Merge branch 'master' into multilingual

tests/testdata/boolq-v1-res.json

+{"results": {"boolq": {"acc": 0.5048929663608562, "acc_stderr": 0.00874463623355505}}, "versions": {"boolq": 1}}
\ No newline at end of file

tests/testdata/drop-v1-greedy_until

+a670f911ab2999d72db15f534b22703d19e7837edbda4f9f199ad587f7aae6b2
\ No newline at end of file

tests/testdata/drop-v1-res.json

+{"results": {"drop": {"em": 0.0, "em_stderr": 0.0, "f1": 0.0, "f1_stderr": 0.0}}, "versions": {"drop": 1}}
\ No newline at end of file

tests/testdata/headqa_en-v0-loglikelihood

+09da45119b12a0144e3081f8fb790c2a22af7b9c3aac42f54423d348a711fbf5
\ No newline at end of file

tests/testdata/headqa_en-v0-res.json

+{"results": {"headqa_en": {"acc": 0.23559445660102116, "acc_norm": 0.2447118891320204, "acc_norm_stderr": 0.008211629406841468, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa_en": 0}}
\ No newline at end of file

tests/testdata/headqa_es-v0-loglikelihood

+767ca34d9714edd9fb030ddbcc35a64e5180d1e247b0cb557fbb22fdf971ad1f
\ No newline at end of file

tests/testdata/headqa_es-v0-res.json

+{"results": {"headqa_es": {"acc": 0.23559445660102116, "acc_norm": 0.25018234865062, "acc_norm_stderr": 0.008272783230806014, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa_es": 0}}
\ No newline at end of file

tests/testdata/lambada_mt_de-v0-loglikelihood

+5ad125e1708499832b2cee8c3388f89f9c0277010fd96fbd3359039ce8105984
\ No newline at end of file

tests/testdata/lambada_mt_de-v0-res.json

+{"results": {"lambada_mt_de": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_mt_de": 0}}
\ No newline at end of file

tests/testdata/lambada_mt_en-v0-loglikelihood

+6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20
\ No newline at end of file