Revert `tests/testdata` changes and address flake8 issues

tests/tests/testdata/blimp_principle_A_domain_1-v0-res.json → tests/testdata/blimp_principle_A_domain_1-v0-res.json

-{"results": {"blimp_principle_A_domain_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_domain_1": 0}}
+{"results": {"blimp_principle_A_domain_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_domain_1": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_principle_A_domain_2-v0-loglikelihood → tests/testdata/blimp_principle_A_domain_2-v0-loglikelihood

-eb5ddf0a97982373ab1a4e58267cfcdebdecdb86c376dfd5ebf46737c9d3ee12
+eb5ddf0a97982373ab1a4e58267cfcdebdecdb86c376dfd5ebf46737c9d3ee12
\ No newline at end of file

tests/tests/testdata/blimp_principle_A_domain_2-v0-res.json → tests/testdata/blimp_principle_A_domain_2-v0-res.json

-{"results": {"blimp_principle_A_domain_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_domain_2": 0}}
+{"results": {"blimp_principle_A_domain_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_domain_2": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_principle_A_domain_3-v0-loglikelihood → tests/testdata/blimp_principle_A_domain_3-v0-loglikelihood

-38454befedcf1f3f6ef27d3bef9ccfdfb3e94a7ab32d86a63493a920d2d50093
+38454befedcf1f3f6ef27d3bef9ccfdfb3e94a7ab32d86a63493a920d2d50093
\ No newline at end of file

tests/tests/testdata/blimp_principle_A_domain_3-v0-res.json → tests/testdata/blimp_principle_A_domain_3-v0-res.json

-{"results": {"blimp_principle_A_domain_3": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_domain_3": 0}}
+{"results": {"blimp_principle_A_domain_3": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_domain_3": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_principle_A_reconstruction-v0-loglikelihood → tests/testdata/blimp_principle_A_reconstruction-v0-loglikelihood

-894efedfd8750d5b8de6157f9b2ed2b51b5290d3a78ea9b041fc62d34e96efbc
+894efedfd8750d5b8de6157f9b2ed2b51b5290d3a78ea9b041fc62d34e96efbc
\ No newline at end of file

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

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

tests/tests/testdata/blimp_regular_plural_subject_verb_agreement_1-v0-loglikelihood → tests/testdata/blimp_regular_plural_subject_verb_agreement_1-v0-loglikelihood

-5bc0441f31e32443cf761bca6e961d504e1e84b15aa4e1d79e5c8ed5b4c2aa3a
+5bc0441f31e32443cf761bca6e961d504e1e84b15aa4e1d79e5c8ed5b4c2aa3a
\ No newline at end of file

tests/tests/testdata/blimp_regular_plural_subject_verb_agreement_1-v0-res.json → tests/testdata/blimp_regular_plural_subject_verb_agreement_1-v0-res.json

-{"results": {"blimp_regular_plural_subject_verb_agreement_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_regular_plural_subject_verb_agreement_1": 0}}
+{"results": {"blimp_regular_plural_subject_verb_agreement_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_regular_plural_subject_verb_agreement_1": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_regular_plural_subject_verb_agreement_2-v0-loglikelihood → tests/testdata/blimp_regular_plural_subject_verb_agreement_2-v0-loglikelihood

-f69d9891f59872538962221fccc425b07df7cfbd83cdc546ce83e6b0e9a93f7c
+f69d9891f59872538962221fccc425b07df7cfbd83cdc546ce83e6b0e9a93f7c
\ No newline at end of file

tests/tests/testdata/blimp_regular_plural_subject_verb_agreement_2-v0-res.json → tests/testdata/blimp_regular_plural_subject_verb_agreement_2-v0-res.json

-{"results": {"blimp_regular_plural_subject_verb_agreement_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_regular_plural_subject_verb_agreement_2": 0}}
+{"results": {"blimp_regular_plural_subject_verb_agreement_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_regular_plural_subject_verb_agreement_2": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_sentential_negation_npi_licensor_present-v0-loglikelihood → tests/testdata/blimp_sentential_negation_npi_licensor_present-v0-loglikelihood

-e6666c5657215ff4bfd646b8ee3ae6df956e71c0be9ab1c287fb1b68291dd0d1
+e6666c5657215ff4bfd646b8ee3ae6df956e71c0be9ab1c287fb1b68291dd0d1
\ No newline at end of file

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

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

tests/tests/testdata/blimp_sentential_negation_npi_scope-v0-loglikelihood → tests/testdata/blimp_sentential_negation_npi_scope-v0-loglikelihood

-32fcbd0a1c6e664af2751bad552587b5ca3911973b07f4fb2cf0a2acd3de5349
+32fcbd0a1c6e664af2751bad552587b5ca3911973b07f4fb2cf0a2acd3de5349
\ No newline at end of file

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

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

tests/tests/testdata/blimp_sentential_subject_island-v0-loglikelihood → tests/testdata/blimp_sentential_subject_island-v0-loglikelihood

-80f5f98fad26240de2767fe58c4b18d864df41cbfa76f06c84c3fce9f14f4833
+80f5f98fad26240de2767fe58c4b18d864df41cbfa76f06c84c3fce9f14f4833
\ No newline at end of file

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

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

tests/tests/testdata/blimp_superlative_quantifiers_1-v0-loglikelihood → tests/testdata/blimp_superlative_quantifiers_1-v0-loglikelihood

-8a01f6a5ea87a01c0c9b0c7b3bc4de4711bf0ff050976976651182b9ed34a0d4
+8a01f6a5ea87a01c0c9b0c7b3bc4de4711bf0ff050976976651182b9ed34a0d4
\ No newline at end of file

tests/tests/testdata/blimp_superlative_quantifiers_1-v0-res.json → tests/testdata/blimp_superlative_quantifiers_1-v0-res.json

-{"results": {"blimp_superlative_quantifiers_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_superlative_quantifiers_1": 0}}
+{"results": {"blimp_superlative_quantifiers_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_superlative_quantifiers_1": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_superlative_quantifiers_2-v0-loglikelihood → tests/testdata/blimp_superlative_quantifiers_2-v0-loglikelihood

-59c20ff0f632cf42afc74ecc682cf92e5e740417b01e6cf9a610a3bc544d2ea5
+59c20ff0f632cf42afc74ecc682cf92e5e740417b01e6cf9a610a3bc544d2ea5
\ No newline at end of file