fastchat/train/train.py [184:206]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.input_ids = data_dict["input_ids"]
        self.labels = data_dict["labels"]
        self.attention_mask = data_dict["attention_mask"]

    def __len__(self):
        return len(self.input_ids)

    def __getitem__(self, i) -> Dict[str, torch.Tensor]:
        return dict(
            input_ids=self.input_ids[i],
            labels=self.labels[i],
            attention_mask=self.attention_mask[i],
        )


class LazySupervisedDataset(Dataset):
    """Dataset for supervised fine-tuning."""

    def __init__(self, raw_data, tokenizer: transformers.PreTrainedTokenizer):
        super(LazySupervisedDataset, self).__init__()
        self.tokenizer = tokenizer

        rank0_print("Formatting inputs...Skip in lazy mode")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



fastchat/train/train_baichuan.py [192:214]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.input_ids = data_dict["input_ids"]
        self.labels = data_dict["labels"]
        self.attention_mask = data_dict["attention_mask"]

    def __len__(self):
        return len(self.input_ids)

    def __getitem__(self, i) -> Dict[str, torch.Tensor]:
        return dict(
            input_ids=self.input_ids[i],
            labels=self.labels[i],
            attention_mask=self.attention_mask[i],
        )


class LazySupervisedDataset(Dataset):
    """Dataset for supervised fine-tuning."""

    def __init__(self, raw_data, tokenizer: transformers.PreTrainedTokenizer):
        super(LazySupervisedDataset, self).__init__()
        self.tokenizer = tokenizer

        rank0_print("Formatting inputs...Skip in lazy mode")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -