Epoch: 0001 train_loss= 1.37761 train_acc= 0.27930 val_loss= 1.42720 val_acc= 0.13333 time= 0.56254
Epoch: 0002 train_loss= 1.37416 train_acc= 0.30664 val_loss= 1.42901 val_acc= 0.26667 time= 0.00000
Epoch: 0003 train_loss= 1.37501 train_acc= 0.29102 val_loss= 1.43079 val_acc= 0.26667 time= 0.00000
Epoch: 0004 train_loss= 1.37277 train_acc= 0.28906 val_loss= 1.43192 val_acc= 0.26667 time= 0.01563
Epoch: 0005 train_loss= 1.36999 train_acc= 0.33984 val_loss= 1.43278 val_acc= 0.26667 time= 0.00000
Epoch: 0006 train_loss= 1.37015 train_acc= 0.32422 val_loss= 1.43320 val_acc= 0.26667 time= 0.01563
Epoch: 0007 train_loss= 1.37020 train_acc= 0.30664 val_loss= 1.43364 val_acc= 0.26667 time= 0.00000
Epoch: 0008 train_loss= 1.36644 train_acc= 0.33203 val_loss= 1.43401 val_acc= 0.26667 time= 0.01563
Epoch: 0009 train_loss= 1.36623 train_acc= 0.30664 val_loss= 1.43430 val_acc= 0.26667 time= 0.00000
Epoch: 0010 train_loss= 1.36781 train_acc= 0.31445 val_loss= 1.43442 val_acc= 0.26667 time= 0.01563
Epoch: 0011 train_loss= 1.36575 train_acc= 0.31836 val_loss= 1.43494 val_acc= 0.26667 time= 0.00000
Epoch: 0012 train_loss= 1.36645 train_acc= 0.31445 val_loss= 1.43505 val_acc= 0.26667 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39275 accuracy= 0.31667 time= 0.00000 
