Merge branch 'main' into longcxt

# Conflicts:
#	lm_eval/tasks/README.md

lm_eval/tasks/arabicmmlu/arabicmmlu_accounting_university.yaml

+"dataset_name": "Accounting (University)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_accounting_university"
+"task_alias": "Accounting (University)"

lm_eval/tasks/arabicmmlu/arabicmmlu_arabic_language_general.yaml

 "dataset_name": "Arabic Language (General)"
-"tag": "arabicmmlu_language_tasks"
 "include": "_default_arabicmmlu_template_yaml"
-"task": "arabicmmlu_arabic_language_(general)"
+"tag": "arabicmmlu_language_tasks"
+"task": "arabicmmlu_arabic_language_general"
 "task_alias": "Arabic Language (General)"

lm_eval/tasks/arabicmmlu/arabicmmlu_arabic_language_grammar.yaml

 "dataset_name": "Arabic Language (Grammar)"
-"tag": "arabicmmlu_language_tasks"
 "include": "_default_arabicmmlu_template_yaml"
-"task": "arabicmmlu_arabic_language_(grammar)"
+"tag": "arabicmmlu_language_tasks"
+"task": "arabicmmlu_arabic_language_grammar"
 "task_alias": "Arabic Language (Grammar)"

lm_eval/tasks/arabicmmlu/arabicmmlu_arabic_language_high_school.yaml

+"dataset_name": "Arabic Language (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_language_tasks"
+"task": "arabicmmlu_arabic_language_high_school"
+"task_alias": "Arabic Language (High School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_arabic_language_middle_school.yaml

+"dataset_name": "Arabic Language (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_language_tasks"
+"task": "arabicmmlu_arabic_language_middle_school"
+"task_alias": "Arabic Language (Middle School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_arabic_language_primary_school.yaml

+"dataset_name": "Arabic Language (Primary School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_language_tasks"
+"task": "arabicmmlu_arabic_language_primary_school"
+"task_alias": "Arabic Language (Primary School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_biology_high_school.yaml

+"dataset_name": "Biology (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_stem_tasks"
+"task": "arabicmmlu_biology_high_school"
+"task_alias": "Biology (High School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_civics_high_school.yaml

+"dataset_name": "Civics (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_civics_high_school"
+"task_alias": "Civics (High School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_civics_middle_school.yaml

+"dataset_name": "Civics (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_civics_middle_school"
+"task_alias": "Civics (Middle School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_computer_science_high_school.yaml

+"dataset_name": "Computer Science (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_stem_tasks"
+"task": "arabicmmlu_computer_science_high_school"
+"task_alias": "Computer Science (High School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_computer_science_middle_school.yaml

+"dataset_name": "Computer Science (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_stem_tasks"
+"task": "arabicmmlu_computer_science_middle_school"
+"task_alias": "Computer Science (Middle School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_computer_science_primary_school.yaml

+"dataset_name": "Computer Science (Primary School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_stem_tasks"
+"task": "arabicmmlu_computer_science_primary_school"
+"task_alias": "Computer Science (Primary School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_computer_science_university.yaml

+"dataset_name": "Computer Science (University)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_stem_tasks"
+"task": "arabicmmlu_computer_science_university"
+"task_alias": "Computer Science (University)"

lm_eval/tasks/arabicmmlu/arabicmmlu_driving_test.yaml

 "dataset_name": "Driving Test"
-"tag": "arabicmmlu_other_tasks"
 "include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_other_tasks"
 "task": "arabicmmlu_driving_test"
 "task_alias": "Driving Test"

lm_eval/tasks/arabicmmlu/arabicmmlu_economics_high_school.yaml

+"dataset_name": "Economics (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_economics_high_school"
+"task_alias": "Economics (High School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_economics_middle_school.yaml

+"dataset_name": "Economics (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_economics_middle_school"
+"task_alias": "Economics (Middle School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_economics_university.yaml

+"dataset_name": "Economics (University)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_economics_university"
+"task_alias": "Economics (University)"

lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge.yaml

 "dataset_name": "General Knowledge"
-"tag": "arabicmmlu_other_tasks"
 "include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_other_tasks"
 "task": "arabicmmlu_general_knowledge"
 "task_alias": "General Knowledge"

lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge_middle_school.yaml

+"dataset_name": "General Knowledge (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_other_tasks"
+"task": "arabicmmlu_general_knowledge_middle_school"
+"task_alias": "General Knowledge (Middle School)"

lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge_primary_school.yaml

+"dataset_name": "General Knowledge (Primary School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_other_tasks"
+"task": "arabicmmlu_general_knowledge_primary_school"
+"task_alias": "General Knowledge (Primary School)"