Merge branch 'upstream' into 'mmlu-pro'

add tokenizer logs info (#1731)

See merge request shijie.yu/lm-evaluation-harness!4

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

 "dataset_name": "philosophy"
 "description": "The following are multiple choice questions (with answers) about philosophy.\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_philosophy"

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

 "dataset_name": "prehistory"
 "description": "The following are multiple choice questions (with answers) about prehistory.\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_prehistory"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_generative_other"
+"tag": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_professional_accounting"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_generative_humanities"
+"tag": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_professional_law"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_generative_other"
+"tag": "mmlu_flan_n_shot_generative_other"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_professional_medicine"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_generative_social_sciences"
+"tag": "mmlu_flan_n_shot_generative_social_sciences"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_professional_psychology"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_generative_social_sciences"
+"tag": "mmlu_flan_n_shot_generative_social_sciences"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_public_relations"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_generative_social_sciences"
+"tag": "mmlu_flan_n_shot_generative_social_sciences"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_security_studies"

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

 "dataset_name": "sociology"
 "description": "The following are multiple choice questions (with answers) about sociology.\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_sociology"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_generative_social_sciences"
+"tag": "mmlu_flan_n_shot_generative_social_sciences"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_us_foreign_policy"

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

 "dataset_name": "virology"
 "description": "The following are multiple choice questions (with answers) about virology.\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_virology"

lm_eval/tasks/mmlu/flan_n_shot/generative/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_generative_humanities"
+"tag": "mmlu_flan_n_shot_generative_humanities"
 "include": "_mmlu_flan_generative_template_yaml"
 "task": "mmlu_flan_n_shot_generative_world_religions"

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

 group: mmlu_flan_n_shot_loglikelihood
+group_alias: mmlu (flan style, loglikelihood)
 task:
-  - mmlu_flan_n_shot_loglikelihood_stem
-  - mmlu_flan_n_shot_loglikelihood_other
-  - mmlu_flan_n_shot_loglikelihood_social_sciences
-  - mmlu_flan_n_shot_loglikelihood_humanities
+  - group: stem
+    task:
+      - mmlu_flan_n_shot_loglikelihood_stem
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: other
+    task:
+      - mmlu_flan_n_shot_loglikelihood_other
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: social sciences
+    task:
+      - mmlu_flan_n_shot_loglikelihood_social_sciences
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: humanities
+    task:
+      - mmlu_flan_n_shot_loglikelihood_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/loglikelihood/_mmlu_flan_loglikelihood_template_yaml

@@ -13,3 +13,5 @@ metric_list:
     higher_is_better: true
 metadata:
   version: 1.0
+dataset_kwargs:
+  trust_remote_code: true

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/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_loglikelihood_stem"
+"tag": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_abstract_algebra"

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

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

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

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

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/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_loglikelihood_other"
+"tag": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_business_ethics"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/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_loglikelihood_other"
+"tag": "mmlu_flan_n_shot_loglikelihood_other"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_clinical_knowledge"

lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/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_loglikelihood_stem"
+"tag": "mmlu_flan_n_shot_loglikelihood_stem"
 "include": "_mmlu_flan_loglikelihood_template_yaml"
 "task": "mmlu_flan_n_shot_loglikelihood_college_biology"