Muennighoff's picture
Add eval
d522938
raw
history blame
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.359,
"acc_stderr": 0.015177264224798592
},
"anli_r2": {
"acc": 0.349,
"acc_stderr": 0.0150806639915631
},
"anli_r3": {
"acc": 0.3383333333333333,
"acc_stderr": 0.013664144006618275
},
"cb": {
"acc": 0.44642857142857145,
"acc_stderr": 0.067031892279424,
"f1": 0.3171262699564586
},
"copa": {
"acc": 0.8,
"acc_stderr": 0.040201512610368445
},
"hellaswag": {
"acc": 0.42869946225851424,
"acc_stderr": 0.004938787067611805,
"acc_norm": 0.5677155945030871,
"acc_norm_stderr": 0.004943809330692693
},
"rte": {
"acc": 0.5090252707581228,
"acc_stderr": 0.030091559826331334
},
"winogrande": {
"acc": 0.5627466456195738,
"acc_stderr": 0.013941393310695918
},
"storycloze_2016": {
"acc": 0.6969535008017104,
"acc_stderr": 0.010627613073376717
},
"boolq": {
"acc": 0.6039755351681957,
"acc_stderr": 0.008553881336813413
},
"arc_easy": {
"acc": 0.5968013468013468,
"acc_stderr": 0.01006566857679479,
"acc_norm": 0.5585016835016835,
"acc_norm_stderr": 0.010189314382749936
},
"arc_challenge": {
"acc": 0.2645051194539249,
"acc_stderr": 0.012889272949313366,
"acc_norm": 0.302901023890785,
"acc_norm_stderr": 0.013428241573185349
},
"sciq": {
"acc": 0.889,
"acc_stderr": 0.009938701010583726,
"acc_norm": 0.87,
"acc_norm_stderr": 0.01064016979249935
},
"piqa": {
"acc": 0.7388465723612623,
"acc_stderr": 0.010248738649935587,
"acc_norm": 0.7393906420021763,
"acc_norm_stderr": 0.010241826155811632
}
},
"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
}
}