lm1-4b2-84b-c4seeds / 4b284b21bc4seed4 /evaluation /rankeval /4b284b21bc4seed4_0_lm-eval_global_step80108_2023-02-15-11-04-01_0shots_backup.json
Muennighoff's picture
Add
31b4221
raw
history blame
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.324,
"acc_stderr": 0.014806864733738859
},
"anli_r2": {
"acc": 0.338,
"acc_stderr": 0.014965960710224482
},
"anli_r3": {
"acc": 0.3416666666666667,
"acc_stderr": 0.013696658778002519
},
"cb": {
"acc": 0.42857142857142855,
"acc_stderr": 0.06672848092813058,
"f1": 0.22212270488132557
},
"copa": {
"acc": 0.74,
"acc_stderr": 0.044084400227680794
},
"hellaswag": {
"acc": 0.48446524596693885,
"acc_stderr": 0.004987372476207027,
"acc_norm": 0.6316470822545309,
"acc_norm_stderr": 0.004813719952829966
},
"rte": {
"acc": 0.5126353790613718,
"acc_stderr": 0.030086851767188564
},
"winogrande": {
"acc": 0.5951065509076559,
"acc_stderr": 0.01379592700312494
},
"storycloze_2016": {
"acc": 0.711918760021379,
"acc_stderr": 0.010472537019822575
},
"boolq": {
"acc": 0.5571865443425077,
"acc_stderr": 0.008687668766930827
},
"arc_easy": {
"acc": 0.6031144781144782,
"acc_stderr": 0.010039236800583206,
"acc_norm": 0.5353535353535354,
"acc_norm_stderr": 0.01023410454341143
},
"arc_challenge": {
"acc": 0.2841296928327645,
"acc_stderr": 0.013179442447653886,
"acc_norm": 0.3003412969283277,
"acc_norm_stderr": 0.013395909309957007
},
"sciq": {
"acc": 0.858,
"acc_stderr": 0.011043457699378237,
"acc_norm": 0.766,
"acc_norm_stderr": 0.01339490288966001
},
"piqa": {
"acc": 0.7627856365614799,
"acc_stderr": 0.009924694933586373,
"acc_norm": 0.7682263329706203,
"acc_norm_stderr": 0.009845143772794052
}
},
"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
}
}