lm5-2b8-55b-c4 / evaluation /rankeval_s_denoiser /checkpoints_2b855b55bc4ul2ndfixnew_3_lm-eval_global_step52452_2023-02-09-17-36-57_3shots_backup.json
Muennighoff's picture
Add files
79391b8
raw
history blame
No virus
2.47 kB
{
"results": {
"anli_r1": {
"acc": 0.314,
"acc_stderr": 0.014683991951087966
},
"anli_r2": {
"acc": 0.341,
"acc_stderr": 0.014998131348402704
},
"anli_r3": {
"acc": 0.3466666666666667,
"acc_stderr": 0.013744022550571949
},
"cb": {
"acc": 0.5178571428571429,
"acc_stderr": 0.06737697508644648,
"f1": 0.347985347985348
},
"copa": {
"acc": 0.59,
"acc_stderr": 0.04943110704237101
},
"hellaswag": {
"acc": 0.2953594901414061,
"acc_stderr": 0.004552718360513099,
"acc_norm": 0.3241386178052181,
"acc_norm_stderr": 0.0046709553996411276
},
"rte": {
"acc": 0.5090252707581228,
"acc_stderr": 0.030091559826331334
},
"winogrande": {
"acc": 0.494869771112865,
"acc_stderr": 0.014051745961790513
},
"storycloze_2016": {
"acc": 0.5788348476750401,
"acc_stderr": 0.011417808278216117
},
"boolq": {
"acc": 0.4694189602446483,
"acc_stderr": 0.008728682900189723
},
"arc_easy": {
"acc": 0.4276094276094276,
"acc_stderr": 0.010151683397430679,
"acc_norm": 0.39141414141414144,
"acc_norm_stderr": 0.010014917532627812
},
"arc_challenge": {
"acc": 0.19027303754266212,
"acc_stderr": 0.011470424179225698,
"acc_norm": 0.2235494880546075,
"acc_norm_stderr": 0.012174896631202607
},
"sciq": {
"acc": 0.716,
"acc_stderr": 0.014267009061031314,
"acc_norm": 0.679,
"acc_norm_stderr": 0.014770821817934645
},
"piqa": {
"acc": 0.6289445048966268,
"acc_stderr": 0.011271222398600525,
"acc_norm": 0.6202393906420022,
"acc_norm_stderr": 0.011323483504715843
}
},
"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
}
}