{ "results": { "anli_r1": { "acc": 0.33, "acc_stderr": 0.014876872027456732 }, "anli_r2": { "acc": 0.337, "acc_stderr": 0.014955087918653598 }, "anli_r3": { "acc": 0.3375, "acc_stderr": 0.013655897185463657 }, "cb": { "acc": 0.44642857142857145, "acc_stderr": 0.06703189227942398, "f1": 0.2706349206349206 }, "copa": { "acc": 0.78, "acc_stderr": 0.04163331998932261 }, "hellaswag": { "acc": 0.43487353116908983, "acc_stderr": 0.004947272454226208, "acc_norm": 0.5603465445130452, "acc_norm_stderr": 0.004953305461311746 }, "rte": { "acc": 0.5270758122743683, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.5785319652722968, "acc_stderr": 0.013878072377497606 }, "storycloze_2016": { "acc": 0.7033671833244255, "acc_stderr": 0.010562819181563227 }, "boolq": { "acc": 0.5825688073394495, "acc_stderr": 0.008624990050216684 }, "arc_easy": { "acc": 0.6056397306397306, "acc_stderr": 0.010028176038393, "acc_norm": 0.5808080808080808, "acc_norm_stderr": 0.010124905282491183 }, "arc_challenge": { "acc": 0.27986348122866894, "acc_stderr": 0.013119040897725922, "acc_norm": 0.2986348122866894, "acc_norm_stderr": 0.01337407861506875 }, "sciq": { "acc": 0.875, "acc_stderr": 0.010463483381956722, "acc_norm": 0.842, "acc_norm_stderr": 0.011539894677559559 }, "piqa": { "acc": 0.7149075081610446, "acc_stderr": 0.010533270588738937, "acc_norm": 0.7110990206746464, "acc_norm_stderr": 0.010575111841364908 } }, "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 } }