{ "results": { "anli_r1": { "acc": 0.367, "acc_stderr": 0.015249378464171749 }, "anli_r2": { "acc": 0.355, "acc_stderr": 0.015139491543780532 }, "anli_r3": { "acc": 0.35583333333333333, "acc_stderr": 0.01382651874849331 }, "cb": { "acc": 0.5178571428571429, "acc_stderr": 0.06737697508644647, "f1": 0.3175 }, "copa": { "acc": 0.78, "acc_stderr": 0.04163331998932261 }, "hellaswag": { "acc": 0.4297948615813583, "acc_stderr": 0.004940349676769324, "acc_norm": 0.5615415255925115, "acc_norm_stderr": 0.0049518409782196935 }, "rte": { "acc": 0.5487364620938628, "acc_stderr": 0.029953149241808946 }, "winogrande": { "acc": 0.5666929755327546, "acc_stderr": 0.013926915052757345 }, "storycloze_2016": { "acc": 0.6932121859967931, "acc_stderr": 0.010664275190473634 }, "boolq": { "acc": 0.5724770642201835, "acc_stderr": 0.008652692997177337 }, "arc_easy": { "acc": 0.5917508417508418, "acc_stderr": 0.010085566195791245, "acc_norm": 0.5669191919191919, "acc_norm_stderr": 0.010167478013701789 }, "arc_challenge": { "acc": 0.2525597269624573, "acc_stderr": 0.012696728980207708, "acc_norm": 0.2832764505119454, "acc_norm_stderr": 0.013167478735134576 }, "sciq": { "acc": 0.874, "acc_stderr": 0.010499249222408047, "acc_norm": 0.853, "acc_norm_stderr": 0.011203415395160328 }, "piqa": { "acc": 0.7295973884657236, "acc_stderr": 0.010363167031620798, "acc_norm": 0.733949945593036, "acc_norm_stderr": 0.010310039263352826 } }, "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 } }