Epoch: 0001 train_loss= 0.70099 train_acc= 0.52182 val_loss= 0.69771 val_acc= 0.72131 time= 0.45573
Epoch: 0002 train_loss= 0.69772 train_acc= 0.59273 val_loss= 0.69492 val_acc= 0.55738 time= 0.00900
Epoch: 0003 train_loss= 0.69522 train_acc= 0.59091 val_loss= 0.69266 val_acc= 0.54098 time= 0.00900
Epoch: 0004 train_loss= 0.69351 train_acc= 0.57636 val_loss= 0.69090 val_acc= 0.54098 time= 0.01100
Epoch: 0005 train_loss= 0.69201 train_acc= 0.56364 val_loss= 0.68948 val_acc= 0.57377 time= 0.00706
Epoch: 0006 train_loss= 0.69040 train_acc= 0.57091 val_loss= 0.68840 val_acc= 0.63934 time= 0.00000
Epoch: 0007 train_loss= 0.68964 train_acc= 0.63818 val_loss= 0.68747 val_acc= 0.67213 time= 0.01563
Epoch: 0008 train_loss= 0.68876 train_acc= 0.60909 val_loss= 0.68665 val_acc= 0.68852 time= 0.00000
Epoch: 0009 train_loss= 0.68822 train_acc= 0.65091 val_loss= 0.68584 val_acc= 0.68852 time= 0.01563
Epoch: 0010 train_loss= 0.68682 train_acc= 0.68727 val_loss= 0.68495 val_acc= 0.68852 time= 0.01563
Epoch: 0011 train_loss= 0.68687 train_acc= 0.65091 val_loss= 0.68404 val_acc= 0.68852 time= 0.00000
Epoch: 0012 train_loss= 0.68602 train_acc= 0.64364 val_loss= 0.68308 val_acc= 0.68852 time= 0.01563
Epoch: 0013 train_loss= 0.68444 train_acc= 0.65273 val_loss= 0.68211 val_acc= 0.68852 time= 0.00000
Epoch: 0014 train_loss= 0.68203 train_acc= 0.65273 val_loss= 0.68109 val_acc= 0.68852 time= 0.01563
Epoch: 0015 train_loss= 0.68173 train_acc= 0.66182 val_loss= 0.68004 val_acc= 0.70492 time= 0.01563
Epoch: 0016 train_loss= 0.68233 train_acc= 0.70364 val_loss= 0.67899 val_acc= 0.72131 time= 0.00000
Epoch: 0017 train_loss= 0.68244 train_acc= 0.66000 val_loss= 0.67794 val_acc= 0.72131 time= 0.01563
Epoch: 0018 train_loss= 0.68105 train_acc= 0.64545 val_loss= 0.67692 val_acc= 0.78689 time= 0.00000
Epoch: 0019 train_loss= 0.67899 train_acc= 0.68364 val_loss= 0.67593 val_acc= 0.77049 time= 0.01563
Epoch: 0020 train_loss= 0.67873 train_acc= 0.68909 val_loss= 0.67496 val_acc= 0.73770 time= 0.01563
Epoch: 0021 train_loss= 0.67683 train_acc= 0.73455 val_loss= 0.67399 val_acc= 0.75410 time= 0.00000
Epoch: 0022 train_loss= 0.67664 train_acc= 0.69818 val_loss= 0.67298 val_acc= 0.75410 time= 0.01563
Epoch: 0023 train_loss= 0.67529 train_acc= 0.68000 val_loss= 0.67189 val_acc= 0.73770 time= 0.00000
Epoch: 0024 train_loss= 0.67468 train_acc= 0.72182 val_loss= 0.67085 val_acc= 0.73770 time= 0.01563
Epoch: 0025 train_loss= 0.67328 train_acc= 0.67818 val_loss= 0.66975 val_acc= 0.77049 time= 0.01563
Epoch: 0026 train_loss= 0.67519 train_acc= 0.63091 val_loss= 0.66877 val_acc= 0.75410 time= 0.00000
Epoch: 0027 train_loss= 0.67044 train_acc= 0.69091 val_loss= 0.66777 val_acc= 0.77049 time= 0.01562
Epoch: 0028 train_loss= 0.67039 train_acc= 0.70545 val_loss= 0.66676 val_acc= 0.75410 time= 0.00000
Epoch: 0029 train_loss= 0.67022 train_acc= 0.67636 val_loss= 0.66577 val_acc= 0.72131 time= 0.01563
Epoch: 0030 train_loss= 0.67367 train_acc= 0.66364 val_loss= 0.66480 val_acc= 0.77049 time= 0.01563
Epoch: 0031 train_loss= 0.67101 train_acc= 0.68909 val_loss= 0.66395 val_acc= 0.73770 time= 0.00000
Epoch: 0032 train_loss= 0.66915 train_acc= 0.69455 val_loss= 0.66315 val_acc= 0.70492 time= 0.01563
Epoch: 0033 train_loss= 0.66814 train_acc= 0.65091 val_loss= 0.66219 val_acc= 0.73770 time= 0.01563
Epoch: 0034 train_loss= 0.66787 train_acc= 0.69273 val_loss= 0.66127 val_acc= 0.75410 time= 0.00000
Epoch: 0035 train_loss= 0.66681 train_acc= 0.65636 val_loss= 0.66036 val_acc= 0.73770 time= 0.01562
Epoch: 0036 train_loss= 0.66519 train_acc= 0.70182 val_loss= 0.65948 val_acc= 0.73770 time= 0.01563
Epoch: 0037 train_loss= 0.66451 train_acc= 0.66545 val_loss= 0.65858 val_acc= 0.73770 time= 0.00000
Epoch: 0038 train_loss= 0.66090 train_acc= 0.70182 val_loss= 0.65781 val_acc= 0.73770 time= 0.02571
Epoch: 0039 train_loss= 0.66060 train_acc= 0.68182 val_loss= 0.65694 val_acc= 0.73770 time= 0.01200
Epoch: 0040 train_loss= 0.66212 train_acc= 0.66364 val_loss= 0.65613 val_acc= 0.73770 time= 0.00900
Epoch: 0041 train_loss= 0.65770 train_acc= 0.69818 val_loss= 0.65537 val_acc= 0.73770 time= 0.00900
Epoch: 0042 train_loss= 0.66240 train_acc= 0.70000 val_loss= 0.65454 val_acc= 0.72131 time= 0.01007
Epoch: 0043 train_loss= 0.65711 train_acc= 0.70727 val_loss= 0.65379 val_acc= 0.72131 time= 0.00000
Epoch: 0044 train_loss= 0.65850 train_acc= 0.65636 val_loss= 0.65310 val_acc= 0.72131 time= 0.01563
Epoch: 0045 train_loss= 0.66068 train_acc= 0.67091 val_loss= 0.65253 val_acc= 0.72131 time= 0.01335
Epoch: 0046 train_loss= 0.65791 train_acc= 0.66182 val_loss= 0.65183 val_acc= 0.73770 time= 0.01000
Epoch: 0047 train_loss= 0.65401 train_acc= 0.70727 val_loss= 0.65124 val_acc= 0.73770 time= 0.00900
Epoch: 0048 train_loss= 0.65493 train_acc= 0.68364 val_loss= 0.65077 val_acc= 0.73770 time= 0.00900
Epoch: 0049 train_loss= 0.65048 train_acc= 0.72545 val_loss= 0.65094 val_acc= 0.70492 time= 0.00800
Epoch: 0050 train_loss= 0.65514 train_acc= 0.68182 val_loss= 0.65247 val_acc= 0.68852 time= 0.00115
Epoch: 0051 train_loss= 0.65481 train_acc= 0.67818 val_loss= 0.65373 val_acc= 0.68852 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.65655 accuracy= 0.67213 time= 0.00000 
