Merge branch 'EleutherAI:main' into main

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_world_religions.yaml

-"dataset_name": "world_religions"
-"description": "The following are multiple choice questions (with answers) about world\
-  \ religions.\n\nQ: How can the Upanishads be characterized?\n(A) Ritual texts (B)\
-  \ Philosophical texts (C) Hymns (D) Origin stories\nA: Let's think step by step.\
-  \ We refer to Wikipedia articles on world religions for help. The Upanishads are\
-  \ the most recent part of Vedas (the oldest scriptures in Hinduism) and supplied\
-  \ the basis of later Hindu philosophy. So they are philosophical texts. The answer\
-  \ is (B).\n\nQ: What is the Second Gem in Buddhism?\n(A) The Dharma (B) The Sangha\
-  \ (C) The Buddha (D) The Bodhisattva\nA: Let's think step by step. We refer to Wikipedia\
-  \ articles on world religions for help. The Second Gem in Buddhism is The Dharma.\
-  \ The answer is (A).\n\nQ: Which Japanese government promoted a kind of national\
-  \ cult based on the emperor and his associations with kami?\n(A) Honen (B) Tanaka\
-  \ (C) Tokugawa (D) Meiji\nA: Let's think step by step. We refer to Wikipedia articles\
-  \ on world religions for help. The promotion of a national cult based on the emperor\
-  \ and his associations with Kami happened during the reign of Emperor Meiji (1852-1912).\
-  \ The answer is (D).\n\nQ: In which dynasty was the \"Mandate of Heaven\" developed\
-  \ to legitimatize the new rulers?\n(A) Shang (B) Zhou (C) Han (D) Xia\nA: Let's\
-  \ think step by step. We refer to Wikipedia articles on world religions for help.\
-  \ The \"Mandate of Heaven\" was developed as an ancient Chinese philosophical concept\
-  \ during the Zhou Dynasty (1046-256 BCE). The answer is (B).\n\nQ: What is the sign\
-  \ of the covenant for Jewish males?\n(A) The rainbow (B) Circumcision (C) A son\
-  \ (D) Bar mitzvah\nA: Let's think step by step. We refer to Wikipedia articles on\
-  \ world religions for help. In Judaism, the most distinctive sign of the covenant\
-  \ is circumcision (brit milah). The answer is (B).\n\n"
-"group": "mmlu_flan_cot_fewshot_humanities"
-"include": "_mmlu_flan_cot_fewshot_template_yaml"
-"task": "mmlu_flan_cot_fewshot_world_religions"
+dataset_name: world_religions
+description: The following are multiple choice questions (with answers) about world
+  religions.
+fewshot_config:
+  sampler: first_n
+  samples:
+  - question: 'How can the Upanishads be characterized?
+
+      (A) Ritual texts (B) Philosophical texts (C) Hymns (D) Origin stories'
+    target: Let's think step by step. We refer to Wikipedia articles on world religions
+      for help. The Upanishads are the most recent part of Vedas (the oldest scriptures
+      in Hinduism) and supplied the basis of later Hindu philosophy. So they are philosophical
+      texts. The answer is (B).
+  - question: 'What is the Second Gem in Buddhism?
+
+      (A) The Dharma (B) The Sangha (C) The Buddha (D) The Bodhisattva'
+    target: Let's think step by step. We refer to Wikipedia articles on world religions
+      for help. The Second Gem in Buddhism is The Dharma. The answer is (A).
+  - question: 'Which Japanese government promoted a kind of national cult based on the
+      emperor and his associations with kami?
+
+      (A) Honen (B) Tanaka (C) Tokugawa (D) Meiji'
+    target: Let's think step by step. We refer to Wikipedia articles on world religions
+      for help. The promotion of a national cult based on the emperor and his associations
+      with Kami happened during the reign of Emperor Meiji (1852-1912). The answer
+      is (D).
+  - question: 'In which dynasty was the "Mandate of Heaven" developed to legitimatize
+      the new rulers?
+
+      (A) Shang (B) Zhou (C) Han (D) Xia'
+    target: Let's think step by step. We refer to Wikipedia articles on world religions
+      for help. The "Mandate of Heaven" was developed as an ancient Chinese philosophical
+      concept during the Zhou Dynasty (1046-256 BCE). The answer is (B).
+  - question: 'What is the sign of the covenant for Jewish males?
+
+      (A) The rainbow (B) Circumcision (C) A son (D) Bar mitzvah'
+    target: 'Let''s think step by step. We refer to Wikipedia articles on world religions
+      for help. In Judaism, the most distinctive sign of the covenant is circumcision
+      (brit milah). The answer is (B).'
+tag: mmlu_flan_cot_fewshot_humanities
+include: _mmlu_flan_cot_fewshot_template_yaml
+task: mmlu_flan_cot_fewshot_world_religions

lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu.yaml

 group: mmlu_flan_cot_zeroshot
+group_alias: mmlu (flan style, zeroshot cot)
 task:
+  - group: stem
+    task:
       - mmlu_flan_cot_zeroshot_stem
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: other
+    task:
       - mmlu_flan_cot_zeroshot_other
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: social sciences
+    task:
       - mmlu_flan_cot_zeroshot_social_sciences
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: humanities
+    task:
       - mmlu_flan_cot_zeroshot_humanities
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+aggregate_metric_list:
+  - metric: acc
+    weight_by_size: True
+metadata:
+  version: 1

lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu_flan_cot_zeroshot_template_yaml

@@ -8,7 +8,7 @@ filter_list:
   - name: "strict-match"
     filter:
       - function: "regex"
-        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=the answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
+        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
       - function: "take_first"
   - name: "flexible-extract"
     filter:
@@ -33,4 +33,6 @@ metric_list:
     ignore_case: true
     ignore_punctuation: true
 metadata:
-  version: 1.0
+  version: 2.0
+dataset_kwargs:
+  trust_remote_code: true

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_abstract_algebra.yaml

 "dataset_name": "abstract_algebra"
 "description": "The following are multiple choice questions (with answers) about abstract\
   \ algebra.\n\n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_abstract_algebra"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_anatomy.yaml

 "dataset_name": "anatomy"
 "description": "The following are multiple choice questions (with answers) about anatomy.\n\
   \n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_anatomy"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_astronomy.yaml

 "dataset_name": "astronomy"
 "description": "The following are multiple choice questions (with answers) about astronomy.\n\
   \n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_astronomy"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_business_ethics.yaml

 "dataset_name": "business_ethics"
 "description": "The following are multiple choice questions (with answers) about business\
   \ ethics.\n\n"
-"group": "mmlu_flan_cot_zeroshot_other"
+"tag": "mmlu_flan_cot_zeroshot_other"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_business_ethics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_clinical_knowledge.yaml

 "dataset_name": "clinical_knowledge"
 "description": "The following are multiple choice questions (with answers) about clinical\
   \ knowledge.\n\n"
-"group": "mmlu_flan_cot_zeroshot_other"
+"tag": "mmlu_flan_cot_zeroshot_other"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_clinical_knowledge"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_biology.yaml

 "dataset_name": "college_biology"
 "description": "The following are multiple choice questions (with answers) about college\
   \ biology.\n\n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_college_biology"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_chemistry.yaml

 "dataset_name": "college_chemistry"
 "description": "The following are multiple choice questions (with answers) about college\
   \ chemistry.\n\n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_college_chemistry"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_computer_science.yaml

 "dataset_name": "college_computer_science"
 "description": "The following are multiple choice questions (with answers) about college\
   \ computer science.\n\n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_college_computer_science"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_mathematics.yaml

 "dataset_name": "college_mathematics"
 "description": "The following are multiple choice questions (with answers) about college\
   \ mathematics.\n\n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_college_mathematics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_medicine.yaml

 "dataset_name": "college_medicine"
 "description": "The following are multiple choice questions (with answers) about college\
   \ medicine.\n\n"
-"group": "mmlu_flan_cot_zeroshot_other"
+"tag": "mmlu_flan_cot_zeroshot_other"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_college_medicine"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_physics.yaml

 "dataset_name": "college_physics"
 "description": "The following are multiple choice questions (with answers) about college\
   \ physics.\n\n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_college_physics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_computer_security.yaml

 "dataset_name": "computer_security"
 "description": "The following are multiple choice questions (with answers) about computer\
   \ security.\n\n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_computer_security"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_conceptual_physics.yaml

 "dataset_name": "conceptual_physics"
 "description": "The following are multiple choice questions (with answers) about conceptual\
   \ physics.\n\n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_conceptual_physics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_econometrics.yaml

 "dataset_name": "econometrics"
 "description": "The following are multiple choice questions (with answers) about econometrics.\n\
   \n"
-"group": "mmlu_flan_cot_zeroshot_social_sciences"
+"tag": "mmlu_flan_cot_zeroshot_social_sciences"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_econometrics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_electrical_engineering.yaml

 "dataset_name": "electrical_engineering"
 "description": "The following are multiple choice questions (with answers) about electrical\
   \ engineering.\n\n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_electrical_engineering"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_elementary_mathematics.yaml

 "dataset_name": "elementary_mathematics"
 "description": "The following are multiple choice questions (with answers) about elementary\
   \ mathematics.\n\n"
-"group": "mmlu_flan_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_elementary_mathematics"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_formal_logic.yaml

 "dataset_name": "formal_logic"
 "description": "The following are multiple choice questions (with answers) about formal\
   \ logic.\n\n"
-"group": "mmlu_flan_cot_zeroshot_humanities"
+"tag": "mmlu_flan_cot_zeroshot_humanities"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_formal_logic"