lm5-2b8-55b-c4 / evaluation /rankeval_r_denoiser /checkpoints_2b855b55bc4ul2ndfixnew_4.json
Muennighoff's picture
Add files
79391b8
raw
history blame
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.336,
"acc_stderr": 0.014944140233795025
},
"anli_r2": {
"acc": 0.352,
"acc_stderr": 0.01511040450564867
},
"anli_r3": {
"acc": 0.3383333333333333,
"acc_stderr": 0.013664144006618266
},
"cb": {
"acc": 0.5178571428571429,
"acc_stderr": 0.06737697508644645,
"f1": 0.3362023995826813
},
"copa": {
"acc": 0.6,
"acc_stderr": 0.049236596391733084
},
"hellaswag": {
"acc": 0.29645488946425014,
"acc_stderr": 0.004557606227194286,
"acc_norm": 0.3234415455088628,
"acc_norm_stderr": 0.004668335725410298
},
"rte": {
"acc": 0.49458483754512633,
"acc_stderr": 0.030094698123239966
},
"winogrande": {
"acc": 0.4877663772691397,
"acc_stderr": 0.01404827882040562
},
"storycloze_2016": {
"acc": 0.5788348476750401,
"acc_stderr": 0.011417808278216117
},
"boolq": {
"acc": 0.44434250764525995,
"acc_stderr": 0.00869070599067338
},
"arc_easy": {
"acc": 0.42845117845117847,
"acc_stderr": 0.010154195733990975,
"acc_norm": 0.3930976430976431,
"acc_norm_stderr": 0.010022540618945312
},
"arc_challenge": {
"acc": 0.1962457337883959,
"acc_stderr": 0.01160601988141629,
"acc_norm": 0.22781569965870307,
"acc_norm_stderr": 0.012256708602326905
},
"sciq": {
"acc": 0.719,
"acc_stderr": 0.014221154708434929,
"acc_norm": 0.686,
"acc_norm_stderr": 0.014683991951087967
},
"piqa": {
"acc": 0.6273122959738846,
"acc_stderr": 0.01128131833289774,
"acc_norm": 0.6169749727965179,
"acc_norm_stderr": 0.01134208170908285
}
},
"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
}
}