{ "results": { "anli_r1": { "acc": 0.322, "acc_stderr": 0.014782913600996666 }, "anli_r2": { "acc": 0.332, "acc_stderr": 0.014899597242811471 }, "anli_r3": { "acc": 0.31583333333333335, "acc_stderr": 0.013424568830356457 }, "cb": { "acc": 0.44642857142857145, "acc_stderr": 0.06703189227942398, "f1": 0.3234429296979417 }, "copa": { "acc": 0.65, "acc_stderr": 0.0479372485441102 }, "hellaswag": { "acc": 0.33339972117108146, "acc_stderr": 0.004704645214506539, "acc_norm": 0.39583748257319257, "acc_norm_stderr": 0.004880303863138502 }, "rte": { "acc": 0.516245487364621, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.5067087608524072, "acc_stderr": 0.014051220692330349 }, "storycloze_2016": { "acc": 0.6215927311598076, "acc_stderr": 0.011215325833205824 }, "boolq": { "acc": 0.5204892966360857, "acc_stderr": 0.008737709345935946 }, "arc_easy": { "acc": 0.5420875420875421, "acc_stderr": 0.010223371342195902, "acc_norm": 0.5214646464646465, "acc_norm_stderr": 0.010250325159456652 }, "arc_challenge": { "acc": 0.23720136518771331, "acc_stderr": 0.012430399829260846, "acc_norm": 0.2551194539249147, "acc_norm_stderr": 0.012739038695202098 }, "sciq": { "acc": 0.882, "acc_stderr": 0.010206869264381791, "acc_norm": 0.874, "acc_norm_stderr": 0.010499249222408033 }, "piqa": { "acc": 0.6708378672470077, "acc_stderr": 0.010963750414134703, "acc_norm": 0.6648531011969532, "acc_norm_stderr": 0.011013513128643931 } }, "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 } }