File size: 3,790 Bytes
f338eb3 | 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 | # Copyright 2024 Bytedance Ltd. and/or its affiliates
#
# 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.
"""
Preprocess the QA dataset to parquet format
"""
import re
import os
import datasets
from verl.utils.hdfs_io import copy, makedirs
import argparse
def make_prefix(dp, template_type):
question = dp['question']
# NOTE: also need to change reward_score/countdown.py
if template_type == 'base':
"""This works for any base model"""
prefix = f"""Answer the given question. \
You must conduct reasoning inside <think> and </think> first every time you get new information. \
After reasoning, if you find you lack some knowledge, you can call a search engine by <search> query </search> and it will return the top searched results between <information> and </information>. \
You can search as many times as your want. \
If you find no further external knowledge needed, you can directly provide the answer inside <answer> and </answer>, without detailed illustrations. For example, <answer> Beijing </answer>. Question: {question}\n"""
else:
raise NotImplementedError
return prefix
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--local_dir', default='./data/nq_search')
parser.add_argument('--hdfs_dir', default=None)
parser.add_argument('--template_type', type=str, default='base')
parser.add_argument('--data_sources', default='nq')
args = parser.parse_args()
# data_source = 'nq'
data_sources = args.data_sources.split(',')
all_dataset = []
for data_source in data_sources:
dataset = datasets.load_dataset('RUC-NLPIR/FlashRAG_datasets', data_source)
train_dataset = dataset['train']
# add a row to each data item that represents a unique id
def make_map_fn(split):
def process_fn(example, idx):
example['question'] = example['question'].strip()
if example['question'][-1] != '?':
example['question'] += '?'
question = make_prefix(example, template_type=args.template_type)
solution = {
"target": example['golden_answers'],
}
data = {
"data_source": data_source,
"prompt": [{
"role": "user",
"content": question,
}],
"ability": "fact-reasoning",
"reward_model": {
"style": "rule",
"ground_truth": solution
},
"extra_info": {
'split': split,
'index': idx,
}
}
return data
return process_fn
train_dataset = train_dataset.map(function=make_map_fn('train'), with_indices=True)
all_dataset.append(train_dataset)
local_dir = args.local_dir
hdfs_dir = args.hdfs_dir
all_train_dataset = datasets.concatenate_datasets(all_dataset)
all_train_dataset.to_parquet(os.path.join(local_dir, 'train.parquet'))
if hdfs_dir is not None:
makedirs(hdfs_dir)
copy(src=local_dir, dst=hdfs_dir)
|