Merge branch 'main' into multimodal-prototyping

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_marketing.yaml

 "dataset_name": "marketing"
 "description": "The following are multiple choice questions (with answers) about marketing.\n\
   \n"
-"group": "mmlu_flan_n_shot_loglikelihood_other"
+"tag": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_marketing"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_medical_genetics.yaml

 "dataset_name": "medical_genetics"
 "description": "The following are multiple choice questions (with answers) about medical\
   \ genetics.\n\n"
-"group": "mmlu_flan_n_shot_loglikelihood_other"
+"tag": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_medical_genetics"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_miscellaneous.yaml

 "dataset_name": "miscellaneous"
 "description": "The following are multiple choice questions (with answers) about miscellaneous.\n\
   \n"
-"group": "mmlu_flan_n_shot_loglikelihood_other"
+"tag": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_miscellaneous"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_moral_disputes.yaml

 "dataset_name": "moral_disputes"
 "description": "The following are multiple choice questions (with answers) about moral\
   \ disputes.\n\n"
-"group": "mmlu_flan_n_shot_loglikelihood_humanities"
+"tag": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_moral_disputes"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_moral_scenarios.yaml

 "dataset_name": "moral_scenarios"
 "description": "The following are multiple choice questions (with answers) about moral\
   \ scenarios.\n\n"
-"group": "mmlu_flan_n_shot_loglikelihood_humanities"
+"tag": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_moral_scenarios"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_nutrition.yaml

 "dataset_name": "nutrition"
 "description": "The following are multiple choice questions (with answers) about nutrition.\n\
   \n"
-"group": "mmlu_flan_n_shot_loglikelihood_other"
+"tag": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_nutrition"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_philosophy.yaml

 "dataset_name": "philosophy"
 "description": "The following are multiple choice questions (with answers) about philosophy.\n\
   \n"
-"group": "mmlu_flan_n_shot_loglikelihood_humanities"
+"tag": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_philosophy"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_prehistory.yaml

 "dataset_name": "prehistory"
 "description": "The following are multiple choice questions (with answers) about prehistory.\n\
   \n"
-"group": "mmlu_flan_n_shot_loglikelihood_humanities"
+"tag": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_prehistory"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_accounting.yaml

 "dataset_name": "professional_accounting"
 "description": "The following are multiple choice questions (with answers) about professional\
   \ accounting.\n\n"
-"group": "mmlu_flan_n_shot_loglikelihood_other"
+"tag": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_professional_accounting"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_law.yaml

 "dataset_name": "professional_law"
 "description": "The following are multiple choice questions (with answers) about professional\
   \ law.\n\n"
-"group": "mmlu_flan_n_shot_loglikelihood_humanities"
+"tag": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_professional_law"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_medicine.yaml

 "dataset_name": "professional_medicine"
 "description": "The following are multiple choice questions (with answers) about professional\
   \ medicine.\n\n"
-"group": "mmlu_flan_n_shot_loglikelihood_other"
+"tag": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_professional_medicine"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_psychology.yaml

 "dataset_name": "professional_psychology"
 "description": "The following are multiple choice questions (with answers) about professional\
   \ psychology.\n\n"
-"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
+"tag": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_professional_psychology"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_public_relations.yaml

 "dataset_name": "public_relations"
 "description": "The following are multiple choice questions (with answers) about public\
   \ relations.\n\n"
-"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
+"tag": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_public_relations"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_security_studies.yaml

 "dataset_name": "security_studies"
 "description": "The following are multiple choice questions (with answers) about security\
   \ studies.\n\n"
-"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
+"tag": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_security_studies"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_sociology.yaml

 "dataset_name": "sociology"
 "description": "The following are multiple choice questions (with answers) about sociology.\n\
   \n"
-"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
+"tag": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_sociology"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_us_foreign_policy.yaml

 "dataset_name": "us_foreign_policy"
 "description": "The following are multiple choice questions (with answers) about us\
   \ foreign policy.\n\n"
-"group": "mmlu_flan_n_shot_loglikelihood_social_sciences"
+"tag": "mmlu_flan_n_shot_loglikelihood_social_sciences"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_us_foreign_policy"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_virology.yaml

 "dataset_name": "virology"
 "description": "The following are multiple choice questions (with answers) about virology.\n\
   \n"
-"group": "mmlu_flan_n_shot_loglikelihood_other"
+"tag": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_virology"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/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_n_shot_loglikelihood_humanities"
+"tag": "mmlu_flan_n_shot_loglikelihood_humanities"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_world_religions"

lm_eval/tasks/mmlu/generative/_mmlu.yaml

 group: mmlu_generative
+group_alias: mmlu (generative)
 task:
-  - mmlu_stem_generative
-  - mmlu_other_generative
-  - mmlu_social_sciences_generative
-  - mmlu_humanities_generative
+  - group: stem
+    task:
+      - mmlu_stem_generative
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: other
+    task:
+      - mmlu_other_generative
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: social sciences
+    task:
+      - mmlu_social_sciences_generative
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: humanities
+    task:
+      - mmlu_humanities_generative
+    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/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_stem_generative"
-"group_alias": "stem"
+"tag": "mmlu_stem_generative"
 "include": "_default_template_yaml"
 "task": "mmlu_abstract_algebra_generative"
 "task_alias": "abstract_algebra"