{ "results": { "anli_r1": { "acc": 0.334, "acc_stderr": 0.014922019523732961 }, "anli_r2": { "acc": 0.34, "acc_stderr": 0.014987482264363935 }, "anli_r3": { "acc": 0.35083333333333333, "acc_stderr": 0.013782212417178197 }, "cb": { "acc": 0.17857142857142858, "acc_stderr": 0.051642771820087224, "f1": 0.18279613107199313 }, "copa": { "acc": 0.82, "acc_stderr": 0.03861229196653697 }, "hellaswag": { "acc": 0.454690300736905, "acc_stderr": 0.004969251445596333, "acc_norm": 0.5943039235212109, "acc_norm_stderr": 0.004900227226433378 }, "rte": { "acc": 0.4548736462093863, "acc_stderr": 0.029973636495415255 }, "winogrande": { "acc": 0.606156274664562, "acc_stderr": 0.013732114472668741 }, "storycloze_2016": { "acc": 0.7247461250668092, "acc_stderr": 0.010328538400500567 }, "boolq": { "acc": 0.6116207951070336, "acc_stderr": 0.008524357307908792 }, "arc_easy": { "acc": 0.5808080808080808, "acc_stderr": 0.010124905282491183, "acc_norm": 0.5711279461279462, "acc_norm_stderr": 0.010155440652900152 }, "arc_challenge": { "acc": 0.27559726962457337, "acc_stderr": 0.01305716965576184, "acc_norm": 0.30802047781569963, "acc_norm_stderr": 0.01349142951729204 }, "sciq": { "acc": 0.915, "acc_stderr": 0.008823426366942317, "acc_norm": 0.919, "acc_norm_stderr": 0.008632121032139993 }, "piqa": { "acc": 0.7285092491838956, "acc_stderr": 0.010376251176596137, "acc_norm": 0.7388465723612623, "acc_norm_stderr": 0.010248738649935587 } }, "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 } }