lm1-2b8-55b-c4-dedup / evaluation /rankeval /lm1-2b8-55b-nodups_4.json
Muennighoff's picture
add
874e9d6
{
"results": {
"anli_r1": {
"acc": 0.331,
"acc_stderr": 0.014888272588203926
},
"anli_r2": {
"acc": 0.339,
"acc_stderr": 0.01497675877162035
},
"anli_r3": {
"acc": 0.34,
"acc_stderr": 0.013680495725767794
},
"cb": {
"acc": 0.3392857142857143,
"acc_stderr": 0.06384226561930825,
"f1": 0.31372797744890774
},
"copa": {
"acc": 0.79,
"acc_stderr": 0.040936018074033256
},
"hellaswag": {
"acc": 0.4364668392750448,
"acc_stderr": 0.0049493353568818635,
"acc_norm": 0.5734913363871739,
"acc_norm_stderr": 0.004935587729948866
},
"rte": {
"acc": 0.48014440433212996,
"acc_stderr": 0.0300727231673172
},
"winogrande": {
"acc": 0.5627466456195738,
"acc_stderr": 0.013941393310695922
},
"storycloze_2016": {
"acc": 0.7172634954569749,
"acc_stderr": 0.010413806486121271
},
"boolq": {
"acc": 0.48807339449541287,
"acc_stderr": 0.008742566760633421
},
"arc_easy": {
"acc": 0.5845959595959596,
"acc_stderr": 0.010111869494911517,
"acc_norm": 0.5555555555555556,
"acc_norm_stderr": 0.01019625483869168
},
"arc_challenge": {
"acc": 0.26109215017064846,
"acc_stderr": 0.012835523909473848,
"acc_norm": 0.2858361774744027,
"acc_norm_stderr": 0.013203196088537367
},
"sciq": {
"acc": 0.857,
"acc_stderr": 0.01107581480856704,
"acc_norm": 0.842,
"acc_norm_stderr": 0.011539894677559564
},
"piqa": {
"acc": 0.7404787812840044,
"acc_stderr": 0.01022793988817392,
"acc_norm": 0.7529923830250272,
"acc_norm_stderr": 0.010062268140772625
}
},
"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
}
}