Epoch: 0001 train_loss= 2.33239 train_acc= 0.49091 val_loss= 1.88724 val_acc= 0.49180 time= 0.27906
Epoch: 0002 train_loss= 2.32556 train_acc= 0.50303 val_loss= 4.17459 val_acc= 0.52459 time= 0.02101
Epoch: 0003 train_loss= 2.56836 train_acc= 0.53939 val_loss= 3.91404 val_acc= 0.52459 time= 0.02301
Epoch: 0004 train_loss= 1.49490 train_acc= 0.52121 val_loss= 2.46186 val_acc= 0.50820 time= 0.02201
Epoch: 0005 train_loss= 2.22521 train_acc= 0.49697 val_loss= 0.82918 val_acc= 0.55738 time= 0.02000
Epoch: 0006 train_loss= 1.08867 train_acc= 0.53939 val_loss= 1.60714 val_acc= 0.47541 time= 0.02101
Epoch: 0007 train_loss= 2.41129 train_acc= 0.50909 val_loss= 2.29777 val_acc= 0.47541 time= 0.02200
Epoch: 0008 train_loss= 1.22949 train_acc= 0.47879 val_loss= 3.02667 val_acc= 0.47541 time= 0.02000
Epoch: 0009 train_loss= 1.01393 train_acc= 0.49697 val_loss= 3.51097 val_acc= 0.47541 time= 0.02100
Epoch: 0010 train_loss= 2.84353 train_acc= 0.52424 val_loss= 3.35328 val_acc= 0.47541 time= 0.02200
Epoch: 0011 train_loss= 2.10411 train_acc= 0.49091 val_loss= 2.93453 val_acc= 0.47541 time= 0.02000
Epoch: 0012 train_loss= 3.25911 train_acc= 0.51212 val_loss= 2.25538 val_acc= 0.47541 time= 0.02200
Epoch: 0013 train_loss= 1.54199 train_acc= 0.49394 val_loss= 1.52111 val_acc= 0.47541 time= 0.02000
Epoch: 0014 train_loss= 1.05836 train_acc= 0.53030 val_loss= 1.02949 val_acc= 0.47541 time= 0.02201
Epoch: 0015 train_loss= 0.79198 train_acc= 0.52121 val_loss= 0.70700 val_acc= 0.47541 time= 0.02000
Epoch: 0016 train_loss= 0.99296 train_acc= 0.47576 val_loss= 0.70361 val_acc= 0.47541 time= 0.02300
Epoch: 0017 train_loss= 1.57678 train_acc= 0.48788 val_loss= 0.70290 val_acc= 0.45902 time= 0.02501
Epoch: 0018 train_loss= 0.83553 train_acc= 0.49697 val_loss= 0.70237 val_acc= 0.45902 time= 0.02100
Epoch: 0019 train_loss= 1.08557 train_acc= 0.51212 val_loss= 0.70197 val_acc= 0.45902 time= 0.02101
Epoch: 0020 train_loss= 0.72661 train_acc= 0.45152 val_loss= 0.70156 val_acc= 0.45902 time= 0.02100
Epoch: 0021 train_loss= 0.71673 train_acc= 0.55758 val_loss= 0.70124 val_acc= 0.45902 time= 0.02100
Epoch: 0022 train_loss= 0.70930 train_acc= 0.53030 val_loss= 0.70098 val_acc= 0.45902 time= 0.02200
Epoch: 0023 train_loss= 1.21006 train_acc= 0.50606 val_loss= 0.70065 val_acc= 0.45902 time= 0.02201
Epoch: 0024 train_loss= 0.71468 train_acc= 0.48485 val_loss= 0.70032 val_acc= 0.45902 time= 0.02135
Epoch: 0025 train_loss= 0.70426 train_acc= 0.46061 val_loss= 0.69998 val_acc= 0.49180 time= 0.01562
Epoch: 0026 train_loss= 0.72243 train_acc= 0.47879 val_loss= 0.69965 val_acc= 0.49180 time= 0.01563
Epoch: 0027 train_loss= 0.70909 train_acc= 0.50909 val_loss= 0.69937 val_acc= 0.49180 time= 0.01563
Epoch: 0028 train_loss= 0.76962 train_acc= 0.51515 val_loss= 0.69914 val_acc= 0.49180 time= 0.03125
Epoch: 0029 train_loss= 1.35394 train_acc= 0.52727 val_loss= 0.69900 val_acc= 0.49180 time= 0.01563
Epoch: 0030 train_loss= 0.72142 train_acc= 0.52424 val_loss= 0.69891 val_acc= 0.47541 time= 0.03125
Epoch: 0031 train_loss= 0.70829 train_acc= 0.49394 val_loss= 0.69880 val_acc= 0.45902 time= 0.01562
Epoch: 0032 train_loss= 0.71099 train_acc= 0.52424 val_loss= 0.69866 val_acc= 0.45902 time= 0.03125
Epoch: 0033 train_loss= 0.70210 train_acc= 0.52121 val_loss= 0.69850 val_acc= 0.45902 time= 0.01563
Epoch: 0034 train_loss= 0.70187 train_acc= 0.50000 val_loss= 0.69839 val_acc= 0.45902 time= 0.01563
Epoch: 0035 train_loss= 0.72354 train_acc= 0.53030 val_loss= 0.69833 val_acc= 0.45902 time= 0.03125
Epoch: 0036 train_loss= 0.70984 train_acc= 0.49394 val_loss= 0.69827 val_acc= 0.45902 time= 0.01563
Epoch: 0037 train_loss= 0.70279 train_acc= 0.48788 val_loss= 0.69823 val_acc= 0.45902 time= 0.01563
Epoch: 0038 train_loss= 0.71149 train_acc= 0.50303 val_loss= 0.69823 val_acc= 0.45902 time= 0.03125
Epoch: 0039 train_loss= 0.71077 train_acc= 0.52727 val_loss= 0.69827 val_acc= 0.45902 time= 0.01563
Epoch: 0040 train_loss= 0.69725 train_acc= 0.53333 val_loss= 0.69833 val_acc= 0.47541 time= 0.01563
Epoch: 0041 train_loss= 0.70317 train_acc= 0.50909 val_loss= 0.69841 val_acc= 0.47541 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 0.70456 accuracy= 0.44262 time= 0.00000 
