Epoch: 0001 train_loss= 0.70126 train_acc= 0.46061 val_loss= 0.69810 val_acc= 0.57377 time= 0.13903
Epoch: 0002 train_loss= 0.69786 train_acc= 0.60606 val_loss= 0.69589 val_acc= 0.59016 time= 0.01562
Epoch: 0003 train_loss= 0.69527 train_acc= 0.62424 val_loss= 0.69426 val_acc= 0.70492 time= 0.00000
Epoch: 0004 train_loss= 0.69363 train_acc= 0.65455 val_loss= 0.69317 val_acc= 0.70492 time= 0.01563
Epoch: 0005 train_loss= 0.69216 train_acc= 0.68788 val_loss= 0.69243 val_acc= 0.73770 time= 0.00000
Epoch: 0006 train_loss= 0.69096 train_acc= 0.71212 val_loss= 0.69198 val_acc= 0.72131 time= 0.01563
Epoch: 0007 train_loss= 0.68969 train_acc= 0.71515 val_loss= 0.69167 val_acc= 0.70492 time= 0.00000
Epoch: 0008 train_loss= 0.68941 train_acc= 0.71818 val_loss= 0.69152 val_acc= 0.70492 time= 0.01563
Epoch: 0009 train_loss= 0.68881 train_acc= 0.67879 val_loss= 0.69137 val_acc= 0.70492 time= 0.00000
Epoch: 0010 train_loss= 0.68768 train_acc= 0.67273 val_loss= 0.69125 val_acc= 0.70492 time= 0.01563
Epoch: 0011 train_loss= 0.68767 train_acc= 0.69394 val_loss= 0.69107 val_acc= 0.68852 time= 0.01563
Epoch: 0012 train_loss= 0.68692 train_acc= 0.65455 val_loss= 0.69078 val_acc= 0.67213 time= 0.00000
Epoch: 0013 train_loss= 0.68561 train_acc= 0.73030 val_loss= 0.69045 val_acc= 0.65574 time= 0.01563
Epoch: 0014 train_loss= 0.68396 train_acc= 0.68788 val_loss= 0.69005 val_acc= 0.67213 time= 0.00000
Epoch: 0015 train_loss= 0.68277 train_acc= 0.71212 val_loss= 0.68965 val_acc= 0.67213 time= 0.01563
Epoch: 0016 train_loss= 0.68267 train_acc= 0.71515 val_loss= 0.68932 val_acc= 0.65574 time= 0.00000
Epoch: 0017 train_loss= 0.68204 train_acc= 0.68788 val_loss= 0.68899 val_acc= 0.65574 time= 0.01563
Epoch: 0018 train_loss= 0.68099 train_acc= 0.67879 val_loss= 0.68872 val_acc= 0.67213 time= 0.01563
Epoch: 0019 train_loss= 0.68104 train_acc= 0.69091 val_loss= 0.68849 val_acc= 0.70492 time= 0.00000
Epoch: 0020 train_loss= 0.67966 train_acc= 0.68485 val_loss= 0.68823 val_acc= 0.70492 time= 0.01563
Epoch: 0021 train_loss= 0.67836 train_acc= 0.70909 val_loss= 0.68794 val_acc= 0.70492 time= 0.00000
Epoch: 0022 train_loss= 0.67874 train_acc= 0.70909 val_loss= 0.68773 val_acc= 0.70492 time= 0.01563
Epoch: 0023 train_loss= 0.67696 train_acc= 0.69697 val_loss= 0.68750 val_acc= 0.72131 time= 0.00000
Epoch: 0024 train_loss= 0.67584 train_acc= 0.70909 val_loss= 0.68723 val_acc= 0.72131 time= 0.01563
Epoch: 0025 train_loss= 0.67778 train_acc= 0.69091 val_loss= 0.68722 val_acc= 0.68852 time= 0.00000
Epoch: 0026 train_loss= 0.67412 train_acc= 0.72121 val_loss= 0.68699 val_acc= 0.68852 time= 0.01562
Epoch: 0027 train_loss= 0.67107 train_acc= 0.70606 val_loss= 0.68652 val_acc= 0.72131 time= 0.00000
Epoch: 0028 train_loss= 0.67073 train_acc= 0.69091 val_loss= 0.68621 val_acc= 0.72131 time= 0.01563
Epoch: 0029 train_loss= 0.67229 train_acc= 0.71818 val_loss= 0.68565 val_acc= 0.70492 time= 0.01562
Epoch: 0030 train_loss= 0.66702 train_acc= 0.69697 val_loss= 0.68501 val_acc= 0.67213 time= 0.00000
Epoch: 0031 train_loss= 0.66972 train_acc= 0.70909 val_loss= 0.68454 val_acc= 0.65574 time= 0.01563
Epoch: 0032 train_loss= 0.66856 train_acc= 0.71212 val_loss= 0.68411 val_acc= 0.65574 time= 0.00000
Epoch: 0033 train_loss= 0.66686 train_acc= 0.69697 val_loss= 0.68388 val_acc= 0.65574 time= 0.01563
Epoch: 0034 train_loss= 0.66378 train_acc= 0.70303 val_loss= 0.68358 val_acc= 0.65574 time= 0.00000
Epoch: 0035 train_loss= 0.66368 train_acc= 0.68485 val_loss= 0.68370 val_acc= 0.65574 time= 0.01563
Epoch: 0036 train_loss= 0.66336 train_acc= 0.67879 val_loss= 0.68365 val_acc= 0.63934 time= 0.00000
Epoch: 0037 train_loss= 0.66542 train_acc= 0.67879 val_loss= 0.68333 val_acc= 0.63934 time= 0.01563
Epoch: 0038 train_loss= 0.66600 train_acc= 0.68788 val_loss= 0.68338 val_acc= 0.68852 time= 0.00000
Epoch: 0039 train_loss= 0.65847 train_acc= 0.72424 val_loss= 0.68336 val_acc= 0.72131 time= 0.01563
Epoch: 0040 train_loss= 0.65635 train_acc= 0.69394 val_loss= 0.68255 val_acc= 0.63934 time= 0.00000
Epoch: 0041 train_loss= 0.65467 train_acc= 0.68788 val_loss= 0.68187 val_acc= 0.67213 time= 0.02019
Epoch: 0042 train_loss= 0.65376 train_acc= 0.70303 val_loss= 0.68168 val_acc= 0.67213 time= 0.00101
Epoch: 0043 train_loss= 0.65640 train_acc= 0.72727 val_loss= 0.68148 val_acc= 0.67213 time= 0.01050
Epoch: 0044 train_loss= 0.65887 train_acc= 0.70909 val_loss= 0.68160 val_acc= 0.65574 time= 0.00000
Epoch: 0045 train_loss= 0.64896 train_acc= 0.71212 val_loss= 0.68218 val_acc= 0.70492 time= 0.01563
Epoch: 0046 train_loss= 0.65117 train_acc= 0.71212 val_loss= 0.68236 val_acc= 0.72131 time= 0.00000
Epoch: 0047 train_loss= 0.64995 train_acc= 0.72727 val_loss= 0.68208 val_acc= 0.70492 time= 0.01563
Epoch: 0048 train_loss= 0.64925 train_acc= 0.71818 val_loss= 0.68268 val_acc= 0.70492 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.68306 accuracy= 0.70492 time= 0.01563 
