Merge branch 'main' into humaneval

# Conflicts:
#	lm_eval/api/task.py

lm_eval/tasks/aradice/ArabicMMLU/EGY/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_egy"
+"task": "AraDiCE_ArabicMMLU_na_language_arabic-language-grammar_egy"
+"task_alias": "na language arabic-language-grammar"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/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_egy"
+"task": "AraDiCE_ArabicMMLU_na_other_driving-test_egy"
+"task_alias": "na other driving-test"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/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_egy"
+"task": "AraDiCE_ArabicMMLU_na_other_general-knowledge_egy"
+"task_alias": "na other general-knowledge"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

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

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

lm_eval/tasks/aradice/ArabicMMLU/EGY/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_egy"
+"task": "AraDiCE_ArabicMMLU_primary_humanities_islamic-studies_egy"
+"task_alias": "primary humanities islamic-studies"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/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_egy"
+"task": "AraDiCE_ArabicMMLU_primary_language_arabic-language_egy"
+"task_alias": "primary language arabic-language"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/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_egy"
+"task": "AraDiCE_ArabicMMLU_primary_other_general-knowledge_egy"
+"task_alias": "primary other general-knowledge"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/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_egy"
+"task": "AraDiCE_ArabicMMLU_primary_social-science_geography_egy"
+"task_alias": "primary social-science geography"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/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_egy"
+"task": "AraDiCE_ArabicMMLU_primary_social-science_social-science_egy"
+"task_alias": "primary social-science social-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/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_egy"
+"task": "AraDiCE_ArabicMMLU_primary_stem_computer-science_egy"
+"task_alias": "primary stem computer-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

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

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

lm_eval/tasks/aradice/ArabicMMLU/EGY/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_egy"
+"task": "AraDiCE_ArabicMMLU_primary_stem_natural-science_egy"
+"task_alias": "primary stem natural-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/AraDiCE_ArabicMMLU_prof_humanities_law.yaml

+"dataset_name": "prof_humanities_law"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_humanities_egy"
+"task": "AraDiCE_ArabicMMLU_prof_humanities_law_egy"
+"task_alias": "prof humanities law"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/AraDiCE_ArabicMMLU_univ_other_management.yaml

+"dataset_name": "univ_other_management"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_other_egy"
+"task": "AraDiCE_ArabicMMLU_univ_other_management_egy"
+"task_alias": "univ other management"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/AraDiCE_ArabicMMLU_univ_social-science_accounting.yaml

+"dataset_name": "univ_social-science_accounting"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_social-science_egy"
+"task": "AraDiCE_ArabicMMLU_univ_social-science_accounting_egy"
+"task_alias": "univ social-science accounting"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/AraDiCE_ArabicMMLU_univ_social-science_economics.yaml

+"dataset_name": "univ_social-science_economics"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_social-science_egy"
+"task": "AraDiCE_ArabicMMLU_univ_social-science_economics_egy"
+"task_alias": "univ social-science economics"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/AraDiCE_ArabicMMLU_univ_social-science_political-science.yaml

+"dataset_name": "univ_social-science_political-science"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_social-science_egy"
+"task": "AraDiCE_ArabicMMLU_univ_social-science_political-science_egy"
+"task_alias": "univ social-science political-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/AraDiCE_ArabicMMLU_univ_stem_computer-science.yaml

+"dataset_name": "univ_stem_computer-science"
+"description": ""
+"fewshot_split": !!null "null"
+"include": "_default_template_yaml"
+"tag": "AraDiCE_ArabicMMLU_stem_egy"
+"task": "AraDiCE_ArabicMMLU_univ_stem_computer-science_egy"
+"task_alias": "univ stem computer-science"
+"test_split": "test"
+"training_split": !!null "null"
+"validation_split": !!null "null"

lm_eval/tasks/aradice/ArabicMMLU/EGY/_default_template_yaml

+dataset_path: "QCRI/AraDICE-ArabicMMLU-egy"
+fewshot_config:
+  sampler: default
+output_type: multiple_choice
+process_docs: !function utils.process_docs
+doc_to_text: "{{prompt}}"
+doc_to_choice: choices
+doc_to_target: target
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+  - metric: f1
+    higher_is_better: true
+    aggregation: !function metrics.micro_f1_score
+metadata:
+  version: 0.0

lm_eval/tasks/aradice/ArabicMMLU/EGY/metrics.py

+from sklearn.metrics import f1_score
+
+
+def macro_f1_score(items):
+    unzipped_list = list(zip(*items))
+    golds = unzipped_list[0]
+    preds = unzipped_list[1]
+    fscore = f1_score(golds, preds, average="macro")
+    return fscore
+
+
+def micro_f1_score(items):
+    unzipped_list = list(zip(*items))
+    golds = unzipped_list[0]
+    preds = unzipped_list[1]
+    fscore = f1_score(golds, preds, average="micro")
+    return fscore
+
+
+def weighted_f1_score(items):
+    unzipped_list = list(zip(*items))
+    golds = unzipped_list[0]
+    preds = unzipped_list[1]
+    fscore = f1_score(golds, preds, average="weighted")
+    return fscore