{ "results": { "anli_r1": { "acc": 0.332, "acc_stderr": 0.014899597242811483 }, "anli_r2": { "acc": 0.344, "acc_stderr": 0.015029633724408947 }, "anli_r3": { "acc": 0.3375, "acc_stderr": 0.013655897185463653 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.285919540229885 }, "copa": { "acc": 0.68, "acc_stderr": 0.04688261722621505 }, "hellaswag": { "acc": 0.39912368054172476, "acc_stderr": 0.004887174080003037, "acc_norm": 0.4940250946026688, "acc_norm_stderr": 0.0049894251333779055 }, "rte": { "acc": 0.48014440433212996, "acc_stderr": 0.0300727231673172 }, "winogrande": { "acc": 0.526440410418311, "acc_stderr": 0.01403282387440722 }, "storycloze_2016": { "acc": 0.6451095670764297, "acc_stderr": 0.011064787659904119 }, "boolq": { "acc": 0.43730886850152906, "acc_stderr": 0.008676043429497427 }, "arc_easy": { "acc": 0.4663299663299663, "acc_stderr": 0.010236494647406476, "acc_norm": 0.4591750841750842, "acc_norm_stderr": 0.010225526906982606 }, "arc_challenge": { "acc": 0.22184300341296928, "acc_stderr": 0.012141659068147884, "acc_norm": 0.23720136518771331, "acc_norm_stderr": 0.01243039982926085 }, "sciq": { "acc": 0.737, "acc_stderr": 0.013929286594259741, "acc_norm": 0.679, "acc_norm_stderr": 0.014770821817934649 }, "piqa": { "acc": 0.6996735582154516, "acc_stderr": 0.010695225308183138, "acc_norm": 0.7018498367791077, "acc_norm_stderr": 0.01067296411400829 } }, "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 } }