Merge branch 'main' into longcxt

lm_eval/tasks/llama3/instruct/mmlu/mmlu_security_studies.yaml

+"dataset_name": "security_studies"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_social_sciences_tasks"
+"task": "mmlu_llama_security_studies"
+"task_alias": "security studies"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_sociology.yaml

+"dataset_name": "sociology"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_social_sciences_tasks"
+"task": "mmlu_llama_sociology"
+"task_alias": "sociology"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_us_foreign_policy.yaml

+"dataset_name": "us_foreign_policy"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_social_sciences_tasks"
+"task": "mmlu_llama_us_foreign_policy"
+"task_alias": "us foreign policy"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_virology.yaml

+"dataset_name": "virology"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_other_tasks"
+"task": "mmlu_llama_virology"
+"task_alias": "virology"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_world_religions.yaml

+"dataset_name": "world_religions"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_humanities_tasks"
+"task": "mmlu_llama_world_religions"
+"task_alias": "world religions"

lm_eval/tasks/llama3/instruct/mmlu_pro/_default_template_yaml

+dataset_path: TIGER-Lab/MMLU-Pro
+output_type: generate_until
+test_split: test
+fewshot_split: validation
+fewshot_config:
+    sampler: first_n
+    doc_to_target: !function utils.fewshot_to_text
+doc_to_text: "{% set letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' %}Given the following question and candidate answers, choose the best answer.\nQuestion: {{question.strip()}}\n{% for choice in options %}{{letters[loop.index0]}}. {{choice}}\n{% endfor %}\nYour response should end with \"The best answer is [the_answer_letter].\" where the [the_answer_letter] is a letter from the provided choices.\n\nLet's think step by step."
+doc_to_target: answer
+num_fewshot: 5
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+    regexes_to_ignore:
+      - "\\$"
+      - "\\.$"
+generation_kwargs:
+  until:
+    - "."
+  max_gen_toks: 1024
+filter_list:
+  - name: strict_match
+    filter:
+        - function: "regex"
+          regex_pattern: "[tT]he best answer is ([A-Z])"
+          group_select: -1
+        - function: take_first
+metadata:
+  version: 1.0
+dataset_kwargs:
+  trust_remote_code: true

lm_eval/tasks/llama3/instruct/mmlu_pro/_mmlu_pro.yaml

+group: mmlu_pro_llama
+task:
+  - mmlu_pro_llama_biology
+  - mmlu_pro_llama_business
+  - mmlu_pro_llama_chemistry
+  - mmlu_pro_llama_computer_science
+  - mmlu_pro_llama_economics
+  - mmlu_pro_llama_engineering
+  - mmlu_pro_llama_health
+  - mmlu_pro_llama_history
+  - mmlu_pro_llama_law
+  - mmlu_pro_llama_math
+  - mmlu_pro_llama_other
+  - mmlu_pro_llama_philosophy
+  - mmlu_pro_llama_physics
+  - mmlu_pro_llama_psychology
+aggregate_metric_list:
+  - aggregation: mean
+    metric: exact_match
+    weight_by_size: true
+    filter_list: custom-extract
+metadata:
+  version: 1.0

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_biology.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_biology"
+task_alias: "biology"
+process_docs: !function utils.process_biology

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_business.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_business"
+task_alias: "business"
+process_docs: !function utils.process_business

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_chemistry.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_chemistry"
+task_alias: "chemistry"
+process_docs: !function utils.process_chemistry

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_computer_science.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_computer_science"
+task_alias: "computer_science"
+process_docs: !function utils.process_computer_science

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_economics.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_economics"
+task_alias: "economics"
+process_docs: !function utils.process_economics

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_engineering.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_engineering"
+task_alias: "engineering"
+process_docs: !function utils.process_engineering

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_health.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_health"
+task_alias: "health"
+process_docs: !function utils.process_health

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_history.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_history"
+task_alias: "history"
+process_docs: !function utils.process_history

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_law.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_law"
+task_alias: "law"
+process_docs: !function utils.process_law

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_math.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_math"
+task_alias: "math"
+process_docs: !function utils.process_math

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_other.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_other"
+task_alias: "other"
+process_docs: !function utils.process_other

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_philosophy.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_philosophy"
+task_alias: "philosophy"
+process_docs: !function utils.process_philosophy

lm_eval/tasks/llama3/instruct/mmlu_pro/mmlu_pro_physics.yaml

+include: "_default_template_yaml"
+task: "mmlu_pro_llama_physics"
+task_alias: "physics"
+process_docs: !function utils.process_physics