{ "results": { "anli_r1": { "acc": 0.333, "acc_stderr": 0.014910846164229864 }, "anli_r2": { "acc": 0.334, "acc_stderr": 0.014922019523732967 }, "anli_r3": { "acc": 0.35, "acc_stderr": 0.013774667009018552 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.30857142857142855 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 }, "hellaswag": { "acc": 0.43925512846046605, "acc_stderr": 0.004952820538831887, "acc_norm": 0.5730930093606851, "acc_norm_stderr": 0.00493617678463196 }, "rte": { "acc": 0.4657039711191336, "acc_stderr": 0.030025579819366422 }, "winogrande": { "acc": 0.5509076558800315, "acc_stderr": 0.013979459389140834 }, "storycloze_2016": { "acc": 0.6937466595403528, "acc_stderr": 0.010659088460112756 }, "boolq": { "acc": 0.5990825688073395, "acc_stderr": 0.008571628711617004 }, "arc_easy": { "acc": 0.5816498316498316, "acc_stderr": 0.010122061470742853, "acc_norm": 0.571969696969697, "acc_norm_stderr": 0.010152943316426265 }, "arc_challenge": { "acc": 0.27474402730375425, "acc_stderr": 0.013044617212771227, "acc_norm": 0.2883959044368601, "acc_norm_stderr": 0.013238394422428164 }, "sciq": { "acc": 0.869, "acc_stderr": 0.010674874844837956, "acc_norm": 0.85, "acc_norm_stderr": 0.011297239823409291 }, "piqa": { "acc": 0.735038084874864, "acc_stderr": 0.010296557993316049, "acc_norm": 0.733949945593036, "acc_norm_stderr": 0.010310039263352824 } }, "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 } }