Epoch: 0001 train_loss= 0.69913 train_acc= 0.50000 val_loss= 0.69584 val_acc= 0.54098 time= 0.35257
Epoch: 0002 train_loss= 0.69813 train_acc= 0.51818 val_loss= 0.69417 val_acc= 0.54098 time= 0.01100
Epoch: 0003 train_loss= 0.69805 train_acc= 0.51091 val_loss= 0.69310 val_acc= 0.54098 time= 0.01500
Epoch: 0004 train_loss= 0.69767 train_acc= 0.50727 val_loss= 0.69236 val_acc= 0.54098 time= 0.01300
Epoch: 0005 train_loss= 0.69726 train_acc= 0.50909 val_loss= 0.69170 val_acc= 0.54098 time= 0.01300
Epoch: 0006 train_loss= 0.69668 train_acc= 0.51455 val_loss= 0.69138 val_acc= 0.54098 time= 0.01200
Epoch: 0007 train_loss= 0.69678 train_acc= 0.50909 val_loss= 0.69147 val_acc= 0.54098 time= 0.01200
Epoch: 0008 train_loss= 0.69597 train_acc= 0.50909 val_loss= 0.69161 val_acc= 0.54098 time= 0.01200
Epoch: 0009 train_loss= 0.69595 train_acc= 0.51091 val_loss= 0.69182 val_acc= 0.54098 time= 0.01300
Epoch: 0010 train_loss= 0.69545 train_acc= 0.50909 val_loss= 0.69193 val_acc= 0.54098 time= 0.01300
Epoch: 0011 train_loss= 0.69512 train_acc= 0.50909 val_loss= 0.69181 val_acc= 0.54098 time= 0.01100
Epoch: 0012 train_loss= 0.69501 train_acc= 0.50727 val_loss= 0.69143 val_acc= 0.54098 time= 0.01300
Epoch: 0013 train_loss= 0.69470 train_acc= 0.51091 val_loss= 0.69111 val_acc= 0.54098 time= 0.01100
Epoch: 0014 train_loss= 0.69454 train_acc= 0.50727 val_loss= 0.69098 val_acc= 0.54098 time= 0.01201
Epoch: 0015 train_loss= 0.69446 train_acc= 0.50727 val_loss= 0.69082 val_acc= 0.54098 time= 0.01200
Epoch: 0016 train_loss= 0.69415 train_acc= 0.51273 val_loss= 0.69057 val_acc= 0.54098 time= 0.01300
Epoch: 0017 train_loss= 0.69358 train_acc= 0.51455 val_loss= 0.69031 val_acc= 0.54098 time= 0.01200
Epoch: 0018 train_loss= 0.69390 train_acc= 0.51273 val_loss= 0.69016 val_acc= 0.54098 time= 0.01200
Epoch: 0019 train_loss= 0.69376 train_acc= 0.51818 val_loss= 0.68999 val_acc= 0.54098 time= 0.01200
Epoch: 0020 train_loss= 0.69342 train_acc= 0.51636 val_loss= 0.68963 val_acc= 0.54098 time= 0.01200
Epoch: 0021 train_loss= 0.69356 train_acc= 0.50727 val_loss= 0.68916 val_acc= 0.54098 time= 0.01100
Epoch: 0022 train_loss= 0.69410 train_acc= 0.50364 val_loss= 0.68907 val_acc= 0.54098 time= 0.01200
Epoch: 0023 train_loss= 0.69373 train_acc= 0.51091 val_loss= 0.68909 val_acc= 0.54098 time= 0.01400
Epoch: 0024 train_loss= 0.69349 train_acc= 0.50909 val_loss= 0.68924 val_acc= 0.54098 time= 0.01300
Epoch: 0025 train_loss= 0.69354 train_acc= 0.50909 val_loss= 0.68946 val_acc= 0.54098 time= 0.01400
Epoch: 0026 train_loss= 0.69326 train_acc= 0.50182 val_loss= 0.68966 val_acc= 0.54098 time= 0.00282
Epoch: 0027 train_loss= 0.69359 train_acc= 0.50909 val_loss= 0.68986 val_acc= 0.54098 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69291 accuracy= 0.53279 time= 0.00000 
