{ "results": { "anli_r1": { "acc": 0.317, "acc_stderr": 0.01472167543888022 }, "anli_r2": { "acc": 0.314, "acc_stderr": 0.014683991951087966 }, "anli_r3": { "acc": 0.355, "acc_stderr": 0.013819249004047296 }, "cb": { "acc": 0.30357142857142855, "acc_stderr": 0.06199938655510754, "f1": 0.20076628352490422 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.477096195976897, "acc_stderr": 0.004984543540932339, "acc_norm": 0.6249751045608445, "acc_norm_stderr": 0.0048313992185002475 }, "rte": { "acc": 0.5126353790613718, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.6006314127861089, "acc_stderr": 0.013764933546717614 }, "storycloze_2016": { "acc": 0.7108498129342598, "acc_stderr": 0.010484068799942077 }, "boolq": { "acc": 0.6030581039755352, "acc_stderr": 0.00855727696467513 }, "arc_easy": { "acc": 0.6241582491582491, "acc_stderr": 0.00993843637317063, "acc_norm": 0.5833333333333334, "acc_norm_stderr": 0.010116282977781263 }, "arc_challenge": { "acc": 0.2883959044368601, "acc_stderr": 0.013238394422428173, "acc_norm": 0.3165529010238908, "acc_norm_stderr": 0.01359243151906808 }, "sciq": { "acc": 0.901, "acc_stderr": 0.00944924802766276, "acc_norm": 0.874, "acc_norm_stderr": 0.010499249222408035 }, "piqa": { "acc": 0.7595212187159956, "acc_stderr": 0.009971345364651073, "acc_norm": 0.750272034820457, "acc_norm_stderr": 0.010099232969867469 } }, "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 } }