Epoch: 0001 train_loss= 2.09972 train_acc= 0.19497 val_loss= 2.05438 val_acc= 0.24138 time= 0.14063
Epoch: 0002 train_loss= 2.09423 train_acc= 0.16352 val_loss= 2.05494 val_acc= 0.24138 time= 0.00000
Epoch: 0003 train_loss= 2.08112 train_acc= 0.13836 val_loss= 2.05488 val_acc= 0.27586 time= 0.01563
Epoch: 0004 train_loss= 2.08126 train_acc= 0.20126 val_loss= 2.05456 val_acc= 0.24138 time= 0.00000
Epoch: 0005 train_loss= 2.07393 train_acc= 0.17610 val_loss= 2.05501 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.06883 train_acc= 0.15094 val_loss= 2.05581 val_acc= 0.24138 time= 0.00000
Epoch: 0007 train_loss= 2.04186 train_acc= 0.22013 val_loss= 2.05692 val_acc= 0.24138 time= 0.01563
Epoch: 0008 train_loss= 2.04549 train_acc= 0.16352 val_loss= 2.05831 val_acc= 0.20690 time= 0.00000
Epoch: 0009 train_loss= 2.05662 train_acc= 0.15094 val_loss= 2.05941 val_acc= 0.13793 time= 0.01819
Epoch: 0010 train_loss= 2.04836 train_acc= 0.17610 val_loss= 2.06056 val_acc= 0.10345 time= 0.00202
Epoch: 0011 train_loss= 2.03796 train_acc= 0.20755 val_loss= 2.06193 val_acc= 0.10345 time= 0.01150
Epoch: 0012 train_loss= 2.03273 train_acc= 0.20126 val_loss= 2.06330 val_acc= 0.03448 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.11630 accuracy= 0.13559 time= 0.00000 
