Fix gradient checkpointing bug in switch transformer (#22081)

src/transformers/models/switch_transformers/modeling_switch_transformers.py

@@ -1039,6 +1039,13 @@ class SwitchTransformersStack(SwitchTransformersPreTrainedModel):
         else:
             encoder_extended_attention_mask = None
 
+        if self.gradient_checkpointing and self.training:
+            if use_cache:
+                logger.warning_once(
+                    "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
+                )
+                use_cache = False
+
         # Prepare head mask if needed
         head_mask = self.get_head_mask(head_mask, self.config.num_layers)
         cross_attn_head_mask = self.get_head_mask(cross_attn_head_mask, self.config.num_layers)
@@ -1060,11 +1067,6 @@ class SwitchTransformersStack(SwitchTransformersPreTrainedModel):
                 all_hidden_states = all_hidden_states + (hidden_states,)
 
             if self.gradient_checkpointing and self.training:
-                if use_cache:
-                    logger.warning_once(
-                        "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
-                    )
-                    use_cache = False
 
                 def create_custom_forward(module):
                     def custom_forward(*inputs):