Merge branch 'main' into multimodal-prototyping

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_us_foreign_policy.yaml

@@ -51,6 +51,6 @@ fewshot_config:
     target: 'Let''s think step by step. We refer to Wikipedia articles on us foreign
       policy for help. The 2008 financial crisis damanged the international reputation
       of the American model of political economy and capitalism. The answer is (A).'
-group: mmlu_flan_cot_fewshot_social_sciences
+tag: mmlu_flan_cot_fewshot_social_sciences
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_us_foreign_policy

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_virology.yaml

@@ -40,6 +40,6 @@ fewshot_config:
     target: 'Let''s think step by step. We refer to Wikipedia articles on virology
       for help. Paroviruses are highly impactful because they do not have nucleic
       acid. The answer is (A).'
-group: mmlu_flan_cot_fewshot_other
+tag: mmlu_flan_cot_fewshot_other
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_virology

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_world_religions.yaml

@@ -37,6 +37,6 @@ fewshot_config:
     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).'
-group: mmlu_flan_cot_fewshot_humanities
+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:
-  - mmlu_flan_cot_zeroshot_stem
-  - mmlu_flan_cot_zeroshot_other
-  - mmlu_flan_cot_zeroshot_social_sciences
-  - mmlu_flan_cot_zeroshot_humanities
+  - 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_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"