Epoch: 0001 train_loss= 0.69067 train_acc= 0.54242 val_loss= 0.69536 val_acc= 0.47541 time= 0.23439
Epoch: 0002 train_loss= 0.69254 train_acc= 0.51212 val_loss= 0.69594 val_acc= 0.49180 time= 0.00000
Epoch: 0003 train_loss= 0.69136 train_acc= 0.53636 val_loss= 0.69673 val_acc= 0.49180 time= 0.00000
Epoch: 0004 train_loss= 0.68893 train_acc= 0.53939 val_loss= 0.69757 val_acc= 0.49180 time= 0.01563
Epoch: 0005 train_loss= 0.68889 train_acc= 0.54242 val_loss= 0.69856 val_acc= 0.49180 time= 0.00000
Epoch: 0006 train_loss= 0.68840 train_acc= 0.54848 val_loss= 0.69963 val_acc= 0.49180 time= 0.03174
Epoch: 0007 train_loss= 0.68832 train_acc= 0.53939 val_loss= 0.70081 val_acc= 0.49180 time= 0.00438
Epoch: 0008 train_loss= 0.68965 train_acc= 0.54242 val_loss= 0.70201 val_acc= 0.49180 time= 0.01563
Epoch: 0009 train_loss= 0.69013 train_acc= 0.53636 val_loss= 0.70315 val_acc= 0.49180 time= 0.00000
Epoch: 0010 train_loss= 0.68966 train_acc= 0.54848 val_loss= 0.70405 val_acc= 0.49180 time= 0.01563
Epoch: 0011 train_loss= 0.68987 train_acc= 0.54848 val_loss= 0.70480 val_acc= 0.49180 time= 0.01165
Epoch: 0012 train_loss= 0.68560 train_acc= 0.54242 val_loss= 0.70558 val_acc= 0.49180 time= 0.00403
Early stopping...
Optimization Finished!
Test set results: cost= 0.70578 accuracy= 0.46721 time= 0.00000 
