diff --git a/src/transformers/models/falcon/modeling_falcon.py b/src/transformers/models/falcon/modeling_falcon.py
index 5c3de182b2a..db8546ffa59 100644
--- a/src/transformers/models/falcon/modeling_falcon.py
+++ b/src/transformers/models/falcon/modeling_falcon.py
@@ -1094,6 +1094,12 @@ class FalconModel(FalconPreTrainedModel):
 
         hidden_states = inputs_embeds
 
+        if self.gradient_checkpointing and self.training:
+            if use_cache:
+                logger.warning(
+                    "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
+                )
+                use_cache = False
         presents = () if use_cache else None
         all_self_attentions = () if output_attentions else None
         all_hidden_states = () if output_hidden_states else None
@@ -1137,11 +1143,6 @@ class FalconModel(FalconPreTrainedModel):
                 all_hidden_states = all_hidden_states + (hidden_states,)
 
             if self.gradient_checkpointing and self.training:
-                if use_cache:
-                    logger.warning(
-                        "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
-                    )
-                    use_cache = False
 
                 def create_custom_forward(module):
                     def custom_forward(*inputs):