Commit 4d147bdd authored by Jonathan Tow's avatar Jonathan Tow
Browse files

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

parents 011cc891 dc937d4b
{"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": 1}}
\ No newline at end of file
d2ebe3a63517d1d481aa1513bebe124c57a0904554a1e95f566979cfe67b1a7f
\ No newline at end of file
{"results": {"sst": {"acc": 0.5172018348623854, "acc_stderr": 0.016931824425903734}}, "versions": {"sst": 0}}
\ No newline at end of file
f8ec05b306b9f6187c0f8117cae441fb85a7a2e4670f4f9a1a3b632b1978421a
\ No newline at end of file
{"results": {"triviaqa": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"triviaqa": 0}}
\ No newline at end of file
96b218173468cc94552a0b946193bda89faba51f1bfc3e7945531f9dff8d6fe9
\ No newline at end of file
{"results": {"webqs": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"webqs": 0}}
\ No newline at end of file
403a08da05e4c44d7e3dd3358382a7ba489c41d223e24cd1a9ed82ef1a2d004b
\ No newline at end of file
{"results": {"wic": {"acc": 0.49216300940438873, "acc_stderr": 0.01980828765781383}}, "versions": {"wic": 0}}
\ No newline at end of file
b6f83e6cf7535ee41b0057c3e2ec2cf7f2fa5a9119b305c479a83091d1142b2c
\ No newline at end of file
{"results": {"wikitext": {"bits_per_byte": 2.219817611605802e-05, "byte_perplexity": 1.0000221984224973, "word_perplexity": 1.000118710696617}}, "versions": {"wikitext": 0}}
\ No newline at end of file
90a3eff49de9173964d46f5ed57bcf9a78a72dd1bfe0e5323b25cebb40b49ea9
\ No newline at end of file
{"results": {"winogrande": {"acc": 0.516179952644041, "acc_stderr": 0.014045126130978606}}, "versions": {"winogrande": 0}}
\ No newline at end of file
368ae7eec0f902b5123f2d5197caa5109a23942011c53fe68d9eaeee20180e46
\ No newline at end of file
{"results": {"wmt14-en-fr": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.011284118461117099, "chrf_stderr": 7.340651275964445e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt14-en-fr": 0}}
\ No newline at end of file
c1d9f7283755fbdd7ecd6cc4278b0ac25a80ac256b7071ea5f839ccd038e5974
\ No newline at end of file
{"results": {"wmt14-fr-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.01275083169440515, "chrf_stderr": 8.45474998563806e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt14-fr-en": 0}}
\ No newline at end of file
d30e23e38d9a45b9c31e1dfd14b58d0b7020df4b9c8a1c697aa6bc5fba8ce08a
\ No newline at end of file
{"results": {"wmt16-de-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.013700416764482968, "chrf_stderr": 0.00016071651360909355, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt16-de-en": 0}}
\ No newline at end of file
d71e2074af3770e9b29ac561caf2e1c29ad6b0dc50ec2e7bcc5501747b11f0da
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment