Epoch: 0001 train_loss= 0.70116 train_acc= 0.53377 val_loss= 0.69797 val_acc= 0.47541 time= 0.84463
Epoch: 0002 train_loss= 0.69777 train_acc= 0.53247 val_loss= 0.69563 val_acc= 0.47541 time= 0.01314
Epoch: 0003 train_loss= 0.69488 train_acc= 0.52987 val_loss= 0.69396 val_acc= 0.47541 time= 0.01308
Epoch: 0004 train_loss= 0.69235 train_acc= 0.52727 val_loss= 0.69284 val_acc= 0.47541 time= 0.01200
Epoch: 0005 train_loss= 0.69068 train_acc= 0.52857 val_loss= 0.69208 val_acc= 0.47541 time= 0.01300
Epoch: 0006 train_loss= 0.69006 train_acc= 0.53117 val_loss= 0.69153 val_acc= 0.49180 time= 0.01300
Epoch: 0007 train_loss= 0.68892 train_acc= 0.53506 val_loss= 0.69110 val_acc= 0.49180 time= 0.01598
Epoch: 0008 train_loss= 0.68775 train_acc= 0.53896 val_loss= 0.69077 val_acc= 0.49180 time= 0.01100
Epoch: 0009 train_loss= 0.68672 train_acc= 0.53896 val_loss= 0.69051 val_acc= 0.49180 time= 0.01300
Epoch: 0010 train_loss= 0.68741 train_acc= 0.54805 val_loss= 0.69024 val_acc= 0.49180 time= 0.01200
Epoch: 0011 train_loss= 0.68651 train_acc= 0.53896 val_loss= 0.68989 val_acc= 0.49180 time= 0.01312
Epoch: 0012 train_loss= 0.68593 train_acc= 0.55065 val_loss= 0.68950 val_acc= 0.49180 time= 0.01309
Epoch: 0013 train_loss= 0.68408 train_acc= 0.54935 val_loss= 0.68910 val_acc= 0.50820 time= 0.01513
Epoch: 0014 train_loss= 0.68424 train_acc= 0.55455 val_loss= 0.68865 val_acc= 0.50820 time= 0.01298
Epoch: 0015 train_loss= 0.68352 train_acc= 0.55455 val_loss= 0.68815 val_acc= 0.50820 time= 0.01700
Epoch: 0016 train_loss= 0.68312 train_acc= 0.55714 val_loss= 0.68762 val_acc= 0.50820 time= 0.01300
Epoch: 0017 train_loss= 0.68018 train_acc= 0.57013 val_loss= 0.68712 val_acc= 0.50820 time= 0.01500
Epoch: 0018 train_loss= 0.68116 train_acc= 0.55844 val_loss= 0.68659 val_acc= 0.50820 time= 0.01200
Epoch: 0019 train_loss= 0.68055 train_acc= 0.55714 val_loss= 0.68606 val_acc= 0.50820 time= 0.01100
Epoch: 0020 train_loss= 0.67890 train_acc= 0.57273 val_loss= 0.68553 val_acc= 0.50820 time= 0.01100
Epoch: 0021 train_loss= 0.67696 train_acc= 0.58442 val_loss= 0.68508 val_acc= 0.52459 time= 0.01000
Epoch: 0022 train_loss= 0.67717 train_acc= 0.58312 val_loss= 0.68466 val_acc= 0.52459 time= 0.01121
Epoch: 0023 train_loss= 0.67758 train_acc= 0.57273 val_loss= 0.68425 val_acc= 0.54098 time= 0.01100
Epoch: 0024 train_loss= 0.67649 train_acc= 0.59870 val_loss= 0.68392 val_acc= 0.54098 time= 0.01000
Epoch: 0025 train_loss= 0.67497 train_acc= 0.59351 val_loss= 0.68354 val_acc= 0.54098 time= 0.00900
Epoch: 0026 train_loss= 0.67404 train_acc= 0.57662 val_loss= 0.68306 val_acc= 0.55738 time= 0.01000
Epoch: 0027 train_loss= 0.67282 train_acc= 0.63506 val_loss= 0.68262 val_acc= 0.55738 time= 0.01000
Epoch: 0028 train_loss= 0.67366 train_acc= 0.62338 val_loss= 0.68221 val_acc= 0.55738 time= 0.01100
Epoch: 0029 train_loss= 0.67389 train_acc= 0.57922 val_loss= 0.68156 val_acc= 0.55738 time= 0.01000
Epoch: 0030 train_loss= 0.67121 train_acc= 0.61169 val_loss= 0.68094 val_acc= 0.55738 time= 0.01000
Epoch: 0031 train_loss= 0.66979 train_acc= 0.61558 val_loss= 0.68029 val_acc= 0.59016 time= 0.00300
Epoch: 0032 train_loss= 0.67209 train_acc= 0.67273 val_loss= 0.67987 val_acc= 0.59016 time= 0.00000
Epoch: 0033 train_loss= 0.66850 train_acc= 0.64805 val_loss= 0.67955 val_acc= 0.55738 time= 0.01563
Epoch: 0034 train_loss= 0.66841 train_acc= 0.65714 val_loss= 0.67933 val_acc= 0.55738 time= 0.01563
Epoch: 0035 train_loss= 0.66938 train_acc= 0.65714 val_loss= 0.67924 val_acc= 0.55738 time= 0.01563
Epoch: 0036 train_loss= 0.66928 train_acc= 0.64545 val_loss= 0.67906 val_acc= 0.55738 time= 0.00000
Epoch: 0037 train_loss= 0.66703 train_acc= 0.60779 val_loss= 0.67841 val_acc= 0.55738 time= 0.01563
Epoch: 0038 train_loss= 0.66380 train_acc= 0.65974 val_loss= 0.67761 val_acc= 0.55738 time= 0.01563
Epoch: 0039 train_loss= 0.66278 train_acc= 0.65065 val_loss= 0.67675 val_acc= 0.57377 time= 0.00000
Epoch: 0040 train_loss= 0.66515 train_acc= 0.66494 val_loss= 0.67586 val_acc= 0.60656 time= 0.01563
Epoch: 0041 train_loss= 0.66164 train_acc= 0.65714 val_loss= 0.67508 val_acc= 0.63934 time= 0.00000
Epoch: 0042 train_loss= 0.66412 train_acc= 0.64805 val_loss= 0.67433 val_acc= 0.65574 time= 0.02371
Epoch: 0043 train_loss= 0.66480 train_acc= 0.66883 val_loss= 0.67405 val_acc= 0.63934 time= 0.01000
Epoch: 0044 train_loss= 0.66272 train_acc= 0.66104 val_loss= 0.67395 val_acc= 0.60656 time= 0.01100
Epoch: 0045 train_loss= 0.65752 train_acc= 0.66234 val_loss= 0.67379 val_acc= 0.57377 time= 0.01200
Epoch: 0046 train_loss= 0.65790 train_acc= 0.69610 val_loss= 0.67437 val_acc= 0.55738 time= 0.01100
Epoch: 0047 train_loss= 0.66228 train_acc= 0.62468 val_loss= 0.67405 val_acc= 0.55738 time= 0.00900
Epoch: 0048 train_loss= 0.65722 train_acc= 0.64156 val_loss= 0.67271 val_acc= 0.57377 time= 0.01100
Epoch: 0049 train_loss= 0.66048 train_acc= 0.63117 val_loss= 0.67064 val_acc= 0.63934 time= 0.01200
Epoch: 0050 train_loss= 0.65184 train_acc= 0.68961 val_loss= 0.66910 val_acc= 0.67213 time= 0.01000
Epoch: 0051 train_loss= 0.65527 train_acc= 0.69870 val_loss= 0.66836 val_acc= 0.67213 time= 0.01000
Epoch: 0052 train_loss= 0.65217 train_acc= 0.72727 val_loss= 0.66778 val_acc= 0.67213 time= 0.00900
Epoch: 0053 train_loss= 0.65405 train_acc= 0.65974 val_loss= 0.66714 val_acc= 0.68852 time= 0.01000
Epoch: 0054 train_loss= 0.65156 train_acc= 0.71039 val_loss= 0.66652 val_acc= 0.68852 time= 0.01000
Epoch: 0055 train_loss= 0.65682 train_acc= 0.66883 val_loss= 0.66613 val_acc= 0.68852 time= 0.01000
Epoch: 0056 train_loss= 0.65340 train_acc= 0.70390 val_loss= 0.66592 val_acc= 0.65574 time= 0.01000
Epoch: 0057 train_loss= 0.65487 train_acc= 0.68831 val_loss= 0.66581 val_acc= 0.65574 time= 0.01007
Epoch: 0058 train_loss= 0.64686 train_acc= 0.69610 val_loss= 0.66610 val_acc= 0.63934 time= 0.00915
Epoch: 0059 train_loss= 0.65266 train_acc= 0.67013 val_loss= 0.66601 val_acc= 0.62295 time= 0.00900
Epoch: 0060 train_loss= 0.65269 train_acc= 0.66364 val_loss= 0.66435 val_acc= 0.65574 time= 0.01100
Epoch: 0061 train_loss= 0.65296 train_acc= 0.70519 val_loss= 0.66288 val_acc= 0.65574 time= 0.01200
Epoch: 0062 train_loss= 0.64475 train_acc= 0.69221 val_loss= 0.66246 val_acc= 0.65574 time= 0.00900
Epoch: 0063 train_loss= 0.64439 train_acc= 0.69481 val_loss= 0.66136 val_acc= 0.67213 time= 0.01100
Epoch: 0064 train_loss= 0.64553 train_acc= 0.71299 val_loss= 0.66086 val_acc= 0.67213 time= 0.01000
Epoch: 0065 train_loss= 0.64343 train_acc= 0.67792 val_loss= 0.66202 val_acc= 0.63934 time= 0.01200
Epoch: 0066 train_loss= 0.64630 train_acc= 0.71039 val_loss= 0.66538 val_acc= 0.59016 time= 0.00900
Early stopping...
Optimization Finished!
Test set results: cost= 0.63131 accuracy= 0.69672 time= 0.00500 
