{ "results": { "anli_r1": { "acc": 0.333, "acc_stderr": 0.014910846164229871 }, "anli_r2": { "acc": 0.342, "acc_stderr": 0.01500870618212173 }, "anli_r3": { "acc": 0.3383333333333333, "acc_stderr": 0.013664144006618278 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.18803418803418803 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909282 }, "hellaswag": { "acc": 0.4357697669786895, "acc_stderr": 0.004948439229523916, "acc_norm": 0.5615415255925115, "acc_norm_stderr": 0.0049518409782196935 }, "rte": { "acc": 0.5234657039711191, "acc_stderr": 0.03006330041190266 }, "winogrande": { "acc": 0.5682715074980268, "acc_stderr": 0.013920872110010713 }, "storycloze_2016": { "acc": 0.694815606627472, "acc_stderr": 0.010648664383985661 }, "boolq": { "acc": 0.6119266055045871, "acc_stderr": 0.008523130584760848 }, "arc_easy": { "acc": 0.561026936026936, "acc_stderr": 0.010183076012972067, "acc_norm": 0.5084175084175084, "acc_norm_stderr": 0.010258329515226459 }, "arc_challenge": { "acc": 0.23890784982935154, "acc_stderr": 0.012461071376316614, "acc_norm": 0.27986348122866894, "acc_norm_stderr": 0.013119040897725925 }, "sciq": { "acc": 0.812, "acc_stderr": 0.012361586015103761, "acc_norm": 0.729, "acc_norm_stderr": 0.014062601350986186 }, "piqa": { "acc": 0.7328618063112078, "acc_stderr": 0.010323440492612433, "acc_norm": 0.7426550598476604, "acc_norm_stderr": 0.01019992106479251 } }, "versions": { "anli_r1": 0, "anli_r2": 0, "anli_r3": 0, "cb": 1, "copa": 0, "hellaswag": 0, "rte": 0, "winogrande": 0, "storycloze_2016": 0, "boolq": 1, "arc_easy": 0, "arc_challenge": 0, "sciq": 0, "piqa": 0 } }