Epoch: 0001 train_loss= 2.08891 train_acc= 0.13208 val_loss= 2.08971 val_acc= 0.06897 time= 0.10938
Epoch: 0002 train_loss= 2.08606 train_acc= 0.11950 val_loss= 2.08860 val_acc= 0.06897 time= 0.01562
Epoch: 0003 train_loss= 2.08406 train_acc= 0.11950 val_loss= 2.08741 val_acc= 0.06897 time= 0.00000
Epoch: 0004 train_loss= 2.08231 train_acc= 0.11950 val_loss= 2.08641 val_acc= 0.06897 time= 0.01563
Epoch: 0005 train_loss= 2.08041 train_acc= 0.11950 val_loss= 2.08559 val_acc= 0.06897 time= 0.00000
Epoch: 0006 train_loss= 2.07896 train_acc= 0.17610 val_loss= 2.08564 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.07719 train_acc= 0.17610 val_loss= 2.08606 val_acc= 0.06897 time= 0.01563
Epoch: 0008 train_loss= 2.07540 train_acc= 0.17610 val_loss= 2.08666 val_acc= 0.06897 time= 0.00000
Epoch: 0009 train_loss= 2.07429 train_acc= 0.17610 val_loss= 2.08740 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.07302 train_acc= 0.17610 val_loss= 2.08830 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.07108 train_acc= 0.17610 val_loss= 2.08945 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.07033 train_acc= 0.17610 val_loss= 2.09081 val_acc= 0.06897 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.06932 accuracy= 0.20339 time= 0.00000 
