Epoch: 0001 train_loss= 0.70104 train_acc= 0.48701 val_loss= 0.69815 val_acc= 0.55738 time= 0.80130
Epoch: 0002 train_loss= 0.69773 train_acc= 0.57013 val_loss= 0.69605 val_acc= 0.54098 time= 0.01200
Epoch: 0003 train_loss= 0.69523 train_acc= 0.55974 val_loss= 0.69465 val_acc= 0.54098 time= 0.01000
Epoch: 0004 train_loss= 0.69334 train_acc= 0.54675 val_loss= 0.69374 val_acc= 0.55738 time= 0.01200
Epoch: 0005 train_loss= 0.69209 train_acc= 0.55455 val_loss= 0.69315 val_acc= 0.55738 time= 0.00875
Epoch: 0006 train_loss= 0.69098 train_acc= 0.58312 val_loss= 0.69280 val_acc= 0.59016 time= 0.00000
Epoch: 0007 train_loss= 0.69032 train_acc= 0.58701 val_loss= 0.69268 val_acc= 0.57377 time= 0.01562
Epoch: 0008 train_loss= 0.68941 train_acc= 0.62468 val_loss= 0.69265 val_acc= 0.57377 time= 0.00000
Epoch: 0009 train_loss= 0.68883 train_acc= 0.60130 val_loss= 0.69264 val_acc= 0.59016 time= 0.02642
Epoch: 0010 train_loss= 0.68812 train_acc= 0.62597 val_loss= 0.69258 val_acc= 0.57377 time= 0.01200
Epoch: 0011 train_loss= 0.68776 train_acc= 0.59351 val_loss= 0.69245 val_acc= 0.57377 time= 0.01100
Epoch: 0012 train_loss= 0.68704 train_acc= 0.65584 val_loss= 0.69233 val_acc= 0.57377 time= 0.01400
Epoch: 0013 train_loss= 0.68511 train_acc= 0.61818 val_loss= 0.69213 val_acc= 0.57377 time= 0.01300
Epoch: 0014 train_loss= 0.68512 train_acc= 0.65844 val_loss= 0.69190 val_acc= 0.57377 time= 0.01000
Epoch: 0015 train_loss= 0.68556 train_acc= 0.63117 val_loss= 0.69162 val_acc= 0.57377 time= 0.01200
Epoch: 0016 train_loss= 0.68367 train_acc= 0.62727 val_loss= 0.69129 val_acc= 0.59016 time= 0.01200
Epoch: 0017 train_loss= 0.68366 train_acc= 0.65455 val_loss= 0.69097 val_acc= 0.59016 time= 0.01100
Epoch: 0018 train_loss= 0.68298 train_acc= 0.64416 val_loss= 0.69067 val_acc= 0.60656 time= 0.01300
Epoch: 0019 train_loss= 0.68076 train_acc= 0.63896 val_loss= 0.69036 val_acc= 0.60656 time= 0.01100
Epoch: 0020 train_loss= 0.68069 train_acc= 0.64156 val_loss= 0.69015 val_acc= 0.60656 time= 0.01100
Epoch: 0021 train_loss= 0.67895 train_acc= 0.68701 val_loss= 0.68997 val_acc= 0.60656 time= 0.01216
Epoch: 0022 train_loss= 0.67893 train_acc= 0.71169 val_loss= 0.68989 val_acc= 0.60656 time= 0.01100
Epoch: 0023 train_loss= 0.67897 train_acc= 0.68571 val_loss= 0.68989 val_acc= 0.59016 time= 0.01200
Epoch: 0024 train_loss= 0.67647 train_acc= 0.64545 val_loss= 0.68972 val_acc= 0.59016 time= 0.01000
Epoch: 0025 train_loss= 0.67788 train_acc= 0.64416 val_loss= 0.68955 val_acc= 0.59016 time= 0.01200
Epoch: 0026 train_loss= 0.67468 train_acc= 0.64416 val_loss= 0.68933 val_acc= 0.59016 time= 0.01600
Epoch: 0027 train_loss= 0.67429 train_acc= 0.66104 val_loss= 0.68901 val_acc= 0.60656 time= 0.01700
Epoch: 0028 train_loss= 0.67400 train_acc= 0.66234 val_loss= 0.68881 val_acc= 0.60656 time= 0.01100
Epoch: 0029 train_loss= 0.67101 train_acc= 0.67143 val_loss= 0.68860 val_acc= 0.60656 time= 0.01100
Epoch: 0030 train_loss= 0.67336 train_acc= 0.65714 val_loss= 0.68819 val_acc= 0.62295 time= 0.01200
Epoch: 0031 train_loss= 0.67302 train_acc= 0.68442 val_loss= 0.68798 val_acc= 0.62295 time= 0.01000
Epoch: 0032 train_loss= 0.67113 train_acc= 0.65974 val_loss= 0.68760 val_acc= 0.62295 time= 0.01200
Epoch: 0033 train_loss= 0.66950 train_acc= 0.68701 val_loss= 0.68730 val_acc= 0.62295 time= 0.01100
Epoch: 0034 train_loss= 0.66752 train_acc= 0.69481 val_loss= 0.68723 val_acc= 0.62295 time= 0.01131
Epoch: 0035 train_loss= 0.66970 train_acc= 0.69481 val_loss= 0.68727 val_acc= 0.60656 time= 0.01000
Epoch: 0036 train_loss= 0.66624 train_acc= 0.64805 val_loss= 0.68697 val_acc= 0.60656 time= 0.01010
Epoch: 0037 train_loss= 0.66756 train_acc= 0.68052 val_loss= 0.68677 val_acc= 0.62295 time= 0.00000
Epoch: 0038 train_loss= 0.66575 train_acc= 0.68831 val_loss= 0.68676 val_acc= 0.60656 time= 0.01908
Epoch: 0039 train_loss= 0.66583 train_acc= 0.69091 val_loss= 0.68629 val_acc= 0.62295 time= 0.01697
Epoch: 0040 train_loss= 0.66636 train_acc= 0.70390 val_loss= 0.68620 val_acc= 0.62295 time= 0.00508
Epoch: 0041 train_loss= 0.66165 train_acc= 0.68182 val_loss= 0.68629 val_acc= 0.60656 time= 0.01563
Epoch: 0042 train_loss= 0.65939 train_acc= 0.69481 val_loss= 0.68591 val_acc= 0.62295 time= 0.00000
Epoch: 0043 train_loss= 0.66001 train_acc= 0.67922 val_loss= 0.68485 val_acc= 0.62295 time= 0.02316
Epoch: 0044 train_loss= 0.65445 train_acc= 0.67662 val_loss= 0.68366 val_acc= 0.68852 time= 0.01000
Epoch: 0045 train_loss= 0.66243 train_acc= 0.69221 val_loss= 0.68337 val_acc= 0.70492 time= 0.00905
Epoch: 0046 train_loss= 0.66026 train_acc= 0.70000 val_loss= 0.68321 val_acc= 0.70492 time= 0.01112
Epoch: 0047 train_loss= 0.65443 train_acc= 0.70779 val_loss= 0.68307 val_acc= 0.72131 time= 0.01107
Epoch: 0048 train_loss= 0.65762 train_acc= 0.69870 val_loss= 0.68293 val_acc= 0.72131 time= 0.00914
Epoch: 0049 train_loss= 0.65820 train_acc= 0.68701 val_loss= 0.68322 val_acc= 0.68852 time= 0.01011
Epoch: 0050 train_loss= 0.65110 train_acc= 0.68961 val_loss= 0.68455 val_acc= 0.63934 time= 0.01012
Early stopping...
Optimization Finished!
Test set results: cost= 0.68422 accuracy= 0.60656 time= 0.00300 
