Muennighoff's picture
Add eval
d522938
raw
history blame
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.33,
"acc_stderr": 0.014876872027456732
},
"anli_r2": {
"acc": 0.351,
"acc_stderr": 0.015100563798316405
},
"anli_r3": {
"acc": 0.3375,
"acc_stderr": 0.013655897185463658
},
"cb": {
"acc": 0.42857142857142855,
"acc_stderr": 0.06672848092813058,
"f1": 0.29390681003584224
},
"copa": {
"acc": 0.8,
"acc_stderr": 0.040201512610368445
},
"hellaswag": {
"acc": 0.42949611631149176,
"acc_stderr": 0.004939925958728869,
"acc_norm": 0.5636327424815774,
"acc_norm_stderr": 0.004949207947265914
},
"rte": {
"acc": 0.5306859205776173,
"acc_stderr": 0.030039730592197812
},
"winogrande": {
"acc": 0.5643251775848461,
"acc_stderr": 0.013935709739615713
},
"storycloze_2016": {
"acc": 0.6932121859967931,
"acc_stderr": 0.010664275190473634
},
"boolq": {
"acc": 0.6103975535168196,
"acc_stderr": 0.008529228894936293
},
"arc_easy": {
"acc": 0.5778619528619529,
"acc_stderr": 0.010134620524592271,
"acc_norm": 0.5635521885521886,
"acc_norm_stderr": 0.010176569980111044
},
"arc_challenge": {
"acc": 0.2593856655290102,
"acc_stderr": 0.012808273573927095,
"acc_norm": 0.2883959044368601,
"acc_norm_stderr": 0.013238394422428175
},
"sciq": {
"acc": 0.886,
"acc_stderr": 0.010055103435823332,
"acc_norm": 0.873,
"acc_norm_stderr": 0.010534798620855762
},
"piqa": {
"acc": 0.736126224156692,
"acc_stderr": 0.010282996367695562,
"acc_norm": 0.7377584330794341,
"acc_norm_stderr": 0.010262502565172443
}
},
"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
}
}