Muennighoff's picture
Add eval
d522938
raw
history blame
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.356,
"acc_stderr": 0.015149042659306626
},
"anli_r2": {
"acc": 0.327,
"acc_stderr": 0.014842213153411247
},
"anli_r3": {
"acc": 0.35083333333333333,
"acc_stderr": 0.013782212417178193
},
"cb": {
"acc": 0.4642857142857143,
"acc_stderr": 0.06724777654937658,
"f1": 0.3249662618083671
},
"copa": {
"acc": 0.79,
"acc_stderr": 0.040936018074033256
},
"hellaswag": {
"acc": 0.4312885879306911,
"acc_stderr": 0.004942440746328494,
"acc_norm": 0.5671181039633539,
"acc_norm_stderr": 0.004944620712318273
},
"rte": {
"acc": 0.5523465703971119,
"acc_stderr": 0.029931070362939526
},
"winogrande": {
"acc": 0.56353591160221,
"acc_stderr": 0.013938569465677019
},
"storycloze_2016": {
"acc": 0.6980224478888295,
"acc_stderr": 0.010616985436073357
},
"boolq": {
"acc": 0.6131498470948012,
"acc_stderr": 0.008518188340844748
},
"arc_easy": {
"acc": 0.5820707070707071,
"acc_stderr": 0.010120628211017888,
"acc_norm": 0.5698653198653199,
"acc_norm_stderr": 0.010159130445178511
},
"arc_challenge": {
"acc": 0.24232081911262798,
"acc_stderr": 0.012521593295800116,
"acc_norm": 0.2815699658703072,
"acc_norm_stderr": 0.013143376735009022
},
"sciq": {
"acc": 0.891,
"acc_stderr": 0.009859828407037186,
"acc_norm": 0.895,
"acc_norm_stderr": 0.00969892102602495
},
"piqa": {
"acc": 0.7388465723612623,
"acc_stderr": 0.010248738649935574,
"acc_norm": 0.7415669205658324,
"acc_norm_stderr": 0.010213971636773306
}
},
"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
}
}