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
22b95671
Commit
22b95671
authored
Jul 02, 2024
by
haileyschoelkopf
Browse files
switch mmlu variants over to using
parent
c1d9e625
Changes
344
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/generative/mmlu_professional_accounting.yaml
.../flan_n_shot/generative/mmlu_professional_accounting.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_professional_law.yaml
...ks/mmlu/flan_n_shot/generative/mmlu_professional_law.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_professional_medicine.yaml
...lu/flan_n_shot/generative/mmlu_professional_medicine.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_professional_psychology.yaml
.../flan_n_shot/generative/mmlu_professional_psychology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_public_relations.yaml
...ks/mmlu/flan_n_shot/generative/mmlu_public_relations.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_security_studies.yaml
...ks/mmlu/flan_n_shot/generative/mmlu_security_studies.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_sociology.yaml
...val/tasks/mmlu/flan_n_shot/generative/mmlu_sociology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_us_foreign_policy.yaml
...s/mmlu/flan_n_shot/generative/mmlu_us_foreign_policy.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_virology.yaml
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_virology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_world_religions.yaml
...sks/mmlu/flan_n_shot/generative/mmlu_world_religions.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_abstract_algebra.yaml
...mmlu/flan_n_shot/loglikelihood/mmlu_abstract_algebra.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_anatomy.yaml
...al/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_anatomy.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_astronomy.yaml
.../tasks/mmlu/flan_n_shot/loglikelihood/mmlu_astronomy.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_business_ethics.yaml
.../mmlu/flan_n_shot/loglikelihood/mmlu_business_ethics.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_clinical_knowledge.yaml
...lu/flan_n_shot/loglikelihood/mmlu_clinical_knowledge.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_biology.yaml
.../mmlu/flan_n_shot/loglikelihood/mmlu_college_biology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_chemistry.yaml
...mlu/flan_n_shot/loglikelihood/mmlu_college_chemistry.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_computer_science.yaml
...n_n_shot/loglikelihood/mmlu_college_computer_science.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_mathematics.yaml
...u/flan_n_shot/loglikelihood/mmlu_college_mathematics.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_medicine.yaml
...mmlu/flan_n_shot/loglikelihood/mmlu_college_medicine.yaml
+1
-1
No files found.
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_professional_accounting.yaml
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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_abstract_algebra.yaml
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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
View file @
22b95671
"
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"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_chemistry.yaml
View file @
22b95671
"
dataset_name"
:
"
college_chemistry"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
chemistry.
\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_chemistry"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_computer_science.yaml
View file @
22b95671
"
dataset_name"
:
"
college_computer_science"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
computer
science.
\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_computer_science"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_mathematics.yaml
View file @
22b95671
"
dataset_name"
:
"
college_mathematics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
mathematics.
\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_mathematics"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_medicine.yaml
View file @
22b95671
"
dataset_name"
:
"
college_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
medicine.
\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_college_medicine"
Prev
1
…
8
9
10
11
12
13
14
15
16
…
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