Epoch: 0001 train_loss= 2.08436 train_acc= 0.16981 val_loss= 2.08390 val_acc= 0.10345 time= 0.12482
Epoch: 0002 train_loss= 2.08069 train_acc= 0.16981 val_loss= 2.08213 val_acc= 0.10345 time= 0.01563
Epoch: 0003 train_loss= 2.07782 train_acc= 0.18239 val_loss= 2.08050 val_acc= 0.27586 time= 0.00000
Epoch: 0004 train_loss= 2.07347 train_acc= 0.17610 val_loss= 2.07902 val_acc= 0.27586 time= 0.01562
Epoch: 0005 train_loss= 2.07083 train_acc= 0.20126 val_loss= 2.07763 val_acc= 0.27586 time= 0.01563
Epoch: 0006 train_loss= 2.06784 train_acc= 0.16981 val_loss= 2.07633 val_acc= 0.27586 time= 0.00000
Epoch: 0007 train_loss= 2.06459 train_acc= 0.14465 val_loss= 2.07514 val_acc= 0.10345 time= 0.01562
Epoch: 0008 train_loss= 2.06029 train_acc= 0.16981 val_loss= 2.07401 val_acc= 0.10345 time= 0.00000
Epoch: 0009 train_loss= 2.05794 train_acc= 0.16981 val_loss= 2.07299 val_acc= 0.10345 time= 0.01563
Epoch: 0010 train_loss= 2.05562 train_acc= 0.18239 val_loss= 2.07209 val_acc= 0.10345 time= 0.01563
Epoch: 0011 train_loss= 2.05146 train_acc= 0.16352 val_loss= 2.07138 val_acc= 0.10345 time= 0.00000
Epoch: 0012 train_loss= 2.04916 train_acc= 0.16981 val_loss= 2.07088 val_acc= 0.10345 time= 0.01563
Epoch: 0013 train_loss= 2.04578 train_acc= 0.16981 val_loss= 2.07065 val_acc= 0.10345 time= 0.00000
Epoch: 0014 train_loss= 2.04226 train_acc= 0.19497 val_loss= 2.07069 val_acc= 0.10345 time= 0.01563
Epoch: 0015 train_loss= 2.04016 train_acc= 0.17610 val_loss= 2.07105 val_acc= 0.10345 time= 0.00000
Epoch: 0016 train_loss= 2.03779 train_acc= 0.16352 val_loss= 2.07173 val_acc= 0.10345 time= 0.01563
Epoch: 0017 train_loss= 2.03891 train_acc= 0.16981 val_loss= 2.07270 val_acc= 0.10345 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.05058 accuracy= 0.13559 time= 0.00000 
