Muennighoff's picture
Add eval
1aec95b
raw
history blame
2.46 kB
{
"results": {
"anli_r1": {
"acc": 0.35,
"acc_stderr": 0.015090650341444233
},
"anli_r2": {
"acc": 0.321,
"acc_stderr": 0.014770821817934642
},
"anli_r3": {
"acc": 0.3458333333333333,
"acc_stderr": 0.013736245342311014
},
"cb": {
"acc": 0.48214285714285715,
"acc_stderr": 0.0673769750864465,
"f1": 0.3401360544217687
},
"copa": {
"acc": 0.74,
"acc_stderr": 0.0440844002276808
},
"hellaswag": {
"acc": 0.43248356901015733,
"acc_stderr": 0.004944080605048775,
"acc_norm": 0.5641306512646883,
"acc_norm_stderr": 0.004948567856373858
},
"rte": {
"acc": 0.5740072202166066,
"acc_stderr": 0.02976495674177765
},
"winogrande": {
"acc": 0.5580110497237569,
"acc_stderr": 0.013957584079108989
},
"storycloze_2016": {
"acc": 0.6926777124532336,
"acc_stderr": 0.01066944508186666
},
"boolq": {
"acc": 0.6027522935779817,
"acc_stderr": 0.008558401855851161
},
"arc_easy": {
"acc": 0.5778619528619529,
"acc_stderr": 0.010134620524592271,
"acc_norm": 0.5404040404040404,
"acc_norm_stderr": 0.010226230740889027
},
"arc_challenge": {
"acc": 0.26023890784982934,
"acc_stderr": 0.012821930225112566,
"acc_norm": 0.29436860068259385,
"acc_norm_stderr": 0.013318528460539427
},
"sciq": {
"acc": 0.851,
"acc_stderr": 0.011266140684632168,
"acc_norm": 0.827,
"acc_norm_stderr": 0.01196721413755994
},
"piqa": {
"acc": 0.7372143634385201,
"acc_stderr": 0.010269354068140767,
"acc_norm": 0.7334058759521219,
"acc_norm_stderr": 0.010316749863541365
}
},
"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
}
}