scriptoriumadmin/ReMe
1
0
Fork 0
mirror of https://github.com/agentscope-ai/ReMe.git synced 2026-08-28 05:25:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

add: split_into_trainval.py

Browse source
This commit is contained in:
zouying 2025-08-12 20:00:05 +08:00
parent 3c1b358e01
commit 8cf10453fe
2 changed files with 33 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
experiencemaker/cookbook/bfcl/run_bfcl.py
View file

@ -95,20 +95,20 @@ def main():
max_workers = 4
num_runs = 4 # Run each task 4 times
use_experience = True
experience_base_url = "http://0.0.0.0:8002/"
experience_workspace_id = "bfcl_v1_extract_compare"
experience_base_url = "http://0.0.0.0:8001/"
experience_workspace_id = "bfcl_v1"
if max_workers > 1:
ray.init(num_cpus=4)
for run_id in range(num_runs):
run_agent(
dataset_name="bfcl-multi-turn-base-val",
experiment_suffix=f"0812-w-exp-w-think-extract-compare-recall-rewrite",
experiment_suffix=f"0812-w-exp-extract-compare-recall",
model_name="qwen3-8b",
max_workers=max_workers,
num_runs=1,
data_path="data/multiturn_data_base_val.jsonl",
answer_path=Path("data/possible_answer"),
enable_thinking=True,
enable_thinking=False,
use_experience=use_experience,
experience_base_url=experience_base_url,
experience_workspace_id=experience_workspace_id,

29
experiencemaker/cookbook/bfcl/split_into_trainval.py Normal file
View file

@ -0,0 +1,29 @@
import json
import random
import argparse
def split_jsonl(input_file, train_file, val_file, ratio=0.8):
with open(input_file, 'r', encoding='utf-8') as f:
data = [json.loads(line) for line in f]
random.shuffle(data)
split_idx = int(len(data) * ratio)
train_data = data[:split_idx]
val_data = data[split_idx:]
with open(train_file, 'w', encoding='utf-8') as f:
for item in train_data:
f.write(json.dumps(item, ensure_ascii=False) + '\n')
with open(val_file, 'w', encoding='utf-8') as f:
for item in val_data:
f.write(json.dumps(item, ensure_ascii=False) + '\n')
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Split JSONL file into train and validation sets.')
parser.add_argument('--input', required=True, help='Path to input JSONL file')
parser.add_argument('--train', required=True, help='Path to output train file')
parser.add_argument('--val', required=True, help='Path to output validation file')
parser.add_argument('--ratio', type=float, default=0.5, help='Train ratio (default: 0.8)')
args = parser.parse_args()
split_jsonl(args.input, args.train, args.val, args.ratio)