Merge branch 'main' into multimodal-prototyping

lm_eval/tasks/mmlu/continuation/mmlu_us_foreign_policy.yaml

 "dataset_name": "us_foreign_policy"
 "description": "The following are questions (with answers) about us\
   \ foreign policy.\n\n"
-"group": "mmlu_continuation_social_sciences"
+"tag": "mmlu_continuation_social_sciences"
 "include": "_continuation_template_yaml"
 "task": "mmlu_continuation_us_foreign_policy"

lm_eval/tasks/mmlu/continuation/mmlu_virology.yaml

 "dataset_name": "virology"
 "description": "The following are questions (with answers) about virology.\n\
   \n"
-"group": "mmlu_continuation_other"
+"tag": "mmlu_continuation_other"
 "include": "_continuation_template_yaml"
 "task": "mmlu_continuation_virology"

lm_eval/tasks/mmlu/continuation/mmlu_world_religions.yaml

 "dataset_name": "world_religions"
 "description": "The following are questions (with answers) about world\
   \ religions.\n\n"
-"group": "mmlu_continuation_humanities"
+"tag": "mmlu_continuation_humanities"
 "include": "_continuation_template_yaml"
 "task": "mmlu_continuation_world_religions"

lm_eval/tasks/mmlu/default/_mmlu.yaml

@@ -4,3 +4,8 @@ task:
   - mmlu_other
   - mmlu_social_sciences
   - mmlu_humanities
+aggregate_metric_list:
+  - metric: acc
+    weight_by_size: True
+metadata:
+  version: 1

lm_eval/tasks/mmlu/default/_mmlu_humanities.yaml

+group: mmlu_humanities
+group_alias: humanities
+task:
+  - mmlu_humanities_tasks
+aggregate_metric_list:
+  - metric: acc
+    weight_by_size: True
+metadata:
+  version: 1

lm_eval/tasks/mmlu/default/_mmlu_other.yaml

+group: mmlu_other
+group_alias: other
+task:
+  - mmlu_other_tasks
+aggregate_metric_list:
+  - metric: acc
+    weight_by_size: True
+metadata:
+  version: 1

lm_eval/tasks/mmlu/default/_mmlu_social_sciences.yaml

+group: mmlu_social_sciences
+group_alias: social sciences
+task:
+  - mmlu_social_sciences_tasks
+aggregate_metric_list:
+  - metric: acc
+    weight_by_size: True
+metadata:
+  version: 1

lm_eval/tasks/mmlu/default/_mmlu_stem.yaml

+group: mmlu_stem
+group_alias: stem
+task:
+  - mmlu_stem_tasks
+aggregate_metric_list:
+  - metric: acc
+    weight_by_size: True
+metadata:
+  version: 1

lm_eval/tasks/mmlu/default/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"
-"group_alias": "stem"
+"tag": "mmlu_stem_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_abstract_algebra"
 "task_alias": "abstract_algebra"

lm_eval/tasks/mmlu/default/mmlu_anatomy.yaml

 "dataset_name": "anatomy"
 "description": "The following are multiple choice questions (with answers) about anatomy.\n\
   \n"
-"group": "mmlu_stem"
-"group_alias": "stem"
+"tag": "mmlu_stem_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_anatomy"
 "task_alias": "anatomy"

lm_eval/tasks/mmlu/default/mmlu_astronomy.yaml

 "dataset_name": "astronomy"
 "description": "The following are multiple choice questions (with answers) about astronomy.\n\
   \n"
-"group": "mmlu_stem"
-"group_alias": "stem"
+"tag": "mmlu_stem_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_astronomy"
 "task_alias": "astronomy"

lm_eval/tasks/mmlu/default/mmlu_business_ethics.yaml

 "dataset_name": "business_ethics"
 "description": "The following are multiple choice questions (with answers) about business\
   \ ethics.\n\n"
-"group": "mmlu_other"
-"group_alias": "other"
+"tag": "mmlu_other_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_business_ethics"
 "task_alias": "business_ethics"

lm_eval/tasks/mmlu/default/mmlu_clinical_knowledge.yaml

 "dataset_name": "clinical_knowledge"
 "description": "The following are multiple choice questions (with answers) about clinical\
   \ knowledge.\n\n"
-"group": "mmlu_other"
-"group_alias": "other"
+"tag": "mmlu_other_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_clinical_knowledge"
 "task_alias": "clinical_knowledge"

lm_eval/tasks/mmlu/default/mmlu_college_biology.yaml

 "dataset_name": "college_biology"
 "description": "The following are multiple choice questions (with answers) about college\
   \ biology.\n\n"
-"group": "mmlu_stem"
-"group_alias": "stem"
+"tag": "mmlu_stem_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_college_biology"
 "task_alias": "college_biology"

lm_eval/tasks/mmlu/default/mmlu_college_chemistry.yaml

 "dataset_name": "college_chemistry"
 "description": "The following are multiple choice questions (with answers) about college\
   \ chemistry.\n\n"
-"group": "mmlu_stem"
-"group_alias": "stem"
+"tag": "mmlu_stem_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_college_chemistry"
 "task_alias": "college_chemistry"

lm_eval/tasks/mmlu/default/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_stem"
-"group_alias": "stem"
+"tag": "mmlu_stem_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_college_computer_science"
 "task_alias": "college_computer_science"

lm_eval/tasks/mmlu/default/mmlu_college_mathematics.yaml

 "dataset_name": "college_mathematics"
 "description": "The following are multiple choice questions (with answers) about college\
   \ mathematics.\n\n"
-"group": "mmlu_stem"
-"group_alias": "stem"
+"tag": "mmlu_stem_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_college_mathematics"
 "task_alias": "college_mathematics"

lm_eval/tasks/mmlu/default/mmlu_college_medicine.yaml

 "dataset_name": "college_medicine"
 "description": "The following are multiple choice questions (with answers) about college\
   \ medicine.\n\n"
-"group": "mmlu_other"
-"group_alias": "other"
+"tag": "mmlu_other_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_college_medicine"
 "task_alias": "college_medicine"

lm_eval/tasks/mmlu/default/mmlu_college_physics.yaml

 "dataset_name": "college_physics"
 "description": "The following are multiple choice questions (with answers) about college\
   \ physics.\n\n"
-"group": "mmlu_stem"
-"group_alias": "stem"
+"tag": "mmlu_stem_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_college_physics"
 "task_alias": "college_physics"

lm_eval/tasks/mmlu/default/mmlu_computer_security.yaml

 "dataset_name": "computer_security"
 "description": "The following are multiple choice questions (with answers) about computer\
   \ security.\n\n"
-"group": "mmlu_stem"
-"group_alias": "stem"
+"tag": "mmlu_stem_tasks"
 "include": "_default_template_yaml"
 "task": "mmlu_computer_security"
 "task_alias": "computer_security"