Muennighoff's picture
Add eval
d522938
raw
history blame contribute delete
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.327,
"acc_stderr": 0.014842213153411249
},
"anli_r2": {
"acc": 0.324,
"acc_stderr": 0.014806864733738854
},
"anli_r3": {
"acc": 0.3175,
"acc_stderr": 0.013443538681348054
},
"cb": {
"acc": 0.5178571428571429,
"acc_stderr": 0.06737697508644648,
"f1": 0.33564993564993567
},
"copa": {
"acc": 0.76,
"acc_stderr": 0.04292346959909283
},
"hellaswag": {
"acc": 0.43158733320055764,
"acc_stderr": 0.004942853459371548,
"acc_norm": 0.5655247958573989,
"acc_norm_stderr": 0.004946748608271348
},
"rte": {
"acc": 0.5270758122743683,
"acc_stderr": 0.030052303463143706
},
"winogrande": {
"acc": 0.5564325177584846,
"acc_stderr": 0.0139626949076204
},
"storycloze_2016": {
"acc": 0.6889363976483164,
"acc_stderr": 0.010705164869803167
},
"boolq": {
"acc": 0.5636085626911315,
"acc_stderr": 0.008674000467432073
},
"arc_easy": {
"acc": 0.5951178451178452,
"acc_stderr": 0.010072423960395701,
"acc_norm": 0.5803872053872053,
"acc_norm_stderr": 0.010126315840891536
},
"arc_challenge": {
"acc": 0.2696245733788396,
"acc_stderr": 0.01296804068686915,
"acc_norm": 0.2883959044368601,
"acc_norm_stderr": 0.013238394422428175
},
"sciq": {
"acc": 0.903,
"acc_stderr": 0.009363689373248111,
"acc_norm": 0.901,
"acc_norm_stderr": 0.009449248027662747
},
"piqa": {
"acc": 0.7328618063112078,
"acc_stderr": 0.010323440492612437,
"acc_norm": 0.7470076169749728,
"acc_norm_stderr": 0.010142888698862453
}
},
"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
}
}