Epoch: 0001 train_loss= 2.08394 train_acc= 0.10943 val_loss= 2.08753 val_acc= 0.03448 time= 0.20315
Epoch: 0002 train_loss= 2.08205 train_acc= 0.10943 val_loss= 2.08771 val_acc= 0.03448 time= 0.01750
Epoch: 0003 train_loss= 2.08098 train_acc= 0.10943 val_loss= 2.08781 val_acc= 0.03448 time= 0.00907
Epoch: 0004 train_loss= 2.07880 train_acc= 0.10943 val_loss= 2.08807 val_acc= 0.03448 time= 0.00000
Epoch: 0005 train_loss= 2.07731 train_acc= 0.10943 val_loss= 2.08841 val_acc= 0.03448 time= 0.01563
Epoch: 0006 train_loss= 2.07563 train_acc= 0.11321 val_loss= 2.08875 val_acc= 0.03448 time= 0.01563
Epoch: 0007 train_loss= 2.07408 train_acc= 0.13208 val_loss= 2.08906 val_acc= 0.06897 time= 0.01563
Epoch: 0008 train_loss= 2.07373 train_acc= 0.14340 val_loss= 2.08937 val_acc= 0.06897 time= 0.00000
Epoch: 0009 train_loss= 2.07108 train_acc= 0.15094 val_loss= 2.08968 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.06917 train_acc= 0.13962 val_loss= 2.08999 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.06722 train_acc= 0.13962 val_loss= 2.09030 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.06544 train_acc= 0.13585 val_loss= 2.09055 val_acc= 0.06897 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.07746 accuracy= 0.18644 time= 0.00000 
