lm5-2b8-55b-c4 / evaluation /rankeval_r_denoiser /checkpoints_2b855b55bc4ul2ndfixnew_5.json
Muennighoff's picture
Add files
79391b8
raw
history blame
No virus
2.47 kB
{
"results": {
"anli_r1": {
"acc": 0.375,
"acc_stderr": 0.015316971293620996
},
"anli_r2": {
"acc": 0.339,
"acc_stderr": 0.014976758771620344
},
"anli_r3": {
"acc": 0.3408333333333333,
"acc_stderr": 0.01368860079329693
},
"cb": {
"acc": 0.5535714285714286,
"acc_stderr": 0.06703189227942395,
"f1": 0.3464373464373464
},
"copa": {
"acc": 0.62,
"acc_stderr": 0.04878317312145633
},
"hellaswag": {
"acc": 0.29486158135829516,
"acc_stderr": 0.0045504861860190746,
"acc_norm": 0.32304321848237405,
"acc_norm_stderr": 0.0046668334527961925
},
"rte": {
"acc": 0.5018050541516246,
"acc_stderr": 0.030096267148976626
},
"winogrande": {
"acc": 0.5027624309392266,
"acc_stderr": 0.014052271211616441
},
"storycloze_2016": {
"acc": 0.5809727418492785,
"acc_stderr": 0.011409804749706194
},
"boolq": {
"acc": 0.44128440366972477,
"acc_stderr": 0.008684548127832634
},
"arc_easy": {
"acc": 0.4297138047138047,
"acc_stderr": 0.010157908005763676,
"acc_norm": 0.3985690235690236,
"acc_norm_stderr": 0.010046455400477931
},
"arc_challenge": {
"acc": 0.19197952218430034,
"acc_stderr": 0.011509598906598112,
"acc_norm": 0.22525597269624573,
"acc_norm_stderr": 0.012207839995407303
},
"sciq": {
"acc": 0.721,
"acc_stderr": 0.014190150117612032,
"acc_norm": 0.682,
"acc_norm_stderr": 0.014734079309311901
},
"piqa": {
"acc": 0.6305767138193689,
"acc_stderr": 0.011260988628572347,
"acc_norm": 0.6180631120783461,
"acc_norm_stderr": 0.011335942557505228
}
},
"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
}
}