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
cd8642e7
"backend/vscode:/vscode.git/clone" did not exist on "500f61b7ee9abc528be14d91dad959c59b030765"
Commit
cd8642e7
authored
Jul 26, 2024
by
Yu Shi Jie
Browse files
mmlu-pro: fixed yaml formatting
parent
cd0983b8
Changes
40
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
20 additions
and
31 deletions
+20
-31
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_computer_science.yaml
...mmlu_pro/flan_cot_zeroshot/mmlu_pro_computer_science.yaml
+1
-1
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_economics.yaml
.../tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_economics.yaml
+1
-1
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_engineering.yaml
...asks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_engineering.yaml
+1
-1
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_health.yaml
...val/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_health.yaml
+1
-1
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_history.yaml
...al/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_history.yaml
+1
-1
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_law.yaml
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_law.yaml
+1
-1
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_miscellaneous.yaml
...ks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_miscellaneous.yaml
+1
-1
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_philosophy.yaml
...tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_philosophy.yaml
+1
-1
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_physics.yaml
...al/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_physics.yaml
+1
-1
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_business.yaml
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_business.yaml
+1
-2
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_computer_science.yaml
.../tasks/mmlu_pro/generative/mmlu_pro_computer_science.yaml
+1
-2
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_economics.yaml
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_economics.yaml
+1
-2
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_engineering.yaml
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_engineering.yaml
+1
-2
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_health.yaml
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_health.yaml
+1
-2
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_history.yaml
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_history.yaml
+1
-2
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_law.yaml
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_law.yaml
+1
-2
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_math.yaml
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_math.yaml
+1
-2
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_miscellaneous.yaml
...val/tasks/mmlu_pro/generative/mmlu_pro_miscellaneous.yaml
+1
-2
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_philosophy.yaml
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_philosophy.yaml
+1
-2
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_physics.yaml
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_physics.yaml
+1
-2
No files found.
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_computer_science.yaml
View file @
cd8642e7
"
dataset_name"
:
"
computer_science"
"
dataset_name"
:
"
computer_science"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer_science.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer_science.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
tag
"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_computer_science"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_computer_science"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_economics.yaml
View file @
cd8642e7
"
dataset_name"
:
"
economics"
"
dataset_name"
:
"
economics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
economics.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
economics.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_pro_flan_cot_zeroshot_social_sciences"
"
tag
"
:
"
mmlu_pro_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_economics"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_economics"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_engineering.yaml
View file @
cd8642e7
"
dataset_name"
:
"
engineering"
"
dataset_name"
:
"
engineering"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
engineering.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
engineering.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
tag
"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_engineering"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_engineering"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_health.yaml
View file @
cd8642e7
"
dataset_name"
:
"
health"
"
dataset_name"
:
"
health"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
health.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
health.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_pro_flan_cot_zeroshot_other"
"
tag
"
:
"
mmlu_pro_flan_cot_zeroshot_other"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_health"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_health"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_history.yaml
View file @
cd8642e7
"
dataset_name"
:
"
history"
"
dataset_name"
:
"
history"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
history.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
history.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_pro_flan_cot_zeroshot_humanities"
"
tag
"
:
"
mmlu_pro_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_history"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_history"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_law.yaml
View file @
cd8642e7
"
dataset_name"
:
"
law"
"
dataset_name"
:
"
law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
law.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
law.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_pro_flan_cot_zeroshot_humanities"
"
tag
"
:
"
mmlu_pro_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_law"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_law"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_miscellaneous.yaml
View file @
cd8642e7
"
dataset_name"
:
"
other"
"
dataset_name"
:
"
other"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
other.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
other.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_pro_flan_cot_zeroshot_other"
"
tag
"
:
"
mmlu_pro_flan_cot_zeroshot_other"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_miscellaneous"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_miscellaneous"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_philosophy.yaml
View file @
cd8642e7
"
dataset_name"
:
"
philosophy"
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_pro_flan_cot_zeroshot_humanities"
"
tag
"
:
"
mmlu_pro_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_philosophy"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_philosophy"
lm_eval/tasks/mmlu_pro/flan_cot_zeroshot/mmlu_pro_physics.yaml
View file @
cd8642e7
"
dataset_name"
:
"
physics"
"
dataset_name"
:
"
physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
physics.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
physics.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
tag
"
:
"
mmlu_pro_flan_cot_zeroshot_stem"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_pro_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_physics"
"
task"
:
"
mmlu_pro_flan_cot_zeroshot_physics"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_business.yaml
View file @
cd8642e7
"
dataset_name"
:
"
business"
"
dataset_name"
:
"
business"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_other_generative"
"
tag"
:
"
mmlu_pro_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_business_generative"
"
task"
:
"
mmlu_pro_business_generative"
"
task_alias"
:
"
business"
"
task_alias"
:
"
business"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_computer_science.yaml
View file @
cd8642e7
"
dataset_name"
:
"
computer_science"
"
dataset_name"
:
"
computer_science"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer_science.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer_science.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_stem_generative"
"
tag"
:
"
mmlu_pro_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_computer_science_generative"
"
task"
:
"
mmlu_pro_computer_science_generative"
"
task_alias"
:
"
computer_science"
"
task_alias"
:
"
computer_science"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_economics.yaml
View file @
cd8642e7
"
dataset_name"
:
"
economics"
"
dataset_name"
:
"
economics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
economics.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
economics.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_social_sciences_generative"
"
tag"
:
"
mmlu_pro_social_sciences_generative"
"
group_alias"
:
"
social_sciences"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_economics_generative"
"
task"
:
"
mmlu_pro_economics_generative"
"
task_alias"
:
"
economics"
"
task_alias"
:
"
economics"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_engineering.yaml
View file @
cd8642e7
"
dataset_name"
:
"
engineering"
"
dataset_name"
:
"
engineering"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
engineering.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
engineering.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_stem_generative"
"
tag"
:
"
mmlu_pro_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_engineering_generative"
"
task"
:
"
mmlu_pro_engineering_generative"
"
task_alias"
:
"
engineering"
"
task_alias"
:
"
engineering"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_health.yaml
View file @
cd8642e7
"
dataset_name"
:
"
health"
"
dataset_name"
:
"
health"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
health.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
health.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_other_generative"
"
tag"
:
"
mmlu_pro_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_health_generative"
"
task"
:
"
mmlu_pro_health_generative"
"
task_alias"
:
"
health"
"
task_alias"
:
"
health"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_history.yaml
View file @
cd8642e7
"
dataset_name"
:
"
history"
"
dataset_name"
:
"
history"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
history.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
history.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_humanities_generative"
"
tag"
:
"
mmlu_pro_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_history_generative"
"
task"
:
"
mmlu_pro_history_generative"
"
task_alias"
:
"
history"
"
task_alias"
:
"
history"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_law.yaml
View file @
cd8642e7
"
dataset_name"
:
"
law"
"
dataset_name"
:
"
law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
law.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
law.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_humanities_generative"
"
tag"
:
"
mmlu_pro_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_law_generative"
"
task"
:
"
mmlu_pro_law_generative"
"
task_alias"
:
"
law"
"
task_alias"
:
"
law"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_math.yaml
View file @
cd8642e7
"
dataset_name"
:
"
math"
"
dataset_name"
:
"
math"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
math.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
math.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_stem_generative"
"
tag"
:
"
mmlu_pro_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_math_generative"
"
task"
:
"
mmlu_pro_math_generative"
"
task_alias"
:
"
math"
"
task_alias"
:
"
math"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_miscellaneous.yaml
View file @
cd8642e7
"
dataset_name"
:
"
other"
"
dataset_name"
:
"
other"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
other.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
other.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_other_generative"
"
tag"
:
"
mmlu_pro_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_miscellaneous_generative"
"
task"
:
"
mmlu_pro_miscellaneous_generative"
"
task_alias"
:
"
miscellaneous"
"
task_alias"
:
"
miscellaneous"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_philosophy.yaml
View file @
cd8642e7
"
dataset_name"
:
"
philosophy"
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_humanities_generative"
"
tag"
:
"
mmlu_pro_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_philosophy_generative"
"
task"
:
"
mmlu_pro_philosophy_generative"
"
task_alias"
:
"
philosophy"
"
task_alias"
:
"
philosophy"
lm_eval/tasks/mmlu_pro/generative/mmlu_pro_physics.yaml
View file @
cd8642e7
"
dataset_name"
:
"
physics"
"
dataset_name"
:
"
physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
physics.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
physics.
\n\
\n
"
\n
"
"
group"
:
"
mmlu_pro_stem_generative"
"
tag"
:
"
mmlu_pro_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_pro_physics_generative"
"
task"
:
"
mmlu_pro_physics_generative"
"
task_alias"
:
"
physics"
"
task_alias"
:
"
physics"
Prev
1
2
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