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
de71ad92
Unverified
Commit
de71ad92
authored
Oct 17, 2023
by
Lintang Sutawika
Committed by
GitHub
Oct 17, 2023
Browse files
Merge branch 'big-refactor' into fix-unittests
parents
09d20bfa
73c80915
Changes
370
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
80 additions
and
0 deletions
+80
-0
lm_eval/tasks/bigbench/generate_until/similarities_abstraction.yaml
...sks/bigbench/generate_until/similarities_abstraction.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/simp_turing_concept.yaml
...al/tasks/bigbench/generate_until/simp_turing_concept.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json.yaml
...tasks/bigbench/generate_until/simple_arithmetic_json.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json_multiple_choice.yaml
...enerate_until/simple_arithmetic_json_multiple_choice.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json_subtasks.yaml
...bench/generate_until/simple_arithmetic_json_subtasks.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/simple_arithmetic_multiple_targets_json.yaml
...nerate_until/simple_arithmetic_multiple_targets_json.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/simple_ethical_questions.yaml
...sks/bigbench/generate_until/simple_ethical_questions.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/simple_text_editing.yaml
...al/tasks/bigbench/generate_until/simple_text_editing.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/snarks.yaml
lm_eval/tasks/bigbench/generate_until/snarks.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/social_iqa.yaml
lm_eval/tasks/bigbench/generate_until/social_iqa.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/social_support.yaml
lm_eval/tasks/bigbench/generate_until/social_support.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/sports_understanding.yaml
...l/tasks/bigbench/generate_until/sports_understanding.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/strange_stories.yaml
lm_eval/tasks/bigbench/generate_until/strange_stories.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/strategyqa.yaml
lm_eval/tasks/bigbench/generate_until/strategyqa.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/sufficient_information.yaml
...tasks/bigbench/generate_until/sufficient_information.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/suicide_risk.yaml
lm_eval/tasks/bigbench/generate_until/suicide_risk.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/swahili_english_proverbs.yaml
...sks/bigbench/generate_until/swahili_english_proverbs.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/swedish_to_german_proverbs.yaml
...s/bigbench/generate_until/swedish_to_german_proverbs.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/symbol_interpretation.yaml
.../tasks/bigbench/generate_until/symbol_interpretation.yaml
+4
-0
lm_eval/tasks/bigbench/generate_until/temporal_sequences.yaml
...val/tasks/bigbench/generate_until/temporal_sequences.yaml
+4
-0
No files found.
lm_eval/tasks/bigbench/g
reedy
_until/similarities_abstraction.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/similarities_abstraction.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
similarities_abstraction_zero_shot
dataset_name
:
similarities_abstraction_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_similarities_abstraction_g
reedy
_until
task
:
bigbench_similarities_abstraction_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/simp_turing_concept.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/simp_turing_concept.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
simp_turing_concept_zero_shot
dataset_name
:
simp_turing_concept_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_simp_turing_concept_g
reedy
_until
task
:
bigbench_simp_turing_concept_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/simple_arithmetic_json.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/simple_arithmetic_json.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
simple_arithmetic_json_zero_shot
dataset_name
:
simple_arithmetic_json_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_simple_arithmetic_json_g
reedy
_until
task
:
bigbench_simple_arithmetic_json_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/simple_arithmetic_json_multiple_choice.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/simple_arithmetic_json_multiple_choice.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
simple_arithmetic_json_multiple_choice_zero_shot
dataset_name
:
simple_arithmetic_json_multiple_choice_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_simple_arithmetic_json_multiple_choice_g
reedy
_until
task
:
bigbench_simple_arithmetic_json_multiple_choice_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/simple_arithmetic_json_subtasks.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/simple_arithmetic_json_subtasks.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
simple_arithmetic_json_subtasks_zero_shot
dataset_name
:
simple_arithmetic_json_subtasks_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_simple_arithmetic_json_subtasks_g
reedy
_until
task
:
bigbench_simple_arithmetic_json_subtasks_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/simple_arithmetic_multiple_targets_json.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/simple_arithmetic_multiple_targets_json.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
simple_arithmetic_multiple_targets_json_zero_shot
dataset_name
:
simple_arithmetic_multiple_targets_json_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_simple_arithmetic_multiple_targets_json_g
reedy
_until
task
:
bigbench_simple_arithmetic_multiple_targets_json_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/simple_ethical_questions.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/simple_ethical_questions.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
simple_ethical_questions_zero_shot
dataset_name
:
simple_ethical_questions_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_simple_ethical_questions_g
reedy
_until
task
:
bigbench_simple_ethical_questions_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/simple_text_editing.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/simple_text_editing.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
simple_text_editing_zero_shot
dataset_name
:
simple_text_editing_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_simple_text_editing_g
reedy
_until
task
:
bigbench_simple_text_editing_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/snarks.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/snarks.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
snarks_zero_shot
dataset_name
:
snarks_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_snarks_g
reedy
_until
task
:
bigbench_snarks_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/social_iqa.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/social_iqa.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
social_iqa_zero_shot
dataset_name
:
social_iqa_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_social_iqa_g
reedy
_until
task
:
bigbench_social_iqa_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/social_support.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/social_support.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
social_support_zero_shot
dataset_name
:
social_support_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_social_support_g
reedy
_until
task
:
bigbench_social_support_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/sports_understanding.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/sports_understanding.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
sports_understanding_zero_shot
dataset_name
:
sports_understanding_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_sports_understanding_g
reedy
_until
task
:
bigbench_sports_understanding_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/strange_stories.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/strange_stories.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
strange_stories_zero_shot
dataset_name
:
strange_stories_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_strange_stories_g
reedy
_until
task
:
bigbench_strange_stories_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/strategyqa.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/strategyqa.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
strategyqa_zero_shot
dataset_name
:
strategyqa_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_strategyqa_g
reedy
_until
task
:
bigbench_strategyqa_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/sufficient_information.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/sufficient_information.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
sufficient_information_zero_shot
dataset_name
:
sufficient_information_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_sufficient_information_g
reedy
_until
task
:
bigbench_sufficient_information_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/suicide_risk.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/suicide_risk.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
suicide_risk_zero_shot
dataset_name
:
suicide_risk_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_suicide_risk_g
reedy
_until
task
:
bigbench_suicide_risk_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/swahili_english_proverbs.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/swahili_english_proverbs.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
swahili_english_proverbs_zero_shot
dataset_name
:
swahili_english_proverbs_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_swahili_english_proverbs_g
reedy
_until
task
:
bigbench_swahili_english_proverbs_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/swedish_to_german_proverbs.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/swedish_to_german_proverbs.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
swedish_to_german_proverbs_zero_shot
dataset_name
:
swedish_to_german_proverbs_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_swedish_to_german_proverbs_g
reedy
_until
task
:
bigbench_swedish_to_german_proverbs_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/symbol_interpretation.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/symbol_interpretation.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
symbol_interpretation_zero_shot
dataset_name
:
symbol_interpretation_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_symbol_interpretation_g
reedy
_until
task
:
bigbench_symbol_interpretation_g
enerate
_until
lm_eval/tasks/bigbench/g
reedy
_until/temporal_sequences.yaml
→
lm_eval/tasks/bigbench/g
enerate
_until/temporal_sequences.yaml
View file @
de71ad92
# Generated by utils.py
# Generated by utils.py
dataset_name
:
temporal_sequences_zero_shot
dataset_name
:
temporal_sequences_zero_shot
include
:
../g
reedy
_until_template_yaml
include
:
../g
enerate
_until_template_yaml
task
:
bigbench_temporal_sequences_g
reedy
_until
task
:
bigbench_temporal_sequences_g
enerate
_until
Prev
1
…
11
12
13
14
15
16
17
18
19
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