RuntimeError: Error(s) in loading state_dict for DebertaV2ForMultipleChoice

[amd-vivekag]

Steps to reproduce:

python run.py -t <testname> -b llvm-cpu -d local-task -c x86_64-linux-gnu  --mode=cl-onnx-iree --cleanup=3 --get-metadata -v

Tests failing:

hf_fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-arceasy

Should get following Error/Stacktrace:

Traceback (most recent call last):
  File "/home/vivekag/scratch/AIGShark/nodai/SharkTestSuite_vivekag/SHARK-TestSuite/alt_e2eshark/onnx_tests/helper_classes.py", line 110, in construct_model
    self.export_model()
  File "/home/vivekag/scratch/AIGShark/nodai/SharkTestSuite_vivekag/SHARK-TestSuite/alt_e2eshark/onnx_tests/models/hf_models.py", line 259, in export_model
    super().export_model("O1" if self.name in basic_opt else None)
  File "/home/vivekag/scratch/AIGShark/nodai/SharkTestSuite_vivekag/SHARK-TestSuite/alt_e2eshark/onnx_tests/helper_classes.py", line 78, in export_model
    main_export(
  File "/home/vivekag/scratch/AIGShark/nodai/SharkTestSuite_nightly/nightly.env/lib/python3.10/site-packages/optimum/exporters/onnx/__main__.py", line 305, in main_export
    model = TasksManager.get_model_from_task(
  File "/home/vivekag/scratch/AIGShark/nodai/SharkTestSuite_nightly/nightly.env/lib/python3.10/site-packages/optimum/exporters/tasks.py", line 2283, in get_model_from_task
    model = model_class.from_pretrained(model_name_or_path, **kwargs)
  File "/home/vivekag/scratch/AIGShark/nodai/SharkTestSuite_nightly/nightly.env/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained
    return model_class.from_pretrained(
  File "/home/vivekag/scratch/AIGShark/nodai/SharkTestSuite_nightly/nightly.env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4245, in from_pretrained
    ) = cls._load_pretrained_model(
  File "/home/vivekag/scratch/AIGShark/nodai/SharkTestSuite_nightly/nightly.env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4873, in _load_pretrained_model
    raise RuntimeError(f"Error(s) in loading state_dict for {model.__class__.__name__}:\n\t{error_msg}")
RuntimeError: Error(s) in loading state_dict for DebertaV2ForMultipleChoice:
  size mismatch for classifier.weight: copying a param with shape torch.Size([2, 1024]) from checkpoint, the shape in current model is torch.Size([1, 1024]).
  size mismatch for classifier.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([1]).
  You may consider adding `ignore_mismatched_sizes=True` in the model `from_pretrained` method.