Epoch: 0001 train_loss= 0.70110 train_acc= 0.50000 val_loss= 0.69806 val_acc= 0.49180 time= 0.14117
Epoch: 0002 train_loss= 0.69801 train_acc= 0.52121 val_loss= 0.69586 val_acc= 0.49180 time= 0.01567
Epoch: 0003 train_loss= 0.69563 train_acc= 0.51818 val_loss= 0.69439 val_acc= 0.49180 time= 0.01563
Epoch: 0004 train_loss= 0.69399 train_acc= 0.51818 val_loss= 0.69352 val_acc= 0.49180 time= 0.00000
Epoch: 0005 train_loss= 0.69296 train_acc= 0.51515 val_loss= 0.69308 val_acc= 0.49180 time= 0.01563
Epoch: 0006 train_loss= 0.69245 train_acc= 0.51818 val_loss= 0.69293 val_acc= 0.49180 time= 0.01563
Epoch: 0007 train_loss= 0.69212 train_acc= 0.52121 val_loss= 0.69298 val_acc= 0.49180 time= 0.01563
Epoch: 0008 train_loss= 0.69201 train_acc= 0.52121 val_loss= 0.69313 val_acc= 0.49180 time= 0.00000
Epoch: 0009 train_loss= 0.69206 train_acc= 0.52121 val_loss= 0.69329 val_acc= 0.49180 time= 0.01563
Epoch: 0010 train_loss= 0.69186 train_acc= 0.51818 val_loss= 0.69341 val_acc= 0.49180 time= 0.01563
Epoch: 0011 train_loss= 0.69125 train_acc= 0.52424 val_loss= 0.69350 val_acc= 0.49180 time= 0.00000
Epoch: 0012 train_loss= 0.69162 train_acc= 0.52121 val_loss= 0.69353 val_acc= 0.49180 time= 0.01563
Epoch: 0013 train_loss= 0.69134 train_acc= 0.52424 val_loss= 0.69351 val_acc= 0.49180 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69030 accuracy= 0.52459 time= 0.00000 
