Muennighoff's picture
Add eval
9e5d26a
raw
history blame
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.336,
"acc_stderr": 0.014944140233795023
},
"anli_r2": {
"acc": 0.349,
"acc_stderr": 0.015080663991563102
},
"anli_r3": {
"acc": 0.3383333333333333,
"acc_stderr": 0.013664144006618268
},
"cb": {
"acc": 0.5,
"acc_stderr": 0.06741998624632421,
"f1": 0.435174510009433
},
"copa": {
"acc": 0.73,
"acc_stderr": 0.0446196043338474
},
"hellaswag": {
"acc": 0.45717984465245964,
"acc_stderr": 0.004971449552787175,
"acc_norm": 0.6003784106751643,
"acc_norm_stderr": 0.004888194985997393
},
"rte": {
"acc": 0.5812274368231047,
"acc_stderr": 0.029696661081234824
},
"winogrande": {
"acc": 0.5611681136543015,
"acc_stderr": 0.013946933444507032
},
"storycloze_2016": {
"acc": 0.7129877071084981,
"acc_stderr": 0.010460934115933266
},
"boolq": {
"acc": 0.5914373088685015,
"acc_stderr": 0.008597580502718664
},
"arc_easy": {
"acc": 0.6460437710437711,
"acc_stderr": 0.009812370644174425,
"acc_norm": 0.6548821548821548,
"acc_norm_stderr": 0.009755139387152029
},
"arc_challenge": {
"acc": 0.3037542662116041,
"acc_stderr": 0.013438909184778755,
"acc_norm": 0.32081911262798635,
"acc_norm_stderr": 0.013640943091946531
},
"sciq": {
"acc": 0.921,
"acc_stderr": 0.00853415677333344,
"acc_norm": 0.921,
"acc_norm_stderr": 0.008534156773333442
},
"piqa": {
"acc": 0.7470076169749728,
"acc_stderr": 0.010142888698862464,
"acc_norm": 0.7535364526659413,
"acc_norm_stderr": 0.010054810789671815
}
},
"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
}
}