{ "results": { "anli_r1": { "acc": 0.321, "acc_stderr": 0.014770821817934661 }, "anli_r2": { "acc": 0.355, "acc_stderr": 0.01513949154378053 }, "anli_r3": { "acc": 0.35083333333333333, "acc_stderr": 0.013782212417178202 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.41546499477533966 }, "copa": { "acc": 0.72, "acc_stderr": 0.04512608598542128 }, "hellaswag": { "acc": 0.4582752439753037, "acc_stderr": 0.004972377085916326, "acc_norm": 0.6056562437761402, "acc_norm_stderr": 0.004877104939356237 }, "rte": { "acc": 0.51985559566787, "acc_stderr": 0.030072723167317184 }, "winogrande": { "acc": 0.5895816890292028, "acc_stderr": 0.013825107120035865 }, "storycloze_2016": { "acc": 0.709246392303581, "acc_stderr": 0.010501233625213076 }, "boolq": { "acc": 0.5871559633027523, "acc_stderr": 0.00861117243047287 }, "arc_easy": { "acc": 0.6300505050505051, "acc_stderr": 0.009906656266021158, "acc_norm": 0.6317340067340067, "acc_norm_stderr": 0.009897286209010888 }, "arc_challenge": { "acc": 0.30716723549488056, "acc_stderr": 0.013481034054980945, "acc_norm": 0.3199658703071672, "acc_norm_stderr": 0.013631345807016195 }, "sciq": { "acc": 0.924, "acc_stderr": 0.008384169266796401, "acc_norm": 0.93, "acc_norm_stderr": 0.008072494358323499 }, "piqa": { "acc": 0.7448313384113167, "acc_stderr": 0.01017157159252182, "acc_norm": 0.7546245919477693, "acc_norm_stderr": 0.010039831320422386 } }, "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 } }