Fix Gradient checkpointing bug BigBird (#21882)

Co-authored-by: saswatmeher <saswatmeher@cse.iitb.ac.in>

src/transformers/models/big_bird/modeling_big_bird.py

@@ -1592,6 +1592,13 @@ class BigBirdEncoder(nn.Module):
         all_self_attentions = () if output_attentions else None
         all_cross_attentions = () if output_attentions and self.config.add_cross_attention else 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
+
         next_decoder_cache = () if use_cache else None
 
         for i, layer_module in enumerate(self.layer):
@@ -1602,11 +1609,6 @@ class BigBirdEncoder(nn.Module):
             past_key_value = past_key_values[i] if past_key_values is not None else 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
 
                 def create_custom_forward(module):
                     def custom_forward(*inputs):