Please tell me, when I try to convert my trained model into a pte file, do I need to pre-load the model's weights?

[tayloryoung-o]

    for i, (input_data, labels) in enumerate(self.train_loader):
      example_shape = input_data.shape
    example_args = (torch.randn(example_shape),)
    
    self.model.eval()
     
    # 1. torch.export: Defines the program with the ATen operator set.
    aten_dialect = export(self.model,example_args)
    # 2. to_edge: Make optimizations for Edge devices
    edge_program = to_edge(aten_dialect)

    # 3. to_executorch: Convert the graph to an ExecuTorch program
    executorch_program = edge_program.to_executorch()

    # 4. Save the compiled .pte program
    with open("Transformer.pte", "wb") as file:
        file.write(executorch_program.buffer)

When I use the above code, the pte file is successfully generated, but after getting the following result, I can't continue to run

I 00:00:00.062442 executorch:executor_runner.cpp:73] Model file ../Transformer.pte is loaded.
I 00:00:00.062491 executorch:executor_runner.cpp:82] Using method forward
I 00:00:00.062504 executorch:executor_runner.cpp:129] Setting up planned buffer 0, size 1204903600.
I 00:00:00.916517 executorch:executor_runner.cpp:152] Method loaded.
I 00:00:00.920503 executorch:executor_runner.cpp:162] Inputs prepared.
^C