configs.py

# coding=utf-8
# coding=utf-8
# Copyright 2023 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import dataclasses
from dataclasses import dataclass, field
from typing import Any, Dict, List, NewType, Optional, Tuple


@dataclass
class DataArguments:
    """
    Arguments pertaining to what data we are going to input our model for training and eval.
    """

    chat_template: Optional[str] = field(default=None, metadata={"help": "The chat template to use."})
    dataset_mixer: Optional[Dict[str, float]] = field(
        default=None,
        metadata={"help": ("Datasets and their proportions to be used for training ift/rl.")},
    )
    dataset_splits: Optional[List[str]] = field(
        default_factory=lambda: ["train", "test"],
        metadata={"help": ("List of train test splits to use in the dataset")},
    )
    max_train_samples: Optional[int] = field(
        default=None,
        metadata={
            "help": (
                "For debugging purposes or quicker training, truncate the number of training examples to this "
                "value if set."
            )
        },
    )
    max_eval_samples: Optional[int] = field(
        default=None,
        metadata={
            "help": (
                "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
                "value if set."
            )
        },
    )
    preprocessing_num_workers: Optional[int] = field(
        default=None,
        metadata={"help": "The number of processes to use for the preprocessing."},
    )
    truncation_side: Optional[str] = field(
        default=None, metadata={"help": "Truncation side to use for the tokenizer."}
    )