Merge branch 'master' of https://github.com/EleutherAI/lm-evaluation-harness into task-guide

tests/testdata/pile_ubuntu-irc-v0-res.json

+{"results": {"pile_ubuntu-irc": {"bits_per_byte": 1.6298315496830533e-06, "byte_perplexity": 1.0000016298328778, "word_perplexity": 1.0000108866656874}}, "versions": {"pile_ubuntu-irc": 0}}
\ No newline at end of file

tests/testdata/pile_uspto-v0-loglikelihood_rolling

+789b2bdb31564d512b70f801316f49320a26c83ba361226bac0afb255341d477
\ No newline at end of file

tests/testdata/pile_uspto-v0-res.json

+{"results": {"pile_uspto": {"bits_per_byte": 0.00012062434384130924, "byte_perplexity": 1.00012063161925, "word_perplexity": 1.0007716198916954}}, "versions": {"pile_uspto": 0}}
\ No newline at end of file

tests/testdata/pile_wikipedia-v0-loglikelihood_rolling

+ef9ec0dd408316ca6537228a6812e839f14b30608973081d41efc47c138338da
\ No newline at end of file

tests/testdata/pile_wikipedia-v0-res.json

+{"results": {"pile_wikipedia": {"bits_per_byte": 0.00016834722287561703, "byte_perplexity": 1.0001683613940646, "word_perplexity": 1.001084677949439}}, "versions": {"pile_wikipedia": 0}}
\ No newline at end of file

tests/testdata/pile_youtubesubtitles-v0-loglikelihood_rolling

+68263c52adc0086011e2220b619983935cabb1cc1f5f9f8ee1a74ab2a7457967
\ No newline at end of file

tests/testdata/pile_youtubesubtitles-v0-res.json

+{"results": {"pile_youtubesubtitles": {"bits_per_byte": 2.3447170928931888e-05, "byte_perplexity": 1.000023447445816, "word_perplexity": 1.0001529192262875}}, "versions": {"pile_youtubesubtitles": 0}}
\ No newline at end of file

tests/testdata/piqa-v0-loglikelihood

+6048a3a2bb3ad1e6a3d98139618e06b4d7de766edd685bd38837596199c3f69f
\ No newline at end of file

tests/testdata/piqa-v0-res.json

+{"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

+7c475f5b36a8b79f94c2be035441e7fd59dac021b0713b1fc72d256424c70b0b
\ No newline at end of file

tests/testdata/prost-v0-res.json

+{"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

+7a04a1fb1d2b19db84fd15c224015d6c0306a41195a4e71fe6abd48fb4d53b9f
\ No newline at end of file

tests/testdata/pubmedqa-v0-res.json

+{"results": {"pubmedqa": {"acc": 0.324, "acc_stderr": 0.01480686473373886}}, "versions": {"pubmedqa": 0}}
\ No newline at end of file

tests/testdata/qa4mre_2011-v0-loglikelihood

+0d09f17c65768e797633494d2d218e4e46a26f718cab8b0bf3d156b073a8c437
\ No newline at end of file

tests/testdata/qa4mre_2011-v0-res.json

+{"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

+7e17261820acb365966cb9431d93aec983b14393eaeefbc96e30a11cf58bc6df
\ No newline at end of file

tests/testdata/qa4mre_2012-v0-res.json

+{"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

+52fc431e94c67f983e28ebc70cf45e6c14116b0ae77dc1bf22347c705a65d054
\ No newline at end of file

tests/testdata/qa4mre_2013-v0-res.json

+{"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

+4281d4ff5cf1244358b0ea0220c67863c69fbade850696b43e8ff05138e01e12
\ No newline at end of file