{ "results": { "anli_r1": { "acc": 0.32, "acc_stderr": 0.014758652303574876 }, "anli_r2": { "acc": 0.34, "acc_stderr": 0.014987482264363935 }, "anli_r3": { "acc": 0.3275, "acc_stderr": 0.013553211167251951 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.28456510809451985 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909282 }, "hellaswag": { "acc": 0.4561840270862378, "acc_stderr": 0.004970585328297621, "acc_norm": 0.6068512248556065, "acc_norm_stderr": 0.0048745114668368 }, "rte": { "acc": 0.4548736462093863, "acc_stderr": 0.029973636495415252 }, "winogrande": { "acc": 0.5951065509076559, "acc_stderr": 0.013795927003124927 }, "storycloze_2016": { "acc": 0.7145911277391769, "acc_stderr": 0.010443395884062106 }, "boolq": { "acc": 0.5978593272171254, "acc_stderr": 0.008575926383211252 }, "arc_easy": { "acc": 0.6220538720538721, "acc_stderr": 0.009949405744045457, "acc_norm": 0.6317340067340067, "acc_norm_stderr": 0.009897286209010888 }, "arc_challenge": { "acc": 0.3037542662116041, "acc_stderr": 0.013438909184778757, "acc_norm": 0.3293515358361775, "acc_norm_stderr": 0.013734057652635474 }, "sciq": { "acc": 0.921, "acc_stderr": 0.008534156773333437, "acc_norm": 0.923, "acc_norm_stderr": 0.00843458014024065 }, "piqa": { "acc": 0.7475516866158868, "acc_stderr": 0.010135665547362364, "acc_norm": 0.7524483133841132, "acc_norm_stderr": 0.010069703966857116 } }, "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 } }