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
7d6ec4d9
Commit
7d6ec4d9
authored
Aug 04, 2025
by
Baber
Browse files
Merge branch 'main' into metrics
# Conflicts: # lm_eval/__init__.py # pyproject.toml
parents
1020c46e
d021bf84
Changes
74
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
40 additions
and
40 deletions
+40
-40
lm_eval/tasks/mmlu/continuation/mmlu_college_physics.yaml
lm_eval/tasks/mmlu/continuation/mmlu_college_physics.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_computer_security.yaml
lm_eval/tasks/mmlu/continuation/mmlu_computer_security.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_conceptual_physics.yaml
lm_eval/tasks/mmlu/continuation/mmlu_conceptual_physics.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_econometrics.yaml
lm_eval/tasks/mmlu/continuation/mmlu_econometrics.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_electrical_engineering.yaml
.../tasks/mmlu/continuation/mmlu_electrical_engineering.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_elementary_mathematics.yaml
.../tasks/mmlu/continuation/mmlu_elementary_mathematics.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_formal_logic.yaml
lm_eval/tasks/mmlu/continuation/mmlu_formal_logic.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_global_facts.yaml
lm_eval/tasks/mmlu/continuation/mmlu_global_facts.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_biology.yaml
...val/tasks/mmlu/continuation/mmlu_high_school_biology.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_chemistry.yaml
...l/tasks/mmlu/continuation/mmlu_high_school_chemistry.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_computer_science.yaml
.../mmlu/continuation/mmlu_high_school_computer_science.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_european_history.yaml
.../mmlu/continuation/mmlu_high_school_european_history.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_geography.yaml
...l/tasks/mmlu/continuation/mmlu_high_school_geography.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_government_and_politics.yaml
...ontinuation/mmlu_high_school_government_and_politics.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_macroeconomics.yaml
...ks/mmlu/continuation/mmlu_high_school_macroeconomics.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_mathematics.yaml
...tasks/mmlu/continuation/mmlu_high_school_mathematics.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_microeconomics.yaml
...ks/mmlu/continuation/mmlu_high_school_microeconomics.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_physics.yaml
...val/tasks/mmlu/continuation/mmlu_high_school_physics.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_psychology.yaml
.../tasks/mmlu/continuation/mmlu_high_school_psychology.yaml
+2
-2
lm_eval/tasks/mmlu/continuation/mmlu_high_school_statistics.yaml
.../tasks/mmlu/continuation/mmlu_high_school_statistics.yaml
+2
-2
No files found.
lm_eval/tasks/mmlu/continuation/mmlu_college_physics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
college_physics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
college
\
\
physics.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_co
ntinuation_co
llege_physics"
"
task"
:
"
mmlu_college_physics
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_computer_security.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
computer_security"
"
description"
:
"
The
following
are
questions
(with
answers)
about
computer
\
\
security.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
computer_security"
"
task"
:
"
mmlu_computer_security
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_conceptual_physics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
conceptual_physics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
conceptual
\
\
physics.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
conceptual_physics"
"
task"
:
"
mmlu_conceptual_physics
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_econometrics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
econometrics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
econometrics.
\n\
\n
"
"
tag"
:
"
mmlu_
continuation_
social_sciences"
"
tag"
:
"
mmlu_social_sciences
_continuation
"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_econometrics
"
"
task"
:
"
mmlu_
econometrics_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_electrical_engineering.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
electrical_engineering"
"
description"
:
"
The
following
are
questions
(with
answers)
about
electrical
\
\
engineering.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
electrical_engineering"
"
task"
:
"
mmlu_electrical_engineering
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_elementary_mathematics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
elementary_mathematics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
elementary
\
\
mathematics.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
elementary_mathematics"
"
task"
:
"
mmlu_elementary_mathematics
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_formal_logic.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
formal_logic"
"
description"
:
"
The
following
are
questions
(with
answers)
about
formal
\
\
logic.
\n\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_formal_logic
"
"
task"
:
"
mmlu_
formal_logic_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_global_facts.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
global_facts"
"
description"
:
"
The
following
are
questions
(with
answers)
about
global
\
\
facts.
\n\n
"
"
tag"
:
"
mmlu_continuation
_other
"
"
tag"
:
"
mmlu_
other_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_global_facts
"
"
task"
:
"
mmlu_
global_facts_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_biology.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_biology"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
biology.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_biology"
"
task"
:
"
mmlu_high_school_biology
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_chemistry.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_chemistry"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
chemistry.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_chemistry"
"
task"
:
"
mmlu_high_school_chemistry
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_computer_science.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_computer_science"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
computer
science.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_computer_science"
"
task"
:
"
mmlu_high_school_computer_science
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_european_history.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_european_history"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
european
history.
\n\n
"
"
tag"
:
"
mmlu_continuation
_humanities
"
"
tag"
:
"
mmlu_
humanities_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_european_history"
"
task"
:
"
mmlu_high_school_european_history
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_geography.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_geography"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
geography.
\n\n
"
"
tag"
:
"
mmlu_
continuation_
social_sciences"
"
tag"
:
"
mmlu_social_sciences
_continuation
"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_geography"
"
task"
:
"
mmlu_high_school_geography
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_government_and_politics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_government_and_politics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
government
and
politics.
\n\n
"
"
tag"
:
"
mmlu_
continuation_
social_sciences"
"
tag"
:
"
mmlu_social_sciences
_continuation
"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_government_and_politics"
"
task"
:
"
mmlu_high_school_government_and_politics
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_macroeconomics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_macroeconomics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
macroeconomics.
\n\n
"
"
tag"
:
"
mmlu_
continuation_
social_sciences"
"
tag"
:
"
mmlu_social_sciences
_continuation
"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_macroeconomics"
"
task"
:
"
mmlu_high_school_macroeconomics
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_mathematics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_mathematics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
mathematics.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_mathematics"
"
task"
:
"
mmlu_high_school_mathematics
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_microeconomics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_microeconomics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
microeconomics.
\n\n
"
"
tag"
:
"
mmlu_
continuation_
social_sciences"
"
tag"
:
"
mmlu_social_sciences
_continuation
"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_microeconomics"
"
task"
:
"
mmlu_high_school_microeconomics
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_physics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_physics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
physics.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_physics"
"
task"
:
"
mmlu_high_school_physics
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_psychology.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_psychology"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
psychology.
\n\n
"
"
tag"
:
"
mmlu_
continuation_
social_sciences"
"
tag"
:
"
mmlu_social_sciences
_continuation
"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_psychology"
"
task"
:
"
mmlu_high_school_psychology
_continuation
"
lm_eval/tasks/mmlu/continuation/mmlu_high_school_statistics.yaml
View file @
7d6ec4d9
"
dataset_name"
:
"
high_school_statistics"
"
description"
:
"
The
following
are
questions
(with
answers)
about
high
\
\
school
statistics.
\n\n
"
"
tag"
:
"
mmlu_continuation
_stem
"
"
tag"
:
"
mmlu_
stem_
continuation"
"
include"
:
"
_continuation_template_yaml"
"
task"
:
"
mmlu_
continuation_
high_school_statistics"
"
task"
:
"
mmlu_high_school_statistics
_continuation
"
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