Muennighoff's picture
Add eval
b851397
raw
history blame
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.325,
"acc_stderr": 0.014818724459095526
},
"anli_r2": {
"acc": 0.325,
"acc_stderr": 0.014818724459095526
},
"anli_r3": {
"acc": 0.3233333333333333,
"acc_stderr": 0.013508372867300217
},
"cb": {
"acc": 0.25,
"acc_stderr": 0.058387420812114225,
"f1": 0.22987012987012986
},
"copa": {
"acc": 0.79,
"acc_stderr": 0.040936018074033256
},
"hellaswag": {
"acc": 0.47988448516231824,
"acc_stderr": 0.004985741706385727,
"acc_norm": 0.6363274248157738,
"acc_norm_stderr": 0.004800728138792371
},
"rte": {
"acc": 0.5631768953068592,
"acc_stderr": 0.02985524739031495
},
"winogrande": {
"acc": 0.5824782951854776,
"acc_stderr": 0.013859978264440248
},
"storycloze_2016": {
"acc": 0.7177979690005345,
"acc_stderr": 0.010407834479647673
},
"boolq": {
"acc": 0.627217125382263,
"acc_stderr": 0.008457255867914694
},
"arc_easy": {
"acc": 0.6308922558922558,
"acc_stderr": 0.009901987410242742,
"acc_norm": 0.6123737373737373,
"acc_norm_stderr": 0.009997307914447612
},
"arc_challenge": {
"acc": 0.30204778156996587,
"acc_stderr": 0.01341751914471642,
"acc_norm": 0.3216723549488055,
"acc_norm_stderr": 0.013650488084494162
},
"sciq": {
"acc": 0.914,
"acc_stderr": 0.008870325962594766,
"acc_norm": 0.883,
"acc_norm_stderr": 0.010169287802713329
},
"piqa": {
"acc": 0.7606093579978237,
"acc_stderr": 0.009955884250291681,
"acc_norm": 0.76550598476605,
"acc_norm_stderr": 0.009885203143240543
}
},
"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
}
}