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
ffc9e6a0
"Plugson/vscode:/vscode.git/clone" did not exist on "c896c03efed5a89bc3405f89e3ea60e00f841af3"
Commit
ffc9e6a0
authored
Jul 15, 2024
by
lintangsutawika
Browse files
udpate tasks
parent
86f3bb3d
Changes
100
Show whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
33 additions
and
32 deletions
+33
-32
lm_eval/tasks/afrimgsm/_afrimgsm.yaml
lm_eval/tasks/afrimgsm/_afrimgsm.yaml
+15
-0
lm_eval/tasks/afrimgsm/_afrimgsm_en_cot.yaml
lm_eval/tasks/afrimgsm/_afrimgsm_en_cot.yaml
+0
-0
lm_eval/tasks/afrimgsm/direct/_afrimgsm_direct.yaml
lm_eval/tasks/afrimgsm/direct/_afrimgsm_direct.yaml
+0
-4
lm_eval/tasks/afrimgsm/translate/_afrimgsm_translate.yaml
lm_eval/tasks/afrimgsm/translate/_afrimgsm_translate.yaml
+0
-4
lm_eval/tasks/afrimmlu/direct/_direct_yaml
lm_eval/tasks/afrimmlu/direct/_direct_yaml
+2
-4
lm_eval/tasks/afrimmlu/translate/_translate_yaml
lm_eval/tasks/afrimmlu/translate/_translate_yaml
+2
-3
lm_eval/tasks/afrixnli/anli_prompt/en-direct/_afrixnli_en_direct_yaml
...s/afrixnli/anli_prompt/en-direct/_afrixnli_en_direct_yaml
+1
-4
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_amh.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_amh.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_eng.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_eng.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_ewe.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_ewe.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_fra.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_fra.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_hau.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_hau.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_ibo.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_ibo.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_kin.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_kin.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_lin.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_lin.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_lug.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_lug.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_orm.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_orm.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_sna.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_sna.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_sot.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_sot.yaml
+1
-1
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_swa.yaml
...frixnli/anli_prompt/en-direct/afrixnli_en_direct_swa.yaml
+1
-1
No files found.
lm_eval/tasks/afrimgsm/_afrimgsm.yaml
0 → 100644
View file @
ffc9e6a0
group
:
afrimgsm
group_alias
:
AfriMGSM
task
:
-
group
:
afrimgsm_direct
group_alias
:
AfriMGSM
task
:
-
afrimgsm_direct_tasks
-
group
:
afrimgsm_translate
group_alias
:
AfriMGSM (Translate)
task
:
-
afrimgsm_translate_tasks
aggregate_metric_list
:
-
metric
:
acc
weight_by_size
:
False
num_fewshot
:
8
lm_eval/tasks/afrimgsm/
en_cot/
_afrimgsm_en_cot.yaml
→
lm_eval/tasks/afrimgsm/_afrimgsm_en_cot.yaml
View file @
ffc9e6a0
File moved
lm_eval/tasks/afrimgsm/direct/_afrimgsm_direct.yaml
deleted
100644 → 0
View file @
86f3bb3d
group
:
afrimgsm_direct
group_alias
:
AfriMGSM
task
:
-
afrimgsm_direct_tasks
\ No newline at end of file
lm_eval/tasks/afrimgsm/translate/_afrimgsm_translate.yaml
deleted
100644 → 0
View file @
86f3bb3d
group
:
afrimgsm_translate
group_alias
:
AfriMGSM (Translate)
task
:
-
afrimgsm_translate_tasks
lm_eval/tasks/afrimmlu/direct/_direct_yaml
View file @
ffc9e6a0
group:
tag: afrimmlu_direct_tasks
- mmlu
- afrimmlu
- afrimmlu_direct
task: null
task: null
dataset_path: masakhane/afrimmlu
dataset_path: masakhane/afrimmlu
dataset_name: null
dataset_name: null
...
@@ -34,5 +31,6 @@ metric_list:
...
@@ -34,5 +31,6 @@ metric_list:
regexes_to_ignore:
regexes_to_ignore:
- ","
- ","
- "\\$"
- "\\$"
num_fewshot: 5
metadata:
metadata:
version: 1.0
version: 1.0
lm_eval/tasks/afrimmlu/translate/_translate_yaml
View file @
ffc9e6a0
group:
tag: afrimmlu_translate
- mmlu
- afrimmlu_translate
task: null
task: null
dataset_path: masakhane/afrimmlu-translate-test
dataset_path: masakhane/afrimmlu-translate-test
dataset_name: null
dataset_name: null
...
@@ -31,5 +29,6 @@ metric_list:
...
@@ -31,5 +29,6 @@ metric_list:
regexes_to_ignore:
regexes_to_ignore:
- ","
- ","
- "\\$"
- "\\$"
num_fewshot: 5
metadata:
metadata:
version: 1.0
version: 1.0
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_yaml
→
lm_eval/tasks/afrixnli/anli_prompt/en-direct/
_
afrixnli_en_direct_yaml
View file @
ffc9e6a0
group:
tag: afrixnli_en_direct
- xnli
- afrixnli
- afrixnli_en_direct
dataset_path: masakhane/afrixnli
dataset_path: masakhane/afrixnli
dataset_name: null
dataset_name: null
output_type: multiple_choice
output_type: multiple_choice
...
...
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_amh.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
amh
dataset_name
:
amh
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_amh
task
:
afrixnli_en_direct_amh
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_eng.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
eng
dataset_name
:
eng
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_eng
task
:
afrixnli_en_direct_eng
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_ewe.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
ewe
dataset_name
:
ewe
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_ewe
task
:
afrixnli_en_direct_ewe
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_fra.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
fra
dataset_name
:
fra
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_fra
task
:
afrixnli_en_direct_fra
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_hau.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
hau
dataset_name
:
hau
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_hau
task
:
afrixnli_en_direct_hau
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_ibo.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
ibo
dataset_name
:
ibo
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_ibo
task
:
afrixnli_en_direct_ibo
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_kin.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
kin
dataset_name
:
kin
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_kin
task
:
afrixnli_en_direct_kin
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_lin.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
lin
dataset_name
:
lin
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_lin
task
:
afrixnli_en_direct_lin
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_lug.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
lug
dataset_name
:
lug
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_lug
task
:
afrixnli_en_direct_lug
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_orm.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
orm
dataset_name
:
orm
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_orm
task
:
afrixnli_en_direct_orm
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_sna.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
sna
dataset_name
:
sna
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_sna
task
:
afrixnli_en_direct_sna
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_sot.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
sot
dataset_name
:
sot
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_sot
task
:
afrixnli_en_direct_sot
lm_eval/tasks/afrixnli/anli_prompt/en-direct/afrixnli_en_direct_swa.yaml
View file @
ffc9e6a0
# Generated by utils.py
# Generated by utils.py
dataset_name
:
swa
dataset_name
:
swa
include
:
afrixnli_en_direct_yaml
include
:
_
afrixnli_en_direct_yaml
task
:
afrixnli_en_direct_swa
task
:
afrixnli_en_direct_swa
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