{ "results": { "anli_r1": { "acc": 0.338, "acc_stderr": 0.014965960710224482 }, "anli_r2": { "acc": 0.371, "acc_stderr": 0.015283736211823188 }, "anli_r3": { "acc": 0.3416666666666667, "acc_stderr": 0.013696658778002514 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.3419913419913419 }, "copa": { "acc": 0.65, "acc_stderr": 0.047937248544110196 }, "hellaswag": { "acc": 0.3921529575781717, "acc_stderr": 0.004872326888655522, "acc_norm": 0.4898426608245369, "acc_norm_stderr": 0.004988751698341149 }, "rte": { "acc": 0.5776173285198556, "acc_stderr": 0.029731622646495887 }, "winogrande": { "acc": 0.5209155485398579, "acc_stderr": 0.014040185494212949 }, "storycloze_2016": { "acc": 0.6467129877071085, "acc_stderr": 0.011053474766125627 }, "boolq": { "acc": 0.5137614678899083, "acc_stderr": 0.008741742106878655 }, "arc_easy": { "acc": 0.49284511784511786, "acc_stderr": 0.01025873302244637, "acc_norm": 0.47685185185185186, "acc_norm_stderr": 0.010248782484554474 }, "arc_challenge": { "acc": 0.23976109215017063, "acc_stderr": 0.012476304127453946, "acc_norm": 0.26706484641638223, "acc_norm_stderr": 0.012928933196496352 }, "sciq": { "acc": 0.749, "acc_stderr": 0.013718133516888923, "acc_norm": 0.74, "acc_norm_stderr": 0.013877773329774166 }, "piqa": { "acc": 0.705658324265506, "acc_stderr": 0.0106333114703475, "acc_norm": 0.7040261153427638, "acc_norm_stderr": 0.010650414317148131 } }, "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 } }