{ "results": { "anli_r1": { "acc": 0.323, "acc_stderr": 0.014794927843348637 }, "anli_r2": { "acc": 0.325, "acc_stderr": 0.014818724459095527 }, "anli_r3": { "acc": 0.33666666666666667, "acc_stderr": 0.013647602942406389 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.32592592592592595 }, "copa": { "acc": 0.74, "acc_stderr": 0.04408440022768077 }, "hellaswag": { "acc": 0.4780920135431189, "acc_stderr": 0.004984989320648131, "acc_norm": 0.6283608842859988, "acc_norm_stderr": 0.004822550638450904 }, "rte": { "acc": 0.5487364620938628, "acc_stderr": 0.029953149241808946 }, "winogrande": { "acc": 0.5895816890292028, "acc_stderr": 0.013825107120035863 }, "storycloze_2016": { "acc": 0.7135221806520577, "acc_stderr": 0.01045510591863303 }, "boolq": { "acc": 0.6235474006116208, "acc_stderr": 0.008473882279194588 }, "arc_easy": { "acc": 0.6321548821548821, "acc_stderr": 0.009894923464455196, "acc_norm": 0.5795454545454546, "acc_norm_stderr": 0.010129114278546524 }, "arc_challenge": { "acc": 0.2713310580204778, "acc_stderr": 0.012993807727545801, "acc_norm": 0.3054607508532423, "acc_norm_stderr": 0.01346008047800251 }, "sciq": { "acc": 0.905, "acc_stderr": 0.009276910103103326, "acc_norm": 0.873, "acc_norm_stderr": 0.010534798620855759 }, "piqa": { "acc": 0.7546245919477693, "acc_stderr": 0.0100398313204224, "acc_norm": 0.7622415669205659, "acc_norm_stderr": 0.009932525779525489 } }, "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 } }