lm1-misc-pile / 221m60b60b /evaluation /rankeval /lm1-221m-60b-results_lm-eval_global_step115203_2023-01-24-17-05-33_5shots.json
Muennighoff's picture
Add
c305798
{
"results": {
"anli_r1": {
"acc": 0.356,
"acc_stderr": 0.015149042659306623
},
"anli_r2": {
"acc": 0.33,
"acc_stderr": 0.014876872027456736
},
"anli_r3": {
"acc": 0.3408333333333333,
"acc_stderr": 0.013688600793296939
},
"cb": {
"acc": 0.5357142857142857,
"acc_stderr": 0.06724777654937658,
"f1": 0.38247863247863245
},
"copa": {
"acc": 0.67,
"acc_stderr": 0.04725815626252607
},
"hellaswag": {
"acc": 0.2932682732523402,
"acc_stderr": 0.00454329933893543,
"acc_norm": 0.32135032861979684,
"acc_norm_stderr": 0.004660405565338758
},
"rte": {
"acc": 0.5379061371841155,
"acc_stderr": 0.030009848912529117
},
"winogrande": {
"acc": 0.5059194948697711,
"acc_stderr": 0.014051500838485807
},
"storycloze_2016": {
"acc": 0.5820416889363976,
"acc_stderr": 0.011405720519793931
},
"boolq": {
"acc": 0.5143730886850153,
"acc_stderr": 0.008741441023424116
},
"arc_easy": {
"acc": 0.4722222222222222,
"acc_stderr": 0.010243938285881115,
"acc_norm": 0.4452861952861953,
"acc_norm_stderr": 0.010198171137873855
},
"arc_challenge": {
"acc": 0.19965870307167236,
"acc_stderr": 0.011681625756888681,
"acc_norm": 0.2295221843003413,
"acc_norm_stderr": 0.01228892676089078
},
"sciq": {
"acc": 0.837,
"acc_stderr": 0.011686212712746856,
"acc_norm": 0.822,
"acc_norm_stderr": 0.012102167676183585
},
"piqa": {
"acc": 0.6360174102285092,
"acc_stderr": 0.011225875703487176,
"acc_norm": 0.6256800870511425,
"acc_norm_stderr": 0.011291276801194992
}
},
"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
}
}