Merge branch 'main' into prefill

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_high_school_geography_light.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_geography_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: high_school_geography
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_high_school_government_and_politics_light.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_government_and_politics_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: high_school_government_and_politics
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_high_school_macroeconomics_light.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_macroeconomics_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: high_school_macroeconomics
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_high_school_mathematics_light.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_mathematics_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: high_school_mathematics
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_high_school_microeconomics_light.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_microeconomics_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: high_school_microeconomics
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_high_school_physics_light.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_physics_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: high_school_physics
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_high_school_psychology_light.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_psychology_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: high_school_psychology
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_high_school_statistics_light.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_statistics_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: high_school_statistics
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_high_school_us_history_light.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_us_history_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: high_school_us_history
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_high_school_world_history_light.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_world_history_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: high_school_world_history
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_human_aging_light.yaml

+task: arabic_leaderboard_arabic_mmlu_human_aging_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: human_aging
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_human_sexuality_light.yaml

+task: arabic_leaderboard_arabic_mmlu_human_sexuality_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: human_sexuality
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_international_law_light.yaml

+task: arabic_leaderboard_arabic_mmlu_international_law_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: international_law
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_jurisprudence_light.yaml

+task: arabic_leaderboard_arabic_mmlu_jurisprudence_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: jurisprudence
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_light.yaml

+group: arabic_leaderboard_arabic_mmlu_light
+task:
+  - arabic_leaderboard_arabic_mmlu_abstract_algebra_light
+  - arabic_leaderboard_arabic_mmlu_anatomy_light
+  - arabic_leaderboard_arabic_mmlu_astronomy_light
+  - arabic_leaderboard_arabic_mmlu_business_ethics_light
+  - arabic_leaderboard_arabic_mmlu_clinical_knowledge_light
+  - arabic_leaderboard_arabic_mmlu_college_biology_light
+  - arabic_leaderboard_arabic_mmlu_college_chemistry_light
+  - arabic_leaderboard_arabic_mmlu_college_computer_science_light
+  - arabic_leaderboard_arabic_mmlu_college_mathematics_light
+  - arabic_leaderboard_arabic_mmlu_college_medicine_light
+  - arabic_leaderboard_arabic_mmlu_college_physics_light
+  - arabic_leaderboard_arabic_mmlu_computer_security_light
+  - arabic_leaderboard_arabic_mmlu_conceptual_physics_light
+  - arabic_leaderboard_arabic_mmlu_econometrics_light
+  - arabic_leaderboard_arabic_mmlu_electrical_engineering_light
+  - arabic_leaderboard_arabic_mmlu_elementary_mathematics_light
+  - arabic_leaderboard_arabic_mmlu_formal_logic_light
+  - arabic_leaderboard_arabic_mmlu_global_facts_light
+  - arabic_leaderboard_arabic_mmlu_high_school_biology_light
+  - arabic_leaderboard_arabic_mmlu_high_school_chemistry_light
+  - arabic_leaderboard_arabic_mmlu_high_school_computer_science_light
+  - arabic_leaderboard_arabic_mmlu_high_school_european_history_light
+  - arabic_leaderboard_arabic_mmlu_high_school_geography_light
+  - arabic_leaderboard_arabic_mmlu_high_school_government_and_politics_light
+  - arabic_leaderboard_arabic_mmlu_high_school_macroeconomics_light
+  - arabic_leaderboard_arabic_mmlu_high_school_mathematics_light
+  - arabic_leaderboard_arabic_mmlu_high_school_microeconomics_light
+  - arabic_leaderboard_arabic_mmlu_high_school_physics_light
+  - arabic_leaderboard_arabic_mmlu_high_school_psychology_light
+  - arabic_leaderboard_arabic_mmlu_high_school_statistics_light
+  - arabic_leaderboard_arabic_mmlu_high_school_us_history_light
+  - arabic_leaderboard_arabic_mmlu_high_school_world_history_light
+  - arabic_leaderboard_arabic_mmlu_human_aging_light
+  - arabic_leaderboard_arabic_mmlu_human_sexuality_light
+  - arabic_leaderboard_arabic_mmlu_international_law_light
+  - arabic_leaderboard_arabic_mmlu_jurisprudence_light
+  - arabic_leaderboard_arabic_mmlu_logical_fallacies_light
+  - arabic_leaderboard_arabic_mmlu_machine_learning_light
+  - arabic_leaderboard_arabic_mmlu_management_light
+  - arabic_leaderboard_arabic_mmlu_marketing_light
+  - arabic_leaderboard_arabic_mmlu_medical_genetics_light
+  - arabic_leaderboard_arabic_mmlu_miscellaneous_light
+  - arabic_leaderboard_arabic_mmlu_moral_disputes_light
+  - arabic_leaderboard_arabic_mmlu_moral_scenarios_light
+  - arabic_leaderboard_arabic_mmlu_nutrition_light
+  - arabic_leaderboard_arabic_mmlu_philosophy_light
+  - arabic_leaderboard_arabic_mmlu_prehistory_light
+  - arabic_leaderboard_arabic_mmlu_professional_accounting_light
+  - arabic_leaderboard_arabic_mmlu_professional_law_light
+  - arabic_leaderboard_arabic_mmlu_professional_medicine_light
+  - arabic_leaderboard_arabic_mmlu_professional_psychology_light
+  - arabic_leaderboard_arabic_mmlu_public_relations_light
+  - arabic_leaderboard_arabic_mmlu_security_studies_light
+  - arabic_leaderboard_arabic_mmlu_sociology_light
+  - arabic_leaderboard_arabic_mmlu_us_foreign_policy_light
+  - arabic_leaderboard_arabic_mmlu_virology_light
+  - arabic_leaderboard_arabic_mmlu_world_religions_light
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: true
+  - metric: acc_norm
+    aggregation: mean
+    weight_by_size: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_logical_fallacies_light.yaml

+task: arabic_leaderboard_arabic_mmlu_logical_fallacies_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: logical_fallacies
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_machine_learning_light.yaml

+task: arabic_leaderboard_arabic_mmlu_machine_learning_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: machine_learning
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_management_light.yaml

+task: arabic_leaderboard_arabic_mmlu_management_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: management
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_marketing_light.yaml

+task: arabic_leaderboard_arabic_mmlu_marketing_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: marketing
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_arabic_mmlu_light/arabic_leaderboard_arabic_mmlu_medical_genetics_light.yaml

+task: arabic_leaderboard_arabic_mmlu_medical_genetics_light
+dataset_path: arcee-globe/Arabic_MMLU-10percent
+dataset_name: medical_genetics
+output_type: multiple_choice
+training_split: null
+validation_split: dev
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0