Revert `tests/testdata` changes and address flake8 issues

tests/testdata/random_insertion-v0-res.json

-{"results": {"random_insertion": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"random_insertion": 0}}
+{"results": {"random_insertion": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"random_insertion": 0}}
\ No newline at end of file

tests/testdata/record-v0-loglikelihood

-a3e378fbde4e28f375cac1561bbfc7d7673c2af193628a774ad012d5192393aa
+a3e378fbde4e28f375cac1561bbfc7d7673c2af193628a774ad012d5192393aa
\ No newline at end of file

tests/testdata/record-v0-res.json

-{"results": {"record": {"em": 0.1521, "em_stderr": 0.0035913575128186616, "f1": 0.1581870634920636, "f1_stderr": 0.0036146895141474576}}, "versions": {"record": 0}}
+{"results": {"record": {"em": 0.1521, "em_stderr": 0.0035913575128186616, "f1": 0.1581870634920636, "f1_stderr": 0.0036146895141474576}}, "versions": {"record": 0}}
\ No newline at end of file

tests/testdata/reversed_words-v0-greedy_until

-1d79fc4f0177f9624a487b9973f4e0e1d3f8404993b419a7b807a690ebbbb290
+1d79fc4f0177f9624a487b9973f4e0e1d3f8404993b419a7b807a690ebbbb290
\ No newline at end of file

tests/testdata/reversed_words-v0-res.json

-{"results": {"reversed_words": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"reversed_words": 0}}
+{"results": {"reversed_words": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"reversed_words": 0}}
\ No newline at end of file

tests/testdata/rte-v0-loglikelihood

-c80ce13c8c736087f1557f8736d5d318b540ff01e4bb7f55e568890dc8b0393e
+c80ce13c8c736087f1557f8736d5d318b540ff01e4bb7f55e568890dc8b0393e
\ No newline at end of file

tests/testdata/rte-v0-res.json

-{"results": {"rte": {"acc": 0.5379061371841155, "acc_stderr": 0.030009848912529117}}, "versions": {"rte": 0}}
+{"results": {"rte": {"acc": 0.5379061371841155, "acc_stderr": 0.030009848912529117}}, "versions": {"rte": 0}}
\ No newline at end of file

tests/testdata/sciq-v0-loglikelihood

-71cbb6e2a7ac4512c3761ea801d420eb3fac49d158c7e4deaa3ab8727bea923c
+71cbb6e2a7ac4512c3761ea801d420eb3fac49d158c7e4deaa3ab8727bea923c
\ No newline at end of file

tests/testdata/sciq-v0-res.json

-{"results": {"sciq": {"acc": 0.234, "acc_norm": 0.239, "acc_norm_stderr": 0.01349300044693758, "acc_stderr": 0.01339490288966001}}, "versions": {"sciq": 0}}
+{"results": {"sciq": {"acc": 0.234, "acc_norm": 0.239, "acc_norm_stderr": 0.01349300044693758, "acc_stderr": 0.01339490288966001}}, "versions": {"sciq": 0}}
\ No newline at end of file

tests/testdata/squad2-v0-greedy_until

-b261e8885c11750ce6911bb11e8693de03d53758297c26fb14cfc1ef508862cb
+b261e8885c11750ce6911bb11e8693de03d53758297c26fb14cfc1ef508862cb
\ No newline at end of file

tests/testdata/squad2-v0-loglikelihood

-287e87cc6878debcc80d9b6df4e2d0a74ed29068e0e0a80906c8441843a17cee
+287e87cc6878debcc80d9b6df4e2d0a74ed29068e0e0a80906c8441843a17cee
\ No newline at end of file

tests/testdata/squad2-v0-res.json

-{"results": {"squad2": {"HasAns_exact": 0.0, "HasAns_f1": 0.0, "NoAns_exact": 0.0, "NoAns_f1": 0.0, "best_exact": 50.07159100480081, "best_f1": 50.07159100480081, "exact": 0.0, "f1": 0.0}}, "versions": {"squad2": 0}}
+{"results": {"squad2": {"HasAns_exact": 0.0, "HasAns_f1": 0.0, "NoAns_exact": 0.0, "NoAns_f1": 0.0, "best_exact": 50.07159100480081, "best_f1": 50.07159100480081, "exact": 0.0, "f1": 0.0}}, "versions": {"squad2": 0}}
\ No newline at end of file

tests/testdata/squad2-v1-greedy_until

-e17e3d85c1d5adaf2d6b4b752c4babc2e0b3a6e144e6de70cb3b2287e85109b8
+e17e3d85c1d5adaf2d6b4b752c4babc2e0b3a6e144e6de70cb3b2287e85109b8
\ No newline at end of file

tests/testdata/squad2-v1-loglikelihood

-f5da6173402b274dc89130755c222c6ca6b2a3bacaaa4e4ab07be9322b7bad65
+f5da6173402b274dc89130755c222c6ca6b2a3bacaaa4e4ab07be9322b7bad65
\ No newline at end of file

tests/testdata/squad2-v1-res.json

-{"results": {"squad2": {"HasAns_exact": 0.0, "HasAns_f1": 0.0, "NoAns_exact": 0.0, "NoAns_f1": 0.0, "best_exact": 50.07159100480081, "best_f1": 50.07159100480081, "exact": 0.0, "f1": 0.0}}, "versions": {"squad2": 1}}
+{"results": {"squad2": {"HasAns_exact": 0.0, "HasAns_f1": 0.0, "NoAns_exact": 0.0, "NoAns_f1": 0.0, "best_exact": 50.07159100480081, "best_f1": 50.07159100480081, "exact": 0.0, "f1": 0.0}}, "versions": {"squad2": 1}}
\ No newline at end of file

tests/testdata/sst-v0-loglikelihood

-d2ebe3a63517d1d481aa1513bebe124c57a0904554a1e95f566979cfe67b1a7f
+d2ebe3a63517d1d481aa1513bebe124c57a0904554a1e95f566979cfe67b1a7f
\ No newline at end of file

tests/testdata/sst-v0-res.json

-{"results": {"sst": {"acc": 0.5172018348623854, "acc_stderr": 0.016931824425903734}}, "versions": {"sst": 0}}
+{"results": {"sst": {"acc": 0.5172018348623854, "acc_stderr": 0.016931824425903734}}, "versions": {"sst": 0}}
\ No newline at end of file

tests/testdata/swag-v0-loglikelihood

-be4fcbad876124c4ba3c71970538a97fec0e36a9cc677c70b6c9243a7bcee0ec
+be4fcbad876124c4ba3c71970538a97fec0e36a9cc677c70b6c9243a7bcee0ec
\ No newline at end of file

tests/testdata/swag-v0-res.json

-{"results": {"swag": {"acc": 0.2482255323402979, "acc_norm": 0.24882535239428172, "acc_norm_stderr": 0.00305666959496067, "acc_stderr": 0.003054201832644171}}, "versions": {"swag": 0}}
+{"results": {"swag": {"acc": 0.2482255323402979, "acc_norm": 0.24882535239428172, "acc_norm_stderr": 0.00305666959496067, "acc_stderr": 0.003054201832644171}}, "versions": {"swag": 0}}
\ No newline at end of file

tests/testdata/triviaqa-v0-loglikelihood

-f8ec05b306b9f6187c0f8117cae441fb85a7a2e4670f4f9a1a3b632b1978421a
+f8ec05b306b9f6187c0f8117cae441fb85a7a2e4670f4f9a1a3b632b1978421a
\ No newline at end of file