Epoch: 0001 train_loss= 1.08072 train_acc= 0.54242 val_loss= 0.83111 val_acc= 0.37705 time= 0.31253
Epoch: 0002 train_loss= 0.92067 train_acc= 0.50303 val_loss= 0.85061 val_acc= 0.45902 time= 0.01562
Epoch: 0003 train_loss= 0.79626 train_acc= 0.50303 val_loss= 0.87241 val_acc= 0.44262 time= 0.03125
Epoch: 0004 train_loss= 0.83902 train_acc= 0.51212 val_loss= 0.84726 val_acc= 0.47541 time= 0.01563
Epoch: 0005 train_loss= 0.85020 train_acc= 0.54545 val_loss= 0.80739 val_acc= 0.54098 time= 0.01563
Epoch: 0006 train_loss= 0.72670 train_acc= 0.53030 val_loss= 0.76981 val_acc= 0.50820 time= 0.03125
Epoch: 0007 train_loss= 0.84275 train_acc= 0.50000 val_loss= 0.75949 val_acc= 0.52459 time= 0.01563
Epoch: 0008 train_loss= 0.70511 train_acc= 0.58485 val_loss= 0.76510 val_acc= 0.52459 time= 0.01562
Epoch: 0009 train_loss= 1.02082 train_acc= 0.55152 val_loss= 0.76838 val_acc= 0.52459 time= 0.03125
Epoch: 0010 train_loss= 0.71581 train_acc= 0.58485 val_loss= 0.76890 val_acc= 0.52459 time= 0.01563
Epoch: 0011 train_loss= 0.73937 train_acc= 0.52121 val_loss= 0.77194 val_acc= 0.52459 time= 0.01563
Epoch: 0012 train_loss= 0.70092 train_acc= 0.54848 val_loss= 0.77433 val_acc= 0.52459 time= 0.03125
Epoch: 0013 train_loss= 0.70528 train_acc= 0.54848 val_loss= 0.77744 val_acc= 0.52459 time= 0.01563
Epoch: 0014 train_loss= 0.72543 train_acc= 0.54848 val_loss= 0.77995 val_acc= 0.52459 time= 0.01563
Epoch: 0015 train_loss= 0.71234 train_acc= 0.56061 val_loss= 0.77987 val_acc= 0.55738 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 0.70836 accuracy= 0.55738 time= 0.00000 
