Epoch: 0001 train_loss= 0.70103 train_acc= 0.49091 val_loss= 0.69850 val_acc= 0.48387 time= 0.86332
Epoch: 0002 train_loss= 0.69771 train_acc= 0.52727 val_loss= 0.69683 val_acc= 0.48387 time= 0.01300
Epoch: 0003 train_loss= 0.69473 train_acc= 0.52857 val_loss= 0.69592 val_acc= 0.50000 time= 0.01300
Epoch: 0004 train_loss= 0.69213 train_acc= 0.53117 val_loss= 0.69546 val_acc= 0.50000 time= 0.01200
Epoch: 0005 train_loss= 0.69110 train_acc= 0.52857 val_loss= 0.69519 val_acc= 0.50000 time= 0.01200
Epoch: 0006 train_loss= 0.69013 train_acc= 0.53117 val_loss= 0.69484 val_acc= 0.50000 time= 0.01200
Epoch: 0007 train_loss= 0.68875 train_acc= 0.53766 val_loss= 0.69437 val_acc= 0.50000 time= 0.01300
Epoch: 0008 train_loss= 0.68768 train_acc= 0.54675 val_loss= 0.69385 val_acc= 0.50000 time= 0.01200
Epoch: 0009 train_loss= 0.68602 train_acc= 0.54675 val_loss= 0.69316 val_acc= 0.51613 time= 0.01100
Epoch: 0010 train_loss= 0.68542 train_acc= 0.54805 val_loss= 0.69243 val_acc= 0.51613 time= 0.01200
Epoch: 0011 train_loss= 0.68487 train_acc= 0.54935 val_loss= 0.69158 val_acc= 0.51613 time= 0.01100
Epoch: 0012 train_loss= 0.68372 train_acc= 0.56753 val_loss= 0.69067 val_acc= 0.51613 time= 0.01200
Epoch: 0013 train_loss= 0.68445 train_acc= 0.56883 val_loss= 0.68990 val_acc= 0.51613 time= 0.01200
Epoch: 0014 train_loss= 0.68208 train_acc= 0.59221 val_loss= 0.68937 val_acc= 0.51613 time= 0.01200
Epoch: 0015 train_loss= 0.68323 train_acc= 0.59610 val_loss= 0.68909 val_acc= 0.51613 time= 0.01400
Epoch: 0016 train_loss= 0.67921 train_acc= 0.57143 val_loss= 0.68875 val_acc= 0.51613 time= 0.01400
Epoch: 0017 train_loss= 0.68106 train_acc= 0.58961 val_loss= 0.68857 val_acc= 0.51613 time= 0.01300
Epoch: 0018 train_loss= 0.67976 train_acc= 0.58961 val_loss= 0.68832 val_acc= 0.51613 time= 0.01200
Epoch: 0019 train_loss= 0.67788 train_acc= 0.59221 val_loss= 0.68789 val_acc= 0.53226 time= 0.01200
Epoch: 0020 train_loss= 0.67723 train_acc= 0.59740 val_loss= 0.68726 val_acc= 0.53226 time= 0.01200
Epoch: 0021 train_loss= 0.67603 train_acc= 0.61299 val_loss= 0.68657 val_acc= 0.53226 time= 0.01200
Epoch: 0022 train_loss= 0.67554 train_acc= 0.60779 val_loss= 0.68578 val_acc= 0.53226 time= 0.01200
Epoch: 0023 train_loss= 0.67501 train_acc= 0.61818 val_loss= 0.68499 val_acc= 0.53226 time= 0.01100
Epoch: 0024 train_loss= 0.67421 train_acc= 0.61169 val_loss= 0.68427 val_acc= 0.53226 time= 0.01100
Epoch: 0025 train_loss= 0.67391 train_acc= 0.62857 val_loss= 0.68382 val_acc= 0.53226 time= 0.01100
Epoch: 0026 train_loss= 0.67408 train_acc= 0.59481 val_loss= 0.68282 val_acc= 0.53226 time= 0.01200
Epoch: 0027 train_loss= 0.67201 train_acc= 0.61558 val_loss= 0.68167 val_acc= 0.51613 time= 0.01200
Epoch: 0028 train_loss= 0.67221 train_acc= 0.62468 val_loss= 0.68076 val_acc= 0.54839 time= 0.01200
Epoch: 0029 train_loss= 0.67207 train_acc= 0.64156 val_loss= 0.68005 val_acc= 0.54839 time= 0.01100
Epoch: 0030 train_loss= 0.67137 train_acc= 0.64026 val_loss= 0.67951 val_acc= 0.56452 time= 0.01100
Epoch: 0031 train_loss= 0.66801 train_acc= 0.66104 val_loss= 0.67913 val_acc= 0.54839 time= 0.01200
Epoch: 0032 train_loss= 0.66819 train_acc= 0.69610 val_loss= 0.67981 val_acc= 0.51613 time= 0.01100
Epoch: 0033 train_loss= 0.66728 train_acc= 0.68442 val_loss= 0.68097 val_acc= 0.53226 time= 0.01100
Epoch: 0034 train_loss= 0.66884 train_acc= 0.62078 val_loss= 0.68090 val_acc= 0.53226 time= 0.01100
Epoch: 0035 train_loss= 0.66721 train_acc= 0.58961 val_loss= 0.67838 val_acc= 0.53226 time= 0.01200
Epoch: 0036 train_loss= 0.66369 train_acc= 0.63896 val_loss= 0.67551 val_acc= 0.67742 time= 0.01100
Epoch: 0037 train_loss= 0.66826 train_acc= 0.62338 val_loss= 0.67274 val_acc= 0.74194 time= 0.01200
Epoch: 0038 train_loss= 0.66370 train_acc= 0.71558 val_loss= 0.67153 val_acc= 0.72581 time= 0.01200
Epoch: 0039 train_loss= 0.66563 train_acc= 0.68701 val_loss= 0.67098 val_acc= 0.75806 time= 0.01100
Epoch: 0040 train_loss= 0.66185 train_acc= 0.71039 val_loss= 0.67092 val_acc= 0.74194 time= 0.01100
Epoch: 0041 train_loss= 0.65910 train_acc= 0.71299 val_loss= 0.67205 val_acc= 0.70968 time= 0.01300
Epoch: 0042 train_loss= 0.66153 train_acc= 0.67662 val_loss= 0.67388 val_acc= 0.58065 time= 0.01200
Epoch: 0043 train_loss= 0.66043 train_acc= 0.65584 val_loss= 0.67445 val_acc= 0.56452 time= 0.01200
Epoch: 0044 train_loss= 0.66311 train_acc= 0.62468 val_loss= 0.67262 val_acc= 0.62903 time= 0.01100
Epoch: 0045 train_loss= 0.65654 train_acc= 0.71039 val_loss= 0.67225 val_acc= 0.62903 time= 0.01100
Epoch: 0046 train_loss= 0.65697 train_acc= 0.67273 val_loss= 0.67052 val_acc= 0.66129 time= 0.01200
Epoch: 0047 train_loss= 0.65502 train_acc= 0.66883 val_loss= 0.66854 val_acc= 0.70968 time= 0.01300
Epoch: 0048 train_loss= 0.65631 train_acc= 0.67273 val_loss= 0.66670 val_acc= 0.72581 time= 0.01300
Epoch: 0049 train_loss= 0.65256 train_acc= 0.71558 val_loss= 0.66622 val_acc= 0.72581 time= 0.01200
Epoch: 0050 train_loss= 0.65486 train_acc= 0.69221 val_loss= 0.66584 val_acc= 0.70968 time= 0.01200
Epoch: 0051 train_loss= 0.66034 train_acc= 0.67403 val_loss= 0.66665 val_acc= 0.70968 time= 0.01200
Epoch: 0052 train_loss= 0.65175 train_acc= 0.67532 val_loss= 0.66651 val_acc= 0.70968 time= 0.01100
Epoch: 0053 train_loss= 0.65578 train_acc= 0.66883 val_loss= 0.66490 val_acc= 0.72581 time= 0.01200
Epoch: 0054 train_loss= 0.65112 train_acc= 0.68312 val_loss= 0.66325 val_acc= 0.72581 time= 0.01300
Epoch: 0055 train_loss= 0.65650 train_acc= 0.69870 val_loss= 0.66211 val_acc= 0.72581 time= 0.01100
Epoch: 0056 train_loss= 0.65263 train_acc= 0.70519 val_loss= 0.66164 val_acc= 0.72581 time= 0.01100
Epoch: 0057 train_loss= 0.65100 train_acc= 0.71039 val_loss= 0.66262 val_acc= 0.72581 time= 0.01100
Epoch: 0058 train_loss= 0.65644 train_acc= 0.67273 val_loss= 0.66337 val_acc= 0.70968 time= 0.01300
Epoch: 0059 train_loss= 0.65104 train_acc= 0.66883 val_loss= 0.66220 val_acc= 0.70968 time= 0.01100
Epoch: 0060 train_loss= 0.64922 train_acc= 0.70390 val_loss= 0.66193 val_acc= 0.70968 time= 0.01100
Epoch: 0061 train_loss= 0.64787 train_acc= 0.69610 val_loss= 0.66060 val_acc= 0.72581 time= 0.01300
Epoch: 0062 train_loss= 0.64539 train_acc= 0.68961 val_loss= 0.65797 val_acc= 0.74194 time= 0.01200
Epoch: 0063 train_loss= 0.65416 train_acc= 0.68442 val_loss= 0.65897 val_acc= 0.70968 time= 0.01200
Epoch: 0064 train_loss= 0.64316 train_acc= 0.68571 val_loss= 0.66136 val_acc= 0.70968 time= 0.01100
Epoch: 0065 train_loss= 0.64921 train_acc= 0.67532 val_loss= 0.66758 val_acc= 0.56452 time= 0.01300
Early stopping...
Optimization Finished!
Test set results: cost= 0.64174 accuracy= 0.66935 time= 0.00500 
