Commit 90ad5db7 authored by lintangsutawika's avatar lintangsutawika
Browse files

merged main

parents f692caa9 b177c82c
group:
- kmmlu
- kmmlu_direct
dataset_path: HAERAE-HUB/KMMLU
output_type: generate_until
test_split: test
fewshot_split: dev
doc_to_text: "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n정답:"
doc_to_target: "{{['A', 'B', 'C', 'D'][answer-1]}}"
metric_list:
- metric: exact_match
aggregation: mean
higher_is_better: true
ignore_case: true
ignore_punctuation: true
regexes_to_ignore:
- " "
generation_kwargs:
until:
- "Q:"
- "\n\n"
- "</s>"
- "."
do_sample: false
temperature: 0.0
metadata:
version: 2.0
dataset_name: Accounting
include: _direct_kmmlu_yaml
task: kmmlu_direct_accounting
dataset_name: Agricultural-Sciences
include: _direct_kmmlu_yaml
task: kmmlu_direct_agricultural_sciences
dataset_name: Aviation-Engineering-and-Maintenance
include: _direct_kmmlu_yaml
task: kmmlu_direct_aviation_engineering_and_maintenance
dataset_name: Biology
include: _direct_kmmlu_yaml
task: kmmlu_direct_biology
dataset_name: Chemical-Engineering
include: _direct_kmmlu_yaml
task: kmmlu_direct_chemical_engineering
dataset_name: Chemistry
include: _direct_kmmlu_yaml
task: kmmlu_direct_chemistry
dataset_name: Civil-Engineering
include: _direct_kmmlu_yaml
task: kmmlu_direct_civil_engineering
dataset_name: Computer-Science
include: _direct_kmmlu_yaml
task: kmmlu_direct_computer_science
dataset_name: Construction
include: _direct_kmmlu_yaml
task: kmmlu_direct_construction
dataset_name: Criminal-Law
include: _direct_kmmlu_yaml
task: kmmlu_direct_criminal_law
dataset_name: Ecology
include: _direct_kmmlu_yaml
task: kmmlu_direct_ecology
dataset_name: Economics
include: _direct_kmmlu_yaml
task: kmmlu_direct_economics
dataset_name: Education
include: _direct_kmmlu_yaml
task: kmmlu_direct_education
dataset_name: Electrical-Engineering
include: _direct_kmmlu_yaml
task: kmmlu_direct_electrical_engineering
dataset_name: Electronics-Engineering
include: _direct_kmmlu_yaml
task: kmmlu_direct_electronics_engineering
dataset_name: Energy-Management
include: _direct_kmmlu_yaml
task: kmmlu_direct_energy_management
dataset_name: Environmental-Science
include: _direct_kmmlu_yaml
task: kmmlu_direct_environmental_science
dataset_name: Fashion
include: _direct_kmmlu_yaml
task: kmmlu_direct_fashion
dataset_name: Food-Processing
include: _direct_kmmlu_yaml
task: kmmlu_direct_food_processing
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment