Epoch: 0001 train_loss= 2.08591 train_acc= 0.09434 val_loss= 2.07952 val_acc= 0.27586 time= 0.25001
Epoch: 0002 train_loss= 2.08484 train_acc= 0.10189 val_loss= 2.07864 val_acc= 0.17241 time= 0.00151
Epoch: 0003 train_loss= 2.08387 train_acc= 0.14717 val_loss= 2.07822 val_acc= 0.17241 time= 0.01651
Epoch: 0004 train_loss= 2.08242 train_acc= 0.14717 val_loss= 2.07803 val_acc= 0.17241 time= 0.00000
Epoch: 0005 train_loss= 2.08114 train_acc= 0.15094 val_loss= 2.07792 val_acc= 0.17241 time= 0.01651
Epoch: 0006 train_loss= 2.08035 train_acc= 0.14717 val_loss= 2.07785 val_acc= 0.17241 time= 0.01651
Epoch: 0007 train_loss= 2.07921 train_acc= 0.15094 val_loss= 2.07806 val_acc= 0.17241 time= 0.00000
Epoch: 0008 train_loss= 2.07858 train_acc= 0.14340 val_loss= 2.07852 val_acc= 0.17241 time= 0.01301
Epoch: 0009 train_loss= 2.07818 train_acc= 0.15094 val_loss= 2.07923 val_acc= 0.17241 time= 0.01563
Epoch: 0010 train_loss= 2.07720 train_acc= 0.15094 val_loss= 2.08018 val_acc= 0.17241 time= 0.00000
Epoch: 0011 train_loss= 2.07566 train_acc= 0.15094 val_loss= 2.08140 val_acc= 0.17241 time= 0.01563
Epoch: 0012 train_loss= 2.07480 train_acc= 0.15094 val_loss= 2.08289 val_acc= 0.17241 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.05315 accuracy= 0.22034 time= 0.00000 
