Epoch: 0001 train_loss= 1.42173 train_acc= 0.26172 val_loss= 1.37019 val_acc= 0.28333 time= 0.56281
Epoch: 0002 train_loss= 1.40782 train_acc= 0.25391 val_loss= 1.37095 val_acc= 0.33333 time= 0.01900
Epoch: 0003 train_loss= 1.39735 train_acc= 0.28125 val_loss= 1.37349 val_acc= 0.30000 time= 0.01800
Epoch: 0004 train_loss= 1.39223 train_acc= 0.30273 val_loss= 1.37685 val_acc= 0.33333 time= 0.01800
Epoch: 0005 train_loss= 1.38847 train_acc= 0.31055 val_loss= 1.38077 val_acc= 0.30000 time= 0.01400
Epoch: 0006 train_loss= 1.38447 train_acc= 0.28516 val_loss= 1.38480 val_acc= 0.31667 time= 0.01500
Epoch: 0007 train_loss= 1.38690 train_acc= 0.25977 val_loss= 1.38761 val_acc= 0.31667 time= 0.01500
Epoch: 0008 train_loss= 1.38339 train_acc= 0.28906 val_loss= 1.39008 val_acc= 0.28333 time= 0.01500
Epoch: 0009 train_loss= 1.37967 train_acc= 0.30078 val_loss= 1.39130 val_acc= 0.26667 time= 0.01800
Epoch: 0010 train_loss= 1.38544 train_acc= 0.30078 val_loss= 1.39251 val_acc= 0.28333 time= 0.01700
Epoch: 0011 train_loss= 1.38526 train_acc= 0.29883 val_loss= 1.39279 val_acc= 0.28333 time= 0.01565
Epoch: 0012 train_loss= 1.37561 train_acc= 0.30078 val_loss= 1.39245 val_acc= 0.28333 time= 0.01600
Early stopping...
Optimization Finished!
Test set results: cost= 1.39701 accuracy= 0.25000 time= 0.00700 
