lm1-2b8-55b-c4-dedup / evaluation /rankeval /lm1-2b8-55b-nodups_3.json
Muennighoff's picture
add
874e9d6
{
"results": {
"anli_r1": {
"acc": 0.343,
"acc_stderr": 0.015019206922356951
},
"anli_r2": {
"acc": 0.35,
"acc_stderr": 0.015090650341444231
},
"anli_r3": {
"acc": 0.3516666666666667,
"acc_stderr": 0.013789711695404794
},
"cb": {
"acc": 0.35714285714285715,
"acc_stderr": 0.06460957383809221,
"f1": 0.3445134575569358
},
"copa": {
"acc": 0.79,
"acc_stderr": 0.04093601807403326
},
"hellaswag": {
"acc": 0.4389563831905995,
"acc_stderr": 0.004952454721934793,
"acc_norm": 0.5718980282812188,
"acc_norm_stderr": 0.0049379243267425755
},
"rte": {
"acc": 0.5126353790613718,
"acc_stderr": 0.030086851767188564
},
"winogrande": {
"acc": 0.5698500394632992,
"acc_stderr": 0.013914685094716694
},
"storycloze_2016": {
"acc": 0.7156600748262961,
"acc_stderr": 0.01043161412866525
},
"boolq": {
"acc": 0.5039755351681957,
"acc_stderr": 0.008744778542942208
},
"arc_easy": {
"acc": 0.5778619528619529,
"acc_stderr": 0.010134620524592271,
"acc_norm": 0.5509259259259259,
"acc_norm_stderr": 0.010206428316323365
},
"arc_challenge": {
"acc": 0.25170648464163825,
"acc_stderr": 0.012682496334042963,
"acc_norm": 0.2841296928327645,
"acc_norm_stderr": 0.013179442447653886
},
"sciq": {
"acc": 0.865,
"acc_stderr": 0.010811655372416053,
"acc_norm": 0.845,
"acc_norm_stderr": 0.01145015747079946
},
"piqa": {
"acc": 0.7421109902067464,
"acc_stderr": 0.010206956662056255,
"acc_norm": 0.7529923830250272,
"acc_norm_stderr": 0.010062268140772625
}
},
"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
}
}