Muennighoff's picture
Add 58b
5328b51
raw
history blame
No virus
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.331,
"acc_stderr": 0.014888272588203936
},
"anli_r2": {
"acc": 0.336,
"acc_stderr": 0.014944140233795027
},
"anli_r3": {
"acc": 0.3425,
"acc_stderr": 0.013704669762934727
},
"cb": {
"acc": 0.42857142857142855,
"acc_stderr": 0.06672848092813058,
"f1": 0.21956970232832299
},
"copa": {
"acc": 0.74,
"acc_stderr": 0.044084400227680794
},
"hellaswag": {
"acc": 0.4480183230432185,
"acc_stderr": 0.004962742426849887,
"acc_norm": 0.5839474208325035,
"acc_norm_stderr": 0.0049189510191838875
},
"rte": {
"acc": 0.5631768953068592,
"acc_stderr": 0.029855247390314945
},
"winogrande": {
"acc": 0.5730071033938438,
"acc_stderr": 0.01390187807257506
},
"storycloze_2016": {
"acc": 0.6916087653661144,
"acc_stderr": 0.010679734445487797
},
"boolq": {
"acc": 0.5892966360856269,
"acc_stderr": 0.008604460608471413
},
"arc_easy": {
"acc": 0.609006734006734,
"acc_stderr": 0.010012992232540633,
"acc_norm": 0.5593434343434344,
"acc_norm_stderr": 0.010187264635711991
},
"arc_challenge": {
"acc": 0.2781569965870307,
"acc_stderr": 0.013094469919538816,
"acc_norm": 0.29436860068259385,
"acc_norm_stderr": 0.013318528460539426
},
"sciq": {
"acc": 0.865,
"acc_stderr": 0.010811655372416053,
"acc_norm": 0.793,
"acc_norm_stderr": 0.012818553557843983
},
"piqa": {
"acc": 0.7442872687704026,
"acc_stderr": 0.010178690109459857,
"acc_norm": 0.7546245919477693,
"acc_norm_stderr": 0.010039831320422386
}
},
"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
}
}