Muennighoff's picture
add
f6c5fad
raw
history blame contribute delete
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.329,
"acc_stderr": 0.014865395385928364
},
"anli_r2": {
"acc": 0.338,
"acc_stderr": 0.014965960710224487
},
"anli_r3": {
"acc": 0.3325,
"acc_stderr": 0.013605417345710528
},
"cb": {
"acc": 0.5535714285714286,
"acc_stderr": 0.06703189227942395,
"f1": 0.3502252252252252
},
"copa": {
"acc": 0.68,
"acc_stderr": 0.04688261722621505
},
"hellaswag": {
"acc": 0.3595897231627166,
"acc_stderr": 0.004788994060654276,
"acc_norm": 0.44911372236606256,
"acc_norm_stderr": 0.004963872936857938
},
"rte": {
"acc": 0.4657039711191336,
"acc_stderr": 0.030025579819366426
},
"winogrande": {
"acc": 0.5224940805051302,
"acc_stderr": 0.014038257824059876
},
"storycloze_2016": {
"acc": 0.6365579903794762,
"acc_stderr": 0.011122841442059708
},
"boolq": {
"acc": 0.5577981651376147,
"acc_stderr": 0.00868643052611449
},
"arc_easy": {
"acc": 0.5433501683501684,
"acc_stderr": 0.010221149650118182,
"acc_norm": 0.523989898989899,
"acc_norm_stderr": 0.010247967392742688
},
"arc_challenge": {
"acc": 0.22525597269624573,
"acc_stderr": 0.012207839995407309,
"acc_norm": 0.25853242320819114,
"acc_norm_stderr": 0.012794553754288673
},
"sciq": {
"acc": 0.895,
"acc_stderr": 0.009698921026024968,
"acc_norm": 0.898,
"acc_norm_stderr": 0.00957536880165389
},
"piqa": {
"acc": 0.7083786724700761,
"acc_stderr": 0.01060444152742879,
"acc_norm": 0.7007616974972797,
"acc_norm_stderr": 0.010684130673134581
}
},
"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
}
}