Revert `tests/testdata` changes and address flake8 issues

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

-{"results": {"blimp_causative": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_causative": 0}}
+{"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 → tests/testdata/blimp_complex_NP_island-v0-loglikelihood

-f46cfcc7e43050a235fd2a6b989cabbfbcce76786df74db9f0d4a9cd1caa1628
+f46cfcc7e43050a235fd2a6b989cabbfbcce76786df74db9f0d4a9cd1caa1628
\ No newline at end of file

tests/tests/testdata/blimp_complex_NP_island-v0-res.json → 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}}
+{"results": {"blimp_complex_NP_island": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_complex_NP_island": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_coordinate_structure_constraint_complex_left_branch-v0-loglikelihood → tests/testdata/blimp_coordinate_structure_constraint_complex_left_branch-v0-loglikelihood

-7e1cc5b9f71abfbe56c4bdf343a1e5632785b66a986b8e904a41ed8f45a2c33e
+7e1cc5b9f71abfbe56c4bdf343a1e5632785b66a986b8e904a41ed8f45a2c33e
\ No newline at end of file

tests/tests/testdata/blimp_coordinate_structure_constraint_complex_left_branch-v0-res.json → tests/testdata/blimp_coordinate_structure_constraint_complex_left_branch-v0-res.json

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

tests/tests/testdata/blimp_coordinate_structure_constraint_object_extraction-v0-loglikelihood → tests/testdata/blimp_coordinate_structure_constraint_object_extraction-v0-loglikelihood

-23ddafdff7b1ebe331b146e23b2c21aa109fe57aa1ce8ca201a0d239fcbdd166
+23ddafdff7b1ebe331b146e23b2c21aa109fe57aa1ce8ca201a0d239fcbdd166
\ No newline at end of file

tests/tests/testdata/blimp_coordinate_structure_constraint_object_extraction-v0-res.json → tests/testdata/blimp_coordinate_structure_constraint_object_extraction-v0-res.json

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

tests/tests/testdata/blimp_determiner_noun_agreement_1-v0-loglikelihood → tests/testdata/blimp_determiner_noun_agreement_1-v0-loglikelihood

-2df8cc7f17089f7e8c7d974dcb324c809d30ef059a5be22aed6b69f44230809f
+2df8cc7f17089f7e8c7d974dcb324c809d30ef059a5be22aed6b69f44230809f
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_1-v0-res.json → tests/testdata/blimp_determiner_noun_agreement_1-v0-res.json

-{"results": {"blimp_determiner_noun_agreement_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_1": 0}}
+{"results": {"blimp_determiner_noun_agreement_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_1": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_2-v0-loglikelihood → tests/testdata/blimp_determiner_noun_agreement_2-v0-loglikelihood

-123e2acd00fbba60aba1fbae607c79a062e512c9e79c7d8dfafff63e30111d76
+123e2acd00fbba60aba1fbae607c79a062e512c9e79c7d8dfafff63e30111d76
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_2-v0-res.json → tests/testdata/blimp_determiner_noun_agreement_2-v0-res.json

-{"results": {"blimp_determiner_noun_agreement_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_2": 0}}
+{"results": {"blimp_determiner_noun_agreement_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_2": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_irregular_1-v0-loglikelihood → tests/testdata/blimp_determiner_noun_agreement_irregular_1-v0-loglikelihood

-7fab9f02e71a224ae7931aa77f8a9a61d887a7480756adc965d4746e97fb04a5
+7fab9f02e71a224ae7931aa77f8a9a61d887a7480756adc965d4746e97fb04a5
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_irregular_1-v0-res.json → tests/testdata/blimp_determiner_noun_agreement_irregular_1-v0-res.json

-{"results": {"blimp_determiner_noun_agreement_irregular_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_irregular_1": 0}}
+{"results": {"blimp_determiner_noun_agreement_irregular_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_irregular_1": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_irregular_2-v0-loglikelihood → tests/testdata/blimp_determiner_noun_agreement_irregular_2-v0-loglikelihood

-ddb24ddfaebe076b3aa7107937d71bf5f4503a78283bc889e39200368603681e
+ddb24ddfaebe076b3aa7107937d71bf5f4503a78283bc889e39200368603681e
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_irregular_2-v0-res.json → 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}}
+{"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 → tests/testdata/blimp_determiner_noun_agreement_with_adj_2-v0-loglikelihood

-95acb74fac7d57ae2c9d208361a5f8ad36b0b19a055f02e648ed8e99505f4b43
+95acb74fac7d57ae2c9d208361a5f8ad36b0b19a055f02e648ed8e99505f4b43
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_with_adj_2-v0-res.json → 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}}
+{"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 → tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_1-v0-loglikelihood

-ad61c619aa79433d02f1aeacde2ab87291fd5d5c370032c24d41c4f0065ed1f9
+ad61c619aa79433d02f1aeacde2ab87291fd5d5c370032c24d41c4f0065ed1f9
\ No newline at end of file

tests/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_1-v0-res.json → 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}}
+{"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 → tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_2-v0-loglikelihood

-ccc64b4d5e80c081d5161aae5828212ba49d277ca8c5a4281f181744727a6a99
+ccc64b4d5e80c081d5161aae5828212ba49d277ca8c5a4281f181744727a6a99
\ No newline at end of file