Muennighoff's picture
Add
77f8dfd
raw
history blame contribute delete
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.34,
"acc_stderr": 0.014987482264363937
},
"anli_r2": {
"acc": 0.317,
"acc_stderr": 0.014721675438880224
},
"anli_r3": {
"acc": 0.345,
"acc_stderr": 0.01372842153945488
},
"cb": {
"acc": 0.48214285714285715,
"acc_stderr": 0.0673769750864465,
"f1": 0.3566561844863732
},
"copa": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446
},
"hellaswag": {
"acc": 0.4736108344951205,
"acc_stderr": 0.00498282691668715,
"acc_norm": 0.6191993626767576,
"acc_norm_stderr": 0.004845912857338672
},
"rte": {
"acc": 0.5740072202166066,
"acc_stderr": 0.029764956741777645
},
"winogrande": {
"acc": 0.5706393054459353,
"acc_stderr": 0.013911537499969165
},
"storycloze_2016": {
"acc": 0.7124532335649385,
"acc_stderr": 0.010466744473098357
},
"boolq": {
"acc": 0.6146788990825688,
"acc_stderr": 0.008511930879680642
},
"arc_easy": {
"acc": 0.6123737373737373,
"acc_stderr": 0.00999730791444761,
"acc_norm": 0.5715488215488216,
"acc_norm_stderr": 0.010154195733990972
},
"arc_challenge": {
"acc": 0.2901023890784983,
"acc_stderr": 0.013261573677520764,
"acc_norm": 0.318259385665529,
"acc_norm_stderr": 0.013611993916971453
},
"sciq": {
"acc": 0.898,
"acc_stderr": 0.00957536880165389,
"acc_norm": 0.875,
"acc_norm_stderr": 0.010463483381956722
},
"piqa": {
"acc": 0.7551686615886833,
"acc_stderr": 0.010032309105568798,
"acc_norm": 0.7529923830250272,
"acc_norm_stderr": 0.010062268140772636
}
},
"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
}
}