Muennighoff's picture
Add
411a88c
raw
history blame
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.337,
"acc_stderr": 0.014955087918653605
},
"anli_r2": {
"acc": 0.327,
"acc_stderr": 0.014842213153411242
},
"anli_r3": {
"acc": 0.3475,
"acc_stderr": 0.013751753243291854
},
"cb": {
"acc": 0.4642857142857143,
"acc_stderr": 0.06724777654937658,
"f1": 0.3011204481792717
},
"copa": {
"acc": 0.79,
"acc_stderr": 0.040936018074033256
},
"hellaswag": {
"acc": 0.4069906393148775,
"acc_stderr": 0.004902690765066426,
"acc_norm": 0.518621788488349,
"acc_norm_stderr": 0.004986319587524956
},
"rte": {
"acc": 0.5487364620938628,
"acc_stderr": 0.029953149241808946
},
"winogrande": {
"acc": 0.5524861878453039,
"acc_stderr": 0.013974847640536203
},
"storycloze_2016": {
"acc": 0.6440406199893105,
"acc_stderr": 0.01107225418438284
},
"boolq": {
"acc": 0.5223241590214067,
"acc_stderr": 0.00873633411558504
},
"arc_easy": {
"acc": 0.5286195286195287,
"acc_stderr": 0.010242962617927195,
"acc_norm": 0.4654882154882155,
"acc_norm_stderr": 0.010235314238969397
},
"arc_challenge": {
"acc": 0.24744027303754265,
"acc_stderr": 0.012610352663292673,
"acc_norm": 0.28924914675767915,
"acc_norm_stderr": 0.013250012579393443
},
"sciq": {
"acc": 0.75,
"acc_stderr": 0.013699915608779773,
"acc_norm": 0.681,
"acc_norm_stderr": 0.014746404865473493
},
"piqa": {
"acc": 0.7143634385201306,
"acc_stderr": 0.010539303948661932,
"acc_norm": 0.7241566920565833,
"acc_norm_stderr": 0.01042780550272912
}
},
"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
}
}