{ "results": { "anli_r1": { "acc": 0.306, "acc_stderr": 0.01458000605543697 }, "anli_r2": { "acc": 0.339, "acc_stderr": 0.014976758771620347 }, "anli_r3": { "acc": 0.33166666666666667, "acc_stderr": 0.013596836729485166 }, "cb": { "acc": 0.19642857142857142, "acc_stderr": 0.05357142857142858, "f1": 0.20578463681911954 }, "copa": { "acc": 0.82, "acc_stderr": 0.038612291966536955 }, "hellaswag": { "acc": 0.5296753634734117, "acc_stderr": 0.004980985384152899, "acc_norm": 0.7057359091814379, "acc_norm_stderr": 0.004547798964126677 }, "rte": { "acc": 0.5667870036101083, "acc_stderr": 0.029826764082138274 }, "winogrande": { "acc": 0.6408839779005525, "acc_stderr": 0.013483115202120234 }, "storycloze_2016": { "acc": 0.7621592731159808, "acc_stderr": 0.009845667782049759 }, "boolq": { "acc": 0.6608562691131499, "acc_stderr": 0.008280145027624473 }, "arc_easy": { "acc": 0.6755050505050505, "acc_stderr": 0.009606970654515781, "acc_norm": 0.6561447811447811, "acc_norm_stderr": 0.009746660584852442 }, "arc_challenge": { "acc": 0.3250853242320819, "acc_stderr": 0.013688147309729119, "acc_norm": 0.35580204778157, "acc_norm_stderr": 0.013990571137918758 }, "sciq": { "acc": 0.944, "acc_stderr": 0.007274401481697058, "acc_norm": 0.935, "acc_norm_stderr": 0.007799733061832014 }, "piqa": { "acc": 0.7758433079434167, "acc_stderr": 0.00972989795641005, "acc_norm": 0.7883569096844396, "acc_norm_stderr": 0.009530351270479393 } }, "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 } }