lm5-2b8-55b-c4 / evaluation /rankeval_r_denoiser /checkpoints_2b855b55bc4ul2ndfixnew_0_lm-eval_global_step52452_2023-02-09-23-24-23_0shots_backup.json
Muennighoff's picture
Add files
79391b8
raw
history blame
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.339,
"acc_stderr": 0.01497675877162034
},
"anli_r2": {
"acc": 0.335,
"acc_stderr": 0.014933117490932573
},
"anli_r3": {
"acc": 0.33416666666666667,
"acc_stderr": 0.013622434813136783
},
"cb": {
"acc": 0.4107142857142857,
"acc_stderr": 0.0663363415035954,
"f1": 0.1940928270042194
},
"copa": {
"acc": 0.62,
"acc_stderr": 0.04878317312145632
},
"hellaswag": {
"acc": 0.2951603266281617,
"acc_stderr": 0.004551826272978059,
"acc_norm": 0.3241386178052181,
"acc_norm_stderr": 0.004670955399641126
},
"rte": {
"acc": 0.5234657039711191,
"acc_stderr": 0.03006330041190266
},
"winogrande": {
"acc": 0.5059194948697711,
"acc_stderr": 0.01405150083848581
},
"storycloze_2016": {
"acc": 0.5873864243719936,
"acc_stderr": 0.011384472322969045
},
"boolq": {
"acc": 0.5938837920489297,
"acc_stderr": 0.008589510943787407
},
"arc_easy": {
"acc": 0.4335016835016835,
"acc_stderr": 0.010168640625454107,
"acc_norm": 0.3846801346801347,
"acc_norm_stderr": 0.009983171707009006
},
"arc_challenge": {
"acc": 0.17918088737201365,
"acc_stderr": 0.011207045216615674,
"acc_norm": 0.2235494880546075,
"acc_norm_stderr": 0.012174896631202614
},
"sciq": {
"acc": 0.732,
"acc_stderr": 0.01401329270272948,
"acc_norm": 0.669,
"acc_norm_stderr": 0.01488827258820394
},
"piqa": {
"acc": 0.6218715995647442,
"acc_stderr": 0.011313980666854535,
"acc_norm": 0.6267682263329706,
"acc_norm_stderr": 0.011284653078254898
}
},
"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
}
}