File size: 7,210 Bytes
e81015c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
# Copyright 2025 HuggingFace Inc. and the LlamaFactory team.
#
# This code is inspired by the HuggingFace's transformers library.
# https://github.com/huggingface/transformers/blob/v4.40.0/examples/pytorch/language-modeling/run_clm.py
#
# 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.

from dataclasses import asdict, dataclass, field
from typing import Any, Literal, Optional


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

    template: Optional[str] = field(
        default=None,
        metadata={"help": "Which template to use for constructing prompts in training and inference."},
    )
    dataset: Optional[str] = field(
        default=None,
        metadata={"help": "The name of dataset(s) to use for training. Use commas to separate multiple datasets."},
    )
    eval_dataset: Optional[str] = field(
        default=None,
        metadata={"help": "The name of dataset(s) to use for evaluation. Use commas to separate multiple datasets."},
    )
    dataset_dir: str = field(
        default="data",
        metadata={"help": "Path to the folder containing the datasets."},
    )
    media_dir: Optional[str] = field(
        default=None,
        metadata={"help": "Path to the folder containing the images, videos or audios. Defaults to `dataset_dir`."},
    )
    cutoff_len: int = field(
        default=2048,
        metadata={"help": "The cutoff length of the tokenized inputs in the dataset."},
    )
    train_on_prompt: bool = field(
        default=False,
        metadata={"help": "Whether or not to disable the mask on the prompt."},
    )
    mask_history: bool = field(
        default=False,
        metadata={"help": "Whether or not to mask the history and train on the last turn only."},
    )
    streaming: bool = field(
        default=False,
        metadata={"help": "Enable dataset streaming."},
    )
    buffer_size: int = field(
        default=16384,
        metadata={"help": "Size of the buffer to randomly sample examples from in dataset streaming."},
    )
    mix_strategy: Literal["concat", "interleave_under", "interleave_over"] = field(
        default="concat",
        metadata={"help": "Strategy to use in dataset mixing (concat/interleave) (undersampling/oversampling)."},
    )
    interleave_probs: Optional[str] = field(
        default=None,
        metadata={"help": "Probabilities to sample data from datasets. Use commas to separate multiple datasets."},
    )
    overwrite_cache: bool = field(
        default=False,
        metadata={"help": "Overwrite the cached training and evaluation sets."},
    )
    preprocessing_batch_size: int = field(
        default=1000,
        metadata={"help": "The number of examples in one group in pre-processing."},
    )
    preprocessing_num_workers: Optional[int] = field(
        default=None,
        metadata={"help": "The number of processes to use for the pre-processing."},
    )
    max_samples: Optional[int] = field(
        default=None,
        metadata={"help": "For debugging purposes, truncate the number of examples for each dataset."},
    )
    eval_num_beams: Optional[int] = field(
        default=None,
        metadata={"help": "Number of beams to use for evaluation. This argument will be passed to `model.generate`"},
    )
    ignore_pad_token_for_loss: bool = field(
        default=True,
        metadata={"help": "Whether or not to ignore the tokens corresponding to the pad label in loss computation."},
    )
    val_size: float = field(
        default=0.0,
        metadata={"help": "Size of the validation set, should be an integer or a float in range `[0,1)`."},
    )
    eval_on_each_dataset: bool = field(
        default=False,
        metadata={"help": "Whether or not to evaluate on each dataset separately."},
    )
    packing: Optional[bool] = field(
        default=None,
        metadata={"help": "Enable sequences packing in training. Will automatically enable in pre-training."},
    )
    neat_packing: bool = field(
        default=False,
        metadata={"help": "Enable sequence packing without cross-attention."},
    )
    tool_format: Optional[str] = field(
        default=None,
        metadata={"help": "Tool format to use for constructing function calling examples."},
    )
    tokenized_path: Optional[str] = field(
        default=None,
        metadata={
            "help": (
                "Path to save or load the tokenized datasets. "
                "If tokenized_path not exists, it will save the tokenized datasets. "
                "If tokenized_path exists, it will load the tokenized datasets."
            )
        },
    )

    def __post_init__(self):
        def split_arg(arg):
            if isinstance(arg, str):
                return [item.strip() for item in arg.split(",")]
            return arg

        self.dataset = split_arg(self.dataset)
        self.eval_dataset = split_arg(self.eval_dataset)

        if self.media_dir is None:
            self.media_dir = self.dataset_dir

        if self.dataset is None and self.val_size > 1e-6:
            raise ValueError("Cannot specify `val_size` if `dataset` is None.")

        if self.eval_dataset is not None and self.val_size > 1e-6:
            raise ValueError("Cannot specify `val_size` if `eval_dataset` is not None.")

        if self.interleave_probs is not None:
            if self.mix_strategy == "concat":
                raise ValueError("`interleave_probs` is only valid for interleaved mixing.")

            self.interleave_probs = list(map(float, split_arg(self.interleave_probs)))
            if self.dataset is not None and len(self.dataset) != len(self.interleave_probs):
                raise ValueError("The length of dataset and interleave probs should be identical.")

            if self.eval_dataset is not None and len(self.eval_dataset) != len(self.interleave_probs):
                raise ValueError("The length of eval dataset and interleave probs should be identical.")

        if self.streaming and self.val_size > 1e-6 and self.val_size < 1:
            raise ValueError("Streaming mode should have an integer val size.")

        if self.streaming and self.max_samples is not None:
            raise ValueError("`max_samples` is incompatible with `streaming`.")

        if self.mask_history and self.train_on_prompt:
            raise ValueError("`mask_history` is incompatible with `train_on_prompt`.")

        if self.neat_packing:
            self.packing = True

        if self.packing:
            self.cutoff_len -= 1  # avoid pad_to_multiple_of, needs improve

    def to_dict(self) -> dict[str, Any]:
        return asdict(self)