Epoch: 0001 train_loss= 2.08711 train_acc= 0.11950 val_loss= 2.08157 val_acc= 0.17241 time= 0.09376
Epoch: 0002 train_loss= 2.08485 train_acc= 0.11950 val_loss= 2.08209 val_acc= 0.17241 time= 0.01563
Epoch: 0003 train_loss= 2.08302 train_acc= 0.11950 val_loss= 2.08290 val_acc= 0.17241 time= 0.00000
Epoch: 0004 train_loss= 2.08066 train_acc= 0.13208 val_loss= 2.08402 val_acc= 0.13793 time= 0.01563
Epoch: 0005 train_loss= 2.07913 train_acc= 0.16981 val_loss= 2.08526 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.07742 train_acc= 0.16981 val_loss= 2.08693 val_acc= 0.13793 time= 0.00000
Epoch: 0007 train_loss= 2.07568 train_acc= 0.16352 val_loss= 2.08901 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.07335 train_acc= 0.16981 val_loss= 2.09163 val_acc= 0.13793 time= 0.01563
Epoch: 0009 train_loss= 2.07201 train_acc= 0.16981 val_loss= 2.09476 val_acc= 0.13793 time= 0.00000
Epoch: 0010 train_loss= 2.07005 train_acc= 0.16981 val_loss= 2.09834 val_acc= 0.13793 time= 0.01563
Epoch: 0011 train_loss= 2.06704 train_acc= 0.16981 val_loss= 2.10243 val_acc= 0.13793 time= 0.00000
Epoch: 0012 train_loss= 2.06683 train_acc= 0.16981 val_loss= 2.10682 val_acc= 0.13793 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.09005 accuracy= 0.18644 time= 0.00000 
