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
60c9c170
Commit
60c9c170
authored
May 29, 2024
by
haileyschoelkopf
Browse files
Merge branch 'main' into inverse-scaling-tasks
parents
4b2d565b
b4cd85d4
Changes
605
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
160 additions
and
0 deletions
+160
-0
lm_eval/tasks/mmlu/generative/mmlu_high_school_mathematics.yaml
...l/tasks/mmlu/generative/mmlu_high_school_mathematics.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_high_school_microeconomics.yaml
...asks/mmlu/generative/mmlu_high_school_microeconomics.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_high_school_physics.yaml
lm_eval/tasks/mmlu/generative/mmlu_high_school_physics.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_high_school_psychology.yaml
...al/tasks/mmlu/generative/mmlu_high_school_psychology.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_high_school_statistics.yaml
...al/tasks/mmlu/generative/mmlu_high_school_statistics.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_high_school_us_history.yaml
...al/tasks/mmlu/generative/mmlu_high_school_us_history.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_high_school_world_history.yaml
...tasks/mmlu/generative/mmlu_high_school_world_history.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_human_aging.yaml
lm_eval/tasks/mmlu/generative/mmlu_human_aging.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_human_sexuality.yaml
lm_eval/tasks/mmlu/generative/mmlu_human_sexuality.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_international_law.yaml
lm_eval/tasks/mmlu/generative/mmlu_international_law.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_jurisprudence.yaml
lm_eval/tasks/mmlu/generative/mmlu_jurisprudence.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_logical_fallacies.yaml
lm_eval/tasks/mmlu/generative/mmlu_logical_fallacies.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_machine_learning.yaml
lm_eval/tasks/mmlu/generative/mmlu_machine_learning.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_management.yaml
lm_eval/tasks/mmlu/generative/mmlu_management.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_marketing.yaml
lm_eval/tasks/mmlu/generative/mmlu_marketing.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_medical_genetics.yaml
lm_eval/tasks/mmlu/generative/mmlu_medical_genetics.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_miscellaneous.yaml
lm_eval/tasks/mmlu/generative/mmlu_miscellaneous.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_moral_disputes.yaml
lm_eval/tasks/mmlu/generative/mmlu_moral_disputes.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_moral_scenarios.yaml
lm_eval/tasks/mmlu/generative/mmlu_moral_scenarios.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_nutrition.yaml
lm_eval/tasks/mmlu/generative/mmlu_nutrition.yaml
+8
-0
No files found.
lm_eval/tasks/mmlu/generative/mmlu_high_school_mathematics.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
high_school_mathematics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
\
school
mathematics.
\n\n
"
"
group"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_high_school_mathematics_generative"
"
task_alias"
:
"
high_school_mathematics"
lm_eval/tasks/mmlu/generative/mmlu_high_school_microeconomics.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
high_school_microeconomics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
\
school
microeconomics.
\n\n
"
"
group"
:
"
mmlu_social_sciences_generative"
"
group_alias"
:
"
social_sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_high_school_microeconomics_generative"
"
task_alias"
:
"
high_school_microeconomics"
lm_eval/tasks/mmlu/generative/mmlu_high_school_physics.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
high_school_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
\
school
physics.
\n\n
"
"
group"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_high_school_physics_generative"
"
task_alias"
:
"
high_school_physics"
lm_eval/tasks/mmlu/generative/mmlu_high_school_psychology.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
high_school_psychology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
\
school
psychology.
\n\n
"
"
group"
:
"
mmlu_social_sciences_generative"
"
group_alias"
:
"
social_sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_high_school_psychology_generative"
"
task_alias"
:
"
high_school_psychology"
lm_eval/tasks/mmlu/generative/mmlu_high_school_statistics.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
high_school_statistics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
\
school
statistics.
\n\n
"
"
group"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_high_school_statistics_generative"
"
task_alias"
:
"
high_school_statistics"
lm_eval/tasks/mmlu/generative/mmlu_high_school_us_history.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
high_school_us_history"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
\
school
us
history.
\n\n
"
"
group"
:
"
mmlu_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_high_school_us_history_generative"
"
task_alias"
:
"
high_school_us_history"
lm_eval/tasks/mmlu/generative/mmlu_high_school_world_history.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
high_school_world_history"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
\
school
world
history.
\n\n
"
"
group"
:
"
mmlu_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_high_school_world_history_generative"
"
task_alias"
:
"
high_school_world_history"
lm_eval/tasks/mmlu/generative/mmlu_human_aging.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
human_aging"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
human
\
\
aging.
\n\n
"
"
group"
:
"
mmlu_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_human_aging_generative"
"
task_alias"
:
"
human_aging"
lm_eval/tasks/mmlu/generative/mmlu_human_sexuality.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
human_sexuality"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
human
\
\
sexuality.
\n\n
"
"
group"
:
"
mmlu_social_sciences_generative"
"
group_alias"
:
"
social_sciences"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_human_sexuality_generative"
"
task_alias"
:
"
human_sexuality"
lm_eval/tasks/mmlu/generative/mmlu_international_law.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
international_law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
international
\
\
law.
\n\n
"
"
group"
:
"
mmlu_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_international_law_generative"
"
task_alias"
:
"
international_law"
lm_eval/tasks/mmlu/generative/mmlu_jurisprudence.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
jurisprudence"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
jurisprudence.
\n\
\n
"
"
group"
:
"
mmlu_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_jurisprudence_generative"
"
task_alias"
:
"
jurisprudence"
lm_eval/tasks/mmlu/generative/mmlu_logical_fallacies.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
logical_fallacies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
logical
\
\
fallacies.
\n\n
"
"
group"
:
"
mmlu_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_logical_fallacies_generative"
"
task_alias"
:
"
logical_fallacies"
lm_eval/tasks/mmlu/generative/mmlu_machine_learning.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
machine_learning"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
machine
\
\
learning.
\n\n
"
"
group"
:
"
mmlu_stem_generative"
"
group_alias"
:
"
stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_machine_learning_generative"
"
task_alias"
:
"
machine_learning"
lm_eval/tasks/mmlu/generative/mmlu_management.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
management"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
management.
\n\
\n
"
"
group"
:
"
mmlu_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_management_generative"
"
task_alias"
:
"
management"
lm_eval/tasks/mmlu/generative/mmlu_marketing.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
marketing"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
marketing.
\n\
\n
"
"
group"
:
"
mmlu_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_marketing_generative"
"
task_alias"
:
"
marketing"
lm_eval/tasks/mmlu/generative/mmlu_medical_genetics.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
medical_genetics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
medical
\
\
genetics.
\n\n
"
"
group"
:
"
mmlu_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_medical_genetics_generative"
"
task_alias"
:
"
medical_genetics"
lm_eval/tasks/mmlu/generative/mmlu_miscellaneous.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
miscellaneous"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
miscellaneous.
\n\
\n
"
"
group"
:
"
mmlu_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_miscellaneous_generative"
"
task_alias"
:
"
miscellaneous"
lm_eval/tasks/mmlu/generative/mmlu_moral_disputes.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
moral_disputes"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
\
\
disputes.
\n\n
"
"
group"
:
"
mmlu_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_moral_disputes_generative"
"
task_alias"
:
"
moral_disputes"
lm_eval/tasks/mmlu/generative/mmlu_moral_scenarios.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
moral_scenarios"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
\
\
scenarios.
\n\n
"
"
group"
:
"
mmlu_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_moral_scenarios_generative"
"
task_alias"
:
"
moral_scenarios"
lm_eval/tasks/mmlu/generative/mmlu_nutrition.yaml
0 → 100644
View file @
60c9c170
"
dataset_name"
:
"
nutrition"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
nutrition.
\n\
\n
"
"
group"
:
"
mmlu_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_nutrition_generative"
"
task_alias"
:
"
nutrition"
Prev
1
…
18
19
20
21
22
23
24
25
26
…
31
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