Fix gradient checkpointing bug in Trajectory Transformer (#22125)

src/transformers/models/trajectory_transformer/modeling_trajectory_transformer.py

@@ -533,6 +533,13 @@ class TrajectoryTransformerModel(TrajectoryTransformerPreTrainedModel):
 
         hidden_states = self.drop(token_embeddings + position_embeddings)
 
+        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
+
         presents = () if use_cache else None
         all_self_attentions = () if output_attentions else None
         all_hidden_states = () if output_hidden_states else None
@@ -542,11 +549,6 @@ class TrajectoryTransformerModel(TrajectoryTransformerPreTrainedModel):
                 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):