Muennighoff's picture
Add eval
990f338
raw
history blame
2.47 kB
{
"results": {
"anli_r1": {
"acc": 0.329,
"acc_stderr": 0.014865395385928369
},
"anli_r2": {
"acc": 0.356,
"acc_stderr": 0.015149042659306625
},
"anli_r3": {
"acc": 0.31666666666666665,
"acc_stderr": 0.013434078660827386
},
"cb": {
"acc": 0.5535714285714286,
"acc_stderr": 0.06703189227942395,
"f1": 0.3779862414008755
},
"copa": {
"acc": 0.68,
"acc_stderr": 0.04688261722621504
},
"hellaswag": {
"acc": 0.3783110934076877,
"acc_stderr": 0.004839746491523513,
"acc_norm": 0.45130452101175067,
"acc_norm_stderr": 0.004966060995315058
},
"rte": {
"acc": 0.49458483754512633,
"acc_stderr": 0.030094698123239966
},
"winogrande": {
"acc": 0.49171270718232046,
"acc_stderr": 0.014050555322824194
},
"storycloze_2016": {
"acc": 0.6386958845537146,
"acc_stderr": 0.011108686479432282
},
"boolq": {
"acc": 0.5085626911314984,
"acc_stderr": 0.008743772513106856
},
"arc_easy": {
"acc": 0.4692760942760943,
"acc_stderr": 0.010240395584815239,
"acc_norm": 0.4473905723905724,
"acc_norm_stderr": 0.010202832385415642
},
"arc_challenge": {
"acc": 0.2380546075085324,
"acc_stderr": 0.012445770028026201,
"acc_norm": 0.26621160409556316,
"acc_norm_stderr": 0.012915774781523223
},
"sciq": {
"acc": 0.715,
"acc_stderr": 0.014282120955200485,
"acc_norm": 0.687,
"acc_norm_stderr": 0.01467127282297789
},
"piqa": {
"acc": 0.691512513601741,
"acc_stderr": 0.01077616467803716,
"acc_norm": 0.6860718171926007,
"acc_norm_stderr": 0.01082792813418964
}
},
"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
}
}