Muennighoff's picture
Add eval
b851397
raw
history blame
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.345,
"acc_stderr": 0.015039986742055235
},
"anli_r2": {
"acc": 0.325,
"acc_stderr": 0.014818724459095526
},
"anli_r3": {
"acc": 0.31416666666666665,
"acc_stderr": 0.013405399314984096
},
"cb": {
"acc": 0.39285714285714285,
"acc_stderr": 0.0658538889806635,
"f1": 0.3647495361781076
},
"copa": {
"acc": 0.82,
"acc_stderr": 0.038612291966536955
},
"hellaswag": {
"acc": 0.4819757020513842,
"acc_stderr": 0.004986538243846636,
"acc_norm": 0.6387173869747063,
"acc_norm_stderr": 0.004793904922401888
},
"rte": {
"acc": 0.48736462093862815,
"acc_stderr": 0.030086851767188564
},
"winogrande": {
"acc": 0.5832675611681136,
"acc_stderr": 0.013856250072796322
},
"storycloze_2016": {
"acc": 0.7386424371993586,
"acc_stderr": 0.010160471460690485
},
"boolq": {
"acc": 0.6275229357798165,
"acc_stderr": 0.008455846866956085
},
"arc_easy": {
"acc": 0.6405723905723906,
"acc_stderr": 0.009845958893373766,
"acc_norm": 0.6212121212121212,
"acc_norm_stderr": 0.00995373765654204
},
"arc_challenge": {
"acc": 0.30204778156996587,
"acc_stderr": 0.01341751914471642,
"acc_norm": 0.32764505119453924,
"acc_norm_stderr": 0.013715847940719344
},
"sciq": {
"acc": 0.92,
"acc_stderr": 0.008583336977753653,
"acc_norm": 0.907,
"acc_norm_stderr": 0.009188875634996702
},
"piqa": {
"acc": 0.7551686615886833,
"acc_stderr": 0.01003230910556879,
"acc_norm": 0.76550598476605,
"acc_norm_stderr": 0.00988520314324054
}
},
"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
}
}