File size: 6,699 Bytes
9c6594c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright 2020-2025 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.

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

from transformers import TrainingArguments


@dataclass
class ORPOConfig(TrainingArguments):
    r"""
    Configuration class for the [`ORPOTrainer`].

    Using [`~transformers.HfArgumentParser`] we can turn this class into
    [argparse](https://docs.python.org/3/library/argparse#module-argparse) arguments that can be specified on the
    command line.

    Parameters:
        learning_rate (`float`, *optional*, defaults to `1e-6`):
            Initial learning rate for [`AdamW`] optimizer. The default value replaces that of
            [`~transformers.TrainingArguments`].
        max_length (`int` or `None`, *optional*, defaults to `1024`):
            Maximum length of the sequences (prompt + completion) in the batch. This argument is required if you want
            to use the default data collator.
        max_prompt_length (`int` or `None`, *optional*, defaults to `512`):
            Maximum length of the prompt. This argument is required if you want to use the default data collator.
        max_completion_length (`int` or `None`, *optional*, defaults to `None`):
            Maximum length of the completion. This argument is required if you want to use the default data collator
            and your model is an encoder-decoder.
        beta (`float`, *optional*, defaults to `0.1`):
            Parameter controlling the relative ratio loss weight in the ORPO loss. In the [paper](https://huggingface.co/papers/2403.07691),
            it is denoted by Ξ». In the [code](https://github.com/xfactlab/orpo), it is denoted by `alpha`.
        disable_dropout (`bool`, *optional*, defaults to `True`):
            Whether to disable dropout in the model.
        label_pad_token_id (`int`, *optional*, defaults to `-100`):
            Label pad token id. This argument is required if you want to use the default data collator.
        padding_value (`int` or `None`, *optional*, defaults to `None`):
            Padding value to use. If `None`, the padding value of the tokenizer is used.
        truncation_mode (`str`, *optional*, defaults to `"keep_end"`):
            Truncation mode to use when the prompt is too long. Possible values are `"keep_end"` or `"keep_start"`.
            This argument is required if you want to use the default data collator.
        generate_during_eval (`bool`, *optional*, defaults to `False`):
            If `True`, generates and logs completions from the model to W&B or Comet during evaluation.
        is_encoder_decoder (`bool` or `None`, *optional*, defaults to `None`):
            When using the `model_init` argument (callable) to instantiate the model instead of the `model` argument,
            you need to specify if the model returned by the callable is an encoder-decoder model.
        model_init_kwargs (`dict[str, Any]` or `None`, *optional*, defaults to `None`):
            Keyword arguments to pass to `AutoModelForCausalLM.from_pretrained` when instantiating the model from a
            string.
        dataset_num_proc (`int` or `None`, *optional*, defaults to `None`):
            Number of processes to use for processing the dataset.
    """

    learning_rate: float = field(
        default=1e-6,
        metadata={
            "help": "Initial learning rate for `AdamW` optimizer. The default value replaces that of "
            "transformers.TrainingArguments."
        },
    )
    max_length: Optional[int] = field(
        default=1024,
        metadata={"help": "Maximum length of the sequences (prompt + completion) in the batch."},
    )
    max_prompt_length: Optional[int] = field(
        default=512,
        metadata={
            "help": "Maximum length of the prompt. This argument is required if you want to use the default data "
            "collator and your model is an encoder-decoder."
        },
    )
    max_completion_length: Optional[int] = field(
        default=None,
        metadata={
            "help": "Maximum length of the completion. This argument is required if you want to use the default data "
            "collator and your model is an encoder-decoder."
        },
    )
    beta: float = field(
        default=0.1,
        metadata={
            "help": "Parameter controlling the relative ratio loss weight in the ORPO loss. In the paper, it is "
            "denoted by Ξ»."
        },
    )
    disable_dropout: bool = field(
        default=True,
        metadata={"help": "Whether to disable dropout in the model."},
    )
    label_pad_token_id: int = field(
        default=-100,
        metadata={
            "help": "Label pad token id. This argument is required if you want to use the default data collator."
        },
    )
    padding_value: Optional[int] = field(
        default=None,
        metadata={"help": "Padding value to use. If `None`, the padding value of the tokenizer is used."},
    )
    truncation_mode: str = field(
        default="keep_end",
        metadata={
            "help": "Truncation mode to use when the prompt is too long.",
            "choices": ["keep_end", "keep_start"],
        },
    )
    generate_during_eval: bool = field(
        default=False,
        metadata={"help": "If `True`, generates and logs completions from the model to W&B during evaluation."},
    )
    is_encoder_decoder: Optional[bool] = field(
        default=None,
        metadata={
            "help": "When using the `model_init` argument (callable) to instantiate the model instead of the `model` "
            "argument, you need to specify if the model returned by the callable is an encoder-decoder model."
        },
    )
    model_init_kwargs: Optional[dict[str, Any]] = field(
        default=None,
        metadata={
            "help": "Keyword arguments to pass to `AutoModelForCausalLM.from_pretrained` when instantiating the model "
            "from a string."
        },
    )
    dataset_num_proc: Optional[int] = field(
        default=None,
        metadata={"help": "Number of processes to use for processing the dataset."},
    )