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
3a4e4674
Unverified
Commit
3a4e4674
authored
Jan 21, 2025
by
Minho Ryu
Committed by
GitHub
Jan 21, 2025
Browse files
apply precommit (#2636)
parent
6dac8c69
Changes
1000
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
177 additions
and
0 deletions
+177
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_medical_genetics.yaml
...al_mmlu/full/id/global_mmlu_full_id_medical_genetics.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_miscellaneous.yaml
...lobal_mmlu/full/id/global_mmlu_full_id_miscellaneous.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_disputes.yaml
...obal_mmlu/full/id/global_mmlu_full_id_moral_disputes.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_scenarios.yaml
...bal_mmlu/full/id/global_mmlu_full_id_moral_scenarios.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_nutrition.yaml
...ks/global_mmlu/full/id/global_mmlu_full_id_nutrition.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_philosophy.yaml
...s/global_mmlu/full/id/global_mmlu_full_id_philosophy.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_prehistory.yaml
...s/global_mmlu/full/id/global_mmlu_full_id_prehistory.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_accounting.yaml
.../full/id/global_mmlu_full_id_professional_accounting.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_law.yaml
...al_mmlu/full/id/global_mmlu_full_id_professional_law.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_medicine.yaml
...lu/full/id/global_mmlu_full_id_professional_medicine.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_psychology.yaml
.../full/id/global_mmlu_full_id_professional_psychology.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_public_relations.yaml
...al_mmlu/full/id/global_mmlu_full_id_public_relations.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_security_studies.yaml
...al_mmlu/full/id/global_mmlu_full_id_security_studies.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_sociology.yaml
...ks/global_mmlu/full/id/global_mmlu_full_id_sociology.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_us_foreign_policy.yaml
...l_mmlu/full/id/global_mmlu_full_id_us_foreign_policy.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_virology.yaml
...sks/global_mmlu/full/id/global_mmlu_full_id_virology.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_world_religions.yaml
...bal_mmlu/full/id/global_mmlu_full_id_world_religions.yaml
+5
-0
lm_eval/tasks/global_mmlu/full/id/utils.py
lm_eval/tasks/global_mmlu/full/id/utils.py
+73
-0
lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig.yaml
lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig.yaml
+11
-0
lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_humanities.yaml
.../global_mmlu/full/ig/_global_mmlu_full_ig_humanities.yaml
+8
-0
No files found.
Too many changes to show.
To preserve performance only
1000 of 1000+
files are displayed.
Plain diff
Email patch
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_medical_genetics.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_medical_genetics
tag
:
global_mmlu_full_id_other_tasks
task
:
global_mmlu_full_id_medical_genetics
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_miscellaneous.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_miscellaneous
tag
:
global_mmlu_full_id_other_tasks
task
:
global_mmlu_full_id_miscellaneous
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_disputes.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_moral_disputes
tag
:
global_mmlu_full_id_humanities_tasks
task
:
global_mmlu_full_id_moral_disputes
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_moral_scenarios.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_moral_scenarios
tag
:
global_mmlu_full_id_humanities_tasks
task
:
global_mmlu_full_id_moral_scenarios
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_nutrition.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_nutrition
tag
:
global_mmlu_full_id_other_tasks
task
:
global_mmlu_full_id_nutrition
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_philosophy.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_philosophy
tag
:
global_mmlu_full_id_humanities_tasks
task
:
global_mmlu_full_id_philosophy
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_prehistory.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_prehistory
tag
:
global_mmlu_full_id_humanities_tasks
task
:
global_mmlu_full_id_prehistory
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_accounting.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_professional_accounting
tag
:
global_mmlu_full_id_other_tasks
task
:
global_mmlu_full_id_professional_accounting
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_law.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_professional_law
tag
:
global_mmlu_full_id_humanities_tasks
task
:
global_mmlu_full_id_professional_law
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_medicine.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_professional_medicine
tag
:
global_mmlu_full_id_other_tasks
task
:
global_mmlu_full_id_professional_medicine
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_professional_psychology.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_professional_psychology
tag
:
global_mmlu_full_id_social_sciences_tasks
task
:
global_mmlu_full_id_professional_psychology
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_public_relations.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_public_relations
tag
:
global_mmlu_full_id_social_sciences_tasks
task
:
global_mmlu_full_id_public_relations
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_security_studies.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_security_studies
tag
:
global_mmlu_full_id_social_sciences_tasks
task
:
global_mmlu_full_id_security_studies
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_sociology.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_sociology
tag
:
global_mmlu_full_id_social_sciences_tasks
task
:
global_mmlu_full_id_sociology
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_us_foreign_policy.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_us_foreign_policy
tag
:
global_mmlu_full_id_social_sciences_tasks
task
:
global_mmlu_full_id_us_foreign_policy
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_virology.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_virology
tag
:
global_mmlu_full_id_other_tasks
task
:
global_mmlu_full_id_virology
lm_eval/tasks/global_mmlu/full/id/global_mmlu_full_id_world_religions.yaml
0 → 100644
View file @
3a4e4674
# Generated by _generate_configs.py
include
:
_id_template_yaml
process_docs
:
!function
utils.process_world_religions
tag
:
global_mmlu_full_id_humanities_tasks
task
:
global_mmlu_full_id_world_religions
lm_eval/tasks/global_mmlu/full/id/utils.py
0 → 100644
View file @
3a4e4674
from
functools
import
partial
SUBJECTS
=
[
"abstract_algebra"
,
"anatomy"
,
"astronomy"
,
"business_ethics"
,
"clinical_knowledge"
,
"college_biology"
,
"college_chemistry"
,
"college_computer_science"
,
"college_mathematics"
,
"college_medicine"
,
"college_physics"
,
"computer_security"
,
"conceptual_physics"
,
"econometrics"
,
"electrical_engineering"
,
"elementary_mathematics"
,
"formal_logic"
,
"global_facts"
,
"high_school_biology"
,
"high_school_chemistry"
,
"high_school_computer_science"
,
"high_school_european_history"
,
"high_school_geography"
,
"high_school_government_and_politics"
,
"high_school_macroeconomics"
,
"high_school_mathematics"
,
"high_school_microeconomics"
,
"high_school_physics"
,
"high_school_psychology"
,
"high_school_statistics"
,
"high_school_us_history"
,
"high_school_world_history"
,
"human_aging"
,
"human_sexuality"
,
"international_law"
,
"jurisprudence"
,
"logical_fallacies"
,
"machine_learning"
,
"management"
,
"marketing"
,
"medical_genetics"
,
"miscellaneous"
,
"moral_disputes"
,
"moral_scenarios"
,
"nutrition"
,
"philosophy"
,
"prehistory"
,
"professional_accounting"
,
"professional_law"
,
"professional_medicine"
,
"professional_psychology"
,
"public_relations"
,
"security_studies"
,
"sociology"
,
"us_foreign_policy"
,
"virology"
,
"world_religions"
,
]
def
process_docs
(
dataset
,
subject
):
return
dataset
.
filter
(
lambda
x
:
x
[
"subject"
]
==
subject
)
process_functions
=
{
f
"process_
{
subject
}
"
:
partial
(
process_docs
,
subject
=
subject
)
for
subject
in
SUBJECTS
}
globals
().
update
(
process_functions
)
lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig.yaml
0 → 100644
View file @
3a4e4674
group
:
global_mmlu_full_ig
task
:
-
global_mmlu_full_ig_stem
-
global_mmlu_full_ig_other
-
global_mmlu_full_ig_social_sciences
-
global_mmlu_full_ig_humanities
aggregate_metric_list
:
-
metric
:
acc
weight_by_size
:
True
metadata
:
version
:
1.0
lm_eval/tasks/global_mmlu/full/ig/_global_mmlu_full_ig_humanities.yaml
0 → 100644
View file @
3a4e4674
group
:
global_mmlu_full_ig_humanities
task
:
-
global_mmlu_full_ig_humanities_tasks
aggregate_metric_list
:
-
metric
:
acc
weight_by_size
:
true
metadata
:
version
:
0.0
Prev
1
…
45
46
47
48
49
50
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