Fix for non-contiguous label tensors in VisonEncoderDecoder (#21582)

* add prints

* add shape

* add reshape

* clean up

src/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py

@@ -625,7 +625,7 @@ class VisionEncoderDecoderModel(PreTrainedModel):
         if labels is not None:
             logits = decoder_outputs.logits if return_dict else decoder_outputs[0]
             loss_fct = CrossEntropyLoss()
-            loss = loss_fct(logits.reshape(-1, self.decoder.config.vocab_size), labels.view(-1))
+            loss = loss_fct(logits.reshape(-1, self.decoder.config.vocab_size), labels.reshape(-1))
 
         if not return_dict:
             if loss is not None: