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
574e565a
"docs/vscode:/vscode.git/clone" did not exist on "1e4226634c253d84ead3017da663dedd3847309f"
Unverified
Commit
574e565a
authored
Nov 10, 2023
by
Lintang Sutawika
Committed by
GitHub
Nov 10, 2023
Browse files
Merge branch 'big-refactor' into verbosity-rework
parents
73f3029c
b7a4ea06
Changes
498
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
60 additions
and
20 deletions
+60
-20
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_high_school_world_history.yaml
...lan_n_shot/generative/mmlu_high_school_world_history.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_human_aging.yaml
...l/tasks/mmlu/flan_n_shot/generative/mmlu_human_aging.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_human_sexuality.yaml
...sks/mmlu/flan_n_shot/generative/mmlu_human_sexuality.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_international_law.yaml
...s/mmlu/flan_n_shot/generative/mmlu_international_law.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_jurisprudence.yaml
...tasks/mmlu/flan_n_shot/generative/mmlu_jurisprudence.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_logical_fallacies.yaml
...s/mmlu/flan_n_shot/generative/mmlu_logical_fallacies.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_machine_learning.yaml
...ks/mmlu/flan_n_shot/generative/mmlu_machine_learning.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_management.yaml
...al/tasks/mmlu/flan_n_shot/generative/mmlu_management.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_marketing.yaml
...val/tasks/mmlu/flan_n_shot/generative/mmlu_marketing.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_medical_genetics.yaml
...ks/mmlu/flan_n_shot/generative/mmlu_medical_genetics.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_miscellaneous.yaml
...tasks/mmlu/flan_n_shot/generative/mmlu_miscellaneous.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_moral_disputes.yaml
...asks/mmlu/flan_n_shot/generative/mmlu_moral_disputes.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_moral_scenarios.yaml
...sks/mmlu/flan_n_shot/generative/mmlu_moral_scenarios.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_nutrition.yaml
...val/tasks/mmlu/flan_n_shot/generative/mmlu_nutrition.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_philosophy.yaml
...al/tasks/mmlu/flan_n_shot/generative/mmlu_philosophy.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_prehistory.yaml
...al/tasks/mmlu/flan_n_shot/generative/mmlu_prehistory.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_professional_accounting.yaml
.../flan_n_shot/generative/mmlu_professional_accounting.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_professional_law.yaml
...ks/mmlu/flan_n_shot/generative/mmlu_professional_law.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_professional_medicine.yaml
...lu/flan_n_shot/generative/mmlu_professional_medicine.yaml
+3
-1
lm_eval/tasks/mmlu/flan_n_shot/generative/mmlu_professional_psychology.yaml
.../flan_n_shot/generative/mmlu_professional_psychology.yaml
+3
-1
No files found.
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_high_school_world_history.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_high_school_world_history.yaml
View file @
574e565a
"
dataset_name"
:
"
high_school_world_history"
"
dataset_name"
:
"
high_school_world_history"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
school
world
history.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
\
school
world
history.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_humanities"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_high_school_world_history"
"
task"
:
"
mmlu_flan_n_shot_generative_high_school_world_history"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_human_aging.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_human_aging.yaml
View file @
574e565a
"
dataset_name"
:
"
human_aging"
"
dataset_name"
:
"
human_aging"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
human
aging.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
human
\
\
aging.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_human_aging"
"
task"
:
"
mmlu_flan_n_shot_generative_human_aging"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_human_sexuality.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_human_sexuality.yaml
View file @
574e565a
"
dataset_name"
:
"
human_sexuality"
"
dataset_name"
:
"
human_sexuality"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
human
sexuality.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
human
\
\
sexuality.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_social_sciences"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_human_sexuality"
"
task"
:
"
mmlu_flan_n_shot_generative_human_sexuality"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_international_law.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_international_law.yaml
View file @
574e565a
"
dataset_name"
:
"
international_law"
"
dataset_name"
:
"
international_law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
international
law.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
international
\
\
law.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_humanities"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_international_law"
"
task"
:
"
mmlu_flan_n_shot_generative_international_law"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_jurisprudence.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_jurisprudence.yaml
View file @
574e565a
"
dataset_name"
:
"
jurisprudence"
"
dataset_name"
:
"
jurisprudence"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
jurisprudence.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
jurisprudence.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_humanities"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_jurisprudence"
"
task"
:
"
mmlu_flan_n_shot_generative_jurisprudence"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_logical_fallacies.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_logical_fallacies.yaml
View file @
574e565a
"
dataset_name"
:
"
logical_fallacies"
"
dataset_name"
:
"
logical_fallacies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
logical
fallacies.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
logical
\
\
fallacies.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_humanities"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_logical_fallacies"
"
task"
:
"
mmlu_flan_n_shot_generative_logical_fallacies"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_machine_learning.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_machine_learning.yaml
View file @
574e565a
"
dataset_name"
:
"
machine_learning"
"
dataset_name"
:
"
machine_learning"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
machine
learning.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
machine
\
\
learning.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_stem"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_machine_learning"
"
task"
:
"
mmlu_flan_n_shot_generative_machine_learning"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_management.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_management.yaml
View file @
574e565a
"
dataset_name"
:
"
management"
"
dataset_name"
:
"
management"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
management.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
management.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_management"
"
task"
:
"
mmlu_flan_n_shot_generative_management"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_marketing.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_marketing.yaml
View file @
574e565a
"
dataset_name"
:
"
marketing"
"
dataset_name"
:
"
marketing"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
marketing.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
marketing.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_marketing"
"
task"
:
"
mmlu_flan_n_shot_generative_marketing"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_medical_genetics.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_medical_genetics.yaml
View file @
574e565a
"
dataset_name"
:
"
medical_genetics"
"
dataset_name"
:
"
medical_genetics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
medical
genetics.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
medical
\
\
genetics.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_medical_genetics"
"
task"
:
"
mmlu_flan_n_shot_generative_medical_genetics"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_miscellaneous.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_miscellaneous.yaml
View file @
574e565a
"
dataset_name"
:
"
miscellaneous"
"
dataset_name"
:
"
miscellaneous"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
miscellaneous.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
miscellaneous.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_miscellaneous"
"
task"
:
"
mmlu_flan_n_shot_generative_miscellaneous"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_moral_disputes.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_moral_disputes.yaml
View file @
574e565a
"
dataset_name"
:
"
moral_disputes"
"
dataset_name"
:
"
moral_disputes"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
disputes.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
\
\
disputes.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_humanities"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_moral_disputes"
"
task"
:
"
mmlu_flan_n_shot_generative_moral_disputes"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_moral_scenarios.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_moral_scenarios.yaml
View file @
574e565a
"
dataset_name"
:
"
moral_scenarios"
"
dataset_name"
:
"
moral_scenarios"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
scenarios.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
\
\
scenarios.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_humanities"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_moral_scenarios"
"
task"
:
"
mmlu_flan_n_shot_generative_moral_scenarios"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_nutrition.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_nutrition.yaml
View file @
574e565a
"
dataset_name"
:
"
nutrition"
"
dataset_name"
:
"
nutrition"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
nutrition.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
nutrition.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_nutrition"
"
task"
:
"
mmlu_flan_n_shot_generative_nutrition"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_philosophy.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_philosophy.yaml
View file @
574e565a
"
dataset_name"
:
"
philosophy"
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_humanities"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_philosophy"
"
task"
:
"
mmlu_flan_n_shot_generative_philosophy"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_prehistory.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_prehistory.yaml
View file @
574e565a
"
dataset_name"
:
"
prehistory"
"
dataset_name"
:
"
prehistory"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
prehistory.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
prehistory.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_humanities"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_prehistory"
"
task"
:
"
mmlu_flan_n_shot_generative_prehistory"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_professional_accounting.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_professional_accounting.yaml
View file @
574e565a
"
dataset_name"
:
"
professional_accounting"
"
dataset_name"
:
"
professional_accounting"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
accounting.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
accounting.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_accounting"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_accounting"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_professional_law.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_professional_law.yaml
View file @
574e565a
"
dataset_name"
:
"
professional_law"
"
dataset_name"
:
"
professional_law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
law.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
law.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_humanities"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_law"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_law"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_professional_medicine.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_professional_medicine.yaml
View file @
574e565a
"
dataset_name"
:
"
professional_medicine"
"
dataset_name"
:
"
professional_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
medicine.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
medicine.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_other"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_medicine"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_medicine"
lm_eval/tasks/mmlu/flan_n_shot/mmlu
_gen
_professional_psychology.yaml
→
lm_eval/tasks/mmlu/flan_n_shot/
generative/
mmlu_professional_psychology.yaml
View file @
574e565a
"
dataset_name"
:
"
professional_psychology"
"
dataset_name"
:
"
professional_psychology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
psychology.
\n\n
"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
psychology.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_generative_social_sciences"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
include"
:
"
_mmlu_flan_generative_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_psychology"
"
task"
:
"
mmlu_flan_n_shot_generative_professional_psychology"
Prev
1
…
8
9
10
11
12
13
14
15
16
…
25
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