[vae_0] training getter supervised:
0 train: [0] = 0.4254
0 train: [0] = 88.1%
0 val: [0] = 0.2212
0 val: [0] = 93.7%
1 train: [0] = 0.1895
1 train: [0] = 94.4%
1 val: [0] = 0.1594
1 val: [0] = 95.6%
2 train: [0] = 0.1363
2 train: [0] = 95.9%
2 val: [0] = 0.125
2 val: [0] = 96.3%
3 train: [0] = 0.1088
3 train: [0] = 96.8%
3 val: [0] = 0.108
3 val: [0] = 96.8%
4 train: [0] = 0.08869
4 train: [0] = 97.3%
4 val: [0] = 0.1066
4 val: [0] = 96.7%
5 train: [0] = 0.07436
5 train: [0] = 97.8%
5 val: [0] = 0.1042
5 val: [0] = 96.9%
6 train: [0] = 0.06475
6 train: [0] = 98.0%
6 val: [0] = 0.1016
6 val: [0] = 97.0%
7 train: [0] = 0.0548
7 train: [0] = 98.3%
7 val: [0] = 0.1034
7 val: [0] = 97.1%
8 train: [0] = 0.0484
8 train: [0] = 98.4%
8 val: [0] = 0.09504
8 val: [0] = 97.4%
9 train: [0] = 0.04095
9 train: [0] = 98.7%
9 val: [0] = 0.1062
9 val: [0] = 97.2%
10 train: [0] = 0.03583
10 train: [0] = 98.9%
10 val: [0] = 0.1138
10 val: [0] = 97.0%
11 train: [0] = 0.032
11 train: [0] = 99.0%
11 val: [0] = 0.1136
11 val: [0] = 97.0%
12 train: [0] = 0.02731
12 train: [0] = 99.1%
12 val: [0] = 0.1062
12 val: [0] = 97.3%
13 train: [0] = 0.0242
13 train: [0] = 99.2%
13 val: [0] = 0.1193
13 val: [0] = 96.9%
14 train: [0] = 0.02094
14 train: [0] = 99.3%
14 val: [0] = 0.1144
14 val: [0] = 97.1%
15 train: [0] = 0.0191
15 train: [0] = 99.4%
15 val: [0] = 0.113
15 val: [0] = 97.4%
16 train: [0] = 0.01898
16 train: [0] = 99.4%
16 val: [0] = 0.1139
16 val: [0] = 97.4%
17 train: [0] = 0.0157
17 train: [0] = 99.5%
17 val: [0] = 0.1192
17 val: [0] = 97.3%
18 train: [0] = 0.01269
18 train: [0] = 99.6%
18 val: [0] = 0.1356
18 val: [0] = 97.1%
19 train: [0] = 0.01333
19 train: [0] = 99.5%
19 val: [0] = 0.1338
19 val: [0] = 97.2%
[vae_0] test accuracy = 97.2%
[vae_0] training vae for step 0:
0 train: [0] = 2.117, [1] = 0.06851, [2] = 0.862, [3] = 0.4641
0 train: [0] = 19.6%
0 val: [0] = 1.856, [1] = 0.06172, [2] = 0.8264, [3] = 0.897
0 val: [0] = 29.0%
1 train: [0] = 1.228, [1] = 0.05869, [2] = 0.7738, [3] = 1.664
1 train: [0] = 51.0%
1 val: [0] = 0.6721, [1] = 0.05472, [2] = 0.7318, [3] = 2.222
1 val: [0] = 74.2%
2 train: [0] = 0.3897, [1] = 0.0546, [2] = 0.7164, [3] = 2.595
2 train: [0] = 85.8%
2 val: [0] = 0.2006, [1] = 0.05197, [2] = 0.6961, [3] = 2.847
2 val: [0] = 93.4%
3 train: [0] = 0.2036, [1] = 0.05251, [2] = 0.6872, [3] = 2.863
3 train: [0] = 92.9%
3 val: [0] = 0.1632, [1] = 0.05038, [2] = 0.6693, [3] = 2.9
3 val: [0] = 94.3%
4 train: [0] = 0.1637, [1] = 0.05088, [2] = 0.6654, [3] = 2.995
4 train: [0] = 94.3%
4 val: [0] = 0.1287, [1] = 0.04856, [2] = 0.6437, [3] = 3.098
4 val: [0] = 95.5%
5 train: [0] = 0.141, [1] = 0.04951, [2] = 0.646, [3] = 3.118
5 train: [0] = 95.1%
5 val: [0] = 0.1238, [1] = 0.04766, [2] = 0.6331, [3] = 3.176
5 val: [0] = 95.5%
6 train: [0] = 0.1237, [1] = 0.04845, [2] = 0.6307, [3] = 3.232
6 train: [0] = 95.7%
6 val: [0] = 0.1313, [1] = 0.04692, [2] = 0.6217, [3] = 3.165
6 val: [0] = 95.2%
7 train: [0] = 0.1114, [1] = 0.04758, [2] = 0.6186, [3] = 3.308
7 train: [0] = 96.1%
7 val: [0] = 0.1084, [1] = 0.04643, [2] = 0.6107, [3] = 3.248
7 val: [0] = 96.5%
8 train: [0] = 0.1015, [1] = 0.04693, [2] = 0.6096, [3] = 3.368
8 train: [0] = 96.4%
8 val: [0] = 0.1323, [1] = 0.04568, [2] = 0.5997, [3] = 3.337
8 val: [0] = 95.6%
9 train: [0] = 0.09549, [1] = 0.04639, [2] = 0.6018, [3] = 3.422
9 train: [0] = 96.7%
9 val: [0] = 0.07334, [1] = 0.04515, [2] = 0.5977, [3] = 3.548
9 val: [0] = 97.3%
10 train: [0] = 0.08984, [1] = 0.04598, [2] = 0.5961, [3] = 3.467
10 train: [0] = 96.9%
10 val: [0] = 0.0725, [1] = 0.04485, [2] = 0.5914, [3] = 3.418
10 val: [0] = 97.4%
11 train: [0] = 0.08631, [1] = 0.0457, [2] = 0.5914, [3] = 3.488
11 train: [0] = 97.1%
11 val: [0] = 0.0696, [1] = 0.0442, [2] = 0.5857, [3] = 3.521
11 val: [0] = 97.7%
12 train: [0] = 0.08146, [1] = 0.04531, [2] = 0.5866, [3] = 3.533
12 train: [0] = 97.2%
12 val: [0] = 0.0772, [1] = 0.04378, [2] = 0.5724, [3] = 3.522
12 val: [0] = 97.4%
13 train: [0] = 0.07904, [1] = 0.04498, [2] = 0.5822, [3] = 3.554
13 train: [0] = 97.3%
13 val: [0] = 0.08046, [1] = 0.04414, [2] = 0.5845, [3] = 3.445
13 val: [0] = 97.4%
14 train: [0] = 0.07704, [1] = 0.04476, [2] = 0.5795, [3] = 3.572
14 train: [0] = 97.3%
14 val: [0] = 0.06367, [1] = 0.04342, [2] = 0.5618, [3] = 3.657
14 val: [0] = 97.8%
15 train: [0] = 0.07632, [1] = 0.0445, [2] = 0.5761, [3] = 3.609
15 train: [0] = 97.4%
15 val: [0] = 0.05715, [1] = 0.04345, [2] = 0.5736, [3] = 3.668
15 val: [0] = 98.2%
16 train: [0] = 0.07283, [1] = 0.04433, [2] = 0.574, [3] = 3.626
16 train: [0] = 97.4%
16 val: [0] = 0.06002, [1] = 0.04298, [2] = 0.567, [3] = 3.66
16 val: [0] = 97.8%
17 train: [0] = 0.07143, [1] = 0.04413, [2] = 0.5715, [3] = 3.648
17 train: [0] = 97.5%
17 val: [0] = 0.09856, [1] = 0.0436, [2] = 0.575, [3] = 3.531
17 val: [0] = 96.5%
18 train: [0] = 0.07069, [1] = 0.04393, [2] = 0.5692, [3] = 3.663
18 train: [0] = 97.6%
18 val: [0] = 0.07211, [1] = 0.04283, [2] = 0.566, [3] = 3.669
18 val: [0] = 97.4%
19 train: [0] = 0.07051, [1] = 0.0437, [2] = 0.5664, [3] = 3.688
19 train: [0] = 97.6%
19 val: [0] = 0.06627, [1] = 0.04255, [2] = 0.5628, [3] = 3.723
19 val: [0] = 97.8%
20 train: [0] = 0.06775, [1] = 0.04355, [2] = 0.565, [3] = 3.699
20 train: [0] = 97.6%
20 val: [0] = 0.07794, [1] = 0.04276, [2] = 0.5636, [3] = 3.682
20 val: [0] = 97.5%
21 train: [0] = 0.06814, [1] = 0.04337, [2] = 0.5621, [3] = 3.733
21 train: [0] = 97.6%
21 val: [0] = 0.06233, [1] = 0.04246, [2] = 0.5591, [3] = 3.792
21 val: [0] = 97.9%
22 train: [0] = 0.06507, [1] = 0.04325, [2] = 0.5607, [3] = 3.736
22 train: [0] = 97.8%
22 val: [0] = 0.06425, [1] = 0.04235, [2] = 0.554, [3] = 3.664
22 val: [0] = 97.8%
23 train: [0] = 0.06352, [1] = 0.04318, [2] = 0.5597, [3] = 3.745
23 train: [0] = 97.8%
23 val: [0] = 0.0471, [1] = 0.04204, [2] = 0.5519, [3] = 3.76
23 val: [0] = 98.4%
24 train: [0] = 0.06383, [1] = 0.04298, [2] = 0.5574, [3] = 3.773
24 train: [0] = 97.8%
24 val: [0] = 0.05128, [1] = 0.04178, [2] = 0.5489, [3] = 3.821
24 val: [0] = 98.3%
25 train: [0] = 0.063, [1] = 0.04283, [2] = 0.5548, [3] = 3.776
25 train: [0] = 97.8%
25 val: [0] = 0.0611, [1] = 0.0421, [2] = 0.5514, [3] = 3.775
25 val: [0] = 97.9%
26 train: [0] = 0.05834, [1] = 0.04271, [2] = 0.5535, [3] = 3.797
26 train: [0] = 97.9%
26 val: [0] = 0.04454, [1] = 0.04161, [2] = 0.5467, [3] = 3.843
26 val: [0] = 98.6%
27 train: [0] = 0.059, [1] = 0.04254, [2] = 0.5511, [3] = 3.817
27 train: [0] = 98.0%
27 val: [0] = 0.04366, [1] = 0.04131, [2] = 0.5427, [3] = 3.864
27 val: [0] = 98.4%
28 train: [0] = 0.05949, [1] = 0.04246, [2] = 0.5505, [3] = 3.832
28 train: [0] = 97.9%
28 val: [0] = 0.05335, [1] = 0.04165, [2] = 0.5463, [3] = 3.839
28 val: [0] = 98.0%
29 train: [0] = 0.05846, [1] = 0.04235, [2] = 0.5485, [3] = 3.848
29 train: [0] = 98.0%
29 val: [0] = 0.07574, [1] = 0.0415, [2] = 0.5446, [3] = 3.806
29 val: [0] = 97.4%
30 train: [0] = 0.05947, [1] = 0.04223, [2] = 0.5472, [3] = 3.848
30 train: [0] = 98.0%
30 val: [0] = 0.0512, [1] = 0.04155, [2] = 0.547, [3] = 3.762
30 val: [0] = 98.2%
31 train: [0] = 0.05674, [1] = 0.04211, [2] = 0.5454, [3] = 3.859
31 train: [0] = 98.0%
31 val: [0] = 0.05355, [1] = 0.04119, [2] = 0.5396, [3] = 3.798
31 val: [0] = 98.1%
32 train: [0] = 0.05753, [1] = 0.04201, [2] = 0.5438, [3] = 3.876
32 train: [0] = 98.0%
32 val: [0] = 0.03699, [1] = 0.04077, [2] = 0.5339, [3] = 3.98
32 val: [0] = 98.8%
33 train: [0] = 0.05581, [1] = 0.04198, [2] = 0.5437, [3] = 3.885
33 train: [0] = 98.1%
33 val: [0] = 0.07334, [1] = 0.04159, [2] = 0.5405, [3] = 3.778
33 val: [0] = 97.5%
34 train: [0] = 0.05467, [1] = 0.04195, [2] = 0.5434, [3] = 3.87
34 train: [0] = 98.1%
34 val: [0] = 0.04705, [1] = 0.04111, [2] = 0.5411, [3] = 3.877
34 val: [0] = 98.4%
35 train: [0] = 0.05368, [1] = 0.04192, [2] = 0.5431, [3] = 3.881
35 train: [0] = 98.1%
35 val: [0] = 0.06374, [1] = 0.04163, [2] = 0.5447, [3] = 3.802
35 val: [0] = 97.7%
36 train: [0] = 0.05228, [1] = 0.04177, [2] = 0.5413, [3] = 3.901
36 train: [0] = 98.2%
36 val: [0] = 0.0484, [1] = 0.04112, [2] = 0.5354, [3] = 3.826
36 val: [0] = 98.3%
37 train: [0] = 0.05441, [1] = 0.0418, [2] = 0.5409, [3] = 3.903
37 train: [0] = 98.1%
37 val: [0] = 0.03873, [1] = 0.04077, [2] = 0.5366, [3] = 3.928
37 val: [0] = 98.8%
38 train: [0] = 0.05306, [1] = 0.04168, [2] = 0.5395, [3] = 3.909
38 train: [0] = 98.2%
38 val: [0] = 0.04274, [1] = 0.04089, [2] = 0.5356, [3] = 3.938
38 val: [0] = 98.5%
39 train: [0] = 0.05454, [1] = 0.04164, [2] = 0.5397, [3] = 3.923
39 train: [0] = 98.1%
39 val: [0] = 0.04528, [1] = 0.04053, [2] = 0.5311, [3] = 3.961
39 val: [0] = 98.3%
[vae_0] training getter for step 0:
0 train: [0] = 0.1863
0 train: [0] = 95.3%
0 val: [0] = 0.03846
0 val: [0] = 98.5%
1 train: [0] = 0.03552
1 train: [0] = 98.6%
1 val: [0] = 0.03913
1 val: [0] = 98.2%
2 train: [0] = 0.03333
2 train: [0] = 98.6%
2 val: [0] = 0.03372
2 val: [0] = 98.7%
3 train: [0] = 0.02766
3 train: [0] = 98.8%
3 val: [0] = 0.04345
3 val: [0] = 98.4%
4 train: [0] = 0.02758
4 train: [0] = 98.9%
4 val: [0] = 0.02406
4 val: [0] = 98.9%
5 train: [0] = 0.02454
5 train: [0] = 98.9%
5 val: [0] = 0.03163
5 val: [0] = 98.6%
6 train: [0] = 0.02329
6 train: [0] = 99.0%
6 val: [0] = 0.01918
6 val: [0] = 99.2%
7 train: [0] = 0.02273
7 train: [0] = 99.0%
7 val: [0] = 0.02141
7 val: [0] = 99.1%
8 train: [0] = 0.02363
8 train: [0] = 99.0%
8 val: [0] = 0.02401
8 val: [0] = 99.0%
9 train: [0] = 0.02244
9 train: [0] = 99.1%
9 val: [0] = 0.01626
9 val: [0] = 99.4%
10 train: [0] = 0.02182
10 train: [0] = 99.0%
10 val: [0] = 0.01698
10 val: [0] = 99.2%
11 train: [0] = 0.02061
11 train: [0] = 99.1%
11 val: [0] = 0.01921
11 val: [0] = 99.2%
12 train: [0] = 0.02155
12 train: [0] = 99.1%
12 val: [0] = 0.01976
12 val: [0] = 99.0%
13 train: [0] = 0.02143
13 train: [0] = 99.1%
13 val: [0] = 0.0146
13 val: [0] = 99.4%
14 train: [0] = 0.01926
14 train: [0] = 99.2%
14 val: [0] = 0.02789
14 val: [0] = 98.9%
15 train: [0] = 0.01953
15 train: [0] = 99.2%
15 val: [0] = 0.016
15 val: [0] = 99.4%
16 train: [0] = 0.02102
16 train: [0] = 99.1%
16 val: [0] = 0.02376
16 val: [0] = 98.8%
17 train: [0] = 0.01889
17 train: [0] = 99.2%
17 val: [0] = 0.01449
17 val: [0] = 99.5%
18 train: [0] = 0.01873
18 train: [0] = 99.2%
18 val: [0] = 0.02264
18 val: [0] = 99.0%
19 train: [0] = 0.0191
19 train: [0] = 99.2%
19 val: [0] = 0.01833
19 val: [0] = 99.2%
[vae_0] test accuracy = 80.4%
[vae_0] training vae for step 1:
0 train: [0] = 2.079, [1] = 0.06818, [2] = 0.8574, [3] = 0.538
0 train: [0] = 21.5%
0 val: [0] = 1.78, [1] = 0.06113, [2] = 0.8113, [3] = 1.073
0 val: [0] = 31.9%
1 train: [0] = 1.35, [1] = 0.05947, [2] = 0.7835, [3] = 1.591
1 train: [0] = 45.8%
1 val: [0] = 0.7944, [1] = 0.05658, [2] = 0.7503, [3] = 2.019
1 val: [0] = 69.3%
2 train: [0] = 0.3882, [1] = 0.05553, [2] = 0.7259, [3] = 2.581
2 train: [0] = 85.7%
2 val: [0] = 0.2443, [1] = 0.05309, [2] = 0.6952, [3] = 2.76
2 val: [0] = 90.9%
3 train: [0] = 0.2193, [1] = 0.05352, [2] = 0.7009, [3] = 2.793
3 train: [0] = 92.0%
3 val: [0] = 0.1664, [1] = 0.0513, [2] = 0.6885, [3] = 2.876
3 val: [0] = 94.2%
4 train: [0] = 0.1772, [1] = 0.05218, [2] = 0.6841, [3] = 2.901
4 train: [0] = 93.6%
4 val: [0] = 0.1417, [1] = 0.05031, [2] = 0.6764, [3] = 2.971
4 val: [0] = 95.2%
5 train: [0] = 0.1469, [1] = 0.0512, [2] = 0.6691, [3] = 2.982
5 train: [0] = 94.7%
5 val: [0] = 0.1174, [1] = 0.04928, [2] = 0.6571, [3] = 3.089
5 val: [0] = 96.0%
6 train: [0] = 0.1325, [1] = 0.05025, [2] = 0.6558, [3] = 3.07
6 train: [0] = 95.4%
6 val: [0] = 0.09969, [1] = 0.04823, [2] = 0.6427, [3] = 3.233
6 val: [0] = 96.6%
7 train: [0] = 0.1211, [1] = 0.04941, [2] = 0.644, [3] = 3.168
7 train: [0] = 95.7%
7 val: [0] = 0.1135, [1] = 0.04803, [2] = 0.6332, [3] = 3.181
7 val: [0] = 96.1%
8 train: [0] = 0.1147, [1] = 0.04857, [2] = 0.6319, [3] = 3.252
8 train: [0] = 95.9%
8 val: [0] = 0.09522, [1] = 0.04698, [2] = 0.625, [3] = 3.343
8 val: [0] = 96.7%
9 train: [0] = 0.1097, [1] = 0.04809, [2] = 0.625, [3] = 3.288
9 train: [0] = 96.2%
9 val: [0] = 0.113, [1] = 0.04641, [2] = 0.6086, [3] = 3.333
9 val: [0] = 96.1%
10 train: [0] = 0.1065, [1] = 0.04769, [2] = 0.6186, [3] = 3.326
10 train: [0] = 96.3%
10 val: [0] = 0.09187, [1] = 0.04643, [2] = 0.6175, [3] = 3.332
10 val: [0] = 96.8%
11 train: [0] = 0.104, [1] = 0.04736, [2] = 0.6141, [3] = 3.368
11 train: [0] = 96.4%
11 val: [0] = 0.06558, [1] = 0.04571, [2] = 0.6041, [3] = 3.545
11 val: [0] = 97.8%
12 train: [0] = 0.1009, [1] = 0.04701, [2] = 0.6097, [3] = 3.404
12 train: [0] = 96.5%
12 val: [0] = 0.05857, [1] = 0.04533, [2] = 0.5984, [3] = 3.565
12 val: [0] = 98.1%
13 train: [0] = 0.09433, [1] = 0.04675, [2] = 0.6059, [3] = 3.426
13 train: [0] = 96.7%
13 val: [0] = 0.06909, [1] = 0.04512, [2] = 0.5971, [3] = 3.493
13 val: [0] = 97.6%
14 train: [0] = 0.0931, [1] = 0.04646, [2] = 0.6024, [3] = 3.451
14 train: [0] = 96.8%
14 val: [0] = 0.09294, [1] = 0.04533, [2] = 0.5924, [3] = 3.531
14 val: [0] = 96.6%
15 train: [0] = 0.09101, [1] = 0.0463, [2] = 0.6003, [3] = 3.463
15 train: [0] = 96.8%
15 val: [0] = 0.08237, [1] = 0.04499, [2] = 0.5986, [3] = 3.488
15 val: [0] = 97.2%
16 train: [0] = 0.08788, [1] = 0.04605, [2] = 0.5974, [3] = 3.509
16 train: [0] = 96.9%
16 val: [0] = 0.07193, [1] = 0.04488, [2] = 0.591, [3] = 3.514
16 val: [0] = 97.4%
17 train: [0] = 0.08673, [1] = 0.04597, [2] = 0.5966, [3] = 3.507
17 train: [0] = 97.0%
17 val: [0] = 0.1031, [1] = 0.04509, [2] = 0.5991, [3] = 3.414
17 val: [0] = 96.4%
18 train: [0] = 0.08561, [1] = 0.04576, [2] = 0.5945, [3] = 3.526
18 train: [0] = 97.0%
18 val: [0] = 0.08844, [1] = 0.04491, [2] = 0.5935, [3] = 3.46
18 val: [0] = 96.7%
19 train: [0] = 0.0834, [1] = 0.04551, [2] = 0.592, [3] = 3.557
19 train: [0] = 97.1%
19 val: [0] = 0.07993, [1] = 0.04449, [2] = 0.592, [3] = 3.654
19 val: [0] = 97.1%
20 train: [0] = 0.08084, [1] = 0.0454, [2] = 0.5897, [3] = 3.567
20 train: [0] = 97.1%
20 val: [0] = 0.07216, [1] = 0.04451, [2] = 0.5906, [3] = 3.555
20 val: [0] = 97.5%
21 train: [0] = 0.07954, [1] = 0.04526, [2] = 0.5885, [3] = 3.589
21 train: [0] = 97.2%
21 val: [0] = 0.07935, [1] = 0.0438, [2] = 0.5812, [3] = 3.651
21 val: [0] = 97.3%
22 train: [0] = 0.07798, [1] = 0.04511, [2] = 0.5863, [3] = 3.598
22 train: [0] = 97.3%
22 val: [0] = 0.08178, [1] = 0.04448, [2] = 0.5872, [3] = 3.524
22 val: [0] = 97.1%
23 train: [0] = 0.07657, [1] = 0.04503, [2] = 0.586, [3] = 3.601
23 train: [0] = 97.3%
23 val: [0] = 0.1212, [1] = 0.04469, [2] = 0.5892, [3] = 3.411
23 val: [0] = 95.7%
24 train: [0] = 0.07771, [1] = 0.04491, [2] = 0.5845, [3] = 3.619
24 train: [0] = 97.4%
24 val: [0] = 0.07121, [1] = 0.04385, [2] = 0.5763, [3] = 3.657
24 val: [0] = 97.7%
25 train: [0] = 0.07515, [1] = 0.0448, [2] = 0.5825, [3] = 3.638
25 train: [0] = 97.4%
25 val: [0] = 0.04695, [1] = 0.04319, [2] = 0.5722, [3] = 3.801
25 val: [0] = 98.5%
26 train: [0] = 0.07243, [1] = 0.04468, [2] = 0.5812, [3] = 3.647
26 train: [0] = 97.4%
26 val: [0] = 0.06757, [1] = 0.04396, [2] = 0.5758, [3] = 3.611
26 val: [0] = 97.6%
27 train: [0] = 0.07282, [1] = 0.04455, [2] = 0.5803, [3] = 3.661
27 train: [0] = 97.4%
27 val: [0] = 0.04544, [1] = 0.04349, [2] = 0.574, [3] = 3.773
27 val: [0] = 98.4%
28 train: [0] = 0.07316, [1] = 0.04446, [2] = 0.5788, [3] = 3.681
28 train: [0] = 97.4%
28 val: [0] = 0.05676, [1] = 0.04321, [2] = 0.5733, [3] = 3.751
28 val: [0] = 98.2%
29 train: [0] = 0.07139, [1] = 0.04423, [2] = 0.5761, [3] = 3.692
29 train: [0] = 97.6%
29 val: [0] = 0.07993, [1] = 0.04377, [2] = 0.5771, [3] = 3.648
29 val: [0] = 96.9%
30 train: [0] = 0.07068, [1] = 0.04422, [2] = 0.5757, [3] = 3.71
30 train: [0] = 97.5%
30 val: [0] = 0.05855, [1] = 0.04329, [2] = 0.5685, [3] = 3.78
30 val: [0] = 98.1%
31 train: [0] = 0.07069, [1] = 0.04413, [2] = 0.5743, [3] = 3.72
31 train: [0] = 97.6%
31 val: [0] = 0.07604, [1] = 0.04344, [2] = 0.5705, [3] = 3.644
31 val: [0] = 97.3%
32 train: [0] = 0.06975, [1] = 0.044, [2] = 0.5729, [3] = 3.736
32 train: [0] = 97.5%
32 val: [0] = 0.07164, [1] = 0.04352, [2] = 0.5709, [3] = 3.67
32 val: [0] = 97.3%
33 train: [0] = 0.06772, [1] = 0.04393, [2] = 0.5722, [3] = 3.729
33 train: [0] = 97.6%
33 val: [0] = 0.07031, [1] = 0.0437, [2] = 0.5684, [3] = 3.606
33 val: [0] = 97.5%
34 train: [0] = 0.06418, [1] = 0.04381, [2] = 0.5701, [3] = 3.749
34 train: [0] = 97.7%
34 val: [0] = 0.06548, [1] = 0.04314, [2] = 0.567, [3] = 3.687
34 val: [0] = 97.5%
35 train: [0] = 0.06528, [1] = 0.04373, [2] = 0.5691, [3] = 3.759
35 train: [0] = 97.7%
35 val: [0] = 0.05612, [1] = 0.04262, [2] = 0.5564, [3] = 3.871
35 val: [0] = 98.0%
36 train: [0] = 0.06685, [1] = 0.04373, [2] = 0.5688, [3] = 3.773
36 train: [0] = 97.6%
36 val: [0] = 0.04962, [1] = 0.04268, [2] = 0.5668, [3] = 3.767
36 val: [0] = 98.3%
37 train: [0] = 0.06304, [1] = 0.04366, [2] = 0.5688, [3] = 3.767
37 train: [0] = 97.7%
37 val: [0] = 0.0497, [1] = 0.04266, [2] = 0.5634, [3] = 3.798
37 val: [0] = 98.3%
38 train: [0] = 0.06575, [1] = 0.04358, [2] = 0.5676, [3] = 3.775
38 train: [0] = 97.8%
38 val: [0] = 0.05548, [1] = 0.04253, [2] = 0.5602, [3] = 3.852
38 val: [0] = 98.0%
39 train: [0] = 0.06288, [1] = 0.04357, [2] = 0.567, [3] = 3.788
39 train: [0] = 97.8%
39 val: [0] = 0.05827, [1] = 0.04259, [2] = 0.5649, [3] = 3.814
39 val: [0] = 98.0%
[vae_0] training getter for step 1:
0 train: [0] = 0.176
0 train: [0] = 95.7%
0 val: [0] = 0.04084
0 val: [0] = 98.3%
1 train: [0] = 0.03707
1 train: [0] = 98.5%
1 val: [0] = 0.02737
1 val: [0] = 99.0%
2 train: [0] = 0.03098
2 train: [0] = 98.7%
2 val: [0] = 0.03213
2 val: [0] = 98.6%
3 train: [0] = 0.03091
3 train: [0] = 98.7%
3 val: [0] = 0.03033
3 val: [0] = 98.7%
4 train: [0] = 0.0278
4 train: [0] = 98.9%
4 val: [0] = 0.03097
4 val: [0] = 98.6%
5 train: [0] = 0.02768
5 train: [0] = 98.9%
5 val: [0] = 0.02651
5 val: [0] = 98.9%
6 train: [0] = 0.02548
6 train: [0] = 98.9%
6 val: [0] = 0.02777
6 val: [0] = 98.7%
7 train: [0] = 0.02647
7 train: [0] = 98.9%
7 val: [0] = 0.02325
7 val: [0] = 99.1%
8 train: [0] = 0.02567
8 train: [0] = 98.9%
8 val: [0] = 0.03439
8 val: [0] = 98.5%
9 train: [0] = 0.02278
9 train: [0] = 99.0%
9 val: [0] = 0.03058
9 val: [0] = 98.9%
10 train: [0] = 0.02204
10 train: [0] = 99.1%
10 val: [0] = 0.01985
10 val: [0] = 99.2%
11 train: [0] = 0.02349
11 train: [0] = 99.0%
11 val: [0] = 0.0345
11 val: [0] = 98.7%
12 train: [0] = 0.02233
12 train: [0] = 99.1%
12 val: [0] = 0.01986
12 val: [0] = 99.2%
13 train: [0] = 0.0218
13 train: [0] = 99.1%
13 val: [0] = 0.0191
13 val: [0] = 99.2%
14 train: [0] = 0.02256
14 train: [0] = 99.0%
14 val: [0] = 0.02076
14 val: [0] = 99.0%
15 train: [0] = 0.02302
15 train: [0] = 99.0%
15 val: [0] = 0.01989
15 val: [0] = 99.2%
16 train: [0] = 0.02041
16 train: [0] = 99.2%
16 val: [0] = 0.01802
16 val: [0] = 99.2%
17 train: [0] = 0.0206
17 train: [0] = 99.1%
17 val: [0] = 0.01271
17 val: [0] = 99.4%
18 train: [0] = 0.02264
18 train: [0] = 99.1%
18 val: [0] = 0.01956
18 val: [0] = 99.2%
19 train: [0] = 0.02105
19 train: [0] = 99.1%
19 val: [0] = 0.01637
19 val: [0] = 99.3%
[vae_0] test accuracy = 74.6%
[vae_0] training vae for step 2:
0 train: [0] = 2.066, [1] = 0.0681, [2] = 0.8579, [3] = 0.51
0 train: [0] = 22.4%
0 val: [0] = 1.654, [1] = 0.06084, [2] = 0.8092, [3] = 1.054
0 val: [0] = 36.7%
1 train: [0] = 1.155, [1] = 0.05976, [2] = 0.7851, [3] = 1.541
1 train: [0] = 50.4%
1 val: [0] = 0.851, [1] = 0.05732, [2] = 0.7596, [3] = 1.893
1 val: [0] = 60.6%
2 train: [0] = 0.6548, [1] = 0.05779, [2] = 0.7543, [3] = 2.017
2 train: [0] = 69.5%
2 val: [0] = 0.5261, [1] = 0.05611, [2] = 0.7452, [3] = 2.114
2 val: [0] = 77.5%
3 train: [0] = 0.3678, [1] = 0.05635, [2] = 0.7345, [3] = 2.316
3 train: [0] = 84.7%
3 val: [0] = 0.277, [1] = 0.05471, [2] = 0.7264, [3] = 2.339
3 val: [0] = 89.1%
4 train: [0] = 0.2096, [1] = 0.05548, [2] = 0.7231, [3] = 2.471
4 train: [0] = 92.2%
4 val: [0] = 0.1515, [1] = 0.05428, [2] = 0.7188, [3] = 2.491
4 val: [0] = 94.8%
5 train: [0] = 0.1424, [1] = 0.05483, [2] = 0.7164, [3] = 2.531
5 train: [0] = 94.8%
5 val: [0] = 0.1301, [1] = 0.05345, [2] = 0.7102, [3] = 2.526
5 val: [0] = 95.3%
6 train: [0] = 0.1241, [1] = 0.05443, [2] = 0.712, [3] = 2.562
6 train: [0] = 95.4%
6 val: [0] = 0.1038, [1] = 0.05306, [2] = 0.708, [3] = 2.543
6 val: [0] = 96.5%
7 train: [0] = 0.1145, [1] = 0.05418, [2] = 0.7088, [3] = 2.581
7 train: [0] = 95.9%
7 val: [0] = 0.1124, [1] = 0.05285, [2] = 0.706, [3] = 2.53
7 val: [0] = 96.1%
8 train: [0] = 0.1081, [1] = 0.05399, [2] = 0.7062, [3] = 2.583
8 train: [0] = 96.2%
8 val: [0] = 0.09683, [1] = 0.05259, [2] = 0.6999, [3] = 2.557
8 val: [0] = 96.5%
9 train: [0] = 0.1019, [1] = 0.05378, [2] = 0.7029, [3] = 2.599
9 train: [0] = 96.4%
9 val: [0] = 0.08192, [1] = 0.05233, [2] = 0.6992, [3] = 2.635
9 val: [0] = 97.2%
10 train: [0] = 0.09783, [1] = 0.0537, [2] = 0.7014, [3] = 2.614
10 train: [0] = 96.4%
10 val: [0] = 0.1095, [1] = 0.05266, [2] = 0.6964, [3] = 2.591
10 val: [0] = 96.2%
11 train: [0] = 0.09693, [1] = 0.05362, [2] = 0.7002, [3] = 2.605
11 train: [0] = 96.6%
11 val: [0] = 0.08274, [1] = 0.05218, [2] = 0.6969, [3] = 2.606
11 val: [0] = 97.1%
12 train: [0] = 0.09226, [1] = 0.05355, [2] = 0.6995, [3] = 2.615
12 train: [0] = 96.6%
12 val: [0] = 0.1039, [1] = 0.05261, [2] = 0.6961, [3] = 2.683
12 val: [0] = 96.0%
13 train: [0] = 0.09504, [1] = 0.05348, [2] = 0.6988, [3] = 2.62
13 train: [0] = 96.6%
13 val: [0] = 0.1196, [1] = 0.05252, [2] = 0.6996, [3] = 2.557
13 val: [0] = 95.8%
14 train: [0] = 0.09155, [1] = 0.05334, [2] = 0.6974, [3] = 2.622
14 train: [0] = 96.7%
14 val: [0] = 0.07911, [1] = 0.05184, [2] = 0.6864, [3] = 2.646
14 val: [0] = 97.3%
15 train: [0] = 0.09216, [1] = 0.05326, [2] = 0.6962, [3] = 2.628
15 train: [0] = 96.7%
15 val: [0] = 0.1435, [1] = 0.05232, [2] = 0.6967, [3] = 2.645
15 val: [0] = 94.8%
16 train: [0] = 0.08994, [1] = 0.05316, [2] = 0.6947, [3] = 2.649
16 train: [0] = 96.8%
16 val: [0] = 0.1352, [1] = 0.05217, [2] = 0.6912, [3] = 2.628
16 val: [0] = 95.3%
17 train: [0] = 0.08787, [1] = 0.05297, [2] = 0.6931, [3] = 2.671
17 train: [0] = 96.8%
17 val: [0] = 0.08678, [1] = 0.05181, [2] = 0.6917, [3] = 2.628
17 val: [0] = 96.9%
18 train: [0] = 0.08393, [1] = 0.05267, [2] = 0.6892, [3] = 2.704
18 train: [0] = 97.0%
18 val: [0] = 0.07807, [1] = 0.05126, [2] = 0.681, [3] = 2.699
18 val: [0] = 97.1%
19 train: [0] = 0.08257, [1] = 0.05234, [2] = 0.6856, [3] = 2.737
19 train: [0] = 97.1%
19 val: [0] = 0.09981, [1] = 0.05119, [2] = 0.6846, [3] = 2.732
19 val: [0] = 96.5%
20 train: [0] = 0.07342, [1] = 0.05203, [2] = 0.681, [3] = 2.761
20 train: [0] = 97.3%
20 val: [0] = 0.07284, [1] = 0.05029, [2] = 0.6729, [3] = 2.824
20 val: [0] = 97.3%
21 train: [0] = 0.07566, [1] = 0.05189, [2] = 0.6794, [3] = 2.784
21 train: [0] = 97.3%
21 val: [0] = 0.08165, [1] = 0.05072, [2] = 0.6718, [3] = 2.79
21 val: [0] = 97.0%
22 train: [0] = 0.07295, [1] = 0.05173, [2] = 0.6768, [3] = 2.8
22 train: [0] = 97.4%
22 val: [0] = 0.0661, [1] = 0.05057, [2] = 0.6743, [3] = 2.768
22 val: [0] = 97.7%
23 train: [0] = 0.06837, [1] = 0.05159, [2] = 0.6745, [3] = 2.813
23 train: [0] = 97.6%
23 val: [0] = 0.08617, [1] = 0.05076, [2] = 0.6756, [3] = 2.664
23 val: [0] = 96.9%
24 train: [0] = 0.06613, [1] = 0.0514, [2] = 0.6729, [3] = 2.822
24 train: [0] = 97.6%
24 val: [0] = 0.06116, [1] = 0.05024, [2] = 0.6677, [3] = 2.829
24 val: [0] = 97.9%
25 train: [0] = 0.06981, [1] = 0.05133, [2] = 0.672, [3] = 2.843
25 train: [0] = 97.6%
25 val: [0] = 0.07277, [1] = 0.05035, [2] = 0.6717, [3] = 2.819
25 val: [0] = 97.3%
26 train: [0] = 0.06553, [1] = 0.05113, [2] = 0.6695, [3] = 2.853
26 train: [0] = 97.7%
26 val: [0] = 0.07782, [1] = 0.0499, [2] = 0.6681, [3] = 2.776
26 val: [0] = 97.2%
27 train: [0] = 0.06421, [1] = 0.05096, [2] = 0.6675, [3] = 2.88
27 train: [0] = 97.7%
27 val: [0] = 0.0527, [1] = 0.04994, [2] = 0.658, [3] = 2.853
27 val: [0] = 98.1%
28 train: [0] = 0.06021, [1] = 0.05066, [2] = 0.6634, [3] = 2.897
28 train: [0] = 97.8%
28 val: [0] = 0.06399, [1] = 0.04953, [2] = 0.6581, [3] = 2.861
28 val: [0] = 97.7%
29 train: [0] = 0.05812, [1] = 0.05033, [2] = 0.6588, [3] = 2.938
29 train: [0] = 97.8%
29 val: [0] = 0.03989, [1] = 0.04887, [2] = 0.6517, [3] = 2.983
29 val: [0] = 98.5%
30 train: [0] = 0.05809, [1] = 0.05018, [2] = 0.6562, [3] = 2.957
30 train: [0] = 98.0%
30 val: [0] = 0.06721, [1] = 0.04937, [2] = 0.6577, [3] = 2.898
30 val: [0] = 97.5%
31 train: [0] = 0.05435, [1] = 0.05, [2] = 0.6541, [3] = 2.979
31 train: [0] = 98.0%
31 val: [0] = 0.04904, [1] = 0.04881, [2] = 0.6473, [3] = 2.953
31 val: [0] = 98.3%
32 train: [0] = 0.05261, [1] = 0.04992, [2] = 0.6525, [3] = 2.98
32 train: [0] = 98.2%
32 val: [0] = 0.06851, [1] = 0.04905, [2] = 0.6515, [3] = 2.918
32 val: [0] = 97.6%
33 train: [0] = 0.05361, [1] = 0.04988, [2] = 0.6517, [3] = 2.979
33 train: [0] = 98.1%
33 val: [0] = 0.0483, [1] = 0.04887, [2] = 0.64, [3] = 2.949
33 val: [0] = 98.2%
34 train: [0] = 0.05219, [1] = 0.04978, [2] = 0.6504, [3] = 2.995
34 train: [0] = 98.1%
34 val: [0] = 0.05188, [1] = 0.04925, [2] = 0.6538, [3] = 3.029
34 val: [0] = 98.2%
35 train: [0] = 0.05253, [1] = 0.04978, [2] = 0.65, [3] = 2.991
35 train: [0] = 98.1%
35 val: [0] = 0.03214, [1] = 0.0487, [2] = 0.6458, [3] = 3.027
35 val: [0] = 98.9%
36 train: [0] = 0.05242, [1] = 0.0497, [2] = 0.6486, [3] = 3.003
36 train: [0] = 98.1%
36 val: [0] = 0.05072, [1] = 0.04851, [2] = 0.6411, [3] = 3.003
36 val: [0] = 98.0%
37 train: [0] = 0.04972, [1] = 0.04959, [2] = 0.6475, [3] = 3.013
37 train: [0] = 98.2%
37 val: [0] = 0.04256, [1] = 0.04847, [2] = 0.6464, [3] = 3.019
37 val: [0] = 98.5%
38 train: [0] = 0.04894, [1] = 0.04949, [2] = 0.6464, [3] = 3.018
38 train: [0] = 98.2%
38 val: [0] = 0.05253, [1] = 0.04883, [2] = 0.6404, [3] = 2.972
38 val: [0] = 98.0%
39 train: [0] = 0.04881, [1] = 0.04948, [2] = 0.6457, [3] = 3.016
39 train: [0] = 98.3%
39 val: [0] = 0.04614, [1] = 0.04855, [2] = 0.643, [3] = 2.955
39 val: [0] = 98.2%
[vae_0] training getter for step 2:
0 train: [0] = 0.1602
0 train: [0] = 96.7%
0 val: [0] = 0.01901
0 val: [0] = 99.3%
1 train: [0] = 0.0196
1 train: [0] = 99.2%
1 val: [0] = 0.01817
1 val: [0] = 99.1%
2 train: [0] = 0.01766
2 train: [0] = 99.2%
2 val: [0] = 0.0139
2 val: [0] = 99.4%
3 train: [0] = 0.01532
3 train: [0] = 99.3%
3 val: [0] = 0.01913
3 val: [0] = 99.1%
4 train: [0] = 0.01527
4 train: [0] = 99.4%
4 val: [0] = 0.01007
4 val: [0] = 99.6%
5 train: [0] = 0.0134
5 train: [0] = 99.4%
5 val: [0] = 0.01545
5 val: [0] = 99.4%
6 train: [0] = 0.01378
6 train: [0] = 99.5%
6 val: [0] = 0.01123
6 val: [0] = 99.5%
7 train: [0] = 0.01366
7 train: [0] = 99.5%
7 val: [0] = 0.01314
7 val: [0] = 99.4%
8 train: [0] = 0.01295
8 train: [0] = 99.4%
8 val: [0] = 0.01193
8 val: [0] = 99.4%
9 train: [0] = 0.0122
9 train: [0] = 99.5%
9 val: [0] = 0.01027
9 val: [0] = 99.6%
10 train: [0] = 0.01205
10 train: [0] = 99.5%
10 val: [0] = 0.01386
10 val: [0] = 99.5%
11 train: [0] = 0.01214
11 train: [0] = 99.5%
11 val: [0] = 0.009544
11 val: [0] = 99.5%
12 train: [0] = 0.01257
12 train: [0] = 99.5%
12 val: [0] = 0.03631
12 val: [0] = 98.8%
13 train: [0] = 0.01329
13 train: [0] = 99.5%
13 val: [0] = 0.01146
13 val: [0] = 99.5%
14 train: [0] = 0.01196
14 train: [0] = 99.5%
14 val: [0] = 0.01481
14 val: [0] = 99.3%
15 train: [0] = 0.01186
15 train: [0] = 99.5%
15 val: [0] = 0.01079
15 val: [0] = 99.5%
16 train: [0] = 0.01142
16 train: [0] = 99.5%
16 val: [0] = 0.03204
16 val: [0] = 98.9%
17 train: [0] = 0.01003
17 train: [0] = 99.6%
17 val: [0] = 0.007343
17 val: [0] = 99.7%
18 train: [0] = 0.01155
18 train: [0] = 99.5%
18 val: [0] = 0.006416
18 val: [0] = 99.7%
19 train: [0] = 0.01078
19 train: [0] = 99.6%
19 val: [0] = 0.008387
19 val: [0] = 99.6%
[vae_0] test accuracy = 69.5%
[vae_0] training vae for step 3:
0 train: [0] = 2.083, [1] = 0.06838, [2] = 0.8583, [3] = 0.5041
0 train: [0] = 23.1%
0 val: [0] = 1.875, [1] = 0.06225, [2] = 0.832, [3] = 0.7801
0 val: [0] = 30.8%
1 train: [0] = 1.296, [1] = 0.0598, [2] = 0.7858, [3] = 1.586
1 train: [0] = 51.6%
1 val: [0] = 0.6067, [1] = 0.05588, [2] = 0.742, [3] = 2.37
1 val: [0] = 76.4%
2 train: [0] = 0.3679, [1] = 0.05614, [2] = 0.734, [3] = 2.577
2 train: [0] = 86.4%
2 val: [0] = 0.2948, [1] = 0.05414, [2] = 0.7205, [3] = 2.614
2 val: [0] = 89.4%
3 train: [0] = 0.2261, [1] = 0.05436, [2] = 0.7109, [3] = 2.766
3 train: [0] = 91.8%
3 val: [0] = 0.1663, [1] = 0.05241, [2] = 0.7001, [3] = 2.899
3 val: [0] = 94.1%
4 train: [0] = 0.1918, [1] = 0.05337, [2] = 0.698, [3] = 2.857
4 train: [0] = 93.2%
4 val: [0] = 0.1818, [1] = 0.05201, [2] = 0.6899, [3] = 2.915
4 val: [0] = 93.4%
5 train: [0] = 0.1745, [1] = 0.05287, [2] = 0.6903, [3] = 2.9
5 train: [0] = 93.8%
5 val: [0] = 0.1848, [1] = 0.05168, [2] = 0.6904, [3] = 2.829
5 val: [0] = 93.4%
6 train: [0] = 0.1609, [1] = 0.05238, [2] = 0.6846, [3] = 2.941
6 train: [0] = 94.2%
6 val: [0] = 0.19, [1] = 0.05146, [2] = 0.6795, [3] = 2.88
6 val: [0] = 93.1%
7 train: [0] = 0.1526, [1] = 0.05195, [2] = 0.6791, [3] = 2.992
7 train: [0] = 94.5%
7 val: [0] = 0.1321, [1] = 0.0509, [2] = 0.6778, [3] = 3.008
7 val: [0] = 95.4%
8 train: [0] = 0.1434, [1] = 0.05145, [2] = 0.6723, [3] = 3.042
8 train: [0] = 94.9%
8 val: [0] = 0.1508, [1] = 0.05036, [2] = 0.6688, [3] = 3.029
8 val: [0] = 94.7%
9 train: [0] = 0.1378, [1] = 0.05087, [2] = 0.6644, [3] = 3.111
9 train: [0] = 95.2%
9 val: [0] = 0.1195, [1] = 0.04926, [2] = 0.651, [3] = 3.241
9 val: [0] = 95.8%
10 train: [0] = 0.1315, [1] = 0.05042, [2] = 0.6583, [3] = 3.161
10 train: [0] = 95.4%
10 val: [0] = 0.1579, [1] = 0.0493, [2] = 0.6503, [3] = 3.137
10 val: [0] = 94.4%
11 train: [0] = 0.1217, [1] = 0.04997, [2] = 0.6518, [3] = 3.213
11 train: [0] = 95.7%
11 val: [0] = 0.1257, [1] = 0.04896, [2] = 0.6455, [3] = 3.222
11 val: [0] = 95.5%
12 train: [0] = 0.1171, [1] = 0.04954, [2] = 0.646, [3] = 3.261
12 train: [0] = 95.9%
12 val: [0] = 0.1426, [1] = 0.04855, [2] = 0.6416, [3] = 3.199
12 val: [0] = 94.7%
13 train: [0] = 0.1156, [1] = 0.04912, [2] = 0.6404, [3] = 3.311
13 train: [0] = 95.9%
13 val: [0] = 0.1226, [1] = 0.04823, [2] = 0.6389, [3] = 3.263
13 val: [0] = 95.6%
14 train: [0] = 0.1088, [1] = 0.04871, [2] = 0.6353, [3] = 3.344
14 train: [0] = 96.2%
14 val: [0] = 0.1372, [1] = 0.0477, [2] = 0.627, [3] = 3.271
14 val: [0] = 95.1%
15 train: [0] = 0.1046, [1] = 0.04829, [2] = 0.6296, [3] = 3.398
15 train: [0] = 96.2%
15 val: [0] = 0.1158, [1] = 0.04747, [2] = 0.6247, [3] = 3.32
15 val: [0] = 95.9%
16 train: [0] = 0.1007, [1] = 0.048, [2] = 0.6257, [3] = 3.425
16 train: [0] = 96.3%
16 val: [0] = 0.1137, [1] = 0.04702, [2] = 0.6223, [3] = 3.352
16 val: [0] = 95.8%
17 train: [0] = 0.09967, [1] = 0.04781, [2] = 0.6224, [3] = 3.445
17 train: [0] = 96.5%
17 val: [0] = 0.08337, [1] = 0.04661, [2] = 0.6152, [3] = 3.435
17 val: [0] = 97.0%
18 train: [0] = 0.09819, [1] = 0.04752, [2] = 0.6186, [3] = 3.475
18 train: [0] = 96.5%
18 val: [0] = 0.07219, [1] = 0.04594, [2] = 0.6048, [3] = 3.612
18 val: [0] = 97.4%
19 train: [0] = 0.09007, [1] = 0.04725, [2] = 0.6142, [3] = 3.491
19 train: [0] = 96.7%
19 val: [0] = 0.09436, [1] = 0.04603, [2] = 0.6009, [3] = 3.586
19 val: [0] = 96.6%
20 train: [0] = 0.09095, [1] = 0.04705, [2] = 0.6118, [3] = 3.526
20 train: [0] = 96.7%
20 val: [0] = 0.08972, [1] = 0.04617, [2] = 0.6089, [3] = 3.465
20 val: [0] = 96.6%
21 train: [0] = 0.08729, [1] = 0.04683, [2] = 0.6083, [3] = 3.541
21 train: [0] = 96.9%
21 val: [0] = 0.09418, [1] = 0.04569, [2] = 0.6028, [3] = 3.538
21 val: [0] = 96.4%
22 train: [0] = 0.08663, [1] = 0.04654, [2] = 0.6048, [3] = 3.589
22 train: [0] = 96.8%
22 val: [0] = 0.09947, [1] = 0.04627, [2] = 0.6056, [3] = 3.445
22 val: [0] = 96.5%
23 train: [0] = 0.08351, [1] = 0.04632, [2] = 0.6018, [3] = 3.607
23 train: [0] = 97.0%
23 val: [0] = 0.09347, [1] = 0.04573, [2] = 0.5967, [3] = 3.478
23 val: [0] = 96.7%
24 train: [0] = 0.07983, [1] = 0.0461, [2] = 0.599, [3] = 3.643
24 train: [0] = 97.2%
24 val: [0] = 0.07558, [1] = 0.0452, [2] = 0.5953, [3] = 3.611
24 val: [0] = 97.3%
25 train: [0] = 0.0757, [1] = 0.04592, [2] = 0.5965, [3] = 3.655
25 train: [0] = 97.2%
25 val: [0] = 0.0785, [1] = 0.04533, [2] = 0.5947, [3] = 3.559
25 val: [0] = 97.3%
26 train: [0] = 0.07781, [1] = 0.04576, [2] = 0.5946, [3] = 3.652
26 train: [0] = 97.1%
26 val: [0] = 0.0671, [1] = 0.04498, [2] = 0.5897, [3] = 3.782
26 val: [0] = 97.4%
27 train: [0] = 0.07605, [1] = 0.04565, [2] = 0.5933, [3] = 3.676
27 train: [0] = 97.3%
27 val: [0] = 0.09276, [1] = 0.04486, [2] = 0.586, [3] = 3.576
27 val: [0] = 96.7%
28 train: [0] = 0.07388, [1] = 0.04551, [2] = 0.5915, [3] = 3.694
28 train: [0] = 97.3%
28 val: [0] = 0.06449, [1] = 0.04432, [2] = 0.5821, [3] = 3.753
28 val: [0] = 97.7%
29 train: [0] = 0.07371, [1] = 0.04533, [2] = 0.5889, [3] = 3.705
29 train: [0] = 97.4%
29 val: [0] = 0.0719, [1] = 0.04434, [2] = 0.5826, [3] = 3.669
29 val: [0] = 97.4%
30 train: [0] = 0.07195, [1] = 0.04523, [2] = 0.5874, [3] = 3.709
30 train: [0] = 97.5%
30 val: [0] = 0.08215, [1] = 0.04461, [2] = 0.5855, [3] = 3.665
30 val: [0] = 97.1%
31 train: [0] = 0.0717, [1] = 0.04521, [2] = 0.587, [3] = 3.725
31 train: [0] = 97.4%
31 val: [0] = 0.05001, [1] = 0.04403, [2] = 0.5759, [3] = 3.769
31 val: [0] = 98.2%
32 train: [0] = 0.06903, [1] = 0.04511, [2] = 0.586, [3] = 3.734
32 train: [0] = 97.5%
32 val: [0] = 0.06393, [1] = 0.0442, [2] = 0.5791, [3] = 3.713
32 val: [0] = 97.5%
33 train: [0] = 0.06864, [1] = 0.04501, [2] = 0.5846, [3] = 3.745
33 train: [0] = 97.6%
33 val: [0] = 0.0652, [1] = 0.04409, [2] = 0.5767, [3] = 3.722
33 val: [0] = 97.5%
34 train: [0] = 0.06995, [1] = 0.0449, [2] = 0.5832, [3] = 3.751
34 train: [0] = 97.6%
34 val: [0] = 0.08411, [1] = 0.04424, [2] = 0.579, [3] = 3.69
34 val: [0] = 97.1%
35 train: [0] = 0.06718, [1] = 0.04487, [2] = 0.5826, [3] = 3.761
35 train: [0] = 97.6%
35 val: [0] = 0.06181, [1] = 0.04374, [2] = 0.5765, [3] = 3.785
35 val: [0] = 97.6%
36 train: [0] = 0.06734, [1] = 0.04476, [2] = 0.5816, [3] = 3.776
36 train: [0] = 97.5%
36 val: [0] = 0.07358, [1] = 0.0443, [2] = 0.5828, [3] = 3.669
36 val: [0] = 97.5%
37 train: [0] = 0.06804, [1] = 0.04474, [2] = 0.5814, [3] = 3.77
37 train: [0] = 97.6%
37 val: [0] = 0.06248, [1] = 0.04383, [2] = 0.575, [3] = 3.722
37 val: [0] = 97.7%
38 train: [0] = 0.06576, [1] = 0.04467, [2] = 0.5803, [3] = 3.772
38 train: [0] = 97.6%
38 val: [0] = 0.04392, [1] = 0.04367, [2] = 0.5704, [3] = 3.793
38 val: [0] = 98.4%
39 train: [0] = 0.06694, [1] = 0.04464, [2] = 0.5792, [3] = 3.766
39 train: [0] = 97.6%
39 val: [0] = 0.07388, [1] = 0.04377, [2] = 0.5749, [3] = 3.728
39 val: [0] = 97.6%
[vae_0] training getter for step 3:
0 train: [0] = 0.1951
0 train: [0] = 94.8%
0 val: [0] = 0.0542
0 val: [0] = 97.8%
1 train: [0] = 0.03943
1 train: [0] = 98.5%
1 val: [0] = 0.03745
1 val: [0] = 98.5%
2 train: [0] = 0.03698
2 train: [0] = 98.5%
2 val: [0] = 0.04511
2 val: [0] = 98.1%
3 train: [0] = 0.0336
3 train: [0] = 98.6%
3 val: [0] = 0.03561
3 val: [0] = 98.3%
4 train: [0] = 0.03042
4 train: [0] = 98.7%
4 val: [0] = 0.0271
4 val: [0] = 98.9%
5 train: [0] = 0.03
5 train: [0] = 98.7%
5 val: [0] = 0.0287
5 val: [0] = 98.7%
6 train: [0] = 0.02596
6 train: [0] = 98.9%
6 val: [0] = 0.02257
6 val: [0] = 99.0%
7 train: [0] = 0.02834
7 train: [0] = 98.8%
7 val: [0] = 0.0278
7 val: [0] = 98.7%
8 train: [0] = 0.0278
8 train: [0] = 98.8%
8 val: [0] = 0.03152
8 val: [0] = 98.8%
9 train: [0] = 0.02509
9 train: [0] = 98.9%
9 val: [0] = 0.0208
9 val: [0] = 99.1%
10 train: [0] = 0.02594
10 train: [0] = 98.9%
10 val: [0] = 0.02407
10 val: [0] = 98.9%
11 train: [0] = 0.02441
11 train: [0] = 99.0%
11 val: [0] = 0.02566
11 val: [0] = 98.9%
12 train: [0] = 0.02556
12 train: [0] = 98.9%
12 val: [0] = 0.0152
12 val: [0] = 99.4%
13 train: [0] = 0.02486
13 train: [0] = 99.0%
13 val: [0] = 0.02731
13 val: [0] = 98.8%
14 train: [0] = 0.02506
14 train: [0] = 98.9%
14 val: [0] = 0.02726
14 val: [0] = 98.8%
15 train: [0] = 0.02288
15 train: [0] = 99.1%
15 val: [0] = 0.02123
15 val: [0] = 99.0%
16 train: [0] = 0.02408
16 train: [0] = 99.0%
16 val: [0] = 0.03157
16 val: [0] = 98.6%
17 train: [0] = 0.02149
17 train: [0] = 99.1%
17 val: [0] = 0.01665
17 val: [0] = 99.3%
18 train: [0] = 0.02157
18 train: [0] = 99.1%
18 val: [0] = 0.01841
18 val: [0] = 99.2%
19 train: [0] = 0.02493
19 train: [0] = 98.9%
19 val: [0] = 0.01973
19 val: [0] = 99.2%
[vae_0] test accuracy = 63.4%
[vae_0] training vae for step 4:
0 train: [0] = 2.078, [1] = 0.06852, [2] = 0.8599, [3] = 0.4787
0 train: [0] = 23.6%
0 val: [0] = 1.793, [1] = 0.06121, [2] = 0.8209, [3] = 1.096
0 val: [0] = 34.1%
1 train: [0] = 1.547, [1] = 0.06078, [2] = 0.8004, [3] = 1.373
1 train: [0] = 40.8%
1 val: [0] = 1.21, [1] = 0.05851, [2] = 0.782, [3] = 1.736
1 val: [0] = 52.6%
2 train: [0] = 0.6927, [1] = 0.05792, [2] = 0.7595, [3] = 2.21
2 train: [0] = 72.9%
2 val: [0] = 0.3254, [1] = 0.05522, [2] = 0.7369, [3] = 2.671
2 val: [0] = 88.4%
3 train: [0] = 0.2579, [1] = 0.05553, [2] = 0.7251, [3] = 2.71
3 train: [0] = 90.8%
3 val: [0] = 0.1961, [1] = 0.05358, [2] = 0.7094, [3] = 2.818
3 val: [0] = 93.0%
4 train: [0] = 0.1889, [1] = 0.05421, [2] = 0.706, [3] = 2.836
4 train: [0] = 93.4%
4 val: [0] = 0.1745, [1] = 0.05242, [2] = 0.6982, [3] = 2.901
4 val: [0] = 94.0%
5 train: [0] = 0.1664, [1] = 0.05313, [2] = 0.6914, [3] = 2.945
5 train: [0] = 94.1%
5 val: [0] = 0.1583, [1] = 0.05167, [2] = 0.6846, [3] = 2.968
5 val: [0] = 94.3%
6 train: [0] = 0.1517, [1] = 0.05232, [2] = 0.6804, [3] = 3.032
6 train: [0] = 94.7%
6 val: [0] = 0.1391, [1] = 0.05068, [2] = 0.6711, [3] = 3.078
6 val: [0] = 95.0%
7 train: [0] = 0.139, [1] = 0.05178, [2] = 0.6726, [3] = 3.104
7 train: [0] = 95.0%
7 val: [0] = 0.1186, [1] = 0.0503, [2] = 0.66, [3] = 3.178
7 val: [0] = 95.8%
8 train: [0] = 0.1294, [1] = 0.05106, [2] = 0.6636, [3] = 3.173
8 train: [0] = 95.5%
8 val: [0] = 0.167, [1] = 0.04967, [2] = 0.6606, [3] = 3.138
8 val: [0] = 94.2%
9 train: [0] = 0.1197, [1] = 0.05038, [2] = 0.6546, [3] = 3.265
9 train: [0] = 95.8%
9 val: [0] = 0.07942, [1] = 0.04842, [2] = 0.6379, [3] = 3.407
9 val: [0] = 97.1%
10 train: [0] = 0.1105, [1] = 0.04975, [2] = 0.6477, [3] = 3.324
10 train: [0] = 96.0%
10 val: [0] = 0.09988, [1] = 0.04847, [2] = 0.6382, [3] = 3.358
10 val: [0] = 96.7%
11 train: [0] = 0.1077, [1] = 0.04931, [2] = 0.6423, [3] = 3.372
11 train: [0] = 96.1%
11 val: [0] = 0.09251, [1] = 0.04773, [2] = 0.6303, [3] = 3.443
11 val: [0] = 96.8%
12 train: [0] = 0.1028, [1] = 0.04884, [2] = 0.6376, [3] = 3.418
12 train: [0] = 96.3%
12 val: [0] = 0.09902, [1] = 0.04767, [2] = 0.6308, [3] = 3.428
12 val: [0] = 96.6%
13 train: [0] = 0.09833, [1] = 0.0485, [2] = 0.6331, [3] = 3.429
13 train: [0] = 96.5%
13 val: [0] = 0.103, [1] = 0.04762, [2] = 0.6251, [3] = 3.49
13 val: [0] = 96.3%
14 train: [0] = 0.0958, [1] = 0.04819, [2] = 0.6299, [3] = 3.466
14 train: [0] = 96.7%
14 val: [0] = 0.08267, [1] = 0.0471, [2] = 0.6256, [3] = 3.524
14 val: [0] = 97.1%
15 train: [0] = 0.09065, [1] = 0.04781, [2] = 0.6244, [3] = 3.523
15 train: [0] = 96.7%
15 val: [0] = 0.07659, [1] = 0.04672, [2] = 0.6137, [3] = 3.553
15 val: [0] = 97.4%
16 train: [0] = 0.08949, [1] = 0.04758, [2] = 0.6209, [3] = 3.542
16 train: [0] = 96.8%
16 val: [0] = 0.08738, [1] = 0.04661, [2] = 0.618, [3] = 3.544
16 val: [0] = 96.8%
17 train: [0] = 0.086, [1] = 0.0473, [2] = 0.617, [3] = 3.573
17 train: [0] = 96.9%
17 val: [0] = 0.07299, [1] = 0.04599, [2] = 0.6085, [3] = 3.625
17 val: [0] = 97.3%
18 train: [0] = 0.08384, [1] = 0.04703, [2] = 0.6133, [3] = 3.607
18 train: [0] = 97.0%
18 val: [0] = 0.0627, [1] = 0.0458, [2] = 0.6043, [3] = 3.669
18 val: [0] = 97.8%
19 train: [0] = 0.08165, [1] = 0.04682, [2] = 0.6106, [3] = 3.619
19 train: [0] = 97.1%
19 val: [0] = 0.07693, [1] = 0.04565, [2] = 0.607, [3] = 3.615
19 val: [0] = 97.2%
20 train: [0] = 0.07981, [1] = 0.04669, [2] = 0.6082, [3] = 3.635
20 train: [0] = 97.1%
20 val: [0] = 0.08772, [1] = 0.04559, [2] = 0.5994, [3] = 3.673
20 val: [0] = 96.7%
21 train: [0] = 0.07816, [1] = 0.04644, [2] = 0.6055, [3] = 3.644
21 train: [0] = 97.2%
21 val: [0] = 0.08686, [1] = 0.04567, [2] = 0.5998, [3] = 3.646
21 val: [0] = 96.9%
22 train: [0] = 0.07871, [1] = 0.04635, [2] = 0.6038, [3] = 3.68
22 train: [0] = 97.2%
22 val: [0] = 0.07059, [1] = 0.04551, [2] = 0.5997, [3] = 3.694
22 val: [0] = 97.5%
23 train: [0] = 0.07893, [1] = 0.04625, [2] = 0.6029, [3] = 3.679
23 train: [0] = 97.2%
23 val: [0] = 0.05576, [1] = 0.04519, [2] = 0.6011, [3] = 3.777
23 val: [0] = 97.9%
24 train: [0] = 0.07392, [1] = 0.0461, [2] = 0.6008, [3] = 3.708
24 train: [0] = 97.4%
24 val: [0] = 0.06961, [1] = 0.04533, [2] = 0.5997, [3] = 3.696
24 val: [0] = 97.3%
25 train: [0] = 0.0731, [1] = 0.04603, [2] = 0.5995, [3] = 3.708
25 train: [0] = 97.3%
25 val: [0] = 0.05404, [1] = 0.04472, [2] = 0.5931, [3] = 3.833
25 val: [0] = 98.1%
26 train: [0] = 0.0728, [1] = 0.04588, [2] = 0.5977, [3] = 3.715
26 train: [0] = 97.5%
26 val: [0] = 0.04973, [1] = 0.04461, [2] = 0.5908, [3] = 3.837
26 val: [0] = 98.2%
27 train: [0] = 0.07378, [1] = 0.04579, [2] = 0.5965, [3] = 3.734
27 train: [0] = 97.4%
27 val: [0] = 0.06865, [1] = 0.04469, [2] = 0.5878, [3] = 3.767
27 val: [0] = 97.6%
28 train: [0] = 0.07275, [1] = 0.04573, [2] = 0.5958, [3] = 3.735
28 train: [0] = 97.4%
28 val: [0] = 0.06842, [1] = 0.04507, [2] = 0.5929, [3] = 3.684
28 val: [0] = 97.7%
29 train: [0] = 0.07293, [1] = 0.04569, [2] = 0.5949, [3] = 3.731
29 train: [0] = 97.4%
29 val: [0] = 0.08716, [1] = 0.04547, [2] = 0.5982, [3] = 3.579
29 val: [0] = 97.0%
30 train: [0] = 0.06915, [1] = 0.04552, [2] = 0.5934, [3] = 3.764
30 train: [0] = 97.5%
30 val: [0] = 0.05366, [1] = 0.04469, [2] = 0.585, [3] = 3.763
30 val: [0] = 98.0%
31 train: [0] = 0.06753, [1] = 0.04545, [2] = 0.5919, [3] = 3.763
31 train: [0] = 97.6%
31 val: [0] = 0.04904, [1] = 0.04447, [2] = 0.5866, [3] = 3.805
31 val: [0] = 98.3%
32 train: [0] = 0.0661, [1] = 0.04537, [2] = 0.5907, [3] = 3.779
32 train: [0] = 97.6%
32 val: [0] = 0.06632, [1] = 0.0447, [2] = 0.5898, [3] = 3.802
32 val: [0] = 97.5%
33 train: [0] = 0.06686, [1] = 0.04529, [2] = 0.5904, [3] = 3.774
33 train: [0] = 97.6%
33 val: [0] = 0.07907, [1] = 0.04483, [2] = 0.5885, [3] = 3.691
33 val: [0] = 97.3%
34 train: [0] = 0.06453, [1] = 0.04521, [2] = 0.5891, [3] = 3.781
34 train: [0] = 97.7%
34 val: [0] = 0.05373, [1] = 0.0442, [2] = 0.5856, [3] = 3.813
34 val: [0] = 98.1%
35 train: [0] = 0.06586, [1] = 0.04518, [2] = 0.5889, [3] = 3.793
35 train: [0] = 97.6%
35 val: [0] = 0.05026, [1] = 0.04445, [2] = 0.5896, [3] = 3.768
35 val: [0] = 98.3%
36 train: [0] = 0.06721, [1] = 0.04513, [2] = 0.5881, [3] = 3.802
36 train: [0] = 97.7%
36 val: [0] = 0.05433, [1] = 0.04447, [2] = 0.5874, [3] = 3.787
36 val: [0] = 98.1%
37 train: [0] = 0.06308, [1] = 0.04498, [2] = 0.5862, [3] = 3.819
37 train: [0] = 97.7%
37 val: [0] = 0.05868, [1] = 0.04419, [2] = 0.5744, [3] = 3.809
37 val: [0] = 97.9%
38 train: [0] = 0.06613, [1] = 0.04502, [2] = 0.5862, [3] = 3.807
38 train: [0] = 97.7%
38 val: [0] = 0.07824, [1] = 0.04433, [2] = 0.5832, [3] = 3.727
38 val: [0] = 97.2%
39 train: [0] = 0.06339, [1] = 0.04484, [2] = 0.5847, [3] = 3.812
39 train: [0] = 97.7%
39 val: [0] = 0.06408, [1] = 0.04426, [2] = 0.5826, [3] = 3.858
39 val: [0] = 97.7%
[vae_0] training getter for step 4:
0 train: [0] = 0.1956
0 train: [0] = 94.5%
0 val: [0] = 0.03532
0 val: [0] = 98.8%
1 train: [0] = 0.04233
1 train: [0] = 98.3%
1 val: [0] = 0.03738
1 val: [0] = 98.5%
2 train: [0] = 0.03619
2 train: [0] = 98.5%
2 val: [0] = 0.03041
2 val: [0] = 98.8%
3 train: [0] = 0.03199
3 train: [0] = 98.7%
3 val: [0] = 0.03808
3 val: [0] = 98.7%
4 train: [0] = 0.03015
4 train: [0] = 98.7%
4 val: [0] = 0.02687
4 val: [0] = 98.8%
5 train: [0] = 0.03007
5 train: [0] = 98.8%
5 val: [0] = 0.02278
5 val: [0] = 99.0%
6 train: [0] = 0.03028
6 train: [0] = 98.8%
6 val: [0] = 0.04703
6 val: [0] = 97.8%
7 train: [0] = 0.02859
7 train: [0] = 98.8%
7 val: [0] = 0.02567
7 val: [0] = 98.9%
8 train: [0] = 0.02816
8 train: [0] = 98.8%
8 val: [0] = 0.03354
8 val: [0] = 98.5%
9 train: [0] = 0.02555
9 train: [0] = 98.9%
9 val: [0] = 0.03078
9 val: [0] = 98.7%
10 train: [0] = 0.02551
10 train: [0] = 98.9%
10 val: [0] = 0.02508
10 val: [0] = 98.9%
11 train: [0] = 0.02821
11 train: [0] = 98.9%
11 val: [0] = 0.02821
11 val: [0] = 98.8%
12 train: [0] = 0.02595
12 train: [0] = 98.9%
12 val: [0] = 0.02679
12 val: [0] = 98.8%
13 train: [0] = 0.02607
13 train: [0] = 98.9%
13 val: [0] = 0.03246
13 val: [0] = 98.8%
14 train: [0] = 0.02469
14 train: [0] = 99.0%
14 val: [0] = 0.04094
14 val: [0] = 98.4%
15 train: [0] = 0.02288
15 train: [0] = 99.0%
15 val: [0] = 0.01517
15 val: [0] = 99.2%
16 train: [0] = 0.02332
16 train: [0] = 99.0%
16 val: [0] = 0.02141
16 val: [0] = 99.1%
17 train: [0] = 0.02163
17 train: [0] = 99.1%
17 val: [0] = 0.02528
17 val: [0] = 99.0%
18 train: [0] = 0.02484
18 train: [0] = 99.0%
18 val: [0] = 0.02242
18 val: [0] = 99.1%
19 train: [0] = 0.02432
19 train: [0] = 99.0%
19 val: [0] = 0.02517
19 val: [0] = 99.0%
[vae_0] test accuracy = 59.0%
