Merge branch 'main' into humaneval

# Conflicts:
#	lm_eval/api/task.py

lm_eval/tasks/arabic_leaderboard_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_econometrics.yaml

+task: arabic_leaderboard_arabic_mmlu_econometrics
+dataset_path: OALL/Arabic_MMLU
+dataset_name: econometrics
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_electrical_engineering.yaml

+task: arabic_leaderboard_arabic_mmlu_electrical_engineering
+dataset_path: OALL/Arabic_MMLU
+dataset_name: electrical_engineering
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_elementary_mathematics.yaml

+task: arabic_leaderboard_arabic_mmlu_elementary_mathematics
+dataset_path: OALL/Arabic_MMLU
+dataset_name: elementary_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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_formal_logic.yaml

+task: arabic_leaderboard_arabic_mmlu_formal_logic
+dataset_path: OALL/Arabic_MMLU
+dataset_name: formal_logic
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_global_facts.yaml

+task: arabic_leaderboard_arabic_mmlu_global_facts
+dataset_path: OALL/Arabic_MMLU
+dataset_name: global_facts
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_biology.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_biology
+dataset_path: OALL/Arabic_MMLU
+dataset_name: high_school_biology
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_chemistry.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_chemistry
+dataset_path: OALL/Arabic_MMLU
+dataset_name: high_school_chemistry
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_computer_science.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_computer_science
+dataset_path: OALL/Arabic_MMLU
+dataset_name: high_school_computer_science
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_european_history.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_european_history
+dataset_path: OALL/Arabic_MMLU
+dataset_name: high_school_european_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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_geography.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_geography
+dataset_path: OALL/Arabic_MMLU
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_government_and_politics.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_government_and_politics
+dataset_path: OALL/Arabic_MMLU
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_macroeconomics.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_macroeconomics
+dataset_path: OALL/Arabic_MMLU
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_mathematics.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_mathematics
+dataset_path: OALL/Arabic_MMLU
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_microeconomics.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_microeconomics
+dataset_path: OALL/Arabic_MMLU
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_physics.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_physics
+dataset_path: OALL/Arabic_MMLU
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_psychology.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_psychology
+dataset_path: OALL/Arabic_MMLU
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_statistics.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_statistics
+dataset_path: OALL/Arabic_MMLU
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_us_history.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_us_history
+dataset_path: OALL/Arabic_MMLU
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_high_school_world_history.yaml

+task: arabic_leaderboard_arabic_mmlu_high_school_world_history
+dataset_path: OALL/Arabic_MMLU
+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_complete/arabic_leaderboard_arabic_mmlu/arabic_leaderboard_arabic_mmlu_human_aging.yaml

+task: arabic_leaderboard_arabic_mmlu_human_aging
+dataset_path: OALL/Arabic_MMLU
+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