Muennighoff's picture
Add eval
d522938
{
"results": {
"anli_r1": {
"acc": 0.337,
"acc_stderr": 0.014955087918653616
},
"anli_r2": {
"acc": 0.328,
"acc_stderr": 0.014853842487270334
},
"anli_r3": {
"acc": 0.33916666666666667,
"acc_stderr": 0.013672343491681822
},
"cb": {
"acc": 0.32142857142857145,
"acc_stderr": 0.06297362289056341,
"f1": 0.24285714285714288
},
"copa": {
"acc": 0.74,
"acc_stderr": 0.04408440022768078
},
"hellaswag": {
"acc": 0.4298944433379805,
"acc_stderr": 0.004940490508240647,
"acc_norm": 0.5665206134236208,
"acc_norm_stderr": 0.004945424771611602
},
"rte": {
"acc": 0.4657039711191336,
"acc_stderr": 0.030025579819366426
},
"winogrande": {
"acc": 0.5461720599842147,
"acc_stderr": 0.01399244156370706
},
"storycloze_2016": {
"acc": 0.6910742918225548,
"acc_stderr": 0.010684853966268455
},
"boolq": {
"acc": 0.5804281345565749,
"acc_stderr": 0.008631175489166726
},
"arc_easy": {
"acc": 0.57996632996633,
"acc_stderr": 0.010127718838529321,
"acc_norm": 0.5681818181818182,
"acc_norm_stderr": 0.010163945352271733
},
"arc_challenge": {
"acc": 0.2696245733788396,
"acc_stderr": 0.012968040686869143,
"acc_norm": 0.28924914675767915,
"acc_norm_stderr": 0.013250012579393443
},
"sciq": {
"acc": 0.891,
"acc_stderr": 0.00985982840703719,
"acc_norm": 0.882,
"acc_norm_stderr": 0.01020686926438179
},
"piqa": {
"acc": 0.7334058759521219,
"acc_stderr": 0.010316749863541367,
"acc_norm": 0.7486398258977149,
"acc_norm_stderr": 0.010121156016819245
}
},
"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
}
}