File size: 3,278 Bytes
f6f64ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright 2024 the LlamaFactory team.
#
# 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 enum import Enum, unique
from typing import TYPE_CHECKING, Dict, List, Optional, Sequence, Set, TypedDict, Union

from datasets import DatasetDict, concatenate_datasets, interleave_datasets

from ..extras.logging import get_logger


if TYPE_CHECKING:
    from datasets import Dataset, IterableDataset

    from ..hparams import DataArguments


logger = get_logger(__name__)


SLOTS = Sequence[Union[str, Set[str], Dict[str, str]]]


@unique
class Role(str, Enum):
    USER = "user"
    ASSISTANT = "assistant"
    SYSTEM = "system"
    FUNCTION = "function"
    OBSERVATION = "observation"


class DatasetModule(TypedDict):
    train_dataset: Optional[Union["Dataset", "IterableDataset"]]
    eval_dataset: Optional[Union["Dataset", "IterableDataset"]]


def merge_dataset(
    all_datasets: List[Union["Dataset", "IterableDataset"]], data_args: "DataArguments", seed: int
) -> Union["Dataset", "IterableDataset"]:
    r"""
    Merges multiple datasets to a unified dataset.
    """
    if len(all_datasets) == 1:
        return all_datasets[0]
    elif data_args.mix_strategy == "concat":
        if data_args.streaming:
            logger.warning("The samples between different datasets will not be mixed in streaming mode.")

        return concatenate_datasets(all_datasets)
    elif data_args.mix_strategy.startswith("interleave"):
        if not data_args.streaming:
            logger.warning("We recommend using `mix_strategy=concat` in non-streaming mode.")

        return interleave_datasets(
            datasets=all_datasets,
            probabilities=data_args.interleave_probs,
            seed=seed,
            stopping_strategy="first_exhausted" if data_args.mix_strategy.endswith("under") else "all_exhausted",
        )
    else:
        raise ValueError("Unknown mixing strategy: {}.".format(data_args.mix_strategy))


def split_dataset(
    dataset: Union["Dataset", "IterableDataset"], data_args: "DataArguments", seed: int
) -> "DatasetDict":
    r"""
    Splits the dataset and returns a dataset dict containing train set and validation set.

    Supports both map dataset and iterable dataset.
    """
    if data_args.streaming:
        dataset = dataset.shuffle(buffer_size=data_args.buffer_size, seed=seed)
        val_set = dataset.take(int(data_args.val_size))
        train_set = dataset.skip(int(data_args.val_size))
        return DatasetDict({"train": train_set, "validation": val_set})
    else:
        val_size = int(data_args.val_size) if data_args.val_size > 1 else data_args.val_size
        dataset = dataset.train_test_split(test_size=val_size, seed=seed)
        return DatasetDict({"train": dataset["train"], "validation": dataset["test"]})