Muennighoff's picture
add
cc04ae0
{
"results": {
"anli_r1": {
"acc": 0.336,
"acc_stderr": 0.014944140233795023
},
"anli_r2": {
"acc": 0.32,
"acc_stderr": 0.014758652303574876
},
"anli_r3": {
"acc": 0.3491666666666667,
"acc_stderr": 0.013767075395077249
},
"cb": {
"acc": 0.4642857142857143,
"acc_stderr": 0.0672477765493766,
"f1": 0.4400465860102907
},
"copa": {
"acc": 0.81,
"acc_stderr": 0.03942772444036622
},
"hellaswag": {
"acc": 0.46873132842063336,
"acc_stderr": 0.004980014536539821,
"acc_norm": 0.6197968532164907,
"acc_norm_stderr": 0.004844445265582643
},
"rte": {
"acc": 0.555956678700361,
"acc_stderr": 0.029907396333795983
},
"winogrande": {
"acc": 0.579321231254933,
"acc_stderr": 0.013874526372008315
},
"storycloze_2016": {
"acc": 0.7145911277391769,
"acc_stderr": 0.010443395884062118
},
"boolq": {
"acc": 0.6165137614678899,
"acc_stderr": 0.008504304838837023
},
"arc_easy": {
"acc": 0.6287878787878788,
"acc_stderr": 0.00991359900184574,
"acc_norm": 0.6031144781144782,
"acc_norm_stderr": 0.010039236800583199
},
"arc_challenge": {
"acc": 0.29692832764505117,
"acc_stderr": 0.013352025976725222,
"acc_norm": 0.310580204778157,
"acc_norm_stderr": 0.013522292098053057
},
"sciq": {
"acc": 0.908,
"acc_stderr": 0.009144376393151105,
"acc_norm": 0.905,
"acc_norm_stderr": 0.009276910103103324
},
"piqa": {
"acc": 0.7551686615886833,
"acc_stderr": 0.010032309105568795,
"acc_norm": 0.7622415669205659,
"acc_norm_stderr": 0.009932525779525489
}
},
"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
}
}