Epoch: 0001 train_loss= 1.40111 train_acc= 0.26536 val_loss= 1.39794 val_acc= 0.23214 time= 0.71880
Epoch: 0002 train_loss= 1.39942 train_acc= 0.26117 val_loss= 1.39362 val_acc= 0.26786 time= 0.01563
Epoch: 0003 train_loss= 1.39441 train_acc= 0.29609 val_loss= 1.39125 val_acc= 0.25000 time= 0.01563
Epoch: 0004 train_loss= 1.38630 train_acc= 0.29330 val_loss= 1.39104 val_acc= 0.26786 time= 0.01563
Epoch: 0005 train_loss= 1.37912 train_acc= 0.31006 val_loss= 1.39093 val_acc= 0.26786 time= 0.01563
Epoch: 0006 train_loss= 1.38129 train_acc= 0.28073 val_loss= 1.39105 val_acc= 0.26786 time= 0.00000
Epoch: 0007 train_loss= 1.38074 train_acc= 0.29330 val_loss= 1.39152 val_acc= 0.26786 time= 0.01563
Epoch: 0008 train_loss= 1.38529 train_acc= 0.29609 val_loss= 1.39176 val_acc= 0.26786 time= 0.01563
Epoch: 0009 train_loss= 1.38541 train_acc= 0.30307 val_loss= 1.39278 val_acc= 0.26786 time= 0.01562
Epoch: 0010 train_loss= 1.39266 train_acc= 0.27933 val_loss= 1.39365 val_acc= 0.26786 time= 0.01563
Epoch: 0011 train_loss= 1.38883 train_acc= 0.29469 val_loss= 1.39434 val_acc= 0.26786 time= 0.00000
Epoch: 0012 train_loss= 1.38580 train_acc= 0.31704 val_loss= 1.39492 val_acc= 0.25000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38597 accuracy= 0.29204 time= 0.00000 
