Epoch: 0001 train_loss= 2.11483 train_acc= 0.12075 val_loss= 2.11193 val_acc= 0.06897 time= 0.38309
Epoch: 0002 train_loss= 2.11385 train_acc= 0.16226 val_loss= 2.10834 val_acc= 0.06897 time= 0.00800
Epoch: 0003 train_loss= 2.08931 train_acc= 0.13962 val_loss= 2.10615 val_acc= 0.10345 time= 0.00800
Epoch: 0004 train_loss= 2.08854 train_acc= 0.11698 val_loss= 2.10415 val_acc= 0.10345 time= 0.00800
Epoch: 0005 train_loss= 2.08784 train_acc= 0.13585 val_loss= 2.10222 val_acc= 0.13793 time= 0.00800
Epoch: 0006 train_loss= 2.07797 train_acc= 0.15094 val_loss= 2.10130 val_acc= 0.10345 time= 0.00900
Epoch: 0007 train_loss= 2.06910 train_acc= 0.15472 val_loss= 2.10062 val_acc= 0.10345 time= 0.00900
Epoch: 0008 train_loss= 2.05294 train_acc= 0.18491 val_loss= 2.10016 val_acc= 0.06897 time= 0.01000
Epoch: 0009 train_loss= 2.06375 train_acc= 0.15849 val_loss= 2.09955 val_acc= 0.06897 time= 0.00900
Epoch: 0010 train_loss= 2.05678 train_acc= 0.18491 val_loss= 2.09917 val_acc= 0.06897 time= 0.00800
Epoch: 0011 train_loss= 2.05911 train_acc= 0.18113 val_loss= 2.09899 val_acc= 0.10345 time= 0.01000
Epoch: 0012 train_loss= 2.04757 train_acc= 0.18491 val_loss= 2.09879 val_acc= 0.13793 time= 0.00900
Epoch: 0013 train_loss= 2.05333 train_acc= 0.19623 val_loss= 2.09893 val_acc= 0.13793 time= 0.00700
Epoch: 0014 train_loss= 2.04251 train_acc= 0.18491 val_loss= 2.09908 val_acc= 0.10345 time= 0.00900
Epoch: 0015 train_loss= 2.04607 train_acc= 0.15849 val_loss= 2.09840 val_acc= 0.10345 time= 0.00800
Epoch: 0016 train_loss= 2.04478 train_acc= 0.17736 val_loss= 2.09761 val_acc= 0.10345 time= 0.00900
Epoch: 0017 train_loss= 2.03924 train_acc= 0.18113 val_loss= 2.09680 val_acc= 0.10345 time= 0.00800
Epoch: 0018 train_loss= 2.04091 train_acc= 0.16981 val_loss= 2.09568 val_acc= 0.10345 time= 0.00700
Epoch: 0019 train_loss= 2.05235 train_acc= 0.14340 val_loss= 2.09389 val_acc= 0.06897 time= 0.00800
Epoch: 0020 train_loss= 2.03926 train_acc= 0.17358 val_loss= 2.09250 val_acc= 0.10345 time= 0.00700
Epoch: 0021 train_loss= 2.02890 train_acc= 0.20000 val_loss= 2.09146 val_acc= 0.10345 time= 0.00700
Epoch: 0022 train_loss= 2.02931 train_acc= 0.19623 val_loss= 2.09061 val_acc= 0.10345 time= 0.00700
Epoch: 0023 train_loss= 2.03733 train_acc= 0.18491 val_loss= 2.09045 val_acc= 0.10345 time= 0.00700
Epoch: 0024 train_loss= 2.03196 train_acc= 0.18491 val_loss= 2.09020 val_acc= 0.13793 time= 0.00700
Epoch: 0025 train_loss= 2.02625 train_acc= 0.18113 val_loss= 2.09022 val_acc= 0.17241 time= 0.00800
Epoch: 0026 train_loss= 2.02658 train_acc= 0.21887 val_loss= 2.09051 val_acc= 0.17241 time= 0.00800
Epoch: 0027 train_loss= 2.03234 train_acc= 0.20377 val_loss= 2.09070 val_acc= 0.17241 time= 0.00800
Epoch: 0028 train_loss= 2.02335 train_acc= 0.19245 val_loss= 2.09079 val_acc= 0.13793 time= 0.00800
Epoch: 0029 train_loss= 2.02648 train_acc= 0.19245 val_loss= 2.09137 val_acc= 0.13793 time= 0.00800
Early stopping...
Optimization Finished!
Test set results: cost= 2.08920 accuracy= 0.10169 time= 0.00300 
