arguments.py

#!/usr/bin/python
# -*- encoding: utf-8 -*-

from dataclasses import dataclass, field
from typing import Optional, Union
import os
from transformers import TrainingArguments

@dataclass
class DataTrainingArguments:
    """
    Arguments control input data path, mask behaviors
    """

    dataset_name: Optional[str] = field(
        default=None, metadata={"help": "The name of the dataset to use (via the datasets library)."}
    )
    dataset_config_name: Optional[str] = field(
        default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
    )
    train_dir: str = field(
        default=None, metadata={"help": "Path to train directory"}
    )
    train_path: str = field(
        default=None, metadata={"help": "Path to train data"}
    )
    train_file: Optional[str] = field(default=None, metadata={"help": "The input training data file (a text file)."})
    overwrite_cache: bool = field(
        default=False, metadata={"help": "Overwrite the cached training and evaluation sets"}
    )

    preprocessing_num_workers: Optional[int] = field(
        default=None,
        metadata={"help": "The number of processes to use for the preprocessing."},
    )
    pad_to_max_length: bool = field(
        default=False,
        metadata={
            "help": "Whether to pad all samples to `max_seq_length`. "
                    "If False, will pad the samples dynamically when batching to the maximum length in the batch."
        },
    )
    ignore_pad_token_for_loss: bool = field(
        default=True,
        metadata={
            "help": "Whether to ignore the tokens corresponding to padded labels in the loss computation or not."
        },
    )
    source_prefix: Optional[str] = field(
        default="", metadata={"help": "A prefix to add before every source text (useful for T5 models)."}
    )
    forced_bos_token: Optional[str] = field(
        default=None,
        metadata={
            "help": (
                "The token to force as the first generated token after the decoder_start_token_id."
                "Useful for multilingual models like mBART where the first generated token"
                "needs to be the target language token (Usually it is the target language token)"
            )
        },
    )




@dataclass
class ModelArguments:
    """
    Arguments control model config, decoder head config
    """

    model_name_or_path: Optional[str] = field(
        default=None,
        metadata={
            "help": "The model checkpoint for weights initialization."
                    "Don't set if you want to train a model from scratch."
        },
    )
    model_type: Optional[str] = field(
        default=None,
    )
    config_name: Optional[str] = field(
        default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
    )
    tokenizer_name: Optional[str] = field(
        default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
    )
    cache_dir: Optional[str] = field(
        default=None,
        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
    )
    use_fast_tokenizer: bool = field(
        default=False,
        metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
    )
    use_auth_token: bool = field(
        default=False,
        metadata={
            "help": (
                "Will use the token generated when running `huggingface-cli login` (necessary to use this script "
                "with private models)."
            )
        },
    )
    resize_position_embeddings: Optional[bool] = field(
        default=None,
        metadata={
            "help": (
                "Whether to automatically resize the position embeddings if `max_source_length` exceeds "
                "the model's position embeddings."
            )
        },
    )
    quantization_bit: Optional[int] = field(
        default=None
    )
    pre_seq_len: Optional[int] = field(
        default=None
    )
    prefix_projection: bool = field(
        default=False
    )
    ptuning_checkpoint: str = field(
        default=None, metadata={"help": "Path to p-tuning v2 checkpoints"}
    )




@dataclass
class FinetuneArguments(TrainingArguments):
    lora_rank: int = field(default=8)
    max_len: int = field(default=700)
    max_input_len: int = field(default=350)
    warmup_ratio: float = field(default=0.1)
    remove_unused_columns: bool = field(default=False)
    local_rank: int = field(default=-1, metadata={"help": "For distributed training: local_rank"})