Epoch: 0001 train_loss= 0.70100 train_acc= 0.52545 val_loss= 0.69827 val_acc= 0.54098 time= 0.44100
Epoch: 0002 train_loss= 0.69803 train_acc= 0.54000 val_loss= 0.69616 val_acc= 0.54098 time= 0.00000
Epoch: 0003 train_loss= 0.69589 train_acc= 0.57818 val_loss= 0.69466 val_acc= 0.57377 time= 0.01563
Epoch: 0004 train_loss= 0.69402 train_acc= 0.56545 val_loss= 0.69356 val_acc= 0.60656 time= 0.01563
Epoch: 0005 train_loss= 0.69291 train_acc= 0.65091 val_loss= 0.69286 val_acc= 0.62295 time= 0.01563
Epoch: 0006 train_loss= 0.69208 train_acc= 0.66364 val_loss= 0.69255 val_acc= 0.60656 time= 0.00000
Epoch: 0007 train_loss= 0.69113 train_acc= 0.68909 val_loss= 0.69259 val_acc= 0.55738 time= 0.01563
Epoch: 0008 train_loss= 0.69089 train_acc= 0.65455 val_loss= 0.69276 val_acc= 0.55738 time= 0.00000
Epoch: 0009 train_loss= 0.69041 train_acc= 0.61455 val_loss= 0.69292 val_acc= 0.55738 time= 0.01563
Epoch: 0010 train_loss= 0.69071 train_acc= 0.65818 val_loss= 0.69305 val_acc= 0.55738 time= 0.00000
Epoch: 0011 train_loss= 0.69018 train_acc= 0.59455 val_loss= 0.69300 val_acc= 0.55738 time= 0.01563
Epoch: 0012 train_loss= 0.68904 train_acc= 0.58909 val_loss= 0.69269 val_acc= 0.55738 time= 0.01563
Epoch: 0013 train_loss= 0.68873 train_acc= 0.64182 val_loss= 0.69231 val_acc= 0.55738 time= 0.00000
Epoch: 0014 train_loss= 0.68772 train_acc= 0.63455 val_loss= 0.69182 val_acc= 0.59016 time= 0.01563
Epoch: 0015 train_loss= 0.68795 train_acc= 0.68364 val_loss= 0.69148 val_acc= 0.59016 time= 0.00000
Epoch: 0016 train_loss= 0.68688 train_acc= 0.70364 val_loss= 0.69117 val_acc= 0.59016 time= 0.01563
Epoch: 0017 train_loss= 0.68481 train_acc= 0.66364 val_loss= 0.69099 val_acc= 0.59016 time= 0.00000
Epoch: 0018 train_loss= 0.68440 train_acc= 0.66545 val_loss= 0.69081 val_acc= 0.59016 time= 0.01563
Epoch: 0019 train_loss= 0.68345 train_acc= 0.66545 val_loss= 0.69091 val_acc= 0.59016 time= 0.00000
Epoch: 0020 train_loss= 0.68306 train_acc= 0.67636 val_loss= 0.69112 val_acc= 0.55738 time= 0.01563
Epoch: 0021 train_loss= 0.68355 train_acc= 0.68000 val_loss= 0.69132 val_acc= 0.55738 time= 0.01563
Epoch: 0022 train_loss= 0.68215 train_acc= 0.60727 val_loss= 0.69105 val_acc= 0.55738 time= 0.00000
Epoch: 0023 train_loss= 0.68061 train_acc= 0.67455 val_loss= 0.69063 val_acc= 0.59016 time= 0.01563
Epoch: 0024 train_loss= 0.68154 train_acc= 0.64182 val_loss= 0.68986 val_acc= 0.59016 time= 0.00000
Epoch: 0025 train_loss= 0.67968 train_acc= 0.71818 val_loss= 0.68936 val_acc= 0.57377 time= 0.01563
Epoch: 0026 train_loss= 0.67817 train_acc= 0.72545 val_loss= 0.68887 val_acc= 0.59016 time= 0.00000
Epoch: 0027 train_loss= 0.67804 train_acc= 0.68000 val_loss= 0.68819 val_acc= 0.60656 time= 0.01563
Epoch: 0028 train_loss= 0.67761 train_acc= 0.68727 val_loss= 0.68790 val_acc= 0.62295 time= 0.00000
Epoch: 0029 train_loss= 0.67577 train_acc= 0.71455 val_loss= 0.68785 val_acc= 0.60656 time= 0.01563
Epoch: 0030 train_loss= 0.67745 train_acc= 0.65818 val_loss= 0.68766 val_acc= 0.59016 time= 0.00000
Epoch: 0031 train_loss= 0.67494 train_acc= 0.67273 val_loss= 0.68692 val_acc= 0.59016 time= 0.01563
Epoch: 0032 train_loss= 0.67383 train_acc= 0.64182 val_loss= 0.68562 val_acc= 0.62295 time= 0.00000
Epoch: 0033 train_loss= 0.67484 train_acc= 0.67636 val_loss= 0.68416 val_acc= 0.70492 time= 0.01563
Epoch: 0034 train_loss= 0.67208 train_acc= 0.66727 val_loss= 0.68327 val_acc= 0.68852 time= 0.01563
Epoch: 0035 train_loss= 0.67139 train_acc= 0.69273 val_loss= 0.68269 val_acc= 0.68852 time= 0.00000
Epoch: 0036 train_loss= 0.66815 train_acc= 0.69273 val_loss= 0.68305 val_acc= 0.62295 time= 0.01563
Epoch: 0037 train_loss= 0.67043 train_acc= 0.69091 val_loss= 0.68370 val_acc= 0.59016 time= 0.00000
Epoch: 0038 train_loss= 0.67044 train_acc= 0.68909 val_loss= 0.68399 val_acc= 0.60656 time= 0.01563
Epoch: 0039 train_loss= 0.67060 train_acc= 0.67818 val_loss= 0.68368 val_acc= 0.59016 time= 0.00000
Epoch: 0040 train_loss= 0.66764 train_acc= 0.67273 val_loss= 0.68261 val_acc= 0.60656 time= 0.01562
Epoch: 0041 train_loss= 0.66665 train_acc= 0.67818 val_loss= 0.68075 val_acc= 0.65574 time= 0.00000
Epoch: 0042 train_loss= 0.66531 train_acc= 0.68545 val_loss= 0.67846 val_acc= 0.68852 time= 0.01563
Epoch: 0043 train_loss= 0.66714 train_acc= 0.71273 val_loss= 0.67698 val_acc= 0.70492 time= 0.00000
Epoch: 0044 train_loss= 0.66738 train_acc= 0.64727 val_loss= 0.67767 val_acc= 0.68852 time= 0.01563
Epoch: 0045 train_loss= 0.65937 train_acc= 0.72364 val_loss= 0.67827 val_acc= 0.70492 time= 0.00000
Epoch: 0046 train_loss= 0.66120 train_acc= 0.70364 val_loss= 0.67985 val_acc= 0.62295 time= 0.01563
Epoch: 0047 train_loss= 0.65811 train_acc= 0.73455 val_loss= 0.68220 val_acc= 0.60656 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.65843 accuracy= 0.73770 time= 0.00000 
