{ "results": { "anli_r1": { "acc": 0.336, "acc_stderr": 0.014944140233795023 }, "anli_r2": { "acc": 0.326, "acc_stderr": 0.014830507204541037 }, "anli_r3": { "acc": 0.33, "acc_stderr": 0.013579531277800922 }, "cb": { "acc": 0.25, "acc_stderr": 0.058387420812114225, "f1": 0.2095321637426901 }, "copa": { "acc": 0.72, "acc_stderr": 0.045126085985421276 }, "hellaswag": { "acc": 0.4051981676956781, "acc_stderr": 0.004899270310557984, "acc_norm": 0.5231029675363473, "acc_norm_stderr": 0.004984452002563928 }, "rte": { "acc": 0.49097472924187724, "acc_stderr": 0.030091559826331334 }, "winogrande": { "acc": 0.5469613259668509, "acc_stderr": 0.013990366632148104 }, "storycloze_2016": { "acc": 0.6632816675574559, "acc_stderr": 0.010928525619392455 }, "boolq": { "acc": 0.57217125382263, "acc_stderr": 0.008653474894637182 }, "arc_easy": { "acc": 0.5854377104377104, "acc_stderr": 0.010108889212447769, "acc_norm": 0.5723905723905723, "acc_norm_stderr": 0.010151683397430677 }, "arc_challenge": { "acc": 0.2721843003412969, "acc_stderr": 0.013006600406423707, "acc_norm": 0.29436860068259385, "acc_norm_stderr": 0.013318528460539422 }, "sciq": { "acc": 0.891, "acc_stderr": 0.009859828407037188, "acc_norm": 0.883, "acc_norm_stderr": 0.010169287802713327 }, "piqa": { "acc": 0.721436343852013, "acc_stderr": 0.010459397235965182, "acc_norm": 0.719260065288357, "acc_norm_stderr": 0.010484325438311827 } }, "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 } }