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
f7f298ee
Commit
f7f298ee
authored
Jan 25, 2024
by
lintangsutawika
Browse files
removed unused files for now
parents
c0d5a660
12bc8fce
Changes
186
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
19 additions
and
132 deletions
+19
-132
lm_eval/tasks/mmlu/generative/mmlu_virology.yaml
lm_eval/tasks/mmlu/generative/mmlu_virology.yaml
+8
-0
lm_eval/tasks/mmlu/generative/mmlu_world_religions.yaml
lm_eval/tasks/mmlu/generative/mmlu_world_religions.yaml
+8
-0
lm_eval/tasks/nq_open/nq_open.yaml
lm_eval/tasks/nq_open/nq_open.yaml
+2
-2
lm_eval/tasks/polemo2/polemo2_in.yaml
lm_eval/tasks/polemo2/polemo2_in.yaml
+1
-1
lm_eval/tasks/super_glue/boolq/alternative_worlds/README.md
lm_eval/tasks/super_glue/boolq/alternative_worlds/README.md
+0
-20
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/_boolq_alt_ov_yaml
...lq/alternative_worlds/output_variation/_boolq_alt_ov_yaml
+0
-21
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/boolq_ov.yaml
...e/boolq/alternative_worlds/output_variation/boolq_ov.yaml
+0
-10
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_01/a.yaml
...boolq/alternative_worlds/output_variation/style_01/a.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_01/b.yaml
...boolq/alternative_worlds/output_variation/style_01/b.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_01/c.yaml
...boolq/alternative_worlds/output_variation/style_01/c.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_02/a.yaml
...boolq/alternative_worlds/output_variation/style_02/a.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_02/b.yaml
...boolq/alternative_worlds/output_variation/style_02/b.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_02/c.yaml
...boolq/alternative_worlds/output_variation/style_02/c.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_03/a.yaml
...boolq/alternative_worlds/output_variation/style_03/a.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_03/b.yaml
...boolq/alternative_worlds/output_variation/style_03/b.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_03/c.yaml
...boolq/alternative_worlds/output_variation/style_03/c.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_04/a.yaml
...boolq/alternative_worlds/output_variation/style_04/a.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_04/b.yaml
...boolq/alternative_worlds/output_variation/style_04/b.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_04/c.yaml
...boolq/alternative_worlds/output_variation/style_04/c.yaml
+0
-6
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_05/a.yaml
...boolq/alternative_worlds/output_variation/style_05/a.yaml
+0
-6
No files found.
lm_eval/tasks/mmlu/generative/mmlu_virology.yaml
0 → 100644
View file @
f7f298ee
"
dataset_name"
:
"
virology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\n\
\n
"
"
group"
:
"
mmlu_other_generative"
"
group_alias"
:
"
other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_virology_generative"
"
task_alias"
:
"
virology"
lm_eval/tasks/mmlu/generative/mmlu_world_religions.yaml
0 → 100644
View file @
f7f298ee
"
dataset_name"
:
"
world_religions"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
\
\
religions.
\n\n
"
"
group"
:
"
mmlu_humanities_generative"
"
group_alias"
:
"
humanities"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_world_religions_generative"
"
task_alias"
:
"
world_religions"
lm_eval/tasks/nq_open/nq_open.yaml
View file @
f7f298ee
...
...
@@ -27,6 +27,6 @@ metric_list:
ignore_case
:
true
ignore_punctuation
:
true
regexes_to_ignore
:
-
"
\
b
an|a|the
\b
"
-
"
\
\
b(?:The
|the
|An
|A
|The
|a
|an
)
"
metadata
:
version
:
2
.0
version
:
3
.0
lm_eval/tasks/polemo2/polemo2_in.yaml
View file @
f7f298ee
...
...
@@ -2,7 +2,7 @@ group:
-
polemo2
task
:
polemo2_in
dataset_path
:
allegro/klej-polemo2-in
dataset_name
:
klej-polemo2-in
dataset_name
:
null
output_type
:
generate_until
training_split
:
train
validation_split
:
validation
...
...
lm_eval/tasks/super_glue/boolq/alternative_worlds/README.md
deleted
100644 → 0
View file @
c0d5a660
Investigate affect of letter options
-
(A)
-
A)
-
A.
-
A
\t
-
(a)
-
a)
-
a.
-
a
\t
Answer types:
-
letters only
-
original option
-
just letter
-
letters + continuation
-
original option
-
just letter
-
continuation
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/_boolq_alt_ov_yaml
deleted
100644 → 0
View file @
c0d5a660
dataset_path: super_glue
dataset_name: boolq
output_type: multiple_choice
training_split: train
validation_split: validation
doc_to_text: "{{passage}}\nQuestion: {{question}}?\nAnswer:"
doc_to_target: label
doc_to_choice: ["no", "yes"]
should_decontaminate: true
doc_to_decontamination_query: passage
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
- metric: brier_score
aggregation: brier_score
higher_is_better: false
metadata:
- version: 1.0
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/boolq_ov.yaml
deleted
100644 → 0
View file @
c0d5a660
group
:
boolq_alt_ov
task
:
-
boolq_alt_ov_01
-
boolq_alt_ov_02
-
boolq_alt_ov_03
-
boolq_alt_ov_04
-
boolq_alt_ov_05
-
boolq_alt_ov_06
-
boolq_alt_ov_07
-
boolq_alt_ov_08
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_01/a.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_01
task
:
boolq_alt_ov_01a
doc_to_text
:
!function
../styles.template_01
doc_to_choice
:
!function
../styles.choice_01a
doc_to_decontamination_query
:
!function
../styles.template_01
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_01/b.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_01
task
:
boolq_alt_ov_01b
doc_to_text
:
!function
../styles.template_01
doc_to_choice
:
!function
../styles.choice_01b
doc_to_decontamination_query
:
!function
../styles.template_01
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_01/c.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_01
task
:
boolq_alt_ov_01c
doc_to_text
:
!function
../styles.template_01
doc_to_choice
:
!function
../styles.choice_01c
doc_to_decontamination_query
:
!function
../styles.template_01
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_02/a.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_02
task
:
boolq_alt_ov_02a
doc_to_text
:
!function
../styles.template_02
doc_to_choice
:
!function
../styles.choice_02a
doc_to_decontamination_query
:
!function
../styles.template_02
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_02/b.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_02
task
:
boolq_alt_ov_02b
doc_to_text
:
!function
../styles.template_02
doc_to_choice
:
!function
../styles.choice_02b
doc_to_decontamination_query
:
!function
../styles.template_02
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_02/c.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_02
task
:
boolq_alt_ov_02c
doc_to_text
:
!function
../styles.template_02
doc_to_choice
:
!function
../styles.choice_02c
doc_to_decontamination_query
:
!function
../styles.template_02
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_03/a.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_03
task
:
boolq_alt_ov_03a
doc_to_text
:
!function
../styles.template_03
doc_to_choice
:
!function
../styles.choice_03a
doc_to_decontamination_query
:
!function
../styles.template_03
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_03/b.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_03
task
:
boolq_alt_ov_03b
doc_to_text
:
!function
../styles.template_03
doc_to_choice
:
!function
../styles.choice_03b
doc_to_decontamination_query
:
!function
../styles.template_03
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_03/c.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_03
task
:
boolq_alt_ov_03c
doc_to_text
:
!function
../styles.template_03
doc_to_choice
:
!function
../styles.choice_03c
doc_to_decontamination_query
:
!function
../styles.template_03
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_04/a.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_04
task
:
boolq_alt_ov_04a
doc_to_text
:
!function
../styles.template_04
doc_to_choice
:
!function
../styles.choice_04a
doc_to_decontamination_query
:
!function
../styles.template_04
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_04/b.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_04
task
:
boolq_alt_ov_04b
doc_to_text
:
!function
../styles.template_04
doc_to_choice
:
!function
../styles.choice_04b
doc_to_decontamination_query
:
!function
../styles.template_04
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_04/c.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_04
task
:
boolq_alt_ov_04c
doc_to_text
:
!function
../styles.template_04
doc_to_choice
:
!function
../styles.choice_04c
doc_to_decontamination_query
:
!function
../styles.template_04
lm_eval/tasks/super_glue/boolq/alternative_worlds/output_variation/style_05/a.yaml
deleted
100644 → 0
View file @
c0d5a660
include
:
../_boolq_alt_ov_yaml
group
:
boolq_alt_ov_05
task
:
boolq_alt_ov_05a
doc_to_text
:
!function
../styles.template_05
doc_to_choice
:
!function
../styles.choice_05a
doc_to_decontamination_query
:
!function
../styles.template_05
Prev
1
…
4
5
6
7
8
9
10
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