Epoch: 0001 train_loss= 2.08733 train_acc= 0.13836 val_loss= 2.08570 val_acc= 0.13793 time= 0.17189
Epoch: 0002 train_loss= 2.08497 train_acc= 0.12579 val_loss= 2.08483 val_acc= 0.06897 time= 0.01562
Epoch: 0003 train_loss= 2.08271 train_acc= 0.14465 val_loss= 2.08446 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.08077 train_acc= 0.12579 val_loss= 2.08451 val_acc= 0.13793 time= 0.01563
Epoch: 0005 train_loss= 2.07945 train_acc= 0.14465 val_loss= 2.08500 val_acc= 0.13793 time= 0.00000
Epoch: 0006 train_loss= 2.07786 train_acc= 0.15723 val_loss= 2.08583 val_acc= 0.13793 time= 0.01563
Epoch: 0007 train_loss= 2.07682 train_acc= 0.15723 val_loss= 2.08693 val_acc= 0.13793 time= 0.00000
Epoch: 0008 train_loss= 2.07562 train_acc= 0.16352 val_loss= 2.08832 val_acc= 0.13793 time= 0.00000
Epoch: 0009 train_loss= 2.07499 train_acc= 0.15094 val_loss= 2.08997 val_acc= 0.13793 time= 0.01563
Epoch: 0010 train_loss= 2.07307 train_acc= 0.16352 val_loss= 2.09191 val_acc= 0.13793 time= 0.00000
Epoch: 0011 train_loss= 2.07246 train_acc= 0.16352 val_loss= 2.09419 val_acc= 0.13793 time= 0.01563
Epoch: 0012 train_loss= 2.07309 train_acc= 0.14465 val_loss= 2.09648 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08616 accuracy= 0.11864 time= 0.00000 
