File size: 2,870 Bytes
66407c5 |
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 |
# 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 Geometry3k dataset to parquet format
"""
import argparse
import os
import datasets
from verl.utils.hdfs_io import copy, makedirs
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--local_dir", default="~/data/geo3k")
parser.add_argument("--hdfs_dir", default=None)
args = parser.parse_args()
data_source = "hiyouga/geometry3k"
dataset = datasets.load_dataset(data_source)
train_dataset = dataset["train"]
test_dataset = dataset["test"]
instruction_following = (
r"You FIRST think about the reasoning process as an internal monologue and then provide the final answer. "
r"The reasoning process MUST BE enclosed within <think> </think> tags. The final answer MUST BE put in \boxed{}."
)
# add a row to each data item that represents a unique id
def make_map_fn(split):
def process_fn(example, idx):
problem = example.pop("problem")
prompt = problem + " " + instruction_following
answer = example.pop("answer")
images = example.pop("images")
data = {
"data_source": data_source,
"prompt": [
{
"role": "user",
"content": prompt,
}
],
"images": images,
"ability": "math",
"reward_model": {"style": "rule", "ground_truth": answer},
"extra_info": {
"split": split,
"index": idx,
"answer": answer,
"question": problem,
},
}
return data
return process_fn
train_dataset = train_dataset.map(function=make_map_fn("train"), with_indices=True, num_proc=8)
test_dataset = test_dataset.map(function=make_map_fn("test"), with_indices=True, num_proc=8)
local_dir = args.local_dir
hdfs_dir = args.hdfs_dir
train_dataset.to_parquet(os.path.join(local_dir, "train.parquet"))
test_dataset.to_parquet(os.path.join(local_dir, "test.parquet"))
if hdfs_dir is not None:
makedirs(hdfs_dir)
copy(src=local_dir, dst=hdfs_dir)
|