{ "results": { "anli_r1": { "acc": 0.327, "acc_stderr": 0.014842213153411249 }, "anli_r2": { "acc": 0.332, "acc_stderr": 0.014899597242811483 }, "anli_r3": { "acc": 0.3416666666666667, "acc_stderr": 0.013696658778002512 }, "cb": { "acc": 0.44642857142857145, "acc_stderr": 0.06703189227942397, "f1": 0.3083804143126177 }, "copa": { "acc": 0.52, "acc_stderr": 0.050211673156867795 }, "hellaswag": { "acc": 0.26329416450906196, "acc_stderr": 0.004395205528158076, "acc_norm": 0.26926906990639315, "acc_norm_stderr": 0.004426734718808876 }, "rte": { "acc": 0.49097472924187724, "acc_stderr": 0.030091559826331334 }, "winogrande": { "acc": 0.505130228887135, "acc_stderr": 0.014051745961790516 }, "storycloze_2016": { "acc": 0.5200427578834848, "acc_stderr": 0.011553138977961012 }, "boolq": { "acc": 0.5938837920489297, "acc_stderr": 0.00858951094378741 }, "arc_easy": { "acc": 0.34595959595959597, "acc_stderr": 0.009760749624427521, "acc_norm": 0.3371212121212121, "acc_norm_stderr": 0.009700146509130083 }, "arc_challenge": { "acc": 0.17064846416382254, "acc_stderr": 0.010993654168413735, "acc_norm": 0.2150170648464164, "acc_norm_stderr": 0.01200571763413361 }, "sciq": { "acc": 0.628, "acc_stderr": 0.015292149942040577, "acc_norm": 0.576, "acc_norm_stderr": 0.01563548747140519 }, "piqa": { "acc": 0.5696409140369967, "acc_stderr": 0.011552114834700509, "acc_norm": 0.5647442872687704, "acc_norm_stderr": 0.011567608588759421 } }, "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 } }