Merge branch 'main' into multimodal-prototyping

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_world_religions.yaml

 "dataset_name": "world_religions"
 "description": "The following are multiple choice questions (with answers) about world\
   \ religions.\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_world_religions"

lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu.yaml

 group: mmlu_flan_n_shot_generative
+group_alias: mmlu (flan style, generative)
 task:
-  - mmlu_flan_n_shot_generative_stem
-  - mmlu_flan_n_shot_generative_other
-  - mmlu_flan_n_shot_generative_social_sciences
-  - mmlu_flan_n_shot_generative_humanities
+  - group: stem
+    task:
+      - mmlu_flan_n_shot_generative_stem
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: other
+    task:
+      - mmlu_flan_n_shot_generative_other
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: social sciences
+    task:
+      - mmlu_flan_n_shot_generative_social_sciences
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: humanities
+    task:
+      - mmlu_flan_n_shot_generative_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_n_shot/generative/_mmlu_flan_generative_template_yaml

-group: mmlu_flan_n_shot_generative
 dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
 test_split: test
 fewshot_split: dev

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_stem"
+"tag": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_abstract_algebra"

lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_anatomy.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_astronomy.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_other"
+"tag": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_business_ethics"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_other"
+"tag": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_clinical_knowledge"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_stem"
+"tag": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_college_biology"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_stem"
+"tag": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_college_chemistry"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_stem"
+"tag": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_college_computer_science"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_stem"
+"tag": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_college_mathematics"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_other"
+"tag": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_college_medicine"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_stem"
+"tag": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_college_physics"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_stem"
+"tag": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_computer_security"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_stem"
+"tag": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_conceptual_physics"

lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_econometrics.yaml

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

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_stem"
+"tag": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_electrical_engineering"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_stem"
+"tag": "mmlu_flan_n_shot_generative_stem"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_elementary_mathematics"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_n_shot_generative_humanities"
+"tag": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_formal_logic"