def __init__(self, csv_file, tokenizer, max_length=None, pad_token_id=50256):
    self.data = pd.read_csv(csv_file)
    self.encoded_texts = [tokenizer.encode(text) for text in self.data["Text"]]
    self.max_length = max_length or max(map(len, self.encoded_texts))

    self.encoded_texts = [tokens[:self.max_length] for tokens in self.encoded_texts]
    self.encoded_texts = [
        tokens + [pad_token_id] * (self.max_length - len(tokens))
        for tokens in self.encoded_texts
    ]

        __
        __