Muennighoff's picture
Add
2d13e6b
{
"results": {
"anli_r1": {
"acc": 0.341,
"acc_stderr": 0.014998131348402709
},
"anli_r2": {
"acc": 0.358,
"acc_stderr": 0.01516792886540756
},
"anli_r3": {
"acc": 0.3516666666666667,
"acc_stderr": 0.013789711695404794
},
"cb": {
"acc": 0.4642857142857143,
"acc_stderr": 0.06724777654937658,
"f1": 0.41697135221649567
},
"copa": {
"acc": 0.8,
"acc_stderr": 0.040201512610368445
},
"hellaswag": {
"acc": 0.4998008364867556,
"acc_stderr": 0.0049897810155954715,
"acc_norm": 0.6693885680143398,
"acc_norm_stderr": 0.004694718918225764
},
"rte": {
"acc": 0.5523465703971119,
"acc_stderr": 0.02993107036293953
},
"winogrande": {
"acc": 0.5887924230465666,
"acc_stderr": 0.013829128358676862
},
"storycloze_2016": {
"acc": 0.7471940138963121,
"acc_stderr": 0.01005054390987858
},
"boolq": {
"acc": 0.6425076452599389,
"acc_stderr": 0.008382336069484898
},
"arc_easy": {
"acc": 0.6506734006734006,
"acc_stderr": 0.009782853449399284,
"acc_norm": 0.6300505050505051,
"acc_norm_stderr": 0.009906656266021148
},
"arc_challenge": {
"acc": 0.3165529010238908,
"acc_stderr": 0.01359243151906808,
"acc_norm": 0.3378839590443686,
"acc_norm_stderr": 0.013822047922283509
},
"sciq": {
"acc": 0.935,
"acc_stderr": 0.007799733061832011,
"acc_norm": 0.925,
"acc_norm_stderr": 0.008333333333333364
},
"piqa": {
"acc": 0.7622415669205659,
"acc_stderr": 0.009932525779525489,
"acc_norm": 0.779651795429815,
"acc_norm_stderr": 0.009670535456853148
}
},
"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
}
}