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
e4db76cb
Commit
e4db76cb
authored
Jul 09, 2024
by
haileyschoelkopf
Browse files
Merge branch 'main' into multimodal-prototyping
parents
6cc6e9cd
ad80f555
Changes
871
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
49 additions
and
23 deletions
+49
-23
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu.yaml
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu.yaml
+30
-4
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_abstract_algebra.yaml
...mmlu/flan_n_shot/loglikelihood/mmlu_abstract_algebra.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_anatomy.yaml
...al/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_anatomy.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_astronomy.yaml
.../tasks/mmlu/flan_n_shot/loglikelihood/mmlu_astronomy.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_business_ethics.yaml
.../mmlu/flan_n_shot/loglikelihood/mmlu_business_ethics.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_clinical_knowledge.yaml
...lu/flan_n_shot/loglikelihood/mmlu_clinical_knowledge.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_biology.yaml
.../mmlu/flan_n_shot/loglikelihood/mmlu_college_biology.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_chemistry.yaml
...mlu/flan_n_shot/loglikelihood/mmlu_college_chemistry.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_computer_science.yaml
...n_n_shot/loglikelihood/mmlu_college_computer_science.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_mathematics.yaml
...u/flan_n_shot/loglikelihood/mmlu_college_mathematics.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_medicine.yaml
...mmlu/flan_n_shot/loglikelihood/mmlu_college_medicine.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_physics.yaml
.../mmlu/flan_n_shot/loglikelihood/mmlu_college_physics.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_computer_security.yaml
...mlu/flan_n_shot/loglikelihood/mmlu_computer_security.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_conceptual_physics.yaml
...lu/flan_n_shot/loglikelihood/mmlu_conceptual_physics.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_econometrics.yaml
...sks/mmlu/flan_n_shot/loglikelihood/mmlu_econometrics.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_electrical_engineering.yaml
...lan_n_shot/loglikelihood/mmlu_electrical_engineering.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_elementary_mathematics.yaml
...lan_n_shot/loglikelihood/mmlu_elementary_mathematics.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_formal_logic.yaml
...sks/mmlu/flan_n_shot/loglikelihood/mmlu_formal_logic.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_global_facts.yaml
...sks/mmlu/flan_n_shot/loglikelihood/mmlu_global_facts.yaml
+1
-1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_high_school_biology.yaml
...u/flan_n_shot/loglikelihood/mmlu_high_school_biology.yaml
+1
-1
No files found.
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu.yaml
View file @
e4db76cb
group
:
mmlu_flan_n_shot_loglikelihood
group_alias
:
mmlu (flan style, loglikelihood)
task
:
-
mmlu_flan_n_shot_loglikelihood_stem
-
mmlu_flan_n_shot_loglikelihood_other
-
mmlu_flan_n_shot_loglikelihood_social_sciences
-
mmlu_flan_n_shot_loglikelihood_humanities
-
group
:
stem
task
:
-
mmlu_flan_n_shot_loglikelihood_stem
aggregate_metric_list
:
-
metric
:
acc
weight_by_size
:
True
-
group
:
other
task
:
-
mmlu_flan_n_shot_loglikelihood_other
aggregate_metric_list
:
-
metric
:
acc
weight_by_size
:
True
-
group
:
social sciences
task
:
-
mmlu_flan_n_shot_loglikelihood_social_sciences
aggregate_metric_list
:
-
metric
:
acc
weight_by_size
:
True
-
group
:
humanities
task
:
-
mmlu_flan_n_shot_loglikelihood_humanities
aggregate_metric_list
:
-
metric
:
acc
weight_by_size
:
True
aggregate_metric_list
:
-
metric
:
acc
weight_by_size
:
True
metadata
:
version
:
1
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_abstract_algebra.yaml
View file @
e4db76cb
"
dataset_name"
:
"
abstract_algebra"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
\
\
algebra.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_abstract_algebra"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_anatomy.yaml
View file @
e4db76cb
"
dataset_name"
:
"
anatomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\
\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_anatomy"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_astronomy.yaml
View file @
e4db76cb
"
dataset_name"
:
"
astronomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\
\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_astronomy"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_business_ethics.yaml
View file @
e4db76cb
"
dataset_name"
:
"
business_ethics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
\
\
ethics.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_other"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_business_ethics"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_clinical_knowledge.yaml
View file @
e4db76cb
"
dataset_name"
:
"
clinical_knowledge"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
clinical
\
\
knowledge.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_other"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_clinical_knowledge"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_biology.yaml
View file @
e4db76cb
"
dataset_name"
:
"
college_biology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
biology.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_college_biology"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_chemistry.yaml
View file @
e4db76cb
"
dataset_name"
:
"
college_chemistry"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
chemistry.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_college_chemistry"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_computer_science.yaml
View file @
e4db76cb
"
dataset_name"
:
"
college_computer_science"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
computer
science.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_college_computer_science"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_mathematics.yaml
View file @
e4db76cb
"
dataset_name"
:
"
college_mathematics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
mathematics.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_college_mathematics"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_medicine.yaml
View file @
e4db76cb
"
dataset_name"
:
"
college_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
medicine.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_other"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_college_medicine"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_college_physics.yaml
View file @
e4db76cb
"
dataset_name"
:
"
college_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
physics.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_college_physics"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_computer_security.yaml
View file @
e4db76cb
"
dataset_name"
:
"
computer_security"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer
\
\
security.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_computer_security"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_conceptual_physics.yaml
View file @
e4db76cb
"
dataset_name"
:
"
conceptual_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
conceptual
\
\
physics.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_conceptual_physics"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_econometrics.yaml
View file @
e4db76cb
"
dataset_name"
:
"
econometrics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
econometrics.
\n\
\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_social_sciences"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_social_sciences"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_econometrics"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_electrical_engineering.yaml
View file @
e4db76cb
"
dataset_name"
:
"
electrical_engineering"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
electrical
\
\
engineering.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_electrical_engineering"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_elementary_mathematics.yaml
View file @
e4db76cb
"
dataset_name"
:
"
elementary_mathematics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
elementary
\
\
mathematics.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_elementary_mathematics"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_formal_logic.yaml
View file @
e4db76cb
"
dataset_name"
:
"
formal_logic"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
formal
\
\
logic.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_humanities"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_humanities"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_formal_logic"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_global_facts.yaml
View file @
e4db76cb
"
dataset_name"
:
"
global_facts"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
global
\
\
facts.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_other"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_other"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_global_facts"
lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/mmlu_high_school_biology.yaml
View file @
e4db76cb
"
dataset_name"
:
"
high_school_biology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
high
\
\
school
biology.
\n\n
"
"
group
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
tag
"
:
"
mmlu_flan_n_shot_loglikelihood_stem"
"
include"
:
"
_mmlu_flan_loglikelihood_template_yaml"
"
task"
:
"
mmlu_flan_n_shot_loglikelihood_high_school_biology"
Prev
1
…
29
30
31
32
33
34
35
36
37
…
44
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