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
5f48dfc2
Commit
5f48dfc2
authored
Dec 21, 2021
by
Igor Ostrovsky
Browse files
Add BLiMP
parent
df5d7cf0
Changes
138
Hide whitespace changes
Inline
Side-by-side
Showing
18 changed files
with
18 additions
and
0 deletions
+18
-0
tests/tests/testdata/blimp_transitive-v0-loglikelihood
tests/tests/testdata/blimp_transitive-v0-loglikelihood
+1
-0
tests/tests/testdata/blimp_transitive-v0-res.json
tests/tests/testdata/blimp_transitive-v0-res.json
+1
-0
tests/tests/testdata/blimp_wh_island-v0-loglikelihood
tests/tests/testdata/blimp_wh_island-v0-loglikelihood
+1
-0
tests/tests/testdata/blimp_wh_island-v0-res.json
tests/tests/testdata/blimp_wh_island-v0-res.json
+1
-0
tests/tests/testdata/blimp_wh_questions_object_gap-v0-loglikelihood
...s/testdata/blimp_wh_questions_object_gap-v0-loglikelihood
+1
-0
tests/tests/testdata/blimp_wh_questions_object_gap-v0-res.json
.../tests/testdata/blimp_wh_questions_object_gap-v0-res.json
+1
-0
tests/tests/testdata/blimp_wh_questions_subject_gap-v0-loglikelihood
.../testdata/blimp_wh_questions_subject_gap-v0-loglikelihood
+1
-0
tests/tests/testdata/blimp_wh_questions_subject_gap-v0-res.json
...tests/testdata/blimp_wh_questions_subject_gap-v0-res.json
+1
-0
tests/tests/testdata/blimp_wh_questions_subject_gap_long_distance-v0-loglikelihood
...p_wh_questions_subject_gap_long_distance-v0-loglikelihood
+1
-0
tests/tests/testdata/blimp_wh_questions_subject_gap_long_distance-v0-res.json
.../blimp_wh_questions_subject_gap_long_distance-v0-res.json
+1
-0
tests/tests/testdata/blimp_wh_vs_that_no_gap-v0-loglikelihood
...s/tests/testdata/blimp_wh_vs_that_no_gap-v0-loglikelihood
+1
-0
tests/tests/testdata/blimp_wh_vs_that_no_gap-v0-res.json
tests/tests/testdata/blimp_wh_vs_that_no_gap-v0-res.json
+1
-0
tests/tests/testdata/blimp_wh_vs_that_no_gap_long_distance-v0-loglikelihood
...ta/blimp_wh_vs_that_no_gap_long_distance-v0-loglikelihood
+1
-0
tests/tests/testdata/blimp_wh_vs_that_no_gap_long_distance-v0-res.json
...estdata/blimp_wh_vs_that_no_gap_long_distance-v0-res.json
+1
-0
tests/tests/testdata/blimp_wh_vs_that_with_gap-v0-loglikelihood
...tests/testdata/blimp_wh_vs_that_with_gap-v0-loglikelihood
+1
-0
tests/tests/testdata/blimp_wh_vs_that_with_gap-v0-res.json
tests/tests/testdata/blimp_wh_vs_that_with_gap-v0-res.json
+1
-0
tests/tests/testdata/blimp_wh_vs_that_with_gap_long_distance-v0-loglikelihood
.../blimp_wh_vs_that_with_gap_long_distance-v0-loglikelihood
+1
-0
tests/tests/testdata/blimp_wh_vs_that_with_gap_long_distance-v0-res.json
...tdata/blimp_wh_vs_that_with_gap_long_distance-v0-res.json
+1
-0
No files found.
tests/tests/testdata/blimp_transitive-v0-loglikelihood
0 → 100644
View file @
5f48dfc2
d0d47fe40a7ee558ba782edbc4f49f7d9123c8472a36decc97f8ab142b45b9d8
\ No newline at end of file
tests/tests/testdata/blimp_transitive-v0-res.json
0 → 100644
View file @
5f48dfc2
{
"results"
:
{
"blimp_transitive"
:
{
"acc"
:
0.485
,
"acc_stderr"
:
0.0158121796418149
}},
"versions"
:
{
"blimp_transitive"
:
0
}}
\ No newline at end of file
tests/tests/testdata/blimp_wh_island-v0-loglikelihood
0 → 100644
View file @
5f48dfc2
91a9e4b60b0f3572a7fdbd7648d0e69f36e5eb34db715315b0082558d7ed8b65
\ No newline at end of file
tests/tests/testdata/blimp_wh_island-v0-res.json
0 → 100644
View file @
5f48dfc2
{
"results"
:
{
"blimp_wh_island"
:
{
"acc"
:
0.485
,
"acc_stderr"
:
0.0158121796418149
}},
"versions"
:
{
"blimp_wh_island"
:
0
}}
\ No newline at end of file
tests/tests/testdata/blimp_wh_questions_object_gap-v0-loglikelihood
0 → 100644
View file @
5f48dfc2
4d4aaa0274ccd485ff8430ed61b8f83806febe18c16616c7d050f637a0463eba
\ No newline at end of file
tests/tests/testdata/blimp_wh_questions_object_gap-v0-res.json
0 → 100644
View file @
5f48dfc2
{
"results"
:
{
"blimp_wh_questions_object_gap"
:
{
"acc"
:
0.485
,
"acc_stderr"
:
0.0158121796418149
}},
"versions"
:
{
"blimp_wh_questions_object_gap"
:
0
}}
\ No newline at end of file
tests/tests/testdata/blimp_wh_questions_subject_gap-v0-loglikelihood
0 → 100644
View file @
5f48dfc2
d5486ffcc075cad4302e37ece9bbf5b2063c0b5a48e76c8e1dd365e22a5a48fc
\ No newline at end of file
tests/tests/testdata/blimp_wh_questions_subject_gap-v0-res.json
0 → 100644
View file @
5f48dfc2
{
"results"
:
{
"blimp_wh_questions_subject_gap"
:
{
"acc"
:
0.485
,
"acc_stderr"
:
0.0158121796418149
}},
"versions"
:
{
"blimp_wh_questions_subject_gap"
:
0
}}
\ No newline at end of file
tests/tests/testdata/blimp_wh_questions_subject_gap_long_distance-v0-loglikelihood
0 → 100644
View file @
5f48dfc2
37483dfda688b62ad27161c9fc1e1e7710c5a6e6a7cd3474df119bcafd30e97f
\ No newline at end of file
tests/tests/testdata/blimp_wh_questions_subject_gap_long_distance-v0-res.json
0 → 100644
View file @
5f48dfc2
{
"results"
:
{
"blimp_wh_questions_subject_gap_long_distance"
:
{
"acc"
:
0.485
,
"acc_stderr"
:
0.0158121796418149
}},
"versions"
:
{
"blimp_wh_questions_subject_gap_long_distance"
:
0
}}
\ No newline at end of file
tests/tests/testdata/blimp_wh_vs_that_no_gap-v0-loglikelihood
0 → 100644
View file @
5f48dfc2
d1d3e439b2020ef5ed232bfebbcc9634adc5117e9eb61e38fdbbe2c8ea128d54
\ No newline at end of file
tests/tests/testdata/blimp_wh_vs_that_no_gap-v0-res.json
0 → 100644
View file @
5f48dfc2
{
"results"
:
{
"blimp_wh_vs_that_no_gap"
:
{
"acc"
:
0.485
,
"acc_stderr"
:
0.0158121796418149
}},
"versions"
:
{
"blimp_wh_vs_that_no_gap"
:
0
}}
\ No newline at end of file
tests/tests/testdata/blimp_wh_vs_that_no_gap_long_distance-v0-loglikelihood
0 → 100644
View file @
5f48dfc2
a142cc2a6fcd93230b650927b07367cad957b8f3f42cb4072151da53dea301df
\ No newline at end of file
tests/tests/testdata/blimp_wh_vs_that_no_gap_long_distance-v0-res.json
0 → 100644
View file @
5f48dfc2
{
"results"
:
{
"blimp_wh_vs_that_no_gap_long_distance"
:
{
"acc"
:
0.485
,
"acc_stderr"
:
0.0158121796418149
}},
"versions"
:
{
"blimp_wh_vs_that_no_gap_long_distance"
:
0
}}
\ No newline at end of file
tests/tests/testdata/blimp_wh_vs_that_with_gap-v0-loglikelihood
0 → 100644
View file @
5f48dfc2
d41a9b85e4c31e445bf9b46b8642df02203ccc02b4a9b254bf76066d5c54b4b7
\ No newline at end of file
tests/tests/testdata/blimp_wh_vs_that_with_gap-v0-res.json
0 → 100644
View file @
5f48dfc2
{
"results"
:
{
"blimp_wh_vs_that_with_gap"
:
{
"acc"
:
0.485
,
"acc_stderr"
:
0.0158121796418149
}},
"versions"
:
{
"blimp_wh_vs_that_with_gap"
:
0
}}
\ No newline at end of file
tests/tests/testdata/blimp_wh_vs_that_with_gap_long_distance-v0-loglikelihood
0 → 100644
View file @
5f48dfc2
eed67491bdf493a1dad8f1d9766bc7bd0e79946365b833c0f7eb81ac998e3dca
\ No newline at end of file
tests/tests/testdata/blimp_wh_vs_that_with_gap_long_distance-v0-res.json
0 → 100644
View file @
5f48dfc2
{
"results"
:
{
"blimp_wh_vs_that_with_gap_long_distance"
:
{
"acc"
:
0.485
,
"acc_stderr"
:
0.0158121796418149
}},
"versions"
:
{
"blimp_wh_vs_that_with_gap_long_distance"
:
0
}}
\ No newline at end of file
Prev
1
…
3
4
5
6
7
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