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
8c997e53
Commit
8c997e53
authored
May 03, 2022
by
jon-tow
Browse files
Revert `tests/testdata` changes and address flake8 issues
parent
d95a4333
Changes
627
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
20 additions
and
20 deletions
+20
-20
tests/testdata/pile_youtubesubtitles-v1-res.json
tests/testdata/pile_youtubesubtitles-v1-res.json
+1
-1
tests/testdata/piqa-v0-loglikelihood
tests/testdata/piqa-v0-loglikelihood
+1
-1
tests/testdata/piqa-v0-res.json
tests/testdata/piqa-v0-res.json
+1
-1
tests/testdata/prost-v0-loglikelihood
tests/testdata/prost-v0-loglikelihood
+1
-1
tests/testdata/prost-v0-res.json
tests/testdata/prost-v0-res.json
+1
-1
tests/testdata/pubmedqa-v0-loglikelihood
tests/testdata/pubmedqa-v0-loglikelihood
+1
-1
tests/testdata/pubmedqa-v0-res.json
tests/testdata/pubmedqa-v0-res.json
+1
-1
tests/testdata/qa4mre_2011-v0-loglikelihood
tests/testdata/qa4mre_2011-v0-loglikelihood
+1
-1
tests/testdata/qa4mre_2011-v0-res.json
tests/testdata/qa4mre_2011-v0-res.json
+1
-1
tests/testdata/qa4mre_2012-v0-loglikelihood
tests/testdata/qa4mre_2012-v0-loglikelihood
+1
-1
tests/testdata/qa4mre_2012-v0-res.json
tests/testdata/qa4mre_2012-v0-res.json
+1
-1
tests/testdata/qa4mre_2013-v0-loglikelihood
tests/testdata/qa4mre_2013-v0-loglikelihood
+1
-1
tests/testdata/qa4mre_2013-v0-res.json
tests/testdata/qa4mre_2013-v0-res.json
+1
-1
tests/testdata/qnli-v0-loglikelihood
tests/testdata/qnli-v0-loglikelihood
+1
-1
tests/testdata/qnli-v0-res.json
tests/testdata/qnli-v0-res.json
+1
-1
tests/testdata/qqp-v0-loglikelihood
tests/testdata/qqp-v0-loglikelihood
+1
-1
tests/testdata/qqp-v0-res.json
tests/testdata/qqp-v0-res.json
+1
-1
tests/testdata/race-v0-loglikelihood
tests/testdata/race-v0-loglikelihood
+1
-1
tests/testdata/race-v0-res.json
tests/testdata/race-v0-res.json
+1
-1
tests/testdata/random_insertion-v0-greedy_until
tests/testdata/random_insertion-v0-greedy_until
+1
-1
No files found.
tests/testdata/pile_youtubesubtitles-v1-res.json
View file @
8c997e53
{
"results"
:
{
"pile_youtubesubtitles"
:
{
"bits_per_byte"
:
3.3827117222045906e-05
,
"byte_perplexity"
:
1.000023447445816
,
"word_perplexity"
:
1.0001529192262875
}},
"versions"
:
{
"pile_youtubesubtitles"
:
1
}}
{
"results"
:
{
"pile_youtubesubtitles"
:
{
"bits_per_byte"
:
3.3827117222045906e-05
,
"byte_perplexity"
:
1.000023447445816
,
"word_perplexity"
:
1.0001529192262875
}},
"versions"
:
{
"pile_youtubesubtitles"
:
1
}}
\ No newline at end of file
tests/testdata/piqa-v0-loglikelihood
View file @
8c997e53
6048a3a2bb3ad1e6a3d98139618e06b4d7de766edd685bd38837596199c3f69f
6048a3a2bb3ad1e6a3d98139618e06b4d7de766edd685bd38837596199c3f69f
\ No newline at end of file
tests/testdata/piqa-v0-res.json
View file @
8c997e53
{
"results"
:
{
"piqa"
:
{
"acc"
:
0.514145810663765
,
"acc_norm"
:
0.5114254624591947
,
"acc_norm_stderr"
:
0.01166277802645167
,
"acc_stderr"
:
0.011661154475524836
}},
"versions"
:
{
"piqa"
:
0
}}
{
"results"
:
{
"piqa"
:
{
"acc"
:
0.514145810663765
,
"acc_norm"
:
0.5114254624591947
,
"acc_norm_stderr"
:
0.01166277802645167
,
"acc_stderr"
:
0.011661154475524836
}},
"versions"
:
{
"piqa"
:
0
}}
\ No newline at end of file
tests/testdata/prost-v0-loglikelihood
View file @
8c997e53
7c475f5b36a8b79f94c2be035441e7fd59dac021b0713b1fc72d256424c70b0b
7c475f5b36a8b79f94c2be035441e7fd59dac021b0713b1fc72d256424c70b0b
\ No newline at end of file
tests/testdata/prost-v0-res.json
View file @
8c997e53
{
"results"
:
{
"prost"
:
{
"acc"
:
0.24631725021349274
,
"acc_norm"
:
0.2581127241673783
,
"acc_norm_stderr"
:
0.00319703079646546
,
"acc_stderr"
:
0.003147855968061357
}},
"versions"
:
{
"prost"
:
0
}}
{
"results"
:
{
"prost"
:
{
"acc"
:
0.24631725021349274
,
"acc_norm"
:
0.2581127241673783
,
"acc_norm_stderr"
:
0.00319703079646546
,
"acc_stderr"
:
0.003147855968061357
}},
"versions"
:
{
"prost"
:
0
}}
\ No newline at end of file
tests/testdata/pubmedqa-v0-loglikelihood
View file @
8c997e53
7a04a1fb1d2b19db84fd15c224015d6c0306a41195a4e71fe6abd48fb4d53b9f
7a04a1fb1d2b19db84fd15c224015d6c0306a41195a4e71fe6abd48fb4d53b9f
\ No newline at end of file
tests/testdata/pubmedqa-v0-res.json
View file @
8c997e53
{
"results"
:
{
"pubmedqa"
:
{
"acc"
:
0.324
,
"acc_stderr"
:
0.01480686473373886
}},
"versions"
:
{
"pubmedqa"
:
0
}}
{
"results"
:
{
"pubmedqa"
:
{
"acc"
:
0.324
,
"acc_stderr"
:
0.01480686473373886
}},
"versions"
:
{
"pubmedqa"
:
0
}}
\ No newline at end of file
tests/testdata/qa4mre_2011-v0-loglikelihood
View file @
8c997e53
0d09f17c65768e797633494d2d218e4e46a26f718cab8b0bf3d156b073a8c437
0d09f17c65768e797633494d2d218e4e46a26f718cab8b0bf3d156b073a8c437
\ No newline at end of file
tests/testdata/qa4mre_2011-v0-res.json
View file @
8c997e53
{
"results"
:
{
"qa4mre_2011"
:
{
"acc"
:
0.225
,
"acc_norm"
:
0.23333333333333334
,
"acc_norm_stderr"
:
0.03877199986918664
,
"acc_stderr"
:
0.0382797091741014
}},
"versions"
:
{
"qa4mre_2011"
:
0
}}
{
"results"
:
{
"qa4mre_2011"
:
{
"acc"
:
0.225
,
"acc_norm"
:
0.23333333333333334
,
"acc_norm_stderr"
:
0.03877199986918664
,
"acc_stderr"
:
0.0382797091741014
}},
"versions"
:
{
"qa4mre_2011"
:
0
}}
\ No newline at end of file
tests/testdata/qa4mre_2012-v0-loglikelihood
View file @
8c997e53
7e17261820acb365966cb9431d93aec983b14393eaeefbc96e30a11cf58bc6df
7e17261820acb365966cb9431d93aec983b14393eaeefbc96e30a11cf58bc6df
\ No newline at end of file
tests/testdata/qa4mre_2012-v0-res.json
View file @
8c997e53
{
"results"
:
{
"qa4mre_2012"
:
{
"acc"
:
0.15625
,
"acc_norm"
:
0.16875
,
"acc_norm_stderr"
:
0.029702236908328808
,
"acc_stderr"
:
0.02879508360159146
}},
"versions"
:
{
"qa4mre_2012"
:
0
}}
{
"results"
:
{
"qa4mre_2012"
:
{
"acc"
:
0.15625
,
"acc_norm"
:
0.16875
,
"acc_norm_stderr"
:
0.029702236908328808
,
"acc_stderr"
:
0.02879508360159146
}},
"versions"
:
{
"qa4mre_2012"
:
0
}}
\ No newline at end of file
tests/testdata/qa4mre_2013-v0-loglikelihood
View file @
8c997e53
52fc431e94c67f983e28ebc70cf45e6c14116b0ae77dc1bf22347c705a65d054
52fc431e94c67f983e28ebc70cf45e6c14116b0ae77dc1bf22347c705a65d054
\ No newline at end of file
tests/testdata/qa4mre_2013-v0-res.json
View file @
8c997e53
{
"results"
:
{
"qa4mre_2013"
:
{
"acc"
:
0.18309859154929578
,
"acc_norm"
:
0.22183098591549297
,
"acc_norm_stderr"
:
0.02469760575535269
,
"acc_stderr"
:
0.022989742475464973
}},
"versions"
:
{
"qa4mre_2013"
:
0
}}
{
"results"
:
{
"qa4mre_2013"
:
{
"acc"
:
0.18309859154929578
,
"acc_norm"
:
0.22183098591549297
,
"acc_norm_stderr"
:
0.02469760575535269
,
"acc_stderr"
:
0.022989742475464973
}},
"versions"
:
{
"qa4mre_2013"
:
0
}}
\ No newline at end of file
tests/testdata/qnli-v0-loglikelihood
View file @
8c997e53
4281d4ff5cf1244358b0ea0220c67863c69fbade850696b43e8ff05138e01e12
4281d4ff5cf1244358b0ea0220c67863c69fbade850696b43e8ff05138e01e12
\ No newline at end of file
tests/testdata/qnli-v0-res.json
View file @
8c997e53
{
"results"
:
{
"qnli"
:
{
"acc"
:
0.5108914515833791
,
"acc_stderr"
:
0.00676380528502966
}},
"versions"
:
{
"qnli"
:
0
}}
{
"results"
:
{
"qnli"
:
{
"acc"
:
0.5108914515833791
,
"acc_stderr"
:
0.00676380528502966
}},
"versions"
:
{
"qnli"
:
0
}}
\ No newline at end of file
tests/testdata/qqp-v0-loglikelihood
View file @
8c997e53
97b551b0fc3d239aad4929a2e8e79c986891aefd9fcd19441fea0382d507889e
97b551b0fc3d239aad4929a2e8e79c986891aefd9fcd19441fea0382d507889e
\ No newline at end of file
tests/testdata/qqp-v0-res.json
View file @
8c997e53
{
"results"
:
{
"qqp"
:
{
"acc"
:
0.49782339846648527
,
"acc_stderr"
:
0.0024866770696239894
,
"f1"
:
0.42322661288031593
,
"f1_stderr"
:
0.002695903831328166
}},
"versions"
:
{
"qqp"
:
0
}}
{
"results"
:
{
"qqp"
:
{
"acc"
:
0.49782339846648527
,
"acc_stderr"
:
0.0024866770696239894
,
"f1"
:
0.42322661288031593
,
"f1_stderr"
:
0.002695903831328166
}},
"versions"
:
{
"qqp"
:
0
}}
\ No newline at end of file
tests/testdata/race-v0-loglikelihood
View file @
8c997e53
bdfdfab7fa1c7af0c1e161785e347b1b8071a15cbf971f6f2a9ae8c8e845199f
bdfdfab7fa1c7af0c1e161785e347b1b8071a15cbf971f6f2a9ae8c8e845199f
\ No newline at end of file
tests/testdata/race-v0-res.json
View file @
8c997e53
{
"results"
:
{
"race"
:
{
"acc"
:
0.23253588516746412
,
"acc_stderr"
:
0.013074460615265295
}},
"versions"
:
{
"race"
:
0
}}
{
"results"
:
{
"race"
:
{
"acc"
:
0.23253588516746412
,
"acc_stderr"
:
0.013074460615265295
}},
"versions"
:
{
"race"
:
0
}}
\ No newline at end of file
tests/testdata/random_insertion-v0-greedy_until
View file @
8c997e53
6c48baa6924f3635120f33062251c4b571b3d4e9fe46b14d91f54ddd1c857997
6c48baa6924f3635120f33062251c4b571b3d4e9fe46b14d91f54ddd1c857997
\ No newline at end of file
Prev
1
…
22
23
24
25
26
27
28
29
30
…
32
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