Revert `tests/testdata` changes and address flake8 issues

tests/testdata/math_num_theory-v1-res.json

-{"results": {"math_num_theory": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_num_theory": 1}}
+{"results": {"math_num_theory": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_num_theory": 1}}
\ No newline at end of file

tests/testdata/math_prealgebra-v0-greedy_until

-752cdf343d7152e476b0273065024f6ea0e0f47ea385c6bdf9067736cb39724a
+752cdf343d7152e476b0273065024f6ea0e0f47ea385c6bdf9067736cb39724a
\ No newline at end of file

tests/testdata/math_prealgebra-v0-res.json

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

tests/testdata/math_prealgebra-v1-greedy_until

-752cdf343d7152e476b0273065024f6ea0e0f47ea385c6bdf9067736cb39724a
+752cdf343d7152e476b0273065024f6ea0e0f47ea385c6bdf9067736cb39724a
\ No newline at end of file

tests/testdata/math_prealgebra-v1-res.json

-{"results": {"math_prealgebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_prealgebra": 1}}
+{"results": {"math_prealgebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_prealgebra": 1}}
\ No newline at end of file

tests/testdata/math_precalc-v0-greedy_until

-bc834b06fd79473ca6fe38a51b714aad0bf0478c1b0eec787eca34dbdf69cb71
+bc834b06fd79473ca6fe38a51b714aad0bf0478c1b0eec787eca34dbdf69cb71
\ No newline at end of file

tests/testdata/math_precalc-v0-res.json

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

tests/testdata/math_precalc-v1-greedy_until

-bc834b06fd79473ca6fe38a51b714aad0bf0478c1b0eec787eca34dbdf69cb71
+bc834b06fd79473ca6fe38a51b714aad0bf0478c1b0eec787eca34dbdf69cb71
\ No newline at end of file

tests/testdata/math_precalc-v1-res.json

-{"results": {"math_precalc": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_precalc": 1}}
+{"results": {"math_precalc": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_precalc": 1}}
\ No newline at end of file

tests/testdata/mathqa-v0-loglikelihood

-a45260e49f02c7cb8886b3746db4d388890860b202dd8a9f0267e3c324e0af13
+a45260e49f02c7cb8886b3746db4d388890860b202dd8a9f0267e3c324e0af13
\ No newline at end of file

tests/testdata/mathqa-v0-res.json

-{"results": {"mathqa": {"acc": 0.20770519262981574, "acc_norm": 0.2050251256281407, "acc_norm_stderr": 0.007390619359738901, "acc_stderr": 0.007426217631188539}}, "versions": {"mathqa": 0}}
+{"results": {"mathqa": {"acc": 0.20770519262981574, "acc_norm": 0.2050251256281407, "acc_norm_stderr": 0.007390619359738901, "acc_stderr": 0.007426217631188539}}, "versions": {"mathqa": 0}}
\ No newline at end of file

tests/testdata/mc_taco-v0-loglikelihood

-1811808ef05afd5f30ffc3471622a3dd7a1b681b17a2f7616695ad6b2a45943c
+1811808ef05afd5f30ffc3471622a3dd7a1b681b17a2f7616695ad6b2a45943c
\ No newline at end of file

tests/testdata/mc_taco-v0-res.json

-{"results": {"mc_taco": {"em": 0.07732732732732733, "f1": 0.41600515965511614}}, "versions": {"mc_taco": 0}}
+{"results": {"mc_taco": {"em": 0.07732732732732733, "f1": 0.41600515965511614}}, "versions": {"mc_taco": 0}}
\ No newline at end of file

tests/testdata/mnli-v0-loglikelihood

-4fc7b56b8f1e37e38f4a052b227baec2df914c898c3405d3e994726ba4fba976
+4fc7b56b8f1e37e38f4a052b227baec2df914c898c3405d3e994726ba4fba976
\ No newline at end of file

tests/testdata/mnli-v0-res.json

-{"results": {"mnli": {"acc": 0.32868059093224655, "acc_stderr": 0.004741640290753859}}, "versions": {"mnli": 0}}
+{"results": {"mnli": {"acc": 0.32868059093224655, "acc_stderr": 0.004741640290753859}}, "versions": {"mnli": 0}}
\ No newline at end of file

tests/testdata/mnli_mismatched-v0-loglikelihood

-3784acf322e79f31702a7a0612030e4ba5c4fc466ad976a34ee3f3d7278c01f0
+3784acf322e79f31702a7a0612030e4ba5c4fc466ad976a34ee3f3d7278c01f0
\ No newline at end of file

tests/testdata/mnli_mismatched-v0-res.json

-{"results": {"mnli_mismatched": {"acc": 0.3360455655004068, "acc_stderr": 0.004763973908606819}}, "versions": {"mnli_mismatched": 0}}
+{"results": {"mnli_mismatched": {"acc": 0.3360455655004068, "acc_stderr": 0.004763973908606819}}, "versions": {"mnli_mismatched": 0}}
\ No newline at end of file

tests/testdata/mrpc-v0-loglikelihood

-9f54cbff8d6accba99cfa2c4c4b359563313941018173d7dcf9e32dc28c06583
+9f54cbff8d6accba99cfa2c4c4b359563313941018173d7dcf9e32dc28c06583
\ No newline at end of file

tests/testdata/mrpc-v0-res.json

-{"results": {"mrpc": {"acc": 0.5392156862745098, "acc_stderr": 0.024707732873723128, "f1": 0.5982905982905982, "f1_stderr": 0.028928325246283727}}, "versions": {"mrpc": 0}}
+{"results": {"mrpc": {"acc": 0.5392156862745098, "acc_stderr": 0.024707732873723128, "f1": 0.5982905982905982, "f1_stderr": 0.028928325246283727}}, "versions": {"mrpc": 0}}
\ No newline at end of file

tests/testdata/multirc-v0-loglikelihood

-cdb026c027437a8b4653212d0944d36fc16f49921dcb8e4bef899d15a55e9f80
+cdb026c027437a8b4653212d0944d36fc16f49921dcb8e4bef899d15a55e9f80
\ No newline at end of file