diff --git a/server/text_generation_server/models/flash_causal_lm.py b/server/text_generation_server/models/flash_causal_lm.py
index 5aa7a568..ee72c033 100644
--- a/server/text_generation_server/models/flash_causal_lm.py
+++ b/server/text_generation_server/models/flash_causal_lm.py
@@ -1101,7 +1101,7 @@ class FlashCausalLM(Model):
             next_token_texts = []
             left = 0
 
-            logger.info(f"Accepted ids {n_accepted_ids}")
+            logger.debug(f"Accepted ids {n_accepted_ids}")
 
             current_stopped = False
             for j in range(index, index + n_accepted_ids):