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
22b95671
"tests/t5/test_modeling_t5.py" did not exist on "d0486c8bc238bc5bb4757871b0c5afc49c3c11cb"
Commit
22b95671
authored
Jul 02, 2024
by
haileyschoelkopf
Browse files
switch mmlu variants over to using
parent
c1d9e625
Changes
344
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
19 additions
and
20 deletions
+19
-20
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_philosophy.yaml
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_philosophy.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_prehistory.yaml
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_prehistory.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_accounting.yaml
.../mmlu/flan_cot_zeroshot/mmlu_professional_accounting.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_law.yaml
...l/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_law.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_medicine.yaml
...ks/mmlu/flan_cot_zeroshot/mmlu_professional_medicine.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_psychology.yaml
.../mmlu/flan_cot_zeroshot/mmlu_professional_psychology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_public_relations.yaml
...l/tasks/mmlu/flan_cot_zeroshot/mmlu_public_relations.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_security_studies.yaml
...l/tasks/mmlu/flan_cot_zeroshot/mmlu_security_studies.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_sociology.yaml
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_sociology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_us_foreign_policy.yaml
.../tasks/mmlu/flan_cot_zeroshot/mmlu_us_foreign_policy.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_virology.yaml
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_virology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_world_religions.yaml
...al/tasks/mmlu/flan_cot_zeroshot/mmlu_world_religions.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu_flan_generative_template_yaml
...lan_n_shot/generative/_mmlu_flan_generative_template_yaml
+0
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_abstract_algebra.yaml
...ks/mmlu/flan_n_shot/generative/mmlu_abstract_algebra.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_anatomy.yaml
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_anatomy.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_astronomy.yaml
...val/tasks/mmlu/flan_n_shot/generative/mmlu_astronomy.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_business_ethics.yaml
...sks/mmlu/flan_n_shot/generative/mmlu_business_ethics.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_clinical_knowledge.yaml
.../mmlu/flan_n_shot/generative/mmlu_clinical_knowledge.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_college_biology.yaml
...sks/mmlu/flan_n_shot/generative/mmlu_college_biology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_college_chemistry.yaml
...s/mmlu/flan_n_shot/generative/mmlu_college_chemistry.yaml
+1
-1
No files found.
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_philosophy.yaml
View file @
22b95671
"
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_flan_cot_zeroshot_humanities"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_philosophy"
"
task"
:
"
mmlu_flan_cot_zeroshot_philosophy"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_prehistory.yaml
View file @
22b95671
"
dataset_name"
:
"
prehistory"
"
dataset_name"
:
"
prehistory"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
prehistory.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
prehistory.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_humanities"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_prehistory"
"
task"
:
"
mmlu_flan_cot_zeroshot_prehistory"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_accounting.yaml
View file @
22b95671
"
dataset_name"
:
"
professional_accounting"
"
dataset_name"
:
"
professional_accounting"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
accounting.
\n\n
"
\
accounting.
\n\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_other"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_other"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_professional_accounting"
"
task"
:
"
mmlu_flan_cot_zeroshot_professional_accounting"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_law.yaml
View file @
22b95671
"
dataset_name"
:
"
professional_law"
"
dataset_name"
:
"
professional_law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
law.
\n\n
"
\
law.
\n\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_humanities"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_professional_law"
"
task"
:
"
mmlu_flan_cot_zeroshot_professional_law"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_medicine.yaml
View file @
22b95671
"
dataset_name"
:
"
professional_medicine"
"
dataset_name"
:
"
professional_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
medicine.
\n\n
"
\
medicine.
\n\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_other"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_other"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_professional_medicine"
"
task"
:
"
mmlu_flan_cot_zeroshot_professional_medicine"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_professional_psychology.yaml
View file @
22b95671
"
dataset_name"
:
"
professional_psychology"
"
dataset_name"
:
"
professional_psychology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
psychology.
\n\n
"
\
psychology.
\n\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_professional_psychology"
"
task"
:
"
mmlu_flan_cot_zeroshot_professional_psychology"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_public_relations.yaml
View file @
22b95671
"
dataset_name"
:
"
public_relations"
"
dataset_name"
:
"
public_relations"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
public
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
public
\
\
relations.
\n\n
"
\
relations.
\n\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_public_relations"
"
task"
:
"
mmlu_flan_cot_zeroshot_public_relations"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_security_studies.yaml
View file @
22b95671
"
dataset_name"
:
"
security_studies"
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
\
\
studies.
\n\n
"
\
studies.
\n\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_security_studies"
"
task"
:
"
mmlu_flan_cot_zeroshot_security_studies"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_sociology.yaml
View file @
22b95671
"
dataset_name"
:
"
sociology"
"
dataset_name"
:
"
sociology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_sociology"
"
task"
:
"
mmlu_flan_cot_zeroshot_sociology"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_us_foreign_policy.yaml
View file @
22b95671
"
dataset_name"
:
"
us_foreign_policy"
"
dataset_name"
:
"
us_foreign_policy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
us
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
us
\
\
foreign
policy.
\n\n
"
\
foreign
policy.
\n\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_social_sciences"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_us_foreign_policy"
"
task"
:
"
mmlu_flan_cot_zeroshot_us_foreign_policy"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_virology.yaml
View file @
22b95671
"
dataset_name"
:
"
virology"
"
dataset_name"
:
"
virology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_other"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_other"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_virology"
"
task"
:
"
mmlu_flan_cot_zeroshot_virology"
lm_eval/tasks/mmlu/flan_cot_zeroshot/mmlu_world_religions.yaml
View file @
22b95671
"
dataset_name"
:
"
world_religions"
"
dataset_name"
:
"
world_religions"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
\
\
religions.
\n\n
"
\
religions.
\n\n
"
"
group
"
:
"
mmlu_flan_cot_zeroshot_humanities"
"
tag
"
:
"
mmlu_flan_cot_zeroshot_humanities"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
include"
:
"
_mmlu_flan_cot_zeroshot_template_yaml"
"
task"
:
"
mmlu_flan_cot_zeroshot_world_religions"
"
task"
:
"
mmlu_flan_cot_zeroshot_world_religions"
lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu_flan_generative_template_yaml
View file @
22b95671
group: mmlu_flan_n_shot_generative
dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
test_split: test
test_split: test
fewshot_split: dev
fewshot_split: dev
...
...
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_abstract_algebra.yaml
View file @
22b95671
"
dataset_name"
:
"
abstract_algebra"
"
dataset_name"
:
"
abstract_algebra"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
\
\
algebra.
\n\n
"
\
algebra.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_generative_stem"
"
tag
"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_abstract_algebra"
"
task"
:
"
mmlu_flan_n_shot_generative_abstract_algebra"
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_anatomy.yaml
View file @
22b95671
"
dataset_name"
:
"
anatomy"
"
dataset_name"
:
"
anatomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_flan_n_shot_generative_stem"
"
tag
"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_anatomy"
"
task"
:
"
mmlu_flan_n_shot_generative_anatomy"
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_astronomy.yaml
View file @
22b95671
"
dataset_name"
:
"
astronomy"
"
dataset_name"
:
"
astronomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\
\n
"
\n
"
"
group
"
:
"
mmlu_flan_n_shot_generative_stem"
"
tag
"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_astronomy"
"
task"
:
"
mmlu_flan_n_shot_generative_astronomy"
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_business_ethics.yaml
View file @
22b95671
"
dataset_name"
:
"
business_ethics"
"
dataset_name"
:
"
business_ethics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
\
\
ethics.
\n\n
"
\
ethics.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_generative_other"
"
tag
"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_business_ethics"
"
task"
:
"
mmlu_flan_n_shot_generative_business_ethics"
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_clinical_knowledge.yaml
View file @
22b95671
"
dataset_name"
:
"
clinical_knowledge"
"
dataset_name"
:
"
clinical_knowledge"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
clinical
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
clinical
\
\
knowledge.
\n\n
"
\
knowledge.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_generative_other"
"
tag
"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_clinical_knowledge"
"
task"
:
"
mmlu_flan_n_shot_generative_clinical_knowledge"
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_college_biology.yaml
View file @
22b95671
"
dataset_name"
:
"
college_biology"
"
dataset_name"
:
"
college_biology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
biology.
\n\n
"
\
biology.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_generative_stem"
"
tag
"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_college_biology"
"
task"
:
"
mmlu_flan_n_shot_generative_college_biology"
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_college_chemistry.yaml
View file @
22b95671
"
dataset_name"
:
"
college_chemistry"
"
dataset_name"
:
"
college_chemistry"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
chemistry.
\n\n
"
\
chemistry.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_generative_stem"
"
tag
"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_college_chemistry"
"
task"
:
"
mmlu_flan_n_shot_generative_college_chemistry"
Prev
1
…
5
6
7
8
9
10
11
12
13
…
18
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