diff --git a/evoprompt/task/text_classification.py b/evoprompt/task/text_classification.py
index 1e19766de03ce76ec451939452d9ebcd06ce22b4..2c40725ee927a0605f6acad89a5c6ac8eb174f0e 100644
--- a/evoprompt/task/text_classification.py
+++ b/evoprompt/task/text_classification.py
@@ -49,7 +49,7 @@ class TextClassification(Task):
         class_mapping = self._get_label_mapping()
         response = response.lower()
         if response not in class_mapping:
-            logger.warning(f"Invalid answer: {response}")
+            logger.debug(f"Invalid answer: {response}")
             return "failed"
         prediction = class_mapping[response]
         classification_result = "incorrect" if prediction != gold_label else "correct"