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

tests/testdata/lambada_mt_es-v0-res.json

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

tests/testdata/lambada_mt_fr-v0-loglikelihood

+5d16f4a0c51dc6d7b6df2ebeba2bbfa51e700b843779b559b3d90183d7b02a11
\ No newline at end of file

tests/testdata/lambada_mt_fr-v0-res.json

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

tests/testdata/lambada_mt_it-v0-loglikelihood

+fd87c6c5cf4e0499c5f9f80e5bd7ee6a4f3d2991902a0cc3ec9e6eaf22d6760a
\ No newline at end of file

tests/testdata/lambada_mt_it-v0-res.json

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

tests/testdata/logiqa-v0-loglikelihood

+12495c50454ba5e1ce0753bd18c09aaca516bebd27648d815e37b15229dbf198
\ No newline at end of file

tests/testdata/logiqa-v0-res.json

+{"results": {"logiqa": {"acc": 0.25806451612903225, "acc_norm": 0.2764976958525346, "acc_norm_stderr": 0.017543209075825194, "acc_stderr": 0.017162894755127077}}, "versions": {"logiqa": 0}}
\ No newline at end of file

tests/testdata/math_algebra-v0-greedy_until

+f19182ce697a2c095d9e5b56ee6659dc38c93994b69ca75d7c3d3f5fd87572b4
\ No newline at end of file

tests/testdata/math_algebra-v0-res.json

+{"results": {"math_algebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_algebra": 0}}
\ No newline at end of file

tests/testdata/math_counting_and_prob-v0-greedy_until

+2aa9ae43ee9dbb2457525247d7b65358632c5eaa9cbfc40cf95a4f17f5d942ad
\ No newline at end of file

tests/testdata/math_counting_and_prob-v0-res.json

+{"results": {"math_counting_and_prob": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_counting_and_prob": 0}}
\ No newline at end of file

tests/testdata/math_geometry-v0-greedy_until

+46bc4cb219b6903397da782699a684bdbb982c0c954ff82e6beeed5c84878f42
\ No newline at end of file

tests/testdata/math_geometry-v0-res.json

+{"results": {"math_geometry": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_geometry": 0}}
\ No newline at end of file

tests/testdata/math_intermediate_algebra-v0-greedy_until

+d53c699de272d517ed7ad783b4e692302be9f9f97a8d4ac7a6541e538a7cabe0
\ No newline at end of file

tests/testdata/math_intermediate_algebra-v0-res.json

+{"results": {"math_intermediate_algebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_intermediate_algebra": 0}}
\ No newline at end of file

tests/testdata/math_num_theory-v0-greedy_until

+b920ccb507afdcf3ef6f4c04891913731e9f32ec914801791c6d9f8abf6e1897
\ No newline at end of file

tests/testdata/math_num_theory-v0-res.json

+{"results": {"math_num_theory": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_num_theory": 0}}
\ No newline at end of file

tests/testdata/math_prealgebra-v0-greedy_until

+752cdf343d7152e476b0273065024f6ea0e0f47ea385c6bdf9067736cb39724a
\ No newline at end of file

tests/testdata/math_prealgebra-v0-res.json

+{"results": {"math_prealgebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_prealgebra": 0}}
\ No newline at end of file

tests/testdata/math_precalc-v0-greedy_until

+bc834b06fd79473ca6fe38a51b714aad0bf0478c1b0eec787eca34dbdf69cb71
\ No newline at end of file