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
6769119f
Unverified
Commit
6769119f
authored
Oct 06, 2023
by
Hailey Schoelkopf
Committed by
GitHub
Oct 06, 2023
Browse files
Merge pull request #816 from EleutherAI/flan-benchmark
[Refactor] Flan benchmark
parents
4824a832
7d5e511c
Changes
448
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
80 additions
and
0 deletions
+80
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_machine_learning.yaml
...val/tasks/mmlu/flan_n_shot/mmlu_gen_machine_learning.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_management.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_management.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_marketing.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_marketing.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_medical_genetics.yaml
...val/tasks/mmlu/flan_n_shot/mmlu_gen_medical_genetics.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_miscellaneous.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_miscellaneous.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_moral_disputes.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_moral_disputes.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_moral_scenarios.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_moral_scenarios.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_nutrition.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_nutrition.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_philosophy.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_philosophy.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_prehistory.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_prehistory.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_professional_accounting.yaml
...ks/mmlu/flan_n_shot/mmlu_gen_professional_accounting.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_professional_law.yaml
...val/tasks/mmlu/flan_n_shot/mmlu_gen_professional_law.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_professional_medicine.yaml
...asks/mmlu/flan_n_shot/mmlu_gen_professional_medicine.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_professional_psychology.yaml
...ks/mmlu/flan_n_shot/mmlu_gen_professional_psychology.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_public_relations.yaml
...val/tasks/mmlu/flan_n_shot/mmlu_gen_public_relations.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_security_studies.yaml
...val/tasks/mmlu/flan_n_shot/mmlu_gen_security_studies.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_sociology.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_sociology.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_us_foreign_policy.yaml
...al/tasks/mmlu/flan_n_shot/mmlu_gen_us_foreign_policy.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_virology.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_virology.yaml
+4
-0
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_world_religions.yaml
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_world_religions.yaml
+4
-0
No files found.
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_machine_learning.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
machine_learning"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
machine
learning.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_machine_learning"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_management.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
management"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
management.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_management"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_marketing.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
marketing"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
marketing.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_marketing"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_medical_genetics.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
medical_genetics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
medical
genetics.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_medical_genetics"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_miscellaneous.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
miscellaneous"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
miscellaneous.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_miscellaneous"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_moral_disputes.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
moral_disputes"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
disputes.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_moral_disputes"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_moral_scenarios.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
moral_scenarios"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
scenarios.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_moral_scenarios"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_nutrition.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
nutrition"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
nutrition.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_nutrition"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_philosophy.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_philosophy"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_prehistory.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
prehistory"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
prehistory.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_prehistory"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_professional_accounting.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
professional_accounting"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
accounting.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_accounting"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_professional_law.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
professional_law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
law.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_law"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_professional_medicine.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
professional_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
medicine.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_medicine"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_professional_psychology.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
professional_psychology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
psychology.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_psychology"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_public_relations.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
public_relations"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
public
relations.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_public_relations"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_security_studies.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
studies.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_security_studies"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_sociology.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
sociology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_sociology"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_us_foreign_policy.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
us_foreign_policy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
us
foreign
policy.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_us_foreign_policy"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_virology.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
virology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_virology"
lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_world_religions.yaml
0 → 100644
View file @
6769119f
"
dataset_name"
:
"
world_religions"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
religions.
\n\n
"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_world_religions"
Prev
1
…
15
16
17
18
19
20
21
22
23
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