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
69186ef2
Commit
69186ef2
authored
Nov 10, 2023
by
lintangsutawika
Browse files
fixes
parent
b7a4ea06
Changes
62
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
40 additions
and
40 deletions
+40
-40
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_jurisprudence.yaml
...ks/mmlu/flan_n_shot/loglikelihood/mmlu_jurisprudence.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_logical_fallacies.yaml
...mlu/flan_n_shot/loglikelihood/mmlu_logical_fallacies.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_machine_learning.yaml
...mmlu/flan_n_shot/loglikelihood/mmlu_machine_learning.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_management.yaml
...tasks/mmlu/flan_n_shot/loglikelihood/mmlu_management.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_marketing.yaml
.../tasks/mmlu/flan_n_shot/loglikelihood/mmlu_marketing.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_medical_genetics.yaml
...mmlu/flan_n_shot/loglikelihood/mmlu_medical_genetics.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_miscellaneous.yaml
...ks/mmlu/flan_n_shot/loglikelihood/mmlu_miscellaneous.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_moral_disputes.yaml
...s/mmlu/flan_n_shot/loglikelihood/mmlu_moral_disputes.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_moral_scenarios.yaml
.../mmlu/flan_n_shot/loglikelihood/mmlu_moral_scenarios.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_nutrition.yaml
.../tasks/mmlu/flan_n_shot/loglikelihood/mmlu_nutrition.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_philosophy.yaml
...tasks/mmlu/flan_n_shot/loglikelihood/mmlu_philosophy.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_prehistory.yaml
...tasks/mmlu/flan_n_shot/loglikelihood/mmlu_prehistory.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_accounting.yaml
...an_n_shot/loglikelihood/mmlu_professional_accounting.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_law.yaml
...mmlu/flan_n_shot/loglikelihood/mmlu_professional_law.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_medicine.yaml
...flan_n_shot/loglikelihood/mmlu_professional_medicine.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_psychology.yaml
...an_n_shot/loglikelihood/mmlu_professional_psychology.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_public_relations.yaml
...mmlu/flan_n_shot/loglikelihood/mmlu_public_relations.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_security_studies.yaml
...mmlu/flan_n_shot/loglikelihood/mmlu_security_studies.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_sociology.yaml
.../tasks/mmlu/flan_n_shot/loglikelihood/mmlu_sociology.yaml
+2
-2
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_us_foreign_policy.yaml
...mlu/flan_n_shot/loglikelihood/mmlu_us_foreign_policy.yaml
+2
-2
No files found.
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_jurisprudence.yaml
View file @
69186ef2
"
dataset_name"
:
"
jurisprudence"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
jurisprudence.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_humanities"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_humanities"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_jurisprudence"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_jurisprudence"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_logical_fallacies.yaml
View file @
69186ef2
"
dataset_name"
:
"
logical_fallacies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
logical
\
\
fallacies.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_humanities"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_humanities"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_logical_fallacies"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_logical_fallacies"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_machine_learning.yaml
View file @
69186ef2
"
dataset_name"
:
"
machine_learning"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
machine
\
\
learning.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_stem"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_machine_learning"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_machine_learning"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_management.yaml
View file @
69186ef2
"
dataset_name"
:
"
management"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
management.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_other"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_management"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_management"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_marketing.yaml
View file @
69186ef2
"
dataset_name"
:
"
marketing"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
marketing.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_other"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_marketing"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_marketing"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_medical_genetics.yaml
View file @
69186ef2
"
dataset_name"
:
"
medical_genetics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
medical
\
\
genetics.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_other"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_medical_genetics"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_medical_genetics"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_miscellaneous.yaml
View file @
69186ef2
"
dataset_name"
:
"
miscellaneous"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
miscellaneous.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_other"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_miscellaneous"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_miscellaneous"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_moral_disputes.yaml
View file @
69186ef2
"
dataset_name"
:
"
moral_disputes"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
\
\
disputes.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_humanities"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_humanities"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_moral_disputes"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_moral_disputes"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_moral_scenarios.yaml
View file @
69186ef2
"
dataset_name"
:
"
moral_scenarios"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
\
\
scenarios.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_humanities"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_humanities"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_moral_scenarios"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_moral_scenarios"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_nutrition.yaml
View file @
69186ef2
"
dataset_name"
:
"
nutrition"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
nutrition.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_other"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_nutrition"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_nutrition"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_philosophy.yaml
View file @
69186ef2
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_humanities"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_humanities"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_philosophy"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_philosophy"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_prehistory.yaml
View file @
69186ef2
"
dataset_name"
:
"
prehistory"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
prehistory.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_humanities"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_humanities"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_prehistory"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_prehistory"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_accounting.yaml
View file @
69186ef2
"
dataset_name"
:
"
professional_accounting"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
accounting.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_other"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_professional_accounting"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_professional_accounting"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_law.yaml
View file @
69186ef2
"
dataset_name"
:
"
professional_law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
law.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_humanities"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_humanities"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_professional_law"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_professional_law"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_medicine.yaml
View file @
69186ef2
"
dataset_name"
:
"
professional_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
medicine.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_other"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_professional_medicine"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_professional_medicine"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_professional_psychology.yaml
View file @
69186ef2
"
dataset_name"
:
"
professional_psychology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
psychology.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_social_sciences"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_social_sciences"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_professional_psychology"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_professional_psychology"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_public_relations.yaml
View file @
69186ef2
"
dataset_name"
:
"
public_relations"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
public
\
\
relations.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_social_sciences"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_social_sciences"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_public_relations"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_public_relations"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_security_studies.yaml
View file @
69186ef2
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
\
\
studies.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_social_sciences"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_social_sciences"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_security_studies"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_security_studies"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_sociology.yaml
View file @
69186ef2
"
dataset_name"
:
"
sociology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\
\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_social_sciences"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_social_sciences"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_sociology"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_sociology"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_us_foreign_policy.yaml
View file @
69186ef2
"
dataset_name"
:
"
us_foreign_policy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
us
\
\
foreign
policy.
\n\n
"
"
group"
:
"
mmlu_flan_n_shot_
generative
_social_sciences"
"
group"
:
"
mmlu_flan_n_shot_
loglikelihood
_social_sciences"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_
generative
_us_foreign_policy"
"
task"
:
"
mmlu_flan_n_shot_
loglikelihood
_us_foreign_policy"
Prev
1
2
3
4
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