Muennighoff's picture
Add
d7c2560
raw
history blame
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.32,
"acc_stderr": 0.014758652303574888
},
"anli_r2": {
"acc": 0.341,
"acc_stderr": 0.0149981313484027
},
"anli_r3": {
"acc": 0.3308333333333333,
"acc_stderr": 0.013588208070708992
},
"cb": {
"acc": 0.3392857142857143,
"acc_stderr": 0.06384226561930825,
"f1": 0.18571428571428572
},
"copa": {
"acc": 0.84,
"acc_stderr": 0.0368452949177471
},
"hellaswag": {
"acc": 0.4788886675960964,
"acc_stderr": 0.004985331652408344,
"acc_norm": 0.6372236606253734,
"acc_norm_stderr": 0.0047981844631563575
},
"rte": {
"acc": 0.51985559566787,
"acc_stderr": 0.030072723167317177
},
"winogrande": {
"acc": 0.6227308602999211,
"acc_stderr": 0.013622567928799501
},
"storycloze_2016": {
"acc": 0.7300908605024051,
"acc_stderr": 0.010265413503221462
},
"boolq": {
"acc": 0.6226299694189602,
"acc_stderr": 0.008477957863309996
},
"arc_easy": {
"acc": 0.640993265993266,
"acc_stderr": 0.009843424713072176,
"acc_norm": 0.6233164983164983,
"acc_norm_stderr": 0.009942848077476165
},
"arc_challenge": {
"acc": 0.3054607508532423,
"acc_stderr": 0.013460080478002496,
"acc_norm": 0.33447098976109213,
"acc_norm_stderr": 0.013787460322441375
},
"sciq": {
"acc": 0.915,
"acc_stderr": 0.00882342636694232,
"acc_norm": 0.906,
"acc_norm_stderr": 0.009233052000787736
},
"piqa": {
"acc": 0.7546245919477693,
"acc_stderr": 0.010039831320422398,
"acc_norm": 0.7709466811751904,
"acc_norm_stderr": 0.009804509865175505
}
},
"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
}
}