{ "results": { "anli_r1": { "acc": 0.321, "acc_stderr": 0.014770821817934642 }, "anli_r2": { "acc": 0.321, "acc_stderr": 0.014770821817934647 }, "anli_r3": { "acc": 0.3333333333333333, "acc_stderr": 0.013613950010225603 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.35714285714285704 }, "copa": { "acc": 0.74, "acc_stderr": 0.04408440022768079 }, "hellaswag": { "acc": 0.4691296554471221, "acc_stderr": 0.004980262025472478, "acc_norm": 0.6161123282214698, "acc_norm_stderr": 0.004853371646239242 }, "rte": { "acc": 0.5667870036101083, "acc_stderr": 0.02982676408213828 }, "winogrande": { "acc": 0.5651144435674822, "acc_stderr": 0.013932814110418025 }, "storycloze_2016": { "acc": 0.721004810261892, "acc_stderr": 0.010371620932652793 }, "boolq": { "acc": 0.5773700305810398, "acc_stderr": 0.008639722698719023 }, "arc_easy": { "acc": 0.6043771043771043, "acc_stderr": 0.010033741393430986, "acc_norm": 0.5686026936026936, "acc_norm_stderr": 0.010162752847747501 }, "arc_challenge": { "acc": 0.28668941979522183, "acc_stderr": 0.013214986329274762, "acc_norm": 0.3037542662116041, "acc_norm_stderr": 0.013438909184778759 }, "sciq": { "acc": 0.883, "acc_stderr": 0.010169287802713329, "acc_norm": 0.859, "acc_norm_stderr": 0.011010914595992445 }, "piqa": { "acc": 0.7519042437431991, "acc_stderr": 0.010077118315574715, "acc_norm": 0.7606093579978237, "acc_norm_stderr": 0.00995588425029168 } }, "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 } }