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
9701ef6e
Unverified
Commit
9701ef6e
authored
May 22, 2024
by
Jess
Committed by
GitHub
May 22, 2024
Browse files
Merge branch 'main' into africamgsm
parents
753e8670
fb142ccd
Changes
82
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
263 additions
and
0 deletions
+263
-0
lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_zul.yaml
...ks/afrimgsm/direct_native/afrimgsm_direct_native_zul.yaml
+12
-0
lm_eval/tasks/afrimgsm/direct_native/direct_native_yaml
lm_eval/tasks/afrimgsm/direct_native/direct_native_yaml
+35
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_amh.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_amh.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_eng.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_eng.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_ewe.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_ewe.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_fra.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_fra.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_hau.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_hau.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_ibo.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_ibo.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_kin.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_kin.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_lin.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_lin.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_lug.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_lug.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_orm.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_orm.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_sna.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_sna.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_sot.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_sot.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_swa.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_swa.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_twi.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_twi.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_wol.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_wol.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_xho.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_xho.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_yor.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_yor.yaml
+12
-0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_zul.yaml
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_zul.yaml
+12
-0
No files found.
lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_zul.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
zul
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nAnswer:"}}{%
else
%}{{"Question:
"+question+"\nAnswer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
direct_native_yaml
task
:
afrimgsm_direct_native_zul
lm_eval/tasks/afrimgsm/direct_native/direct_native_yaml
0 → 100644
View file @
9701ef6e
# This file will be included in the generated language-specific task configs.
# It doesn't have a yaml file extension as it is not meant to be imported directly
# by the harness.
group: afrimgsm_direct
dataset_path: masakhane/afrimgsm
dataset_name: null # Overridden by language-specific config.
output_type: generate_until
# training_split: train
test_split: test
target_delimiter: ""
generation_kwargs:
until:
- "\n\n"
- "\n"
do_sample: false
temperature: 0.0
filter_list:
- name: remove_whitespace
filter:
- function: remove_whitespace
- function: take_first
- filter:
- function: regex
group_select: -1
regex_pattern: (-?[$0-9.,]{2,})|(-?[0-9]+)
- function: take_first
name: flexible-extract
metric_list:
- metric: exact_match
aggregation: mean
higher_is_better: true
ignore_case: true
ignore_punctuation: true
metadata:
version: 2.0
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_amh.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
amh
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[15:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_amh
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_eng.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
eng
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_eng
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_ewe.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
ewe
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_ewe
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_fra.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
fra
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_fra
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_hau.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
hau
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_hau
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_ibo.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
ibo
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_ibo
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_kin.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
kin
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_kin
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_lin.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
lin
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_lin
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_lug.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
lug
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_lug
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_orm.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
orm
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_orm
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_sna.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
sna
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_sna
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_sot.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
sot
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_sot
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_swa.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
swa
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_swa
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_twi.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
twi
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_twi
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_wol.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
wol
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_wol
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_xho.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
xho
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_xho
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_yor.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
yor
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[16:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_yor
lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_zul.yaml
0 → 100644
View file @
9701ef6e
# Generated by utils.py
dataset_name
:
zul
doc_to_target
:
'
{%
if
answer
is
not
none
%}{{answer[21:]}}{%
else
%}{{answer_number|string}}{%
endif
%}'
doc_to_text
:
'
{%
if
answer
is
not
none
%}{{question+"\nStep-by-Step
Answer:"}}{%
else
%}{{"Question:
"+question+"\nStep-by-Step
Answer:"}}{%
endif
%}'
generation_kwargs
:
do_sample
:
false
until
:
-
'
Question:'
-
</s>
-
<|im_end|>
include
:
cot_yaml
task
:
afrimgsm_en_cot_zul
Prev
1
2
3
4
5
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