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
c039c20e
Commit
c039c20e
authored
Jan 25, 2023
by
Dashiell Stander
Browse files
Merge branch 'master' into topk
parents
54ce0195
f9eca2c8
Changes
50
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
20 additions
and
0 deletions
+20
-0
tests/testdata/crows_pairs_english_religion-v0-loglikelihood
tests/testdata/crows_pairs_english_religion-v0-loglikelihood
+1
-0
tests/testdata/crows_pairs_english_religion-v0-res.json
tests/testdata/crows_pairs_english_religion-v0-res.json
+1
-0
tests/testdata/crows_pairs_english_sexual_orientation-v0-loglikelihood
...a/crows_pairs_english_sexual_orientation-v0-loglikelihood
+1
-0
tests/testdata/crows_pairs_english_sexual_orientation-v0-res.json
...stdata/crows_pairs_english_sexual_orientation-v0-res.json
+1
-0
tests/testdata/crows_pairs_english_socioeconomic-v0-loglikelihood
...stdata/crows_pairs_english_socioeconomic-v0-loglikelihood
+1
-0
tests/testdata/crows_pairs_english_socioeconomic-v0-res.json
tests/testdata/crows_pairs_english_socioeconomic-v0-res.json
+1
-0
tests/testdata/crows_pairs_french-v0-loglikelihood
tests/testdata/crows_pairs_french-v0-loglikelihood
+1
-0
tests/testdata/crows_pairs_french-v0-res.json
tests/testdata/crows_pairs_french-v0-res.json
+1
-0
tests/testdata/crows_pairs_french_age-v0-loglikelihood
tests/testdata/crows_pairs_french_age-v0-loglikelihood
+1
-0
tests/testdata/crows_pairs_french_age-v0-res.json
tests/testdata/crows_pairs_french_age-v0-res.json
+1
-0
tests/testdata/crows_pairs_french_autre-v0-loglikelihood
tests/testdata/crows_pairs_french_autre-v0-loglikelihood
+1
-0
tests/testdata/crows_pairs_french_autre-v0-res.json
tests/testdata/crows_pairs_french_autre-v0-res.json
+1
-0
tests/testdata/crows_pairs_french_disability-v0-loglikelihood
...s/testdata/crows_pairs_french_disability-v0-loglikelihood
+1
-0
tests/testdata/crows_pairs_french_disability-v0-res.json
tests/testdata/crows_pairs_french_disability-v0-res.json
+1
-0
tests/testdata/crows_pairs_french_gender-v0-loglikelihood
tests/testdata/crows_pairs_french_gender-v0-loglikelihood
+1
-0
tests/testdata/crows_pairs_french_gender-v0-res.json
tests/testdata/crows_pairs_french_gender-v0-res.json
+1
-0
tests/testdata/crows_pairs_french_nationality-v0-loglikelihood
.../testdata/crows_pairs_french_nationality-v0-loglikelihood
+1
-0
tests/testdata/crows_pairs_french_nationality-v0-res.json
tests/testdata/crows_pairs_french_nationality-v0-res.json
+1
-0
tests/testdata/crows_pairs_french_physical_appearance-v0-loglikelihood
...a/crows_pairs_french_physical_appearance-v0-loglikelihood
+1
-0
tests/testdata/crows_pairs_french_physical_appearance-v0-res.json
...stdata/crows_pairs_french_physical_appearance-v0-res.json
+1
-0
No files found.
tests/testdata/crows_pairs_english_religion-v0-loglikelihood
0 → 100644
View file @
c039c20e
2ed57377174adaf0fb30037eb055eafdd02cd46e57bc32066d5fecd90a14b6e1
\ No newline at end of file
tests/testdata/crows_pairs_english_religion-v0-res.json
0 → 100644
View file @
c039c20e
{
"results"
:
{
"crows_pairs_english_religion"
:
{
"likelihood_difference"
:
0.32170622542430666
,
"likelihood_difference_stderr"
:
0.022101541392310232
,
"pct_stereotype"
:
0.43243243243243246
,
"pct_stereotype_stderr"
:
0.04723583229758394
}},
"versions"
:
{
"crows_pairs_english_religion"
:
0
}}
\ No newline at end of file
tests/testdata/crows_pairs_english_sexual_orientation-v0-loglikelihood
0 → 100644
View file @
c039c20e
e754a309296b157677dfba6e6feef983d1ce38dd0169ae726265621a7b573163
\ No newline at end of file
tests/testdata/crows_pairs_english_sexual_orientation-v0-res.json
0 → 100644
View file @
c039c20e
{
"results"
:
{
"crows_pairs_english_sexual_orientation"
:
{
"likelihood_difference"
:
0.31947594049467243
,
"likelihood_difference_stderr"
:
0.024404952720497735
,
"pct_stereotype"
:
0.43010752688172044
,
"pct_stereotype_stderr"
:
0.051616798980291805
}},
"versions"
:
{
"crows_pairs_english_sexual_orientation"
:
0
}}
\ No newline at end of file
tests/testdata/crows_pairs_english_socioeconomic-v0-loglikelihood
0 → 100644
View file @
c039c20e
c309eabfd247a702e32efc4e08211f9a72693d38995be5dd444d497b476396bd
\ No newline at end of file
tests/testdata/crows_pairs_english_socioeconomic-v0-res.json
0 → 100644
View file @
c039c20e
{
"results"
:
{
"crows_pairs_english_socioeconomic"
:
{
"likelihood_difference"
:
0.3424577735757881
,
"likelihood_difference_stderr"
:
0.017459994170011896
,
"pct_stereotype"
:
0.46842105263157896
,
"pct_stereotype_stderr"
:
0.036297038088316094
}},
"versions"
:
{
"crows_pairs_english_socioeconomic"
:
0
}}
\ No newline at end of file
tests/testdata/crows_pairs_french-v0-loglikelihood
0 → 100644
View file @
c039c20e
4fb61dcf4d2c59d6470b297a01d5f429ee442864e225e1760fbf191b2a0901cd
\ No newline at end of file
tests/testdata/crows_pairs_french-v0-res.json
0 → 100644
View file @
c039c20e
{
"results"
:
{
"crows_pairs_french"
:
{
"likelihood_difference"
:
0.3367363060632734
,
"likelihood_difference_stderr"
:
0.005827747024053628
,
"pct_stereotype"
:
0.5062611806797853
,
"pct_stereotype_stderr"
:
0.012212341600228745
}},
"versions"
:
{
"crows_pairs_french"
:
0
}}
\ No newline at end of file
tests/testdata/crows_pairs_french_age-v0-loglikelihood
0 → 100644
View file @
c039c20e
b14a5769f415a234abe89063a1b546aa4a990c84217e5d4a697874cd7f85af35
\ No newline at end of file
tests/testdata/crows_pairs_french_age-v0-res.json
0 → 100644
View file @
c039c20e
{
"results"
:
{
"crows_pairs_french_age"
:
{
"likelihood_difference"
:
0.31896094607685194
,
"likelihood_difference_stderr"
:
0.024068391933540753
,
"pct_stereotype"
:
0.4444444444444444
,
"pct_stereotype_stderr"
:
0.05267171812666418
}},
"versions"
:
{
"crows_pairs_french_age"
:
0
}}
\ No newline at end of file
tests/testdata/crows_pairs_french_autre-v0-loglikelihood
0 → 100644
View file @
c039c20e
f145ad5086da0bf8c76f0730258529fa243efe32b7ab792d3c4716284b4b5495
\ No newline at end of file
tests/testdata/crows_pairs_french_autre-v0-res.json
0 → 100644
View file @
c039c20e
{
"results"
:
{
"crows_pairs_french_autre"
:
{
"likelihood_difference"
:
0.3517045997290783
,
"likelihood_difference_stderr"
:
0.07647821858130377
,
"pct_stereotype"
:
0.23076923076923078
,
"pct_stereotype_stderr"
:
0.12162606385262997
}},
"versions"
:
{
"crows_pairs_french_autre"
:
0
}}
\ No newline at end of file
tests/testdata/crows_pairs_french_disability-v0-loglikelihood
0 → 100644
View file @
c039c20e
fa1e5fc7492a66c9a90765e605003c38408347617db5ecf36706f1d374af5d42
\ No newline at end of file
tests/testdata/crows_pairs_french_disability-v0-res.json
0 → 100644
View file @
c039c20e
{
"results"
:
{
"crows_pairs_french_disability"
:
{
"likelihood_difference"
:
0.31387939561315326
,
"likelihood_difference_stderr"
:
0.027598132299657168
,
"pct_stereotype"
:
0.36363636363636365
,
"pct_stereotype_stderr"
:
0.05966637484671758
}},
"versions"
:
{
"crows_pairs_french_disability"
:
0
}}
\ No newline at end of file
tests/testdata/crows_pairs_french_gender-v0-loglikelihood
0 → 100644
View file @
c039c20e
010b8404655911c86555616da23afffce9dc3981e1acbbfdb022d9c474430209
\ No newline at end of file
tests/testdata/crows_pairs_french_gender-v0-res.json
0 → 100644
View file @
c039c20e
{
"results"
:
{
"crows_pairs_french_gender"
:
{
"likelihood_difference"
:
0.3364019171359413
,
"likelihood_difference_stderr"
:
0.012815700745990895
,
"pct_stereotype"
:
0.4766355140186916
,
"pct_stereotype_stderr"
:
0.027920316348204986
}},
"versions"
:
{
"crows_pairs_french_gender"
:
0
}}
\ No newline at end of file
tests/testdata/crows_pairs_french_nationality-v0-loglikelihood
0 → 100644
View file @
c039c20e
146eb60c8796fe3f25307a6776337f0b077b58ce02edec64c99df4b906c19b9f
\ No newline at end of file
tests/testdata/crows_pairs_french_nationality-v0-res.json
0 → 100644
View file @
c039c20e
{
"results"
:
{
"crows_pairs_french_nationality"
:
{
"likelihood_difference"
:
0.33534193269044926
,
"likelihood_difference_stderr"
:
0.01429836309463257
,
"pct_stereotype"
:
0.4743083003952569
,
"pct_stereotype_stderr"
:
0.031455431847992904
}},
"versions"
:
{
"crows_pairs_french_nationality"
:
0
}}
\ No newline at end of file
tests/testdata/crows_pairs_french_physical_appearance-v0-loglikelihood
0 → 100644
View file @
c039c20e
ea61eaad64e9292790d4bbef955ffeebed7a595de098bc5ac726a6e51f27f9af
\ No newline at end of file
tests/testdata/crows_pairs_french_physical_appearance-v0-res.json
0 → 100644
View file @
c039c20e
{
"results"
:
{
"crows_pairs_french_physical_appearance"
:
{
"likelihood_difference"
:
0.3221673223187262
,
"likelihood_difference_stderr"
:
0.026978346460100555
,
"pct_stereotype"
:
0.4027777777777778
,
"pct_stereotype_stderr"
:
0.05820650942569533
}},
"versions"
:
{
"crows_pairs_french_physical_appearance"
:
0
}}
\ No newline at end of file
Prev
1
2
3
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