Merge branch 'main' into longcxt

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_middle_social-science_civics.yaml

+"dataset_name": "middle_social-science_civics"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_social-science_lev"
+"task": "AraDiCE_ArabicMMLU_middle_social-science_civics_lev"
+"task_alias": "middle social-science civics"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_middle_social-science_economics.yaml

+"dataset_name": "middle_social-science_economics"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_social-science_lev"
+"task": "AraDiCE_ArabicMMLU_middle_social-science_economics_lev"
+"task_alias": "middle social-science economics"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_middle_social-science_geography.yaml

+"dataset_name": "middle_social-science_geography"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_social-science_lev"
+"task": "AraDiCE_ArabicMMLU_middle_social-science_geography_lev"
+"task_alias": "middle social-science geography"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_middle_social-science_social-science.yaml

+"dataset_name": "middle_social-science_social-science"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_social-science_lev"
+"task": "AraDiCE_ArabicMMLU_middle_social-science_social-science_lev"
+"task_alias": "middle social-science social-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_middle_stem_computer-science.yaml

+"dataset_name": "middle_stem_computer-science"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_stem_lev"
+"task": "AraDiCE_ArabicMMLU_middle_stem_computer-science_lev"
+"task_alias": "middle stem computer-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_middle_stem_natural-science.yaml

+"dataset_name": "middle_stem_natural-science"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_stem_lev"
+"task": "AraDiCE_ArabicMMLU_middle_stem_natural-science_lev"
+"task_alias": "middle stem natural-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_na_humanities_islamic-studies.yaml

+"dataset_name": "na_humanities_islamic-studies"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_humanities_lev"
+"task": "AraDiCE_ArabicMMLU_na_humanities_islamic-studies_lev"
+"task_alias": "na humanities islamic-studies"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_na_language_arabic-language-general.yaml

+"dataset_name": "na_language_arabic-language-general"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_language_lev"
+"task": "AraDiCE_ArabicMMLU_na_language_arabic-language-general_lev"
+"task_alias": "na language arabic-language-general"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_na_language_arabic-language-grammar.yaml

+"dataset_name": "na_language_arabic-language-grammar"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_language_lev"
+"task": "AraDiCE_ArabicMMLU_na_language_arabic-language-grammar_lev"
+"task_alias": "na language arabic-language-grammar"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_na_other_driving-test.yaml

+"dataset_name": "na_other_driving-test"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_other_lev"
+"task": "AraDiCE_ArabicMMLU_na_other_driving-test_lev"
+"task_alias": "na other driving-test"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_na_other_general-knowledge.yaml

+"dataset_name": "na_other_general-knowledge"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_other_lev"
+"task": "AraDiCE_ArabicMMLU_na_other_general-knowledge_lev"
+"task_alias": "na other general-knowledge"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_primary_humanities_history.yaml

+"dataset_name": "primary_humanities_history"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_humanities_lev"
+"task": "AraDiCE_ArabicMMLU_primary_humanities_history_lev"
+"task_alias": "primary humanities history"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_primary_humanities_islamic-studies.yaml

+"dataset_name": "primary_humanities_islamic-studies"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_humanities_lev"
+"task": "AraDiCE_ArabicMMLU_primary_humanities_islamic-studies_lev"
+"task_alias": "primary humanities islamic-studies"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_primary_language_arabic-language.yaml

+"dataset_name": "primary_language_arabic-language"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_language_lev"
+"task": "AraDiCE_ArabicMMLU_primary_language_arabic-language_lev"
+"task_alias": "primary language arabic-language"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_primary_other_general-knowledge.yaml

+"dataset_name": "primary_other_general-knowledge"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_other_lev"
+"task": "AraDiCE_ArabicMMLU_primary_other_general-knowledge_lev"
+"task_alias": "primary other general-knowledge"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_primary_social-science_geography.yaml

+"dataset_name": "primary_social-science_geography"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_social-science_lev"
+"task": "AraDiCE_ArabicMMLU_primary_social-science_geography_lev"
+"task_alias": "primary social-science geography"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_primary_social-science_social-science.yaml

+"dataset_name": "primary_social-science_social-science"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_social-science_lev"
+"task": "AraDiCE_ArabicMMLU_primary_social-science_social-science_lev"
+"task_alias": "primary social-science social-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_primary_stem_computer-science.yaml

+"dataset_name": "primary_stem_computer-science"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_stem_lev"
+"task": "AraDiCE_ArabicMMLU_primary_stem_computer-science_lev"
+"task_alias": "primary stem computer-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_primary_stem_math.yaml

+"dataset_name": "primary_stem_math"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_stem_lev"
+"task": "AraDiCE_ArabicMMLU_primary_stem_math_lev"
+"task_alias": "primary stem math"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/LEV/AraDiCE_ArabicMMLU_primary_stem_natural-science.yaml

+"dataset_name": "primary_stem_natural-science"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_stem_lev"
+"task": "AraDiCE_ArabicMMLU_primary_stem_natural-science_lev"
+"task_alias": "primary stem natural-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"