Epoch: 0001 train_loss= 2.08593 train_acc= 0.09434 val_loss= 2.07439 val_acc= 0.20690 time= 0.12501
Epoch: 0002 train_loss= 2.10536 train_acc= 0.11950 val_loss= 2.07198 val_acc= 0.17241 time= 0.01563
Epoch: 0003 train_loss= 2.07521 train_acc= 0.12579 val_loss= 2.06997 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.07487 train_acc= 0.16352 val_loss= 2.06859 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.05483 train_acc= 0.19497 val_loss= 2.06926 val_acc= 0.20690 time= 0.00000
Epoch: 0006 train_loss= 2.06885 train_acc= 0.15723 val_loss= 2.07004 val_acc= 0.17241 time= 0.01563
Epoch: 0007 train_loss= 2.05077 train_acc= 0.20126 val_loss= 2.07110 val_acc= 0.17241 time= 0.01563
Epoch: 0008 train_loss= 2.05479 train_acc= 0.16352 val_loss= 2.07245 val_acc= 0.17241 time= 0.00000
Epoch: 0009 train_loss= 2.05000 train_acc= 0.16352 val_loss= 2.07396 val_acc= 0.10345 time= 0.01563
Epoch: 0010 train_loss= 2.03090 train_acc= 0.22642 val_loss= 2.07553 val_acc= 0.06897 time= 0.00000
Epoch: 0011 train_loss= 2.02401 train_acc= 0.22013 val_loss= 2.07713 val_acc= 0.06897 time= 0.01563
Epoch: 0012 train_loss= 2.03174 train_acc= 0.16981 val_loss= 2.07878 val_acc= 0.06897 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.10938 accuracy= 0.16949 time= 0.01562 
