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

Merge branch 'master' of github.com:EleutherAI/lm-evaluation-harness into evaluator-description-option

tests/testdata/pile_youtubesubtitles-v1-loglikelihood_rolling

+68263c52adc0086011e2220b619983935cabb1cc1f5f9f8ee1a74ab2a7457967
\ No newline at end of file

tests/testdata/pile_youtubesubtitles-v1-res.json

+{"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/wikitext-v1-loglikelihood_rolling

+b6f83e6cf7535ee41b0057c3e2ec2cf7f2fa5a9119b305c479a83091d1142b2c
\ No newline at end of file

tests/testdata/wikitext-v1-res.json

+{"results": {"wikitext": {"bits_per_byte": 3.202519859941674e-05, "byte_perplexity": 1.0000221984224973, "word_perplexity": 1.000118710696617}}, "versions": {"wikitext": 1}}
\ No newline at end of file

tests/testdata/wnli-v1-loglikelihood

+8a0f81661d2ab2334bbc8031fac31c0c8882f1d9271dd51599d21dfdbb726dea
\ No newline at end of file

tests/testdata/wnli-v1-res.json

+{"results": {"wnli": {"acc": 0.5633802816901409, "acc_stderr": 0.0592793555841297}}, "versions": {"wnli": 1}}
\ No newline at end of file

tests/tests/testdata/blimp_adjunct_island-v0-loglikelihood

+976a5cac4bdb724632eebd4cb9e522203ce3da8d5525288a597c86e80469f3f2
\ No newline at end of file

tests/tests/testdata/blimp_adjunct_island-v0-res.json

+{"results": {"blimp_adjunct_island": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_adjunct_island": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_anaphor_gender_agreement-v0-loglikelihood

+2d8964e56a17661502ecf3f09c0befba63915360ddf2145b0bd845816950515d
\ No newline at end of file

tests/tests/testdata/blimp_anaphor_gender_agreement-v0-res.json

+{"results": {"blimp_anaphor_gender_agreement": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_anaphor_gender_agreement": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_anaphor_number_agreement-v0-loglikelihood

+0bdad31c974ba064e1f1ba931841ec2ba7461e8b0ca54ea5f79f08b6bae0bab5
\ No newline at end of file

tests/tests/testdata/blimp_anaphor_number_agreement-v0-res.json

+{"results": {"blimp_anaphor_number_agreement": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_anaphor_number_agreement": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_animate_subject_passive-v0-loglikelihood

+064c38fcd072b8bd12f54ea4f8e41599ed4e11dc386e93b77e1fc07967d1f960
\ No newline at end of file

tests/tests/testdata/blimp_animate_subject_passive-v0-res.json

+{"results": {"blimp_animate_subject_passive": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_animate_subject_passive": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_animate_subject_trans-v0-loglikelihood

+2a84231e7b79f517427e57e2099c88fed3d60a7efab4ef9506e263b4091d5cfa
\ No newline at end of file

tests/tests/testdata/blimp_animate_subject_trans-v0-res.json

+{"results": {"blimp_animate_subject_trans": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_animate_subject_trans": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_causative-v0-loglikelihood

+3d67ad025185dbb0808ebd7f508edcb5750c18fc3c01ad91f20fda80780c916c
\ No newline at end of file

tests/tests/testdata/blimp_causative-v0-res.json

+{"results": {"blimp_causative": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_causative": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_complex_NP_island-v0-loglikelihood

+f46cfcc7e43050a235fd2a6b989cabbfbcce76786df74db9f0d4a9cd1caa1628
\ No newline at end of file

tests/tests/testdata/blimp_complex_NP_island-v0-res.json

+{"results": {"blimp_complex_NP_island": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_complex_NP_island": 0}}
\ No newline at end of file