Muennighoff's picture
Add eval
b851397
raw
history blame
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.327,
"acc_stderr": 0.014842213153411247
},
"anli_r2": {
"acc": 0.333,
"acc_stderr": 0.01491084616422986
},
"anli_r3": {
"acc": 0.3408333333333333,
"acc_stderr": 0.01368860079329693
},
"cb": {
"acc": 0.5357142857142857,
"acc_stderr": 0.06724777654937658,
"f1": 0.3829365079365079
},
"copa": {
"acc": 0.78,
"acc_stderr": 0.04163331998932262
},
"hellaswag": {
"acc": 0.48048197570205137,
"acc_stderr": 0.00498597821493792,
"acc_norm": 0.6397132045409281,
"acc_norm_stderr": 0.004791024004587989
},
"rte": {
"acc": 0.5090252707581228,
"acc_stderr": 0.030091559826331334
},
"winogrande": {
"acc": 0.6053670086819258,
"acc_stderr": 0.013736915172371883
},
"storycloze_2016": {
"acc": 0.7161945483698557,
"acc_stderr": 0.01042569627973092
},
"boolq": {
"acc": 0.5920489296636086,
"acc_stderr": 0.008595583792654892
},
"arc_easy": {
"acc": 0.622895622895623,
"acc_stderr": 0.009945041946366499,
"acc_norm": 0.6018518518518519,
"acc_norm_stderr": 0.010044662374653398
},
"arc_challenge": {
"acc": 0.295221843003413,
"acc_stderr": 0.013329750293382318,
"acc_norm": 0.32337883959044367,
"acc_norm_stderr": 0.013669421630012129
},
"sciq": {
"acc": 0.903,
"acc_stderr": 0.009363689373248092,
"acc_norm": 0.882,
"acc_norm_stderr": 0.010206869264381791
},
"piqa": {
"acc": 0.7578890097932536,
"acc_stderr": 0.009994371269104376,
"acc_norm": 0.7682263329706203,
"acc_norm_stderr": 0.009845143772794043
}
},
"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
}
}