Epoch: 0001 train_loss= 0.69280 train_acc= 0.52727 val_loss= 0.68674 val_acc= 0.62295 time= 0.26564
Epoch: 0002 train_loss= 0.69477 train_acc= 0.50303 val_loss= 0.68820 val_acc= 0.60656 time= 0.00000
Epoch: 0003 train_loss= 0.69206 train_acc= 0.51212 val_loss= 0.68864 val_acc= 0.60656 time= 0.01563
Epoch: 0004 train_loss= 0.69343 train_acc= 0.53636 val_loss= 0.68846 val_acc= 0.60656 time= 0.00000
Epoch: 0005 train_loss= 0.69443 train_acc= 0.51515 val_loss= 0.68833 val_acc= 0.60656 time= 0.00000
Epoch: 0006 train_loss= 0.69355 train_acc= 0.51515 val_loss= 0.68847 val_acc= 0.60656 time= 0.01563
Epoch: 0007 train_loss= 0.69425 train_acc= 0.50303 val_loss= 0.68885 val_acc= 0.59016 time= 0.00000
Epoch: 0008 train_loss= 0.69421 train_acc= 0.50606 val_loss= 0.68889 val_acc= 0.59016 time= 0.00000
Epoch: 0009 train_loss= 0.69297 train_acc= 0.54545 val_loss= 0.68890 val_acc= 0.60656 time= 0.01563
Epoch: 0010 train_loss= 0.69331 train_acc= 0.55152 val_loss= 0.68874 val_acc= 0.60656 time= 0.00000
Epoch: 0011 train_loss= 0.69311 train_acc= 0.48485 val_loss= 0.68843 val_acc= 0.60656 time= 0.00000
Epoch: 0012 train_loss= 0.69272 train_acc= 0.52121 val_loss= 0.68827 val_acc= 0.62295 time= 0.01563
Epoch: 0013 train_loss= 0.69270 train_acc= 0.54242 val_loss= 0.68802 val_acc= 0.62295 time= 0.01772
Epoch: 0014 train_loss= 0.69320 train_acc= 0.52727 val_loss= 0.68805 val_acc= 0.62295 time= 0.00600
Epoch: 0015 train_loss= 0.69323 train_acc= 0.51212 val_loss= 0.68817 val_acc= 0.62295 time= 0.00000
Epoch: 0016 train_loss= 0.69348 train_acc= 0.50303 val_loss= 0.68832 val_acc= 0.62295 time= 0.01567
Epoch: 0017 train_loss= 0.69375 train_acc= 0.52121 val_loss= 0.68858 val_acc= 0.62295 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69150 accuracy= 0.54918 time= 0.01563 
