File size: 2,245 Bytes
2852136
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# coding=utf-8
# 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 collections import defaultdict

import fire
from tqdm import tqdm

from llamafactory.data import get_dataset
from llamafactory.hparams import get_train_args
from llamafactory.model import load_tokenizer


def length_cdf(
    model_name_or_path: str,
    dataset: str = "alpaca_en",
    dataset_dir: str = "data",
    template: str = "default",
    interval: int = 1000,
):
    r"""
    Calculates the distribution of the input lengths in the dataset.
    Usage: python length_cdf.py --model_name_or_path path_to_model --dataset alpaca_en --template default
    """
    model_args, data_args, training_args, _, _ = get_train_args(
        dict(
            stage="sft",
            model_name_or_path=model_name_or_path,
            dataset=dataset,
            dataset_dir=dataset_dir,
            template=template,
            cutoff_len=1_000_000,
            output_dir="dummy_dir",
            overwrite_cache=True,
        )
    )
    tokenizer_module = load_tokenizer(model_args)
    trainset = get_dataset(model_args, data_args, training_args, stage="sft", **tokenizer_module)
    total_num = len(trainset)
    length_dict = defaultdict(int)
    for sample in tqdm(trainset["input_ids"]):
        length_dict[len(sample) // interval * interval] += 1

    length_tuples = list(length_dict.items())
    length_tuples.sort()
    count_accu, prob_accu = 0, 0
    for length, count in length_tuples:
        count_accu += count
        prob_accu += count / total_num * 100
        print("{:d} ({:.2f}%) samples have length < {}.".format(count_accu, prob_accu, length + interval))


if __name__ == "__main__":
    fire.Fire(length_cdf)