{ "results": { "anli_r1": { "acc": 0.334, "acc_stderr": 0.014922019523732953 }, "anli_r2": { "acc": 0.321, "acc_stderr": 0.01477082181793464 }, "anli_r3": { "acc": 0.3408333333333333, "acc_stderr": 0.013688600793296936 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.3390804597701149 }, "copa": { "acc": 0.77, "acc_stderr": 0.04229525846816506 }, "hellaswag": { "acc": 0.4743079067914758, "acc_stderr": 0.004983189711208521, "acc_norm": 0.625273849830711, "acc_norm_stderr": 0.004830628620181016 }, "rte": { "acc": 0.5090252707581228, "acc_stderr": 0.030091559826331334 }, "winogrande": { "acc": 0.5722178374112076, "acc_stderr": 0.01390513401383995 }, "storycloze_2016": { "acc": 0.7113842864778194, "acc_stderr": 0.01047831178564294 }, "boolq": { "acc": 0.6305810397553517, "acc_stderr": 0.008441557531799619 }, "arc_easy": { "acc": 0.6224747474747475, "acc_stderr": 0.009947227833469432, "acc_norm": 0.5686026936026936, "acc_norm_stderr": 0.01016275284774751 }, "arc_challenge": { "acc": 0.29692832764505117, "acc_stderr": 0.013352025976725225, "acc_norm": 0.31313993174061433, "acc_norm_stderr": 0.013552671543623504 }, "sciq": { "acc": 0.889, "acc_stderr": 0.009938701010583726, "acc_norm": 0.867, "acc_norm_stderr": 0.010743669132397337 }, "piqa": { "acc": 0.7480957562568009, "acc_stderr": 0.010128421335088683, "acc_norm": 0.7562568008705114, "acc_norm_stderr": 0.010017199471500609 } }, "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 } }