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

tests/testdata/qnli-v0-res.json

+{"results": {"qnli": {"acc": 0.5108914515833791, "acc_stderr": 0.00676380528502966}}, "versions": {"qnli": 0}}
\ No newline at end of file

tests/testdata/qqp-v0-loglikelihood

+97b551b0fc3d239aad4929a2e8e79c986891aefd9fcd19441fea0382d507889e
\ No newline at end of file

tests/testdata/qqp-v0-res.json

+{"results": {"qqp": {"acc": 0.49782339846648527, "acc_stderr": 0.0024866770696239894, "f1": 0.42322661288031593, "f1_stderr": 0.002695903831328166}}, "versions": {"qqp": 0}}
\ No newline at end of file

tests/testdata/race-v0-loglikelihood

+bdfdfab7fa1c7af0c1e161785e347b1b8071a15cbf971f6f2a9ae8c8e845199f
\ No newline at end of file

tests/testdata/race-v0-res.json

+{"results": {"race": {"acc": 0.23253588516746412, "acc_stderr": 0.013074460615265295}}, "versions": {"race": 0}}
\ No newline at end of file

tests/testdata/random_insertion-v0-greedy_until

+6c48baa6924f3635120f33062251c4b571b3d4e9fe46b14d91f54ddd1c857997
\ No newline at end of file

tests/testdata/random_insertion-v0-res.json

+{"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
\ 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}}
\ No newline at end of file

tests/testdata/reversed_words-v0-greedy_until

+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}}
\ No newline at end of file

tests/testdata/rte-v0-loglikelihood

+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}}
\ No newline at end of file

tests/testdata/sciq-v0-loglikelihood

+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}}
\ No newline at end of file

tests/testdata/squad2-v0-greedy_until

+b261e8885c11750ce6911bb11e8693de03d53758297c26fb14cfc1ef508862cb
\ No newline at end of file

tests/testdata/squad2-v0-loglikelihood

+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}}
\ No newline at end of file

tests/testdata/squad2-v1-greedy_until

+e17e3d85c1d5adaf2d6b4b752c4babc2e0b3a6e144e6de70cb3b2287e85109b8
\ No newline at end of file

tests/testdata/squad2-v1-loglikelihood

+f5da6173402b274dc89130755c222c6ca6b2a3bacaaa4e4ab07be9322b7bad65
\ No newline at end of file