Merge branch 'master' of https://github.com/EleutherAI/lm-evaluation-harness into task-guide

tests/testdata/arithmetic_3da-v0-res.json

+{"results": {"arithmetic_3da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_3da": 0}}
\ No newline at end of file

tests/testdata/arithmetic_3ds-v0-loglikelihood

+d3d8bad8827d4530945a1d8b3c7589c0235bbed0bc89e7561a6fdac678f6ce5c
\ No newline at end of file

tests/testdata/arithmetic_3ds-v0-res.json

+{"results": {"arithmetic_3ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_3ds": 0}}
\ No newline at end of file

tests/testdata/arithmetic_4da-v0-loglikelihood

+d3557beb8b9e5704122c2fc6362b11fbe2c3f2f3cb72aed4462b208767c40e01
\ No newline at end of file

tests/testdata/arithmetic_4da-v0-res.json

+{"results": {"arithmetic_4da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_4da": 0}}
\ No newline at end of file

tests/testdata/arithmetic_4ds-v0-loglikelihood

+d915830b8621e66331383bb2ae4c60acebf008e2f94741092ef4c33ea5441037
\ No newline at end of file

tests/testdata/arithmetic_4ds-v0-res.json

+{"results": {"arithmetic_4ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_4ds": 0}}
\ No newline at end of file

tests/testdata/arithmetic_5da-v0-loglikelihood

+49edb1e735660631ea6cc309721e6c0b80b7106a613a6959514852ca48f1130e
\ No newline at end of file

tests/testdata/arithmetic_5da-v0-res.json

+{"results": {"arithmetic_5da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_5da": 0}}
\ No newline at end of file

tests/testdata/arithmetic_5ds-v0-loglikelihood

+2888d6d098a5ef8c1e7f0d8295ba80826e2e04e431f57508dfb71d53e1cd4604
\ No newline at end of file

tests/testdata/arithmetic_5ds-v0-res.json

+{"results": {"arithmetic_5ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_5ds": 0}}
\ No newline at end of file

tests/testdata/boolq-v0-loglikelihood

+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}}
\ No newline at end of file

tests/testdata/cb-v0-loglikelihood

+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}}
\ No newline at end of file

tests/testdata/cola-v0-loglikelihood

+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}}
\ No newline at end of file

tests/testdata/copa-v0-loglikelihood

+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}}
\ No newline at end of file

tests/testdata/coqa-v0-greedy_until

+4a8605d5deed0423ec095700251ed93325b45d320aca35d4ce1e94702094435e
\ No newline at end of file