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_cot_fewshot/mmlu_moral_scenarios.yaml

@@ -57,6 +57,6 @@ fewshot_config:
     target: 'Let''s think step by step. We refer to Wikipedia articles on moral scenarios
       for help. Loving someone is not wrong. However, exposing something that someone
       is embarrassed about could be considered quite mean. The answer is (C).'
-group: mmlu_flan_cot_fewshot_humanities
+tag: mmlu_flan_cot_fewshot_humanities
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_moral_scenarios

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_nutrition.yaml

@@ -58,6 +58,6 @@ fewshot_config:
     target: 'Let''s think step by step. We refer to Wikipedia articles on nutrition
       for help. The risk ratio is not sufficiently reduced that it could not be explained
       by random chance given the studies sample size. The answer is (C).'
-group: mmlu_flan_cot_fewshot_other
+tag: mmlu_flan_cot_fewshot_other
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_nutrition

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_philosophy.yaml

@@ -39,6 +39,6 @@ fewshot_config:
       for help. Psychological egoism suggests that one behaves based on what makes
       one feels good, hence it is a claim about human nature and how humans are capable
       of behaving. The answer is (C).'
-group: mmlu_flan_cot_fewshot_humanities
+tag: mmlu_flan_cot_fewshot_humanities
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_philosophy

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_prehistory.yaml

@@ -54,6 +54,6 @@ fewshot_config:
     target: 'Let''s think step by step. We refer to Wikipedia articles on prehistory
       for help. Pacal built the temples as the funerary monument to legitimize his
       kingship. The answer is (D).'
-group: mmlu_flan_cot_fewshot_humanities
+tag: mmlu_flan_cot_fewshot_humanities
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_prehistory

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_professional_accounting.yaml

@@ -58,6 +58,6 @@ fewshot_config:
       for help. Among the four transactions, only Proceeds from long-term debt belongs
       to the financing activities section of cashflow, hence the amount reported should
       be $100000. The answer is (D).'
-group: mmlu_flan_cot_fewshot_other
+tag: mmlu_flan_cot_fewshot_other
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_professional_accounting

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_professional_law.yaml

@@ -117,6 +117,6 @@ fewshot_config:
       a due process clause. Hence the strongest argument should be the statute is
       overbroad and consequently invalid under the First and Fourteenth Amendments.
       The answer is (D).'
-group: mmlu_flan_cot_fewshot_humanities
+tag: mmlu_flan_cot_fewshot_humanities
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_professional_law

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_professional_medicine.yaml

@@ -77,6 +77,6 @@ fewshot_config:
       for help. The symptoms and the adrenal mass suggested pheochromocytoma, and
       the blood pressure indicates hypertension. Phenoxybenzamine is used to treat
       hypertension caused by pheochromocytoma. The answer is (D).'
-group: mmlu_flan_cot_fewshot_other
+tag: mmlu_flan_cot_fewshot_other
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_professional_medicine

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_professional_psychology.yaml

@@ -57,6 +57,6 @@ fewshot_config:
       for help. Based on the circumstances, you should tell your client about the
       pros and cons of each program, but it would be inappropriate to receive the
       bonus, so you should not claim the $50 bonus. The answer is (D).'
-group: mmlu_flan_cot_fewshot_social_sciences
+tag: mmlu_flan_cot_fewshot_social_sciences
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_professional_psychology

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_public_relations.yaml

@@ -50,6 +50,6 @@ fewshot_config:
       for help. If a public relations media practitioner does not know the answer
       to a reporter''s question, they should say ''I don''t know'' and offer to provide
       the information later. The answer is (C).'
-group: mmlu_flan_cot_fewshot_social_sciences
+tag: mmlu_flan_cot_fewshot_social_sciences
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_public_relations

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_security_studies.yaml

@@ -99,6 +99,6 @@ fewshot_config:
     target: 'Let''s think step by step. We refer to Wikipedia articles on security
       studies for help. Coercive diplomacy uses the threat of force to induce the
       opponent to comply with demands. The answer is (B).'
-group: mmlu_flan_cot_fewshot_social_sciences
+tag: mmlu_flan_cot_fewshot_social_sciences
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_security_studies

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_sociology.yaml

@@ -53,6 +53,6 @@ fewshot_config:
       for help. The post-war welfare state of 1948 aimed to provide free healthcare
       and education, full employment, and universal welfare. But it did not aim to
       provide a minimum wage. The answer is (B).'
-group: mmlu_flan_cot_fewshot_social_sciences
+tag: mmlu_flan_cot_fewshot_social_sciences
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_sociology

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_us_foreign_policy.yaml

@@ -51,6 +51,6 @@ fewshot_config:
     target: 'Let''s think step by step. We refer to Wikipedia articles on us foreign
       policy for help. The 2008 financial crisis damanged the international reputation
       of the American model of political economy and capitalism. The answer is (A).'
-group: mmlu_flan_cot_fewshot_social_sciences
+tag: mmlu_flan_cot_fewshot_social_sciences
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_us_foreign_policy

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_virology.yaml

@@ -40,6 +40,6 @@ fewshot_config:
     target: 'Let''s think step by step. We refer to Wikipedia articles on virology
       for help. Paroviruses are highly impactful because they do not have nucleic
       acid. The answer is (A).'
-group: mmlu_flan_cot_fewshot_other
+tag: mmlu_flan_cot_fewshot_other
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_virology

lm_eval/tasks/mmlu/flan_cot_fewshot/mmlu_world_religions.yaml

@@ -37,6 +37,6 @@ fewshot_config:
     target: 'Let''s think step by step. We refer to Wikipedia articles on world religions
       for help. In Judaism, the most distinctive sign of the covenant is circumcision
       (brit milah). The answer is (B).'
-group: mmlu_flan_cot_fewshot_humanities
+tag: mmlu_flan_cot_fewshot_humanities
 include: _mmlu_flan_cot_fewshot_template_yaml
 task: mmlu_flan_cot_fewshot_world_religions

lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu.yaml

 group: mmlu_flan_cot_zeroshot
+group_alias: mmlu (flan style, zeroshot cot)
 task:
-  - mmlu_flan_cot_zeroshot_stem
-  - mmlu_flan_cot_zeroshot_other
-  - mmlu_flan_cot_zeroshot_social_sciences
-  - mmlu_flan_cot_zeroshot_humanities
+  - group: stem
+    task:
+      - mmlu_flan_cot_zeroshot_stem
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: other
+    task:
+      - mmlu_flan_cot_zeroshot_other
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: social sciences
+    task:
+      - mmlu_flan_cot_zeroshot_social_sciences
+    aggregate_metric_list:
+      - metric: acc
+        weight_by_size: True
+  - group: humanities
+    task:
+      - mmlu_flan_cot_zeroshot_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_cot_zeroshot/_mmlu_flan_cot_zeroshot_template_yaml

@@ -34,3 +34,5 @@ metric_list:
     ignore_punctuation: true
 metadata:
   version: 2.0
+dataset_kwargs:
+  trust_remote_code: true

lm_eval/tasks/mmlu/flan_cot_zeroshot/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_cot_zeroshot_stem"
+"tag": "mmlu_flan_cot_zeroshot_stem"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_abstract_algebra"

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_anatomy.yaml

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

lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_astronomy.yaml

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

lm_eval/tasks/mmlu/flan_cot_zeroshot/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_cot_zeroshot_other"
+"tag": "mmlu_flan_cot_zeroshot_other"
 "include": "_mmlu_flan_cot_zeroshot_template_yaml"
 "task": "mmlu_flan_cot_zeroshot_business_ethics"