Muennighoff's picture
Add eval
9e5d26a
raw
history blame
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.325,
"acc_stderr": 0.014818724459095522
},
"anli_r2": {
"acc": 0.312,
"acc_stderr": 0.014658474370509017
},
"anli_r3": {
"acc": 0.3541666666666667,
"acc_stderr": 0.013811933499570961
},
"cb": {
"acc": 0.42857142857142855,
"acc_stderr": 0.06672848092813058,
"f1": 0.299808429118774
},
"copa": {
"acc": 0.76,
"acc_stderr": 0.04292346959909282
},
"hellaswag": {
"acc": 0.45518820952001593,
"acc_stderr": 0.004969701081068372,
"acc_norm": 0.5997809201354312,
"acc_norm_stderr": 0.004889413126208782
},
"rte": {
"acc": 0.4981949458483754,
"acc_stderr": 0.030096267148976633
},
"winogrande": {
"acc": 0.5761641673243884,
"acc_stderr": 0.01388849238994452
},
"storycloze_2016": {
"acc": 0.711918760021379,
"acc_stderr": 0.010472537019822582
},
"boolq": {
"acc": 0.5954128440366973,
"acc_stderr": 0.008584355308932687
},
"arc_easy": {
"acc": 0.6452020202020202,
"acc_stderr": 0.009817629113069696,
"acc_norm": 0.6494107744107744,
"acc_norm_stderr": 0.009791003829831557
},
"arc_challenge": {
"acc": 0.3097269624573379,
"acc_stderr": 0.01351205841523836,
"acc_norm": 0.3148464163822526,
"acc_norm_stderr": 0.013572657703084948
},
"sciq": {
"acc": 0.915,
"acc_stderr": 0.00882342636694233,
"acc_norm": 0.917,
"acc_norm_stderr": 0.008728527206074792
},
"piqa": {
"acc": 0.733949945593036,
"acc_stderr": 0.010310039263352831,
"acc_norm": 0.7383025027203483,
"acc_norm_stderr": 0.010255630772708232
}
},
"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
}
}