Muennighoff's picture
add files
f80bf0d
raw
history blame
No virus
2.44 kB
{
"results": {
"anli_r1": {
"acc": 0.289,
"acc_stderr": 0.014341711358296191
},
"anli_r2": {
"acc": 0.352,
"acc_stderr": 0.015110404505648666
},
"anli_r3": {
"acc": 0.335,
"acc_stderr": 0.013630871843821474
},
"cb": {
"acc": 0.5,
"acc_stderr": 0.06741998624632421,
"f1": 0.35047619047619044
},
"copa": {
"acc": 0.68,
"acc_stderr": 0.04688261722621504
},
"hellaswag": {
"acc": 0.36247759410476,
"acc_stderr": 0.004797332565990064,
"acc_norm": 0.44911372236606256,
"acc_norm_stderr": 0.0049638729368579396
},
"rte": {
"acc": 0.5415162454873647,
"acc_stderr": 0.029992535385373314
},
"winogrande": {
"acc": 0.5138121546961326,
"acc_stderr": 0.01404712291644041
},
"storycloze_2016": {
"acc": 0.6392303580972741,
"acc_stderr": 0.011105110530046357
},
"boolq": {
"acc": 0.5382262996941896,
"acc_stderr": 0.00871946009810685
},
"arc_easy": {
"acc": 0.5332491582491582,
"acc_stderr": 0.010237073872130744,
"acc_norm": 0.5227272727272727,
"acc_norm_stderr": 0.010249179090605987
},
"arc_challenge": {
"acc": 0.23122866894197952,
"acc_stderr": 0.012320858834772276,
"acc_norm": 0.26791808873720135,
"acc_norm_stderr": 0.012942030195136432
},
"sciq": {
"acc": 0.891,
"acc_stderr": 0.009859828407037186,
"acc_norm": 0.882,
"acc_norm_stderr": 0.010206869264381791
},
"piqa": {
"acc": 0.6985854189336235,
"acc_stderr": 0.010706248242753761,
"acc_norm": 0.6942328618063112,
"acc_norm_stderr": 0.010749627366141642
}
},
"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
}
}