{ "results": { "anli_r1": { "acc": 0.337, "acc_stderr": 0.014955087918653591 }, "anli_r2": { "acc": 0.324, "acc_stderr": 0.014806864733738854 }, "anli_r3": { "acc": 0.3416666666666667, "acc_stderr": 0.013696658778002515 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.3235294117647059 }, "copa": { "acc": 0.78, "acc_stderr": 0.041633319989322626 }, "hellaswag": { "acc": 0.47849034056960765, "acc_stderr": 0.004985162074336111, "acc_norm": 0.6335391356303525, "acc_norm_stderr": 0.0048085268027185865 }, "rte": { "acc": 0.5523465703971119, "acc_stderr": 0.029931070362939533 }, "winogrande": { "acc": 0.585635359116022, "acc_stderr": 0.013844846232268563 }, "storycloze_2016": { "acc": 0.7188669160876536, "acc_stderr": 0.010395836091628105 }, "boolq": { "acc": 0.5889908256880734, "acc_stderr": 0.008605429733982185 }, "arc_easy": { "acc": 0.6123737373737373, "acc_stderr": 0.009997307914447612, "acc_norm": 0.5778619528619529, "acc_norm_stderr": 0.01013462052459227 }, "arc_challenge": { "acc": 0.28668941979522183, "acc_stderr": 0.01321498632927479, "acc_norm": 0.31399317406143346, "acc_norm_stderr": 0.013562691224726298 }, "sciq": { "acc": 0.898, "acc_stderr": 0.009575368801653885, "acc_norm": 0.89, "acc_norm_stderr": 0.009899393819724442 }, "piqa": { "acc": 0.7540805223068553, "acc_stderr": 0.010047331865625191, "acc_norm": 0.7573449401523396, "acc_norm_stderr": 0.01000200256970869 } }, "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 } }