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

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}}
\ No newline at end of file

tests/testdata/openbookqa-v0-loglikelihood

+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}}
\ No newline at end of file

tests/testdata/pile_arxiv-v0-loglikelihood_rolling

+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}}
\ No newline at end of file

tests/testdata/pile_bookcorpus2-v0-loglikelihood_rolling

+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}}
\ No newline at end of file

tests/testdata/pile_books3-v0-loglikelihood_rolling

+0f8f36f705b999b6d55fa72ff89a82793dd1cb568ab1f8727a6a2086a12b9410
\ No newline at end of file

tests/testdata/pile_books3-v0-res.json

+{"results": {"pile_books3": {"bits_per_byte": 8.942486206275221e-07, "byte_perplexity": 1.0000008942490204, "word_perplexity": 1.0000052870063607}}, "versions": {"pile_books3": 0}}
\ No newline at end of file

tests/testdata/pile_dm-mathematics-v0-loglikelihood_rolling

+d5b7967c0ece8b816f3921a8bd0fad23365349e935b491595e2ad1135af42da6
\ No newline at end of file

tests/testdata/pile_dm-mathematics-v0-res.json

+{"results": {"pile_dm-mathematics": {"bits_per_byte": 6.176600873627999e-05, "byte_perplexity": 1.0000617679162955, "word_perplexity": 1.0002875035042451}}, "versions": {"pile_dm-mathematics": 0}}
\ No newline at end of file

tests/testdata/pile_enron-v0-loglikelihood_rolling

+4baa6ccdc9e3aa9921675ab4400d5e89d7b546b844a8ea28f6461d649066418a
\ No newline at end of file

tests/testdata/pile_enron-v0-res.json

+{"results": {"pile_enron": {"bits_per_byte": 0.0003163902828673244, "byte_perplexity": 1.000316440339552, "word_perplexity": 1.00224668051869}}, "versions": {"pile_enron": 0}}
\ No newline at end of file

tests/testdata/pile_europarl-v0-loglikelihood_rolling

+e67d3dbccd47d308bfc5b0e66b76d0dfc5e386ebfa94e056562c2281c395543f
\ No newline at end of file

tests/testdata/pile_europarl-v0-res.json

+{"results": {"pile_europarl": {"bits_per_byte": 8.648858203555344e-06, "byte_perplexity": 1.000008648895605, "word_perplexity": 1.000063506523818}}, "versions": {"pile_europarl": 0}}
\ No newline at end of file

tests/testdata/pile_freelaw-v0-loglikelihood_rolling

+d77f3f68aadd6cbf1290c2f6737b2ed5d5c2a60e4c81a65c280f207783caabe1
\ No newline at end of file

tests/testdata/pile_freelaw-v0-res.json

+{"results": {"pile_freelaw": {"bits_per_byte": 3.16238943008513e-05, "byte_perplexity": 1.0000316243943415, "word_perplexity": 1.000203169094218}}, "versions": {"pile_freelaw": 0}}
\ No newline at end of file

tests/testdata/pile_github-v0-loglikelihood_rolling

+df384c3df3d8f53273e97127c5bb84c17e638acad7d6bc9c91f6dee96d43b639
\ No newline at end of file

tests/testdata/pile_github-v0-res.json

+{"results": {"pile_github": {"bits_per_byte": 9.540627613754646e-05, "byte_perplexity": 1.0000954108274611, "word_perplexity": 1.0009643183931227}}, "versions": {"pile_github": 0}}
\ No newline at end of file

tests/testdata/pile_gutenberg-v0-loglikelihood_rolling

+02a559f74a9105145e7d4d9c5ddea372b5b4938f5368dc8ffafc39cbe3b4c7ef
\ No newline at end of file