{ "results": { "anli_r1": { "acc": 0.325, "acc_stderr": 0.014818724459095526 }, "anli_r2": { "acc": 0.326, "acc_stderr": 0.014830507204541033 }, "anli_r3": { "acc": 0.3475, "acc_stderr": 0.013751753243291854 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.06737697508644648, "f1": 0.3356643356643356 }, "copa": { "acc": 0.72, "acc_stderr": 0.04512608598542129 }, "hellaswag": { "acc": 0.4523003385779725, "acc_stderr": 0.004967023435680015, "acc_norm": 0.5990838478390759, "acc_norm_stderr": 0.004890824718530304 }, "rte": { "acc": 0.49458483754512633, "acc_stderr": 0.030094698123239966 }, "winogrande": { "acc": 0.5911602209944752, "acc_stderr": 0.013816954295135686 }, "storycloze_2016": { "acc": 0.694815606627472, "acc_stderr": 0.010648664383985665 }, "boolq": { "acc": 0.6039755351681957, "acc_stderr": 0.008553881336813412 }, "arc_easy": { "acc": 0.6367845117845118, "acc_stderr": 0.009868397136118794, "acc_norm": 0.63510101010101, "acc_norm_stderr": 0.009878157021155649 }, "arc_challenge": { "acc": 0.31569965870307165, "acc_stderr": 0.013582571095815293, "acc_norm": 0.3250853242320819, "acc_norm_stderr": 0.013688147309729124 }, "sciq": { "acc": 0.927, "acc_stderr": 0.00823035471524406, "acc_norm": 0.924, "acc_norm_stderr": 0.008384169266796384 }, "piqa": { "acc": 0.750816104461371, "acc_stderr": 0.01009188277012022, "acc_norm": 0.7546245919477693, "acc_norm_stderr": 0.010039831320422386 } }, "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 } }