Epoch: 0001 train_loss= 2.29718 train_acc= 0.25407 val_loss= 1.51693 val_acc= 0.16071 time= 0.33948
Epoch: 0002 train_loss= 1.55734 train_acc= 0.22801 val_loss= 1.44230 val_acc= 0.16071 time= 0.02329
Epoch: 0003 train_loss= 1.85528 train_acc= 0.22476 val_loss= 1.47453 val_acc= 0.19643 time= 0.02325
Epoch: 0004 train_loss= 1.45982 train_acc= 0.19870 val_loss= 1.58849 val_acc= 0.23214 time= 0.02212
Epoch: 0005 train_loss= 1.79949 train_acc= 0.29316 val_loss= 1.56228 val_acc= 0.23214 time= 0.01221
Epoch: 0006 train_loss= 1.71201 train_acc= 0.27362 val_loss= 1.45940 val_acc= 0.23214 time= 0.03308
Epoch: 0007 train_loss= 1.99828 train_acc= 0.23453 val_loss= 1.40551 val_acc= 0.25000 time= 0.02401
Epoch: 0008 train_loss= 1.53880 train_acc= 0.29316 val_loss= 1.39542 val_acc= 0.23214 time= 0.02254
Epoch: 0009 train_loss= 1.42592 train_acc= 0.17915 val_loss= 1.39427 val_acc= 0.23214 time= 0.02401
Epoch: 0010 train_loss= 1.39993 train_acc= 0.24430 val_loss= 1.39261 val_acc= 0.23214 time= 0.02501
Epoch: 0011 train_loss= 1.54833 train_acc= 0.26384 val_loss= 1.39021 val_acc= 0.28571 time= 0.02501
Epoch: 0012 train_loss= 1.53183 train_acc= 0.25733 val_loss= 1.38738 val_acc= 0.26786 time= 0.03118
Epoch: 0013 train_loss= 1.39955 train_acc= 0.25733 val_loss= 1.38505 val_acc= 0.33929 time= 0.02950
Epoch: 0014 train_loss= 1.44027 train_acc= 0.28013 val_loss= 1.38273 val_acc= 0.33929 time= 0.05415
Epoch: 0015 train_loss= 1.40229 train_acc= 0.28664 val_loss= 1.38090 val_acc= 0.26786 time= 0.02885
Epoch: 0016 train_loss= 1.41927 train_acc= 0.30293 val_loss= 1.37930 val_acc= 0.28571 time= 0.02874
Epoch: 0017 train_loss= 1.39115 train_acc= 0.29316 val_loss= 1.37795 val_acc= 0.26786 time= 0.02111
Epoch: 0018 train_loss= 1.38552 train_acc= 0.30619 val_loss= 1.37694 val_acc= 0.26786 time= 0.01563
Epoch: 0019 train_loss= 1.41228 train_acc= 0.28664 val_loss= 1.37625 val_acc= 0.28571 time= 0.01563
Epoch: 0020 train_loss= 1.39831 train_acc= 0.27687 val_loss= 1.37583 val_acc= 0.28571 time= 0.03125
Epoch: 0021 train_loss= 1.40286 train_acc= 0.25733 val_loss= 1.37549 val_acc= 0.28571 time= 0.02547
Epoch: 0022 train_loss= 1.39232 train_acc= 0.28990 val_loss= 1.37529 val_acc= 0.28571 time= 0.02360
Epoch: 0023 train_loss= 1.40224 train_acc= 0.28990 val_loss= 1.37515 val_acc= 0.28571 time= 0.02627
Epoch: 0024 train_loss= 1.39325 train_acc= 0.28339 val_loss= 1.37510 val_acc= 0.28571 time= 0.02401
Epoch: 0025 train_loss= 1.39405 train_acc= 0.28339 val_loss= 1.37510 val_acc= 0.28571 time= 0.02200
Epoch: 0026 train_loss= 1.39927 train_acc= 0.25733 val_loss= 1.37515 val_acc= 0.28571 time= 0.02326
Epoch: 0027 train_loss= 1.38448 train_acc= 0.28664 val_loss= 1.37537 val_acc= 0.30357 time= 0.02401
Epoch: 0028 train_loss= 1.40221 train_acc= 0.28339 val_loss= 1.37573 val_acc= 0.30357 time= 0.02200
Early stopping...
Optimization Finished!
Test set results: cost= 1.38108 accuracy= 0.33628 time= 0.01400 
