{ "results": { "anli_r1": { "acc": 0.319, "acc_stderr": 0.014746404865473479 }, "anli_r2": { "acc": 0.318, "acc_stderr": 0.0147340793093119 }, "anli_r3": { "acc": 0.3458333333333333, "acc_stderr": 0.013736245342311012 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.31876138433515483 }, "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036623 }, "hellaswag": { "acc": 0.533559051981677, "acc_stderr": 0.0049785296421409365, "acc_norm": 0.7054371639115714, "acc_norm_stderr": 0.004549143750428458 }, "rte": { "acc": 0.5523465703971119, "acc_stderr": 0.02993107036293953 }, "winogrande": { "acc": 0.6179952644041041, "acc_stderr": 0.013655578215970422 }, "storycloze_2016": { "acc": 0.7455905932656334, "acc_stderr": 0.010071542492663043 }, "boolq": { "acc": 0.6461773700305811, "acc_stderr": 0.008362983020904465 }, "arc_easy": { "acc": 0.6704545454545454, "acc_stderr": 0.009645184190953855, "acc_norm": 0.6439393939393939, "acc_norm_stderr": 0.009825454608416303 }, "arc_challenge": { "acc": 0.34215017064846415, "acc_stderr": 0.013864152159177278, "acc_norm": 0.35494880546075086, "acc_norm_stderr": 0.013983036904094095 }, "sciq": { "acc": 0.928, "acc_stderr": 0.008178195576218681, "acc_norm": 0.915, "acc_norm_stderr": 0.008823426366942317 }, "piqa": { "acc": 0.7736670293797606, "acc_stderr": 0.009763294246879425, "acc_norm": 0.7823721436343852, "acc_norm_stderr": 0.009627407474840869 } }, "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 } }