File size: 3,855 Bytes
9114cf2 | 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 | # 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 MATH-lighteval dataset to parquet format
"""
import argparse
import json
import os
import datasets
from verl.utils.hdfs_io import copy, makedirs
from verl.utils.reward_score.math_reward import last_boxed_only_string, remove_boxed
def extract_solution(solution_str):
return remove_boxed(last_boxed_only_string(solution_str))
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--local_dir", default=None)
parser.add_argument("--hdfs_dir", default=None)
parser.add_argument("--local_dataset_path", default=None, help="The local path to the raw dataset, if it exists.")
parser.add_argument(
"--local_save_dir", default="~/data/math", help="The save directory for the preprocessed dataset."
)
args = parser.parse_args()
local_dataset_path = args.local_dataset_path
# 'lighteval/MATH' is no longer available on huggingface.
# Use mirror repo: DigitalLearningGmbH/MATH-lighteval
data_source = "DigitalLearningGmbH/MATH-lighteval"
print(f"Loading the {data_source} dataset from huggingface...", flush=True)
if local_dataset_path is not None:
dataset = datasets.load_dataset(
local_dataset_path,
)
else:
dataset = datasets.load_dataset(
data_source,
)
train_dataset = dataset["train"]
test_dataset = dataset["test"]
instruction_following = "Let's think step by step and output the final answer within \\boxed{}."
# add a row to each data item that represents a unique id
def make_map_fn(split):
def process_fn(example, idx):
question = example.pop("problem")
question = question + " " + instruction_following
answer = example.pop("solution")
solution = extract_solution(answer)
data = {
"data_source": data_source,
"prompt": [{"role": "user", "content": question}],
"ability": "math",
"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)
test_dataset = test_dataset.map(function=make_map_fn("test"), with_indices=True)
local_save_dir = args.local_dir
if local_save_dir is not None:
print("Warning: Argument 'local_dir' is deprecated. Please use 'local_save_dir' instead.")
else:
local_save_dir = args.local_save_dir
local_dir = os.path.expanduser(local_save_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"))
# Save one example as JSON for reference
example = train_dataset[0]
with open(os.path.join(local_dir, "train_example.json"), "w") as f:
json.dump(example, f, indent=2)
example = test_dataset[0]
with open(os.path.join(local_dir, "test_example.json"), "w") as f:
json.dump(example, f, indent=2)
if hdfs_dir is not None:
makedirs(hdfs_dir)
copy(src=local_dir, dst=hdfs_dir)
|