lm1-4b2-84b-c4seeds / 4b284b42bc4seed2 /evaluation /rankeval /4b284b42bc4seed2_2_lm-eval_global_step80108_2023-02-15-11-04-03_2shots_backup.json
Muennighoff's picture
Add
48e5290
raw
history blame
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.331,
"acc_stderr": 0.014888272588203945
},
"anli_r2": {
"acc": 0.35,
"acc_stderr": 0.015090650341444231
},
"anli_r3": {
"acc": 0.33416666666666667,
"acc_stderr": 0.013622434813136769
},
"cb": {
"acc": 0.375,
"acc_stderr": 0.06527912098338669,
"f1": 0.26182156999767064
},
"copa": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446
},
"hellaswag": {
"acc": 0.468034256124278,
"acc_stderr": 0.0049795737655758555,
"acc_norm": 0.6188010356502689,
"acc_norm_stderr": 0.00484688692976345
},
"rte": {
"acc": 0.5342960288808665,
"acc_stderr": 0.03002557981936643
},
"winogrande": {
"acc": 0.5769534333070244,
"acc_stderr": 0.013885055359056472
},
"storycloze_2016": {
"acc": 0.7151256012827365,
"acc_stderr": 0.01043751398661172
},
"boolq": {
"acc": 0.5519877675840978,
"acc_stderr": 0.008697655510897228
},
"arc_easy": {
"acc": 0.6102693602693603,
"acc_stderr": 0.01000716939179705,
"acc_norm": 0.5993265993265994,
"acc_norm_stderr": 0.010055304474255582
},
"arc_challenge": {
"acc": 0.28924914675767915,
"acc_stderr": 0.013250012579393443,
"acc_norm": 0.30887372013651876,
"acc_norm_stderr": 0.013501770929344003
},
"sciq": {
"acc": 0.883,
"acc_stderr": 0.010169287802713329,
"acc_norm": 0.865,
"acc_norm_stderr": 0.010811655372416053
},
"piqa": {
"acc": 0.7529923830250272,
"acc_stderr": 0.010062268140772622,
"acc_norm": 0.7584330794341676,
"acc_norm_stderr": 0.00998671800180446
}
},
"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
}
}