Epoch: 0001 train_loss= 0.93429 train_acc= 0.53273 val_loss= 2.11593 val_acc= 0.59016 time= 0.40809
Epoch: 0002 train_loss= 0.72481 train_acc= 0.50000 val_loss= 2.46867 val_acc= 0.57377 time= 0.01400
Epoch: 0003 train_loss= 0.97031 train_acc= 0.51273 val_loss= 2.91157 val_acc= 0.54098 time= 0.01300
Epoch: 0004 train_loss= 0.78857 train_acc= 0.51455 val_loss= 3.14980 val_acc= 0.52459 time= 0.01300
Epoch: 0005 train_loss= 0.72333 train_acc= 0.51818 val_loss= 3.34745 val_acc= 0.52459 time= 0.01200
Epoch: 0006 train_loss= 0.76421 train_acc= 0.51818 val_loss= 3.41411 val_acc= 0.52459 time= 0.01200
Epoch: 0007 train_loss= 0.75024 train_acc= 0.56000 val_loss= 3.44346 val_acc= 0.49180 time= 0.01300
Epoch: 0008 train_loss= 0.76946 train_acc= 0.52909 val_loss= 3.42591 val_acc= 0.49180 time= 0.01300
Epoch: 0009 train_loss= 0.72690 train_acc= 0.53818 val_loss= 3.37292 val_acc= 0.49180 time= 0.01200
Epoch: 0010 train_loss= 0.74990 train_acc= 0.52364 val_loss= 3.30077 val_acc= 0.49180 time= 0.01300
Epoch: 0011 train_loss= 0.78539 train_acc= 0.54000 val_loss= 3.14349 val_acc= 0.49180 time= 0.01500
Epoch: 0012 train_loss= 0.73997 train_acc= 0.51455 val_loss= 3.11911 val_acc= 0.49180 time= 0.01200
Epoch: 0013 train_loss= 0.77844 train_acc= 0.50182 val_loss= 3.07799 val_acc= 0.47541 time= 0.01200
Epoch: 0014 train_loss= 0.71887 train_acc= 0.51455 val_loss= 3.03635 val_acc= 0.42623 time= 0.01200
Epoch: 0015 train_loss= 0.77092 train_acc= 0.51273 val_loss= 2.97167 val_acc= 0.47541 time= 0.01300
Epoch: 0016 train_loss= 0.71653 train_acc= 0.52000 val_loss= 2.89816 val_acc= 0.45902 time= 0.01200
Epoch: 0017 train_loss= 0.70764 train_acc= 0.53455 val_loss= 2.83282 val_acc= 0.45902 time= 0.01300
Epoch: 0018 train_loss= 0.73349 train_acc= 0.52000 val_loss= 2.74378 val_acc= 0.45902 time= 0.01400
Epoch: 0019 train_loss= 0.73600 train_acc= 0.50909 val_loss= 2.64345 val_acc= 0.42623 time= 0.01300
Epoch: 0020 train_loss= 0.70813 train_acc= 0.54909 val_loss= 2.58810 val_acc= 0.44262 time= 0.01300
Epoch: 0021 train_loss= 0.70167 train_acc= 0.49273 val_loss= 2.53516 val_acc= 0.44262 time= 0.01200
Epoch: 0022 train_loss= 0.74153 train_acc= 0.51818 val_loss= 2.45129 val_acc= 0.44262 time= 0.01100
Epoch: 0023 train_loss= 0.72164 train_acc= 0.52909 val_loss= 2.33958 val_acc= 0.44262 time= 0.01300
Epoch: 0024 train_loss= 0.72174 train_acc= 0.53455 val_loss= 2.21972 val_acc= 0.44262 time= 0.01200
Epoch: 0025 train_loss= 0.70453 train_acc= 0.50364 val_loss= 2.11844 val_acc= 0.44262 time= 0.01100
Epoch: 0026 train_loss= 0.69744 train_acc= 0.54364 val_loss= 2.01914 val_acc= 0.45902 time= 0.01200
Epoch: 0027 train_loss= 0.70142 train_acc= 0.52364 val_loss= 1.93334 val_acc= 0.44262 time= 0.01300
Epoch: 0028 train_loss= 0.69815 train_acc= 0.53273 val_loss= 1.84447 val_acc= 0.47541 time= 0.01400
Epoch: 0029 train_loss= 0.71353 train_acc= 0.52545 val_loss= 1.75419 val_acc= 0.49180 time= 0.01200
Epoch: 0030 train_loss= 0.68942 train_acc= 0.53455 val_loss= 1.66116 val_acc= 0.49180 time= 0.01200
Epoch: 0031 train_loss= 0.72313 train_acc= 0.52182 val_loss= 1.58259 val_acc= 0.47541 time= 0.01400
Epoch: 0032 train_loss= 0.70459 train_acc= 0.56182 val_loss= 1.56070 val_acc= 0.47541 time= 0.01100
Epoch: 0033 train_loss= 0.71030 train_acc= 0.50909 val_loss= 1.54216 val_acc= 0.49180 time= 0.01300
Epoch: 0034 train_loss= 0.70871 train_acc= 0.52545 val_loss= 1.51736 val_acc= 0.52459 time= 0.01200
Epoch: 0035 train_loss= 0.70248 train_acc= 0.54182 val_loss= 1.48947 val_acc= 0.52459 time= 0.01300
Epoch: 0036 train_loss= 0.72527 train_acc= 0.51818 val_loss= 1.45797 val_acc= 0.52459 time= 0.01200
Epoch: 0037 train_loss= 0.72279 train_acc= 0.51091 val_loss= 1.42804 val_acc= 0.50820 time= 0.01300
Epoch: 0038 train_loss= 0.70695 train_acc= 0.54364 val_loss= 1.42041 val_acc= 0.50820 time= 0.01200
Epoch: 0039 train_loss= 0.70572 train_acc= 0.54909 val_loss= 1.40945 val_acc= 0.49180 time= 0.01300
Epoch: 0040 train_loss= 0.69283 train_acc= 0.54909 val_loss= 1.39576 val_acc= 0.45902 time= 0.01200
Epoch: 0041 train_loss= 0.70353 train_acc= 0.52364 val_loss= 1.38085 val_acc= 0.44262 time= 0.01200
Epoch: 0042 train_loss= 0.69778 train_acc= 0.53091 val_loss= 1.36729 val_acc= 0.42623 time= 0.01500
Epoch: 0043 train_loss= 0.70239 train_acc= 0.52000 val_loss= 1.34872 val_acc= 0.42623 time= 0.01500
Epoch: 0044 train_loss= 0.69950 train_acc= 0.52727 val_loss= 1.32489 val_acc= 0.42623 time= 0.01500
Epoch: 0045 train_loss= 0.70322 train_acc= 0.52727 val_loss= 1.30319 val_acc= 0.42623 time= 0.01400
Epoch: 0046 train_loss= 0.70740 train_acc= 0.50000 val_loss= 1.27681 val_acc= 0.42623 time= 0.01300
Epoch: 0047 train_loss= 0.69719 train_acc= 0.55091 val_loss= 1.25057 val_acc= 0.44262 time= 0.01300
Epoch: 0048 train_loss= 0.69135 train_acc= 0.52909 val_loss= 1.22779 val_acc= 0.44262 time= 0.01300
Epoch: 0049 train_loss= 0.70614 train_acc= 0.52909 val_loss= 1.20057 val_acc= 0.44262 time= 0.01200
Epoch: 0050 train_loss= 0.68464 train_acc= 0.54000 val_loss= 1.18017 val_acc= 0.44262 time= 0.01200
Epoch: 0051 train_loss= 0.69700 train_acc= 0.51273 val_loss= 1.15935 val_acc= 0.44262 time= 0.01200
Epoch: 0052 train_loss= 0.68828 train_acc= 0.54000 val_loss= 1.13509 val_acc= 0.44262 time= 0.01300
Epoch: 0053 train_loss= 0.69146 train_acc= 0.52000 val_loss= 1.11262 val_acc= 0.44262 time= 0.01300
Epoch: 0054 train_loss= 0.69856 train_acc= 0.52545 val_loss= 1.09033 val_acc= 0.42623 time= 0.01300
Epoch: 0055 train_loss= 0.69814 train_acc= 0.52909 val_loss= 1.13335 val_acc= 0.40984 time= 0.01300
Epoch: 0056 train_loss= 0.69297 train_acc= 0.54364 val_loss= 1.16820 val_acc= 0.42623 time= 0.01200
Epoch: 0057 train_loss= 0.69287 train_acc= 0.51273 val_loss= 1.20003 val_acc= 0.42623 time= 0.01300
Early stopping...
Optimization Finished!
Test set results: cost= 0.84233 accuracy= 0.46721 time= 0.00700 
