53,10 @@ class GRPOStrategy:
             for reward_func_fqn in cfg.grpo_reward_funcs:
                 reward_funcs.append(cls.get_reward_func(reward_func_fqn))
             trainer_kwargs["reward_funcs"] = reward_funcs
+        if cfg.grpo_reward_processing_classes:
+            trainer_kwargs[
+                "reward_processing_classes"
+            ] = cfg.grpo_reward_processing_classes
         return trainer_kwargs
 
     @classmethod