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
bbb8386c
Commit
bbb8386c
authored
Apr 16, 2024
by
lintangsutawika
Browse files
removed alt worlds prompts
parent
3e5e9da2
Changes
1000
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
0 additions
and
125 deletions
+0
-125
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/b/mmlu_security_studies.yaml
...ds/output_variation/style_03/b/mmlu_security_studies.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/b/mmlu_sociology.yaml
...ve_worlds/output_variation/style_03/b/mmlu_sociology.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/b/mmlu_us_foreign_policy.yaml
...s/output_variation/style_03/b/mmlu_us_foreign_policy.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/b/mmlu_virology.yaml
...ive_worlds/output_variation/style_03/b/mmlu_virology.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/b/mmlu_world_religions.yaml
...lds/output_variation/style_03/b/mmlu_world_religions.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/_mmlu.yaml
...alternative_worlds/output_variation/style_03/c/_mmlu.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/_template_yaml
...rnative_worlds/output_variation/style_03/c/_template_yaml
+0
-11
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_abstract_algebra.yaml
...ds/output_variation/style_03/c/mmlu_abstract_algebra.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_anatomy.yaml
...tive_worlds/output_variation/style_03/c/mmlu_anatomy.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_astronomy.yaml
...ve_worlds/output_variation/style_03/c/mmlu_astronomy.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_business_ethics.yaml
...lds/output_variation/style_03/c/mmlu_business_ethics.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_clinical_knowledge.yaml
.../output_variation/style_03/c/mmlu_clinical_knowledge.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_biology.yaml
...lds/output_variation/style_03/c/mmlu_college_biology.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_chemistry.yaml
...s/output_variation/style_03/c/mmlu_college_chemistry.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_computer_science.yaml
...t_variation/style_03/c/mmlu_college_computer_science.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_mathematics.yaml
...output_variation/style_03/c/mmlu_college_mathematics.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_medicine.yaml
...ds/output_variation/style_03/c/mmlu_college_medicine.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_physics.yaml
...lds/output_variation/style_03/c/mmlu_college_physics.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_computer_security.yaml
...s/output_variation/style_03/c/mmlu_computer_security.yaml
+0
-6
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_conceptual_physics.yaml
.../output_variation/style_03/c/mmlu_conceptual_physics.yaml
+0
-6
No files found.
Too many changes to show.
To preserve performance only
1000 of 1000+
files are displayed.
Plain diff
Email patch
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/b/mmlu_security_studies.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
\
\
studies.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03b_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03b_security_studies"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/b/mmlu_sociology.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
sociology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_03b_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03b_sociology"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/b/mmlu_us_foreign_policy.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
us_foreign_policy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
us
\
\
foreign
policy.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03b_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03b_us_foreign_policy"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/b/mmlu_virology.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
virology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_03b_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03b_virology"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/b/mmlu_world_religions.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
world_religions"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
\
\
religions.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03b_humanities"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03b_world_religions"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/_mmlu.yaml
deleted
100644 → 0
View file @
3e5e9da2
group
:
mmlu_alt_ov_03c
task
:
-
mmlu_alt_ov_03c_stem
-
mmlu_alt_ov_03c_other
-
mmlu_alt_ov_03c_social_sciences
-
mmlu_alt_ov_03c_humanities
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/_template_yaml
deleted
100644 → 0
View file @
3e5e9da2
dataset_path: hails/mmlu_no_train
test_split: test
fewshot_split: dev
output_type: multiple_choice
doc_to_text: !function ../../../styles.template_03
doc_to_choice: !function ../../../styles.choice_03c
doc_to_target: answer
metric_list:
- metric: acc
- metric: acc_norm
- metric: brier_score
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_abstract_algebra.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
abstract_algebra"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
\
\
algebra.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_abstract_algebra"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_anatomy.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
anatomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_03c_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_anatomy"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_astronomy.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
astronomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_03c_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_astronomy"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_business_ethics.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
business_ethics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
\
\
ethics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_business_ethics"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_clinical_knowledge.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
clinical_knowledge"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
clinical
\
\
knowledge.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_clinical_knowledge"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_biology.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
college_biology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
biology.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_college_biology"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_chemistry.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
college_chemistry"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
chemistry.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_college_chemistry"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_computer_science.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
college_computer_science"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
computer
science.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_college_computer_science"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_mathematics.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
college_mathematics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
mathematics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_college_mathematics"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_medicine.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
college_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
medicine.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_college_medicine"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_college_physics.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
college_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
physics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_college_physics"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_computer_security.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
computer_security"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer
\
\
security.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_computer_security"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_03/c/mmlu_conceptual_physics.yaml
deleted
100644 → 0
View file @
3e5e9da2
"
dataset_name"
:
"
conceptual_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
conceptual
\
\
physics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_03c_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_03c_conceptual_physics"
Prev
1
…
34
35
36
37
38
39
40
41
42
…
50
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