Merge branch 'master' into multilingual

tests/testdata/pile_youtubesubtitles-v1-res.json

+{"results": {"pile_youtubesubtitles": {"bits_per_byte": 3.3827117222045906e-05, "byte_perplexity": 1.000023447445816, "word_perplexity": 1.0001529192262875}}, "versions": {"pile_youtubesubtitles": 1}}
\ 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

tests/testdata/squad2-v1-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": 1}}
\ No newline at end of file

tests/testdata/truthfulqa_gen-v0-greedy_until

+0d7c56e1aa71ffd8f94bde28f6e8dfdd35f7aaadffa0620bd2a27704253d6c14
\ No newline at end of file

tests/testdata/truthfulqa_gen-v0-res.json

+{"results": {"truthfulqa_gen": {"bleu_acc": 0.0, "bleu_acc_stderr": 0.0, "bleu_diff": 0.0, "bleu_diff_stderr": 0.0, "bleu_max": 0.0, "bleu_max_stderr": 0.0, "bleurt_acc": 0.8372093023255814, "bleurt_acc_stderr": 0.012923696051772253, "bleurt_diff": 0.13967358205134603, "bleurt_diff_stderr": 0.00532907098769571, "bleurt_max": -1.4402793981454072, "bleurt_max_stderr": 0.0021884846359458963, "rouge1_acc": 0.0, "rouge1_acc_stderr": 0.0, "rouge1_diff": 0.0, "rouge1_diff_stderr": 0.0, "rouge1_max": 0.0, "rouge1_max_stderr": 0.0, "rouge2_acc": 0.0, "rouge2_acc_stderr": 0.0, "rouge2_diff": 0.0, "rouge2_diff_stderr": 0.0, "rouge2_max": 0.0, "rouge2_max_stderr": 0.0, "rougeL_acc": 0.0, "rougeL_acc_stderr": 0.0, "rougeL_diff": 0.0, "rougeL_diff_stderr": 0.0, "rougeL_max": 0.0, "rougeL_max_stderr": 0.0}}, "versions": {"truthfulqa_gen": 0}}
\ No newline at end of file

tests/testdata/truthfulqa_gen-v1-greedy_until

+1a280973bbac2b7ac29dd64dddac474fb4749585f7de893483b4034814466c67
\ No newline at end of file

tests/testdata/truthfulqa_gen-v1-res.json

+{"results": {"truthfulqa_gen": {"bleu_acc": 0.0, "bleu_acc_stderr": 0.0, "bleu_diff": 0.0, "bleu_diff_stderr": 0.0, "bleu_max": 0.0, "bleu_max_stderr": 0.0, "bleurt_acc": 0.835985312117503, "bleurt_acc_stderr": 0.012962704327492454, "bleurt_diff": 0.14077322143090107, "bleurt_diff_stderr": 0.005459888909582694, "bleurt_max": -1.4399358725752065, "bleurt_max_stderr": 0.0022126992369197133, "rouge1_acc": 0.0, "rouge1_acc_stderr": 0.0, "rouge1_diff": 0.0, "rouge1_diff_stderr": 0.0, "rouge1_max": 0.0, "rouge1_max_stderr": 0.0, "rouge2_acc": 0.0, "rouge2_acc_stderr": 0.0, "rouge2_diff": 0.0, "rouge2_diff_stderr": 0.0, "rouge2_max": 0.0, "rouge2_max_stderr": 0.0, "rougeL_acc": 0.0, "rougeL_acc_stderr": 0.0, "rougeL_diff": 0.0, "rougeL_diff_stderr": 0.0, "rougeL_max": 0.0, "rougeL_max_stderr": 0.0}}, "versions": {"truthfulqa_gen": 1}}
\ No newline at end of file

tests/testdata/truthfulqa_mc-v0-loglikelihood

+226a6783976177dc9ceda5688623ff37023242eff30ddf270b886bf7b9b32228
\ No newline at end of file

tests/testdata/truthfulqa_mc-v0-res.json

+{"results": {"truthfulqa_mc": {"mc1": 0.2141982864137087, "mc1_stderr": 0.01436214815569045, "mc2": 0.465436996173817, "mc2_stderr": 0.0048422530880316405}}, "versions": {"truthfulqa_mc": 0}}
\ No newline at end of file

tests/testdata/truthfulqa_mc-v1-loglikelihood

+1e07020e9cf41d46ed65312eb39d2b8e6599673d4f0d6b67c0d0eba0efb493bb
\ No newline at end of file

tests/testdata/truthfulqa_mc-v1-res.json

+{"results": {"truthfulqa_mc": {"mc1": 0.23255813953488372, "mc1_stderr": 0.01478915753108052, "mc2": 0.4462325560722362, "mc2_stderr": 0.004986523944692003}}, "versions": {"truthfulqa_mc": 1}}
\ No newline at end of file

tests/testdata/wikitext-v1-loglikelihood_rolling

+b6f83e6cf7535ee41b0057c3e2ec2cf7f2fa5a9119b305c479a83091d1142b2c
\ No newline at end of file

tests/testdata/wikitext-v1-res.json

+{"results": {"wikitext": {"bits_per_byte": 3.202519859941674e-05, "byte_perplexity": 1.0000221984224973, "word_perplexity": 1.000118710696617}}, "versions": {"wikitext": 1}}
\ No newline at end of file

tests/testdata/wmt20-en-ja-v1-greedy_until

+7fe61f5847a51e93e97c84b39f4420978727754e4b6cf636a27851c615857530
\ No newline at end of file

tests/testdata/wmt20-en-ja-v1-res.json

+{"results": {"wmt20-en-ja": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 4.1305928226819116e-05, "chrf_stderr": 2.0455354158878388e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-ja": 1}}
\ No newline at end of file

tests/testdata/wmt20-en-zh-v1-greedy_until

+67f0333ddbcb07d7a9ac12919129a18fe4fea24e4826a11bbdde4fd5ed5ed83f
\ No newline at end of file

tests/testdata/wmt20-en-zh-v1-res.json

+{"results": {"wmt20-en-zh": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.00014170297316825535, "chrf_stderr": 6.590669847391838e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-zh": 1}}
\ No newline at end of file

tests/testdata/wnli-v1-loglikelihood

+8a0f81661d2ab2334bbc8031fac31c0c8882f1d9271dd51599d21dfdbb726dea
\ No newline at end of file

tests/testdata/wnli-v1-res.json

+{"results": {"wnli": {"acc": 0.5633802816901409, "acc_stderr": 0.0592793555841297}}, "versions": {"wnli": 1}}
\ No newline at end of file