Epoch: 0001 train_loss= 1.34746 train_acc= 0.48961 val_loss= 0.80697 val_acc= 0.52459 time= 0.74266
Epoch: 0002 train_loss= 1.47975 train_acc= 0.48182 val_loss= 0.75302 val_acc= 0.55738 time= 0.01727
Epoch: 0003 train_loss= 1.30416 train_acc= 0.48961 val_loss= 0.79529 val_acc= 0.50820 time= 0.01311
Epoch: 0004 train_loss= 1.70545 train_acc= 0.48182 val_loss= 0.88011 val_acc= 0.45902 time= 0.01514
Epoch: 0005 train_loss= 1.85299 train_acc= 0.48052 val_loss= 0.92652 val_acc= 0.44262 time= 0.01414
Epoch: 0006 train_loss= 1.09045 train_acc= 0.48182 val_loss= 0.97916 val_acc= 0.50820 time= 0.01300
Epoch: 0007 train_loss= 1.56557 train_acc= 0.48571 val_loss= 0.97775 val_acc= 0.45902 time= 0.01500
Epoch: 0008 train_loss= 2.73610 train_acc= 0.51169 val_loss= 0.93994 val_acc= 0.45902 time= 0.01300
Epoch: 0009 train_loss= 1.46262 train_acc= 0.52597 val_loss= 0.88901 val_acc= 0.45902 time= 0.01300
Epoch: 0010 train_loss= 1.72195 train_acc= 0.53117 val_loss= 0.82431 val_acc= 0.45902 time= 0.01400
Epoch: 0011 train_loss= 0.90998 train_acc= 0.51169 val_loss= 0.77855 val_acc= 0.42623 time= 0.01400
Epoch: 0012 train_loss= 1.54434 train_acc= 0.48961 val_loss= 0.76262 val_acc= 0.37705 time= 0.01500
Epoch: 0013 train_loss= 1.02030 train_acc= 0.49740 val_loss= 0.75630 val_acc= 0.37705 time= 0.01508
Epoch: 0014 train_loss= 1.16018 train_acc= 0.50130 val_loss= 0.75195 val_acc= 0.39344 time= 0.01319
Epoch: 0015 train_loss= 1.49719 train_acc= 0.51688 val_loss= 0.75376 val_acc= 0.40984 time= 0.01416
Epoch: 0016 train_loss= 1.55421 train_acc= 0.50779 val_loss= 0.75043 val_acc= 0.42623 time= 0.01315
Epoch: 0017 train_loss= 0.90471 train_acc= 0.51039 val_loss= 0.74905 val_acc= 0.40984 time= 0.01400
Epoch: 0018 train_loss= 1.22556 train_acc= 0.47792 val_loss= 0.74686 val_acc= 0.40984 time= 0.01400
Epoch: 0019 train_loss= 1.07685 train_acc= 0.50000 val_loss= 0.74221 val_acc= 0.40984 time= 0.01400
Epoch: 0020 train_loss= 0.91775 train_acc= 0.50649 val_loss= 0.73833 val_acc= 0.40984 time= 0.01300
Epoch: 0021 train_loss= 1.03222 train_acc= 0.48701 val_loss= 0.73599 val_acc= 0.42623 time= 0.01400
Epoch: 0022 train_loss= 1.02592 train_acc= 0.51299 val_loss= 0.73377 val_acc= 0.42623 time= 0.01400
Epoch: 0023 train_loss= 0.91578 train_acc= 0.51948 val_loss= 0.73177 val_acc= 0.44262 time= 0.01400
Epoch: 0024 train_loss= 0.84663 train_acc= 0.51558 val_loss= 0.73058 val_acc= 0.42623 time= 0.01400
Epoch: 0025 train_loss= 0.97218 train_acc= 0.52208 val_loss= 0.72932 val_acc= 0.40984 time= 0.01400
Epoch: 0026 train_loss= 0.79605 train_acc= 0.55195 val_loss= 0.72866 val_acc= 0.40984 time= 0.01400
Epoch: 0027 train_loss= 0.89658 train_acc= 0.51688 val_loss= 0.72827 val_acc= 0.42623 time= 0.01400
Epoch: 0028 train_loss= 0.81259 train_acc= 0.51818 val_loss= 0.72810 val_acc= 0.40984 time= 0.01300
Epoch: 0029 train_loss= 0.85959 train_acc= 0.49091 val_loss= 0.72820 val_acc= 0.42623 time= 0.01500
Epoch: 0030 train_loss= 0.77914 train_acc= 0.49610 val_loss= 0.72800 val_acc= 0.44262 time= 0.01300
Epoch: 0031 train_loss= 0.84113 train_acc= 0.52078 val_loss= 0.72764 val_acc= 0.44262 time= 0.01500
Epoch: 0032 train_loss= 0.79552 train_acc= 0.51818 val_loss= 0.72699 val_acc= 0.44262 time= 0.01600
Epoch: 0033 train_loss= 0.85492 train_acc= 0.52468 val_loss= 0.72581 val_acc= 0.45902 time= 0.01500
Epoch: 0034 train_loss= 0.77566 train_acc= 0.52597 val_loss= 0.72449 val_acc= 0.44262 time= 0.01500
Epoch: 0035 train_loss= 0.78563 train_acc= 0.51558 val_loss= 0.72322 val_acc= 0.44262 time= 0.01600
Epoch: 0036 train_loss= 0.80022 train_acc= 0.47013 val_loss= 0.72211 val_acc= 0.44262 time= 0.01400
Epoch: 0037 train_loss= 0.76334 train_acc= 0.50130 val_loss= 0.72088 val_acc= 0.42623 time= 0.01600
Epoch: 0038 train_loss= 0.73675 train_acc= 0.51169 val_loss= 0.71972 val_acc= 0.42623 time= 0.01609
Epoch: 0039 train_loss= 0.81597 train_acc= 0.50649 val_loss= 0.71847 val_acc= 0.40984 time= 0.01800
Epoch: 0040 train_loss= 0.75056 train_acc= 0.52078 val_loss= 0.71723 val_acc= 0.40984 time= 0.01400
Epoch: 0041 train_loss= 0.71817 train_acc= 0.52208 val_loss= 0.71604 val_acc= 0.45902 time= 0.01700
Epoch: 0042 train_loss= 0.76211 train_acc= 0.48052 val_loss= 0.71492 val_acc= 0.42623 time= 0.01400
Epoch: 0043 train_loss= 0.80000 train_acc= 0.48571 val_loss= 0.71404 val_acc= 0.42623 time= 0.01500
Epoch: 0044 train_loss= 0.92908 train_acc= 0.48182 val_loss= 0.71387 val_acc= 0.44262 time= 0.01500
Epoch: 0045 train_loss= 0.81813 train_acc= 0.54156 val_loss= 0.71390 val_acc= 0.40984 time= 0.01612
Epoch: 0046 train_loss= 0.72945 train_acc= 0.50260 val_loss= 0.71396 val_acc= 0.39344 time= 0.01311
Epoch: 0047 train_loss= 0.78436 train_acc= 0.53506 val_loss= 0.71352 val_acc= 0.39344 time= 0.01420
Epoch: 0048 train_loss= 0.78234 train_acc= 0.51169 val_loss= 0.71286 val_acc= 0.39344 time= 0.00112
Epoch: 0049 train_loss= 0.74349 train_acc= 0.52468 val_loss= 0.71211 val_acc= 0.39344 time= 0.01563
Epoch: 0050 train_loss= 0.73926 train_acc= 0.51429 val_loss= 0.71160 val_acc= 0.40984 time= 0.01563
Epoch: 0051 train_loss= 0.75337 train_acc= 0.54675 val_loss= 0.71095 val_acc= 0.40984 time= 0.01563
Epoch: 0052 train_loss= 0.86053 train_acc= 0.49610 val_loss= 0.71029 val_acc= 0.40984 time= 0.01990
Epoch: 0053 train_loss= 0.74837 train_acc= 0.52208 val_loss= 0.70947 val_acc= 0.40984 time= 0.01500
Epoch: 0054 train_loss= 0.71268 train_acc= 0.52208 val_loss= 0.70879 val_acc= 0.40984 time= 0.01600
Epoch: 0055 train_loss= 0.83984 train_acc= 0.45455 val_loss= 0.70807 val_acc= 0.37705 time= 0.01500
Epoch: 0056 train_loss= 0.77839 train_acc= 0.50519 val_loss= 0.70749 val_acc= 0.39344 time= 0.01400
Epoch: 0057 train_loss= 0.73862 train_acc= 0.48961 val_loss= 0.70731 val_acc= 0.40984 time= 0.01400
Epoch: 0058 train_loss= 0.73886 train_acc= 0.52597 val_loss= 0.70732 val_acc= 0.37705 time= 0.01300
Epoch: 0059 train_loss= 0.73016 train_acc= 0.48701 val_loss= 0.70746 val_acc= 0.37705 time= 0.01600
Epoch: 0060 train_loss= 0.72978 train_acc= 0.51039 val_loss= 0.70720 val_acc= 0.39344 time= 0.01600
Epoch: 0061 train_loss= 0.73481 train_acc= 0.48312 val_loss= 0.70706 val_acc= 0.39344 time= 0.01611
Epoch: 0062 train_loss= 0.71291 train_acc= 0.50779 val_loss= 0.70692 val_acc= 0.37705 time= 0.01524
Epoch: 0063 train_loss= 0.75490 train_acc= 0.49091 val_loss= 0.70730 val_acc= 0.39344 time= 0.01507
Epoch: 0064 train_loss= 0.73858 train_acc= 0.52727 val_loss= 0.70727 val_acc= 0.39344 time= 0.01400
Epoch: 0065 train_loss= 0.71562 train_acc= 0.50000 val_loss= 0.70729 val_acc= 0.39344 time= 0.00838
Epoch: 0066 train_loss= 0.74747 train_acc= 0.49221 val_loss= 0.70746 val_acc= 0.39344 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 0.70002 accuracy= 0.47541 time= 0.00000 
