Muennighoff's picture
Add eval
5c159b1
raw
history blame
2.47 kB
{
"results": {
"anli_r1": {
"acc": 0.325,
"acc_stderr": 0.014818724459095526
},
"anli_r2": {
"acc": 0.33,
"acc_stderr": 0.014876872027456738
},
"anli_r3": {
"acc": 0.32666666666666666,
"acc_stderr": 0.013544340907003663
},
"cb": {
"acc": 0.5714285714285714,
"acc_stderr": 0.06672848092813058,
"f1": 0.42867867867867865
},
"copa": {
"acc": 0.77,
"acc_stderr": 0.042295258468165065
},
"hellaswag": {
"acc": 0.4495120493925513,
"acc_stderr": 0.004964277999318813,
"acc_norm": 0.5978888667596096,
"acc_norm_stderr": 0.004893220635011786
},
"rte": {
"acc": 0.5234657039711191,
"acc_stderr": 0.030063300411902652
},
"winogrande": {
"acc": 0.5722178374112076,
"acc_stderr": 0.013905134013839951
},
"storycloze_2016": {
"acc": 0.6985569214323891,
"acc_stderr": 0.010611646032767584
},
"boolq": {
"acc": 0.6253822629969419,
"acc_stderr": 0.008465633983431928
},
"arc_easy": {
"acc": 0.6376262626262627,
"acc_stderr": 0.009863468202583775,
"acc_norm": 0.6338383838383839,
"acc_norm_stderr": 0.009885391390947709
},
"arc_challenge": {
"acc": 0.28754266211604096,
"acc_stderr": 0.013226719056266129,
"acc_norm": 0.3250853242320819,
"acc_norm_stderr": 0.013688147309729122
},
"sciq": {
"acc": 0.926,
"acc_stderr": 0.008282064512704159,
"acc_norm": 0.927,
"acc_norm_stderr": 0.008230354715244066
},
"piqa": {
"acc": 0.7383025027203483,
"acc_stderr": 0.010255630772708227,
"acc_norm": 0.735038084874864,
"acc_norm_stderr": 0.010296557993316047
}
},
"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
}
}