{ "results": { "anli_r1": { "acc": 0.324, "acc_stderr": 0.014806864733738863 }, "anli_r2": { "acc": 0.373, "acc_stderr": 0.01530049362292281 }, "anli_r3": { "acc": 0.3475, "acc_stderr": 0.013751753243291852 }, "cb": { "acc": 0.5357142857142857, "acc_stderr": 0.06724777654937658, "f1": 0.466241360978203 }, "copa": { "acc": 0.8, "acc_stderr": 0.04020151261036845 }, "hellaswag": { "acc": 0.47231627165903206, "acc_stderr": 0.004982127315605219, "acc_norm": 0.6231826329416451, "acc_norm_stderr": 0.004835981632401606 }, "rte": { "acc": 0.6028880866425993, "acc_stderr": 0.029452371378346828 }, "winogrande": { "acc": 0.5840568271507498, "acc_stderr": 0.013852485356798252 }, "storycloze_2016": { "acc": 0.7231427044361304, "acc_stderr": 0.01034711289027692 }, "boolq": { "acc": 0.617125382262997, "acc_stderr": 0.008501734385335953 }, "arc_easy": { "acc": 0.6216329966329966, "acc_stderr": 0.009951575683331949, "acc_norm": 0.6018518518518519, "acc_norm_stderr": 0.010044662374653396 }, "arc_challenge": { "acc": 0.2815699658703072, "acc_stderr": 0.013143376735009026, "acc_norm": 0.3225255972696246, "acc_norm_stderr": 0.01365998089427737 }, "sciq": { "acc": 0.905, "acc_stderr": 0.009276910103103286, "acc_norm": 0.891, "acc_norm_stderr": 0.009859828407037186 }, "piqa": { "acc": 0.7540805223068553, "acc_stderr": 0.010047331865625193, "acc_norm": 0.7627856365614799, "acc_norm_stderr": 0.009924694933586371 } }, "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 } }