{ "results": { "anli_r1": { "acc": 0.329, "acc_stderr": 0.014865395385928367 }, "anli_r2": { "acc": 0.32, "acc_stderr": 0.014758652303574878 }, "anli_r3": { "acc": 0.3408333333333333, "acc_stderr": 0.013688600793296939 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.0673769750864465, "f1": 0.3335687382297552 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 }, "hellaswag": { "acc": 0.48028281218880703, "acc_stderr": 0.004985900172317698, "acc_norm": 0.6314479187412866, "acc_norm_stderr": 0.004814261966376849 }, "rte": { "acc": 0.5090252707581228, "acc_stderr": 0.030091559826331334 }, "winogrande": { "acc": 0.5682715074980268, "acc_stderr": 0.01392087211001071 }, "storycloze_2016": { "acc": 0.7215392838054516, "acc_stderr": 0.010365521460604413 }, "boolq": { "acc": 0.6180428134556575, "acc_stderr": 0.008497851998427192 }, "arc_easy": { "acc": 0.6102693602693603, "acc_stderr": 0.010007169391797051, "acc_norm": 0.5538720538720538, "acc_norm_stderr": 0.01020005782876501 }, "arc_challenge": { "acc": 0.26023890784982934, "acc_stderr": 0.012821930225112566, "acc_norm": 0.3003412969283277, "acc_norm_stderr": 0.013395909309956997 }, "sciq": { "acc": 0.853, "acc_stderr": 0.011203415395160336, "acc_norm": 0.773, "acc_norm_stderr": 0.013253174964763921 }, "piqa": { "acc": 0.7633297062023939, "acc_stderr": 0.009916841655042809, "acc_norm": 0.7665941240478781, "acc_norm_stderr": 0.009869247889520986 } }, "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 } }