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
e200c24e
Commit
e200c24e
authored
Jul 03, 2024
by
lintangsutawika
Browse files
update mmlu
parent
43765669
Changes
342
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
20 additions
and
20 deletions
+20
-20
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_security_studies.yaml
...mmlu/flan_n_shot/loglikelihood/mmlu_security_studies.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_sociology.yaml
.../tasks/mmlu/flan_n_shot/loglikelihood/mmlu_sociology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_us_foreign_policy.yaml
...mlu/flan_n_shot/loglikelihood/mmlu_us_foreign_policy.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_virology.yaml
...l/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_virology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_world_religions.yaml
.../mmlu/flan_n_shot/loglikelihood/mmlu_world_religions.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_abstract_algebra.yaml
lm_eval/tasks/mmlu/generative/mmlu_abstract_algebra.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_anatomy.yaml
lm_eval/tasks/mmlu/generative/mmlu_anatomy.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_astronomy.yaml
lm_eval/tasks/mmlu/generative/mmlu_astronomy.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_business_ethics.yaml
lm_eval/tasks/mmlu/generative/mmlu_business_ethics.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_clinical_knowledge.yaml
lm_eval/tasks/mmlu/generative/mmlu_clinical_knowledge.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_college_biology.yaml
lm_eval/tasks/mmlu/generative/mmlu_college_biology.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_college_chemistry.yaml
lm_eval/tasks/mmlu/generative/mmlu_college_chemistry.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_college_computer_science.yaml
.../tasks/mmlu/generative/mmlu_college_computer_science.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_college_mathematics.yaml
lm_eval/tasks/mmlu/generative/mmlu_college_mathematics.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_college_medicine.yaml
lm_eval/tasks/mmlu/generative/mmlu_college_medicine.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_college_physics.yaml
lm_eval/tasks/mmlu/generative/mmlu_college_physics.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_computer_security.yaml
lm_eval/tasks/mmlu/generative/mmlu_computer_security.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_conceptual_physics.yaml
lm_eval/tasks/mmlu/generative/mmlu_conceptual_physics.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_econometrics.yaml
lm_eval/tasks/mmlu/generative/mmlu_econometrics.yaml
+1
-1
lm_eval/tasks/mmlu/generative/mmlu_electrical_engineering.yaml
...al/tasks/mmlu/generative/mmlu_electrical_engineering.yaml
+1
-1
No files found.
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_security_studies.yaml
View file @
e200c24e
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
\
\
studies.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_social_sciences"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_social_sciences"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_security_studies"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_sociology.yaml
View file @
e200c24e
"
dataset_name"
:
"
sociology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\
\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_social_sciences"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_social_sciences"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_sociology"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_us_foreign_policy.yaml
View file @
e200c24e
"
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_loglikelihood_social_sciences"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_social_sciences"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_us_foreign_policy"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_virology.yaml
View file @
e200c24e
"
dataset_name"
:
"
virology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\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_virology"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_world_religions.yaml
View file @
e200c24e
"
dataset_name"
:
"
world_religions"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
\
\
religions.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_humanities"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_humanities"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_world_religions"
lm_eval/tasks/mmlu/generative/mmlu_abstract_algebra.yaml
View file @
e200c24e
"
dataset_name"
:
"
abstract_algebra"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
\
\
algebra.
\n\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_abstract_algebra_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_anatomy.yaml
View file @
e200c24e
"
dataset_name"
:
"
anatomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\
\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_anatomy_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_astronomy.yaml
View file @
e200c24e
"
dataset_name"
:
"
astronomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\
\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_astronomy_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_business_ethics.yaml
View file @
e200c24e
"
dataset_name"
:
"
business_ethics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
\
\
ethics.
\n\n
"
"
group
"
:
"
mmlu_other_generative"
"
tag
"
:
"
mmlu_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_business_ethics_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_clinical_knowledge.yaml
View file @
e200c24e
"
dataset_name"
:
"
clinical_knowledge"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
clinical
\
\
knowledge.
\n\n
"
"
group
"
:
"
mmlu_other_generative"
"
tag
"
:
"
mmlu_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_clinical_knowledge_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_college_biology.yaml
View file @
e200c24e
"
dataset_name"
:
"
college_biology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
biology.
\n\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_college_biology_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_college_chemistry.yaml
View file @
e200c24e
"
dataset_name"
:
"
college_chemistry"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
chemistry.
\n\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_college_chemistry_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_college_computer_science.yaml
View file @
e200c24e
"
dataset_name"
:
"
college_computer_science"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
computer
science.
\n\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_college_computer_science_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_college_mathematics.yaml
View file @
e200c24e
"
dataset_name"
:
"
college_mathematics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
mathematics.
\n\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_college_mathematics_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_college_medicine.yaml
View file @
e200c24e
"
dataset_name"
:
"
college_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
medicine.
\n\n
"
"
group
"
:
"
mmlu_other_generative"
"
tag
"
:
"
mmlu_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_college_medicine_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_college_physics.yaml
View file @
e200c24e
"
dataset_name"
:
"
college_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
physics.
\n\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_college_physics_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_computer_security.yaml
View file @
e200c24e
"
dataset_name"
:
"
computer_security"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer
\
\
security.
\n\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_computer_security_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_conceptual_physics.yaml
View file @
e200c24e
"
dataset_name"
:
"
conceptual_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
conceptual
\
\
physics.
\n\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_conceptual_physics_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_econometrics.yaml
View file @
e200c24e
"
dataset_name"
:
"
econometrics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
econometrics.
\n\
\n
"
"
group
"
:
"
mmlu_social_sciences_generative"
"
tag
"
:
"
mmlu_social_sciences_generative"
"
group_alias"
:
"
social_sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_econometrics_generative"
...
...
lm_eval/tasks/mmlu/generative/mmlu_electrical_engineering.yaml
View file @
e200c24e
"
dataset_name"
:
"
electrical_engineering"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
electrical
\
\
engineering.
\n\n
"
"
group
"
:
"
mmlu_stem_generative"
"
tag
"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_electrical_engineering_generative"
...
...
Prev
1
…
11
12
13
14
15
16
17
18
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