Epoch: 0001 train_loss= 0.96598 train_acc= 0.49091 val_loss= 0.96698 val_acc= 0.65574 time= 0.12503
Epoch: 0002 train_loss= 1.64101 train_acc= 0.53939 val_loss= 0.93175 val_acc= 0.65574 time= 0.01200
Epoch: 0003 train_loss= 0.92855 train_acc= 0.52727 val_loss= 0.88631 val_acc= 0.65574 time= 0.01300
Epoch: 0004 train_loss= 1.49938 train_acc= 0.54545 val_loss= 0.78674 val_acc= 0.65574 time= 0.01100
Epoch: 0005 train_loss= 0.85588 train_acc= 0.54848 val_loss= 0.70990 val_acc= 0.62295 time= 0.01100
Epoch: 0006 train_loss= 0.82626 train_acc= 0.56667 val_loss= 0.69792 val_acc= 0.55738 time= 0.01100
Epoch: 0007 train_loss= 1.12317 train_acc= 0.50606 val_loss= 0.73135 val_acc= 0.45902 time= 0.01200
Epoch: 0008 train_loss= 1.20445 train_acc= 0.48788 val_loss= 0.77938 val_acc= 0.36066 time= 0.01000
Epoch: 0009 train_loss= 0.85155 train_acc= 0.49394 val_loss= 0.82433 val_acc= 0.37705 time= 0.01300
Epoch: 0010 train_loss= 0.77649 train_acc= 0.50909 val_loss= 0.87729 val_acc= 0.34426 time= 0.01200
Epoch: 0011 train_loss= 0.82793 train_acc= 0.51515 val_loss= 0.90949 val_acc= 0.34426 time= 0.01300
Epoch: 0012 train_loss= 0.94265 train_acc= 0.47273 val_loss= 0.90175 val_acc= 0.31148 time= 0.01200
Early stopping...
Optimization Finished!
Test set results: cost= 0.92598 accuracy= 0.42623 time= 0.00600 
