{ "results": { "anli_r1": { "acc": 0.328, "acc_stderr": 0.014853842487270333 }, "anli_r2": { "acc": 0.351, "acc_stderr": 0.015100563798316409 }, "anli_r3": { "acc": 0.34833333333333333, "acc_stderr": 0.013759437498874086 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.06633634150359541, "f1": 0.3815668202764977 }, "copa": { "acc": 0.8, "acc_stderr": 0.04020151261036845 }, "hellaswag": { "acc": 0.46863174666401114, "acc_stderr": 0.004979952166595543, "acc_norm": 0.6213901613224457, "acc_norm_stderr": 0.0048404936031661945 }, "rte": { "acc": 0.5090252707581228, "acc_stderr": 0.030091559826331334 }, "winogrande": { "acc": 0.574585635359116, "acc_stderr": 0.013895257666646378 }, "storycloze_2016": { "acc": 0.7258150721539284, "acc_stderr": 0.010316062787590006 }, "boolq": { "acc": 0.6058103975535168, "acc_stderr": 0.008546995661233634 }, "arc_easy": { "acc": 0.6165824915824916, "acc_stderr": 0.009976995068264717, "acc_norm": 0.6060606060606061, "acc_norm_stderr": 0.010026305355981814 }, "arc_challenge": { "acc": 0.30119453924914674, "acc_stderr": 0.01340674176784762, "acc_norm": 0.31143344709897613, "acc_norm_stderr": 0.013532472099850947 }, "sciq": { "acc": 0.903, "acc_stderr": 0.009363689373248088, "acc_norm": 0.891, "acc_norm_stderr": 0.009859828407037185 }, "piqa": { "acc": 0.7611534276387377, "acc_stderr": 0.0099481203853375, "acc_norm": 0.7600652883569097, "acc_norm_stderr": 0.009963625892809545 } }, "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 } }