Unverified Commit b2c090cc authored by Minho Ryu's avatar Minho Ryu Committed by GitHub
Browse files

aggregate by group (total and categories) (#2643)

parent ed9c6fc8
dataset_name: education
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_education
task: kmmlu_direct_hard_education
tag: kmmlu_direct_hard_humss_tasks
dataset_name: electrical_engineering
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_electrical_engineering
task: kmmlu_direct_hard_electrical_engineering
tag: kmmlu_direct_hard_stem_tasks
dataset_name: electronics_engineering
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_electronics_engineering
task: kmmlu_direct_hard_electronics_engineering
tag: kmmlu_direct_hard_applied_science_tasks
dataset_name: energy_management
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_energy_management
task: kmmlu_direct_hard_energy_management
tag: kmmlu_direct_hard_applied_science_tasks
dataset_name: environmental_science
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_environmental_science
task: kmmlu_direct_hard_environmental_science
tag: kmmlu_direct_hard_applied_science_tasks
dataset_name: fashion
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_fashion
task: kmmlu_direct_hard_fashion
tag: kmmlu_direct_hard_other_tasks
dataset_name: food_processing
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_food_processing
task: kmmlu_direct_hard_food_processing
tag: kmmlu_direct_hard_other_tasks
dataset_name: gas_technology_and_engineering
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_gas_technology_and_engineering
task: kmmlu_direct_hard_gas_technology_and_engineering
tag: kmmlu_direct_hard_applied_science_tasks
dataset_name: geomatics
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_geomatics
task: kmmlu_direct_hard_geomatics
tag: kmmlu_direct_hard_applied_science_tasks
dataset_name: health
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_health
task: kmmlu_direct_hard_health
tag: kmmlu_direct_hard_other_tasks
dataset_name: industrial_engineer
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_industrial_engineer
task: kmmlu_direct_hard_industrial_engineer
tag: kmmlu_direct_hard_applied_science_tasks
dataset_name: information_technology
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_information_technology
task: kmmlu_direct_hard_information_technology
tag: kmmlu_direct_hard_stem_tasks
dataset_name: interior_architecture_and_design
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_interior_architecture_and_design
task: kmmlu_direct_hard_interior_architecture_and_design
tag: kmmlu_direct_hard_other_tasks
dataset_name: korean_history
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_korean_history
task: kmmlu_direct_hard_korean_history
tag: kmmlu_direct_hard_humss_tasks
dataset_name: law
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_law
task: kmmlu_direct_hard_law
tag: kmmlu_direct_hard_humss_tasks
dataset_name: machine_design_and_manufacturing
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_machine_design_and_manufacturing
task: kmmlu_direct_hard_machine_design_and_manufacturing
tag: kmmlu_direct_hard_applied_science_tasks
dataset_name: management
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_management
task: kmmlu_direct_hard_management
tag: kmmlu_direct_hard_humss_tasks
dataset_name: maritime_engineering
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_maritime_engineering
task: kmmlu_direct_hard_maritime_engineering
tag: kmmlu_direct_hard_applied_science_tasks
dataset_name: marketing
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_marketing
task: kmmlu_direct_hard_marketing
tag: kmmlu_direct_hard_other_tasks
dataset_name: materials_engineering
include: _direct_hard_kmmlu_yaml
task: kmmlu_hard_direct_materials_engineering
task: kmmlu_direct_hard_materials_engineering
tag: kmmlu_direct_hard_stem_tasks
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