fix alllll the merge conflicts

lm_eval/tasks/mmlu/continuation/mmlu_professional_law.yaml

 "dataset_name": "professional_law"
 "description": "The following are questions (with answers) about professional\
   \ law.\n\n"
-"group": "mmlu_continuation_humanities"
+"tag": "mmlu_continuation_humanities"
 "include": "_continuation_template_yaml"
 "task": "mmlu_continuation_professional_law"

lm_eval/tasks/mmlu/continuation/mmlu_professional_medicine.yaml

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

lm_eval/tasks/mmlu/continuation/mmlu_professional_psychology.yaml

 "dataset_name": "professional_psychology"
 "description": "The following are questions (with answers) about professional\
   \ psychology.\n\n"
-"group": "mmlu_continuation_social_sciences"
+"tag": "mmlu_continuation_social_sciences"
 "include": "_continuation_template_yaml"
 "task": "mmlu_continuation_professional_psychology"

lm_eval/tasks/mmlu/continuation/mmlu_public_relations.yaml

 "dataset_name": "public_relations"
 "description": "The following are questions (with answers) about public\
   \ relations.\n\n"
-"group": "mmlu_continuation_social_sciences"
+"tag": "mmlu_continuation_social_sciences"
 "include": "_continuation_template_yaml"
 "task": "mmlu_continuation_public_relations"

lm_eval/tasks/mmlu/continuation/mmlu_security_studies.yaml

 "dataset_name": "security_studies"
 "description": "The following are questions (with answers) about security\
   \ studies.\n\n"
-"group": "mmlu_continuation_social_sciences"
+"tag": "mmlu_continuation_social_sciences"
 "include": "_continuation_template_yaml"
 "task": "mmlu_continuation_security_studies"

lm_eval/tasks/mmlu/continuation/mmlu_sociology.yaml

 "dataset_name": "sociology"
 "description": "The following are questions (with answers) about sociology.\n\
   \n"
-"group": "mmlu_continuation_social_sciences"
+"tag": "mmlu_continuation_social_sciences"
 "include": "_continuation_template_yaml"
 "task": "mmlu_continuation_sociology"

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

@@ -4,7 +4,7 @@ task:
   - mmlu_other
   - mmlu_social_sciences
   - mmlu_humanities
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     weight_by_size: True
 metadata:

lm_eval/tasks/mmlu/default/_mmlu_humanities.yaml

@@ -2,7 +2,7 @@ group: mmlu_humanities
 group_alias: humanities
 task:
   - mmlu_humanities_tasks
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     weight_by_size: True
 metadata:

lm_eval/tasks/mmlu/default/_mmlu_other.yaml

@@ -2,7 +2,7 @@ group: mmlu_other
 group_alias: other
 task:
   - mmlu_other_tasks
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     weight_by_size: True
 metadata:

lm_eval/tasks/mmlu/default/_mmlu_social_sciences.yaml

@@ -2,7 +2,7 @@ group: mmlu_social_sciences
 group_alias: social sciences
 task:
   - mmlu_social_sciences_tasks
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     weight_by_size: True
 metadata:

lm_eval/tasks/mmlu/default/_mmlu_stem.yaml

@@ -2,7 +2,7 @@ group: mmlu_stem
 group_alias: stem
 task:
   - mmlu_stem_tasks
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     weight_by_size: True
 metadata:

lm_eval/tasks/mmlu/flan_cot_fewshot/_mmlu.yaml

@@ -4,28 +4,28 @@ task:
   - group: stem
     task:
       - mmlu_flan_cot_fewshot_stem
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: other
     task:
       - mmlu_flan_cot_fewshot_other
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: social sciences
     task:
       - mmlu_flan_cot_fewshot_social_sciences
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: humanities
     task:
       - mmlu_flan_cot_fewshot_humanities
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     weight_by_size: True
 metadata:

lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu.yaml

@@ -4,28 +4,28 @@ task:
   - group: stem
     task:
       - mmlu_flan_cot_zeroshot_stem
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: other
     task:
       - mmlu_flan_cot_zeroshot_other
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: social sciences
     task:
       - mmlu_flan_cot_zeroshot_social_sciences
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: humanities
     task:
       - mmlu_flan_cot_zeroshot_humanities
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     weight_by_size: True
 metadata:

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

@@ -4,28 +4,28 @@ task:
   - group: stem
     task:
       - mmlu_flan_n_shot_generative_stem
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: other
     task:
       - mmlu_flan_n_shot_generative_other
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: social sciences
     task:
       - mmlu_flan_n_shot_generative_social_sciences
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: humanities
     task:
       - mmlu_flan_n_shot_generative_humanities
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     weight_by_size: True
 metadata:

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/loglikelihood/_mmlu.yaml

@@ -4,28 +4,28 @@ task:
   - group: stem
     task:
       - mmlu_flan_n_shot_loglikelihood_stem
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: other
     task:
       - mmlu_flan_n_shot_loglikelihood_other
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: social sciences
     task:
       - mmlu_flan_n_shot_loglikelihood_social_sciences
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: humanities
     task:
       - mmlu_flan_n_shot_loglikelihood_humanities
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     weight_by_size: True
 metadata:

lm_eval/tasks/mmlu/generative/_mmlu.yaml

@@ -4,28 +4,28 @@ task:
   - group: stem
     task:
       - mmlu_stem_generative
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: other
     task:
       - mmlu_other_generative
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: social sciences
     task:
       - mmlu_social_sciences_generative
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
   - group: humanities
     task:
       - mmlu_humanities_generative
-    aggregate_metric:
+    aggregate_metric_list:
       - metric: acc
         weight_by_size: True
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     weight_by_size: True
 metadata: