Epoch: 0001 train_loss= 0.70137 train_acc= 0.48182 val_loss= 0.69829 val_acc= 0.49180 time= 0.17304
Epoch: 0002 train_loss= 0.69796 train_acc= 0.54242 val_loss= 0.69641 val_acc= 0.49180 time= 0.00900
Epoch: 0003 train_loss= 0.69532 train_acc= 0.52424 val_loss= 0.69501 val_acc= 0.49180 time= 0.00900
Epoch: 0004 train_loss= 0.69357 train_acc= 0.52727 val_loss= 0.69401 val_acc= 0.47541 time= 0.00900
Epoch: 0005 train_loss= 0.69243 train_acc= 0.51212 val_loss= 0.69337 val_acc= 0.47541 time= 0.00900
Epoch: 0006 train_loss= 0.69118 train_acc= 0.54848 val_loss= 0.69305 val_acc= 0.47541 time= 0.00800
Epoch: 0007 train_loss= 0.69026 train_acc= 0.54545 val_loss= 0.69281 val_acc= 0.47541 time= 0.01000
Epoch: 0008 train_loss= 0.68907 train_acc= 0.55152 val_loss= 0.69263 val_acc= 0.47541 time= 0.00900
Epoch: 0009 train_loss= 0.68852 train_acc= 0.56364 val_loss= 0.69233 val_acc= 0.47541 time= 0.01100
Epoch: 0010 train_loss= 0.68703 train_acc= 0.57879 val_loss= 0.69193 val_acc= 0.49180 time= 0.00800
Epoch: 0011 train_loss= 0.68607 train_acc= 0.58788 val_loss= 0.69145 val_acc= 0.54098 time= 0.01000
Epoch: 0012 train_loss= 0.68559 train_acc= 0.59091 val_loss= 0.69095 val_acc= 0.57377 time= 0.00900
Epoch: 0013 train_loss= 0.68513 train_acc= 0.62121 val_loss= 0.69040 val_acc= 0.59016 time= 0.00900
Epoch: 0014 train_loss= 0.68330 train_acc= 0.65758 val_loss= 0.68994 val_acc= 0.60656 time= 0.01100
Epoch: 0015 train_loss= 0.68249 train_acc= 0.65758 val_loss= 0.68957 val_acc= 0.60656 time= 0.00900
Epoch: 0016 train_loss= 0.68224 train_acc= 0.60303 val_loss= 0.68914 val_acc= 0.60656 time= 0.00900
Epoch: 0017 train_loss= 0.68137 train_acc= 0.63333 val_loss= 0.68871 val_acc= 0.60656 time= 0.01000
Epoch: 0018 train_loss= 0.67996 train_acc= 0.64545 val_loss= 0.68830 val_acc= 0.60656 time= 0.00900
Epoch: 0019 train_loss= 0.67815 train_acc= 0.63939 val_loss= 0.68774 val_acc= 0.60656 time= 0.00900
Epoch: 0020 train_loss= 0.67981 train_acc= 0.59697 val_loss= 0.68701 val_acc= 0.63934 time= 0.00900
Epoch: 0021 train_loss= 0.67611 train_acc= 0.64242 val_loss= 0.68622 val_acc= 0.63934 time= 0.01000
Epoch: 0022 train_loss= 0.67451 train_acc= 0.69091 val_loss= 0.68561 val_acc= 0.65574 time= 0.00900
Epoch: 0023 train_loss= 0.67408 train_acc= 0.70000 val_loss= 0.68517 val_acc= 0.65574 time= 0.00900
Epoch: 0024 train_loss= 0.67410 train_acc= 0.62424 val_loss= 0.68456 val_acc= 0.67213 time= 0.01000
Epoch: 0025 train_loss= 0.67340 train_acc= 0.68182 val_loss= 0.68420 val_acc= 0.65574 time= 0.01000
Epoch: 0026 train_loss= 0.67295 train_acc= 0.62727 val_loss= 0.68352 val_acc= 0.67213 time= 0.01000
Epoch: 0027 train_loss= 0.66990 train_acc= 0.69091 val_loss= 0.68295 val_acc= 0.67213 time= 0.01100
Epoch: 0028 train_loss= 0.67044 train_acc= 0.67273 val_loss= 0.68224 val_acc= 0.68852 time= 0.00900
Epoch: 0029 train_loss= 0.66952 train_acc= 0.66970 val_loss= 0.68150 val_acc= 0.68852 time= 0.00888
Epoch: 0030 train_loss= 0.66697 train_acc= 0.69394 val_loss= 0.68100 val_acc= 0.68852 time= 0.00000
Epoch: 0031 train_loss= 0.66678 train_acc= 0.66061 val_loss= 0.68015 val_acc= 0.68852 time= 0.01563
Epoch: 0032 train_loss= 0.66178 train_acc= 0.67879 val_loss= 0.67899 val_acc= 0.73770 time= 0.00000
Epoch: 0033 train_loss= 0.66725 train_acc= 0.70606 val_loss= 0.67816 val_acc= 0.73770 time= 0.01563
Epoch: 0034 train_loss= 0.66592 train_acc= 0.66364 val_loss= 0.67721 val_acc= 0.72131 time= 0.01563
Epoch: 0035 train_loss= 0.66544 train_acc= 0.73939 val_loss= 0.67677 val_acc= 0.73770 time= 0.00000
Epoch: 0036 train_loss= 0.66493 train_acc= 0.72424 val_loss= 0.67649 val_acc= 0.73770 time= 0.01563
Epoch: 0037 train_loss= 0.66150 train_acc= 0.71212 val_loss= 0.67598 val_acc= 0.73770 time= 0.01563
Epoch: 0038 train_loss= 0.66249 train_acc= 0.67879 val_loss= 0.67534 val_acc= 0.73770 time= 0.00000
Epoch: 0039 train_loss= 0.66094 train_acc= 0.70303 val_loss= 0.67525 val_acc= 0.68852 time= 0.01563
Epoch: 0040 train_loss= 0.65275 train_acc= 0.70303 val_loss= 0.67431 val_acc= 0.72131 time= 0.00000
Epoch: 0041 train_loss= 0.65750 train_acc= 0.68485 val_loss= 0.67278 val_acc= 0.72131 time= 0.01563
Epoch: 0042 train_loss= 0.65961 train_acc= 0.67273 val_loss= 0.67112 val_acc= 0.75410 time= 0.01562
Epoch: 0043 train_loss= 0.65607 train_acc= 0.72121 val_loss= 0.66983 val_acc= 0.80328 time= 0.00000
Epoch: 0044 train_loss= 0.65928 train_acc= 0.68485 val_loss= 0.66944 val_acc= 0.77049 time= 0.01563
Epoch: 0045 train_loss= 0.65414 train_acc= 0.69091 val_loss= 0.66933 val_acc= 0.75410 time= 0.00000
Epoch: 0046 train_loss= 0.65672 train_acc= 0.71818 val_loss= 0.67064 val_acc= 0.68852 time= 0.01563
Epoch: 0047 train_loss= 0.65537 train_acc= 0.68182 val_loss= 0.67147 val_acc= 0.68852 time= 0.00000
Epoch: 0048 train_loss= 0.65131 train_acc= 0.70303 val_loss= 0.67198 val_acc= 0.65574 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.68041 accuracy= 0.57377 time= 0.00000 
