有用过proc glmselect的大师吗？

有个问题想请教一下，为什么每次可以纳入的变量数都不能超过3000？

超过3000，会提醒：ERROR: Selection aborted because there are no suitable observations for training.

Observation Profile for Analysis Data
Number of Observations Read 500
Number of Observations Used 0
Number of Observations Used for Training 0

Observation Profile for Validation Data
Number of Observations Read 500
Number of Observations Used 0

Observation Profile for Test Data
Number of Observations Read 500
Number of Observations Used 0

原始代码如下：
proc glmselect testdata=train valdata=test;
model y=x1-x10000/selection=elasticnet(stop=none L2=0.1 choose=validate) cvmethod=random(10);
run;

初学SAS，应该怎么调整呢？应该纳入10000才对，谢谢