Muennighoff's picture
Add
2d13e6b
{
"results": {
"anli_r1": {
"acc": 0.334,
"acc_stderr": 0.014922019523732958
},
"anli_r2": {
"acc": 0.322,
"acc_stderr": 0.014782913600996673
},
"anli_r3": {
"acc": 0.3425,
"acc_stderr": 0.013704669762934727
},
"cb": {
"acc": 0.4642857142857143,
"acc_stderr": 0.06724777654937658,
"f1": 0.34145702306079667
},
"copa": {
"acc": 0.81,
"acc_stderr": 0.03942772444036623
},
"hellaswag": {
"acc": 0.49591714797849035,
"acc_stderr": 0.004989615052547472,
"acc_norm": 0.6609241187014538,
"acc_norm_stderr": 0.004724281487819379
},
"rte": {
"acc": 0.5595667870036101,
"acc_stderr": 0.029882123363118716
},
"winogrande": {
"acc": 0.5935280189423836,
"acc_stderr": 0.013804448697753375
},
"storycloze_2016": {
"acc": 0.7279529663281668,
"acc_stderr": 0.010290888060871242
},
"boolq": {
"acc": 0.6085626911314985,
"acc_stderr": 0.008536430524403954
},
"arc_easy": {
"acc": 0.6266835016835017,
"acc_stderr": 0.009925009142802914,
"acc_norm": 0.5782828282828283,
"acc_norm_stderr": 0.010133255284012316
},
"arc_challenge": {
"acc": 0.3037542662116041,
"acc_stderr": 0.013438909184778755,
"acc_norm": 0.32849829351535836,
"acc_norm_stderr": 0.013724978465537363
},
"sciq": {
"acc": 0.906,
"acc_stderr": 0.009233052000787733,
"acc_norm": 0.887,
"acc_norm_stderr": 0.010016552866696851
},
"piqa": {
"acc": 0.7562568008705114,
"acc_stderr": 0.010017199471500617,
"acc_norm": 0.7627856365614799,
"acc_norm_stderr": 0.009924694933586371
}
},
"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
}
}