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

tests/tests/testdata/blimp_determiner_noun_agreement_irregular_2-v0-loglikelihood

+ddb24ddfaebe076b3aa7107937d71bf5f4503a78283bc889e39200368603681e
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_irregular_2-v0-res.json

+{"results": {"blimp_determiner_noun_agreement_irregular_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_irregular_2": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_with_adj_2-v0-loglikelihood

+95acb74fac7d57ae2c9d208361a5f8ad36b0b19a055f02e648ed8e99505f4b43
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_with_adj_2-v0-res.json

+{"results": {"blimp_determiner_noun_agreement_with_adj_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_with_adj_2": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_1-v0-loglikelihood

+ad61c619aa79433d02f1aeacde2ab87291fd5d5c370032c24d41c4f0065ed1f9
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_1-v0-res.json

+{"results": {"blimp_determiner_noun_agreement_with_adj_irregular_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_with_adj_irregular_1": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_2-v0-loglikelihood

+ccc64b4d5e80c081d5161aae5828212ba49d277ca8c5a4281f181744727a6a99
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_2-v0-res.json

+{"results": {"blimp_determiner_noun_agreement_with_adj_irregular_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_with_adj_irregular_2": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_with_adjective_1-v0-loglikelihood

+007c47e5fbf88119c5180feef75e1345d448e56adcd4c7ab2d52fb8d67350d34
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_with_adjective_1-v0-res.json

+{"results": {"blimp_determiner_noun_agreement_with_adjective_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_with_adjective_1": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_distractor_agreement_relational_noun-v0-loglikelihood

+8aab641bd5933f84f46a14f5c1208a3c855cace7e67b44abcd5aff8fec96717d
\ No newline at end of file

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

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

tests/tests/testdata/blimp_distractor_agreement_relative_clause-v0-loglikelihood

+bf78e2b53c0f3531303c668c96bd3897a0a35e960da37439e63724ecba4e371a
\ No newline at end of file

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

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

tests/tests/testdata/blimp_drop_argument-v0-loglikelihood

+616109e63f162dcd31a632943e7ef0c9e0431afeb179e83e9b04b39007b16f5b
\ No newline at end of file

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

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

tests/tests/testdata/blimp_ellipsis_n_bar_1-v0-loglikelihood

+d14e4b7fcdd68991eb39b9cf3ade4b37dee9ddd39b688f861d81a327e47a969f
\ No newline at end of file

tests/tests/testdata/blimp_ellipsis_n_bar_1-v0-res.json

+{"results": {"blimp_ellipsis_n_bar_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_ellipsis_n_bar_1": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_ellipsis_n_bar_2-v0-loglikelihood

+0523771a217759f0b22b89807694ee7f6381ce98a584b1fd070ba96194a3273b
\ No newline at end of file

tests/tests/testdata/blimp_ellipsis_n_bar_2-v0-res.json

+{"results": {"blimp_ellipsis_n_bar_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_ellipsis_n_bar_2": 0}}
\ No newline at end of file