Epoch: 0001 train_loss= 2.08522 train_acc= 0.11590 val_loss= 2.08267 val_acc= 0.10345 time= 0.31252
Epoch: 0002 train_loss= 2.08387 train_acc= 0.15633 val_loss= 2.08116 val_acc= 0.10345 time= 0.01563
Epoch: 0003 train_loss= 2.08266 train_acc= 0.15633 val_loss= 2.07891 val_acc= 0.10345 time= 0.01563
Epoch: 0004 train_loss= 2.08146 train_acc= 0.15633 val_loss= 2.07652 val_acc= 0.10345 time= 0.00000
Epoch: 0005 train_loss= 2.08047 train_acc= 0.15633 val_loss= 2.07388 val_acc= 0.10345 time= 0.01563
Epoch: 0006 train_loss= 2.07927 train_acc= 0.15633 val_loss= 2.07114 val_acc= 0.10345 time= 0.00000
Epoch: 0007 train_loss= 2.07787 train_acc= 0.15633 val_loss= 2.06820 val_acc= 0.10345 time= 0.01562
Epoch: 0008 train_loss= 2.07655 train_acc= 0.15633 val_loss= 2.06506 val_acc= 0.10345 time= 0.01563
Epoch: 0009 train_loss= 2.07460 train_acc= 0.15633 val_loss= 2.06154 val_acc= 0.10345 time= 0.00000
Epoch: 0010 train_loss= 2.07403 train_acc= 0.15633 val_loss= 2.05783 val_acc= 0.10345 time= 0.01563
Epoch: 0011 train_loss= 2.07271 train_acc= 0.15633 val_loss= 2.05402 val_acc= 0.10345 time= 0.00000
Epoch: 0012 train_loss= 2.07070 train_acc= 0.15633 val_loss= 2.05019 val_acc= 0.10345 time= 0.01562
Epoch: 0013 train_loss= 2.06928 train_acc= 0.15633 val_loss= 2.04648 val_acc= 0.10345 time= 0.00000
Epoch: 0014 train_loss= 2.06857 train_acc= 0.15633 val_loss= 2.04302 val_acc= 0.10345 time= 0.01563
Epoch: 0015 train_loss= 2.06772 train_acc= 0.15633 val_loss= 2.03980 val_acc= 0.10345 time= 0.01563
Epoch: 0016 train_loss= 2.06751 train_acc= 0.15633 val_loss= 2.03678 val_acc= 0.10345 time= 0.00000
Epoch: 0017 train_loss= 2.06653 train_acc= 0.15633 val_loss= 2.03403 val_acc= 0.10345 time= 0.01563
Epoch: 0018 train_loss= 2.06625 train_acc= 0.15633 val_loss= 2.03153 val_acc= 0.10345 time= 0.00000
Epoch: 0019 train_loss= 2.06570 train_acc= 0.15633 val_loss= 2.02918 val_acc= 0.10345 time= 0.01563
Epoch: 0020 train_loss= 2.06591 train_acc= 0.15633 val_loss= 2.02704 val_acc= 0.10345 time= 0.01563
Epoch: 0021 train_loss= 2.06586 train_acc= 0.15633 val_loss= 2.02502 val_acc= 0.10345 time= 0.00000
Epoch: 0022 train_loss= 2.06539 train_acc= 0.15633 val_loss= 2.02315 val_acc= 0.10345 time= 0.01563
Epoch: 0023 train_loss= 2.06526 train_acc= 0.15633 val_loss= 2.02160 val_acc= 0.10345 time= 0.00000
Epoch: 0024 train_loss= 2.06441 train_acc= 0.15633 val_loss= 2.02031 val_acc= 0.10345 time= 0.01563
Epoch: 0025 train_loss= 2.06322 train_acc= 0.15633 val_loss= 2.01917 val_acc= 0.10345 time= 0.01563
Epoch: 0026 train_loss= 2.06361 train_acc= 0.15633 val_loss= 2.01818 val_acc= 0.10345 time= 0.00000
Epoch: 0027 train_loss= 2.06424 train_acc= 0.15903 val_loss= 2.01736 val_acc= 0.10345 time= 0.01562
Epoch: 0028 train_loss= 2.06391 train_acc= 0.15903 val_loss= 2.01675 val_acc= 0.31034 time= 0.00000
Epoch: 0029 train_loss= 2.06366 train_acc= 0.16173 val_loss= 2.01626 val_acc= 0.31034 time= 0.01563
Epoch: 0030 train_loss= 2.06430 train_acc= 0.15364 val_loss= 2.01611 val_acc= 0.31034 time= 0.01563
Epoch: 0031 train_loss= 2.06365 train_acc= 0.15094 val_loss= 2.01604 val_acc= 0.31034 time= 0.00000
Epoch: 0032 train_loss= 2.06351 train_acc= 0.15364 val_loss= 2.01595 val_acc= 0.31034 time= 0.01563
Epoch: 0033 train_loss= 2.06291 train_acc= 0.15364 val_loss= 2.01592 val_acc= 0.31034 time= 0.00000
Epoch: 0034 train_loss= 2.06357 train_acc= 0.15364 val_loss= 2.01585 val_acc= 0.31034 time= 0.01562
Epoch: 0035 train_loss= 2.06257 train_acc= 0.15364 val_loss= 2.01575 val_acc= 0.31034 time= 0.01563
Epoch: 0036 train_loss= 2.06315 train_acc= 0.15364 val_loss= 2.01558 val_acc= 0.31034 time= 0.00000
Epoch: 0037 train_loss= 2.06347 train_acc= 0.15364 val_loss= 2.01540 val_acc= 0.31034 time= 0.01563
Epoch: 0038 train_loss= 2.06366 train_acc= 0.15364 val_loss= 2.01524 val_acc= 0.31034 time= 0.00000
Epoch: 0039 train_loss= 2.06348 train_acc= 0.15364 val_loss= 2.01510 val_acc= 0.31034 time= 0.01562
Epoch: 0040 train_loss= 2.06198 train_acc= 0.15364 val_loss= 2.01477 val_acc= 0.31034 time= 0.01563
Epoch: 0041 train_loss= 2.06254 train_acc= 0.15094 val_loss= 2.01436 val_acc= 0.31034 time= 0.00000
Epoch: 0042 train_loss= 2.06378 train_acc= 0.14555 val_loss= 2.01399 val_acc= 0.31034 time= 0.01563
Epoch: 0043 train_loss= 2.06228 train_acc= 0.15633 val_loss= 2.01366 val_acc= 0.31034 time= 0.00000
Epoch: 0044 train_loss= 2.06236 train_acc= 0.15633 val_loss= 2.01325 val_acc= 0.31034 time= 0.01562
Epoch: 0045 train_loss= 2.06232 train_acc= 0.16712 val_loss= 2.01296 val_acc= 0.10345 time= 0.00000
Epoch: 0046 train_loss= 2.06245 train_acc= 0.16442 val_loss= 2.01262 val_acc= 0.10345 time= 0.01563
Epoch: 0047 train_loss= 2.06163 train_acc= 0.17520 val_loss= 2.01209 val_acc= 0.10345 time= 0.01563
Epoch: 0048 train_loss= 2.06205 train_acc= 0.14825 val_loss= 2.01161 val_acc= 0.10345 time= 0.00000
Epoch: 0049 train_loss= 2.06145 train_acc= 0.14016 val_loss= 2.01102 val_acc= 0.10345 time= 0.01563
Epoch: 0050 train_loss= 2.06213 train_acc= 0.15633 val_loss= 2.01032 val_acc= 0.10345 time= 0.00000
Epoch: 0051 train_loss= 2.06248 train_acc= 0.15364 val_loss= 2.01005 val_acc= 0.31034 time= 0.01562
Epoch: 0052 train_loss= 2.06202 train_acc= 0.14286 val_loss= 2.01011 val_acc= 0.31034 time= 0.01563
Epoch: 0053 train_loss= 2.06098 train_acc= 0.14016 val_loss= 2.01021 val_acc= 0.31034 time= 0.00000
Epoch: 0054 train_loss= 2.06135 train_acc= 0.16173 val_loss= 2.01026 val_acc= 0.31034 time= 0.01562
Epoch: 0055 train_loss= 2.06220 train_acc= 0.16712 val_loss= 2.01040 val_acc= 0.31034 time= 0.00000
Epoch: 0056 train_loss= 2.06223 train_acc= 0.15633 val_loss= 2.01099 val_acc= 0.31034 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.06388 accuracy= 0.11864 time= 0.00000 
