Revert `tests/testdata` changes and address flake8 issues

tests/testdata/multirc-v0-res.json

-{"results": {"multirc": {"acc": 0.07450157397691501, "acc_stderr": 0.008510441526175931}}, "versions": {"multirc": 0}}
+{"results": {"multirc": {"acc": 0.07450157397691501, "acc_stderr": 0.008510441526175931}}, "versions": {"multirc": 0}}
\ No newline at end of file

tests/testdata/multirc-v1-loglikelihood

-0e793bd6f637a70a04c6f2cda080188fc037961b2f909095fe63f7bdbc4a90c6
+0e793bd6f637a70a04c6f2cda080188fc037961b2f909095fe63f7bdbc4a90c6
\ No newline at end of file

tests/testdata/multirc-v1-res.json

-{"results": {"multirc": {"acc": 0.046169989506820566, "acc_stderr": 0.006801377886208738}}, "versions": {"multirc": 1}}
+{"results": {"multirc": {"acc": 0.046169989506820566, "acc_stderr": 0.006801377886208738}}, "versions": {"multirc": 1}}
\ No newline at end of file

tests/testdata/mutual-v0-loglikelihood

-f759213a28f0412510bf1a24c9cab0dae64bdee902d42a26225295445e7779db
+f759213a28f0412510bf1a24c9cab0dae64bdee902d42a26225295445e7779db
\ No newline at end of file

tests/testdata/mutual-v0-res.json

-{"results": {"mutual": {"mrr": 0.5023513920240772, "mrr_stderr": 0.009501864812936679, "r@1": 0.22573363431151242, "r@1_stderr": 0.014053085820407457, "r@2": 0.4221218961625282, "r@2_stderr": 0.016602191705517556}}, "versions": {"mutual": 0}}
+{"results": {"mutual": {"mrr": 0.5023513920240772, "mrr_stderr": 0.009501864812936679, "r@1": 0.22573363431151242, "r@1_stderr": 0.014053085820407457, "r@2": 0.4221218961625282, "r@2_stderr": 0.016602191705517556}}, "versions": {"mutual": 0}}
\ No newline at end of file

tests/testdata/mutual-v1-loglikelihood

-f759213a28f0412510bf1a24c9cab0dae64bdee902d42a26225295445e7779db
+f759213a28f0412510bf1a24c9cab0dae64bdee902d42a26225295445e7779db
\ No newline at end of file

tests/testdata/mutual-v1-res.json

-{"results": {"mutual": {"mrr": 0.5023513920240772, "mrr_stderr": 0.009501864812936679, "r@1": 0.22460496613995484, "r@1_stderr": 0.014028122493992806, "r@2": 0.4706546275395034, "r@2_stderr": 0.016778343895001414}}, "versions": {"mutual": 1}}
+{"results": {"mutual": {"mrr": 0.5023513920240772, "mrr_stderr": 0.009501864812936679, "r@1": 0.22460496613995484, "r@1_stderr": 0.014028122493992806, "r@2": 0.4706546275395034, "r@2_stderr": 0.016778343895001414}}, "versions": {"mutual": 1}}
\ No newline at end of file

tests/testdata/mutual_plus-v0-loglikelihood

-b846bb9db109535f59a93d1ce340cf09f68bdf4fed5b8decd168784220fe07fa
+b846bb9db109535f59a93d1ce340cf09f68bdf4fed5b8decd168784220fe07fa
\ No newline at end of file

tests/testdata/mutual_plus-v0-res.json

-{"results": {"mutual_plus": {"mrr": 0.5275583145221953, "mrr_stderr": 0.009940894824430708, "r@1": 0.2595936794582393, "r@1_stderr": 0.014737047402750955, "r@2": 0.45372460496614, "r@2_stderr": 0.01673517854461967}}, "versions": {"mutual_plus": 0}}
+{"results": {"mutual_plus": {"mrr": 0.5275583145221953, "mrr_stderr": 0.009940894824430708, "r@1": 0.2595936794582393, "r@1_stderr": 0.014737047402750955, "r@2": 0.45372460496614, "r@2_stderr": 0.01673517854461967}}, "versions": {"mutual_plus": 0}}
\ No newline at end of file

tests/testdata/mutual_plus-v1-loglikelihood

-b846bb9db109535f59a93d1ce340cf09f68bdf4fed5b8decd168784220fe07fa
+b846bb9db109535f59a93d1ce340cf09f68bdf4fed5b8decd168784220fe07fa
\ No newline at end of file

tests/testdata/mutual_plus-v1-res.json

-{"results": {"mutual_plus": {"mrr": 0.5275583145221953, "mrr_stderr": 0.009940894824430708, "r@1": 0.26297968397291194, "r@1_stderr": 0.01479889176605113, "r@2": 0.5, "r@2_stderr": 0.01680731613632036}}, "versions": {"mutual_plus": 1}}
+{"results": {"mutual_plus": {"mrr": 0.5275583145221953, "mrr_stderr": 0.009940894824430708, "r@1": 0.26297968397291194, "r@1_stderr": 0.01479889176605113, "r@2": 0.5, "r@2_stderr": 0.01680731613632036}}, "versions": {"mutual_plus": 1}}
\ No newline at end of file

tests/testdata/openbookqa-v0-loglikelihood

-78a49a0ca1a47373adb33463b1d092e6bc0d8f4b01bcb380ada48065037849d7
+78a49a0ca1a47373adb33463b1d092e6bc0d8f4b01bcb380ada48065037849d7
\ No newline at end of file

tests/testdata/openbookqa-v0-res.json

-{"results": {"openbookqa": {"acc": 0.214, "acc_norm": 0.276, "acc_norm_stderr": 0.020011219298073517, "acc_stderr": 0.018359797502387046}}, "versions": {"openbookqa": 0}}
+{"results": {"openbookqa": {"acc": 0.214, "acc_norm": 0.276, "acc_norm_stderr": 0.020011219298073517, "acc_stderr": 0.018359797502387046}}, "versions": {"openbookqa": 0}}
\ No newline at end of file

tests/testdata/pile_arxiv-v0-loglikelihood_rolling

-814f9954e44368559602c00f7e85fa3971acdfd0315f508ec7df6318a79c55ec
+814f9954e44368559602c00f7e85fa3971acdfd0315f508ec7df6318a79c55ec
\ No newline at end of file

tests/testdata/pile_arxiv-v0-res.json

-{"results": {"pile_arxiv": {"bits_per_byte": 1.0750412350569374e-05, "byte_perplexity": 1.0000107504701365, "word_perplexity": 1.0000819333090385}}, "versions": {"pile_arxiv": 0}}
+{"results": {"pile_arxiv": {"bits_per_byte": 1.0750412350569374e-05, "byte_perplexity": 1.0000107504701365, "word_perplexity": 1.0000819333090385}}, "versions": {"pile_arxiv": 0}}
\ No newline at end of file

tests/testdata/pile_arxiv-v1-loglikelihood_rolling

-814f9954e44368559602c00f7e85fa3971acdfd0315f508ec7df6318a79c55ec
+814f9954e44368559602c00f7e85fa3971acdfd0315f508ec7df6318a79c55ec
\ No newline at end of file

tests/testdata/pile_arxiv-v1-res.json

-{"results": {"pile_arxiv": {"bits_per_byte": 1.55095665856779e-05, "byte_perplexity": 1.0000107504701365, "word_perplexity": 1.0000819333090385}}, "versions": {"pile_arxiv": 1}}
+{"results": {"pile_arxiv": {"bits_per_byte": 1.55095665856779e-05, "byte_perplexity": 1.0000107504701365, "word_perplexity": 1.0000819333090385}}, "versions": {"pile_arxiv": 1}}
\ No newline at end of file

tests/testdata/pile_bookcorpus2-v0-loglikelihood_rolling

-5c17ddfebeab8c41dabadb6fc216ceda91e3fe5dc95aaf1b2c843d7f11828b03
+5c17ddfebeab8c41dabadb6fc216ceda91e3fe5dc95aaf1b2c843d7f11828b03
\ No newline at end of file

tests/testdata/pile_bookcorpus2-v0-res.json

-{"results": {"pile_bookcorpus2": {"bits_per_byte": 1.1631037706429144e-06, "byte_perplexity": 1.000001163104447, "word_perplexity": 1.0000066499426599}}, "versions": {"pile_bookcorpus2": 0}}
+{"results": {"pile_bookcorpus2": {"bits_per_byte": 1.1631037706429144e-06, "byte_perplexity": 1.000001163104447, "word_perplexity": 1.0000066499426599}}, "versions": {"pile_bookcorpus2": 0}}
\ No newline at end of file

tests/testdata/pile_bookcorpus2-v1-loglikelihood_rolling

-5c17ddfebeab8c41dabadb6fc216ceda91e3fe5dc95aaf1b2c843d7f11828b03
+5c17ddfebeab8c41dabadb6fc216ceda91e3fe5dc95aaf1b2c843d7f11828b03
\ No newline at end of file