def test_eos_pad():
    from datasets import load_dataset
    import torch
    from transformers import GPT2Tokenizer, GPT2LMHeadModel

    raw_text_batch = 'a'

    tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
    # print(f'{tokenizer.eos_token=}')
    # print(f'{tokenizer.eos_token_id=}')
    # print(f'{tokenizer.pad_token=}')
    # print(f'{tokenizer.pad_token_id=}')

    # print(f'{raw_text_batch=}')
    # tokenize_batch = tokenizer(raw_text_batch, padding="max_length", max_length=5, truncation=True, return_tensors="pt")
    # print(f'{tokenize_batch=}')

    if tokenizer.pad_token_id is None:
        tokenizer.pad_token = tokenizer.eos_token
    probe_network = GPT2LMHeadModel.from_pretrained("gpt2")
    device = torch.device(f"cuda:{0}" if torch.cuda.is_available() else "cpu")
    probe_network = probe_network.to(device)

    print(f'{tokenizer.eos_token=}')
    print(f'{tokenizer.eos_token_id=}')
    print(f'{tokenizer.pad_token=}')
    print(f'{tokenizer.pad_token_id=}')

    print(f'{raw_text_batch=}')
    tokenize_batch = tokenizer(raw_text_batch, padding="max_length", max_length=5, truncation=True, return_tensors="pt")
    print(f'{tokenize_batch=}')
    print('Done')