Muennighoff's picture
Add
f526fda
raw
history blame
2.43 kB
{
"results": {
"anli_r1": {
"acc": 0.331,
"acc_stderr": 0.01488827258820394
},
"anli_r2": {
"acc": 0.341,
"acc_stderr": 0.0149981313484027
},
"anli_r3": {
"acc": 0.34,
"acc_stderr": 0.0136804957257678
},
"cb": {
"acc": 0.2857142857142857,
"acc_stderr": 0.060914490387317256,
"f1": 0.2849772788024592
},
"copa": {
"acc": 0.8,
"acc_stderr": 0.04020151261036843
},
"hellaswag": {
"acc": 0.47450707030472017,
"acc_stderr": 0.00498329157828904,
"acc_norm": 0.6297550288787094,
"acc_norm_stderr": 0.004818833521340352
},
"rte": {
"acc": 0.49458483754512633,
"acc_stderr": 0.03009469812323996
},
"winogrande": {
"acc": 0.5761641673243884,
"acc_stderr": 0.013888492389944511
},
"storycloze_2016": {
"acc": 0.7177979690005345,
"acc_stderr": 0.01040783447964767
},
"boolq": {
"acc": 0.6278287461773701,
"acc_stderr": 0.008454434247373908
},
"arc_easy": {
"acc": 0.625,
"acc_stderr": 0.009933992677987828,
"acc_norm": 0.5984848484848485,
"acc_norm_stderr": 0.010058790020755562
},
"arc_challenge": {
"acc": 0.3037542662116041,
"acc_stderr": 0.01343890918477875,
"acc_norm": 0.3319112627986348,
"acc_norm_stderr": 0.013760988200880538
},
"sciq": {
"acc": 0.901,
"acc_stderr": 0.009449248027662751,
"acc_norm": 0.886,
"acc_norm_stderr": 0.010055103435823332
},
"piqa": {
"acc": 0.7486398258977149,
"acc_stderr": 0.010121156016819257,
"acc_norm": 0.7665941240478781,
"acc_norm_stderr": 0.009869247889520998
}
},
"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
}
}