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

tests/testdata/anagrams2-v0-res.json

+{"results": {"anagrams2": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"anagrams2": 0}}
\ No newline at end of file

tests/testdata/anli_r1-v0-loglikelihood

+3a84baf2f170e138c6ce0bc9f06f905def35d705fa2b8781f10c87aef404c4cb
\ No newline at end of file

tests/testdata/anli_r1-v0-res.json

+{"results": {"anli_r1": {"acc": 0.334, "acc_stderr": 0.014922019523732967}}, "versions": {"anli_r1": 0}}
\ No newline at end of file

tests/testdata/anli_r2-v0-loglikelihood

+d0ea3c3e09d533982c15b4c034439896d6af4bbafb2254d305e20215534a251d
\ No newline at end of file

tests/testdata/anli_r2-v0-res.json

+{"results": {"anli_r2": {"acc": 0.356, "acc_stderr": 0.015149042659306628}}, "versions": {"anli_r2": 0}}
\ No newline at end of file

tests/testdata/anli_r3-v0-loglikelihood

+6b6e5c6a794f2fbff78b7aa24fe0c90156039334bbd1cb34f7af9fc6e6183845
\ No newline at end of file

tests/testdata/anli_r3-v0-res.json

+{"results": {"anli_r3": {"acc": 0.31916666666666665, "acc_stderr": 0.01346230971200514}}, "versions": {"anli_r3": 0}}
\ No newline at end of file

tests/testdata/arc_challenge-v0-loglikelihood

+41c34c96cca8ace661911d0033d630c554b283f5a3953bcdc50720ae6b00a9c1
\ No newline at end of file

tests/testdata/arc_challenge-v0-res.json

+{"results": {"arc_challenge": {"acc": 0.24488054607508533, "acc_norm": 0.2440273037542662, "acc_norm_stderr": 0.012551447627856257, "acc_stderr": 0.012566273985131354}}, "versions": {"arc_challenge": 0}}
\ No newline at end of file

tests/testdata/arc_easy-v0-loglikelihood

+ffa6e39a35a16299dcb015f17f986aaa598ad8b4840c4cebe0339a7042232741
\ No newline at end of file

tests/testdata/arc_easy-v0-res.json

+{"results": {"arc_easy": {"acc": 0.2474747474747475, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.008772796145221907, "acc_stderr": 0.008855114414834707}}, "versions": {"arc_easy": 0}}
\ No newline at end of file

tests/testdata/arithmetic_1dc-v0-loglikelihood

+04c3a63a6b3c579bd3775d92b3076ba9130041d5ce7cf9244d3f86e95c804387
\ No newline at end of file

tests/testdata/arithmetic_1dc-v0-res.json

+{"results": {"arithmetic_1dc": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_1dc": 0}}
\ No newline at end of file

tests/testdata/arithmetic_2da-v0-loglikelihood

+6ca1ca6ebd7cac4420d5005f7f35b0edbc921377f5e4f8874cc176e4fb6d79d4
\ No newline at end of file

tests/testdata/arithmetic_2da-v0-res.json

+{"results": {"arithmetic_2da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_2da": 0}}
\ No newline at end of file

tests/testdata/arithmetic_2dm-v0-loglikelihood

+14ac5e510cdf82967d6827a9ca059906ee1db2e347be1b17f36403a157e73552
\ No newline at end of file

tests/testdata/arithmetic_2dm-v0-res.json

+{"results": {"arithmetic_2dm": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_2dm": 0}}
\ No newline at end of file

tests/testdata/arithmetic_2ds-v0-loglikelihood

+66f7ff3b40251ee38fadcbee658e309a200224356fc3efa07d0a490a2c24bfa3
\ No newline at end of file

tests/testdata/arithmetic_2ds-v0-res.json

+{"results": {"arithmetic_2ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_2ds": 0}}
\ No newline at end of file

tests/testdata/arithmetic_3da-v0-loglikelihood

+c421f9cd5a5001b80e528441da925128177a04db8526ebcdab543a90b33c9ce2
\ No newline at end of file