Epoch: 0001 train_loss= 0.70129 train_acc= 0.51299 val_loss= 0.69768 val_acc= 0.59016 time= 0.79205
Epoch: 0002 train_loss= 0.69809 train_acc= 0.52857 val_loss= 0.69515 val_acc= 0.62295 time= 0.01996
Epoch: 0003 train_loss= 0.69582 train_acc= 0.54286 val_loss= 0.69314 val_acc= 0.62295 time= 0.01200
Epoch: 0004 train_loss= 0.69396 train_acc= 0.54286 val_loss= 0.69160 val_acc= 0.63934 time= 0.01100
Epoch: 0005 train_loss= 0.69259 train_acc= 0.54026 val_loss= 0.69049 val_acc= 0.63934 time= 0.01000
Epoch: 0006 train_loss= 0.69163 train_acc= 0.54545 val_loss= 0.68977 val_acc= 0.63934 time= 0.01100
Epoch: 0007 train_loss= 0.69110 train_acc= 0.56234 val_loss= 0.68923 val_acc= 0.63934 time= 0.00897
Epoch: 0008 train_loss= 0.69066 train_acc= 0.54416 val_loss= 0.68887 val_acc= 0.63934 time= 0.00000
Epoch: 0009 train_loss= 0.69045 train_acc= 0.55714 val_loss= 0.68863 val_acc= 0.65574 time= 0.01562
Epoch: 0010 train_loss= 0.68991 train_acc= 0.58182 val_loss= 0.68830 val_acc= 0.65574 time= 0.01563
Epoch: 0011 train_loss= 0.68899 train_acc= 0.59351 val_loss= 0.68790 val_acc= 0.65574 time= 0.00000
Epoch: 0012 train_loss= 0.68823 train_acc= 0.58701 val_loss= 0.68740 val_acc= 0.67213 time= 0.01563
Epoch: 0013 train_loss= 0.68825 train_acc= 0.61299 val_loss= 0.68679 val_acc= 0.67213 time= 0.01563
Epoch: 0014 train_loss= 0.68758 train_acc= 0.60000 val_loss= 0.68625 val_acc= 0.67213 time= 0.00000
Epoch: 0015 train_loss= 0.68670 train_acc= 0.60519 val_loss= 0.68578 val_acc= 0.68852 time= 0.01563
Epoch: 0016 train_loss= 0.68569 train_acc= 0.68052 val_loss= 0.68515 val_acc= 0.68852 time= 0.01606
Epoch: 0017 train_loss= 0.68363 train_acc= 0.63247 val_loss= 0.68457 val_acc= 0.68852 time= 0.01200
Epoch: 0018 train_loss= 0.68392 train_acc= 0.69221 val_loss= 0.68382 val_acc= 0.68852 time= 0.00286
Epoch: 0019 train_loss= 0.68492 train_acc= 0.67273 val_loss= 0.68304 val_acc= 0.68852 time= 0.01562
Epoch: 0020 train_loss= 0.68407 train_acc= 0.62208 val_loss= 0.68246 val_acc= 0.68852 time= 0.00000
Epoch: 0021 train_loss= 0.68213 train_acc= 0.62727 val_loss= 0.68214 val_acc= 0.68852 time= 0.01563
Epoch: 0022 train_loss= 0.68274 train_acc= 0.62857 val_loss= 0.68192 val_acc= 0.68852 time= 0.01872
Epoch: 0023 train_loss= 0.67987 train_acc= 0.65974 val_loss= 0.68171 val_acc= 0.70492 time= 0.00464
Epoch: 0024 train_loss= 0.67916 train_acc= 0.64156 val_loss= 0.68174 val_acc= 0.72131 time= 0.01812
Epoch: 0025 train_loss= 0.67911 train_acc= 0.71429 val_loss= 0.68138 val_acc= 0.72131 time= 0.00607
Epoch: 0026 train_loss= 0.67551 train_acc= 0.64935 val_loss= 0.68141 val_acc= 0.73770 time= 0.01563
Epoch: 0027 train_loss= 0.67963 train_acc= 0.67662 val_loss= 0.68098 val_acc= 0.73770 time= 0.00000
Epoch: 0028 train_loss= 0.67777 train_acc= 0.66753 val_loss= 0.68073 val_acc= 0.72131 time= 0.01563
Epoch: 0029 train_loss= 0.67583 train_acc= 0.71688 val_loss= 0.68013 val_acc= 0.72131 time= 0.01563
Epoch: 0030 train_loss= 0.67793 train_acc= 0.67013 val_loss= 0.67881 val_acc= 0.73770 time= 0.00000
Epoch: 0031 train_loss= 0.67368 train_acc= 0.67532 val_loss= 0.67758 val_acc= 0.72131 time= 0.01563
Epoch: 0032 train_loss= 0.67517 train_acc= 0.68312 val_loss= 0.67607 val_acc= 0.70492 time= 0.00000
Epoch: 0033 train_loss= 0.67401 train_acc= 0.68701 val_loss= 0.67482 val_acc= 0.70492 time= 0.01563
Epoch: 0034 train_loss= 0.67420 train_acc= 0.66623 val_loss= 0.67425 val_acc= 0.70492 time= 0.01563
Epoch: 0035 train_loss= 0.67348 train_acc= 0.68182 val_loss= 0.67359 val_acc= 0.70492 time= 0.00000
Epoch: 0036 train_loss= 0.67045 train_acc= 0.70000 val_loss= 0.67291 val_acc= 0.70492 time= 0.02133
Epoch: 0037 train_loss= 0.67044 train_acc= 0.64545 val_loss= 0.67387 val_acc= 0.73770 time= 0.00518
Epoch: 0038 train_loss= 0.66946 train_acc= 0.69870 val_loss= 0.67468 val_acc= 0.72131 time= 0.01503
Epoch: 0039 train_loss= 0.66825 train_acc= 0.69740 val_loss= 0.67563 val_acc= 0.73770 time= 0.00317
Epoch: 0040 train_loss= 0.66956 train_acc= 0.69091 val_loss= 0.67467 val_acc= 0.72131 time= 0.01365
Epoch: 0041 train_loss= 0.66672 train_acc= 0.69091 val_loss= 0.67357 val_acc= 0.73770 time= 0.02111
Epoch: 0042 train_loss= 0.66997 train_acc= 0.68831 val_loss= 0.67105 val_acc= 0.75410 time= 0.01400
Epoch: 0043 train_loss= 0.66556 train_acc= 0.69091 val_loss= 0.66988 val_acc= 0.73770 time= 0.00577
Epoch: 0044 train_loss= 0.67022 train_acc= 0.65974 val_loss= 0.66680 val_acc= 0.70492 time= 0.01808
Epoch: 0045 train_loss= 0.66176 train_acc= 0.66753 val_loss= 0.66576 val_acc= 0.70492 time= 0.01300
Epoch: 0046 train_loss= 0.66463 train_acc= 0.66883 val_loss= 0.66595 val_acc= 0.72131 time= 0.01100
Epoch: 0047 train_loss= 0.66564 train_acc= 0.66883 val_loss= 0.66795 val_acc= 0.73770 time= 0.00100
Epoch: 0048 train_loss= 0.66460 train_acc= 0.68571 val_loss= 0.67057 val_acc= 0.72131 time= 0.01566
Epoch: 0049 train_loss= 0.66128 train_acc= 0.71688 val_loss= 0.67212 val_acc= 0.72131 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.66773 accuracy= 0.72131 time= 0.00000 
