evalstone/bash/run_group2.py
2026-07-21 09:32:49 +00:00

41 lines
815 B
Python

"""
Group 2: Knowledge + Long-context + Agent (est. ~20-24h)
Run on machine 2.
"""
from pathlib import Path
import sys
# Ensure we can import run.py from the same directory inside or outside Docker
sys.path.insert(0, str(Path(__file__).parent))
import run as run_module
# Override dataset lists for group 2
run_module._multi_run_order = []
run_module._single_run_order = [
'drop',
'bbh',
'openai_mrcr',
'longbench_v2',
'mmlu',
'cmmlu',
'super_gpqa',
'simple_qa',
]
run_module._agent_order = [
'general_fc',
]
run_module.DATASETS = (
run_module._multi_run_order
+ run_module._single_run_order
+ run_module._agent_order
)
if __name__ == '__main__':
print('Group 2 benchmarks:', run_module.DATASETS)
print('Estimated time: ~20-24h')
run_module.main()