fix bugs in gathering state dict

Author: bursteratom

src/transformers/modeling_utils.py

@@ -3667,7 +3667,8 @@ def save_pretrained(
         for key, value in state_dict.items():
             if hasattr(value, "_local_tensor"):
                 gathered_state_dict[key] = value.to_local()
-            gathered_state_dict[key] = value
+            else:
+                gathered_state_dict[key] = value
 
         del state_dict
         state_dict = gathered_state_dict