Unverified Commit 9e03d9d0 authored by seungduk.kim.2304's avatar seungduk.kim.2304 Committed by GitHub
Browse files

Fix Column Naming and Dataset Naming Conventions in K-MMLU Evaluation (#1171)



* Correct column names and dataset names

* Remove kmmlu_general_physics.yaml and kmmlu_korean_language.yaml

* Update _default_kmmlu_yaml

---------
Co-authored-by: default avatarHailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>
parent 78545d42
...@@ -18,4 +18,4 @@ metric_list: ...@@ -18,4 +18,4 @@ metric_list:
aggregation: mean aggregation: mean
higher_is_better: true higher_is_better: true
metadata: metadata:
- version: 0.0 version: 1.0
"dataset_name": "Agricultural Sciences" "dataset_name": "Agricultural-Sciences"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_agricultural_sciences" "task": "kmmlu_agricultural_sciences"
"dataset_name": "Aviation Engineering and Maintenance" "dataset_name": "Aviation-Engineering-and-Maintenance"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_aviation_engineering_and_maintenance" "task": "kmmlu_aviation_engineering_and_maintenance"
"dataset_name": "Chemical Engineering" "dataset_name": "Chemical-Engineering"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_chemical_engineering" "task": "kmmlu_chemical_engineering"
"dataset_name": "Civil Engineering" "dataset_name": "Civil-Engineering"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_civil_engineering" "task": "kmmlu_civil_engineering"
"dataset_name": "Computer Science" "dataset_name": "Computer-Science"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_computer_science" "task": "kmmlu_computer_science"
"dataset_name": "Criminal Law" "dataset_name": "Criminal-Law"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_criminal_law" "task": "kmmlu_criminal_law"
"dataset_name": "Electrical Engineering" "dataset_name": "Electrical-Engineering"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_electrical_engineering" "task": "kmmlu_electrical_engineering"
"dataset_name": "Electronics Engineering" "dataset_name": "Electronics-Engineering"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_electronics_engineering" "task": "kmmlu_electronics_engineering"
"dataset_name": "Energy Management" "dataset_name": "Energy-Management"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_energy_management" "task": "kmmlu_energy_management"
"dataset_name": "Environmental Science" "dataset_name": "Environmental-Science"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_environmental_science" "task": "kmmlu_environmental_science"
"dataset_name": "Food Processing" "dataset_name": "Food-Processing"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_food_processing" "task": "kmmlu_food_processing"
"dataset_name": "Gas Technology and Engineering" "dataset_name": "Gas-Technology-and-Engineering"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_gas_technology_and_engineering" "task": "kmmlu_gas_technology_and_engineering"
"dataset_name": "General Physics"
"include": "_default_kmmlu_yaml"
"task": "kmmlu_general_physics"
"dataset_name": "Industrial Engineer" "dataset_name": "Industrial-Engineer"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_industrial_engineer" "task": "kmmlu_industrial_engineer"
"dataset_name": "Information Technology" "dataset_name": "Information-Technology"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_information_technology" "task": "kmmlu_information_technology"
"dataset_name": "Interior Architecture and Design" "dataset_name": "Interior-Architecture-and-Design"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_interior_architecture_and_design" "task": "kmmlu_interior_architecture_and_design"
"dataset_name": "Korean Language"
"include": "_default_kmmlu_yaml"
"task": "kmmlu_korean_language"
"dataset_name": "Machine Design and Manufacturing" "dataset_name": "Machine-Design-and-Manufacturing"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_machine_design_and_manufacturing" "task": "kmmlu_machine_design_and_manufacturing"
"dataset_name": "Maritime Engineering" "dataset_name": "Maritime-Engineering"
"include": "_default_kmmlu_yaml" "include": "_default_kmmlu_yaml"
"task": "kmmlu_maritime_engineering" "task": "kmmlu_maritime_engineering"
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