Muennighoff's picture
Add eval
9e5d26a
raw
history blame
No virus
2.47 kB
{
"results": {
"anli_r1": {
"acc": 0.326,
"acc_stderr": 0.014830507204541044
},
"anli_r2": {
"acc": 0.344,
"acc_stderr": 0.015029633724408947
},
"anli_r3": {
"acc": 0.35583333333333333,
"acc_stderr": 0.013826518748493315
},
"cb": {
"acc": 0.5357142857142857,
"acc_stderr": 0.06724777654937658,
"f1": 0.35670453061757407
},
"copa": {
"acc": 0.74,
"acc_stderr": 0.04408440022768078
},
"hellaswag": {
"acc": 0.45140410276837284,
"acc_stderr": 0.004966158142645416,
"acc_norm": 0.5934076877116112,
"acc_norm_stderr": 0.004901936511546116
},
"rte": {
"acc": 0.5415162454873647,
"acc_stderr": 0.02999253538537331
},
"winogrande": {
"acc": 0.5698500394632992,
"acc_stderr": 0.013914685094716692
},
"storycloze_2016": {
"acc": 0.6996258685195083,
"acc_stderr": 0.010600915927985026
},
"boolq": {
"acc": 0.5574923547400612,
"acc_stderr": 0.008687051315181374
},
"arc_easy": {
"acc": 0.6418350168350169,
"acc_stderr": 0.009838331651451844,
"acc_norm": 0.6300505050505051,
"acc_norm_stderr": 0.009906656266021155
},
"arc_challenge": {
"acc": 0.31143344709897613,
"acc_stderr": 0.013532472099850949,
"acc_norm": 0.32764505119453924,
"acc_norm_stderr": 0.013715847940719344
},
"sciq": {
"acc": 0.913,
"acc_stderr": 0.008916866630745925,
"acc_norm": 0.911,
"acc_norm_stderr": 0.009008893392651516
},
"piqa": {
"acc": 0.7388465723612623,
"acc_stderr": 0.010248738649935581,
"acc_norm": 0.750272034820457,
"acc_norm_stderr": 0.010099232969867483
}
},
"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
}
}