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
0d5748b7
Commit
0d5748b7
authored
Dec 13, 2023
by
lintangsutawika
Browse files
added mmlu alt world prompts
parent
b9e55312
Changes
891
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
153 additions
and
0 deletions
+153
-0
lm_eval/tasks/mmlu/alternative_worlds/mmlu_output_variation.yaml
.../tasks/mmlu/alternative_worlds/mmlu_output_variation.yaml
+26
-0
lm_eval/tasks/mmlu/alternative_worlds/mmlu_prompt_variation.yaml
.../tasks/mmlu/alternative_worlds/mmlu_prompt_variation.yaml
+18
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/_mmlu_ov_01.yaml
...mmlu/alternative_worlds/output_variation/_mmlu_ov_01.yaml
+5
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/_mmlu_ov_02.yaml
...mmlu/alternative_worlds/output_variation/_mmlu_ov_02.yaml
+5
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/_mmlu_ov_03.yaml
...mmlu/alternative_worlds/output_variation/_mmlu_ov_03.yaml
+5
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/_mmlu_ov_04.yaml
...mmlu/alternative_worlds/output_variation/_mmlu_ov_04.yaml
+5
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/_mmlu.yaml
...alternative_worlds/output_variation/style_01/a/_mmlu.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/_template_yaml
...rnative_worlds/output_variation/style_01/a/_template_yaml
+11
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_abstract_algebra.yaml
...ds/output_variation/style_01/a/mmlu_abstract_algebra.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_anatomy.yaml
...tive_worlds/output_variation/style_01/a/mmlu_anatomy.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_astronomy.yaml
...ve_worlds/output_variation/style_01/a/mmlu_astronomy.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_business_ethics.yaml
...lds/output_variation/style_01/a/mmlu_business_ethics.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_clinical_knowledge.yaml
.../output_variation/style_01/a/mmlu_clinical_knowledge.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_biology.yaml
...lds/output_variation/style_01/a/mmlu_college_biology.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_chemistry.yaml
...s/output_variation/style_01/a/mmlu_college_chemistry.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_computer_science.yaml
...t_variation/style_01/a/mmlu_college_computer_science.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_mathematics.yaml
...output_variation/style_01/a/mmlu_college_mathematics.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_medicine.yaml
...ds/output_variation/style_01/a/mmlu_college_medicine.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_physics.yaml
...lds/output_variation/style_01/a/mmlu_college_physics.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_computer_security.yaml
...s/output_variation/style_01/a/mmlu_computer_security.yaml
+6
-0
No files found.
lm_eval/tasks/mmlu/alternative_worlds/mmlu_output_variation.yaml
0 → 100644
View file @
0d5748b7
group
:
mmlu_alt_ov
task
:
-
mmlu_alt_ov_01a
-
mmlu_alt_ov_01b
-
mmlu_alt_ov_01c
-
mmlu_alt_ov_02a
-
mmlu_alt_ov_02b
-
mmlu_alt_ov_02c
-
mmlu_alt_ov_03a
-
mmlu_alt_ov_03b
-
mmlu_alt_ov_03c
-
mmlu_alt_ov_04a
-
mmlu_alt_ov_04b
-
mmlu_alt_ov_04c
-
mmlu_alt_ov_05a
-
mmlu_alt_ov_05b
-
mmlu_alt_ov_05c
-
mmlu_alt_ov_06a
-
mmlu_alt_ov_06b
-
mmlu_alt_ov_06c
-
mmlu_alt_ov_07a
-
mmlu_alt_ov_07b
-
mmlu_alt_ov_07c
-
mmlu_alt_ov_08a
-
mmlu_alt_ov_08b
-
mmlu_alt_ov_08c
lm_eval/tasks/mmlu/alternative_worlds/mmlu_prompt_variation.yaml
0 → 100644
View file @
0d5748b7
group
:
mmlu_alt_pv
task
:
-
mmlu_alt_pv_01
-
mmlu_alt_pv_02
-
mmlu_alt_pv_03
# - mmlu_alt_pv_01_stem
# - mmlu_alt_pv_01_other
# - mmlu_alt_pv_01_social_sciences
# - mmlu_alt_pv_01_humanities
# - mmlu_alt_pv_02_stem
# - mmlu_alt_pv_02_other
# - mmlu_alt_pv_02_social_sciences
# - mmlu_alt_pv_02_humanities
# - mmlu_alt_pv_03_stem
# - mmlu_alt_pv_03_other
# - mmlu_alt_pv_03_social_sciences
# - mmlu_alt_pv_03_humanities
lm_eval/tasks/mmlu/alternative_worlds/output_variation/_mmlu_ov_01.yaml
0 → 100644
View file @
0d5748b7
group
:
mmlu_alt_ov_01
task
:
-
mmlu_alt_ov_01a
-
mmlu_alt_ov_01b
-
mmlu_alt_ov_01c
lm_eval/tasks/mmlu/alternative_worlds/output_variation/_mmlu_ov_02.yaml
0 → 100644
View file @
0d5748b7
group
:
mmlu_alt_ov_02
task
:
-
mmlu_alt_ov_02a
-
mmlu_alt_ov_02b
-
mmlu_alt_ov_02c
lm_eval/tasks/mmlu/alternative_worlds/output_variation/_mmlu_ov_03.yaml
0 → 100644
View file @
0d5748b7
group
:
mmlu_alt_ov_03
task
:
-
mmlu_alt_ov_03a
-
mmlu_alt_ov_03b
-
mmlu_alt_ov_03c
lm_eval/tasks/mmlu/alternative_worlds/output_variation/_mmlu_ov_04.yaml
0 → 100644
View file @
0d5748b7
group
:
mmlu_alt_ov_04
task
:
-
mmlu_alt_ov_04a
-
mmlu_alt_ov_04b
-
mmlu_alt_ov_04c
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/_mmlu.yaml
0 → 100644
View file @
0d5748b7
group
:
mmlu_alt_ov_01a
task
:
-
mmlu_alt_ov_01a_stem
-
mmlu_alt_ov_01a_other
-
mmlu_alt_ov_01a_social_sciences
-
mmlu_alt_ov_01a_humanities
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/_template_yaml
0 → 100644
View file @
0d5748b7
dataset_path: hails/mmlu_no_train
test_split: test
fewshot_split: dev
output_type: multiple_choice
doc_to_text: !function ../../../styles.template_01
doc_to_choice: !function ../../../styles.choice_01a
doc_to_target: answer
metric_list:
- metric: acc
- metric: acc_norm
- metric: brier_score
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_abstract_algebra.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
abstract_algebra"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
\
\
algebra.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_abstract_algebra"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_anatomy.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
anatomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_01a_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_anatomy"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_astronomy.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
astronomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_01a_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_astronomy"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_business_ethics.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
business_ethics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
\
\
ethics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_business_ethics"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_clinical_knowledge.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
clinical_knowledge"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
clinical
\
\
knowledge.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_clinical_knowledge"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_biology.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_biology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
biology.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_college_biology"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_chemistry.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_chemistry"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
chemistry.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_college_chemistry"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_computer_science.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_computer_science"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
computer
science.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_college_computer_science"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_mathematics.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_mathematics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
mathematics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_college_mathematics"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_medicine.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
medicine.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_college_medicine"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_college_physics.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
college_physics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
college
\
\
physics.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_college_physics"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_01/a/mmlu_computer_security.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
computer_security"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
computer
\
\
security.
\n\n
"
"
group"
:
"
mmlu_alt_ov_01a_stem"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_01a_computer_security"
Prev
1
2
3
4
5
…
45
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