{ "results": { "anli_r1": { "acc": 0.335, "acc_stderr": 0.014933117490932575 }, "anli_r2": { "acc": 0.333, "acc_stderr": 0.01491084616422986 }, "anli_r3": { "acc": 0.33416666666666667, "acc_stderr": 0.013622434813136781 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.21956970232832299 }, "copa": { "acc": 0.68, "acc_stderr": 0.046882617226215034 }, "hellaswag": { "acc": 0.4700258912567218, "acc_stderr": 0.00498080723113675, "acc_norm": 0.6167098187612029, "acc_norm_stderr": 0.00485194417067125 }, "rte": { "acc": 0.5270758122743683, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.595895816890292, "acc_stderr": 0.013791610664670858 }, "storycloze_2016": { "acc": 0.7167290219134153, "acc_stderr": 0.010419760409155363 }, "boolq": { "acc": 0.5984709480122324, "acc_stderr": 0.008573784490094752 }, "arc_easy": { "acc": 0.5888047138047138, "acc_stderr": 0.010096663811817681, "acc_norm": 0.5197811447811448, "acc_norm_stderr": 0.010251751199542738 }, "arc_challenge": { "acc": 0.2619453924914676, "acc_stderr": 0.012849054826858115, "acc_norm": 0.29180887372013653, "acc_norm_stderr": 0.013284525292403508 }, "sciq": { "acc": 0.845, "acc_stderr": 0.01145015747079947, "acc_norm": 0.766, "acc_norm_stderr": 0.01339490288966001 }, "piqa": { "acc": 0.7519042437431991, "acc_stderr": 0.010077118315574719, "acc_norm": 0.7568008705114254, "acc_norm_stderr": 0.01000961195385892 } }, "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 } }