{ "results": { "anli_r1": { "acc": 0.327, "acc_stderr": 0.014842213153411242 }, "anli_r2": { "acc": 0.334, "acc_stderr": 0.014922019523732968 }, "anli_r3": { "acc": 0.3358333333333333, "acc_stderr": 0.013639261190932889 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.36502627806975624 }, "copa": { "acc": 0.66, "acc_stderr": 0.04760952285695238 }, "hellaswag": { "acc": 0.3937462656841267, "acc_stderr": 0.004875812021461996, "acc_norm": 0.48994224258115915, "acc_norm_stderr": 0.004988771791854512 }, "rte": { "acc": 0.5595667870036101, "acc_stderr": 0.02988212336311872 }, "winogrande": { "acc": 0.5303867403314917, "acc_stderr": 0.014026510839428743 }, "storycloze_2016": { "acc": 0.6702298236237306, "acc_stderr": 0.01087168247139514 }, "boolq": { "acc": 0.45321100917431195, "acc_stderr": 0.00870668126587249 }, "arc_easy": { "acc": 0.494949494949495, "acc_stderr": 0.010259260102565861, "acc_norm": 0.44612794612794615, "acc_norm_stderr": 0.01020005782876501 }, "arc_challenge": { "acc": 0.24232081911262798, "acc_stderr": 0.012521593295800115, "acc_norm": 0.2781569965870307, "acc_norm_stderr": 0.013094469919538793 }, "sciq": { "acc": 0.704, "acc_stderr": 0.01444273494157502, "acc_norm": 0.637, "acc_norm_stderr": 0.015213890444671283 }, "piqa": { "acc": 0.6969532100108814, "acc_stderr": 0.010722648689531525, "acc_norm": 0.7018498367791077, "acc_norm_stderr": 0.01067296411400829 } }, "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 } }