Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
lm-evaluation-harness
Commits
0ffdee02
Commit
0ffdee02
authored
May 11, 2024
by
lintangsutawika
Browse files
revert mmlu tasks
parent
39246084
Changes
62
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
52 additions
and
12 deletions
+52
-12
lm_eval/tasks/mmlu/default/mmlu_jurisprudence.yaml
lm_eval/tasks/mmlu/default/mmlu_jurisprudence.yaml
+2
-0
lm_eval/tasks/mmlu/default/mmlu_logical_fallacies.yaml
lm_eval/tasks/mmlu/default/mmlu_logical_fallacies.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_machine_learning.yaml
lm_eval/tasks/mmlu/default/mmlu_machine_learning.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_management.yaml
lm_eval/tasks/mmlu/default/mmlu_management.yaml
+2
-0
lm_eval/tasks/mmlu/default/mmlu_marketing.yaml
lm_eval/tasks/mmlu/default/mmlu_marketing.yaml
+2
-0
lm_eval/tasks/mmlu/default/mmlu_medical_genetics.yaml
lm_eval/tasks/mmlu/default/mmlu_medical_genetics.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_miscellaneous.yaml
lm_eval/tasks/mmlu/default/mmlu_miscellaneous.yaml
+2
-0
lm_eval/tasks/mmlu/default/mmlu_moral_disputes.yaml
lm_eval/tasks/mmlu/default/mmlu_moral_disputes.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_moral_scenarios.yaml
lm_eval/tasks/mmlu/default/mmlu_moral_scenarios.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_nutrition.yaml
lm_eval/tasks/mmlu/default/mmlu_nutrition.yaml
+2
-0
lm_eval/tasks/mmlu/default/mmlu_philosophy.yaml
lm_eval/tasks/mmlu/default/mmlu_philosophy.yaml
+2
-0
lm_eval/tasks/mmlu/default/mmlu_prehistory.yaml
lm_eval/tasks/mmlu/default/mmlu_prehistory.yaml
+2
-0
lm_eval/tasks/mmlu/default/mmlu_professional_accounting.yaml
lm_eval/tasks/mmlu/default/mmlu_professional_accounting.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_professional_law.yaml
lm_eval/tasks/mmlu/default/mmlu_professional_law.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_professional_medicine.yaml
lm_eval/tasks/mmlu/default/mmlu_professional_medicine.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_professional_psychology.yaml
lm_eval/tasks/mmlu/default/mmlu_professional_psychology.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_public_relations.yaml
lm_eval/tasks/mmlu/default/mmlu_public_relations.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_security_studies.yaml
lm_eval/tasks/mmlu/default/mmlu_security_studies.yaml
+3
-1
lm_eval/tasks/mmlu/default/mmlu_sociology.yaml
lm_eval/tasks/mmlu/default/mmlu_sociology.yaml
+2
-0
lm_eval/tasks/mmlu/default/mmlu_us_foreign_policy.yaml
lm_eval/tasks/mmlu/default/mmlu_us_foreign_policy.yaml
+3
-1
No files found.
lm_eval/tasks/mmlu/default/mmlu_jurisprudence.yaml
View file @
0ffdee02
"
dataset_name"
:
"
jurisprudence"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
jurisprudence.
\n\
\n
"
"
group"
:
"
mmlu_humanities"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_jurisprudence"
"
task_alias"
:
"
jurisprudence"
lm_eval/tasks/mmlu/default/mmlu_logical_fallacies.yaml
View file @
0ffdee02
"
dataset_name"
:
"
logical_fallacies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
logical
\
\
fallacies.
\n\n
"
"
group"
:
"
mmlu_humanities"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_logical_fallacies"
"
task_alias"
:
"
logical
fallacies"
"
task_alias"
:
"
logical
_
fallacies"
lm_eval/tasks/mmlu/default/mmlu_machine_learning.yaml
View file @
0ffdee02
"
dataset_name"
:
"
machine_learning"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
machine
\
\
learning.
\n\n
"
"
group"
:
"
mmlu_stem"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_machine_learning"
"
task_alias"
:
"
machine
learning"
"
task_alias"
:
"
machine
_
learning"
lm_eval/tasks/mmlu/default/mmlu_management.yaml
View file @
0ffdee02
"
dataset_name"
:
"
management"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
management.
\n\
\n
"
"
group"
:
"
mmlu_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_management"
"
task_alias"
:
"
management"
lm_eval/tasks/mmlu/default/mmlu_marketing.yaml
View file @
0ffdee02
"
dataset_name"
:
"
marketing"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
marketing.
\n\
\n
"
"
group"
:
"
mmlu_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_marketing"
"
task_alias"
:
"
marketing"
lm_eval/tasks/mmlu/default/mmlu_medical_genetics.yaml
View file @
0ffdee02
"
dataset_name"
:
"
medical_genetics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
medical
\
\
genetics.
\n\n
"
"
group"
:
"
mmlu_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_medical_genetics"
"
task_alias"
:
"
medical
genetics"
"
task_alias"
:
"
medical
_
genetics"
lm_eval/tasks/mmlu/default/mmlu_miscellaneous.yaml
View file @
0ffdee02
"
dataset_name"
:
"
miscellaneous"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
miscellaneous.
\n\
\n
"
"
group"
:
"
mmlu_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_miscellaneous"
"
task_alias"
:
"
miscellaneous"
lm_eval/tasks/mmlu/default/mmlu_moral_disputes.yaml
View file @
0ffdee02
"
dataset_name"
:
"
moral_disputes"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
\
\
disputes.
\n\n
"
"
group"
:
"
mmlu_humanities"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_moral_disputes"
"
task_alias"
:
"
moral
disputes"
"
task_alias"
:
"
moral
_
disputes"
lm_eval/tasks/mmlu/default/mmlu_moral_scenarios.yaml
View file @
0ffdee02
"
dataset_name"
:
"
moral_scenarios"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
\
\
scenarios.
\n\n
"
"
group"
:
"
mmlu_humanities"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_moral_scenarios"
"
task_alias"
:
"
moral
scenarios"
"
task_alias"
:
"
moral
_
scenarios"
lm_eval/tasks/mmlu/default/mmlu_nutrition.yaml
View file @
0ffdee02
"
dataset_name"
:
"
nutrition"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
nutrition.
\n\
\n
"
"
group"
:
"
mmlu_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_nutrition"
"
task_alias"
:
"
nutrition"
lm_eval/tasks/mmlu/default/mmlu_philosophy.yaml
View file @
0ffdee02
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\
\n
"
"
group"
:
"
mmlu_humanities"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_philosophy"
"
task_alias"
:
"
philosophy"
lm_eval/tasks/mmlu/default/mmlu_prehistory.yaml
View file @
0ffdee02
"
dataset_name"
:
"
prehistory"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
prehistory.
\n\
\n
"
"
group"
:
"
mmlu_humanities"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_prehistory"
"
task_alias"
:
"
prehistory"
lm_eval/tasks/mmlu/default/mmlu_professional_accounting.yaml
View file @
0ffdee02
"
dataset_name"
:
"
professional_accounting"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
accounting.
\n\n
"
"
group"
:
"
mmlu_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_professional_accounting"
"
task_alias"
:
"
professional
accounting"
"
task_alias"
:
"
professional
_
accounting"
lm_eval/tasks/mmlu/default/mmlu_professional_law.yaml
View file @
0ffdee02
"
dataset_name"
:
"
professional_law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
law.
\n\n
"
"
group"
:
"
mmlu_humanities"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_professional_law"
"
task_alias"
:
"
professional
law"
"
task_alias"
:
"
professional
_
law"
lm_eval/tasks/mmlu/default/mmlu_professional_medicine.yaml
View file @
0ffdee02
"
dataset_name"
:
"
professional_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
medicine.
\n\n
"
"
group"
:
"
mmlu_other"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_professional_medicine"
"
task_alias"
:
"
professional
medicine"
"
task_alias"
:
"
professional
_
medicine"
lm_eval/tasks/mmlu/default/mmlu_professional_psychology.yaml
View file @
0ffdee02
"
dataset_name"
:
"
professional_psychology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
psychology.
\n\n
"
"
group"
:
"
mmlu_social_sciences"
"
group_alias"
:
"
social_sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_professional_psychology"
"
task_alias"
:
"
professional
psychology"
"
task_alias"
:
"
professional
_
psychology"
lm_eval/tasks/mmlu/default/mmlu_public_relations.yaml
View file @
0ffdee02
"
dataset_name"
:
"
public_relations"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
public
\
\
relations.
\n\n
"
"
group"
:
"
mmlu_social_sciences"
"
group_alias"
:
"
social_sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_public_relations"
"
task_alias"
:
"
public
relations"
"
task_alias"
:
"
public
_
relations"
lm_eval/tasks/mmlu/default/mmlu_security_studies.yaml
View file @
0ffdee02
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
\
\
studies.
\n\n
"
"
group"
:
"
mmlu_social_sciences"
"
group_alias"
:
"
social_sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_security_studies"
"
task_alias"
:
"
security
studies"
"
task_alias"
:
"
security
_
studies"
lm_eval/tasks/mmlu/default/mmlu_sociology.yaml
View file @
0ffdee02
"
dataset_name"
:
"
sociology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\
\n
"
"
group"
:
"
mmlu_social_sciences"
"
group_alias"
:
"
social_sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_sociology"
"
task_alias"
:
"
sociology"
lm_eval/tasks/mmlu/default/mmlu_us_foreign_policy.yaml
View file @
0ffdee02
"
dataset_name"
:
"
us_foreign_policy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
us
\
\
foreign
policy.
\n\n
"
"
group"
:
"
mmlu_social_sciences"
"
group_alias"
:
"
social_sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_us_foreign_policy"
"
task_alias"
:
"
us
foreign
policy"
"
task_alias"
:
"
us
_
foreign
_
policy"
Prev
1
2
3
4
Next
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment