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
574e565a
Unverified
Commit
574e565a
authored
Nov 10, 2023
by
Lintang Sutawika
Committed by
GitHub
Nov 10, 2023
Browse files
Merge branch 'big-refactor' into verbosity-rework
parents
73f3029c
b7a4ea06
Changes
498
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
81 additions
and
65 deletions
+81
-65
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_psychology.yaml
.../mmlu/flan_cot_zeroshot/mmlu_professional_psychology.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_public_relations.yaml
...l/tasks/mmlu/flan_cot_zeroshot/mmlu_public_relations.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_security_studies.yaml
...l/tasks/mmlu/flan_cot_zeroshot/mmlu_security_studies.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_sociology.yaml
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_sociology.yaml
+6
-7
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_us_foreign_policy.yaml
.../tasks/mmlu/flan_cot_zeroshot/mmlu_us_foreign_policy.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_virology.yaml
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_virology.yaml
+6
-7
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_world_religions.yaml
...al/tasks/mmlu/flan_cot_zeroshot/mmlu_world_religions.yaml
+6
-8
lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu.yaml
lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu.yaml
+6
-0
lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu_flan_generative_template_yaml
...lan_n_shot/generative/_mmlu_flan_generative_template_yaml
+0
-0
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_abstract_algebra.yaml
...ks/mmlu/flan_n_shot/generative/mmlu_abstract_algebra.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_anatomy.yaml
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_anatomy.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_astronomy.yaml
...val/tasks/mmlu/flan_n_shot/generative/mmlu_astronomy.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_business_ethics.yaml
...sks/mmlu/flan_n_shot/generative/mmlu_business_ethics.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_clinical_knowledge.yaml
.../mmlu/flan_n_shot/generative/mmlu_clinical_knowledge.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_college_biology.yaml
...sks/mmlu/flan_n_shot/generative/mmlu_college_biology.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_college_chemistry.yaml
...s/mmlu/flan_n_shot/generative/mmlu_college_chemistry.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_college_computer_science.yaml
...flan_n_shot/generative/mmlu_college_computer_science.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_college_mathematics.yaml
...mmlu/flan_n_shot/generative/mmlu_college_mathematics.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_college_medicine.yaml
...ks/mmlu/flan_n_shot/generative/mmlu_college_medicine.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_college_physics.yaml
...sks/mmlu/flan_n_shot/generative/mmlu_college_physics.yaml
+3
-1
No files found.
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_psychology.yaml
View file @
574e565a
dataset_name
:
professional_psychology
"
dataset_name"
:
"
professional_psychology"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
professional
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
psychology.
\
psychology.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_professional_psychology"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_professional_psychology
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_public_relations.yaml
View file @
574e565a
dataset_name
:
public_relations
"
dataset_name"
:
"
public_relations"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
public
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
public
\
relations.
\
relations.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_public_relations"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_public_relations
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_security_studies.yaml
View file @
574e565a
dataset_name
:
security_studies
"
dataset_name"
:
"
security_studies"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
security
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
\
studies.
\
studies.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_security_studies"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_security_studies
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_sociology.yaml
View file @
574e565a
dataset_name
:
sociology
"
dataset_name"
:
"
sociology"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\
\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
'
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
include
:
_mmlu_flan_generative_template_yaml
"
task"
:
"
mmlu_flan_cot_zeroshot_sociology"
task
:
mmlu_flan_cot_zeroshot_sociology
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_us_foreign_policy.yaml
View file @
574e565a
dataset_name
:
us_foreign_policy
"
dataset_name"
:
"
us_foreign_policy"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
us
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
us
\
foreign
policy.
\
foreign
policy.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_us_foreign_policy"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_us_foreign_policy
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_virology.yaml
View file @
574e565a
dataset_name
:
virology
"
dataset_name"
:
"
virology"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\n\
\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_other"
'
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
include
:
_mmlu_flan_generative_template_yaml
"
task"
:
"
mmlu_flan_cot_zeroshot_virology"
task
:
mmlu_flan_cot_zeroshot_virology
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_world_religions.yaml
View file @
574e565a
dataset_name
:
world_religions
"
dataset_name"
:
"
world_religions"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
world
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
\
religions.
\
religions.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_world_religions"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_world_religions
lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu.yaml
0 → 100644
View file @
574e565a
group
:
mmlu_flan_n_shot_generative
task
:
-
mmlu_flan_n_shot_generative_stem
-
mmlu_flan_n_shot_generative_other
-
mmlu_flan_n_shot_generative_social_sciences
-
mmlu_flan_n_shot_generative_humanities
lm_eval/tasks/mmlu/flan_n_shot/_mmlu_flan_generative_template_yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
_mmlu_flan_generative_template_yaml
View file @
574e565a
File moved
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_abstract_algebra.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_abstract_algebra.yaml
View file @
574e565a
"
dataset_name"
:
"
abstract_algebra"
"
dataset_name"
:
"
abstract_algebra"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
algebra.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
\
\
algebra.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_abstract_algebra"
"
task"
:
"
mmlu_flan_n_shot_generative_abstract_algebra"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_anatomy.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_anatomy.yaml
View file @
574e565a
"
dataset_name"
:
"
anatomy"
"
dataset_name"
:
"
anatomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_anatomy"
"
task"
:
"
mmlu_flan_n_shot_generative_anatomy"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_astronomy.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_astronomy.yaml
View file @
574e565a
"
dataset_name"
:
"
astronomy"
"
dataset_name"
:
"
astronomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_astronomy"
"
task"
:
"
mmlu_flan_n_shot_generative_astronomy"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_business_ethics.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_business_ethics.yaml
View file @
574e565a
"
dataset_name"
:
"
business_ethics"
"
dataset_name"
:
"
business_ethics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
ethics.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
\
\
ethics.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_business_ethics"
"
task"
:
"
mmlu_flan_n_shot_generative_business_ethics"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_clinical_knowledge.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_clinical_knowledge.yaml
View file @
574e565a
"
dataset_name"
:
"
clinical_knowledge"
"
dataset_name"
:
"
clinical_knowledge"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
clinical
knowledge.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
clinical
\
\
knowledge.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_clinical_knowledge"
"
task"
:
"
mmlu_flan_n_shot_generative_clinical_knowledge"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_college_biology.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_college_biology.yaml
View file @
574e565a
"
dataset_name"
:
"
college_biology"
"
dataset_name"
:
"
college_biology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
biology.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
biology.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_college_biology"
"
task"
:
"
mmlu_flan_n_shot_generative_college_biology"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_college_chemistry.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_college_chemistry.yaml
View file @
574e565a
"
dataset_name"
:
"
college_chemistry"
"
dataset_name"
:
"
college_chemistry"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
chemistry.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
chemistry.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_college_chemistry"
"
task"
:
"
mmlu_flan_n_shot_generative_college_chemistry"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_college_computer_science.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_college_computer_science.yaml
View file @
574e565a
"
dataset_name"
:
"
college_computer_science"
"
dataset_name"
:
"
college_computer_science"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
computer
science.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
computer
science.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_college_computer_science"
"
task"
:
"
mmlu_flan_n_shot_generative_college_computer_science"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_college_mathematics.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_college_mathematics.yaml
View file @
574e565a
"
dataset_name"
:
"
college_mathematics"
"
dataset_name"
:
"
college_mathematics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
mathematics.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
mathematics.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_college_mathematics"
"
task"
:
"
mmlu_flan_n_shot_generative_college_mathematics"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_college_medicine.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_college_medicine.yaml
View file @
574e565a
"
dataset_name"
:
"
college_medicine"
"
dataset_name"
:
"
college_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
medicine.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
medicine.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_college_medicine"
"
task"
:
"
mmlu_flan_n_shot_generative_college_medicine"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_college_physics.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_college_physics.yaml
View file @
574e565a
"
dataset_name"
:
"
college_physics"
"
dataset_name"
:
"
college_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
physics.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
physics.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_college_physics"
"
task"
:
"
mmlu_flan_n_shot_generative_college_physics"
Prev
1
…
6
7
8
9
10
11
12
13
14
…
25
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