Muennighoff's picture
Add eval
b851397
raw
history blame
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.344,
"acc_stderr": 0.015029633724408947
},
"anli_r2": {
"acc": 0.321,
"acc_stderr": 0.01477082181793464
},
"anli_r3": {
"acc": 0.34833333333333333,
"acc_stderr": 0.01375943749887408
},
"cb": {
"acc": 0.35714285714285715,
"acc_stderr": 0.06460957383809221,
"f1": 0.1754385964912281
},
"copa": {
"acc": 0.8,
"acc_stderr": 0.040201512610368445
},
"hellaswag": {
"acc": 0.4792869946225851,
"acc_stderr": 0.004985498055190357,
"acc_norm": 0.6265684126667994,
"acc_norm_stderr": 0.004827266662144035
},
"rte": {
"acc": 0.5342960288808665,
"acc_stderr": 0.030025579819366422
},
"winogrande": {
"acc": 0.5753749013417522,
"acc_stderr": 0.013891893150264213
},
"storycloze_2016": {
"acc": 0.7231427044361304,
"acc_stderr": 0.01034711289027692
},
"boolq": {
"acc": 0.5700305810397553,
"acc_stderr": 0.008658853690729254
},
"arc_easy": {
"acc": 0.5984848484848485,
"acc_stderr": 0.010058790020755567,
"acc_norm": 0.5395622895622896,
"acc_norm_stderr": 0.01022761638628902
},
"arc_challenge": {
"acc": 0.27986348122866894,
"acc_stderr": 0.013119040897725922,
"acc_norm": 0.31143344709897613,
"acc_norm_stderr": 0.013532472099850942
},
"sciq": {
"acc": 0.848,
"acc_stderr": 0.011358918303475274,
"acc_norm": 0.769,
"acc_norm_stderr": 0.013334797216936438
},
"piqa": {
"acc": 0.7584330794341676,
"acc_stderr": 0.009986718001804467,
"acc_norm": 0.7633297062023939,
"acc_norm_stderr": 0.009916841655042809
}
},
"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
}
}