Переглянути джерело

adding logs of second round hyperparameter tuning

Sebastian Vendt 5 роки тому
батько
коміт
922fbeec08

+ 634 - 0
julia/logs/csv_29_09_2019_165206.csv

@@ -0,0 +1,634 @@
+epoch, loss(train), loss(val)
+1, 0.106532, 0.109270
+2, 0.095428, 0.097530
+3, 0.090024, 0.091654
+4, 0.086840, 0.088290
+5, 0.085175, 0.086443
+6, 0.084256, 0.085231
+7, 0.083388, 0.084379
+8, 0.082766, 0.083685
+9, 0.082271, 0.083217
+10, 0.081836, 0.082803
+11, 0.081547, 0.082447
+12, 0.081178, 0.082092
+13, 0.080869, 0.081751
+14, 0.080644, 0.081556
+15, 0.080391, 0.081279
+16, 0.080222, 0.081098
+17, 0.080038, 0.080880
+18, 0.079911, 0.080777
+19, 0.079714, 0.080606
+20, 0.079589, 0.080480
+21, 0.079406, 0.080328
+22, 0.079339, 0.080205
+23, 0.079207, 0.080088
+24, 0.079084, 0.079978
+25, 0.079040, 0.079932
+26, 0.078889, 0.079799
+27, 0.078822, 0.079725
+28, 0.078742, 0.079628
+29, 0.078611, 0.079555
+30, 0.078586, 0.079513
+31, 0.078523, 0.079450
+32, 0.078456, 0.079391
+33, 0.078401, 0.079339
+34, 0.078364, 0.079309
+35, 0.078296, 0.079267
+36, 0.078242, 0.079220
+37, 0.078217, 0.079206
+38, 0.078172, 0.079159
+39, 0.078125, 0.079112
+40, 0.078090, 0.079078
+41, 0.078064, 0.079061
+42, 0.078024, 0.079030
+43, 0.077999, 0.079014
+44, 0.077969, 0.079004
+45, 0.077942, 0.078974
+46, 0.077913, 0.078955
+47, 0.077897, 0.078943
+48, 0.077872, 0.078943
+49, 0.077860, 0.078925
+50, 0.077845, 0.078909
+1, 0.106738, 0.110443
+2, 0.094961, 0.097940
+3, 0.089637, 0.092018
+4, 0.086759, 0.088715
+5, 0.085159, 0.086774
+6, 0.084000, 0.085421
+7, 0.083180, 0.084470
+8, 0.082572, 0.083797
+9, 0.082123, 0.083295
+10, 0.081630, 0.082839
+11, 0.081291, 0.082452
+12, 0.080972, 0.082084
+13, 0.080653, 0.081747
+14, 0.080442, 0.081523
+15, 0.080123, 0.081291
+16, 0.079901, 0.081047
+17, 0.079744, 0.080816
+18, 0.079591, 0.080666
+19, 0.079401, 0.080512
+20, 0.079236, 0.080347
+21, 0.079109, 0.080221
+22, 0.078977, 0.080101
+23, 0.078854, 0.080001
+24, 0.078805, 0.079867
+25, 0.078686, 0.079800
+26, 0.078619, 0.079673
+27, 0.078528, 0.079612
+28, 0.078430, 0.079535
+29, 0.078359, 0.079456
+30, 0.078281, 0.079384
+31, 0.078242, 0.079335
+32, 0.078183, 0.079284
+33, 0.078123, 0.079225
+34, 0.078082, 0.079195
+35, 0.078023, 0.079155
+36, 0.077983, 0.079103
+37, 0.077936, 0.079066
+38, 0.077902, 0.079045
+39, 0.077875, 0.079019
+40, 0.077839, 0.078968
+41, 0.077803, 0.078962
+42, 0.077777, 0.078970
+43, 0.077755, 0.078905
+44, 0.077733, 0.078915
+45, 0.077713, 0.078907
+46, 0.077690, 0.078885
+47, 0.077666, 0.078863
+48, 0.077652, 0.078851
+49, 0.077632, 0.078827
+50, 0.077617, 0.078828
+51, 0.077603, 0.078800
+52, 0.077587, 0.078780
+53, 0.077573, 0.078771
+54, 0.077561, 0.078770
+55, 0.077551, 0.078766
+56, 0.077541, 0.078755
+57, 0.077533, 0.078769
+58, 0.077520, 0.078739
+59, 0.077514, 0.078746
+60, 0.077504, 0.078725
+61, 0.077499, 0.078735
+62, 0.077492, 0.078728
+63, 0.077485, 0.078724
+64, 0.077478, 0.078721
+65, 0.077468, 0.078695
+66, 0.077468, 0.078714
+67, 0.077462, 0.078705
+68, 0.077458, 0.078700
+69, 0.077453, 0.078694
+70, 0.077454, 0.078712
+71, 0.077449, 0.078707
+72, 0.077444, 0.078695
+73, 0.077440, 0.078689
+74, 0.077438, 0.078692
+75, 0.077435, 0.078691
+76, 0.077430, 0.078680
+77, 0.077427, 0.078679
+78, 0.077426, 0.078680
+79, 0.077424, 0.078680
+80, 0.077420, 0.078671
+81, 0.077419, 0.078675
+82, 0.077415, 0.078664
+83, 0.077414, 0.078668
+84, 0.077410, 0.078661
+85, 0.077410, 0.078663
+86, 0.077409, 0.078667
+87, 0.077407, 0.078664
+88, 0.077406, 0.078664
+89, 0.077404, 0.078660
+90, 0.077403, 0.078663
+91, 0.077401, 0.078657
+92, 0.077399, 0.078655
+93, 0.077399, 0.078657
+94, 0.077399, 0.078657
+95, 0.077398, 0.078657
+96, 0.077397, 0.078658
+97, 0.077397, 0.078657
+98, 0.077394, 0.078651
+99, 0.077394, 0.078652
+100, 0.077393, 0.078650
+101, 0.077392, 0.078649
+102, 0.077391, 0.078646
+103, 0.077390, 0.078645
+104, 0.077389, 0.078644
+105, 0.077389, 0.078644
+106, 0.077388, 0.078642
+107, 0.077388, 0.078642
+108, 0.077388, 0.078644
+109, 0.077387, 0.078643
+110, 0.077387, 0.078643
+111, 0.077386, 0.078641
+112, 0.077386, 0.078641
+113, 0.077386, 0.078642
+114, 0.077386, 0.078641
+115, 0.077385, 0.078641
+116, 0.077385, 0.078641
+117, 0.077385, 0.078641
+118, 0.077385, 0.078641
+119, 0.077385, 0.078642
+120, 0.077384, 0.078641
+121, 0.077384, 0.078641
+122, 0.077384, 0.078641
+123, 0.077384, 0.078641
+124, 0.077384, 0.078641
+125, 0.077384, 0.078640
+126, 0.077384, 0.078640
+127, 0.077384, 0.078641
+128, 0.077384, 0.078640
+129, 0.077383, 0.078640
+130, 0.077383, 0.078640
+131, 0.077383, 0.078639
+132, 0.077383, 0.078640
+133, 0.077383, 0.078640
+134, 0.077383, 0.078639
+135, 0.077383, 0.078639
+136, 0.077383, 0.078639
+137, 0.077383, 0.078639
+138, 0.077383, 0.078639
+139, 0.077383, 0.078639
+140, 0.077383, 0.078639
+141, 0.077383, 0.078639
+142, 0.077383, 0.078639
+143, 0.077383, 0.078639
+144, 0.077383, 0.078639
+145, 0.077383, 0.078639
+146, 0.077383, 0.078640
+147, 0.077383, 0.078639
+148, 0.077383, 0.078639
+149, 0.077383, 0.078639
+150, 0.077383, 0.078639
+151, 0.077383, 0.078639
+152, 0.077383, 0.078639
+153, 0.077383, 0.078639
+154, 0.077382, 0.078639
+155, 0.077382, 0.078639
+156, 0.077382, 0.078639
+157, 0.077382, 0.078639
+158, 0.077382, 0.078639
+159, 0.077382, 0.078639
+160, 0.077382, 0.078639
+161, 0.077382, 0.078639
+162, 0.077382, 0.078639
+163, 0.077382, 0.078639
+164, 0.077382, 0.078639
+165, 0.077382, 0.078639
+166, 0.077382, 0.078639
+167, 0.077382, 0.078639
+168, 0.077382, 0.078639
+169, 0.077382, 0.078639
+170, 0.077382, 0.078639
+171, 0.077382, 0.078639
+172, 0.077382, 0.078639
+173, 0.077382, 0.078639
+174, 0.077382, 0.078639
+175, 0.077382, 0.078639
+176, 0.077382, 0.078639
+177, 0.077382, 0.078639
+178, 0.077382, 0.078639
+179, 0.077382, 0.078639
+180, 0.077382, 0.078639
+181, 0.077382, 0.078639
+182, 0.077382, 0.078639
+183, 0.077382, 0.078639
+184, 0.077382, 0.078639
+185, 0.077382, 0.078639
+186, 0.077382, 0.078639
+187, 0.077382, 0.078639
+188, 0.077382, 0.078639
+189, 0.077382, 0.078639
+190, 0.077382, 0.078639
+191, 0.077382, 0.078639
+192, 0.077382, 0.078639
+193, 0.077382, 0.078639
+194, 0.077382, 0.078639
+195, 0.077382, 0.078639
+196, 0.077382, 0.078639
+197, 0.077382, 0.078639
+198, 0.077382, 0.078639
+199, 0.077382, 0.078639
+200, 0.077382, 0.078639
+201, 0.077382, 0.078639
+202, 0.077382, 0.078639
+203, 0.077382, 0.078639
+204, 0.077382, 0.078639
+205, 0.077382, 0.078639
+206, 0.077382, 0.078639
+207, 0.077382, 0.078639
+208, 0.077382, 0.078639
+209, 0.077382, 0.078639
+210, 0.077382, 0.078639
+211, 0.077382, 0.078639
+212, 0.077382, 0.078639
+213, 0.077382, 0.078639
+214, 0.077382, 0.078639
+215, 0.077382, 0.078639
+216, 0.077382, 0.078639
+217, 0.077382, 0.078639
+218, 0.077382, 0.078639
+219, 0.077382, 0.078639
+220, 0.077382, 0.078639
+221, 0.077382, 0.078639
+222, 0.077382, 0.078639
+223, 0.077382, 0.078639
+224, 0.077382, 0.078639
+225, 0.077382, 0.078639
+226, 0.077382, 0.078639
+227, 0.077382, 0.078639
+228, 0.077382, 0.078639
+229, 0.077382, 0.078639
+230, 0.077382, 0.078639
+231, 0.077382, 0.078639
+232, 0.077382, 0.078639
+233, 0.077382, 0.078639
+234, 0.077382, 0.078639
+235, 0.077382, 0.078639
+236, 0.077382, 0.078639
+237, 0.077382, 0.078639
+238, 0.077382, 0.078639
+239, 0.077382, 0.078639
+240, 0.077382, 0.078639
+241, 0.077382, 0.078639
+242, 0.077382, 0.078639
+243, 0.077382, 0.078639
+244, 0.077382, 0.078639
+245, 0.077382, 0.078639
+246, 0.077382, 0.078639
+247, 0.077382, 0.078639
+248, 0.077382, 0.078639
+249, 0.077382, 0.078639
+250, 0.077382, 0.078639
+251, 0.077382, 0.078639
+252, 0.077382, 0.078639
+253, 0.077382, 0.078639
+254, 0.077382, 0.078639
+255, 0.077382, 0.078639
+256, 0.077382, 0.078639
+257, 0.077382, 0.078639
+258, 0.077382, 0.078639
+259, 0.077382, 0.078639
+260, 0.077382, 0.078639
+261, 0.077382, 0.078639
+262, 0.077382, 0.078639
+263, 0.077382, 0.078639
+264, 0.077382, 0.078639
+265, 0.077382, 0.078639
+266, 0.077382, 0.078639
+267, 0.077382, 0.078639
+268, 0.077382, 0.078639
+269, 0.077382, 0.078639
+270, 0.077382, 0.078639
+271, 0.077382, 0.078639
+272, 0.077382, 0.078639
+273, 0.077382, 0.078639
+274, 0.077382, 0.078639
+275, 0.077382, 0.078639
+276, 0.077382, 0.078639
+277, 0.077382, 0.078639
+278, 0.077382, 0.078639
+279, 0.077382, 0.078639
+280, 0.077382, 0.078639
+281, 0.077382, 0.078639
+282, 0.077382, 0.078639
+1, 0.107054, 0.109363
+2, 0.095789, 0.097876
+3, 0.090508, 0.092148
+4, 0.087590, 0.088927
+5, 0.085521, 0.086741
+6, 0.084280, 0.085431
+7, 0.083406, 0.084504
+8, 0.082772, 0.083805
+9, 0.082204, 0.083247
+10, 0.081678, 0.082771
+11, 0.081268, 0.082301
+12, 0.080904, 0.081968
+13, 0.080724, 0.081766
+14, 0.080442, 0.081502
+15, 0.080174, 0.081228
+16, 0.079994, 0.081023
+17, 0.079753, 0.080801
+18, 0.079578, 0.080634
+19, 0.079432, 0.080512
+20, 0.079271, 0.080309
+21, 0.079122, 0.080194
+22, 0.079044, 0.080105
+23, 0.078923, 0.079973
+24, 0.078793, 0.079894
+25, 0.078695, 0.079780
+26, 0.078608, 0.079694
+27, 0.078494, 0.079601
+28, 0.078417, 0.079530
+29, 0.078361, 0.079450
+30, 0.078333, 0.079394
+31, 0.078235, 0.079327
+32, 0.078153, 0.079252
+33, 0.078107, 0.079232
+34, 0.078064, 0.079163
+35, 0.078004, 0.079139
+36, 0.077960, 0.079076
+37, 0.077932, 0.079059
+38, 0.077874, 0.079005
+39, 0.077841, 0.078978
+40, 0.077795, 0.078931
+41, 0.077764, 0.078925
+42, 0.077733, 0.078916
+43, 0.077707, 0.078873
+44, 0.077685, 0.078852
+45, 0.077660, 0.078848
+46, 0.077632, 0.078837
+47, 0.077619, 0.078815
+48, 0.077599, 0.078788
+49, 0.077581, 0.078782
+50, 0.077557, 0.078758
+51, 0.077544, 0.078751
+52, 0.077522, 0.078734
+53, 0.077510, 0.078726
+54, 0.077499, 0.078728
+55, 0.077487, 0.078702
+56, 0.077474, 0.078712
+57, 0.077465, 0.078715
+58, 0.077457, 0.078715
+59, 0.077445, 0.078696
+60, 0.077437, 0.078695
+61, 0.077429, 0.078679
+62, 0.077426, 0.078690
+63, 0.077418, 0.078677
+64, 0.077412, 0.078690
+65, 0.077403, 0.078668
+66, 0.077400, 0.078670
+67, 0.077396, 0.078664
+68, 0.077391, 0.078665
+69, 0.077385, 0.078659
+70, 0.077380, 0.078658
+71, 0.077376, 0.078658
+72, 0.077374, 0.078661
+73, 0.077371, 0.078655
+74, 0.077368, 0.078656
+75, 0.077364, 0.078651
+76, 0.077361, 0.078648
+77, 0.077359, 0.078647
+78, 0.077356, 0.078647
+79, 0.077351, 0.078638
+80, 0.077349, 0.078634
+81, 0.077346, 0.078634
+82, 0.077344, 0.078633
+83, 0.077345, 0.078639
+84, 0.077343, 0.078638
+85, 0.077342, 0.078642
+86, 0.077339, 0.078636
+87, 0.077338, 0.078637
+88, 0.077337, 0.078637
+89, 0.077335, 0.078632
+90, 0.077334, 0.078630
+91, 0.077332, 0.078628
+92, 0.077331, 0.078627
+93, 0.077330, 0.078627
+94, 0.077328, 0.078623
+95, 0.077327, 0.078619
+96, 0.077327, 0.078623
+97, 0.077327, 0.078625
+98, 0.077326, 0.078626
+99, 0.077326, 0.078625
+100, 0.077325, 0.078622
+101, 0.077324, 0.078623
+102, 0.077324, 0.078622
+103, 0.077323, 0.078622
+104, 0.077323, 0.078622
+105, 0.077322, 0.078622
+106, 0.077321, 0.078619
+107, 0.077320, 0.078616
+108, 0.077319, 0.078615
+109, 0.077319, 0.078616
+110, 0.077319, 0.078615
+111, 0.077318, 0.078614
+112, 0.077319, 0.078616
+113, 0.077318, 0.078615
+114, 0.077318, 0.078617
+115, 0.077319, 0.078618
+116, 0.077319, 0.078618
+117, 0.077318, 0.078617
+118, 0.077318, 0.078617
+119, 0.077318, 0.078617
+120, 0.077317, 0.078616
+121, 0.077317, 0.078617
+122, 0.077317, 0.078618
+123, 0.077318, 0.078618
+124, 0.077318, 0.078619
+125, 0.077317, 0.078619
+126, 0.077317, 0.078619
+127, 0.077317, 0.078618
+128, 0.077317, 0.078618
+129, 0.077317, 0.078618
+130, 0.077317, 0.078618
+131, 0.077317, 0.078618
+132, 0.077317, 0.078617
+133, 0.077317, 0.078617
+134, 0.077316, 0.078617
+135, 0.077316, 0.078617
+136, 0.077316, 0.078617
+137, 0.077316, 0.078616
+138, 0.077316, 0.078616
+139, 0.077316, 0.078616
+140, 0.077316, 0.078616
+141, 0.077316, 0.078616
+142, 0.077316, 0.078615
+143, 0.077316, 0.078615
+144, 0.077316, 0.078615
+145, 0.077316, 0.078615
+146, 0.077316, 0.078615
+147, 0.077316, 0.078615
+148, 0.077316, 0.078615
+149, 0.077316, 0.078615
+150, 0.077316, 0.078615
+151, 0.077315, 0.078615
+152, 0.077315, 0.078615
+153, 0.077315, 0.078615
+154, 0.077315, 0.078615
+155, 0.077315, 0.078615
+156, 0.077315, 0.078615
+157, 0.077315, 0.078615
+158, 0.077315, 0.078615
+159, 0.077315, 0.078615
+1, 0.108645, 0.110902
+2, 0.097215, 0.099030
+3, 0.091263, 0.092792
+4, 0.088060, 0.089313
+5, 0.086003, 0.087071
+6, 0.084676, 0.085638
+7, 0.083821, 0.084719
+8, 0.083102, 0.083924
+9, 0.082514, 0.083343
+10, 0.082124, 0.082861
+11, 0.081586, 0.082425
+12, 0.081260, 0.082115
+13, 0.080916, 0.081760
+14, 0.080611, 0.081422
+15, 0.080433, 0.081247
+16, 0.080208, 0.081032
+17, 0.080056, 0.080846
+18, 0.079824, 0.080675
+19, 0.079619, 0.080466
+20, 0.079563, 0.080365
+21, 0.079408, 0.080246
+22, 0.079267, 0.080076
+23, 0.079120, 0.079969
+24, 0.079023, 0.079840
+25, 0.078940, 0.079775
+26, 0.078815, 0.079648
+27, 0.078760, 0.079581
+28, 0.078676, 0.079495
+29, 0.078605, 0.079448
+30, 0.078492, 0.079332
+31, 0.078412, 0.079296
+32, 0.078362, 0.079227
+33, 0.078317, 0.079200
+34, 0.078244, 0.079147
+35, 0.078228, 0.079104
+36, 0.078162, 0.079045
+37, 0.078107, 0.079005
+38, 0.078047, 0.078963
+39, 0.078025, 0.078911
+40, 0.077986, 0.078901
+41, 0.077959, 0.078886
+42, 0.077921, 0.078858
+43, 0.077886, 0.078826
+44, 0.077849, 0.078798
+45, 0.077820, 0.078793
+46, 0.077805, 0.078768
+47, 0.077782, 0.078746
+48, 0.077759, 0.078739
+49, 0.077742, 0.078724
+50, 0.077717, 0.078697
+51, 0.077710, 0.078685
+52, 0.077692, 0.078671
+53, 0.077666, 0.078661
+54, 0.077662, 0.078661
+55, 0.077645, 0.078655
+56, 0.077640, 0.078639
+57, 0.077625, 0.078633
+58, 0.077610, 0.078614
+59, 0.077602, 0.078613
+60, 0.077597, 0.078604
+61, 0.077585, 0.078593
+62, 0.077575, 0.078597
+63, 0.077566, 0.078592
+64, 0.077563, 0.078593
+65, 0.077556, 0.078583
+66, 0.077552, 0.078584
+67, 0.077546, 0.078584
+68, 0.077539, 0.078566
+69, 0.077531, 0.078566
+70, 0.077528, 0.078561
+71, 0.077520, 0.078549
+72, 0.077516, 0.078549
+73, 0.077514, 0.078551
+74, 0.077510, 0.078550
+75, 0.077506, 0.078551
+76, 0.077503, 0.078544
+77, 0.077501, 0.078549
+78, 0.077498, 0.078546
+79, 0.077495, 0.078537
+80, 0.077493, 0.078541
+81, 0.077491, 0.078534
+82, 0.077488, 0.078536
+83, 0.077485, 0.078529
+84, 0.077483, 0.078526
+85, 0.077481, 0.078524
+86, 0.077480, 0.078528
+87, 0.077477, 0.078526
+88, 0.077476, 0.078521
+89, 0.077475, 0.078524
+90, 0.077473, 0.078523
+91, 0.077472, 0.078522
+92, 0.077471, 0.078519
+93, 0.077469, 0.078519
+94, 0.077468, 0.078517
+95, 0.077467, 0.078516
+96, 0.077466, 0.078516
+97, 0.077465, 0.078516
+98, 0.077464, 0.078514
+99, 0.077464, 0.078514
+100, 0.077463, 0.078512
+101, 0.077462, 0.078514
+102, 0.077461, 0.078513
+103, 0.077460, 0.078513
+104, 0.077460, 0.078512
+105, 0.077460, 0.078513
+106, 0.077459, 0.078512
+107, 0.077459, 0.078512
+108, 0.077458, 0.078510
+109, 0.077458, 0.078511
+110, 0.077457, 0.078510
+111, 0.077457, 0.078508
+112, 0.077456, 0.078508
+113, 0.077456, 0.078507
+114, 0.077456, 0.078506
+115, 0.077455, 0.078507
+116, 0.077455, 0.078507
+117, 0.077455, 0.078507
+118, 0.077455, 0.078506
+119, 0.077455, 0.078507
+120, 0.077454, 0.078506
+121, 0.077454, 0.078506
+122, 0.077454, 0.078507
+123, 0.077454, 0.078506
+124, 0.077454, 0.078506
+125, 0.077454, 0.078506
+126, 0.077454, 0.078506
+127, 0.077454, 0.078506
+128, 0.077454, 0.078505
+129, 0.077453, 0.078505
+130, 0.077453, 0.078505
+131, 0.077453, 0.078505
+132, 0.077453, 0.078504
+133, 0.077453, 0.078504
+134, 0.077453, 0.078504
+135, 0.077453, 0.078504
+136, 0.077453, 0.078504
+137, 0.077453, 0.078504
+138, 0.077453, 0.078504
+139, 0.077453, 0.078504
+140, 0.077453, 0.078504
+141, 0.077453, 0.078504
+142, 0.077453, 0.078504

+ 901 - 0
julia/logs/csv_30_09_2019_14_27_20.csv

@@ -0,0 +1,901 @@
+epoch, loss(train), loss(val)
+1, 0.093080, 0.092508
+2, 0.069031, 0.067629
+3, 0.064291, 0.062943
+4, 0.060827, 0.059568
+5, 0.059301, 0.058460
+6, 0.058672, 0.057920
+7, 0.057834, 0.057255
+8, 0.057435, 0.057099
+9, 0.057113, 0.056812
+10, 0.057030, 0.056849
+11, 0.056916, 0.056893
+12, 0.056653, 0.056813
+13, 0.056223, 0.056521
+14, 0.055907, 0.056257
+15, 0.055811, 0.056153
+16, 0.055996, 0.056253
+17, 0.056509, 0.056749
+18, 0.056736, 0.057002
+19, 0.056825, 0.057148
+20, 0.056349, 0.056709
+21, 0.055339, 0.055721
+22, 0.054080, 0.054463
+23, 0.053393, 0.053672
+24, 0.053121, 0.053326
+25, 0.053043, 0.053181
+26, 0.052858, 0.053029
+27, 0.052826, 0.052986
+28, 0.052841, 0.053040
+29, 0.052777, 0.053036
+30, 0.052711, 0.052963
+31, 0.052688, 0.052891
+32, 0.052576, 0.052782
+33, 0.052667, 0.052730
+34, 0.052779, 0.052696
+35, 0.052854, 0.052653
+36, 0.053212, 0.052754
+37, 0.053448, 0.052824
+38, 0.053491, 0.052787
+39, 0.053333, 0.052663
+40, 0.052837, 0.052362
+41, 0.052389, 0.052117
+42, 0.052066, 0.051959
+43, 0.051788, 0.051844
+44, 0.051640, 0.051785
+45, 0.051530, 0.051748
+46, 0.051493, 0.051737
+47, 0.051452, 0.051726
+48, 0.051433, 0.051714
+49, 0.051401, 0.051703
+50, 0.051384, 0.051694
+51, 0.051362, 0.051680
+52, 0.051325, 0.051665
+53, 0.051259, 0.051651
+54, 0.051197, 0.051644
+55, 0.051136, 0.051634
+56, 0.051068, 0.051633
+57, 0.051019, 0.051637
+58, 0.050977, 0.051658
+59, 0.050942, 0.051691
+60, 0.050919, 0.051711
+61, 0.050904, 0.051738
+62, 0.050891, 0.051758
+63, 0.050875, 0.051761
+64, 0.050858, 0.051750
+65, 0.050837, 0.051725
+66, 0.050814, 0.051685
+67, 0.050799, 0.051681
+68, 0.050780, 0.051648
+69, 0.050765, 0.051627
+70, 0.050754, 0.051615
+71, 0.050742, 0.051595
+72, 0.050732, 0.051581
+73, 0.050722, 0.051563
+74, 0.050714, 0.051547
+75, 0.050708, 0.051543
+76, 0.050701, 0.051528
+77, 0.050696, 0.051524
+78, 0.050690, 0.051518
+79, 0.050685, 0.051510
+80, 0.050680, 0.051509
+81, 0.050676, 0.051503
+82, 0.050673, 0.051498
+83, 0.050669, 0.051496
+84, 0.050666, 0.051490
+85, 0.050663, 0.051489
+86, 0.050660, 0.051486
+87, 0.050657, 0.051482
+88, 0.050655, 0.051479
+89, 0.050653, 0.051477
+90, 0.050651, 0.051476
+91, 0.050649, 0.051473
+92, 0.050647, 0.051470
+93, 0.050646, 0.051464
+94, 0.050644, 0.051465
+95, 0.050643, 0.051466
+96, 0.050641, 0.051465
+97, 0.050640, 0.051461
+98, 0.050639, 0.051463
+99, 0.050638, 0.051463
+100, 0.050637, 0.051460
+1, 0.085145, 0.084277
+2, 0.068091, 0.066436
+3, 0.062043, 0.061092
+4, 0.059993, 0.059272
+5, 0.058545, 0.058204
+6, 0.057621, 0.057397
+7, 0.057388, 0.057294
+8, 0.057485, 0.057341
+9, 0.057354, 0.057369
+10, 0.056581, 0.056680
+11, 0.056511, 0.056548
+12, 0.056471, 0.056751
+13, 0.056514, 0.056947
+14, 0.056266, 0.056668
+15, 0.056044, 0.056443
+16, 0.056162, 0.056465
+17, 0.056294, 0.056613
+18, 0.056623, 0.056966
+19, 0.056799, 0.057218
+20, 0.056388, 0.056934
+21, 0.055646, 0.056139
+22, 0.054702, 0.055054
+23, 0.054107, 0.054288
+24, 0.053836, 0.053849
+25, 0.053429, 0.053493
+26, 0.053345, 0.053398
+27, 0.053229, 0.053307
+28, 0.053138, 0.053215
+29, 0.052939, 0.053058
+30, 0.052790, 0.052942
+31, 0.052683, 0.052816
+32, 0.052602, 0.052753
+33, 0.052579, 0.052674
+34, 0.052610, 0.052597
+35, 0.052611, 0.052530
+36, 0.052680, 0.052476
+37, 0.052791, 0.052449
+38, 0.052758, 0.052363
+39, 0.052682, 0.052269
+40, 0.052525, 0.052156
+41, 0.052267, 0.051996
+42, 0.051986, 0.051854
+43, 0.051762, 0.051751
+44, 0.051592, 0.051681
+45, 0.051479, 0.051643
+46, 0.051394, 0.051616
+47, 0.051367, 0.051600
+48, 0.051341, 0.051579
+49, 0.051304, 0.051564
+50, 0.051285, 0.051563
+51, 0.051286, 0.051553
+52, 0.051247, 0.051551
+53, 0.051221, 0.051543
+54, 0.051172, 0.051541
+55, 0.051131, 0.051537
+56, 0.051072, 0.051525
+57, 0.051019, 0.051529
+58, 0.050963, 0.051544
+59, 0.050920, 0.051560
+60, 0.050894, 0.051591
+61, 0.050878, 0.051636
+62, 0.050867, 0.051668
+63, 0.050860, 0.051702
+64, 0.050847, 0.051702
+65, 0.050832, 0.051699
+66, 0.050821, 0.051700
+67, 0.050801, 0.051675
+68, 0.050779, 0.051646
+69, 0.050759, 0.051619
+70, 0.050744, 0.051600
+71, 0.050733, 0.051590
+72, 0.050716, 0.051555
+73, 0.050704, 0.051538
+74, 0.050693, 0.051523
+75, 0.050684, 0.051510
+76, 0.050677, 0.051499
+77, 0.050668, 0.051481
+78, 0.050662, 0.051477
+79, 0.050656, 0.051464
+80, 0.050651, 0.051460
+81, 0.050647, 0.051460
+82, 0.050642, 0.051450
+83, 0.050638, 0.051445
+84, 0.050634, 0.051439
+85, 0.050631, 0.051434
+86, 0.050628, 0.051434
+87, 0.050625, 0.051429
+88, 0.050622, 0.051431
+89, 0.050619, 0.051418
+90, 0.050617, 0.051419
+91, 0.050615, 0.051416
+92, 0.050613, 0.051413
+93, 0.050611, 0.051410
+94, 0.050610, 0.051410
+95, 0.050608, 0.051405
+96, 0.050606, 0.051401
+97, 0.050605, 0.051403
+98, 0.050604, 0.051404
+99, 0.050603, 0.051399
+100, 0.050602, 0.051401
+1, 0.085466, 0.083448
+2, 0.067009, 0.065906
+3, 0.063191, 0.062418
+4, 0.059964, 0.059266
+5, 0.059229, 0.058537
+6, 0.059260, 0.058677
+7, 0.059613, 0.058838
+8, 0.058372, 0.057957
+9, 0.058023, 0.057690
+10, 0.058341, 0.057856
+11, 0.058291, 0.057867
+12, 0.057441, 0.057287
+13, 0.056272, 0.056194
+14, 0.055851, 0.055663
+15, 0.055405, 0.055219
+16, 0.055548, 0.055248
+17, 0.055654, 0.055321
+18, 0.055723, 0.055456
+19, 0.055744, 0.055502
+20, 0.055564, 0.055416
+21, 0.055276, 0.055244
+22, 0.054920, 0.054917
+23, 0.054450, 0.054397
+24, 0.054105, 0.053996
+25, 0.053674, 0.053549
+26, 0.053361, 0.053270
+27, 0.053233, 0.053125
+28, 0.053071, 0.053007
+29, 0.052948, 0.052935
+30, 0.052997, 0.052941
+31, 0.053064, 0.052970
+32, 0.053172, 0.052973
+33, 0.053340, 0.053012
+34, 0.053407, 0.053008
+35, 0.053488, 0.053011
+36, 0.053523, 0.052991
+37, 0.053434, 0.052903
+38, 0.053004, 0.052646
+39, 0.052548, 0.052387
+40, 0.052184, 0.052197
+41, 0.051921, 0.052086
+42, 0.051787, 0.052001
+43, 0.051664, 0.051921
+44, 0.051557, 0.051856
+45, 0.051499, 0.051807
+46, 0.051440, 0.051767
+47, 0.051405, 0.051744
+48, 0.051368, 0.051721
+49, 0.051326, 0.051705
+50, 0.051288, 0.051689
+51, 0.051239, 0.051667
+52, 0.051180, 0.051656
+53, 0.051117, 0.051658
+54, 0.051078, 0.051665
+55, 0.051036, 0.051678
+56, 0.051011, 0.051702
+57, 0.050990, 0.051737
+58, 0.050977, 0.051756
+59, 0.050971, 0.051791
+60, 0.050955, 0.051786
+61, 0.050941, 0.051792
+62, 0.050929, 0.051794
+63, 0.050904, 0.051764
+64, 0.050879, 0.051731
+65, 0.050859, 0.051707
+66, 0.050838, 0.051671
+67, 0.050822, 0.051655
+68, 0.050804, 0.051619
+69, 0.050792, 0.051603
+70, 0.050781, 0.051588
+71, 0.050770, 0.051567
+72, 0.050762, 0.051553
+73, 0.050755, 0.051545
+74, 0.050748, 0.051538
+75, 0.050742, 0.051527
+76, 0.050736, 0.051523
+77, 0.050731, 0.051517
+78, 0.050726, 0.051506
+79, 0.050722, 0.051507
+80, 0.050717, 0.051499
+81, 0.050713, 0.051492
+82, 0.050709, 0.051488
+83, 0.050706, 0.051491
+84, 0.050703, 0.051484
+85, 0.050700, 0.051476
+86, 0.050698, 0.051476
+87, 0.050695, 0.051471
+88, 0.050693, 0.051474
+89, 0.050691, 0.051469
+90, 0.050689, 0.051463
+91, 0.050687, 0.051464
+92, 0.050685, 0.051462
+93, 0.050683, 0.051460
+94, 0.050682, 0.051455
+95, 0.050681, 0.051457
+96, 0.050679, 0.051455
+97, 0.050678, 0.051454
+98, 0.050677, 0.051455
+99, 0.050676, 0.051454
+100, 0.050675, 0.051452
+1, 0.086237, 0.086168
+2, 0.066817, 0.065911
+3, 0.063177, 0.062407
+4, 0.061026, 0.060297
+5, 0.059943, 0.059473
+6, 0.058618, 0.058114
+7, 0.057991, 0.057816
+8, 0.057960, 0.057804
+9, 0.058586, 0.058320
+10, 0.058809, 0.058750
+11, 0.057933, 0.058105
+12, 0.057471, 0.057670
+13, 0.057318, 0.057520
+14, 0.057432, 0.057578
+15, 0.057712, 0.057838
+16, 0.058157, 0.058160
+17, 0.058045, 0.058048
+18, 0.057258, 0.057315
+19, 0.056103, 0.056101
+20, 0.055167, 0.055090
+21, 0.054440, 0.054323
+22, 0.053996, 0.053912
+23, 0.053813, 0.053733
+24, 0.053584, 0.053587
+25, 0.053363, 0.053465
+26, 0.053242, 0.053413
+27, 0.053028, 0.053261
+28, 0.052812, 0.053128
+29, 0.052652, 0.052984
+30, 0.052535, 0.052863
+31, 0.052439, 0.052725
+32, 0.052366, 0.052586
+33, 0.052277, 0.052462
+34, 0.052236, 0.052378
+35, 0.052206, 0.052301
+36, 0.052131, 0.052229
+37, 0.052080, 0.052175
+38, 0.051932, 0.052086
+39, 0.051834, 0.052032
+40, 0.051742, 0.051984
+41, 0.051577, 0.051924
+42, 0.051501, 0.051901
+43, 0.051449, 0.051876
+44, 0.051393, 0.051869
+45, 0.051368, 0.051851
+46, 0.051376, 0.051837
+47, 0.051365, 0.051807
+48, 0.051349, 0.051793
+49, 0.051350, 0.051774
+50, 0.051308, 0.051759
+51, 0.051285, 0.051734
+52, 0.051267, 0.051716
+53, 0.051197, 0.051707
+54, 0.051160, 0.051691
+55, 0.051111, 0.051690
+56, 0.051065, 0.051692
+57, 0.051019, 0.051708
+58, 0.050985, 0.051736
+59, 0.050964, 0.051761
+60, 0.050948, 0.051782
+61, 0.050943, 0.051836
+62, 0.050930, 0.051840
+63, 0.050921, 0.051851
+64, 0.050902, 0.051832
+65, 0.050885, 0.051809
+66, 0.050869, 0.051790
+67, 0.050854, 0.051774
+68, 0.050836, 0.051741
+69, 0.050824, 0.051727
+70, 0.050812, 0.051704
+71, 0.050800, 0.051679
+72, 0.050792, 0.051671
+73, 0.050785, 0.051665
+74, 0.050776, 0.051649
+75, 0.050770, 0.051641
+76, 0.050764, 0.051627
+77, 0.050759, 0.051624
+78, 0.050753, 0.051614
+79, 0.050748, 0.051609
+80, 0.050744, 0.051604
+81, 0.050740, 0.051599
+82, 0.050736, 0.051592
+83, 0.050733, 0.051590
+84, 0.050730, 0.051590
+85, 0.050727, 0.051587
+86, 0.050724, 0.051580
+87, 0.050721, 0.051575
+88, 0.050719, 0.051574
+89, 0.050717, 0.051573
+90, 0.050715, 0.051568
+91, 0.050713, 0.051565
+92, 0.050712, 0.051564
+93, 0.050710, 0.051562
+94, 0.050709, 0.051560
+95, 0.050707, 0.051559
+96, 0.050706, 0.051555
+97, 0.050705, 0.051552
+98, 0.050704, 0.051554
+99, 0.050703, 0.051554
+100, 0.050702, 0.051551
+1, 0.089826, 0.087610
+2, 0.067577, 0.066210
+3, 0.064038, 0.063006
+4, 0.060244, 0.059602
+5, 0.059227, 0.058822
+6, 0.058737, 0.058792
+7, 0.058215, 0.058426
+8, 0.057274, 0.057502
+9, 0.057132, 0.057426
+10, 0.056904, 0.057230
+11, 0.057148, 0.057484
+12, 0.057290, 0.057630
+13, 0.057313, 0.057586
+14, 0.056691, 0.056890
+15, 0.055783, 0.055999
+16, 0.055334, 0.055583
+17, 0.055496, 0.055625
+18, 0.055848, 0.055966
+19, 0.056469, 0.056572
+20, 0.057220, 0.057206
+21, 0.057383, 0.057452
+22, 0.056780, 0.056885
+23, 0.055630, 0.055793
+24, 0.054334, 0.054489
+25, 0.053592, 0.053724
+26, 0.053303, 0.053389
+27, 0.053062, 0.053169
+28, 0.053093, 0.053166
+29, 0.053281, 0.053265
+30, 0.053359, 0.053331
+31, 0.053417, 0.053345
+32, 0.053442, 0.053321
+33, 0.053280, 0.053169
+34, 0.053042, 0.052970
+35, 0.052677, 0.052694
+36, 0.052356, 0.052496
+37, 0.052130, 0.052343
+38, 0.051967, 0.052270
+39, 0.051858, 0.052225
+40, 0.051766, 0.052186
+41, 0.051688, 0.052134
+42, 0.051594, 0.052048
+43, 0.051490, 0.051962
+44, 0.051394, 0.051891
+45, 0.051314, 0.051834
+46, 0.051240, 0.051802
+47, 0.051188, 0.051788
+48, 0.051140, 0.051788
+49, 0.051096, 0.051787
+50, 0.051063, 0.051781
+51, 0.051026, 0.051795
+52, 0.050999, 0.051804
+53, 0.050980, 0.051816
+54, 0.050963, 0.051823
+55, 0.050948, 0.051837
+56, 0.050931, 0.051833
+57, 0.050918, 0.051838
+58, 0.050899, 0.051821
+59, 0.050875, 0.051788
+60, 0.050850, 0.051753
+61, 0.050831, 0.051731
+62, 0.050811, 0.051693
+63, 0.050796, 0.051672
+64, 0.050784, 0.051655
+65, 0.050771, 0.051625
+66, 0.050760, 0.051608
+67, 0.050751, 0.051598
+68, 0.050744, 0.051597
+69, 0.050736, 0.051580
+70, 0.050730, 0.051581
+71, 0.050723, 0.051565
+72, 0.050717, 0.051560
+73, 0.050711, 0.051549
+74, 0.050706, 0.051550
+75, 0.050702, 0.051542
+76, 0.050696, 0.051532
+77, 0.050693, 0.051534
+78, 0.050688, 0.051525
+79, 0.050684, 0.051525
+80, 0.050681, 0.051526
+81, 0.050677, 0.051521
+82, 0.050675, 0.051520
+83, 0.050671, 0.051510
+84, 0.050668, 0.051509
+85, 0.050666, 0.051507
+86, 0.050664, 0.051506
+87, 0.050661, 0.051503
+88, 0.050659, 0.051504
+89, 0.050657, 0.051499
+90, 0.050655, 0.051496
+91, 0.050654, 0.051497
+92, 0.050652, 0.051498
+93, 0.050650, 0.051495
+94, 0.050649, 0.051495
+95, 0.050648, 0.051491
+96, 0.050647, 0.051491
+97, 0.050646, 0.051491
+98, 0.050645, 0.051490
+99, 0.050644, 0.051491
+100, 0.050643, 0.051489
+1, 0.085300, 0.083685
+2, 0.066953, 0.065985
+3, 0.064071, 0.063177
+4, 0.061052, 0.060448
+5, 0.059383, 0.059186
+6, 0.058582, 0.058385
+7, 0.057840, 0.057679
+8, 0.057490, 0.057312
+9, 0.057308, 0.057126
+10, 0.056718, 0.056649
+11, 0.056284, 0.056397
+12, 0.055857, 0.056005
+13, 0.055451, 0.055661
+14, 0.055363, 0.055531
+15, 0.055445, 0.055545
+16, 0.055360, 0.055467
+17, 0.055204, 0.055398
+18, 0.054983, 0.055307
+19, 0.054601, 0.055000
+20, 0.054591, 0.054917
+21, 0.054396, 0.054738
+22, 0.054501, 0.054852
+23, 0.054861, 0.055244
+24, 0.055324, 0.055727
+25, 0.055759, 0.056135
+26, 0.056071, 0.056407
+27, 0.055936, 0.056284
+28, 0.055192, 0.055479
+29, 0.054194, 0.054437
+30, 0.053646, 0.053798
+31, 0.053466, 0.053572
+32, 0.053537, 0.053568
+33, 0.053592, 0.053585
+34, 0.053791, 0.053701
+35, 0.053868, 0.053710
+36, 0.053803, 0.053639
+37, 0.053587, 0.053460
+38, 0.053151, 0.053148
+39, 0.052732, 0.052863
+40, 0.052385, 0.052624
+41, 0.052123, 0.052437
+42, 0.051956, 0.052307
+43, 0.051858, 0.052221
+44, 0.051767, 0.052147
+45, 0.051678, 0.052093
+46, 0.051649, 0.052045
+47, 0.051587, 0.051998
+48, 0.051510, 0.051950
+49, 0.051464, 0.051920
+50, 0.051407, 0.051894
+51, 0.051346, 0.051874
+52, 0.051286, 0.051866
+53, 0.051240, 0.051856
+54, 0.051194, 0.051873
+55, 0.051154, 0.051884
+56, 0.051128, 0.051895
+57, 0.051107, 0.051928
+58, 0.051096, 0.051963
+59, 0.051089, 0.051990
+60, 0.051084, 0.052012
+61, 0.051071, 0.052018
+62, 0.051056, 0.052011
+63, 0.051039, 0.052001
+64, 0.051017, 0.051979
+65, 0.050996, 0.051954
+66, 0.050975, 0.051927
+67, 0.050955, 0.051898
+68, 0.050940, 0.051876
+69, 0.050923, 0.051856
+70, 0.050910, 0.051839
+71, 0.050899, 0.051830
+72, 0.050885, 0.051802
+73, 0.050876, 0.051789
+74, 0.050868, 0.051780
+75, 0.050859, 0.051767
+76, 0.050852, 0.051755
+77, 0.050847, 0.051750
+78, 0.050841, 0.051743
+79, 0.050836, 0.051736
+80, 0.050831, 0.051728
+81, 0.050826, 0.051721
+82, 0.050822, 0.051717
+83, 0.050818, 0.051712
+84, 0.050814, 0.051704
+85, 0.050811, 0.051707
+86, 0.050808, 0.051702
+87, 0.050805, 0.051700
+88, 0.050802, 0.051695
+89, 0.050800, 0.051694
+90, 0.050797, 0.051688
+91, 0.050796, 0.051688
+92, 0.050794, 0.051688
+93, 0.050792, 0.051685
+94, 0.050790, 0.051679
+95, 0.050788, 0.051678
+96, 0.050787, 0.051676
+97, 0.050786, 0.051680
+98, 0.050784, 0.051672
+99, 0.050783, 0.051673
+100, 0.050782, 0.051673
+1, 0.083241, 0.081338
+2, 0.068011, 0.066275
+3, 0.064500, 0.062939
+4, 0.062763, 0.061977
+5, 0.060735, 0.060340
+6, 0.059243, 0.058967
+7, 0.058659, 0.058494
+8, 0.058254, 0.058243
+9, 0.058391, 0.058417
+10, 0.058190, 0.058318
+11, 0.057913, 0.058267
+12, 0.057026, 0.057716
+13, 0.056899, 0.057677
+14, 0.056948, 0.057710
+15, 0.056834, 0.057578
+16, 0.056879, 0.057601
+17, 0.056644, 0.057316
+18, 0.056123, 0.056696
+19, 0.055539, 0.055993
+20, 0.054817, 0.055192
+21, 0.054251, 0.054556
+22, 0.053735, 0.054037
+23, 0.053590, 0.053807
+24, 0.053532, 0.053687
+25, 0.053535, 0.053628
+26, 0.053524, 0.053611
+27, 0.053373, 0.053523
+28, 0.053050, 0.053344
+29, 0.052943, 0.053259
+30, 0.052761, 0.053106
+31, 0.052696, 0.053025
+32, 0.052689, 0.052930
+33, 0.052740, 0.052846
+34, 0.052706, 0.052756
+35, 0.052765, 0.052704
+36, 0.052756, 0.052639
+37, 0.052711, 0.052555
+38, 0.052549, 0.052426
+39, 0.052322, 0.052297
+40, 0.052060, 0.052150
+41, 0.051793, 0.052026
+42, 0.051636, 0.051965
+43, 0.051514, 0.051931
+44, 0.051438, 0.051905
+45, 0.051403, 0.051888
+46, 0.051358, 0.051865
+47, 0.051337, 0.051848
+48, 0.051338, 0.051840
+49, 0.051314, 0.051821
+50, 0.051277, 0.051795
+51, 0.051270, 0.051777
+52, 0.051233, 0.051768
+53, 0.051212, 0.051756
+54, 0.051174, 0.051745
+55, 0.051122, 0.051735
+56, 0.051073, 0.051735
+57, 0.051029, 0.051744
+58, 0.051000, 0.051749
+59, 0.050973, 0.051769
+60, 0.050952, 0.051795
+61, 0.050937, 0.051807
+62, 0.050928, 0.051828
+63, 0.050916, 0.051835
+64, 0.050908, 0.051846
+65, 0.050891, 0.051827
+66, 0.050875, 0.051813
+67, 0.050859, 0.051792
+68, 0.050848, 0.051785
+69, 0.050833, 0.051761
+70, 0.050818, 0.051735
+71, 0.050805, 0.051714
+72, 0.050798, 0.051715
+73, 0.050788, 0.051700
+74, 0.050779, 0.051684
+75, 0.050772, 0.051674
+76, 0.050765, 0.051667
+77, 0.050759, 0.051653
+78, 0.050753, 0.051646
+79, 0.050748, 0.051638
+80, 0.050743, 0.051630
+81, 0.050740, 0.051629
+82, 0.050735, 0.051620
+83, 0.050732, 0.051618
+84, 0.050728, 0.051612
+85, 0.050725, 0.051609
+86, 0.050722, 0.051603
+87, 0.050719, 0.051599
+88, 0.050716, 0.051596
+89, 0.050714, 0.051596
+90, 0.050711, 0.051589
+91, 0.050710, 0.051587
+92, 0.050708, 0.051584
+93, 0.050706, 0.051585
+94, 0.050705, 0.051585
+95, 0.050703, 0.051586
+96, 0.050702, 0.051580
+97, 0.050700, 0.051578
+98, 0.050699, 0.051579
+99, 0.050698, 0.051577
+100, 0.050697, 0.051575
+1, 0.086009, 0.084843
+2, 0.068264, 0.066110
+3, 0.064122, 0.062628
+4, 0.060438, 0.059920
+5, 0.059801, 0.059508
+6, 0.059259, 0.058924
+7, 0.058629, 0.058101
+8, 0.058048, 0.057791
+9, 0.058454, 0.058416
+10, 0.058675, 0.058777
+11, 0.058370, 0.058430
+12, 0.057999, 0.058021
+13, 0.057656, 0.057744
+14, 0.057686, 0.057843
+15, 0.058182, 0.058384
+16, 0.058460, 0.058770
+17, 0.058416, 0.058736
+18, 0.057461, 0.057750
+19, 0.056130, 0.056310
+20, 0.054899, 0.055004
+21, 0.054311, 0.054304
+22, 0.054011, 0.053956
+23, 0.053804, 0.053789
+24, 0.053912, 0.053940
+25, 0.053980, 0.054102
+26, 0.054036, 0.054221
+27, 0.054032, 0.054174
+28, 0.053859, 0.053952
+29, 0.053869, 0.053855
+30, 0.053897, 0.053789
+31, 0.053977, 0.053684
+32, 0.054146, 0.053690
+33, 0.054114, 0.053585
+34, 0.053837, 0.053342
+35, 0.053427, 0.053079
+36, 0.052834, 0.052732
+37, 0.052377, 0.052473
+38, 0.052059, 0.052323
+39, 0.051822, 0.052194
+40, 0.051687, 0.052090
+41, 0.051599, 0.052035
+42, 0.051543, 0.052002
+43, 0.051492, 0.051979
+44, 0.051441, 0.051964
+45, 0.051421, 0.051940
+46, 0.051367, 0.051917
+47, 0.051326, 0.051903
+48, 0.051282, 0.051888
+49, 0.051247, 0.051872
+50, 0.051210, 0.051871
+51, 0.051175, 0.051883
+52, 0.051149, 0.051886
+53, 0.051129, 0.051913
+54, 0.051116, 0.051936
+55, 0.051102, 0.051941
+56, 0.051099, 0.051973
+57, 0.051085, 0.051980
+58, 0.051069, 0.051975
+59, 0.051041, 0.051938
+60, 0.051020, 0.051919
+61, 0.050994, 0.051884
+62, 0.050970, 0.051851
+63, 0.050952, 0.051824
+64, 0.050932, 0.051791
+65, 0.050915, 0.051762
+66, 0.050900, 0.051739
+67, 0.050888, 0.051720
+68, 0.050880, 0.051714
+69, 0.050870, 0.051703
+70, 0.050862, 0.051696
+71, 0.050854, 0.051680
+72, 0.050847, 0.051672
+73, 0.050842, 0.051672
+74, 0.050836, 0.051663
+75, 0.050830, 0.051650
+76, 0.050825, 0.051648
+77, 0.050820, 0.051643
+78, 0.050817, 0.051644
+79, 0.050812, 0.051636
+80, 0.050809, 0.051635
+81, 0.050805, 0.051629
+82, 0.050801, 0.051625
+83, 0.050798, 0.051623
+84, 0.050795, 0.051622
+85, 0.050792, 0.051617
+86, 0.050790, 0.051615
+87, 0.050787, 0.051613
+88, 0.050785, 0.051612
+89, 0.050783, 0.051612
+90, 0.050781, 0.051609
+91, 0.050779, 0.051608
+92, 0.050778, 0.051606
+93, 0.050776, 0.051605
+94, 0.050775, 0.051604
+95, 0.050774, 0.051602
+96, 0.050772, 0.051599
+97, 0.050771, 0.051599
+98, 0.050770, 0.051600
+99, 0.050769, 0.051597
+100, 0.050768, 0.051596
+1, 0.084326, 0.082111
+2, 0.067675, 0.066096
+3, 0.063037, 0.061884
+4, 0.060235, 0.059597
+5, 0.059429, 0.059154
+6, 0.059058, 0.058983
+7, 0.058302, 0.058147
+8, 0.058073, 0.057841
+9, 0.057751, 0.057718
+10, 0.057868, 0.057935
+11, 0.057844, 0.058059
+12, 0.057605, 0.057729
+13, 0.056757, 0.056798
+14, 0.056279, 0.056278
+15, 0.056084, 0.056146
+16, 0.056607, 0.056665
+17, 0.057447, 0.057562
+18, 0.057931, 0.058062
+19, 0.057932, 0.058026
+20, 0.056523, 0.056666
+21, 0.054813, 0.054965
+22, 0.053830, 0.054018
+23, 0.053511, 0.053685
+24, 0.053198, 0.053462
+25, 0.053054, 0.053336
+26, 0.052948, 0.053279
+27, 0.052850, 0.053252
+28, 0.052809, 0.053145
+29, 0.052700, 0.053007
+30, 0.052565, 0.052855
+31, 0.052525, 0.052728
+32, 0.052521, 0.052635
+33, 0.052542, 0.052554
+34, 0.052591, 0.052510
+35, 0.052629, 0.052478
+36, 0.052609, 0.052442
+37, 0.052505, 0.052344
+38, 0.052283, 0.052196
+39, 0.052129, 0.052099
+40, 0.051865, 0.051973
+41, 0.051727, 0.051912
+42, 0.051614, 0.051869
+43, 0.051569, 0.051843
+44, 0.051505, 0.051823
+45, 0.051464, 0.051800
+46, 0.051440, 0.051774
+47, 0.051418, 0.051756
+48, 0.051364, 0.051738
+49, 0.051345, 0.051721
+50, 0.051294, 0.051708
+51, 0.051244, 0.051699
+52, 0.051217, 0.051687
+53, 0.051168, 0.051685
+54, 0.051129, 0.051696
+55, 0.051096, 0.051717
+56, 0.051069, 0.051752
+57, 0.051054, 0.051791
+58, 0.051046, 0.051823
+59, 0.051033, 0.051830
+60, 0.051030, 0.051859
+61, 0.051019, 0.051869
+62, 0.051008, 0.051871
+63, 0.050986, 0.051852
+64, 0.050960, 0.051816
+65, 0.050938, 0.051782
+66, 0.050921, 0.051765
+67, 0.050905, 0.051737
+68, 0.050893, 0.051723
+69, 0.050879, 0.051702
+70, 0.050866, 0.051684
+71, 0.050855, 0.051657
+72, 0.050848, 0.051651
+73, 0.050842, 0.051645
+74, 0.050834, 0.051638
+75, 0.050828, 0.051627
+76, 0.050821, 0.051613
+77, 0.050817, 0.051616
+78, 0.050811, 0.051602
+79, 0.050808, 0.051602
+80, 0.050804, 0.051598
+81, 0.050800, 0.051593
+82, 0.050796, 0.051591
+83, 0.050792, 0.051581
+84, 0.050789, 0.051579
+85, 0.050786, 0.051579
+86, 0.050783, 0.051572
+87, 0.050781, 0.051570
+88, 0.050779, 0.051571
+89, 0.050777, 0.051571
+90, 0.050774, 0.051563
+91, 0.050773, 0.051561
+92, 0.050771, 0.051558
+93, 0.050769, 0.051557
+94, 0.050767, 0.051552
+95, 0.050766, 0.051551
+96, 0.050765, 0.051556
+97, 0.050764, 0.051553
+98, 0.050763, 0.051555
+99, 0.050762, 0.051552
+100, 0.050761, 0.051550

+ 2 - 0
julia/logs/log_29_09_2019.log

@@ -646,3 +646,5 @@ Configuration learning_rate=0.1, decay_step=20
 [13:48:43] Epoch 137: Loss(train): 0.077453 Loss(val): 0.078504
 [13:52:31] Epoch 138: Loss(train): 0.077453 Loss(val): 0.078504
 [13:56:19] Epoch 139: Loss(train): 0.077453 Loss(val): 0.078504
+[13:59:54] Epoch 140: Loss(train): 0.077453 Loss(val): 0.078504
+[14:03:34] Epoch 141: Loss(train): 0.077453 Loss(val): 0.078504

+ 939 - 0
julia/logs/log_30_09_2019.log

@@ -0,0 +1,939 @@
+
+--------[30_09_2019 14:27:20]--------
+second stage Hyperparameter Tuning with 1 net, reevaluation with fixed epochs now, using testset
+
+Configuration learning_rate=0.03, decay_step=20
+[14:29:16] INIT Loss(test): 0.191895 Accuarcy: 0.061824
+[14:31:42] Epoch   1: Loss(train): 0.093080 Loss(val): 0.092508 acc(val): 0.274541
+[14:32:12] Epoch   2: Loss(train): 0.069031 Loss(val): 0.067629 acc(val): 0.436054
+[14:32:32] Epoch   3: Loss(train): 0.064291 Loss(val): 0.062943 acc(val): 0.508061
+[14:32:52] Epoch   4: Loss(train): 0.060827 Loss(val): 0.059568 acc(val): 0.543418
+[14:33:29] Epoch   5: Loss(train): 0.059301 Loss(val): 0.058460 acc(val): 0.555391
+[14:33:58] Epoch   6: Loss(train): 0.058672 Loss(val): 0.057920 acc(val): 0.556820
+[14:34:30] Epoch   7: Loss(train): 0.057834 Loss(val): 0.057255 acc(val): 0.570561
+[14:34:56] Epoch   8: Loss(train): 0.057435 Loss(val): 0.057099 acc(val): 0.570017
+[14:35:21] Epoch   9: Loss(train): 0.057113 Loss(val): 0.056812 acc(val): 0.573146
+[14:35:39] Epoch  10: Loss(train): 0.057030 Loss(val): 0.056849 acc(val): 0.571531
+[14:35:57] Epoch  11: Loss(train): 0.056916 Loss(val): 0.056893 acc(val): 0.572823
+[14:36:15] Epoch  12: Loss(train): 0.056653 Loss(val): 0.056813 acc(val): 0.571803
+[14:36:34] Epoch  13: Loss(train): 0.056223 Loss(val): 0.056521 acc(val): 0.577925
+[14:36:52] Epoch  14: Loss(train): 0.055907 Loss(val): 0.056257 acc(val): 0.581054
+[14:37:10] Epoch  15: Loss(train): 0.055811 Loss(val): 0.056153 acc(val): 0.581939
+[14:37:29] Epoch  16: Loss(train): 0.055996 Loss(val): 0.056253 acc(val): 0.577585
+[14:37:48] Epoch  17: Loss(train): 0.056509 Loss(val): 0.056749 acc(val): 0.566701
+[14:38:09] Epoch  18: Loss(train): 0.056736 Loss(val): 0.057002 acc(val): 0.561259
+[14:38:28] Epoch  19: Loss(train): 0.056825 Loss(val): 0.057148 acc(val): 0.557993
+[14:38:47] Epoch  20: Loss(train): 0.056349 Loss(val): 0.056709 acc(val): 0.564524
+[14:39:06] Epoch  21: Loss(train): 0.055339 Loss(val): 0.055721 acc(val): 0.583095
+[14:39:25] Epoch  22: Loss(train): 0.054080 Loss(val): 0.054463 acc(val): 0.616633
+[14:39:43] Epoch  23: Loss(train): 0.053393 Loss(val): 0.053672 acc(val): 0.634405
+[14:40:01] Epoch  24: Loss(train): 0.053121 Loss(val): 0.053326 acc(val): 0.641888
+[14:40:21] Epoch  25: Loss(train): 0.053043 Loss(val): 0.053181 acc(val): 0.640799
+[14:40:45] Epoch  26: Loss(train): 0.052858 Loss(val): 0.053029 acc(val): 0.641956
+[14:41:04] Epoch  27: Loss(train): 0.052826 Loss(val): 0.052986 acc(val): 0.641003
+[14:41:23] Epoch  28: Loss(train): 0.052841 Loss(val): 0.053040 acc(val): 0.639337
+[14:41:42] Epoch  29: Loss(train): 0.052777 Loss(val): 0.053036 acc(val): 0.638929
+[14:42:01] Epoch  30: Loss(train): 0.052711 Loss(val): 0.052963 acc(val): 0.639813
+[14:42:20] Epoch  31: Loss(train): 0.052688 Loss(val): 0.052891 acc(val): 0.640765
+[14:42:39] Epoch  32: Loss(train): 0.052576 Loss(val): 0.052782 acc(val): 0.643214
+[14:42:59] Epoch  33: Loss(train): 0.052667 Loss(val): 0.052730 acc(val): 0.642058
+[14:43:17] Epoch  34: Loss(train): 0.052779 Loss(val): 0.052696 acc(val): 0.639490
+[14:43:37] Epoch  35: Loss(train): 0.052854 Loss(val): 0.052653 acc(val): 0.637721
+[14:43:55] Epoch  36: Loss(train): 0.053212 Loss(val): 0.052754 acc(val): 0.630391
+[14:44:14] Epoch  37: Loss(train): 0.053448 Loss(val): 0.052824 acc(val): 0.625561
+[14:44:33] Epoch  38: Loss(train): 0.053491 Loss(val): 0.052787 acc(val): 0.625153
+[14:44:52] Epoch  39: Loss(train): 0.053333 Loss(val): 0.052663 acc(val): 0.629847
+[14:45:11] Epoch  40: Loss(train): 0.052837 Loss(val): 0.052362 acc(val): 0.641480
+[14:45:32] Epoch  41: Loss(train): 0.052389 Loss(val): 0.052117 acc(val): 0.649711
+[14:45:51] Epoch  42: Loss(train): 0.052066 Loss(val): 0.051959 acc(val): 0.657534
+[14:46:10] Epoch  43: Loss(train): 0.051788 Loss(val): 0.051844 acc(val): 0.663503
+[14:46:29] Epoch  44: Loss(train): 0.051640 Loss(val): 0.051785 acc(val): 0.666020
+[14:46:48] Epoch  45: Loss(train): 0.051530 Loss(val): 0.051748 acc(val): 0.668265
+[14:47:07] Epoch  46: Loss(train): 0.051493 Loss(val): 0.051737 acc(val): 0.667857
+[14:47:26] Epoch  47: Loss(train): 0.051452 Loss(val): 0.051726 acc(val): 0.668078
+[14:47:46] Epoch  48: Loss(train): 0.051433 Loss(val): 0.051714 acc(val): 0.668486
+[14:48:05] Epoch  49: Loss(train): 0.051401 Loss(val): 0.051703 acc(val): 0.668690
+[14:48:25] Epoch  50: Loss(train): 0.051384 Loss(val): 0.051694 acc(val): 0.669235
+[14:48:46] Epoch  51: Loss(train): 0.051362 Loss(val): 0.051680 acc(val): 0.669303
+[14:49:05] Epoch  52: Loss(train): 0.051325 Loss(val): 0.051665 acc(val): 0.670527
+[14:49:24] Epoch  53: Loss(train): 0.051259 Loss(val): 0.051651 acc(val): 0.670595
+[14:49:43] Epoch  54: Loss(train): 0.051197 Loss(val): 0.051644 acc(val): 0.670867
+[14:50:02] Epoch  55: Loss(train): 0.051136 Loss(val): 0.051634 acc(val): 0.671276
+[14:50:21] Epoch  56: Loss(train): 0.051068 Loss(val): 0.051633 acc(val): 0.671871
+[14:50:40] Epoch  57: Loss(train): 0.051019 Loss(val): 0.051637 acc(val): 0.674116
+[14:50:59] Epoch  58: Loss(train): 0.050977 Loss(val): 0.051658 acc(val): 0.674456
+[14:51:18] Epoch  59: Loss(train): 0.050942 Loss(val): 0.051691 acc(val): 0.673231
+[14:51:37] Epoch  60: Loss(train): 0.050919 Loss(val): 0.051711 acc(val): 0.673248
+[14:51:56] Epoch  61: Loss(train): 0.050904 Loss(val): 0.051738 acc(val): 0.672704
+[14:52:15] Epoch  62: Loss(train): 0.050891 Loss(val): 0.051758 acc(val): 0.672432
+[14:52:34] Epoch  63: Loss(train): 0.050875 Loss(val): 0.051761 acc(val): 0.672908
+[14:52:53] Epoch  64: Loss(train): 0.050858 Loss(val): 0.051750 acc(val): 0.673248
+[14:53:12] Epoch  65: Loss(train): 0.050837 Loss(val): 0.051725 acc(val): 0.674065
+[14:53:30] Epoch  66: Loss(train): 0.050814 Loss(val): 0.051685 acc(val): 0.674201
+[14:53:49] Epoch  67: Loss(train): 0.050799 Loss(val): 0.051681 acc(val): 0.674133
+[14:54:08] Epoch  68: Loss(train): 0.050780 Loss(val): 0.051648 acc(val): 0.674269
+[14:54:27] Epoch  69: Loss(train): 0.050765 Loss(val): 0.051627 acc(val): 0.674133
+[14:54:46] Epoch  70: Loss(train): 0.050754 Loss(val): 0.051615 acc(val): 0.674133
+[14:55:05] Epoch  71: Loss(train): 0.050742 Loss(val): 0.051595 acc(val): 0.674541
+[14:55:24] Epoch  72: Loss(train): 0.050732 Loss(val): 0.051581 acc(val): 0.674745
+[14:55:42] Epoch  73: Loss(train): 0.050722 Loss(val): 0.051563 acc(val): 0.675561
+[14:56:01] Epoch  74: Loss(train): 0.050714 Loss(val): 0.051547 acc(val): 0.675833
+[14:56:20] Epoch  75: Loss(train): 0.050708 Loss(val): 0.051543 acc(val): 0.675493
+[14:56:38] Epoch  76: Loss(train): 0.050701 Loss(val): 0.051528 acc(val): 0.676446
+[14:56:59] Epoch  77: Loss(train): 0.050696 Loss(val): 0.051524 acc(val): 0.676514
+[14:57:19] Epoch  78: Loss(train): 0.050690 Loss(val): 0.051518 acc(val): 0.676718
+[14:57:39] Epoch  79: Loss(train): 0.050685 Loss(val): 0.051510 acc(val): 0.676990
+[14:57:59] Epoch  80: Loss(train): 0.050680 Loss(val): 0.051509 acc(val): 0.677126
+[14:58:19] Epoch  81: Loss(train): 0.050676 Loss(val): 0.051503 acc(val): 0.677126
+[14:58:39] Epoch  82: Loss(train): 0.050673 Loss(val): 0.051498 acc(val): 0.677398
+[14:58:59] Epoch  83: Loss(train): 0.050669 Loss(val): 0.051496 acc(val): 0.677534
+[14:59:19] Epoch  84: Loss(train): 0.050666 Loss(val): 0.051490 acc(val): 0.677602
+[14:59:40] Epoch  85: Loss(train): 0.050663 Loss(val): 0.051489 acc(val): 0.677330
+[15:00:01] Epoch  86: Loss(train): 0.050660 Loss(val): 0.051486 acc(val): 0.677534
+[15:00:21] Epoch  87: Loss(train): 0.050657 Loss(val): 0.051482 acc(val): 0.677330
+[15:00:41] Epoch  88: Loss(train): 0.050655 Loss(val): 0.051479 acc(val): 0.677602
+[15:01:01] Epoch  89: Loss(train): 0.050653 Loss(val): 0.051477 acc(val): 0.677466
+[15:01:21] Epoch  90: Loss(train): 0.050651 Loss(val): 0.051476 acc(val): 0.677466
+[15:01:41] Epoch  91: Loss(train): 0.050649 Loss(val): 0.051473 acc(val): 0.677534
+[15:02:01] Epoch  92: Loss(train): 0.050647 Loss(val): 0.051470 acc(val): 0.677534
+[15:02:21] Epoch  93: Loss(train): 0.050646 Loss(val): 0.051464 acc(val): 0.677466
+[15:02:41] Epoch  94: Loss(train): 0.050644 Loss(val): 0.051465 acc(val): 0.677534
+[15:03:01] Epoch  95: Loss(train): 0.050643 Loss(val): 0.051466 acc(val): 0.677466
+[15:03:21] Epoch  96: Loss(train): 0.050641 Loss(val): 0.051465 acc(val): 0.677398
+[15:03:42] Epoch  97: Loss(train): 0.050640 Loss(val): 0.051461 acc(val): 0.677330
+[15:04:02] Epoch  98: Loss(train): 0.050639 Loss(val): 0.051463 acc(val): 0.677466
+[15:04:22] Epoch  99: Loss(train): 0.050638 Loss(val): 0.051463 acc(val): 0.677602
+[15:04:43] Epoch 100: Loss(train): 0.050637 Loss(val): 0.051460
+[15:04:46] FINAL(100) Loss(test): 0.051915 Accuarcy: 0.600135
+
+Configuration learning_rate=0.03, decay_step=40
+[15:04:52] INIT Loss(test): 0.133920 Accuarcy: 0.117973
+[15:05:10] Epoch   1: Loss(train): 0.085145 Loss(val): 0.084277 acc(val): 0.303997
+[15:05:31] Epoch   2: Loss(train): 0.068091 Loss(val): 0.066436 acc(val): 0.462330
+[15:05:52] Epoch   3: Loss(train): 0.062043 Loss(val): 0.061092 acc(val): 0.528452
+[15:06:12] Epoch   4: Loss(train): 0.059993 Loss(val): 0.059272 acc(val): 0.556088
+[15:06:32] Epoch   5: Loss(train): 0.058545 Loss(val): 0.058204 acc(val): 0.572500
+[15:06:53] Epoch   6: Loss(train): 0.057621 Loss(val): 0.057397 acc(val): 0.584167
+[15:07:14] Epoch   7: Loss(train): 0.057388 Loss(val): 0.057294 acc(val): 0.581582
+[15:07:35] Epoch   8: Loss(train): 0.057485 Loss(val): 0.057341 acc(val): 0.577262
+[15:07:55] Epoch   9: Loss(train): 0.057354 Loss(val): 0.057369 acc(val): 0.581293
+[15:08:16] Epoch  10: Loss(train): 0.056581 Loss(val): 0.056680 acc(val): 0.596803
+[15:08:36] Epoch  11: Loss(train): 0.056511 Loss(val): 0.056548 acc(val): 0.596735
+[15:08:56] Epoch  12: Loss(train): 0.056471 Loss(val): 0.056751 acc(val): 0.591293
+[15:09:16] Epoch  13: Loss(train): 0.056514 Loss(val): 0.056947 acc(val): 0.584286
+[15:09:35] Epoch  14: Loss(train): 0.056266 Loss(val): 0.056668 acc(val): 0.586871
+[15:09:55] Epoch  15: Loss(train): 0.056044 Loss(val): 0.056443 acc(val): 0.589592
+[15:10:16] Epoch  16: Loss(train): 0.056162 Loss(val): 0.056465 acc(val): 0.584524
+[15:10:36] Epoch  17: Loss(train): 0.056294 Loss(val): 0.056613 acc(val): 0.581003
+[15:10:56] Epoch  18: Loss(train): 0.056623 Loss(val): 0.056966 acc(val): 0.573537
+[15:11:16] Epoch  19: Loss(train): 0.056799 Loss(val): 0.057218 acc(val): 0.571514
+[15:11:37] Epoch  20: Loss(train): 0.056388 Loss(val): 0.056934 acc(val): 0.577432
+[15:11:58] Epoch  21: Loss(train): 0.055646 Loss(val): 0.056139 acc(val): 0.588741
+[15:12:19] Epoch  22: Loss(train): 0.054702 Loss(val): 0.055054 acc(val): 0.609184
+[15:12:39] Epoch  23: Loss(train): 0.054107 Loss(val): 0.054288 acc(val): 0.625357
+[15:12:59] Epoch  24: Loss(train): 0.053836 Loss(val): 0.053849 acc(val): 0.634252
+[15:13:19] Epoch  25: Loss(train): 0.053429 Loss(val): 0.053493 acc(val): 0.643112
+[15:13:40] Epoch  26: Loss(train): 0.053345 Loss(val): 0.053398 acc(val): 0.643912
+[15:14:01] Epoch  27: Loss(train): 0.053229 Loss(val): 0.053307 acc(val): 0.645136
+[15:14:21] Epoch  28: Loss(train): 0.053138 Loss(val): 0.053215 acc(val): 0.644388
+[15:14:42] Epoch  29: Loss(train): 0.052939 Loss(val): 0.053058 acc(val): 0.649422
+[15:15:03] Epoch  30: Loss(train): 0.052790 Loss(val): 0.052942 acc(val): 0.651071
+[15:15:23] Epoch  31: Loss(train): 0.052683 Loss(val): 0.052816 acc(val): 0.653112
+[15:15:44] Epoch  32: Loss(train): 0.052602 Loss(val): 0.052753 acc(val): 0.654065
+[15:16:05] Epoch  33: Loss(train): 0.052579 Loss(val): 0.052674 acc(val): 0.654133
+[15:16:26] Epoch  34: Loss(train): 0.052610 Loss(val): 0.052597 acc(val): 0.655085
+[15:16:47] Epoch  35: Loss(train): 0.052611 Loss(val): 0.052530 acc(val): 0.655357
+[15:17:11] Epoch  36: Loss(train): 0.052680 Loss(val): 0.052476 acc(val): 0.653639
+[15:17:34] Epoch  37: Loss(train): 0.052791 Loss(val): 0.052449 acc(val): 0.653095
+[15:17:58] Epoch  38: Loss(train): 0.052758 Loss(val): 0.052363 acc(val): 0.655340
+[15:18:21] Epoch  39: Loss(train): 0.052682 Loss(val): 0.052269 acc(val): 0.656905
+[15:18:43] Epoch  40: Loss(train): 0.052525 Loss(val): 0.052156 acc(val): 0.661003
+[15:19:03] Epoch  41: Loss(train): 0.052267 Loss(val): 0.051996 acc(val): 0.665833
+[15:19:24] Epoch  42: Loss(train): 0.051986 Loss(val): 0.051854 acc(val): 0.671139
+[15:19:44] Epoch  43: Loss(train): 0.051762 Loss(val): 0.051751 acc(val): 0.675017
+[15:20:04] Epoch  44: Loss(train): 0.051592 Loss(val): 0.051681 acc(val): 0.679235
+[15:20:25] Epoch  45: Loss(train): 0.051479 Loss(val): 0.051643 acc(val): 0.680119
+[15:20:45] Epoch  46: Loss(train): 0.051394 Loss(val): 0.051616 acc(val): 0.681071
+[15:21:05] Epoch  47: Loss(train): 0.051367 Loss(val): 0.051600 acc(val): 0.680051
+[15:21:25] Epoch  48: Loss(train): 0.051341 Loss(val): 0.051579 acc(val): 0.680867
+[15:21:46] Epoch  49: Loss(train): 0.051304 Loss(val): 0.051564 acc(val): 0.681344
+[15:22:06] Epoch  50: Loss(train): 0.051285 Loss(val): 0.051563 acc(val): 0.681003
+[15:22:26] Epoch  51: Loss(train): 0.051286 Loss(val): 0.051553 acc(val): 0.681888
+[15:22:50] Epoch  52: Loss(train): 0.051247 Loss(val): 0.051551 acc(val): 0.681548
+[15:23:29] Epoch  53: Loss(train): 0.051221 Loss(val): 0.051543 acc(val): 0.681412
+[15:24:06] Epoch  54: Loss(train): 0.051172 Loss(val): 0.051541 acc(val): 0.680663
+[15:24:47] Epoch  55: Loss(train): 0.051131 Loss(val): 0.051537 acc(val): 0.679711
+[15:25:26] Epoch  56: Loss(train): 0.051072 Loss(val): 0.051525 acc(val): 0.680459
+[15:26:06] Epoch  57: Loss(train): 0.051019 Loss(val): 0.051529 acc(val): 0.679575
+[15:26:46] Epoch  58: Loss(train): 0.050963 Loss(val): 0.051544 acc(val): 0.680816
+[15:27:24] Epoch  59: Loss(train): 0.050920 Loss(val): 0.051560 acc(val): 0.680884
+[15:28:03] Epoch  60: Loss(train): 0.050894 Loss(val): 0.051591 acc(val): 0.681429
+[15:28:39] Epoch  61: Loss(train): 0.050878 Loss(val): 0.051636 acc(val): 0.680408
+[15:29:12] Epoch  62: Loss(train): 0.050867 Loss(val): 0.051668 acc(val): 0.678844
+[15:29:41] Epoch  63: Loss(train): 0.050860 Loss(val): 0.051702 acc(val): 0.676667
+[15:30:06] Epoch  64: Loss(train): 0.050847 Loss(val): 0.051702 acc(val): 0.677619
+[15:30:36] Epoch  65: Loss(train): 0.050832 Loss(val): 0.051699 acc(val): 0.677211
+[15:30:56] Epoch  66: Loss(train): 0.050821 Loss(val): 0.051700 acc(val): 0.677687
+[15:31:17] Epoch  67: Loss(train): 0.050801 Loss(val): 0.051675 acc(val): 0.678435
+[15:31:38] Epoch  68: Loss(train): 0.050779 Loss(val): 0.051646 acc(val): 0.678980
+[15:31:59] Epoch  69: Loss(train): 0.050759 Loss(val): 0.051619 acc(val): 0.679796
+[15:32:20] Epoch  70: Loss(train): 0.050744 Loss(val): 0.051600 acc(val): 0.679796
+[15:32:41] Epoch  71: Loss(train): 0.050733 Loss(val): 0.051590 acc(val): 0.680272
+[15:33:02] Epoch  72: Loss(train): 0.050716 Loss(val): 0.051555 acc(val): 0.680748
+[15:33:23] Epoch  73: Loss(train): 0.050704 Loss(val): 0.051538 acc(val): 0.681156
+[15:33:44] Epoch  74: Loss(train): 0.050693 Loss(val): 0.051523 acc(val): 0.681156
+[15:34:06] Epoch  75: Loss(train): 0.050684 Loss(val): 0.051510 acc(val): 0.681361
+[15:34:29] Epoch  76: Loss(train): 0.050677 Loss(val): 0.051499 acc(val): 0.681905
+[15:35:14] Epoch  77: Loss(train): 0.050668 Loss(val): 0.051481 acc(val): 0.682041
+[15:35:46] Epoch  78: Loss(train): 0.050662 Loss(val): 0.051477 acc(val): 0.681769
+[15:36:15] Epoch  79: Loss(train): 0.050656 Loss(val): 0.051464 acc(val): 0.682041
+[15:36:43] Epoch  80: Loss(train): 0.050651 Loss(val): 0.051460 acc(val): 0.682177
+[15:37:03] Epoch  81: Loss(train): 0.050647 Loss(val): 0.051460 acc(val): 0.681633
+[15:37:24] Epoch  82: Loss(train): 0.050642 Loss(val): 0.051450 acc(val): 0.681633
+[15:37:45] Epoch  83: Loss(train): 0.050638 Loss(val): 0.051445 acc(val): 0.681429
+[15:38:07] Epoch  84: Loss(train): 0.050634 Loss(val): 0.051439 acc(val): 0.681293
+[15:38:29] Epoch  85: Loss(train): 0.050631 Loss(val): 0.051434 acc(val): 0.681224
+[15:38:50] Epoch  86: Loss(train): 0.050628 Loss(val): 0.051434 acc(val): 0.681497
+[15:39:11] Epoch  87: Loss(train): 0.050625 Loss(val): 0.051429 acc(val): 0.681565
+[15:39:32] Epoch  88: Loss(train): 0.050622 Loss(val): 0.051431 acc(val): 0.681633
+[15:39:53] Epoch  89: Loss(train): 0.050619 Loss(val): 0.051418 acc(val): 0.681293
+[15:40:18] Epoch  90: Loss(train): 0.050617 Loss(val): 0.051419 acc(val): 0.681361
+[15:40:47] Epoch  91: Loss(train): 0.050615 Loss(val): 0.051416 acc(val): 0.681429
+[15:41:10] Epoch  92: Loss(train): 0.050613 Loss(val): 0.051413 acc(val): 0.681429
+[15:41:34] Epoch  93: Loss(train): 0.050611 Loss(val): 0.051410 acc(val): 0.681429
+[15:41:55] Epoch  94: Loss(train): 0.050610 Loss(val): 0.051410 acc(val): 0.681497
+[15:42:17] Epoch  95: Loss(train): 0.050608 Loss(val): 0.051405 acc(val): 0.681769
+[15:42:38] Epoch  96: Loss(train): 0.050606 Loss(val): 0.051401 acc(val): 0.681905
+[15:42:59] Epoch  97: Loss(train): 0.050605 Loss(val): 0.051403 acc(val): 0.681429
+[15:43:20] Epoch  98: Loss(train): 0.050604 Loss(val): 0.051404 acc(val): 0.681361
+[15:43:41] Epoch  99: Loss(train): 0.050603 Loss(val): 0.051399 acc(val): 0.681565
+[15:44:02] Epoch 100: Loss(train): 0.050602 Loss(val): 0.051401
+[15:44:05] FINAL(100) Loss(test): 0.051667 Accuarcy: 0.604730
+
+Configuration learning_rate=0.03, decay_step=60
+[15:44:11] INIT Loss(test): 0.142111 Accuarcy: 0.116081
+[15:44:29] Epoch   1: Loss(train): 0.085466 Loss(val): 0.083448 acc(val): 0.324014
+[15:44:52] Epoch   2: Loss(train): 0.067009 Loss(val): 0.065906 acc(val): 0.454150
+[15:45:17] Epoch   3: Loss(train): 0.063191 Loss(val): 0.062418 acc(val): 0.506139
+[15:45:38] Epoch   4: Loss(train): 0.059964 Loss(val): 0.059266 acc(val): 0.545680
+[15:46:00] Epoch   5: Loss(train): 0.059229 Loss(val): 0.058537 acc(val): 0.556088
+[15:46:21] Epoch   6: Loss(train): 0.059260 Loss(val): 0.058677 acc(val): 0.551599
+[15:46:42] Epoch   7: Loss(train): 0.059613 Loss(val): 0.058838 acc(val): 0.540663
+[15:47:04] Epoch   8: Loss(train): 0.058372 Loss(val): 0.057957 acc(val): 0.553929
+[15:47:25] Epoch   9: Loss(train): 0.058023 Loss(val): 0.057690 acc(val): 0.559796
+[15:47:47] Epoch  10: Loss(train): 0.058341 Loss(val): 0.057856 acc(val): 0.557891
+[15:48:08] Epoch  11: Loss(train): 0.058291 Loss(val): 0.057867 acc(val): 0.555442
+[15:48:29] Epoch  12: Loss(train): 0.057441 Loss(val): 0.057287 acc(val): 0.566054
+[15:48:51] Epoch  13: Loss(train): 0.056272 Loss(val): 0.056194 acc(val): 0.584490
+[15:49:13] Epoch  14: Loss(train): 0.055851 Loss(val): 0.055663 acc(val): 0.594898
+[15:49:36] Epoch  15: Loss(train): 0.055405 Loss(val): 0.055219 acc(val): 0.603129
+[15:49:58] Epoch  16: Loss(train): 0.055548 Loss(val): 0.055248 acc(val): 0.600952
+[15:50:20] Epoch  17: Loss(train): 0.055654 Loss(val): 0.055321 acc(val): 0.599456
+[15:50:41] Epoch  18: Loss(train): 0.055723 Loss(val): 0.055456 acc(val): 0.598384
+[15:51:03] Epoch  19: Loss(train): 0.055744 Loss(val): 0.055502 acc(val): 0.597228
+[15:51:25] Epoch  20: Loss(train): 0.055564 Loss(val): 0.055416 acc(val): 0.596956
+[15:51:48] Epoch  21: Loss(train): 0.055276 Loss(val): 0.055244 acc(val): 0.600612
+[15:52:11] Epoch  22: Loss(train): 0.054920 Loss(val): 0.054917 acc(val): 0.607024
+[15:52:34] Epoch  23: Loss(train): 0.054450 Loss(val): 0.054397 acc(val): 0.612534
+[15:52:57] Epoch  24: Loss(train): 0.054105 Loss(val): 0.053996 acc(val): 0.619677
+[15:53:19] Epoch  25: Loss(train): 0.053674 Loss(val): 0.053549 acc(val): 0.630493
+[15:53:42] Epoch  26: Loss(train): 0.053361 Loss(val): 0.053270 acc(val): 0.637772
+[15:54:11] Epoch  27: Loss(train): 0.053233 Loss(val): 0.053125 acc(val): 0.640765
+[15:54:50] Epoch  28: Loss(train): 0.053071 Loss(val): 0.053007 acc(val): 0.644643
+[15:55:27] Epoch  29: Loss(train): 0.052948 Loss(val): 0.052935 acc(val): 0.644099
+[15:56:04] Epoch  30: Loss(train): 0.052997 Loss(val): 0.052941 acc(val): 0.643214
+[15:56:40] Epoch  31: Loss(train): 0.053064 Loss(val): 0.052970 acc(val): 0.639133
+[15:57:17] Epoch  32: Loss(train): 0.053172 Loss(val): 0.052973 acc(val): 0.636888
+[15:57:43] Epoch  33: Loss(train): 0.053340 Loss(val): 0.053012 acc(val): 0.632194
+[15:58:05] Epoch  34: Loss(train): 0.053407 Loss(val): 0.053008 acc(val): 0.631173
+[15:58:26] Epoch  35: Loss(train): 0.053488 Loss(val): 0.053011 acc(val): 0.630561
+[15:58:48] Epoch  36: Loss(train): 0.053523 Loss(val): 0.052991 acc(val): 0.626956
+[15:59:11] Epoch  37: Loss(train): 0.053434 Loss(val): 0.052903 acc(val): 0.629473
+[15:59:39] Epoch  38: Loss(train): 0.053004 Loss(val): 0.052646 acc(val): 0.638656
+[16:00:06] Epoch  39: Loss(train): 0.052548 Loss(val): 0.052387 acc(val): 0.650289
+[16:00:30] Epoch  40: Loss(train): 0.052184 Loss(val): 0.052197 acc(val): 0.658656
+[16:00:53] Epoch  41: Loss(train): 0.051921 Loss(val): 0.052086 acc(val): 0.663895
+[16:01:25] Epoch  42: Loss(train): 0.051787 Loss(val): 0.052001 acc(val): 0.667024
+[16:01:57] Epoch  43: Loss(train): 0.051664 Loss(val): 0.051921 acc(val): 0.669269
+[16:02:21] Epoch  44: Loss(train): 0.051557 Loss(val): 0.051856 acc(val): 0.670272
+[16:02:57] Epoch  45: Loss(train): 0.051499 Loss(val): 0.051807 acc(val): 0.671582
+[16:03:22] Epoch  46: Loss(train): 0.051440 Loss(val): 0.051767 acc(val): 0.672058
+[16:03:51] Epoch  47: Loss(train): 0.051405 Loss(val): 0.051744 acc(val): 0.672874
+[16:04:31] Epoch  48: Loss(train): 0.051368 Loss(val): 0.051721 acc(val): 0.673146
+[16:05:07] Epoch  49: Loss(train): 0.051326 Loss(val): 0.051705 acc(val): 0.673690
+[16:05:30] Epoch  50: Loss(train): 0.051288 Loss(val): 0.051689 acc(val): 0.673759
+[16:05:53] Epoch  51: Loss(train): 0.051239 Loss(val): 0.051667 acc(val): 0.674915
+[16:06:16] Epoch  52: Loss(train): 0.051180 Loss(val): 0.051656 acc(val): 0.675595
+[16:06:38] Epoch  53: Loss(train): 0.051117 Loss(val): 0.051658 acc(val): 0.677500
+[16:07:00] Epoch  54: Loss(train): 0.051078 Loss(val): 0.051665 acc(val): 0.678044
+[16:07:22] Epoch  55: Loss(train): 0.051036 Loss(val): 0.051678 acc(val): 0.677432
+[16:07:45] Epoch  56: Loss(train): 0.051011 Loss(val): 0.051702 acc(val): 0.677636
+[16:08:08] Epoch  57: Loss(train): 0.050990 Loss(val): 0.051737 acc(val): 0.676752
+[16:08:31] Epoch  58: Loss(train): 0.050977 Loss(val): 0.051756 acc(val): 0.675323
+[16:08:56] Epoch  59: Loss(train): 0.050971 Loss(val): 0.051791 acc(val): 0.675867
+[16:09:23] Epoch  60: Loss(train): 0.050955 Loss(val): 0.051786 acc(val): 0.675272
+[16:09:49] Epoch  61: Loss(train): 0.050941 Loss(val): 0.051792 acc(val): 0.675544
+[16:10:14] Epoch  62: Loss(train): 0.050929 Loss(val): 0.051794 acc(val): 0.674864
+[16:10:37] Epoch  63: Loss(train): 0.050904 Loss(val): 0.051764 acc(val): 0.674932
+[16:10:59] Epoch  64: Loss(train): 0.050879 Loss(val): 0.051731 acc(val): 0.675476
+[16:11:22] Epoch  65: Loss(train): 0.050859 Loss(val): 0.051707 acc(val): 0.676361
+[16:11:44] Epoch  66: Loss(train): 0.050838 Loss(val): 0.051671 acc(val): 0.677857
+[16:12:06] Epoch  67: Loss(train): 0.050822 Loss(val): 0.051655 acc(val): 0.678741
+[16:12:28] Epoch  68: Loss(train): 0.050804 Loss(val): 0.051619 acc(val): 0.680238
+[16:12:50] Epoch  69: Loss(train): 0.050792 Loss(val): 0.051603 acc(val): 0.680170
+[16:13:14] Epoch  70: Loss(train): 0.050781 Loss(val): 0.051588 acc(val): 0.680510
+[16:13:37] Epoch  71: Loss(train): 0.050770 Loss(val): 0.051567 acc(val): 0.681463
+[16:14:00] Epoch  72: Loss(train): 0.050762 Loss(val): 0.051553 acc(val): 0.681463
+[16:14:23] Epoch  73: Loss(train): 0.050755 Loss(val): 0.051545 acc(val): 0.681531
+[16:14:47] Epoch  74: Loss(train): 0.050748 Loss(val): 0.051538 acc(val): 0.680986
+[16:15:11] Epoch  75: Loss(train): 0.050742 Loss(val): 0.051527 acc(val): 0.681259
+[16:15:33] Epoch  76: Loss(train): 0.050736 Loss(val): 0.051523 acc(val): 0.681054
+[16:15:56] Epoch  77: Loss(train): 0.050731 Loss(val): 0.051517 acc(val): 0.681122
+[16:16:19] Epoch  78: Loss(train): 0.050726 Loss(val): 0.051506 acc(val): 0.681463
+[16:16:41] Epoch  79: Loss(train): 0.050722 Loss(val): 0.051507 acc(val): 0.681463
+[16:17:04] Epoch  80: Loss(train): 0.050717 Loss(val): 0.051499 acc(val): 0.681259
+[16:17:26] Epoch  81: Loss(train): 0.050713 Loss(val): 0.051492 acc(val): 0.681463
+[16:17:49] Epoch  82: Loss(train): 0.050709 Loss(val): 0.051488 acc(val): 0.681122
+[16:18:12] Epoch  83: Loss(train): 0.050706 Loss(val): 0.051491 acc(val): 0.681463
+[16:18:35] Epoch  84: Loss(train): 0.050703 Loss(val): 0.051484 acc(val): 0.681463
+[16:18:57] Epoch  85: Loss(train): 0.050700 Loss(val): 0.051476 acc(val): 0.681939
+[16:19:20] Epoch  86: Loss(train): 0.050698 Loss(val): 0.051476 acc(val): 0.681803
+[16:19:43] Epoch  87: Loss(train): 0.050695 Loss(val): 0.051471 acc(val): 0.682007
+[16:20:05] Epoch  88: Loss(train): 0.050693 Loss(val): 0.051474 acc(val): 0.681735
+[16:20:28] Epoch  89: Loss(train): 0.050691 Loss(val): 0.051469 acc(val): 0.681939
+[16:20:51] Epoch  90: Loss(train): 0.050689 Loss(val): 0.051463 acc(val): 0.681803
+[16:21:14] Epoch  91: Loss(train): 0.050687 Loss(val): 0.051464 acc(val): 0.681803
+[16:21:37] Epoch  92: Loss(train): 0.050685 Loss(val): 0.051462 acc(val): 0.681667
+[16:21:59] Epoch  93: Loss(train): 0.050683 Loss(val): 0.051460 acc(val): 0.681939
+[16:22:22] Epoch  94: Loss(train): 0.050682 Loss(val): 0.051455 acc(val): 0.682007
+[16:22:45] Epoch  95: Loss(train): 0.050681 Loss(val): 0.051457 acc(val): 0.681939
+[16:23:08] Epoch  96: Loss(train): 0.050679 Loss(val): 0.051455 acc(val): 0.682007
+[16:23:31] Epoch  97: Loss(train): 0.050678 Loss(val): 0.051454 acc(val): 0.682075
+[16:23:54] Epoch  98: Loss(train): 0.050677 Loss(val): 0.051455 acc(val): 0.682211
+[16:24:17] Epoch  99: Loss(train): 0.050676 Loss(val): 0.051454 acc(val): 0.682211
+[16:24:40] Epoch 100: Loss(train): 0.050675 Loss(val): 0.051452
+[16:24:43] FINAL(100) Loss(test): 0.051842 Accuarcy: 0.601622
+
+Configuration learning_rate=0.01, decay_step=20
+[16:24:49] INIT Loss(test): 0.123722 Accuarcy: 0.127973
+[16:25:10] Epoch   1: Loss(train): 0.086237 Loss(val): 0.086168 acc(val): 0.291888
+[16:25:47] Epoch   2: Loss(train): 0.066817 Loss(val): 0.065911 acc(val): 0.445901
+[16:26:21] Epoch   3: Loss(train): 0.063177 Loss(val): 0.062407 acc(val): 0.499915
+[16:26:54] Epoch   4: Loss(train): 0.061026 Loss(val): 0.060297 acc(val): 0.540425
+[16:27:28] Epoch   5: Loss(train): 0.059943 Loss(val): 0.059473 acc(val): 0.551259
+[16:28:03] Epoch   6: Loss(train): 0.058618 Loss(val): 0.058114 acc(val): 0.565204
+[16:28:45] Epoch   7: Loss(train): 0.057991 Loss(val): 0.057816 acc(val): 0.570017
+[16:29:12] Epoch   8: Loss(train): 0.057960 Loss(val): 0.057804 acc(val): 0.568316
+[16:29:53] Epoch   9: Loss(train): 0.058586 Loss(val): 0.058320 acc(val): 0.558980
+[16:31:02] Epoch  10: Loss(train): 0.058809 Loss(val): 0.058750 acc(val): 0.551156
+[16:32:04] Epoch  11: Loss(train): 0.057933 Loss(val): 0.058105 acc(val): 0.555714
+[16:33:09] Epoch  12: Loss(train): 0.057471 Loss(val): 0.057670 acc(val): 0.557619
+[16:34:03] Epoch  13: Loss(train): 0.057318 Loss(val): 0.057520 acc(val): 0.555918
+[16:34:45] Epoch  14: Loss(train): 0.057432 Loss(val): 0.057578 acc(val): 0.551905
+[16:35:26] Epoch  15: Loss(train): 0.057712 Loss(val): 0.057838 acc(val): 0.549864
+[16:36:24] Epoch  16: Loss(train): 0.058157 Loss(val): 0.058160 acc(val): 0.547075
+[16:37:16] Epoch  17: Loss(train): 0.058045 Loss(val): 0.058048 acc(val): 0.550969
+[16:38:01] Epoch  18: Loss(train): 0.057258 Loss(val): 0.057315 acc(val): 0.562279
+[16:38:48] Epoch  19: Loss(train): 0.056103 Loss(val): 0.056101 acc(val): 0.582143
+[16:39:35] Epoch  20: Loss(train): 0.055167 Loss(val): 0.055090 acc(val): 0.605000
+[16:40:16] Epoch  21: Loss(train): 0.054440 Loss(val): 0.054323 acc(val): 0.621939
+[16:40:59] Epoch  22: Loss(train): 0.053996 Loss(val): 0.053912 acc(val): 0.627585
+[16:41:44] Epoch  23: Loss(train): 0.053813 Loss(val): 0.053733 acc(val): 0.627653
+[16:42:31] Epoch  24: Loss(train): 0.053584 Loss(val): 0.053587 acc(val): 0.629626
+[16:43:12] Epoch  25: Loss(train): 0.053363 Loss(val): 0.053465 acc(val): 0.630238
+[16:43:56] Epoch  26: Loss(train): 0.053242 Loss(val): 0.053413 acc(val): 0.630306
+[16:44:40] Epoch  27: Loss(train): 0.053028 Loss(val): 0.053261 acc(val): 0.634932
+[16:45:23] Epoch  28: Loss(train): 0.052812 Loss(val): 0.053128 acc(val): 0.638197
+[16:46:04] Epoch  29: Loss(train): 0.052652 Loss(val): 0.052984 acc(val): 0.642143
+[16:46:49] Epoch  30: Loss(train): 0.052535 Loss(val): 0.052863 acc(val): 0.645680
+[16:47:31] Epoch  31: Loss(train): 0.052439 Loss(val): 0.052725 acc(val): 0.649694
+[16:48:14] Epoch  32: Loss(train): 0.052366 Loss(val): 0.052586 acc(val): 0.653844
+[16:48:57] Epoch  33: Loss(train): 0.052277 Loss(val): 0.052462 acc(val): 0.655204
+[16:49:39] Epoch  34: Loss(train): 0.052236 Loss(val): 0.052378 acc(val): 0.655340
+[16:50:20] Epoch  35: Loss(train): 0.052206 Loss(val): 0.052301 acc(val): 0.656905
+[16:51:02] Epoch  36: Loss(train): 0.052131 Loss(val): 0.052229 acc(val): 0.657262
+[16:51:43] Epoch  37: Loss(train): 0.052080 Loss(val): 0.052175 acc(val): 0.659235
+[16:52:26] Epoch  38: Loss(train): 0.051932 Loss(val): 0.052086 acc(val): 0.663112
+[16:53:08] Epoch  39: Loss(train): 0.051834 Loss(val): 0.052032 acc(val): 0.663929
+[16:53:52] Epoch  40: Loss(train): 0.051742 Loss(val): 0.051984 acc(val): 0.664745
+[16:54:35] Epoch  41: Loss(train): 0.051577 Loss(val): 0.051924 acc(val): 0.668078
+[16:55:19] Epoch  42: Loss(train): 0.051501 Loss(val): 0.051901 acc(val): 0.667466
+[16:56:06] Epoch  43: Loss(train): 0.051449 Loss(val): 0.051876 acc(val): 0.668078
+[16:57:15] Epoch  44: Loss(train): 0.051393 Loss(val): 0.051869 acc(val): 0.667721
+[16:58:19] Epoch  45: Loss(train): 0.051368 Loss(val): 0.051851 acc(val): 0.666497
+[16:59:26] Epoch  46: Loss(train): 0.051376 Loss(val): 0.051837 acc(val): 0.666241
+[17:00:17] Epoch  47: Loss(train): 0.051365 Loss(val): 0.051807 acc(val): 0.667398
+[17:01:31] Epoch  48: Loss(train): 0.051349 Loss(val): 0.051793 acc(val): 0.667262
+[17:02:32] Epoch  49: Loss(train): 0.051350 Loss(val): 0.051774 acc(val): 0.667262
+[17:03:24] Epoch  50: Loss(train): 0.051308 Loss(val): 0.051759 acc(val): 0.668622
+[17:04:19] Epoch  51: Loss(train): 0.051285 Loss(val): 0.051734 acc(val): 0.669439
+[17:05:10] Epoch  52: Loss(train): 0.051267 Loss(val): 0.051716 acc(val): 0.669847
+[17:05:54] Epoch  53: Loss(train): 0.051197 Loss(val): 0.051707 acc(val): 0.670663
+[17:06:43] Epoch  54: Loss(train): 0.051160 Loss(val): 0.051691 acc(val): 0.672432
+[17:07:32] Epoch  55: Loss(train): 0.051111 Loss(val): 0.051690 acc(val): 0.672772
+[17:08:29] Epoch  56: Loss(train): 0.051065 Loss(val): 0.051692 acc(val): 0.674269
+[17:09:18] Epoch  57: Loss(train): 0.051019 Loss(val): 0.051708 acc(val): 0.672483
+[17:10:05] Epoch  58: Loss(train): 0.050985 Loss(val): 0.051736 acc(val): 0.673231
+[17:10:50] Epoch  59: Loss(train): 0.050964 Loss(val): 0.051761 acc(val): 0.673163
+[17:11:38] Epoch  60: Loss(train): 0.050948 Loss(val): 0.051782 acc(val): 0.671667
+[17:12:21] Epoch  61: Loss(train): 0.050943 Loss(val): 0.051836 acc(val): 0.671684
+[17:13:13] Epoch  62: Loss(train): 0.050930 Loss(val): 0.051840 acc(val): 0.671412
+[17:14:01] Epoch  63: Loss(train): 0.050921 Loss(val): 0.051851 acc(val): 0.671276
+[17:14:46] Epoch  64: Loss(train): 0.050902 Loss(val): 0.051832 acc(val): 0.671956
+[17:15:30] Epoch  65: Loss(train): 0.050885 Loss(val): 0.051809 acc(val): 0.672092
+[17:16:19] Epoch  66: Loss(train): 0.050869 Loss(val): 0.051790 acc(val): 0.672024
+[17:17:03] Epoch  67: Loss(train): 0.050854 Loss(val): 0.051774 acc(val): 0.673044
+[17:17:51] Epoch  68: Loss(train): 0.050836 Loss(val): 0.051741 acc(val): 0.672891
+[17:18:37] Epoch  69: Loss(train): 0.050824 Loss(val): 0.051727 acc(val): 0.673435
+[17:19:23] Epoch  70: Loss(train): 0.050812 Loss(val): 0.051704 acc(val): 0.674116
+[17:20:07] Epoch  71: Loss(train): 0.050800 Loss(val): 0.051679 acc(val): 0.673912
+[17:20:53] Epoch  72: Loss(train): 0.050792 Loss(val): 0.051671 acc(val): 0.674388
+[17:21:38] Epoch  73: Loss(train): 0.050785 Loss(val): 0.051665 acc(val): 0.673776
+[17:22:24] Epoch  74: Loss(train): 0.050776 Loss(val): 0.051649 acc(val): 0.674116
+[17:23:09] Epoch  75: Loss(train): 0.050770 Loss(val): 0.051641 acc(val): 0.674660
+[17:23:55] Epoch  76: Loss(train): 0.050764 Loss(val): 0.051627 acc(val): 0.675544
+[17:24:40] Epoch  77: Loss(train): 0.050759 Loss(val): 0.051624 acc(val): 0.675408
+[17:25:26] Epoch  78: Loss(train): 0.050753 Loss(val): 0.051614 acc(val): 0.675952
+[17:26:11] Epoch  79: Loss(train): 0.050748 Loss(val): 0.051609 acc(val): 0.675612
+[17:27:19] Epoch  80: Loss(train): 0.050744 Loss(val): 0.051604 acc(val): 0.675884
+[17:28:38] Epoch  81: Loss(train): 0.050740 Loss(val): 0.051599 acc(val): 0.675816
+[17:29:45] Epoch  82: Loss(train): 0.050736 Loss(val): 0.051592 acc(val): 0.676020
+[17:30:30] Epoch  83: Loss(train): 0.050733 Loss(val): 0.051590 acc(val): 0.676088
+[17:31:31] Epoch  84: Loss(train): 0.050730 Loss(val): 0.051590 acc(val): 0.676020
+[17:32:34] Epoch  85: Loss(train): 0.050727 Loss(val): 0.051587 acc(val): 0.676293
+[17:33:24] Epoch  86: Loss(train): 0.050724 Loss(val): 0.051580 acc(val): 0.676429
+[17:34:37] Epoch  87: Loss(train): 0.050721 Loss(val): 0.051575 acc(val): 0.676837
+[17:35:41] Epoch  88: Loss(train): 0.050719 Loss(val): 0.051574 acc(val): 0.676769
+[17:36:29] Epoch  89: Loss(train): 0.050717 Loss(val): 0.051573 acc(val): 0.676701
+[17:37:33] Epoch  90: Loss(train): 0.050715 Loss(val): 0.051568 acc(val): 0.676701
+[17:38:23] Epoch  91: Loss(train): 0.050713 Loss(val): 0.051565 acc(val): 0.676905
+[17:39:10] Epoch  92: Loss(train): 0.050712 Loss(val): 0.051564 acc(val): 0.676837
+[17:39:57] Epoch  93: Loss(train): 0.050710 Loss(val): 0.051562 acc(val): 0.677177
+[17:40:43] Epoch  94: Loss(train): 0.050709 Loss(val): 0.051560 acc(val): 0.676973
+[17:41:33] Epoch  95: Loss(train): 0.050707 Loss(val): 0.051559 acc(val): 0.676905
+[17:42:22] Epoch  96: Loss(train): 0.050706 Loss(val): 0.051555 acc(val): 0.677177
+[17:43:18] Epoch  97: Loss(train): 0.050705 Loss(val): 0.051552 acc(val): 0.677177
+[17:44:05] Epoch  98: Loss(train): 0.050704 Loss(val): 0.051554 acc(val): 0.677041
+[17:44:52] Epoch  99: Loss(train): 0.050703 Loss(val): 0.051554 acc(val): 0.677109
+[17:45:40] Epoch 100: Loss(train): 0.050702 Loss(val): 0.051551
+[17:45:47] FINAL(100) Loss(test): 0.052029 Accuarcy: 0.599189
+
+Configuration learning_rate=0.01, decay_step=40
+[17:46:00] INIT Loss(test): 0.176727 Accuarcy: 0.092973
+[17:46:50] Epoch   1: Loss(train): 0.089826 Loss(val): 0.087610 acc(val): 0.284201
+[17:47:38] Epoch   2: Loss(train): 0.067577 Loss(val): 0.066210 acc(val): 0.447466
+[17:48:25] Epoch   3: Loss(train): 0.064038 Loss(val): 0.063006 acc(val): 0.497551
+[17:49:13] Epoch   4: Loss(train): 0.060244 Loss(val): 0.059602 acc(val): 0.554031
+[17:49:58] Epoch   5: Loss(train): 0.059227 Loss(val): 0.058822 acc(val): 0.565595
+[17:50:47] Epoch   6: Loss(train): 0.058737 Loss(val): 0.058792 acc(val): 0.559677
+[17:51:34] Epoch   7: Loss(train): 0.058215 Loss(val): 0.058426 acc(val): 0.559405
+[17:52:21] Epoch   8: Loss(train): 0.057274 Loss(val): 0.057502 acc(val): 0.570986
+[17:53:07] Epoch   9: Loss(train): 0.057132 Loss(val): 0.057426 acc(val): 0.570986
+[17:53:55] Epoch  10: Loss(train): 0.056904 Loss(val): 0.057230 acc(val): 0.571310
+[17:54:40] Epoch  11: Loss(train): 0.057148 Loss(val): 0.057484 acc(val): 0.560357
+[17:55:27] Epoch  12: Loss(train): 0.057290 Loss(val): 0.057630 acc(val): 0.556003
+[17:56:12] Epoch  13: Loss(train): 0.057313 Loss(val): 0.057586 acc(val): 0.550935
+[17:56:59] Epoch  14: Loss(train): 0.056691 Loss(val): 0.056890 acc(val): 0.563316
+[17:57:44] Epoch  15: Loss(train): 0.055783 Loss(val): 0.055999 acc(val): 0.579507
+[17:58:36] Epoch  16: Loss(train): 0.055334 Loss(val): 0.055583 acc(val): 0.590187
+[17:59:33] Epoch  17: Loss(train): 0.055496 Loss(val): 0.055625 acc(val): 0.587330
+[18:00:46] Epoch  18: Loss(train): 0.055848 Loss(val): 0.055966 acc(val): 0.582908
+[18:01:46] Epoch  19: Loss(train): 0.056469 Loss(val): 0.056572 acc(val): 0.573180
+[18:02:41] Epoch  20: Loss(train): 0.057220 Loss(val): 0.057206 acc(val): 0.559711
+[18:03:34] Epoch  21: Loss(train): 0.057383 Loss(val): 0.057452 acc(val): 0.557330
+[18:04:45] Epoch  22: Loss(train): 0.056780 Loss(val): 0.056885 acc(val): 0.568622
+[18:05:45] Epoch  23: Loss(train): 0.055630 Loss(val): 0.055793 acc(val): 0.584541
+[18:06:40] Epoch  24: Loss(train): 0.054334 Loss(val): 0.054489 acc(val): 0.612364
+[18:07:32] Epoch  25: Loss(train): 0.053592 Loss(val): 0.053724 acc(val): 0.624881
+[18:08:31] Epoch  26: Loss(train): 0.053303 Loss(val): 0.053389 acc(val): 0.628095
+[18:09:22] Epoch  27: Loss(train): 0.053062 Loss(val): 0.053169 acc(val): 0.633333
+[18:10:13] Epoch  28: Loss(train): 0.053093 Loss(val): 0.053166 acc(val): 0.630663
+[18:11:03] Epoch  29: Loss(train): 0.053281 Loss(val): 0.053265 acc(val): 0.624609
+[18:12:01] Epoch  30: Loss(train): 0.053359 Loss(val): 0.053331 acc(val): 0.620595
+[18:12:51] Epoch  31: Loss(train): 0.053417 Loss(val): 0.053345 acc(val): 0.619507
+[18:13:42] Epoch  32: Loss(train): 0.053442 Loss(val): 0.053321 acc(val): 0.619847
+[18:14:34] Epoch  33: Loss(train): 0.053280 Loss(val): 0.053169 acc(val): 0.622364
+[18:15:26] Epoch  34: Loss(train): 0.053042 Loss(val): 0.052970 acc(val): 0.628282
+[18:16:15] Epoch  35: Loss(train): 0.052677 Loss(val): 0.052694 acc(val): 0.637058
+[18:17:06] Epoch  36: Loss(train): 0.052356 Loss(val): 0.052496 acc(val): 0.643793
+[18:17:55] Epoch  37: Loss(train): 0.052130 Loss(val): 0.052343 acc(val): 0.649915
+[18:18:48] Epoch  38: Loss(train): 0.051967 Loss(val): 0.052270 acc(val): 0.653044
+[18:19:37] Epoch  39: Loss(train): 0.051858 Loss(val): 0.052225 acc(val): 0.655510
+[18:20:28] Epoch  40: Loss(train): 0.051766 Loss(val): 0.052186 acc(val): 0.659609
+[18:21:17] Epoch  41: Loss(train): 0.051688 Loss(val): 0.052134 acc(val): 0.661922
+[18:22:09] Epoch  42: Loss(train): 0.051594 Loss(val): 0.052048 acc(val): 0.664235
+[18:22:57] Epoch  43: Loss(train): 0.051490 Loss(val): 0.051962 acc(val): 0.665799
+[18:23:47] Epoch  44: Loss(train): 0.051394 Loss(val): 0.051891 acc(val): 0.666956
+[18:24:36] Epoch  45: Loss(train): 0.051314 Loss(val): 0.051834 acc(val): 0.670221
+[18:25:27] Epoch  46: Loss(train): 0.051240 Loss(val): 0.051802 acc(val): 0.670544
+[18:26:16] Epoch  47: Loss(train): 0.051188 Loss(val): 0.051788 acc(val): 0.671088
+[18:27:07] Epoch  48: Loss(train): 0.051140 Loss(val): 0.051788 acc(val): 0.670680
+[18:27:55] Epoch  49: Loss(train): 0.051096 Loss(val): 0.051787 acc(val): 0.670816
+[18:28:45] Epoch  50: Loss(train): 0.051063 Loss(val): 0.051781 acc(val): 0.671497
+[18:29:34] Epoch  51: Loss(train): 0.051026 Loss(val): 0.051795 acc(val): 0.670612
+[18:30:36] Epoch  52: Loss(train): 0.050999 Loss(val): 0.051804 acc(val): 0.671769
+[18:31:57] Epoch  53: Loss(train): 0.050980 Loss(val): 0.051816 acc(val): 0.671684
+[18:32:49] Epoch  54: Loss(train): 0.050963 Loss(val): 0.051823 acc(val): 0.672500
+[18:33:40] Epoch  55: Loss(train): 0.050948 Loss(val): 0.051837 acc(val): 0.672296
+[18:34:51] Epoch  56: Loss(train): 0.050931 Loss(val): 0.051833 acc(val): 0.673112
+[18:35:48] Epoch  57: Loss(train): 0.050918 Loss(val): 0.051838 acc(val): 0.672840
+[18:36:51] Epoch  58: Loss(train): 0.050899 Loss(val): 0.051821 acc(val): 0.673520
+[18:37:45] Epoch  59: Loss(train): 0.050875 Loss(val): 0.051788 acc(val): 0.674133
+[18:39:01] Epoch  60: Loss(train): 0.050850 Loss(val): 0.051753 acc(val): 0.673861
+[18:40:02] Epoch  61: Loss(train): 0.050831 Loss(val): 0.051731 acc(val): 0.673997
+[18:40:53] Epoch  62: Loss(train): 0.050811 Loss(val): 0.051693 acc(val): 0.673997
+[18:41:46] Epoch  63: Loss(train): 0.050796 Loss(val): 0.051672 acc(val): 0.674609
+[18:42:42] Epoch  64: Loss(train): 0.050784 Loss(val): 0.051655 acc(val): 0.674813
+[18:43:46] Epoch  65: Loss(train): 0.050771 Loss(val): 0.051625 acc(val): 0.675289
+[18:44:43] Epoch  66: Loss(train): 0.050760 Loss(val): 0.051608 acc(val): 0.674745
+[18:45:35] Epoch  67: Loss(train): 0.050751 Loss(val): 0.051598 acc(val): 0.675221
+[18:46:26] Epoch  68: Loss(train): 0.050744 Loss(val): 0.051597 acc(val): 0.675289
+[18:47:18] Epoch  69: Loss(train): 0.050736 Loss(val): 0.051580 acc(val): 0.675493
+[18:48:13] Epoch  70: Loss(train): 0.050730 Loss(val): 0.051581 acc(val): 0.675425
+[18:49:04] Epoch  71: Loss(train): 0.050723 Loss(val): 0.051565 acc(val): 0.675085
+[18:50:03] Epoch  72: Loss(train): 0.050717 Loss(val): 0.051560 acc(val): 0.674881
+[18:50:57] Epoch  73: Loss(train): 0.050711 Loss(val): 0.051549 acc(val): 0.675646
+[18:51:50] Epoch  74: Loss(train): 0.050706 Loss(val): 0.051550 acc(val): 0.675153
+[18:52:42] Epoch  75: Loss(train): 0.050702 Loss(val): 0.051542 acc(val): 0.675289
+[18:53:33] Epoch  76: Loss(train): 0.050696 Loss(val): 0.051532 acc(val): 0.675714
+[18:54:24] Epoch  77: Loss(train): 0.050693 Loss(val): 0.051534 acc(val): 0.675493
+[18:55:16] Epoch  78: Loss(train): 0.050688 Loss(val): 0.051525 acc(val): 0.675493
+[18:56:07] Epoch  79: Loss(train): 0.050684 Loss(val): 0.051525 acc(val): 0.675561
+[18:57:00] Epoch  80: Loss(train): 0.050681 Loss(val): 0.051526 acc(val): 0.675561
+[18:57:51] Epoch  81: Loss(train): 0.050677 Loss(val): 0.051521 acc(val): 0.675901
+[18:58:44] Epoch  82: Loss(train): 0.050675 Loss(val): 0.051520 acc(val): 0.675629
+[18:59:33] Epoch  83: Loss(train): 0.050671 Loss(val): 0.051510 acc(val): 0.675510
+[19:00:25] Epoch  84: Loss(train): 0.050668 Loss(val): 0.051509 acc(val): 0.675085
+[19:01:14] Epoch  85: Loss(train): 0.050666 Loss(val): 0.051507 acc(val): 0.675289
+[19:02:05] Epoch  86: Loss(train): 0.050664 Loss(val): 0.051506 acc(val): 0.675357
+[19:02:56] Epoch  87: Loss(train): 0.050661 Loss(val): 0.051503 acc(val): 0.675425
+[19:03:52] Epoch  88: Loss(train): 0.050659 Loss(val): 0.051504 acc(val): 0.675289
+[19:05:08] Epoch  89: Loss(train): 0.050657 Loss(val): 0.051499 acc(val): 0.675289
+[19:06:39] Epoch  90: Loss(train): 0.050655 Loss(val): 0.051496 acc(val): 0.675425
+[19:07:35] Epoch  91: Loss(train): 0.050654 Loss(val): 0.051497 acc(val): 0.675289
+[19:08:29] Epoch  92: Loss(train): 0.050652 Loss(val): 0.051498 acc(val): 0.675425
+[19:09:40] Epoch  93: Loss(train): 0.050650 Loss(val): 0.051495 acc(val): 0.675561
+[19:10:33] Epoch  94: Loss(train): 0.050649 Loss(val): 0.051495 acc(val): 0.675425
+[19:11:24] Epoch  95: Loss(train): 0.050648 Loss(val): 0.051491 acc(val): 0.675493
+[19:12:25] Epoch  96: Loss(train): 0.050647 Loss(val): 0.051491 acc(val): 0.675629
+[19:13:50] Epoch  97: Loss(train): 0.050646 Loss(val): 0.051491 acc(val): 0.675561
+[19:14:53] Epoch  98: Loss(train): 0.050645 Loss(val): 0.051490 acc(val): 0.675425
+[19:15:44] Epoch  99: Loss(train): 0.050644 Loss(val): 0.051491 acc(val): 0.675629
+[19:16:42] Epoch 100: Loss(train): 0.050643 Loss(val): 0.051489
+[19:16:51] FINAL(100) Loss(test): 0.051861 Accuarcy: 0.601014
+
+Configuration learning_rate=0.01, decay_step=60
+[19:17:05] INIT Loss(test): 0.146561 Accuarcy: 0.112095
+[19:18:05] Epoch   1: Loss(train): 0.085300 Loss(val): 0.083685 acc(val): 0.301548
+[19:19:02] Epoch   2: Loss(train): 0.066953 Loss(val): 0.065985 acc(val): 0.446310
+[19:19:57] Epoch   3: Loss(train): 0.064071 Loss(val): 0.063177 acc(val): 0.500459
+[19:20:56] Epoch   4: Loss(train): 0.061052 Loss(val): 0.060448 acc(val): 0.525357
+[19:21:48] Epoch   5: Loss(train): 0.059383 Loss(val): 0.059186 acc(val): 0.546735
+[19:22:43] Epoch   6: Loss(train): 0.058582 Loss(val): 0.058385 acc(val): 0.555374
+[19:23:36] Epoch   7: Loss(train): 0.057840 Loss(val): 0.057679 acc(val): 0.568571
+[19:24:32] Epoch   8: Loss(train): 0.057490 Loss(val): 0.057312 acc(val): 0.574575
+[19:25:24] Epoch   9: Loss(train): 0.057308 Loss(val): 0.057126 acc(val): 0.578878
+[19:26:21] Epoch  10: Loss(train): 0.056718 Loss(val): 0.056649 acc(val): 0.588265
+[19:27:16] Epoch  11: Loss(train): 0.056284 Loss(val): 0.056397 acc(val): 0.592483
+[19:28:11] Epoch  12: Loss(train): 0.055857 Loss(val): 0.056005 acc(val): 0.598810
+[19:29:04] Epoch  13: Loss(train): 0.055451 Loss(val): 0.055661 acc(val): 0.603044
+[19:29:59] Epoch  14: Loss(train): 0.055363 Loss(val): 0.055531 acc(val): 0.600935
+[19:30:50] Epoch  15: Loss(train): 0.055445 Loss(val): 0.055545 acc(val): 0.597874
+[19:31:43] Epoch  16: Loss(train): 0.055360 Loss(val): 0.055467 acc(val): 0.598963
+[19:32:36] Epoch  17: Loss(train): 0.055204 Loss(val): 0.055398 acc(val): 0.599099
+[19:33:31] Epoch  18: Loss(train): 0.054983 Loss(val): 0.055307 acc(val): 0.599456
+[19:34:24] Epoch  19: Loss(train): 0.054601 Loss(val): 0.055000 acc(val): 0.606395
+[19:35:21] Epoch  20: Loss(train): 0.054591 Loss(val): 0.054917 acc(val): 0.607279
+[19:36:13] Epoch  21: Loss(train): 0.054396 Loss(val): 0.054738 acc(val): 0.610272
+[19:37:07] Epoch  22: Loss(train): 0.054501 Loss(val): 0.054852 acc(val): 0.605850
+[19:37:59] Epoch  23: Loss(train): 0.054861 Loss(val): 0.055244 acc(val): 0.594490
+[19:38:53] Epoch  24: Loss(train): 0.055324 Loss(val): 0.055727 acc(val): 0.583316
+[19:39:44] Epoch  25: Loss(train): 0.055759 Loss(val): 0.056135 acc(val): 0.574099
+[19:40:46] Epoch  26: Loss(train): 0.056071 Loss(val): 0.056407 acc(val): 0.565527
+[19:41:55] Epoch  27: Loss(train): 0.055936 Loss(val): 0.056284 acc(val): 0.567636
+[19:43:12] Epoch  28: Loss(train): 0.055192 Loss(val): 0.055479 acc(val): 0.581173
+[19:44:18] Epoch  29: Loss(train): 0.054194 Loss(val): 0.054437 acc(val): 0.602874
+[19:45:41] Epoch  30: Loss(train): 0.053646 Loss(val): 0.053798 acc(val): 0.615340
+[19:46:36] Epoch  31: Loss(train): 0.053466 Loss(val): 0.053572 acc(val): 0.619558
+[19:47:32] Epoch  32: Loss(train): 0.053537 Loss(val): 0.053568 acc(val): 0.618214
+[19:48:26] Epoch  33: Loss(train): 0.053592 Loss(val): 0.053585 acc(val): 0.616446
+[19:49:32] Epoch  34: Loss(train): 0.053791 Loss(val): 0.053701 acc(val): 0.610850
+[19:50:27] Epoch  35: Loss(train): 0.053868 Loss(val): 0.053710 acc(val): 0.609422
+[19:51:33] Epoch  36: Loss(train): 0.053803 Loss(val): 0.053639 acc(val): 0.611122
+[19:52:48] Epoch  37: Loss(train): 0.053587 Loss(val): 0.053460 acc(val): 0.617041
+[19:53:47] Epoch  38: Loss(train): 0.053151 Loss(val): 0.053148 acc(val): 0.626616
+[19:54:45] Epoch  39: Loss(train): 0.052732 Loss(val): 0.052863 acc(val): 0.636973
+[19:55:43] Epoch  40: Loss(train): 0.052385 Loss(val): 0.052624 acc(val): 0.646854
+[19:56:37] Epoch  41: Loss(train): 0.052123 Loss(val): 0.052437 acc(val): 0.653316
+[19:57:42] Epoch  42: Loss(train): 0.051956 Loss(val): 0.052307 acc(val): 0.656922
+[19:58:41] Epoch  43: Loss(train): 0.051858 Loss(val): 0.052221 acc(val): 0.658776
+[19:59:43] Epoch  44: Loss(train): 0.051767 Loss(val): 0.052147 acc(val): 0.661769
+[20:00:38] Epoch  45: Loss(train): 0.051678 Loss(val): 0.052093 acc(val): 0.663197
+[20:01:37] Epoch  46: Loss(train): 0.051649 Loss(val): 0.052045 acc(val): 0.664422
+[20:02:33] Epoch  47: Loss(train): 0.051587 Loss(val): 0.051998 acc(val): 0.664983
+[20:03:31] Epoch  48: Loss(train): 0.051510 Loss(val): 0.051950 acc(val): 0.665595
+[20:04:27] Epoch  49: Loss(train): 0.051464 Loss(val): 0.051920 acc(val): 0.665595
+[20:05:24] Epoch  50: Loss(train): 0.051407 Loss(val): 0.051894 acc(val): 0.665867
+[20:06:19] Epoch  51: Loss(train): 0.051346 Loss(val): 0.051874 acc(val): 0.665255
+[20:07:15] Epoch  52: Loss(train): 0.051286 Loss(val): 0.051866 acc(val): 0.665391
+[20:08:09] Epoch  53: Loss(train): 0.051240 Loss(val): 0.051856 acc(val): 0.665731
+[20:09:05] Epoch  54: Loss(train): 0.051194 Loss(val): 0.051873 acc(val): 0.666939
+[20:09:59] Epoch  55: Loss(train): 0.051154 Loss(val): 0.051884 acc(val): 0.668316
+[20:10:57] Epoch  56: Loss(train): 0.051128 Loss(val): 0.051895 acc(val): 0.669065
+[20:12:18] Epoch  57: Loss(train): 0.051107 Loss(val): 0.051928 acc(val): 0.669609
+[20:13:30] Epoch  58: Loss(train): 0.051096 Loss(val): 0.051963 acc(val): 0.668571
+[20:15:09] Epoch  59: Loss(train): 0.051089 Loss(val): 0.051990 acc(val): 0.666327
+[20:16:36] Epoch  60: Loss(train): 0.051084 Loss(val): 0.052012 acc(val): 0.667007
+[20:17:35] Epoch  61: Loss(train): 0.051071 Loss(val): 0.052018 acc(val): 0.667075
+[20:18:56] Epoch  62: Loss(train): 0.051056 Loss(val): 0.052011 acc(val): 0.667279
+[20:20:15] Epoch  63: Loss(train): 0.051039 Loss(val): 0.052001 acc(val): 0.667075
+[20:21:25] Epoch  64: Loss(train): 0.051017 Loss(val): 0.051979 acc(val): 0.667347
+[20:22:32] Epoch  65: Loss(train): 0.050996 Loss(val): 0.051954 acc(val): 0.668571
+[20:23:39] Epoch  66: Loss(train): 0.050975 Loss(val): 0.051927 acc(val): 0.668639
+[20:24:43] Epoch  67: Loss(train): 0.050955 Loss(val): 0.051898 acc(val): 0.669048
+[20:25:45] Epoch  68: Loss(train): 0.050940 Loss(val): 0.051876 acc(val): 0.669864
+[20:26:40] Epoch  69: Loss(train): 0.050923 Loss(val): 0.051856 acc(val): 0.670408
+[20:27:41] Epoch  70: Loss(train): 0.050910 Loss(val): 0.051839 acc(val): 0.671361
+[20:28:42] Epoch  71: Loss(train): 0.050899 Loss(val): 0.051830 acc(val): 0.670748
+[20:29:47] Epoch  72: Loss(train): 0.050885 Loss(val): 0.051802 acc(val): 0.671769
+[20:30:46] Epoch  73: Loss(train): 0.050876 Loss(val): 0.051789 acc(val): 0.671905
+[20:31:45] Epoch  74: Loss(train): 0.050868 Loss(val): 0.051780 acc(val): 0.671769
+[20:32:43] Epoch  75: Loss(train): 0.050859 Loss(val): 0.051767 acc(val): 0.672517
+[20:33:43] Epoch  76: Loss(train): 0.050852 Loss(val): 0.051755 acc(val): 0.673061
+[20:34:42] Epoch  77: Loss(train): 0.050847 Loss(val): 0.051750 acc(val): 0.672789
+[20:35:42] Epoch  78: Loss(train): 0.050841 Loss(val): 0.051743 acc(val): 0.672653
+[20:36:39] Epoch  79: Loss(train): 0.050836 Loss(val): 0.051736 acc(val): 0.672585
+[20:37:39] Epoch  80: Loss(train): 0.050831 Loss(val): 0.051728 acc(val): 0.672245
+[20:38:37] Epoch  81: Loss(train): 0.050826 Loss(val): 0.051721 acc(val): 0.672449
+[20:39:38] Epoch  82: Loss(train): 0.050822 Loss(val): 0.051717 acc(val): 0.672517
+[20:40:37] Epoch  83: Loss(train): 0.050818 Loss(val): 0.051712 acc(val): 0.672381
+[20:41:36] Epoch  84: Loss(train): 0.050814 Loss(val): 0.051704 acc(val): 0.672925
+[20:42:32] Epoch  85: Loss(train): 0.050811 Loss(val): 0.051707 acc(val): 0.672449
+[20:44:12] Epoch  86: Loss(train): 0.050808 Loss(val): 0.051702 acc(val): 0.672449
+[20:45:56] Epoch  87: Loss(train): 0.050805 Loss(val): 0.051700 acc(val): 0.672517
+[20:47:19] Epoch  88: Loss(train): 0.050802 Loss(val): 0.051695 acc(val): 0.672653
+[20:48:38] Epoch  89: Loss(train): 0.050800 Loss(val): 0.051694 acc(val): 0.672721
+[20:49:47] Epoch  90: Loss(train): 0.050797 Loss(val): 0.051688 acc(val): 0.672993
+[20:51:04] Epoch  91: Loss(train): 0.050796 Loss(val): 0.051688 acc(val): 0.672993
+[20:52:29] Epoch  92: Loss(train): 0.050794 Loss(val): 0.051688 acc(val): 0.673129
+[20:53:54] Epoch  93: Loss(train): 0.050792 Loss(val): 0.051685 acc(val): 0.673197
+[20:54:59] Epoch  94: Loss(train): 0.050790 Loss(val): 0.051679 acc(val): 0.673129
+[20:56:01] Epoch  95: Loss(train): 0.050788 Loss(val): 0.051678 acc(val): 0.673129
+[20:57:04] Epoch  96: Loss(train): 0.050787 Loss(val): 0.051676 acc(val): 0.673197
+[20:58:13] Epoch  97: Loss(train): 0.050786 Loss(val): 0.051680 acc(val): 0.673537
+[20:59:20] Epoch  98: Loss(train): 0.050784 Loss(val): 0.051672 acc(val): 0.673265
+[21:00:19] Epoch  99: Loss(train): 0.050783 Loss(val): 0.051673 acc(val): 0.673469
+[21:01:21] Epoch 100: Loss(train): 0.050782 Loss(val): 0.051673
+[21:01:28] FINAL(100) Loss(test): 0.051884 Accuarcy: 0.596351
+
+Configuration learning_rate=0.003, decay_step=20
+[21:01:44] INIT Loss(test): 0.158548 Accuarcy: 0.098919
+[21:02:53] Epoch   1: Loss(train): 0.083241 Loss(val): 0.081338 acc(val): 0.315714
+[21:03:52] Epoch   2: Loss(train): 0.068011 Loss(val): 0.066275 acc(val): 0.454677
+[21:04:49] Epoch   3: Loss(train): 0.064500 Loss(val): 0.062939 acc(val): 0.506276
+[21:05:51] Epoch   4: Loss(train): 0.062763 Loss(val): 0.061977 acc(val): 0.521054
+[21:06:49] Epoch   5: Loss(train): 0.060735 Loss(val): 0.060340 acc(val): 0.539966
+[21:07:50] Epoch   6: Loss(train): 0.059243 Loss(val): 0.058967 acc(val): 0.554847
+[21:08:47] Epoch   7: Loss(train): 0.058659 Loss(val): 0.058494 acc(val): 0.556156
+[21:09:46] Epoch   8: Loss(train): 0.058254 Loss(val): 0.058243 acc(val): 0.558197
+[21:10:44] Epoch   9: Loss(train): 0.058391 Loss(val): 0.058417 acc(val): 0.550850
+[21:11:44] Epoch  10: Loss(train): 0.058190 Loss(val): 0.058318 acc(val): 0.549354
+[21:12:40] Epoch  11: Loss(train): 0.057913 Loss(val): 0.058267 acc(val): 0.551378
+[21:14:00] Epoch  12: Loss(train): 0.057026 Loss(val): 0.057716 acc(val): 0.558044
+[21:15:32] Epoch  13: Loss(train): 0.056899 Loss(val): 0.057677 acc(val): 0.556956
+[21:16:50] Epoch  14: Loss(train): 0.056948 Loss(val): 0.057710 acc(val): 0.556480
+[21:18:38] Epoch  15: Loss(train): 0.056834 Loss(val): 0.057578 acc(val): 0.559133
+[21:20:31] Epoch  16: Loss(train): 0.056879 Loss(val): 0.057601 acc(val): 0.558929
+[21:22:05] Epoch  17: Loss(train): 0.056644 Loss(val): 0.057316 acc(val): 0.562126
+[21:23:53] Epoch  18: Loss(train): 0.056123 Loss(val): 0.056696 acc(val): 0.573963
+[21:24:56] Epoch  19: Loss(train): 0.055539 Loss(val): 0.055993 acc(val): 0.589218
+[21:25:58] Epoch  20: Loss(train): 0.054817 Loss(val): 0.055192 acc(val): 0.604456
+[21:27:20] Epoch  21: Loss(train): 0.054251 Loss(val): 0.054556 acc(val): 0.617109
+[21:28:24] Epoch  22: Loss(train): 0.053735 Loss(val): 0.054037 acc(val): 0.628810
+[21:29:40] Epoch  23: Loss(train): 0.053590 Loss(val): 0.053807 acc(val): 0.629881
+[21:30:46] Epoch  24: Loss(train): 0.053532 Loss(val): 0.053687 acc(val): 0.628997
+[21:31:47] Epoch  25: Loss(train): 0.053535 Loss(val): 0.053628 acc(val): 0.628997
+[21:32:51] Epoch  26: Loss(train): 0.053524 Loss(val): 0.053611 acc(val): 0.626071
+[21:33:53] Epoch  27: Loss(train): 0.053373 Loss(val): 0.053523 acc(val): 0.628384
+[21:35:07] Epoch  28: Loss(train): 0.053050 Loss(val): 0.053344 acc(val): 0.634711
+[21:36:09] Epoch  29: Loss(train): 0.052943 Loss(val): 0.053259 acc(val): 0.636071
+[21:37:08] Epoch  30: Loss(train): 0.052761 Loss(val): 0.053106 acc(val): 0.640153
+[21:38:11] Epoch  31: Loss(train): 0.052696 Loss(val): 0.053025 acc(val): 0.642670
+[21:39:12] Epoch  32: Loss(train): 0.052689 Loss(val): 0.052930 acc(val): 0.642330
+[21:40:15] Epoch  33: Loss(train): 0.052740 Loss(val): 0.052846 acc(val): 0.641514
+[21:41:14] Epoch  34: Loss(train): 0.052706 Loss(val): 0.052756 acc(val): 0.642058
+[21:42:16] Epoch  35: Loss(train): 0.052765 Loss(val): 0.052704 acc(val): 0.640017
+[21:43:14] Epoch  36: Loss(train): 0.052756 Loss(val): 0.052639 acc(val): 0.638180
+[21:44:17] Epoch  37: Loss(train): 0.052711 Loss(val): 0.052555 acc(val): 0.640153
+[21:45:17] Epoch  38: Loss(train): 0.052549 Loss(val): 0.052426 acc(val): 0.644031
+[21:46:26] Epoch  39: Loss(train): 0.052322 Loss(val): 0.052297 acc(val): 0.650969
+[21:48:10] Epoch  40: Loss(train): 0.052060 Loss(val): 0.052150 acc(val): 0.658333
+[21:50:08] Epoch  41: Loss(train): 0.051793 Loss(val): 0.052026 acc(val): 0.665612
+[21:51:53] Epoch  42: Loss(train): 0.051636 Loss(val): 0.051965 acc(val): 0.668197
+[21:53:38] Epoch  43: Loss(train): 0.051514 Loss(val): 0.051931 acc(val): 0.670646
+[21:55:21] Epoch  44: Loss(train): 0.051438 Loss(val): 0.051905 acc(val): 0.669966
+[21:57:04] Epoch  45: Loss(train): 0.051403 Loss(val): 0.051888 acc(val): 0.670714
+[21:58:07] Epoch  46: Loss(train): 0.051358 Loss(val): 0.051865 acc(val): 0.670918
+[21:59:30] Epoch  47: Loss(train): 0.051337 Loss(val): 0.051848 acc(val): 0.670782
+[22:00:47] Epoch  48: Loss(train): 0.051338 Loss(val): 0.051840 acc(val): 0.670714
+[22:02:03] Epoch  49: Loss(train): 0.051314 Loss(val): 0.051821 acc(val): 0.670646
+[22:03:13] Epoch  50: Loss(train): 0.051277 Loss(val): 0.051795 acc(val): 0.670782
+[22:04:19] Epoch  51: Loss(train): 0.051270 Loss(val): 0.051777 acc(val): 0.671599
+[22:05:26] Epoch  52: Loss(train): 0.051233 Loss(val): 0.051768 acc(val): 0.671259
+[22:06:34] Epoch  53: Loss(train): 0.051212 Loss(val): 0.051756 acc(val): 0.671871
+[22:07:37] Epoch  54: Loss(train): 0.051174 Loss(val): 0.051745 acc(val): 0.673163
+[22:08:44] Epoch  55: Loss(train): 0.051122 Loss(val): 0.051735 acc(val): 0.673639
+[22:09:47] Epoch  56: Loss(train): 0.051073 Loss(val): 0.051735 acc(val): 0.672959
+[22:10:53] Epoch  57: Loss(train): 0.051029 Loss(val): 0.051744 acc(val): 0.672959
+[22:11:53] Epoch  58: Loss(train): 0.051000 Loss(val): 0.051749 acc(val): 0.674252
+[22:12:56] Epoch  59: Loss(train): 0.050973 Loss(val): 0.051769 acc(val): 0.674524
+[22:13:57] Epoch  60: Loss(train): 0.050952 Loss(val): 0.051795 acc(val): 0.673231
+[22:15:00] Epoch  61: Loss(train): 0.050937 Loss(val): 0.051807 acc(val): 0.673724
+[22:16:02] Epoch  62: Loss(train): 0.050928 Loss(val): 0.051828 acc(val): 0.673588
+[22:17:06] Epoch  63: Loss(train): 0.050916 Loss(val): 0.051835 acc(val): 0.673861
+[22:18:08] Epoch  64: Loss(train): 0.050908 Loss(val): 0.051846 acc(val): 0.673452
+[22:19:37] Epoch  65: Loss(train): 0.050891 Loss(val): 0.051827 acc(val): 0.673861
+[22:21:30] Epoch  66: Loss(train): 0.050875 Loss(val): 0.051813 acc(val): 0.673861
+[22:23:05] Epoch  67: Loss(train): 0.050859 Loss(val): 0.051792 acc(val): 0.674269
+[22:24:45] Epoch  68: Loss(train): 0.050848 Loss(val): 0.051785 acc(val): 0.674065
+[22:26:41] Epoch  69: Loss(train): 0.050833 Loss(val): 0.051761 acc(val): 0.675085
+[22:28:20] Epoch  70: Loss(train): 0.050818 Loss(val): 0.051735 acc(val): 0.675425
+[22:29:44] Epoch  71: Loss(train): 0.050805 Loss(val): 0.051714 acc(val): 0.676105
+[22:31:19] Epoch  72: Loss(train): 0.050798 Loss(val): 0.051715 acc(val): 0.676037
+[22:32:43] Epoch  73: Loss(train): 0.050788 Loss(val): 0.051700 acc(val): 0.676241
+[22:33:55] Epoch  74: Loss(train): 0.050779 Loss(val): 0.051684 acc(val): 0.676786
+[22:35:13] Epoch  75: Loss(train): 0.050772 Loss(val): 0.051674 acc(val): 0.676582
+[22:36:24] Epoch  76: Loss(train): 0.050765 Loss(val): 0.051667 acc(val): 0.676718
+[22:37:34] Epoch  77: Loss(train): 0.050759 Loss(val): 0.051653 acc(val): 0.677058
+[22:38:41] Epoch  78: Loss(train): 0.050753 Loss(val): 0.051646 acc(val): 0.676990
+[22:39:49] Epoch  79: Loss(train): 0.050748 Loss(val): 0.051638 acc(val): 0.677058
+[22:41:00] Epoch  80: Loss(train): 0.050743 Loss(val): 0.051630 acc(val): 0.676990
+[22:42:08] Epoch  81: Loss(train): 0.050740 Loss(val): 0.051629 acc(val): 0.677058
+[22:43:14] Epoch  82: Loss(train): 0.050735 Loss(val): 0.051620 acc(val): 0.676650
+[22:44:21] Epoch  83: Loss(train): 0.050732 Loss(val): 0.051618 acc(val): 0.676582
+[22:45:26] Epoch  84: Loss(train): 0.050728 Loss(val): 0.051612 acc(val): 0.676922
+[22:46:32] Epoch  85: Loss(train): 0.050725 Loss(val): 0.051609 acc(val): 0.676990
+[22:47:37] Epoch  86: Loss(train): 0.050722 Loss(val): 0.051603 acc(val): 0.676854
+[22:48:44] Epoch  87: Loss(train): 0.050719 Loss(val): 0.051599 acc(val): 0.677126
+[22:49:47] Epoch  88: Loss(train): 0.050716 Loss(val): 0.051596 acc(val): 0.676990
+[22:50:53] Epoch  89: Loss(train): 0.050714 Loss(val): 0.051596 acc(val): 0.676990
+[22:51:58] Epoch  90: Loss(train): 0.050711 Loss(val): 0.051589 acc(val): 0.677398
+[22:53:07] Epoch  91: Loss(train): 0.050710 Loss(val): 0.051587 acc(val): 0.677058
+[22:54:13] Epoch  92: Loss(train): 0.050708 Loss(val): 0.051584 acc(val): 0.677534
+[22:55:22] Epoch  93: Loss(train): 0.050706 Loss(val): 0.051585 acc(val): 0.677534
+[22:56:28] Epoch  94: Loss(train): 0.050705 Loss(val): 0.051585 acc(val): 0.677466
+[22:57:38] Epoch  95: Loss(train): 0.050703 Loss(val): 0.051586 acc(val): 0.677330
+[22:58:44] Epoch  96: Loss(train): 0.050702 Loss(val): 0.051580 acc(val): 0.677466
+[22:59:53] Epoch  97: Loss(train): 0.050700 Loss(val): 0.051578 acc(val): 0.677398
+[23:00:59] Epoch  98: Loss(train): 0.050699 Loss(val): 0.051579 acc(val): 0.677466
+[23:02:09] Epoch  99: Loss(train): 0.050698 Loss(val): 0.051577 acc(val): 0.677602
+[23:03:16] Epoch 100: Loss(train): 0.050697 Loss(val): 0.051575
+[23:03:25] FINAL(100) Loss(test): 0.051971 Accuarcy: 0.586486
+
+Configuration learning_rate=0.003, decay_step=40
+[23:03:43] INIT Loss(test): 0.119407 Accuarcy: 0.131892
+[23:04:57] Epoch   1: Loss(train): 0.086009 Loss(val): 0.084843 acc(val): 0.304133
+[23:06:07] Epoch   2: Loss(train): 0.068264 Loss(val): 0.066110 acc(val): 0.453316
+[23:07:15] Epoch   3: Loss(train): 0.064122 Loss(val): 0.062628 acc(val): 0.517568
+[23:08:25] Epoch   4: Loss(train): 0.060438 Loss(val): 0.059920 acc(val): 0.540153
+[23:09:34] Epoch   5: Loss(train): 0.059801 Loss(val): 0.059508 acc(val): 0.544507
+[23:10:47] Epoch   6: Loss(train): 0.059259 Loss(val): 0.058924 acc(val): 0.546412
+[23:12:21] Epoch   7: Loss(train): 0.058629 Loss(val): 0.058101 acc(val): 0.558673
+[23:13:41] Epoch   8: Loss(train): 0.058048 Loss(val): 0.057791 acc(val): 0.564099
+[23:14:46] Epoch   9: Loss(train): 0.058454 Loss(val): 0.058416 acc(val): 0.551122
+[23:15:55] Epoch  10: Loss(train): 0.058675 Loss(val): 0.058777 acc(val): 0.543724
+[23:17:04] Epoch  11: Loss(train): 0.058370 Loss(val): 0.058430 acc(val): 0.546582
+[23:19:16] Epoch  12: Loss(train): 0.057999 Loss(val): 0.058021 acc(val): 0.547126
+[23:21:09] Epoch  13: Loss(train): 0.057656 Loss(val): 0.057744 acc(val): 0.555425
+[23:23:13] Epoch  14: Loss(train): 0.057686 Loss(val): 0.057843 acc(val): 0.555289
+[23:24:54] Epoch  15: Loss(train): 0.058182 Loss(val): 0.058384 acc(val): 0.554949
+[23:26:00] Epoch  16: Loss(train): 0.058460 Loss(val): 0.058770 acc(val): 0.556037
+[23:27:03] Epoch  17: Loss(train): 0.058416 Loss(val): 0.058736 acc(val): 0.558486
+[23:28:10] Epoch  18: Loss(train): 0.057461 Loss(val): 0.057750 acc(val): 0.571888
+[23:29:45] Epoch  19: Loss(train): 0.056130 Loss(val): 0.056310 acc(val): 0.588895
+[23:31:09] Epoch  20: Loss(train): 0.054899 Loss(val): 0.055004 acc(val): 0.607738
+[23:32:13] Epoch  21: Loss(train): 0.054311 Loss(val): 0.054304 acc(val): 0.618214
+[23:33:22] Epoch  22: Loss(train): 0.054011 Loss(val): 0.053956 acc(val): 0.620323
+[23:34:39] Epoch  23: Loss(train): 0.053804 Loss(val): 0.053789 acc(val): 0.625425
+[23:35:56] Epoch  24: Loss(train): 0.053912 Loss(val): 0.053940 acc(val): 0.621361
+[23:37:02] Epoch  25: Loss(train): 0.053980 Loss(val): 0.054102 acc(val): 0.616105
+[23:38:12] Epoch  26: Loss(train): 0.054036 Loss(val): 0.054221 acc(val): 0.612364
+[23:39:21] Epoch  27: Loss(train): 0.054032 Loss(val): 0.054174 acc(val): 0.612636
+[23:40:32] Epoch  28: Loss(train): 0.053859 Loss(val): 0.053952 acc(val): 0.615374
+[23:41:39] Epoch  29: Loss(train): 0.053869 Loss(val): 0.053855 acc(val): 0.616395
+[23:42:47] Epoch  30: Loss(train): 0.053897 Loss(val): 0.053789 acc(val): 0.615714
+[23:43:53] Epoch  31: Loss(train): 0.053977 Loss(val): 0.053684 acc(val): 0.612789
+[23:45:01] Epoch  32: Loss(train): 0.054146 Loss(val): 0.053690 acc(val): 0.608929
+[23:46:05] Epoch  33: Loss(train): 0.054114 Loss(val): 0.053585 acc(val): 0.607143
+[23:47:12] Epoch  34: Loss(train): 0.053837 Loss(val): 0.053342 acc(val): 0.614286
+[23:48:54] Epoch  35: Loss(train): 0.053427 Loss(val): 0.053079 acc(val): 0.621905
+[23:51:05] Epoch  36: Loss(train): 0.052834 Loss(val): 0.052732 acc(val): 0.637143
+[23:52:37] Epoch  37: Loss(train): 0.052377 Loss(val): 0.052473 acc(val): 0.647075
+[23:53:55] Epoch  38: Loss(train): 0.052059 Loss(val): 0.052323 acc(val): 0.655765
+[23:55:00] Epoch  39: Loss(train): 0.051822 Loss(val): 0.052194 acc(val): 0.659711
+[23:56:37] Epoch  40: Loss(train): 0.051687 Loss(val): 0.052090 acc(val): 0.662432
+[23:57:56] Epoch  41: Loss(train): 0.051599 Loss(val): 0.052035 acc(val): 0.663452
+[23:59:27] Epoch  42: Loss(train): 0.051543 Loss(val): 0.052002 acc(val): 0.666105
+[00:00:40] Epoch  43: Loss(train): 0.051492 Loss(val): 0.051979 acc(val): 0.665289
+[00:01:55] Epoch  44: Loss(train): 0.051441 Loss(val): 0.051964 acc(val): 0.666514
+[00:03:10] Epoch  45: Loss(train): 0.051421 Loss(val): 0.051940 acc(val): 0.668078
+[00:04:31] Epoch  46: Loss(train): 0.051367 Loss(val): 0.051917 acc(val): 0.668827
+[00:05:37] Epoch  47: Loss(train): 0.051326 Loss(val): 0.051903 acc(val): 0.669031
+[00:06:46] Epoch  48: Loss(train): 0.051282 Loss(val): 0.051888 acc(val): 0.670119
+[00:07:54] Epoch  49: Loss(train): 0.051247 Loss(val): 0.051872 acc(val): 0.670391
+[00:09:08] Epoch  50: Loss(train): 0.051210 Loss(val): 0.051871 acc(val): 0.670391
+[00:10:13] Epoch  51: Loss(train): 0.051175 Loss(val): 0.051883 acc(val): 0.670187
+[00:11:22] Epoch  52: Loss(train): 0.051149 Loss(val): 0.051886 acc(val): 0.670051
+[00:12:27] Epoch  53: Loss(train): 0.051129 Loss(val): 0.051913 acc(val): 0.669099
+[00:13:37] Epoch  54: Loss(train): 0.051116 Loss(val): 0.051936 acc(val): 0.667330
+[00:14:45] Epoch  55: Loss(train): 0.051102 Loss(val): 0.051941 acc(val): 0.667602
+[00:15:57] Epoch  56: Loss(train): 0.051099 Loss(val): 0.051973 acc(val): 0.666718
+[00:17:04] Epoch  57: Loss(train): 0.051085 Loss(val): 0.051980 acc(val): 0.666718
+[00:18:26] Epoch  58: Loss(train): 0.051069 Loss(val): 0.051975 acc(val): 0.666650
+[00:20:26] Epoch  59: Loss(train): 0.051041 Loss(val): 0.051938 acc(val): 0.667602
+[00:21:56] Epoch  60: Loss(train): 0.051020 Loss(val): 0.051919 acc(val): 0.667738
+[00:23:31] Epoch  61: Loss(train): 0.050994 Loss(val): 0.051884 acc(val): 0.668963
+[00:24:50] Epoch  62: Loss(train): 0.050970 Loss(val): 0.051851 acc(val): 0.669915
+[00:26:36] Epoch  63: Loss(train): 0.050952 Loss(val): 0.051824 acc(val): 0.670187
+[00:27:56] Epoch  64: Loss(train): 0.050932 Loss(val): 0.051791 acc(val): 0.671207
+[00:29:25] Epoch  65: Loss(train): 0.050915 Loss(val): 0.051762 acc(val): 0.671888
+[00:30:38] Epoch  66: Loss(train): 0.050900 Loss(val): 0.051739 acc(val): 0.671820
+[00:31:47] Epoch  67: Loss(train): 0.050888 Loss(val): 0.051720 acc(val): 0.671956
+[00:33:12] Epoch  68: Loss(train): 0.050880 Loss(val): 0.051714 acc(val): 0.671956
+[00:34:24] Epoch  69: Loss(train): 0.050870 Loss(val): 0.051703 acc(val): 0.672024
+[00:35:42] Epoch  70: Loss(train): 0.050862 Loss(val): 0.051696 acc(val): 0.672636
+[00:36:54] Epoch  71: Loss(train): 0.050854 Loss(val): 0.051680 acc(val): 0.673044
+[00:38:13] Epoch  72: Loss(train): 0.050847 Loss(val): 0.051672 acc(val): 0.672840
+[00:39:21] Epoch  73: Loss(train): 0.050842 Loss(val): 0.051672 acc(val): 0.671888
+[00:40:37] Epoch  74: Loss(train): 0.050836 Loss(val): 0.051663 acc(val): 0.672364
+[00:41:45] Epoch  75: Loss(train): 0.050830 Loss(val): 0.051650 acc(val): 0.672432
+[00:43:00] Epoch  76: Loss(train): 0.050825 Loss(val): 0.051648 acc(val): 0.672840
+[00:44:08] Epoch  77: Loss(train): 0.050820 Loss(val): 0.051643 acc(val): 0.672568
+[00:45:20] Epoch  78: Loss(train): 0.050817 Loss(val): 0.051644 acc(val): 0.672500
+[00:46:30] Epoch  79: Loss(train): 0.050812 Loss(val): 0.051636 acc(val): 0.672364
+[00:47:41] Epoch  80: Loss(train): 0.050809 Loss(val): 0.051635 acc(val): 0.672704
+[00:48:51] Epoch  81: Loss(train): 0.050805 Loss(val): 0.051629 acc(val): 0.672840
+[00:50:33] Epoch  82: Loss(train): 0.050801 Loss(val): 0.051625 acc(val): 0.672704
+[00:52:14] Epoch  83: Loss(train): 0.050798 Loss(val): 0.051623 acc(val): 0.672772
+[00:53:55] Epoch  84: Loss(train): 0.050795 Loss(val): 0.051622 acc(val): 0.672704
+[00:55:43] Epoch  85: Loss(train): 0.050792 Loss(val): 0.051617 acc(val): 0.673112
+[00:57:16] Epoch  86: Loss(train): 0.050790 Loss(val): 0.051615 acc(val): 0.673248
+[00:58:46] Epoch  87: Loss(train): 0.050787 Loss(val): 0.051613 acc(val): 0.673520
+[01:00:14] Epoch  88: Loss(train): 0.050785 Loss(val): 0.051612 acc(val): 0.673248
+[01:01:36] Epoch  89: Loss(train): 0.050783 Loss(val): 0.051612 acc(val): 0.673180
+[01:02:53] Epoch  90: Loss(train): 0.050781 Loss(val): 0.051609 acc(val): 0.673248
+[01:04:05] Epoch  91: Loss(train): 0.050779 Loss(val): 0.051608 acc(val): 0.673316
+[01:05:24] Epoch  92: Loss(train): 0.050778 Loss(val): 0.051606 acc(val): 0.673384
+[01:06:45] Epoch  93: Loss(train): 0.050776 Loss(val): 0.051605 acc(val): 0.673452
+[01:07:59] Epoch  94: Loss(train): 0.050775 Loss(val): 0.051604 acc(val): 0.673588
+[01:09:13] Epoch  95: Loss(train): 0.050774 Loss(val): 0.051602 acc(val): 0.673452
+[01:10:25] Epoch  96: Loss(train): 0.050772 Loss(val): 0.051599 acc(val): 0.673316
+[01:11:35] Epoch  97: Loss(train): 0.050771 Loss(val): 0.051599 acc(val): 0.673520
+[01:12:45] Epoch  98: Loss(train): 0.050770 Loss(val): 0.051600 acc(val): 0.673588
+[01:13:54] Epoch  99: Loss(train): 0.050769 Loss(val): 0.051597 acc(val): 0.673452
+[01:15:04] Epoch 100: Loss(train): 0.050768 Loss(val): 0.051596
+[01:15:13] FINAL(100) Loss(test): 0.052151 Accuarcy: 0.602703
+
+Configuration learning_rate=0.003, decay_step=60
+[01:15:31] INIT Loss(test): 0.118268 Accuarcy: 0.130541
+[01:16:50] Epoch   1: Loss(train): 0.084326 Loss(val): 0.082111 acc(val): 0.317891
+[01:18:01] Epoch   2: Loss(train): 0.067675 Loss(val): 0.066096 acc(val): 0.453265
+[01:19:07] Epoch   3: Loss(train): 0.063037 Loss(val): 0.061884 acc(val): 0.512517
+[01:20:51] Epoch   4: Loss(train): 0.060235 Loss(val): 0.059597 acc(val): 0.557024
+[01:22:50] Epoch   5: Loss(train): 0.059429 Loss(val): 0.059154 acc(val): 0.559099
+[01:24:33] Epoch   6: Loss(train): 0.059058 Loss(val): 0.058983 acc(val): 0.559303
+[01:26:15] Epoch   7: Loss(train): 0.058302 Loss(val): 0.058147 acc(val): 0.566718
+[01:27:41] Epoch   8: Loss(train): 0.058073 Loss(val): 0.057841 acc(val): 0.566241
+[01:29:14] Epoch   9: Loss(train): 0.057751 Loss(val): 0.057718 acc(val): 0.568078
+[01:30:49] Epoch  10: Loss(train): 0.057868 Loss(val): 0.057935 acc(val): 0.561003
+[01:32:08] Epoch  11: Loss(train): 0.057844 Loss(val): 0.058059 acc(val): 0.559439
+[01:33:28] Epoch  12: Loss(train): 0.057605 Loss(val): 0.057729 acc(val): 0.561207
+[01:34:45] Epoch  13: Loss(train): 0.056757 Loss(val): 0.056798 acc(val): 0.574422
+[01:36:09] Epoch  14: Loss(train): 0.056279 Loss(val): 0.056278 acc(val): 0.585034
+[01:37:26] Epoch  15: Loss(train): 0.056084 Loss(val): 0.056146 acc(val): 0.587619
+[01:38:40] Epoch  16: Loss(train): 0.056607 Loss(val): 0.056665 acc(val): 0.580119
+[01:39:54] Epoch  17: Loss(train): 0.057447 Loss(val): 0.057562 acc(val): 0.563656
+[01:41:13] Epoch  18: Loss(train): 0.057931 Loss(val): 0.058062 acc(val): 0.555493
+[01:42:26] Epoch  19: Loss(train): 0.057932 Loss(val): 0.058026 acc(val): 0.556786
+[01:43:42] Epoch  20: Loss(train): 0.056523 Loss(val): 0.056666 acc(val): 0.581956
+[01:44:55] Epoch  21: Loss(train): 0.054813 Loss(val): 0.054965 acc(val): 0.613197
+[01:46:10] Epoch  22: Loss(train): 0.053830 Loss(val): 0.054018 acc(val): 0.632517
+[01:47:20] Epoch  23: Loss(train): 0.053511 Loss(val): 0.053685 acc(val): 0.635442
+[01:48:35] Epoch  24: Loss(train): 0.053198 Loss(val): 0.053462 acc(val): 0.640272
+[01:49:48] Epoch  25: Loss(train): 0.053054 Loss(val): 0.053336 acc(val): 0.642041
+[01:51:41] Epoch  26: Loss(train): 0.052948 Loss(val): 0.053279 acc(val): 0.643265
+[01:53:14] Epoch  27: Loss(train): 0.052850 Loss(val): 0.053252 acc(val): 0.644490
+[01:54:52] Epoch  28: Loss(train): 0.052809 Loss(val): 0.053145 acc(val): 0.644626
+[01:56:30] Epoch  29: Loss(train): 0.052700 Loss(val): 0.053007 acc(val): 0.646735
+[01:58:28] Epoch  30: Loss(train): 0.052565 Loss(val): 0.052855 acc(val): 0.650000
+[01:59:41] Epoch  31: Loss(train): 0.052525 Loss(val): 0.052728 acc(val): 0.651769
+[02:01:14] Epoch  32: Loss(train): 0.052521 Loss(val): 0.052635 acc(val): 0.649660
+[02:02:32] Epoch  33: Loss(train): 0.052542 Loss(val): 0.052554 acc(val): 0.649252
+[02:04:04] Epoch  34: Loss(train): 0.052591 Loss(val): 0.052510 acc(val): 0.646463
+[02:05:17] Epoch  35: Loss(train): 0.052629 Loss(val): 0.052478 acc(val): 0.645731
+[02:06:41] Epoch  36: Loss(train): 0.052609 Loss(val): 0.052442 acc(val): 0.647160
+[02:07:55] Epoch  37: Loss(train): 0.052505 Loss(val): 0.052344 acc(val): 0.649065
+[02:09:16] Epoch  38: Loss(train): 0.052283 Loss(val): 0.052196 acc(val): 0.653827
+[02:10:30] Epoch  39: Loss(train): 0.052129 Loss(val): 0.052099 acc(val): 0.656616
+[02:11:46] Epoch  40: Loss(train): 0.051865 Loss(val): 0.051973 acc(val): 0.660901
+[02:12:59] Epoch  41: Loss(train): 0.051727 Loss(val): 0.051912 acc(val): 0.664643
+[02:14:16] Epoch  42: Loss(train): 0.051614 Loss(val): 0.051869 acc(val): 0.666888
+[02:15:26] Epoch  43: Loss(train): 0.051569 Loss(val): 0.051843 acc(val): 0.666003
+[02:16:41] Epoch  44: Loss(train): 0.051505 Loss(val): 0.051823 acc(val): 0.667024
+[02:17:52] Epoch  45: Loss(train): 0.051464 Loss(val): 0.051800 acc(val): 0.667568
+[02:19:07] Epoch  46: Loss(train): 0.051440 Loss(val): 0.051774 acc(val): 0.667432
+[02:20:20] Epoch  47: Loss(train): 0.051418 Loss(val): 0.051756 acc(val): 0.667976
+[02:22:02] Epoch  48: Loss(train): 0.051364 Loss(val): 0.051738 acc(val): 0.669813
+[02:23:45] Epoch  49: Loss(train): 0.051345 Loss(val): 0.051721 acc(val): 0.669201
+[02:25:46] Epoch  50: Loss(train): 0.051294 Loss(val): 0.051708 acc(val): 0.671037
+[02:27:28] Epoch  51: Loss(train): 0.051244 Loss(val): 0.051699 acc(val): 0.670765
+[02:29:26] Epoch  52: Loss(train): 0.051217 Loss(val): 0.051687 acc(val): 0.671241
+[02:30:49] Epoch  53: Loss(train): 0.051168 Loss(val): 0.051685 acc(val): 0.671582
+[02:32:24] Epoch  54: Loss(train): 0.051129 Loss(val): 0.051696 acc(val): 0.672262
+[02:33:48] Epoch  55: Loss(train): 0.051096 Loss(val): 0.051717 acc(val): 0.670833
+[02:35:18] Epoch  56: Loss(train): 0.051069 Loss(val): 0.051752 acc(val): 0.669609
+[02:36:37] Epoch  57: Loss(train): 0.051054 Loss(val): 0.051791 acc(val): 0.668793
+[02:38:02] Epoch  58: Loss(train): 0.051046 Loss(val): 0.051823 acc(val): 0.668793
+[02:39:22] Epoch  59: Loss(train): 0.051033 Loss(val): 0.051830 acc(val): 0.668180
+[02:40:42] Epoch  60: Loss(train): 0.051030 Loss(val): 0.051859 acc(val): 0.667296
+[02:41:56] Epoch  61: Loss(train): 0.051019 Loss(val): 0.051869 acc(val): 0.666276
+[02:43:18] Epoch  62: Loss(train): 0.051008 Loss(val): 0.051871 acc(val): 0.666003
+[02:44:34] Epoch  63: Loss(train): 0.050986 Loss(val): 0.051852 acc(val): 0.665935
+[02:45:51] Epoch  64: Loss(train): 0.050960 Loss(val): 0.051816 acc(val): 0.667364
+[02:47:05] Epoch  65: Loss(train): 0.050938 Loss(val): 0.051782 acc(val): 0.668316
+[02:48:24] Epoch  66: Loss(train): 0.050921 Loss(val): 0.051765 acc(val): 0.668793
+[02:49:39] Epoch  67: Loss(train): 0.050905 Loss(val): 0.051737 acc(val): 0.669337
+[02:51:00] Epoch  68: Loss(train): 0.050893 Loss(val): 0.051723 acc(val): 0.669745
+[02:52:31] Epoch  69: Loss(train): 0.050879 Loss(val): 0.051702 acc(val): 0.670221
+[02:54:48] Epoch  70: Loss(train): 0.050866 Loss(val): 0.051684 acc(val): 0.669813
+[02:56:36] Epoch  71: Loss(train): 0.050855 Loss(val): 0.051657 acc(val): 0.670425
+[02:58:05] Epoch  72: Loss(train): 0.050848 Loss(val): 0.051651 acc(val): 0.670357
+[02:59:25] Epoch  73: Loss(train): 0.050842 Loss(val): 0.051645 acc(val): 0.670765
+[03:01:09] Epoch  74: Loss(train): 0.050834 Loss(val): 0.051638 acc(val): 0.670901
+[03:02:44] Epoch  75: Loss(train): 0.050828 Loss(val): 0.051627 acc(val): 0.671378
+[03:04:13] Epoch  76: Loss(train): 0.050821 Loss(val): 0.051613 acc(val): 0.671582
+[03:05:28] Epoch  77: Loss(train): 0.050817 Loss(val): 0.051616 acc(val): 0.671446
+[03:07:01] Epoch  78: Loss(train): 0.050811 Loss(val): 0.051602 acc(val): 0.671446
+[03:08:26] Epoch  79: Loss(train): 0.050808 Loss(val): 0.051602 acc(val): 0.671922
+[03:09:55] Epoch  80: Loss(train): 0.050804 Loss(val): 0.051598 acc(val): 0.672262
+[03:11:08] Epoch  81: Loss(train): 0.050800 Loss(val): 0.051593 acc(val): 0.671990
+[03:12:34] Epoch  82: Loss(train): 0.050796 Loss(val): 0.051591 acc(val): 0.672398
+[03:13:52] Epoch  83: Loss(train): 0.050792 Loss(val): 0.051581 acc(val): 0.672534
+[03:15:11] Epoch  84: Loss(train): 0.050789 Loss(val): 0.051579 acc(val): 0.672466
+[03:16:28] Epoch  85: Loss(train): 0.050786 Loss(val): 0.051579 acc(val): 0.672398
+[03:17:47] Epoch  86: Loss(train): 0.050783 Loss(val): 0.051572 acc(val): 0.672398
+[03:19:04] Epoch  87: Loss(train): 0.050781 Loss(val): 0.051570 acc(val): 0.672534
+[03:20:23] Epoch  88: Loss(train): 0.050779 Loss(val): 0.051571 acc(val): 0.672602
+[03:21:39] Epoch  89: Loss(train): 0.050777 Loss(val): 0.051571 acc(val): 0.672330
+[03:23:02] Epoch  90: Loss(train): 0.050774 Loss(val): 0.051563 acc(val): 0.672534
+[03:24:57] Epoch  91: Loss(train): 0.050773 Loss(val): 0.051561 acc(val): 0.672602
+[03:27:00] Epoch  92: Loss(train): 0.050771 Loss(val): 0.051558 acc(val): 0.672670
+[03:29:00] Epoch  93: Loss(train): 0.050769 Loss(val): 0.051557 acc(val): 0.672602
+[03:31:00] Epoch  94: Loss(train): 0.050767 Loss(val): 0.051552 acc(val): 0.672738
+[03:32:35] Epoch  95: Loss(train): 0.050766 Loss(val): 0.051551 acc(val): 0.672874
+[03:34:01] Epoch  96: Loss(train): 0.050765 Loss(val): 0.051556 acc(val): 0.672670
+[03:35:31] Epoch  97: Loss(train): 0.050764 Loss(val): 0.051553 acc(val): 0.673146
+[03:37:11] Epoch  98: Loss(train): 0.050763 Loss(val): 0.051555 acc(val): 0.672942
+[03:38:30] Epoch  99: Loss(train): 0.050762 Loss(val): 0.051552 acc(val): 0.673010
+[03:39:58] Epoch 100: Loss(train): 0.050761 Loss(val): 0.051550
+[03:40:09] FINAL(100) Loss(test): 0.051995 Accuarcy: 0.592703