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
120 additions
and
159 deletions
+120
-159
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_college_physics.yaml
...al/tasks/mmlu/flan_cot_zeroshot/mmlu_college_physics.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_computer_security.yaml
.../tasks/mmlu/flan_cot_zeroshot/mmlu_computer_security.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_conceptual_physics.yaml
...tasks/mmlu/flan_cot_zeroshot/mmlu_conceptual_physics.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_econometrics.yaml
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_econometrics.yaml
+6
-7
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_electrical_engineering.yaml
...s/mmlu/flan_cot_zeroshot/mmlu_electrical_engineering.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_elementary_mathematics.yaml
...s/mmlu/flan_cot_zeroshot/mmlu_elementary_mathematics.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_formal_logic.yaml
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_formal_logic.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_global_facts.yaml
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_global_facts.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_biology.yaml
...asks/mmlu/flan_cot_zeroshot/mmlu_high_school_biology.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_chemistry.yaml
...ks/mmlu/flan_cot_zeroshot/mmlu_high_school_chemistry.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_computer_science.yaml
.../flan_cot_zeroshot/mmlu_high_school_computer_science.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_european_history.yaml
.../flan_cot_zeroshot/mmlu_high_school_european_history.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_geography.yaml
...ks/mmlu/flan_cot_zeroshot/mmlu_high_school_geography.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_government_and_politics.yaml
...ot_zeroshot/mmlu_high_school_government_and_politics.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_macroeconomics.yaml
...lu/flan_cot_zeroshot/mmlu_high_school_macroeconomics.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_mathematics.yaml
.../mmlu/flan_cot_zeroshot/mmlu_high_school_mathematics.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_microeconomics.yaml
...lu/flan_cot_zeroshot/mmlu_high_school_microeconomics.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_physics.yaml
...asks/mmlu/flan_cot_zeroshot/mmlu_high_school_physics.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_psychology.yaml
...s/mmlu/flan_cot_zeroshot/mmlu_high_school_psychology.yaml
+6
-8
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_statistics.yaml
...s/mmlu/flan_cot_zeroshot/mmlu_high_school_statistics.yaml
+6
-8
No files found.
lm_eval/tasks/mmlu/flan_cot_zeroshot/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
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
physics.
\
physics.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_college_physics"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_college_physics
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_computer_security.yaml
View file @
574e565a
dataset_name
:
computer_security
"
dataset_name"
:
"
computer_security"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
computer
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer
\
security.
\
security.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_computer_security"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_computer_security
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_conceptual_physics.yaml
View file @
574e565a
dataset_name
:
conceptual_physics
"
dataset_name"
:
"
conceptual_physics"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
conceptual
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
conceptual
\
physics.
\
physics.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_conceptual_physics"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_conceptual_physics
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_econometrics.yaml
View file @
574e565a
dataset_name
:
econometrics
"
dataset_name"
:
"
econometrics"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
econometrics.
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
econometrics.
\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_econometrics"
task
:
mmlu_flan_cot_zeroshot_econometrics
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_electrical_engineering.yaml
View file @
574e565a
dataset_name
:
electrical_engineering
"
dataset_name"
:
"
electrical_engineering"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
electrical
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
electrical
\
engineering.
\
engineering.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_electrical_engineering"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_electrical_engineering
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_elementary_mathematics.yaml
View file @
574e565a
dataset_name
:
elementary_mathematics
"
dataset_name"
:
"
elementary_mathematics"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
elementary
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
elementary
\
mathematics.
\
mathematics.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_elementary_mathematics"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_elementary_mathematics
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_formal_logic.yaml
View file @
574e565a
dataset_name
:
formal_logic
"
dataset_name"
:
"
formal_logic"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
formal
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
formal
\
logic.
\
logic.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_formal_logic"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_formal_logic
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_global_facts.yaml
View file @
574e565a
dataset_name
:
global_facts
"
dataset_name"
:
"
global_facts"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
global
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
global
\
facts.
\
facts.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_other"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_global_facts"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_global_facts
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_biology.yaml
View file @
574e565a
dataset_name
:
high_school_biology
"
dataset_name"
:
"
high_school_biology"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
biology.
\
school
biology.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_biology"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_biology
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_chemistry.yaml
View file @
574e565a
dataset_name
:
high_school_chemistry
"
dataset_name"
:
"
high_school_chemistry"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
chemistry.
\
school
chemistry.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_chemistry"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_chemistry
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_computer_science.yaml
View file @
574e565a
dataset_name
:
high_school_computer_science
"
dataset_name"
:
"
high_school_computer_science"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
computer
science.
\
school
computer
science.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_computer_science"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_computer_science
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_european_history.yaml
View file @
574e565a
dataset_name
:
high_school_european_history
"
dataset_name"
:
"
high_school_european_history"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
european
history.
\
school
european
history.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_european_history"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_european_history
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_geography.yaml
View file @
574e565a
dataset_name
:
high_school_geography
"
dataset_name"
:
"
high_school_geography"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
geography.
\
school
geography.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_geography"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_geography
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_government_and_politics.yaml
View file @
574e565a
dataset_name
:
high_school_government_and_politics
"
dataset_name"
:
"
high_school_government_and_politics"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
government
and
politics.
\
school
government
and
politics.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_government_and_politics"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_government_and_politics
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_macroeconomics.yaml
View file @
574e565a
dataset_name
:
high_school_macroeconomics
"
dataset_name"
:
"
high_school_macroeconomics"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
macroeconomics.
\
school
macroeconomics.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_macroeconomics"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_macroeconomics
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_mathematics.yaml
View file @
574e565a
dataset_name
:
high_school_mathematics
"
dataset_name"
:
"
high_school_mathematics"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
mathematics.
\
school
mathematics.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_mathematics"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_mathematics
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_microeconomics.yaml
View file @
574e565a
dataset_name
:
high_school_microeconomics
"
dataset_name"
:
"
high_school_microeconomics"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
microeconomics.
\
school
microeconomics.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_microeconomics"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_microeconomics
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_physics.yaml
View file @
574e565a
dataset_name
:
high_school_physics
"
dataset_name"
:
"
high_school_physics"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
physics.
\
school
physics.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_physics"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_physics
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_psychology.yaml
View file @
574e565a
dataset_name
:
high_school_psychology
"
dataset_name"
:
"
high_school_psychology"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
psychology.
\
school
psychology.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_psychology"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_psychology
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_high_school_statistics.yaml
View file @
574e565a
dataset_name
:
high_school_statistics
"
dataset_name"
:
"
high_school_statistics"
description
:
'
The
following
are
multiple
choice
questions
(with
answers)
about
high
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
school
statistics.
\
school
statistics.
\n\n
"
"
group"
:
"
mmlu_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
'
"
task"
:
"
mmlu_flan_cot_zeroshot_high_school_statistics"
include
:
_mmlu_flan_generative_template_yaml
task
:
mmlu_flan_cot_zeroshot_high_school_statistics
Prev
1
…
4
5
6
7
8
9
10
11
12
…
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