Revert `tests/testdata` changes and address flake8 issues

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

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

tests/tests/testdata/blimp_wh_vs_that_with_gap_long_distance-v0-loglikelihood → tests/testdata/blimp_wh_vs_that_with_gap_long_distance-v0-loglikelihood

-eed67491bdf493a1dad8f1d9766bc7bd0e79946365b833c0f7eb81ac998e3dca
+eed67491bdf493a1dad8f1d9766bc7bd0e79946365b833c0f7eb81ac998e3dca
\ No newline at end of file

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

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

tests/testdata/boolq-v0-loglikelihood

-de5aa6f77a2e0fd050b9c272f10c4d5d5581e4f75ffa60926f79e60ae1738960
+de5aa6f77a2e0fd050b9c272f10c4d5d5581e4f75ffa60926f79e60ae1738960
\ No newline at end of file

tests/testdata/boolq-v0-res.json

-{"results": {"boolq": {"acc": 0.5048929663608562, "acc_stderr": 0.00874463623355505}}, "versions": {"boolq": 0}}
+{"results": {"boolq": {"acc": 0.5048929663608562, "acc_stderr": 0.00874463623355505}}, "versions": {"boolq": 0}}
\ No newline at end of file

tests/testdata/boolq-v1-loglikelihood

-6577e0d88572772ef08e64f624c0e3df0953286ae1f118ccef15623b59ffeabf
+6577e0d88572772ef08e64f624c0e3df0953286ae1f118ccef15623b59ffeabf
\ No newline at end of file

tests/testdata/boolq-v1-res.json

-{"results": {"boolq": {"acc": 0.5048929663608562, "acc_stderr": 0.00874463623355505}}, "versions": {"boolq": 1}}
+{"results": {"boolq": {"acc": 0.5048929663608562, "acc_stderr": 0.00874463623355505}}, "versions": {"boolq": 1}}
\ No newline at end of file

tests/testdata/cb-v0-loglikelihood

-ec3b1bbb9561e39c43c6f77a23b4060b15c606141c5346e3d0791b3e92aaa5d0
+ec3b1bbb9561e39c43c6f77a23b4060b15c606141c5346e3d0791b3e92aaa5d0
\ No newline at end of file

tests/testdata/cb-v0-res.json

-{"results": {"cb": {"acc": 0.3392857142857143, "acc_stderr": 0.06384226561930825, "f1": 0.2819143819143819}}, "versions": {"cb": 0}}
+{"results": {"cb": {"acc": 0.3392857142857143, "acc_stderr": 0.06384226561930825, "f1": 0.2819143819143819}}, "versions": {"cb": 0}}
\ No newline at end of file

tests/testdata/cb-v1-loglikelihood

-77b11f4348eb8a7f57faf95c531fda01ab4bf0e729f91a82451ed8e71ec8e66d
+77b11f4348eb8a7f57faf95c531fda01ab4bf0e729f91a82451ed8e71ec8e66d
\ No newline at end of file

tests/testdata/cb-v1-res.json

-{"results": {"cb": {"acc": 0.3392857142857143, "acc_stderr": 0.06384226561930825, "f1": 0.2819143819143819}}, "versions": {"cb": 1}}
+{"results": {"cb": {"acc": 0.3392857142857143, "acc_stderr": 0.06384226561930825, "f1": 0.2819143819143819}}, "versions": {"cb": 1}}
\ No newline at end of file

tests/testdata/cola-v0-loglikelihood

-e8635578ed8ee70b707a666d35e468b9321db24470f80c92080651e2bfa01751
+e8635578ed8ee70b707a666d35e468b9321db24470f80c92080651e2bfa01751
\ No newline at end of file

tests/testdata/cola-v0-res.json

-{"results": {"cola": {"mcc": -0.04538802810223175, "mcc_stderr": 0.023100371589225246}}, "versions": {"cola": 0}}
+{"results": {"cola": {"mcc": -0.04538802810223175, "mcc_stderr": 0.023100371589225246}}, "versions": {"cola": 0}}
\ No newline at end of file

tests/testdata/copa-v0-loglikelihood

-66276b9045b5300cba4b81340db06f674f031fa0b8883714ad0d03be464cd799
+66276b9045b5300cba4b81340db06f674f031fa0b8883714ad0d03be464cd799
\ No newline at end of file

tests/testdata/copa-v0-res.json

-{"results": {"copa": {"acc": 0.48, "acc_stderr": 0.050211673156867795}}, "versions": {"copa": 0}}
+{"results": {"copa": {"acc": 0.48, "acc_stderr": 0.050211673156867795}}, "versions": {"copa": 0}}
\ No newline at end of file

tests/testdata/coqa-v0-greedy_until

-4a8605d5deed0423ec095700251ed93325b45d320aca35d4ce1e94702094435e
+4a8605d5deed0423ec095700251ed93325b45d320aca35d4ce1e94702094435e
\ No newline at end of file

tests/testdata/coqa-v0-res.json

-{"results": {"coqa": {"em": 0.0, "em_stderr": 0.0, "f1": 0.0, "f1_stderr": 0.0}}, "versions": {"coqa": 0}}
+{"results": {"coqa": {"em": 0.0, "em_stderr": 0.0, "f1": 0.0, "f1_stderr": 0.0}}, "versions": {"coqa": 0}}
\ No newline at end of file

tests/testdata/coqa-v1-greedy_until

-57581470b921435d40da97872bb1cfda6ecf963ccc4b0240a3b04e3fea8c8e3a
+57581470b921435d40da97872bb1cfda6ecf963ccc4b0240a3b04e3fea8c8e3a
\ No newline at end of file

tests/testdata/coqa-v1-res.json

-{"results": {"coqa": {"em": 0.0, "em_stderr": 0.0, "f1": 0.0, "f1_stderr": 0.0}}, "versions": {"coqa": 1}}
+{"results": {"coqa": {"em": 0.0, "em_stderr": 0.0, "f1": 0.0, "f1_stderr": 0.0}}, "versions": {"coqa": 1}}
\ No newline at end of file

tests/testdata/cycle_letters-v0-greedy_until

-eb23f7d5de7528eefd8ed5f8054c402ff947319cccfef7195995946f99389201
+eb23f7d5de7528eefd8ed5f8054c402ff947319cccfef7195995946f99389201
\ No newline at end of file