Muennighoff's picture
Add
d7c2560
raw
history blame
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.335,
"acc_stderr": 0.014933117490932573
},
"anli_r2": {
"acc": 0.334,
"acc_stderr": 0.014922019523732954
},
"anli_r3": {
"acc": 0.3425,
"acc_stderr": 0.013704669762934727
},
"cb": {
"acc": 0.39285714285714285,
"acc_stderr": 0.0658538889806635,
"f1": 0.258008658008658
},
"copa": {
"acc": 0.83,
"acc_stderr": 0.03775251680686371
},
"hellaswag": {
"acc": 0.4801832304321848,
"acc_stderr": 0.0049858608534276315,
"acc_norm": 0.6342362079267079,
"acc_norm_stderr": 0.004806593424942264
},
"rte": {
"acc": 0.5703971119133574,
"acc_stderr": 0.02979666882912467
},
"winogrande": {
"acc": 0.6029992107340174,
"acc_stderr": 0.013751092519806702
},
"storycloze_2016": {
"acc": 0.72367717797969,
"acc_stderr": 0.010340939873166822
},
"boolq": {
"acc": 0.6048929663608563,
"acc_stderr": 0.0085504542482809
},
"arc_easy": {
"acc": 0.6224747474747475,
"acc_stderr": 0.009947227833469432,
"acc_norm": 0.6047979797979798,
"acc_norm_stderr": 0.010031894052790978
},
"arc_challenge": {
"acc": 0.2935153583617747,
"acc_stderr": 0.01330725044494113,
"acc_norm": 0.32764505119453924,
"acc_norm_stderr": 0.013715847940719346
},
"sciq": {
"acc": 0.913,
"acc_stderr": 0.008916866630745908,
"acc_norm": 0.897,
"acc_norm_stderr": 0.009616833339695798
},
"piqa": {
"acc": 0.7546245919477693,
"acc_stderr": 0.010039831320422401,
"acc_norm": 0.7622415669205659,
"acc_norm_stderr": 0.009932525779525492
}
},
"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
}
}