Epoch: 0001 train_loss= 2.08500 train_acc= 0.15903 val_loss= 2.08181 val_acc= 0.03448 time= 0.34377
Epoch: 0002 train_loss= 2.08233 train_acc= 0.15903 val_loss= 2.07824 val_acc= 0.03448 time= 0.00000
Epoch: 0003 train_loss= 2.08040 train_acc= 0.15633 val_loss= 2.07524 val_acc= 0.03448 time= 0.01563
Epoch: 0004 train_loss= 2.07843 train_acc= 0.15903 val_loss= 2.07264 val_acc= 0.03448 time= 0.00000
Epoch: 0005 train_loss= 2.07654 train_acc= 0.15903 val_loss= 2.07068 val_acc= 0.03448 time= 0.01563
Epoch: 0006 train_loss= 2.07366 train_acc= 0.15903 val_loss= 2.06959 val_acc= 0.03448 time= 0.01563
Epoch: 0007 train_loss= 2.07182 train_acc= 0.15903 val_loss= 2.06934 val_acc= 0.03448 time= 0.00000
Epoch: 0008 train_loss= 2.06973 train_acc= 0.15903 val_loss= 2.07005 val_acc= 0.03448 time= 0.01562
Epoch: 0009 train_loss= 2.06786 train_acc= 0.15903 val_loss= 2.07162 val_acc= 0.03448 time= 0.00000
Epoch: 0010 train_loss= 2.06566 train_acc= 0.15903 val_loss= 2.07413 val_acc= 0.03448 time= 0.01563
Epoch: 0011 train_loss= 2.06333 train_acc= 0.15903 val_loss= 2.07749 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.06137 train_acc= 0.15903 val_loss= 2.08171 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.10328 accuracy= 0.13559 time= 0.00000 
