{ "results": { "anli_r1": { "acc": 0.335, "acc_stderr": 0.014933117490932575 }, "anli_r2": { "acc": 0.351, "acc_stderr": 0.015100563798316403 }, "anli_r3": { "acc": 0.3375, "acc_stderr": 0.013655897185463658 }, "cb": { "acc": 0.32142857142857145, "acc_stderr": 0.0629736228905634, "f1": 0.2819405899886936 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909282 }, "hellaswag": { "acc": 0.47629954192391954, "acc_stderr": 0.004984172621822885, "acc_norm": 0.6317466640111532, "acc_norm_stderr": 0.00481344861540445 }, "rte": { "acc": 0.5342960288808665, "acc_stderr": 0.030025579819366422 }, "winogrande": { "acc": 0.6069455406471981, "acc_stderr": 0.013727276249108453 }, "storycloze_2016": { "acc": 0.7194013896312133, "acc_stderr": 0.010389809647288827 }, "boolq": { "acc": 0.5755351681957187, "acc_stderr": 0.008644688121685498 }, "arc_easy": { "acc": 0.6376262626262627, "acc_stderr": 0.009863468202583783, "acc_norm": 0.627104377104377, "acc_norm_stderr": 0.009922743197129241 }, "arc_challenge": { "acc": 0.2841296928327645, "acc_stderr": 0.013179442447653887, "acc_norm": 0.3199658703071672, "acc_norm_stderr": 0.013631345807016191 }, "sciq": { "acc": 0.912, "acc_stderr": 0.008963053962592074, "acc_norm": 0.889, "acc_norm_stderr": 0.009938701010583726 }, "piqa": { "acc": 0.750816104461371, "acc_stderr": 0.010091882770120216, "acc_norm": 0.7682263329706203, "acc_norm_stderr": 0.009845143772794048 } }, "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 } }