Muennighoff's picture
Add eval
d522938
{
"results": {
"anli_r1": {
"acc": 0.354,
"acc_stderr": 0.015129868238451773
},
"anli_r2": {
"acc": 0.334,
"acc_stderr": 0.014922019523732965
},
"anli_r3": {
"acc": 0.3525,
"acc_stderr": 0.013797164918918355
},
"cb": {
"acc": 0.5178571428571429,
"acc_stderr": 0.06737697508644647,
"f1": 0.34887334887334887
},
"copa": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446
},
"hellaswag": {
"acc": 0.4297948615813583,
"acc_stderr": 0.004940349676769321,
"acc_norm": 0.5647281418044214,
"acc_norm_stderr": 0.004947793051042662
},
"rte": {
"acc": 0.5523465703971119,
"acc_stderr": 0.029931070362939526
},
"winogrande": {
"acc": 0.5611681136543015,
"acc_stderr": 0.013946933444507032
},
"storycloze_2016": {
"acc": 0.6905398182789952,
"acc_stderr": 0.010689956745189072
},
"boolq": {
"acc": 0.6128440366972477,
"acc_stderr": 0.008519429207594416
},
"arc_easy": {
"acc": 0.5867003367003367,
"acc_stderr": 0.010104361780747513,
"acc_norm": 0.5774410774410774,
"acc_norm_stderr": 0.010135978222981075
},
"arc_challenge": {
"acc": 0.24744027303754265,
"acc_stderr": 0.012610352663292673,
"acc_norm": 0.27559726962457337,
"acc_norm_stderr": 0.013057169655761838
},
"sciq": {
"acc": 0.901,
"acc_stderr": 0.009449248027662732,
"acc_norm": 0.912,
"acc_norm_stderr": 0.008963053962592085
},
"piqa": {
"acc": 0.733949945593036,
"acc_stderr": 0.010310039263352831,
"acc_norm": 0.7421109902067464,
"acc_norm_stderr": 0.010206956662056232
}
},
"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
}
}