Hugging Face's logo

SFD-Project
/
SFD

Model card Files
xet
Community
1
RuoyuFeng commited on
Commit
239184f
·
verified ·
1 Parent(s): 2282caf

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. semantic_vae/dinov2_vitb14_reg/transformer_ch16/checkpoints/semantic_ae_final.pt +3 -0
  2. semantic_vae/dinov2_vitb14_reg/transformer_ch16/eval_log.txt +501 -0
  3. semantic_vae/dinov2_vitb14_reg/transformer_ch16/semantic_vae_training_log_20251208_165804.txt +0 -0
semantic_vae/dinov2_vitb14_reg/transformer_ch16/checkpoints/semantic_ae_final.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13cc6fb3e08e49d479d101415fa613e9f90e102d60c3ee5977352c475d227745
3
+ size 695233434
semantic_vae/dinov2_vitb14_reg/transformer_ch16/eval_log.txt ADDED
@@ -0,0 +1,501 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Iteration 0, MSE: 1.205577, L1: 0.862134, Cosine Similarity: -0.0055, KL Loss: 1008.889885, Classification Loss: 0.000000
2
+ Iteration 2000, MSE: 0.420600, L1: 0.510619, Cosine Similarity: 0.7162, KL Loss: 17640.437012, Classification Loss: 0.000000
3
+ Iteration 4000, MSE: 0.323604, L1: 0.447552, Cosine Similarity: 0.7899, KL Loss: 18379.940674, Classification Loss: 0.000000
4
+ Iteration 6000, MSE: 0.282597, L1: 0.417791, Cosine Similarity: 0.8182, KL Loss: 18558.535645, Classification Loss: 0.000000
5
+ Iteration 8000, MSE: 0.255805, L1: 0.397178, Cosine Similarity: 0.8365, KL Loss: 18626.315674, Classification Loss: 0.000000
6
+ Iteration 10000, MSE: 0.241924, L1: 0.386140, Cosine Similarity: 0.8458, KL Loss: 18582.302002, Classification Loss: 0.000000
7
+ Iteration 12000, MSE: 0.227471, L1: 0.374162, Cosine Similarity: 0.8556, KL Loss: 18567.914062, Classification Loss: 0.000000
8
+ Iteration 14000, MSE: 0.220317, L1: 0.368359, Cosine Similarity: 0.8605, KL Loss: 18551.423584, Classification Loss: 0.000000
9
+ Iteration 16000, MSE: 0.212593, L1: 0.361784, Cosine Similarity: 0.8657, KL Loss: 18448.310547, Classification Loss: 0.000000
10
+ Iteration 18000, MSE: 0.206776, L1: 0.356796, Cosine Similarity: 0.8697, KL Loss: 18497.733154, Classification Loss: 0.000000
11
+ Iteration 20000, MSE: 0.200707, L1: 0.351442, Cosine Similarity: 0.8737, KL Loss: 18462.513428, Classification Loss: 0.000000
12
+ Iteration 22000, MSE: 0.196345, L1: 0.347496, Cosine Similarity: 0.8767, KL Loss: 18523.855957, Classification Loss: 0.000000
13
+ Iteration 24000, MSE: 0.192196, L1: 0.343843, Cosine Similarity: 0.8794, KL Loss: 18520.897217, Classification Loss: 0.000000
14
+ Iteration 26000, MSE: 0.188707, L1: 0.340686, Cosine Similarity: 0.8818, KL Loss: 18522.754639, Classification Loss: 0.000000
15
+ Iteration 28000, MSE: 0.184890, L1: 0.337156, Cosine Similarity: 0.8843, KL Loss: 18501.010010, Classification Loss: 0.000000
16
+ Iteration 30000, MSE: 0.182633, L1: 0.335159, Cosine Similarity: 0.8858, KL Loss: 18490.080566, Classification Loss: 0.000000
17
+ Iteration 32000, MSE: 0.179366, L1: 0.332048, Cosine Similarity: 0.8880, KL Loss: 18469.303223, Classification Loss: 0.000000
18
+ Iteration 34000, MSE: 0.177544, L1: 0.330432, Cosine Similarity: 0.8892, KL Loss: 18487.743896, Classification Loss: 0.000000
19
+ Iteration 36000, MSE: 0.175275, L1: 0.328255, Cosine Similarity: 0.8907, KL Loss: 18440.844238, Classification Loss: 0.000000
20
+ Iteration 38000, MSE: 0.173465, L1: 0.326652, Cosine Similarity: 0.8919, KL Loss: 18453.927734, Classification Loss: 0.000000
21
+ Iteration 40000, MSE: 0.169900, L1: 0.323149, Cosine Similarity: 0.8942, KL Loss: 18502.963623, Classification Loss: 0.000000
22
+ Iteration 42000, MSE: 0.168478, L1: 0.321804, Cosine Similarity: 0.8951, KL Loss: 18499.752686, Classification Loss: 0.000000
23
+ Iteration 44000, MSE: 0.167237, L1: 0.320647, Cosine Similarity: 0.8959, KL Loss: 18522.969482, Classification Loss: 0.000000
24
+ Iteration 46000, MSE: 0.165746, L1: 0.319251, Cosine Similarity: 0.8969, KL Loss: 18476.560059, Classification Loss: 0.000000
25
+ Iteration 48000, MSE: 0.163708, L1: 0.317191, Cosine Similarity: 0.8983, KL Loss: 18467.981689, Classification Loss: 0.000000
26
+ Iteration 50000, MSE: 0.163799, L1: 0.317375, Cosine Similarity: 0.8982, KL Loss: 18493.207031, Classification Loss: 0.000000
27
+ Iteration 52000, MSE: 0.161929, L1: 0.315493, Cosine Similarity: 0.8995, KL Loss: 18457.795654, Classification Loss: 0.000000
28
+ Iteration 54000, MSE: 0.161041, L1: 0.314674, Cosine Similarity: 0.9001, KL Loss: 18504.987549, Classification Loss: 0.000000
29
+ Iteration 56000, MSE: 0.159543, L1: 0.313225, Cosine Similarity: 0.9010, KL Loss: 18482.766846, Classification Loss: 0.000000
30
+ Iteration 58000, MSE: 0.158112, L1: 0.311716, Cosine Similarity: 0.9019, KL Loss: 18413.397461, Classification Loss: 0.000000
31
+ Iteration 60000, MSE: 0.157818, L1: 0.311431, Cosine Similarity: 0.9022, KL Loss: 18456.808594, Classification Loss: 0.000000
32
+ Iteration 62000, MSE: 0.156100, L1: 0.309751, Cosine Similarity: 0.9033, KL Loss: 18520.864746, Classification Loss: 0.000000
33
+ Iteration 64000, MSE: 0.155561, L1: 0.309239, Cosine Similarity: 0.9036, KL Loss: 18460.157715, Classification Loss: 0.000000
34
+ Iteration 66000, MSE: 0.154774, L1: 0.308472, Cosine Similarity: 0.9042, KL Loss: 18485.780762, Classification Loss: 0.000000
35
+ Iteration 68000, MSE: 0.154143, L1: 0.307837, Cosine Similarity: 0.9046, KL Loss: 18491.011230, Classification Loss: 0.000000
36
+ Iteration 70000, MSE: 0.153057, L1: 0.306720, Cosine Similarity: 0.9053, KL Loss: 18468.268066, Classification Loss: 0.000000
37
+ Iteration 72000, MSE: 0.152041, L1: 0.305681, Cosine Similarity: 0.9059, KL Loss: 18478.676270, Classification Loss: 0.000000
38
+ Iteration 74000, MSE: 0.151011, L1: 0.304597, Cosine Similarity: 0.9066, KL Loss: 18479.905762, Classification Loss: 0.000000
39
+ Iteration 76000, MSE: 0.150804, L1: 0.304477, Cosine Similarity: 0.9067, KL Loss: 18467.026855, Classification Loss: 0.000000
40
+ Iteration 78000, MSE: 0.149791, L1: 0.303400, Cosine Similarity: 0.9074, KL Loss: 18465.816406, Classification Loss: 0.000000
41
+ Iteration 80000, MSE: 0.149095, L1: 0.302687, Cosine Similarity: 0.9078, KL Loss: 18461.814697, Classification Loss: 0.000000
42
+ Iteration 82000, MSE: 0.148686, L1: 0.302278, Cosine Similarity: 0.9081, KL Loss: 18482.692627, Classification Loss: 0.000000
43
+ Iteration 84000, MSE: 0.148042, L1: 0.301642, Cosine Similarity: 0.9085, KL Loss: 18445.470459, Classification Loss: 0.000000
44
+ Iteration 86000, MSE: 0.147372, L1: 0.300956, Cosine Similarity: 0.9090, KL Loss: 18489.060059, Classification Loss: 0.000000
45
+ Iteration 88000, MSE: 0.147227, L1: 0.300760, Cosine Similarity: 0.9091, KL Loss: 18495.015381, Classification Loss: 0.000000
46
+ Iteration 90000, MSE: 0.145360, L1: 0.298733, Cosine Similarity: 0.9102, KL Loss: 18487.679199, Classification Loss: 0.000000
47
+ Iteration 92000, MSE: 0.145115, L1: 0.298567, Cosine Similarity: 0.9104, KL Loss: 18496.440186, Classification Loss: 0.000000
48
+ Iteration 94000, MSE: 0.144270, L1: 0.297694, Cosine Similarity: 0.9110, KL Loss: 18426.512695, Classification Loss: 0.000000
49
+ Iteration 96000, MSE: 0.144063, L1: 0.297534, Cosine Similarity: 0.9111, KL Loss: 18438.703857, Classification Loss: 0.000000
50
+ Iteration 98000, MSE: 0.143763, L1: 0.297214, Cosine Similarity: 0.9113, KL Loss: 18439.104980, Classification Loss: 0.000000
51
+ Iteration 100000, MSE: 0.143476, L1: 0.296950, Cosine Similarity: 0.9115, KL Loss: 18463.082275, Classification Loss: 0.000000
52
+ Iteration 102000, MSE: 0.142999, L1: 0.296431, Cosine Similarity: 0.9118, KL Loss: 18493.525879, Classification Loss: 0.000000
53
+ Iteration 104000, MSE: 0.142410, L1: 0.295783, Cosine Similarity: 0.9122, KL Loss: 18448.456299, Classification Loss: 0.000000
54
+ Iteration 106000, MSE: 0.141784, L1: 0.295123, Cosine Similarity: 0.9126, KL Loss: 18446.669922, Classification Loss: 0.000000
55
+ Iteration 108000, MSE: 0.141589, L1: 0.294978, Cosine Similarity: 0.9127, KL Loss: 18464.635742, Classification Loss: 0.000000
56
+ Iteration 110000, MSE: 0.141041, L1: 0.294375, Cosine Similarity: 0.9131, KL Loss: 18469.235107, Classification Loss: 0.000000
57
+ Iteration 112000, MSE: 0.140337, L1: 0.293564, Cosine Similarity: 0.9135, KL Loss: 18485.431641, Classification Loss: 0.000000
58
+ Iteration 114000, MSE: 0.140234, L1: 0.293492, Cosine Similarity: 0.9136, KL Loss: 18467.624023, Classification Loss: 0.000000
59
+ Iteration 116000, MSE: 0.139748, L1: 0.292988, Cosine Similarity: 0.9139, KL Loss: 18454.233154, Classification Loss: 0.000000
60
+ Iteration 118000, MSE: 0.139144, L1: 0.292363, Cosine Similarity: 0.9143, KL Loss: 18476.957520, Classification Loss: 0.000000
61
+ Iteration 120000, MSE: 0.138632, L1: 0.291765, Cosine Similarity: 0.9146, KL Loss: 18420.035400, Classification Loss: 0.000000
62
+ Iteration 122000, MSE: 0.138466, L1: 0.291613, Cosine Similarity: 0.9147, KL Loss: 18502.729736, Classification Loss: 0.000000
63
+ Iteration 124000, MSE: 0.137830, L1: 0.290902, Cosine Similarity: 0.9151, KL Loss: 18470.733398, Classification Loss: 0.000000
64
+ Iteration 126000, MSE: 0.137788, L1: 0.290910, Cosine Similarity: 0.9151, KL Loss: 18480.120605, Classification Loss: 0.000000
65
+ Iteration 128000, MSE: 0.137157, L1: 0.290275, Cosine Similarity: 0.9155, KL Loss: 18497.282715, Classification Loss: 0.000000
66
+ Iteration 130000, MSE: 0.136931, L1: 0.289987, Cosine Similarity: 0.9157, KL Loss: 18484.512207, Classification Loss: 0.000000
67
+ Iteration 132000, MSE: 0.136726, L1: 0.289853, Cosine Similarity: 0.9158, KL Loss: 18455.908936, Classification Loss: 0.000000
68
+ Iteration 134000, MSE: 0.136191, L1: 0.289214, Cosine Similarity: 0.9162, KL Loss: 18480.534180, Classification Loss: 0.000000
69
+ Iteration 136000, MSE: 0.136043, L1: 0.289084, Cosine Similarity: 0.9163, KL Loss: 18482.905762, Classification Loss: 0.000000
70
+ Iteration 138000, MSE: 0.135856, L1: 0.288860, Cosine Similarity: 0.9164, KL Loss: 18452.770508, Classification Loss: 0.000000
71
+ Iteration 140000, MSE: 0.135022, L1: 0.287914, Cosine Similarity: 0.9169, KL Loss: 18481.919922, Classification Loss: 0.000000
72
+ Iteration 142000, MSE: 0.134700, L1: 0.287637, Cosine Similarity: 0.9171, KL Loss: 18459.712158, Classification Loss: 0.000000
73
+ Iteration 144000, MSE: 0.134385, L1: 0.287235, Cosine Similarity: 0.9173, KL Loss: 18455.075439, Classification Loss: 0.000000
74
+ Iteration 146000, MSE: 0.134349, L1: 0.287249, Cosine Similarity: 0.9173, KL Loss: 18456.003174, Classification Loss: 0.000000
75
+ Iteration 148000, MSE: 0.134011, L1: 0.286862, Cosine Similarity: 0.9176, KL Loss: 18493.236572, Classification Loss: 0.000000
76
+ Iteration 150000, MSE: 0.133755, L1: 0.286613, Cosine Similarity: 0.9177, KL Loss: 18488.733154, Classification Loss: 0.000000
77
+ Iteration 152000, MSE: 0.133329, L1: 0.286110, Cosine Similarity: 0.9180, KL Loss: 18429.347412, Classification Loss: 0.000000
78
+ Iteration 154000, MSE: 0.133446, L1: 0.286360, Cosine Similarity: 0.9179, KL Loss: 18478.921631, Classification Loss: 0.000000
79
+ Iteration 156000, MSE: 0.132888, L1: 0.285618, Cosine Similarity: 0.9183, KL Loss: 18466.389160, Classification Loss: 0.000000
80
+ Iteration 158000, MSE: 0.132117, L1: 0.284846, Cosine Similarity: 0.9188, KL Loss: 18442.168213, Classification Loss: 0.000000
81
+ Iteration 160000, MSE: 0.132446, L1: 0.285247, Cosine Similarity: 0.9186, KL Loss: 18426.275879, Classification Loss: 0.000000
82
+ Iteration 162000, MSE: 0.132431, L1: 0.285229, Cosine Similarity: 0.9186, KL Loss: 18475.635498, Classification Loss: 0.000000
83
+ Iteration 164000, MSE: 0.132220, L1: 0.284989, Cosine Similarity: 0.9187, KL Loss: 18446.235840, Classification Loss: 0.000000
84
+ Iteration 166000, MSE: 0.131487, L1: 0.284130, Cosine Similarity: 0.9192, KL Loss: 18467.777344, Classification Loss: 0.000000
85
+ Iteration 168000, MSE: 0.130978, L1: 0.283532, Cosine Similarity: 0.9195, KL Loss: 18467.393311, Classification Loss: 0.000000
86
+ Iteration 170000, MSE: 0.130632, L1: 0.283235, Cosine Similarity: 0.9197, KL Loss: 18453.027344, Classification Loss: 0.000000
87
+ Iteration 172000, MSE: 0.130462, L1: 0.282987, Cosine Similarity: 0.9198, KL Loss: 18465.076904, Classification Loss: 0.000000
88
+ Iteration 174000, MSE: 0.130297, L1: 0.282852, Cosine Similarity: 0.9199, KL Loss: 18461.486084, Classification Loss: 0.000000
89
+ Iteration 176000, MSE: 0.130009, L1: 0.282524, Cosine Similarity: 0.9201, KL Loss: 18437.253418, Classification Loss: 0.000000
90
+ Iteration 178000, MSE: 0.129967, L1: 0.282466, Cosine Similarity: 0.9202, KL Loss: 18457.934326, Classification Loss: 0.000000
91
+ Iteration 180000, MSE: 0.129917, L1: 0.282393, Cosine Similarity: 0.9202, KL Loss: 18445.013916, Classification Loss: 0.000000
92
+ Iteration 182000, MSE: 0.129484, L1: 0.281913, Cosine Similarity: 0.9205, KL Loss: 18452.794922, Classification Loss: 0.000000
93
+ Iteration 184000, MSE: 0.129401, L1: 0.281843, Cosine Similarity: 0.9205, KL Loss: 18448.067627, Classification Loss: 0.000000
94
+ Iteration 186000, MSE: 0.129297, L1: 0.281728, Cosine Similarity: 0.9206, KL Loss: 18443.370605, Classification Loss: 0.000000
95
+ Iteration 188000, MSE: 0.129190, L1: 0.281622, Cosine Similarity: 0.9206, KL Loss: 18434.082031, Classification Loss: 0.000000
96
+ Iteration 190000, MSE: 0.129131, L1: 0.281596, Cosine Similarity: 0.9207, KL Loss: 18455.481689, Classification Loss: 0.000000
97
+ Iteration 192000, MSE: 0.128476, L1: 0.280826, Cosine Similarity: 0.9211, KL Loss: 18467.767090, Classification Loss: 0.000000
98
+ Iteration 194000, MSE: 0.128181, L1: 0.280498, Cosine Similarity: 0.9213, KL Loss: 18428.986084, Classification Loss: 0.000000
99
+ Iteration 196000, MSE: 0.128232, L1: 0.280595, Cosine Similarity: 0.9213, KL Loss: 18413.087402, Classification Loss: 0.000000
100
+ Iteration 198000, MSE: 0.127416, L1: 0.279658, Cosine Similarity: 0.9218, KL Loss: 18415.302246, Classification Loss: 0.000000
101
+ Iteration 200000, MSE: 0.127520, L1: 0.279749, Cosine Similarity: 0.9217, KL Loss: 18398.968262, Classification Loss: 0.000000
102
+ Iteration 202000, MSE: 0.127299, L1: 0.279499, Cosine Similarity: 0.9219, KL Loss: 18466.892822, Classification Loss: 0.000000
103
+ Iteration 204000, MSE: 0.127503, L1: 0.279776, Cosine Similarity: 0.9217, KL Loss: 18459.223633, Classification Loss: 0.000000
104
+ Iteration 206000, MSE: 0.127465, L1: 0.279751, Cosine Similarity: 0.9218, KL Loss: 18462.308838, Classification Loss: 0.000000
105
+ Iteration 208000, MSE: 0.126725, L1: 0.278907, Cosine Similarity: 0.9222, KL Loss: 18443.282227, Classification Loss: 0.000000
106
+ Iteration 210000, MSE: 0.126727, L1: 0.278945, Cosine Similarity: 0.9222, KL Loss: 18481.995361, Classification Loss: 0.000000
107
+ Iteration 212000, MSE: 0.126589, L1: 0.278781, Cosine Similarity: 0.9223, KL Loss: 18453.269287, Classification Loss: 0.000000
108
+ Iteration 214000, MSE: 0.126864, L1: 0.279093, Cosine Similarity: 0.9222, KL Loss: 18455.252441, Classification Loss: 0.000000
109
+ Iteration 216000, MSE: 0.126627, L1: 0.278821, Cosine Similarity: 0.9223, KL Loss: 18465.869385, Classification Loss: 0.000000
110
+ Iteration 218000, MSE: 0.125627, L1: 0.277655, Cosine Similarity: 0.9229, KL Loss: 18425.380371, Classification Loss: 0.000000
111
+ Iteration 220000, MSE: 0.125918, L1: 0.278026, Cosine Similarity: 0.9228, KL Loss: 18480.342041, Classification Loss: 0.000000
112
+ Iteration 222000, MSE: 0.125491, L1: 0.277537, Cosine Similarity: 0.9230, KL Loss: 18505.230713, Classification Loss: 0.000000
113
+ Iteration 224000, MSE: 0.125260, L1: 0.277300, Cosine Similarity: 0.9232, KL Loss: 18518.577393, Classification Loss: 0.000000
114
+ Iteration 226000, MSE: 0.125187, L1: 0.277167, Cosine Similarity: 0.9232, KL Loss: 18450.948730, Classification Loss: 0.000000
115
+ Iteration 228000, MSE: 0.125071, L1: 0.277048, Cosine Similarity: 0.9233, KL Loss: 18476.931396, Classification Loss: 0.000000
116
+ Iteration 230000, MSE: 0.124746, L1: 0.276655, Cosine Similarity: 0.9235, KL Loss: 18472.796631, Classification Loss: 0.000000
117
+ Iteration 232000, MSE: 0.124441, L1: 0.276319, Cosine Similarity: 0.9237, KL Loss: 18457.138428, Classification Loss: 0.000000
118
+ Iteration 234000, MSE: 0.124825, L1: 0.276766, Cosine Similarity: 0.9235, KL Loss: 18507.587402, Classification Loss: 0.000000
119
+ Iteration 236000, MSE: 0.124204, L1: 0.276074, Cosine Similarity: 0.9239, KL Loss: 18516.887695, Classification Loss: 0.000000
120
+ Iteration 238000, MSE: 0.124094, L1: 0.275911, Cosine Similarity: 0.9239, KL Loss: 18416.590088, Classification Loss: 0.000000
121
+ Iteration 240000, MSE: 0.123751, L1: 0.275588, Cosine Similarity: 0.9241, KL Loss: 18463.850830, Classification Loss: 0.000000
122
+ Iteration 242000, MSE: 0.123627, L1: 0.275411, Cosine Similarity: 0.9242, KL Loss: 18487.141113, Classification Loss: 0.000000
123
+ Iteration 244000, MSE: 0.123769, L1: 0.275645, Cosine Similarity: 0.9241, KL Loss: 18490.387939, Classification Loss: 0.000000
124
+ Iteration 246000, MSE: 0.123544, L1: 0.275335, Cosine Similarity: 0.9243, KL Loss: 18474.789062, Classification Loss: 0.000000
125
+ Iteration 248000, MSE: 0.123224, L1: 0.274925, Cosine Similarity: 0.9244, KL Loss: 18475.372314, Classification Loss: 0.000000
126
+ Iteration 250000, MSE: 0.123234, L1: 0.274953, Cosine Similarity: 0.9245, KL Loss: 18488.488525, Classification Loss: 0.000000
127
+ Iteration 252000, MSE: 0.123194, L1: 0.275022, Cosine Similarity: 0.9245, KL Loss: 18454.738037, Classification Loss: 0.000000
128
+ Iteration 254000, MSE: 0.123037, L1: 0.274844, Cosine Similarity: 0.9246, KL Loss: 18495.982910, Classification Loss: 0.000000
129
+ Iteration 256000, MSE: 0.122606, L1: 0.274323, Cosine Similarity: 0.9249, KL Loss: 18530.723389, Classification Loss: 0.000000
130
+ Iteration 258000, MSE: 0.122585, L1: 0.274264, Cosine Similarity: 0.9249, KL Loss: 18487.666260, Classification Loss: 0.000000
131
+ Iteration 260000, MSE: 0.122822, L1: 0.274524, Cosine Similarity: 0.9247, KL Loss: 18461.871826, Classification Loss: 0.000000
132
+ Iteration 262000, MSE: 0.122223, L1: 0.273847, Cosine Similarity: 0.9251, KL Loss: 18494.208740, Classification Loss: 0.000000
133
+ Iteration 264000, MSE: 0.122490, L1: 0.274156, Cosine Similarity: 0.9249, KL Loss: 18493.054199, Classification Loss: 0.000000
134
+ Iteration 266000, MSE: 0.121923, L1: 0.273469, Cosine Similarity: 0.9253, KL Loss: 18458.547363, Classification Loss: 0.000000
135
+ Iteration 268000, MSE: 0.121871, L1: 0.273452, Cosine Similarity: 0.9253, KL Loss: 18466.977051, Classification Loss: 0.000000
136
+ Iteration 270000, MSE: 0.121740, L1: 0.273302, Cosine Similarity: 0.9254, KL Loss: 18441.298584, Classification Loss: 0.000000
137
+ Iteration 272000, MSE: 0.121513, L1: 0.273043, Cosine Similarity: 0.9255, KL Loss: 18488.137207, Classification Loss: 0.000000
138
+ Iteration 274000, MSE: 0.121565, L1: 0.273143, Cosine Similarity: 0.9255, KL Loss: 18492.721924, Classification Loss: 0.000000
139
+ Iteration 276000, MSE: 0.121575, L1: 0.273152, Cosine Similarity: 0.9255, KL Loss: 18460.417725, Classification Loss: 0.000000
140
+ Iteration 278000, MSE: 0.121451, L1: 0.272966, Cosine Similarity: 0.9256, KL Loss: 18439.874512, Classification Loss: 0.000000
141
+ Iteration 280000, MSE: 0.120689, L1: 0.272072, Cosine Similarity: 0.9261, KL Loss: 18497.331543, Classification Loss: 0.000000
142
+ Iteration 282000, MSE: 0.120687, L1: 0.272120, Cosine Similarity: 0.9261, KL Loss: 18487.142090, Classification Loss: 0.000000
143
+ Iteration 284000, MSE: 0.120359, L1: 0.271687, Cosine Similarity: 0.9263, KL Loss: 18499.536621, Classification Loss: 0.000000
144
+ Iteration 286000, MSE: 0.121011, L1: 0.272477, Cosine Similarity: 0.9259, KL Loss: 18486.465088, Classification Loss: 0.000000
145
+ Iteration 288000, MSE: 0.120519, L1: 0.271919, Cosine Similarity: 0.9262, KL Loss: 18447.884033, Classification Loss: 0.000000
146
+ Iteration 290000, MSE: 0.120373, L1: 0.271773, Cosine Similarity: 0.9263, KL Loss: 18492.553223, Classification Loss: 0.000000
147
+ Iteration 292000, MSE: 0.120220, L1: 0.271577, Cosine Similarity: 0.9264, KL Loss: 18486.211182, Classification Loss: 0.000000
148
+ Iteration 294000, MSE: 0.120449, L1: 0.271856, Cosine Similarity: 0.9262, KL Loss: 18452.805176, Classification Loss: 0.000000
149
+ Iteration 296000, MSE: 0.119957, L1: 0.271272, Cosine Similarity: 0.9265, KL Loss: 18473.359375, Classification Loss: 0.000000
150
+ Iteration 298000, MSE: 0.120099, L1: 0.271445, Cosine Similarity: 0.9265, KL Loss: 18515.663330, Classification Loss: 0.000000
151
+ Iteration 300000, MSE: 0.120176, L1: 0.271558, Cosine Similarity: 0.9264, KL Loss: 18509.222412, Classification Loss: 0.000000
152
+ Iteration 302000, MSE: 0.119575, L1: 0.270830, Cosine Similarity: 0.9268, KL Loss: 18470.879150, Classification Loss: 0.000000
153
+ Iteration 304000, MSE: 0.119267, L1: 0.270400, Cosine Similarity: 0.9270, KL Loss: 18498.318359, Classification Loss: 0.000000
154
+ Iteration 306000, MSE: 0.119429, L1: 0.270688, Cosine Similarity: 0.9269, KL Loss: 18526.301758, Classification Loss: 0.000000
155
+ Iteration 308000, MSE: 0.119389, L1: 0.270624, Cosine Similarity: 0.9269, KL Loss: 18432.687012, Classification Loss: 0.000000
156
+ Iteration 310000, MSE: 0.119605, L1: 0.270904, Cosine Similarity: 0.9268, KL Loss: 18478.406006, Classification Loss: 0.000000
157
+ Iteration 312000, MSE: 0.118987, L1: 0.270127, Cosine Similarity: 0.9272, KL Loss: 18492.151123, Classification Loss: 0.000000
158
+ Iteration 314000, MSE: 0.119282, L1: 0.270543, Cosine Similarity: 0.9270, KL Loss: 18489.646973, Classification Loss: 0.000000
159
+ Iteration 316000, MSE: 0.118515, L1: 0.269601, Cosine Similarity: 0.9275, KL Loss: 18492.218018, Classification Loss: 0.000000
160
+ Iteration 318000, MSE: 0.118293, L1: 0.269351, Cosine Similarity: 0.9276, KL Loss: 18487.656250, Classification Loss: 0.000000
161
+ Iteration 320000, MSE: 0.118468, L1: 0.269576, Cosine Similarity: 0.9275, KL Loss: 18440.536621, Classification Loss: 0.000000
162
+ Iteration 322000, MSE: 0.118361, L1: 0.269470, Cosine Similarity: 0.9276, KL Loss: 18519.775391, Classification Loss: 0.000000
163
+ Iteration 324000, MSE: 0.118128, L1: 0.269177, Cosine Similarity: 0.9277, KL Loss: 18502.168945, Classification Loss: 0.000000
164
+ Iteration 326000, MSE: 0.118007, L1: 0.269034, Cosine Similarity: 0.9278, KL Loss: 18489.204346, Classification Loss: 0.000000
165
+ Iteration 328000, MSE: 0.118264, L1: 0.269331, Cosine Similarity: 0.9276, KL Loss: 18500.139648, Classification Loss: 0.000000
166
+ Iteration 330000, MSE: 0.118265, L1: 0.269339, Cosine Similarity: 0.9276, KL Loss: 18480.953369, Classification Loss: 0.000000
167
+ Iteration 332000, MSE: 0.118283, L1: 0.269387, Cosine Similarity: 0.9276, KL Loss: 18474.314453, Classification Loss: 0.000000
168
+ Iteration 334000, MSE: 0.118040, L1: 0.269095, Cosine Similarity: 0.9278, KL Loss: 18479.544434, Classification Loss: 0.000000
169
+ Iteration 336000, MSE: 0.117824, L1: 0.268821, Cosine Similarity: 0.9279, KL Loss: 18509.551758, Classification Loss: 0.000000
170
+ Iteration 338000, MSE: 0.117407, L1: 0.268357, Cosine Similarity: 0.9282, KL Loss: 18522.021484, Classification Loss: 0.000000
171
+ Iteration 340000, MSE: 0.117261, L1: 0.268135, Cosine Similarity: 0.9283, KL Loss: 18489.677734, Classification Loss: 0.000000
172
+ Iteration 342000, MSE: 0.117383, L1: 0.268401, Cosine Similarity: 0.9282, KL Loss: 18506.826416, Classification Loss: 0.000000
173
+ Iteration 344000, MSE: 0.117694, L1: 0.268744, Cosine Similarity: 0.9280, KL Loss: 18506.625977, Classification Loss: 0.000000
174
+ Iteration 346000, MSE: 0.117036, L1: 0.267900, Cosine Similarity: 0.9284, KL Loss: 18491.677246, Classification Loss: 0.000000
175
+ Iteration 348000, MSE: 0.117044, L1: 0.267907, Cosine Similarity: 0.9284, KL Loss: 18474.105469, Classification Loss: 0.000000
176
+ Iteration 350000, MSE: 0.117478, L1: 0.268481, Cosine Similarity: 0.9281, KL Loss: 18479.648682, Classification Loss: 0.000000
177
+ Iteration 352000, MSE: 0.116595, L1: 0.267361, Cosine Similarity: 0.9287, KL Loss: 18523.013428, Classification Loss: 0.000000
178
+ Iteration 354000, MSE: 0.116627, L1: 0.267415, Cosine Similarity: 0.9287, KL Loss: 18527.567139, Classification Loss: 0.000000
179
+ Iteration 356000, MSE: 0.116395, L1: 0.267131, Cosine Similarity: 0.9288, KL Loss: 18473.763428, Classification Loss: 0.000000
180
+ Iteration 358000, MSE: 0.116213, L1: 0.266896, Cosine Similarity: 0.9289, KL Loss: 18528.789551, Classification Loss: 0.000000
181
+ Iteration 360000, MSE: 0.116204, L1: 0.266939, Cosine Similarity: 0.9289, KL Loss: 18486.220215, Classification Loss: 0.000000
182
+ Iteration 362000, MSE: 0.116375, L1: 0.267139, Cosine Similarity: 0.9288, KL Loss: 18530.551270, Classification Loss: 0.000000
183
+ Iteration 364000, MSE: 0.116167, L1: 0.266881, Cosine Similarity: 0.9290, KL Loss: 18553.431641, Classification Loss: 0.000000
184
+ Iteration 366000, MSE: 0.115921, L1: 0.266614, Cosine Similarity: 0.9291, KL Loss: 18477.985596, Classification Loss: 0.000000
185
+ Iteration 368000, MSE: 0.115760, L1: 0.266419, Cosine Similarity: 0.9292, KL Loss: 18469.287354, Classification Loss: 0.000000
186
+ Iteration 370000, MSE: 0.116212, L1: 0.266955, Cosine Similarity: 0.9290, KL Loss: 18501.143311, Classification Loss: 0.000000
187
+ Iteration 372000, MSE: 0.115933, L1: 0.266625, Cosine Similarity: 0.9291, KL Loss: 18533.864014, Classification Loss: 0.000000
188
+ Iteration 374000, MSE: 0.115956, L1: 0.266612, Cosine Similarity: 0.9291, KL Loss: 18504.907959, Classification Loss: 0.000000
189
+ Iteration 376000, MSE: 0.115714, L1: 0.266331, Cosine Similarity: 0.9292, KL Loss: 18500.648926, Classification Loss: 0.000000
190
+ Iteration 378000, MSE: 0.115402, L1: 0.266009, Cosine Similarity: 0.9294, KL Loss: 18559.538574, Classification Loss: 0.000000
191
+ Iteration 380000, MSE: 0.115291, L1: 0.265876, Cosine Similarity: 0.9295, KL Loss: 18501.677002, Classification Loss: 0.000000
192
+ Iteration 382000, MSE: 0.115299, L1: 0.265856, Cosine Similarity: 0.9295, KL Loss: 18523.438965, Classification Loss: 0.000000
193
+ Iteration 384000, MSE: 0.115385, L1: 0.265931, Cosine Similarity: 0.9295, KL Loss: 18510.807861, Classification Loss: 0.000000
194
+ Iteration 386000, MSE: 0.115448, L1: 0.266037, Cosine Similarity: 0.9294, KL Loss: 18528.902832, Classification Loss: 0.000000
195
+ Iteration 388000, MSE: 0.115253, L1: 0.265808, Cosine Similarity: 0.9296, KL Loss: 18521.649414, Classification Loss: 0.000000
196
+ Iteration 390000, MSE: 0.115259, L1: 0.265831, Cosine Similarity: 0.9295, KL Loss: 18474.075684, Classification Loss: 0.000000
197
+ Iteration 392000, MSE: 0.114824, L1: 0.265294, Cosine Similarity: 0.9298, KL Loss: 18517.051758, Classification Loss: 0.000000
198
+ Iteration 394000, MSE: 0.115040, L1: 0.265578, Cosine Similarity: 0.9297, KL Loss: 18499.220947, Classification Loss: 0.000000
199
+ Iteration 396000, MSE: 0.114808, L1: 0.265312, Cosine Similarity: 0.9298, KL Loss: 18488.421143, Classification Loss: 0.000000
200
+ Iteration 398000, MSE: 0.114536, L1: 0.264996, Cosine Similarity: 0.9300, KL Loss: 18524.037109, Classification Loss: 0.000000
201
+ Iteration 400000, MSE: 0.114614, L1: 0.265084, Cosine Similarity: 0.9300, KL Loss: 18498.032715, Classification Loss: 0.000000
202
+ Iteration 402000, MSE: 0.114211, L1: 0.264588, Cosine Similarity: 0.9302, KL Loss: 18488.531006, Classification Loss: 0.000000
203
+ Iteration 404000, MSE: 0.114394, L1: 0.264823, Cosine Similarity: 0.9301, KL Loss: 18517.589355, Classification Loss: 0.000000
204
+ Iteration 406000, MSE: 0.114073, L1: 0.264408, Cosine Similarity: 0.9303, KL Loss: 18484.362793, Classification Loss: 0.000000
205
+ Iteration 408000, MSE: 0.114178, L1: 0.264532, Cosine Similarity: 0.9302, KL Loss: 18541.244385, Classification Loss: 0.000000
206
+ Iteration 410000, MSE: 0.114042, L1: 0.264376, Cosine Similarity: 0.9303, KL Loss: 18487.148926, Classification Loss: 0.000000
207
+ Iteration 412000, MSE: 0.113857, L1: 0.264153, Cosine Similarity: 0.9304, KL Loss: 18484.422119, Classification Loss: 0.000000
208
+ Iteration 414000, MSE: 0.113894, L1: 0.264205, Cosine Similarity: 0.9304, KL Loss: 18474.881836, Classification Loss: 0.000000
209
+ Iteration 416000, MSE: 0.114155, L1: 0.264532, Cosine Similarity: 0.9303, KL Loss: 18516.914795, Classification Loss: 0.000000
210
+ Iteration 418000, MSE: 0.113443, L1: 0.263699, Cosine Similarity: 0.9307, KL Loss: 18527.687500, Classification Loss: 0.000000
211
+ Iteration 420000, MSE: 0.113757, L1: 0.264041, Cosine Similarity: 0.9305, KL Loss: 18504.458252, Classification Loss: 0.000000
212
+ Iteration 422000, MSE: 0.113767, L1: 0.264066, Cosine Similarity: 0.9305, KL Loss: 18496.157959, Classification Loss: 0.000000
213
+ Iteration 424000, MSE: 0.113830, L1: 0.264191, Cosine Similarity: 0.9305, KL Loss: 18523.013184, Classification Loss: 0.000000
214
+ Iteration 426000, MSE: 0.113651, L1: 0.263934, Cosine Similarity: 0.9306, KL Loss: 18515.134766, Classification Loss: 0.000000
215
+ Iteration 428000, MSE: 0.113908, L1: 0.264232, Cosine Similarity: 0.9304, KL Loss: 18523.775391, Classification Loss: 0.000000
216
+ Iteration 430000, MSE: 0.113236, L1: 0.263428, Cosine Similarity: 0.9308, KL Loss: 18537.898682, Classification Loss: 0.000000
217
+ Iteration 432000, MSE: 0.113392, L1: 0.263646, Cosine Similarity: 0.9307, KL Loss: 18482.367920, Classification Loss: 0.000000
218
+ Iteration 434000, MSE: 0.113316, L1: 0.263573, Cosine Similarity: 0.9308, KL Loss: 18517.962402, Classification Loss: 0.000000
219
+ Iteration 436000, MSE: 0.113033, L1: 0.263206, Cosine Similarity: 0.9310, KL Loss: 18496.226318, Classification Loss: 0.000000
220
+ Iteration 438000, MSE: 0.113295, L1: 0.263547, Cosine Similarity: 0.9308, KL Loss: 18487.672607, Classification Loss: 0.000000
221
+ Iteration 440000, MSE: 0.112726, L1: 0.262842, Cosine Similarity: 0.9312, KL Loss: 18476.207275, Classification Loss: 0.000000
222
+ Iteration 442000, MSE: 0.113138, L1: 0.263334, Cosine Similarity: 0.9309, KL Loss: 18518.620605, Classification Loss: 0.000000
223
+ Iteration 444000, MSE: 0.112455, L1: 0.262490, Cosine Similarity: 0.9313, KL Loss: 18537.851807, Classification Loss: 0.000000
224
+ Iteration 446000, MSE: 0.112631, L1: 0.262751, Cosine Similarity: 0.9312, KL Loss: 18504.405029, Classification Loss: 0.000000
225
+ Iteration 448000, MSE: 0.112942, L1: 0.263082, Cosine Similarity: 0.9310, KL Loss: 18503.389160, Classification Loss: 0.000000
226
+ Iteration 450000, MSE: 0.112334, L1: 0.262369, Cosine Similarity: 0.9314, KL Loss: 18501.834473, Classification Loss: 0.000000
227
+ Iteration 452000, MSE: 0.112271, L1: 0.262302, Cosine Similarity: 0.9315, KL Loss: 18500.824707, Classification Loss: 0.000000
228
+ Iteration 454000, MSE: 0.112105, L1: 0.262054, Cosine Similarity: 0.9316, KL Loss: 18507.036133, Classification Loss: 0.000000
229
+ Iteration 456000, MSE: 0.112338, L1: 0.262367, Cosine Similarity: 0.9314, KL Loss: 18462.983154, Classification Loss: 0.000000
230
+ Iteration 458000, MSE: 0.112104, L1: 0.262055, Cosine Similarity: 0.9316, KL Loss: 18504.541992, Classification Loss: 0.000000
231
+ Iteration 460000, MSE: 0.111923, L1: 0.261833, Cosine Similarity: 0.9317, KL Loss: 18511.089355, Classification Loss: 0.000000
232
+ Iteration 462000, MSE: 0.111909, L1: 0.261807, Cosine Similarity: 0.9317, KL Loss: 18513.679443, Classification Loss: 0.000000
233
+ Iteration 464000, MSE: 0.111720, L1: 0.261592, Cosine Similarity: 0.9318, KL Loss: 18476.485107, Classification Loss: 0.000000
234
+ Iteration 466000, MSE: 0.111643, L1: 0.261510, Cosine Similarity: 0.9318, KL Loss: 18466.056396, Classification Loss: 0.000000
235
+ Iteration 468000, MSE: 0.111679, L1: 0.261574, Cosine Similarity: 0.9318, KL Loss: 18512.677002, Classification Loss: 0.000000
236
+ Iteration 470000, MSE: 0.111536, L1: 0.261432, Cosine Similarity: 0.9319, KL Loss: 18478.828613, Classification Loss: 0.000000
237
+ Iteration 472000, MSE: 0.111557, L1: 0.261415, Cosine Similarity: 0.9319, KL Loss: 18538.888916, Classification Loss: 0.000000
238
+ Iteration 474000, MSE: 0.111582, L1: 0.261517, Cosine Similarity: 0.9319, KL Loss: 18502.381592, Classification Loss: 0.000000
239
+ Iteration 476000, MSE: 0.111474, L1: 0.261365, Cosine Similarity: 0.9320, KL Loss: 18500.675781, Classification Loss: 0.000000
240
+ Iteration 478000, MSE: 0.111484, L1: 0.261376, Cosine Similarity: 0.9320, KL Loss: 18495.399414, Classification Loss: 0.000000
241
+ Iteration 480000, MSE: 0.111538, L1: 0.261446, Cosine Similarity: 0.9319, KL Loss: 18496.845459, Classification Loss: 0.000000
242
+ Iteration 482000, MSE: 0.111489, L1: 0.261365, Cosine Similarity: 0.9320, KL Loss: 18485.541992, Classification Loss: 0.000000
243
+ Iteration 484000, MSE: 0.111082, L1: 0.260888, Cosine Similarity: 0.9322, KL Loss: 18489.414062, Classification Loss: 0.000000
244
+ Iteration 486000, MSE: 0.111090, L1: 0.260888, Cosine Similarity: 0.9322, KL Loss: 18507.081299, Classification Loss: 0.000000
245
+ Iteration 488000, MSE: 0.111031, L1: 0.260838, Cosine Similarity: 0.9322, KL Loss: 18494.894531, Classification Loss: 0.000000
246
+ Iteration 490000, MSE: 0.110760, L1: 0.260478, Cosine Similarity: 0.9324, KL Loss: 18516.105469, Classification Loss: 0.000000
247
+ Iteration 492000, MSE: 0.110891, L1: 0.260595, Cosine Similarity: 0.9323, KL Loss: 18509.413086, Classification Loss: 0.000000
248
+ Iteration 494000, MSE: 0.110891, L1: 0.260632, Cosine Similarity: 0.9323, KL Loss: 18543.138916, Classification Loss: 0.000000
249
+ Iteration 496000, MSE: 0.110723, L1: 0.260453, Cosine Similarity: 0.9324, KL Loss: 18504.202148, Classification Loss: 0.000000
250
+ Iteration 498000, MSE: 0.110381, L1: 0.259997, Cosine Similarity: 0.9326, KL Loss: 18464.514160, Classification Loss: 0.000000
251
+ Iteration 500000, MSE: 0.110435, L1: 0.260054, Cosine Similarity: 0.9326, KL Loss: 18492.584961, Classification Loss: 0.000000
252
+ Iteration 502000, MSE: 0.110458, L1: 0.260131, Cosine Similarity: 0.9326, KL Loss: 18508.783691, Classification Loss: 0.000000
253
+ Iteration 504000, MSE: 0.110421, L1: 0.260065, Cosine Similarity: 0.9326, KL Loss: 18531.077148, Classification Loss: 0.000000
254
+ Iteration 506000, MSE: 0.110385, L1: 0.260015, Cosine Similarity: 0.9327, KL Loss: 18486.255859, Classification Loss: 0.000000
255
+ Iteration 508000, MSE: 0.110260, L1: 0.259880, Cosine Similarity: 0.9327, KL Loss: 18475.932861, Classification Loss: 0.000000
256
+ Iteration 510000, MSE: 0.110179, L1: 0.259766, Cosine Similarity: 0.9328, KL Loss: 18441.755371, Classification Loss: 0.000000
257
+ Iteration 512000, MSE: 0.110286, L1: 0.259923, Cosine Similarity: 0.9327, KL Loss: 18482.320557, Classification Loss: 0.000000
258
+ Iteration 514000, MSE: 0.110059, L1: 0.259654, Cosine Similarity: 0.9329, KL Loss: 18469.185059, Classification Loss: 0.000000
259
+ Iteration 516000, MSE: 0.109756, L1: 0.259279, Cosine Similarity: 0.9330, KL Loss: 18517.994873, Classification Loss: 0.000000
260
+ Iteration 518000, MSE: 0.110295, L1: 0.259993, Cosine Similarity: 0.9327, KL Loss: 18469.097900, Classification Loss: 0.000000
261
+ Iteration 520000, MSE: 0.109788, L1: 0.259291, Cosine Similarity: 0.9330, KL Loss: 18486.631592, Classification Loss: 0.000000
262
+ Iteration 522000, MSE: 0.109766, L1: 0.259291, Cosine Similarity: 0.9330, KL Loss: 18515.353271, Classification Loss: 0.000000
263
+ Iteration 524000, MSE: 0.109734, L1: 0.259239, Cosine Similarity: 0.9331, KL Loss: 18499.682861, Classification Loss: 0.000000
264
+ Iteration 526000, MSE: 0.109947, L1: 0.259512, Cosine Similarity: 0.9329, KL Loss: 18510.872559, Classification Loss: 0.000000
265
+ Iteration 528000, MSE: 0.109613, L1: 0.259124, Cosine Similarity: 0.9331, KL Loss: 18499.034180, Classification Loss: 0.000000
266
+ Iteration 530000, MSE: 0.109352, L1: 0.258768, Cosine Similarity: 0.9333, KL Loss: 18451.683350, Classification Loss: 0.000000
267
+ Iteration 532000, MSE: 0.109603, L1: 0.259092, Cosine Similarity: 0.9332, KL Loss: 18466.951416, Classification Loss: 0.000000
268
+ Iteration 534000, MSE: 0.109870, L1: 0.259487, Cosine Similarity: 0.9330, KL Loss: 18481.806152, Classification Loss: 0.000000
269
+ Iteration 536000, MSE: 0.109383, L1: 0.258829, Cosine Similarity: 0.9333, KL Loss: 18483.859619, Classification Loss: 0.000000
270
+ Iteration 538000, MSE: 0.109092, L1: 0.258407, Cosine Similarity: 0.9335, KL Loss: 18476.481445, Classification Loss: 0.000000
271
+ Iteration 540000, MSE: 0.109326, L1: 0.258723, Cosine Similarity: 0.9333, KL Loss: 18489.484375, Classification Loss: 0.000000
272
+ Iteration 542000, MSE: 0.108824, L1: 0.258082, Cosine Similarity: 0.9336, KL Loss: 18493.769531, Classification Loss: 0.000000
273
+ Iteration 544000, MSE: 0.109263, L1: 0.258648, Cosine Similarity: 0.9334, KL Loss: 18490.770264, Classification Loss: 0.000000
274
+ Iteration 546000, MSE: 0.108944, L1: 0.258224, Cosine Similarity: 0.9336, KL Loss: 18473.704102, Classification Loss: 0.000000
275
+ Iteration 548000, MSE: 0.109028, L1: 0.258370, Cosine Similarity: 0.9335, KL Loss: 18426.499268, Classification Loss: 0.000000
276
+ Iteration 550000, MSE: 0.108774, L1: 0.258070, Cosine Similarity: 0.9337, KL Loss: 18471.687988, Classification Loss: 0.000000
277
+ Iteration 552000, MSE: 0.109007, L1: 0.258365, Cosine Similarity: 0.9335, KL Loss: 18480.864746, Classification Loss: 0.000000
278
+ Iteration 554000, MSE: 0.108442, L1: 0.257643, Cosine Similarity: 0.9339, KL Loss: 18519.570312, Classification Loss: 0.000000
279
+ Iteration 556000, MSE: 0.108939, L1: 0.258265, Cosine Similarity: 0.9336, KL Loss: 18497.264404, Classification Loss: 0.000000
280
+ Iteration 558000, MSE: 0.108987, L1: 0.258381, Cosine Similarity: 0.9335, KL Loss: 18464.705566, Classification Loss: 0.000000
281
+ Iteration 560000, MSE: 0.108578, L1: 0.257855, Cosine Similarity: 0.9338, KL Loss: 18486.041016, Classification Loss: 0.000000
282
+ Iteration 562000, MSE: 0.108332, L1: 0.257556, Cosine Similarity: 0.9339, KL Loss: 18480.326904, Classification Loss: 0.000000
283
+ Iteration 564000, MSE: 0.108512, L1: 0.257761, Cosine Similarity: 0.9338, KL Loss: 18507.503174, Classification Loss: 0.000000
284
+ Iteration 566000, MSE: 0.108655, L1: 0.257977, Cosine Similarity: 0.9338, KL Loss: 18493.450684, Classification Loss: 0.000000
285
+ Iteration 568000, MSE: 0.108495, L1: 0.257771, Cosine Similarity: 0.9338, KL Loss: 18475.915771, Classification Loss: 0.000000
286
+ Iteration 570000, MSE: 0.108465, L1: 0.257700, Cosine Similarity: 0.9339, KL Loss: 18479.282959, Classification Loss: 0.000000
287
+ Iteration 572000, MSE: 0.108608, L1: 0.257918, Cosine Similarity: 0.9338, KL Loss: 18473.351318, Classification Loss: 0.000000
288
+ Iteration 574000, MSE: 0.108125, L1: 0.257271, Cosine Similarity: 0.9341, KL Loss: 18503.644775, Classification Loss: 0.000000
289
+ Iteration 576000, MSE: 0.108403, L1: 0.257622, Cosine Similarity: 0.9339, KL Loss: 18462.730957, Classification Loss: 0.000000
290
+ Iteration 578000, MSE: 0.107925, L1: 0.257033, Cosine Similarity: 0.9342, KL Loss: 18468.821045, Classification Loss: 0.000000
291
+ Iteration 580000, MSE: 0.108020, L1: 0.257160, Cosine Similarity: 0.9341, KL Loss: 18480.777588, Classification Loss: 0.000000
292
+ Iteration 582000, MSE: 0.108119, L1: 0.257332, Cosine Similarity: 0.9341, KL Loss: 18496.340088, Classification Loss: 0.000000
293
+ Iteration 584000, MSE: 0.108228, L1: 0.257444, Cosine Similarity: 0.9340, KL Loss: 18461.665039, Classification Loss: 0.000000
294
+ Iteration 586000, MSE: 0.107859, L1: 0.256988, Cosine Similarity: 0.9342, KL Loss: 18458.831299, Classification Loss: 0.000000
295
+ Iteration 588000, MSE: 0.107598, L1: 0.256628, Cosine Similarity: 0.9344, KL Loss: 18517.136475, Classification Loss: 0.000000
296
+ Iteration 590000, MSE: 0.108183, L1: 0.257363, Cosine Similarity: 0.9341, KL Loss: 18511.543457, Classification Loss: 0.000000
297
+ Iteration 592000, MSE: 0.107433, L1: 0.256411, Cosine Similarity: 0.9345, KL Loss: 18464.670410, Classification Loss: 0.000000
298
+ Iteration 594000, MSE: 0.107957, L1: 0.257148, Cosine Similarity: 0.9342, KL Loss: 18485.941895, Classification Loss: 0.000000
299
+ Iteration 596000, MSE: 0.107987, L1: 0.257155, Cosine Similarity: 0.9342, KL Loss: 18467.041016, Classification Loss: 0.000000
300
+ Iteration 598000, MSE: 0.107591, L1: 0.256641, Cosine Similarity: 0.9344, KL Loss: 18484.382812, Classification Loss: 0.000000
301
+ Iteration 600000, MSE: 0.107557, L1: 0.256579, Cosine Similarity: 0.9345, KL Loss: 18470.332520, Classification Loss: 0.000000
302
+ Iteration 602000, MSE: 0.107479, L1: 0.256497, Cosine Similarity: 0.9345, KL Loss: 18463.722412, Classification Loss: 0.000000
303
+ Iteration 604000, MSE: 0.107387, L1: 0.256398, Cosine Similarity: 0.9346, KL Loss: 18438.896973, Classification Loss: 0.000000
304
+ Iteration 606000, MSE: 0.107364, L1: 0.256376, Cosine Similarity: 0.9346, KL Loss: 18450.390869, Classification Loss: 0.000000
305
+ Iteration 608000, MSE: 0.107487, L1: 0.256497, Cosine Similarity: 0.9345, KL Loss: 18508.659424, Classification Loss: 0.000000
306
+ Iteration 610000, MSE: 0.107022, L1: 0.256003, Cosine Similarity: 0.9348, KL Loss: 18467.742676, Classification Loss: 0.000000
307
+ Iteration 612000, MSE: 0.107405, L1: 0.256426, Cosine Similarity: 0.9345, KL Loss: 18493.399170, Classification Loss: 0.000000
308
+ Iteration 614000, MSE: 0.106787, L1: 0.255663, Cosine Similarity: 0.9349, KL Loss: 18471.268066, Classification Loss: 0.000000
309
+ Iteration 616000, MSE: 0.107240, L1: 0.256172, Cosine Similarity: 0.9347, KL Loss: 18481.469482, Classification Loss: 0.000000
310
+ Iteration 618000, MSE: 0.106887, L1: 0.255745, Cosine Similarity: 0.9349, KL Loss: 18429.385742, Classification Loss: 0.000000
311
+ Iteration 620000, MSE: 0.107191, L1: 0.256163, Cosine Similarity: 0.9347, KL Loss: 18512.556885, Classification Loss: 0.000000
312
+ Iteration 622000, MSE: 0.107048, L1: 0.255926, Cosine Similarity: 0.9348, KL Loss: 18487.471191, Classification Loss: 0.000000
313
+ Iteration 624000, MSE: 0.106833, L1: 0.255731, Cosine Similarity: 0.9349, KL Loss: 18496.087646, Classification Loss: 0.000000
314
+ Iteration 626000, MSE: 0.107004, L1: 0.255920, Cosine Similarity: 0.9348, KL Loss: 18492.092773, Classification Loss: 0.000000
315
+ Iteration 628000, MSE: 0.106712, L1: 0.255573, Cosine Similarity: 0.9350, KL Loss: 18497.549805, Classification Loss: 0.000000
316
+ Iteration 630000, MSE: 0.106839, L1: 0.255725, Cosine Similarity: 0.9349, KL Loss: 18458.359131, Classification Loss: 0.000000
317
+ Iteration 632000, MSE: 0.106745, L1: 0.255634, Cosine Similarity: 0.9350, KL Loss: 18470.534424, Classification Loss: 0.000000
318
+ Iteration 634000, MSE: 0.106589, L1: 0.255436, Cosine Similarity: 0.9351, KL Loss: 18479.275146, Classification Loss: 0.000000
319
+ Iteration 636000, MSE: 0.106583, L1: 0.255404, Cosine Similarity: 0.9351, KL Loss: 18473.116455, Classification Loss: 0.000000
320
+ Iteration 638000, MSE: 0.106684, L1: 0.255512, Cosine Similarity: 0.9350, KL Loss: 18490.317627, Classification Loss: 0.000000
321
+ Iteration 640000, MSE: 0.106523, L1: 0.255392, Cosine Similarity: 0.9351, KL Loss: 18469.505859, Classification Loss: 0.000000
322
+ Iteration 642000, MSE: 0.106401, L1: 0.255159, Cosine Similarity: 0.9352, KL Loss: 18452.044922, Classification Loss: 0.000000
323
+ Iteration 644000, MSE: 0.106233, L1: 0.254976, Cosine Similarity: 0.9353, KL Loss: 18475.096680, Classification Loss: 0.000000
324
+ Iteration 646000, MSE: 0.106352, L1: 0.255183, Cosine Similarity: 0.9352, KL Loss: 18457.837158, Classification Loss: 0.000000
325
+ Iteration 648000, MSE: 0.106305, L1: 0.255045, Cosine Similarity: 0.9353, KL Loss: 18415.748291, Classification Loss: 0.000000
326
+ Iteration 650000, MSE: 0.106389, L1: 0.255214, Cosine Similarity: 0.9352, KL Loss: 18501.102295, Classification Loss: 0.000000
327
+ Iteration 652000, MSE: 0.105978, L1: 0.254713, Cosine Similarity: 0.9354, KL Loss: 18470.495361, Classification Loss: 0.000000
328
+ Iteration 654000, MSE: 0.105840, L1: 0.254501, Cosine Similarity: 0.9355, KL Loss: 18484.519531, Classification Loss: 0.000000
329
+ Iteration 656000, MSE: 0.105926, L1: 0.254629, Cosine Similarity: 0.9355, KL Loss: 18479.162842, Classification Loss: 0.000000
330
+ Iteration 658000, MSE: 0.105930, L1: 0.254614, Cosine Similarity: 0.9355, KL Loss: 18477.673584, Classification Loss: 0.000000
331
+ Iteration 660000, MSE: 0.106293, L1: 0.255078, Cosine Similarity: 0.9353, KL Loss: 18496.901855, Classification Loss: 0.000000
332
+ Iteration 662000, MSE: 0.106009, L1: 0.254711, Cosine Similarity: 0.9355, KL Loss: 18475.550293, Classification Loss: 0.000000
333
+ Iteration 664000, MSE: 0.105931, L1: 0.254624, Cosine Similarity: 0.9355, KL Loss: 18444.657715, Classification Loss: 0.000000
334
+ Iteration 666000, MSE: 0.105897, L1: 0.254590, Cosine Similarity: 0.9355, KL Loss: 18477.467041, Classification Loss: 0.000000
335
+ Iteration 668000, MSE: 0.106111, L1: 0.254876, Cosine Similarity: 0.9354, KL Loss: 18462.554443, Classification Loss: 0.000000
336
+ Iteration 670000, MSE: 0.106116, L1: 0.254882, Cosine Similarity: 0.9354, KL Loss: 18477.079346, Classification Loss: 0.000000
337
+ Iteration 672000, MSE: 0.105748, L1: 0.254374, Cosine Similarity: 0.9356, KL Loss: 18460.259033, Classification Loss: 0.000000
338
+ Iteration 674000, MSE: 0.105248, L1: 0.253739, Cosine Similarity: 0.9359, KL Loss: 18488.043457, Classification Loss: 0.000000
339
+ Iteration 676000, MSE: 0.105591, L1: 0.254209, Cosine Similarity: 0.9357, KL Loss: 18496.805908, Classification Loss: 0.000000
340
+ Iteration 678000, MSE: 0.105390, L1: 0.253890, Cosine Similarity: 0.9358, KL Loss: 18481.056641, Classification Loss: 0.000000
341
+ Iteration 680000, MSE: 0.105406, L1: 0.253973, Cosine Similarity: 0.9358, KL Loss: 18478.553955, Classification Loss: 0.000000
342
+ Iteration 682000, MSE: 0.105247, L1: 0.253719, Cosine Similarity: 0.9359, KL Loss: 18483.213867, Classification Loss: 0.000000
343
+ Iteration 684000, MSE: 0.105124, L1: 0.253621, Cosine Similarity: 0.9360, KL Loss: 18444.374023, Classification Loss: 0.000000
344
+ Iteration 686000, MSE: 0.105331, L1: 0.253893, Cosine Similarity: 0.9359, KL Loss: 18449.610352, Classification Loss: 0.000000
345
+ Iteration 688000, MSE: 0.105217, L1: 0.253777, Cosine Similarity: 0.9359, KL Loss: 18483.127686, Classification Loss: 0.000000
346
+ Iteration 690000, MSE: 0.105093, L1: 0.253563, Cosine Similarity: 0.9360, KL Loss: 18462.136963, Classification Loss: 0.000000
347
+ Iteration 692000, MSE: 0.105296, L1: 0.253841, Cosine Similarity: 0.9359, KL Loss: 18446.729004, Classification Loss: 0.000000
348
+ Iteration 694000, MSE: 0.105128, L1: 0.253636, Cosine Similarity: 0.9360, KL Loss: 18447.596680, Classification Loss: 0.000000
349
+ Iteration 696000, MSE: 0.105159, L1: 0.253671, Cosine Similarity: 0.9360, KL Loss: 18471.822998, Classification Loss: 0.000000
350
+ Iteration 698000, MSE: 0.105201, L1: 0.253713, Cosine Similarity: 0.9359, KL Loss: 18488.987061, Classification Loss: 0.000000
351
+ Iteration 700000, MSE: 0.104925, L1: 0.253357, Cosine Similarity: 0.9361, KL Loss: 18449.748047, Classification Loss: 0.000000
352
+ Iteration 702000, MSE: 0.104999, L1: 0.253496, Cosine Similarity: 0.9361, KL Loss: 18512.106934, Classification Loss: 0.000000
353
+ Iteration 704000, MSE: 0.104981, L1: 0.253437, Cosine Similarity: 0.9361, KL Loss: 18470.187500, Classification Loss: 0.000000
354
+ Iteration 706000, MSE: 0.104998, L1: 0.253496, Cosine Similarity: 0.9361, KL Loss: 18447.586670, Classification Loss: 0.000000
355
+ Iteration 708000, MSE: 0.104778, L1: 0.253189, Cosine Similarity: 0.9362, KL Loss: 18465.009277, Classification Loss: 0.000000
356
+ Iteration 710000, MSE: 0.104803, L1: 0.253280, Cosine Similarity: 0.9362, KL Loss: 18466.506592, Classification Loss: 0.000000
357
+ Iteration 712000, MSE: 0.104759, L1: 0.253181, Cosine Similarity: 0.9362, KL Loss: 18463.396973, Classification Loss: 0.000000
358
+ Iteration 714000, MSE: 0.104404, L1: 0.252734, Cosine Similarity: 0.9364, KL Loss: 18490.259521, Classification Loss: 0.000000
359
+ Iteration 716000, MSE: 0.104802, L1: 0.253234, Cosine Similarity: 0.9362, KL Loss: 18457.175781, Classification Loss: 0.000000
360
+ Iteration 718000, MSE: 0.104425, L1: 0.252739, Cosine Similarity: 0.9364, KL Loss: 18444.049805, Classification Loss: 0.000000
361
+ Iteration 720000, MSE: 0.104962, L1: 0.253461, Cosine Similarity: 0.9361, KL Loss: 18424.492432, Classification Loss: 0.000000
362
+ Iteration 722000, MSE: 0.104680, L1: 0.253101, Cosine Similarity: 0.9363, KL Loss: 18463.762939, Classification Loss: 0.000000
363
+ Iteration 724000, MSE: 0.104582, L1: 0.252954, Cosine Similarity: 0.9363, KL Loss: 18472.429443, Classification Loss: 0.000000
364
+ Iteration 726000, MSE: 0.103996, L1: 0.252207, Cosine Similarity: 0.9367, KL Loss: 18481.173340, Classification Loss: 0.000000
365
+ Iteration 728000, MSE: 0.104508, L1: 0.252948, Cosine Similarity: 0.9364, KL Loss: 18433.177734, Classification Loss: 0.000000
366
+ Iteration 730000, MSE: 0.103946, L1: 0.252182, Cosine Similarity: 0.9367, KL Loss: 18470.448242, Classification Loss: 0.000000
367
+ Iteration 732000, MSE: 0.104044, L1: 0.252300, Cosine Similarity: 0.9367, KL Loss: 18461.723389, Classification Loss: 0.000000
368
+ Iteration 734000, MSE: 0.104156, L1: 0.252441, Cosine Similarity: 0.9366, KL Loss: 18480.887695, Classification Loss: 0.000000
369
+ Iteration 736000, MSE: 0.104210, L1: 0.252486, Cosine Similarity: 0.9366, KL Loss: 18459.705322, Classification Loss: 0.000000
370
+ Iteration 738000, MSE: 0.103829, L1: 0.252012, Cosine Similarity: 0.9368, KL Loss: 18485.344971, Classification Loss: 0.000000
371
+ Iteration 740000, MSE: 0.104036, L1: 0.252283, Cosine Similarity: 0.9367, KL Loss: 18421.830566, Classification Loss: 0.000000
372
+ Iteration 742000, MSE: 0.104027, L1: 0.252213, Cosine Similarity: 0.9367, KL Loss: 18468.379883, Classification Loss: 0.000000
373
+ Iteration 744000, MSE: 0.103868, L1: 0.252058, Cosine Similarity: 0.9368, KL Loss: 18416.744141, Classification Loss: 0.000000
374
+ Iteration 746000, MSE: 0.103795, L1: 0.251996, Cosine Similarity: 0.9368, KL Loss: 18491.666748, Classification Loss: 0.000000
375
+ Iteration 748000, MSE: 0.103537, L1: 0.251651, Cosine Similarity: 0.9370, KL Loss: 18481.607910, Classification Loss: 0.000000
376
+ Iteration 750000, MSE: 0.103750, L1: 0.251908, Cosine Similarity: 0.9369, KL Loss: 18496.179688, Classification Loss: 0.000000
377
+ Iteration 752000, MSE: 0.103902, L1: 0.252153, Cosine Similarity: 0.9368, KL Loss: 18471.006592, Classification Loss: 0.000000
378
+ Iteration 754000, MSE: 0.103740, L1: 0.251919, Cosine Similarity: 0.9369, KL Loss: 18486.033447, Classification Loss: 0.000000
379
+ Iteration 756000, MSE: 0.104037, L1: 0.252285, Cosine Similarity: 0.9367, KL Loss: 18465.973877, Classification Loss: 0.000000
380
+ Iteration 758000, MSE: 0.103685, L1: 0.251841, Cosine Similarity: 0.9369, KL Loss: 18450.890137, Classification Loss: 0.000000
381
+ Iteration 760000, MSE: 0.103574, L1: 0.251712, Cosine Similarity: 0.9370, KL Loss: 18477.734131, Classification Loss: 0.000000
382
+ Iteration 762000, MSE: 0.103516, L1: 0.251629, Cosine Similarity: 0.9370, KL Loss: 18435.597900, Classification Loss: 0.000000
383
+ Iteration 764000, MSE: 0.103375, L1: 0.251474, Cosine Similarity: 0.9371, KL Loss: 18451.657715, Classification Loss: 0.000000
384
+ Iteration 766000, MSE: 0.103433, L1: 0.251494, Cosine Similarity: 0.9371, KL Loss: 18485.111816, Classification Loss: 0.000000
385
+ Iteration 768000, MSE: 0.103725, L1: 0.251887, Cosine Similarity: 0.9369, KL Loss: 18486.857422, Classification Loss: 0.000000
386
+ Iteration 770000, MSE: 0.103246, L1: 0.251283, Cosine Similarity: 0.9372, KL Loss: 18451.266846, Classification Loss: 0.000000
387
+ Iteration 772000, MSE: 0.103215, L1: 0.251289, Cosine Similarity: 0.9372, KL Loss: 18487.846436, Classification Loss: 0.000000
388
+ Iteration 774000, MSE: 0.103427, L1: 0.251556, Cosine Similarity: 0.9371, KL Loss: 18460.368408, Classification Loss: 0.000000
389
+ Iteration 776000, MSE: 0.103333, L1: 0.251430, Cosine Similarity: 0.9371, KL Loss: 18439.204346, Classification Loss: 0.000000
390
+ Iteration 778000, MSE: 0.103168, L1: 0.251185, Cosine Similarity: 0.9372, KL Loss: 18453.054443, Classification Loss: 0.000000
391
+ Iteration 780000, MSE: 0.103119, L1: 0.251143, Cosine Similarity: 0.9373, KL Loss: 18414.820557, Classification Loss: 0.000000
392
+ Iteration 782000, MSE: 0.103042, L1: 0.251033, Cosine Similarity: 0.9373, KL Loss: 18448.472412, Classification Loss: 0.000000
393
+ Iteration 784000, MSE: 0.103017, L1: 0.251012, Cosine Similarity: 0.9373, KL Loss: 18480.205566, Classification Loss: 0.000000
394
+ Iteration 786000, MSE: 0.103044, L1: 0.251022, Cosine Similarity: 0.9373, KL Loss: 18451.413330, Classification Loss: 0.000000
395
+ Iteration 788000, MSE: 0.103499, L1: 0.251655, Cosine Similarity: 0.9371, KL Loss: 18423.661621, Classification Loss: 0.000000
396
+ Iteration 790000, MSE: 0.102912, L1: 0.250875, Cosine Similarity: 0.9374, KL Loss: 18455.104248, Classification Loss: 0.000000
397
+ Iteration 792000, MSE: 0.102774, L1: 0.250725, Cosine Similarity: 0.9375, KL Loss: 18445.239502, Classification Loss: 0.000000
398
+ Iteration 794000, MSE: 0.102716, L1: 0.250651, Cosine Similarity: 0.9375, KL Loss: 18456.004395, Classification Loss: 0.000000
399
+ Iteration 796000, MSE: 0.102784, L1: 0.250713, Cosine Similarity: 0.9375, KL Loss: 18454.802246, Classification Loss: 0.000000
400
+ Iteration 798000, MSE: 0.102717, L1: 0.250669, Cosine Similarity: 0.9375, KL Loss: 18440.719727, Classification Loss: 0.000000
401
+ Iteration 800000, MSE: 0.102355, L1: 0.250203, Cosine Similarity: 0.9377, KL Loss: 18446.400635, Classification Loss: 0.000000
402
+ Iteration 802000, MSE: 0.102396, L1: 0.250233, Cosine Similarity: 0.9377, KL Loss: 18455.526123, Classification Loss: 0.000000
403
+ Iteration 804000, MSE: 0.102750, L1: 0.250681, Cosine Similarity: 0.9375, KL Loss: 18414.267334, Classification Loss: 0.000000
404
+ Iteration 806000, MSE: 0.102633, L1: 0.250540, Cosine Similarity: 0.9376, KL Loss: 18436.698242, Classification Loss: 0.000000
405
+ Iteration 808000, MSE: 0.102342, L1: 0.250163, Cosine Similarity: 0.9378, KL Loss: 18429.113525, Classification Loss: 0.000000
406
+ Iteration 810000, MSE: 0.102683, L1: 0.250607, Cosine Similarity: 0.9376, KL Loss: 18445.991699, Classification Loss: 0.000000
407
+ Iteration 812000, MSE: 0.102213, L1: 0.249997, Cosine Similarity: 0.9378, KL Loss: 18413.644287, Classification Loss: 0.000000
408
+ Iteration 814000, MSE: 0.102319, L1: 0.250171, Cosine Similarity: 0.9378, KL Loss: 18403.853516, Classification Loss: 0.000000
409
+ Iteration 816000, MSE: 0.102403, L1: 0.250238, Cosine Similarity: 0.9377, KL Loss: 18414.604004, Classification Loss: 0.000000
410
+ Iteration 818000, MSE: 0.102076, L1: 0.249838, Cosine Similarity: 0.9379, KL Loss: 18465.095947, Classification Loss: 0.000000
411
+ Iteration 820000, MSE: 0.102146, L1: 0.249904, Cosine Similarity: 0.9379, KL Loss: 18425.920166, Classification Loss: 0.000000
412
+ Iteration 822000, MSE: 0.102207, L1: 0.249979, Cosine Similarity: 0.9378, KL Loss: 18485.024902, Classification Loss: 0.000000
413
+ Iteration 824000, MSE: 0.101531, L1: 0.249132, Cosine Similarity: 0.9383, KL Loss: 18444.058594, Classification Loss: 0.000000
414
+ Iteration 826000, MSE: 0.101846, L1: 0.249556, Cosine Similarity: 0.9381, KL Loss: 18415.103271, Classification Loss: 0.000000
415
+ Iteration 828000, MSE: 0.101704, L1: 0.249326, Cosine Similarity: 0.9382, KL Loss: 18445.734619, Classification Loss: 0.000000
416
+ Iteration 830000, MSE: 0.102080, L1: 0.249799, Cosine Similarity: 0.9380, KL Loss: 18458.854004, Classification Loss: 0.000000
417
+ Iteration 832000, MSE: 0.101782, L1: 0.249461, Cosine Similarity: 0.9381, KL Loss: 18479.637695, Classification Loss: 0.000000
418
+ Iteration 834000, MSE: 0.101371, L1: 0.248918, Cosine Similarity: 0.9384, KL Loss: 18485.641602, Classification Loss: 0.000000
419
+ Iteration 836000, MSE: 0.101361, L1: 0.248912, Cosine Similarity: 0.9384, KL Loss: 18428.356201, Classification Loss: 0.000000
420
+ Iteration 838000, MSE: 0.101344, L1: 0.248913, Cosine Similarity: 0.9384, KL Loss: 18478.897705, Classification Loss: 0.000000
421
+ Iteration 840000, MSE: 0.101278, L1: 0.248820, Cosine Similarity: 0.9384, KL Loss: 18451.013184, Classification Loss: 0.000000
422
+ Iteration 842000, MSE: 0.101067, L1: 0.248569, Cosine Similarity: 0.9386, KL Loss: 18464.973877, Classification Loss: 0.000000
423
+ Iteration 844000, MSE: 0.100981, L1: 0.248447, Cosine Similarity: 0.9386, KL Loss: 18452.390625, Classification Loss: 0.000000
424
+ Iteration 846000, MSE: 0.100921, L1: 0.248374, Cosine Similarity: 0.9386, KL Loss: 18469.261230, Classification Loss: 0.000000
425
+ Iteration 848000, MSE: 0.100704, L1: 0.248086, Cosine Similarity: 0.9388, KL Loss: 18482.445068, Classification Loss: 0.000000
426
+ Iteration 850000, MSE: 0.101179, L1: 0.248657, Cosine Similarity: 0.9385, KL Loss: 18451.671631, Classification Loss: 0.000000
427
+ Iteration 852000, MSE: 0.100875, L1: 0.248317, Cosine Similarity: 0.9387, KL Loss: 18455.531738, Classification Loss: 0.000000
428
+ Iteration 854000, MSE: 0.100699, L1: 0.248080, Cosine Similarity: 0.9388, KL Loss: 18469.973633, Classification Loss: 0.000000
429
+ Iteration 856000, MSE: 0.100337, L1: 0.247628, Cosine Similarity: 0.9390, KL Loss: 18477.623779, Classification Loss: 0.000000
430
+ Iteration 858000, MSE: 0.100216, L1: 0.247417, Cosine Similarity: 0.9391, KL Loss: 18427.282959, Classification Loss: 0.000000
431
+ Iteration 860000, MSE: 0.100411, L1: 0.247710, Cosine Similarity: 0.9390, KL Loss: 18489.769531, Classification Loss: 0.000000
432
+ Iteration 862000, MSE: 0.100487, L1: 0.247837, Cosine Similarity: 0.9389, KL Loss: 18454.492920, Classification Loss: 0.000000
433
+ Iteration 864000, MSE: 0.100079, L1: 0.247252, Cosine Similarity: 0.9392, KL Loss: 18497.179199, Classification Loss: 0.000000
434
+ Iteration 866000, MSE: 0.100019, L1: 0.247210, Cosine Similarity: 0.9392, KL Loss: 18437.434814, Classification Loss: 0.000000
435
+ Iteration 868000, MSE: 0.100118, L1: 0.247329, Cosine Similarity: 0.9392, KL Loss: 18481.109619, Classification Loss: 0.000000
436
+ Iteration 870000, MSE: 0.099835, L1: 0.246959, Cosine Similarity: 0.9393, KL Loss: 18459.681641, Classification Loss: 0.000000
437
+ Iteration 872000, MSE: 0.099799, L1: 0.246937, Cosine Similarity: 0.9394, KL Loss: 18489.503662, Classification Loss: 0.000000
438
+ Iteration 874000, MSE: 0.099639, L1: 0.246747, Cosine Similarity: 0.9394, KL Loss: 18474.109863, Classification Loss: 0.000000
439
+ Iteration 876000, MSE: 0.099432, L1: 0.246460, Cosine Similarity: 0.9396, KL Loss: 18485.809570, Classification Loss: 0.000000
440
+ Iteration 878000, MSE: 0.099281, L1: 0.246214, Cosine Similarity: 0.9397, KL Loss: 18463.343994, Classification Loss: 0.000000
441
+ Iteration 880000, MSE: 0.099254, L1: 0.246218, Cosine Similarity: 0.9397, KL Loss: 18485.435791, Classification Loss: 0.000000
442
+ Iteration 882000, MSE: 0.099299, L1: 0.246278, Cosine Similarity: 0.9397, KL Loss: 18494.688965, Classification Loss: 0.000000
443
+ Iteration 884000, MSE: 0.098971, L1: 0.245829, Cosine Similarity: 0.9399, KL Loss: 18495.642334, Classification Loss: 0.000000
444
+ Iteration 886000, MSE: 0.099153, L1: 0.246078, Cosine Similarity: 0.9398, KL Loss: 18513.989746, Classification Loss: 0.000000
445
+ Iteration 888000, MSE: 0.099052, L1: 0.245946, Cosine Similarity: 0.9398, KL Loss: 18489.333984, Classification Loss: 0.000000
446
+ Iteration 890000, MSE: 0.098705, L1: 0.245498, Cosine Similarity: 0.9400, KL Loss: 18487.294678, Classification Loss: 0.000000
447
+ Iteration 892000, MSE: 0.098789, L1: 0.245665, Cosine Similarity: 0.9400, KL Loss: 18514.280029, Classification Loss: 0.000000
448
+ Iteration 894000, MSE: 0.098593, L1: 0.245353, Cosine Similarity: 0.9401, KL Loss: 18529.573486, Classification Loss: 0.000000
449
+ Iteration 896000, MSE: 0.098469, L1: 0.245220, Cosine Similarity: 0.9402, KL Loss: 18500.986572, Classification Loss: 0.000000
450
+ Iteration 898000, MSE: 0.098349, L1: 0.245052, Cosine Similarity: 0.9402, KL Loss: 18511.311279, Classification Loss: 0.000000
451
+ Iteration 900000, MSE: 0.098402, L1: 0.245110, Cosine Similarity: 0.9402, KL Loss: 18519.218018, Classification Loss: 0.000000
452
+ Iteration 902000, MSE: 0.098072, L1: 0.244678, Cosine Similarity: 0.9404, KL Loss: 18514.489014, Classification Loss: 0.000000
453
+ Iteration 904000, MSE: 0.097970, L1: 0.244565, Cosine Similarity: 0.9405, KL Loss: 18505.617432, Classification Loss: 0.000000
454
+ Iteration 906000, MSE: 0.097775, L1: 0.244299, Cosine Similarity: 0.9406, KL Loss: 18522.286865, Classification Loss: 0.000000
455
+ Iteration 908000, MSE: 0.097903, L1: 0.244472, Cosine Similarity: 0.9405, KL Loss: 18500.706299, Classification Loss: 0.000000
456
+ Iteration 910000, MSE: 0.097673, L1: 0.244174, Cosine Similarity: 0.9407, KL Loss: 18516.614258, Classification Loss: 0.000000
457
+ Iteration 912000, MSE: 0.097555, L1: 0.244010, Cosine Similarity: 0.9407, KL Loss: 18535.685059, Classification Loss: 0.000000
458
+ Iteration 914000, MSE: 0.097467, L1: 0.243871, Cosine Similarity: 0.9408, KL Loss: 18493.055176, Classification Loss: 0.000000
459
+ Iteration 916000, MSE: 0.097429, L1: 0.243837, Cosine Similarity: 0.9408, KL Loss: 18512.528564, Classification Loss: 0.000000
460
+ Iteration 918000, MSE: 0.097337, L1: 0.243740, Cosine Similarity: 0.9409, KL Loss: 18539.639160, Classification Loss: 0.000000
461
+ Iteration 920000, MSE: 0.097259, L1: 0.243592, Cosine Similarity: 0.9409, KL Loss: 18509.941162, Classification Loss: 0.000000
462
+ Iteration 922000, MSE: 0.097139, L1: 0.243459, Cosine Similarity: 0.9410, KL Loss: 18545.998047, Classification Loss: 0.000000
463
+ Iteration 924000, MSE: 0.097036, L1: 0.243356, Cosine Similarity: 0.9411, KL Loss: 18544.685791, Classification Loss: 0.000000
464
+ Iteration 926000, MSE: 0.096875, L1: 0.243127, Cosine Similarity: 0.9412, KL Loss: 18543.946045, Classification Loss: 0.000000
465
+ Iteration 928000, MSE: 0.096872, L1: 0.243099, Cosine Similarity: 0.9412, KL Loss: 18553.716797, Classification Loss: 0.000000
466
+ Iteration 930000, MSE: 0.096758, L1: 0.242948, Cosine Similarity: 0.9412, KL Loss: 18551.958252, Classification Loss: 0.000000
467
+ Iteration 932000, MSE: 0.096725, L1: 0.242918, Cosine Similarity: 0.9413, KL Loss: 18569.738281, Classification Loss: 0.000000
468
+ Iteration 934000, MSE: 0.096630, L1: 0.242780, Cosine Similarity: 0.9413, KL Loss: 18560.712646, Classification Loss: 0.000000
469
+ Iteration 936000, MSE: 0.096602, L1: 0.242736, Cosine Similarity: 0.9413, KL Loss: 18563.565674, Classification Loss: 0.000000
470
+ Iteration 938000, MSE: 0.096405, L1: 0.242506, Cosine Similarity: 0.9414, KL Loss: 18569.750000, Classification Loss: 0.000000
471
+ Iteration 940000, MSE: 0.096426, L1: 0.242526, Cosine Similarity: 0.9414, KL Loss: 18573.546875, Classification Loss: 0.000000
472
+ Iteration 942000, MSE: 0.096168, L1: 0.242188, Cosine Similarity: 0.9416, KL Loss: 18601.734375, Classification Loss: 0.000000
473
+ Iteration 944000, MSE: 0.096209, L1: 0.242223, Cosine Similarity: 0.9416, KL Loss: 18582.366211, Classification Loss: 0.000000
474
+ Iteration 946000, MSE: 0.096122, L1: 0.242116, Cosine Similarity: 0.9416, KL Loss: 18588.955566, Classification Loss: 0.000000
475
+ Iteration 948000, MSE: 0.095955, L1: 0.241913, Cosine Similarity: 0.9417, KL Loss: 18580.580566, Classification Loss: 0.000000
476
+ Iteration 950000, MSE: 0.095827, L1: 0.241738, Cosine Similarity: 0.9418, KL Loss: 18574.227539, Classification Loss: 0.000000
477
+ Iteration 952000, MSE: 0.095878, L1: 0.241817, Cosine Similarity: 0.9418, KL Loss: 18580.423828, Classification Loss: 0.000000
478
+ Iteration 954000, MSE: 0.095827, L1: 0.241722, Cosine Similarity: 0.9418, KL Loss: 18596.068604, Classification Loss: 0.000000
479
+ Iteration 956000, MSE: 0.095729, L1: 0.241596, Cosine Similarity: 0.9419, KL Loss: 18593.202393, Classification Loss: 0.000000
480
+ Iteration 958000, MSE: 0.095689, L1: 0.241552, Cosine Similarity: 0.9419, KL Loss: 18600.536377, Classification Loss: 0.000000
481
+ Iteration 960000, MSE: 0.095674, L1: 0.241542, Cosine Similarity: 0.9419, KL Loss: 18597.517578, Classification Loss: 0.000000
482
+ Iteration 962000, MSE: 0.095555, L1: 0.241372, Cosine Similarity: 0.9420, KL Loss: 18616.042480, Classification Loss: 0.000000
483
+ Iteration 964000, MSE: 0.095557, L1: 0.241373, Cosine Similarity: 0.9420, KL Loss: 18610.511475, Classification Loss: 0.000000
484
+ Iteration 966000, MSE: 0.095453, L1: 0.241233, Cosine Similarity: 0.9420, KL Loss: 18593.153809, Classification Loss: 0.000000
485
+ Iteration 968000, MSE: 0.095449, L1: 0.241219, Cosine Similarity: 0.9420, KL Loss: 18602.462891, Classification Loss: 0.000000
486
+ Iteration 970000, MSE: 0.095400, L1: 0.241161, Cosine Similarity: 0.9421, KL Loss: 18601.651367, Classification Loss: 0.000000
487
+ Iteration 972000, MSE: 0.095412, L1: 0.241165, Cosine Similarity: 0.9421, KL Loss: 18600.261230, Classification Loss: 0.000000
488
+ Iteration 974000, MSE: 0.095270, L1: 0.241017, Cosine Similarity: 0.9421, KL Loss: 18601.692627, Classification Loss: 0.000000
489
+ Iteration 976000, MSE: 0.095300, L1: 0.241026, Cosine Similarity: 0.9421, KL Loss: 18621.441895, Classification Loss: 0.000000
490
+ Iteration 978000, MSE: 0.095217, L1: 0.240919, Cosine Similarity: 0.9422, KL Loss: 18611.337158, Classification Loss: 0.000000
491
+ Iteration 980000, MSE: 0.095221, L1: 0.240931, Cosine Similarity: 0.9422, KL Loss: 18611.842041, Classification Loss: 0.000000
492
+ Iteration 982000, MSE: 0.095172, L1: 0.240863, Cosine Similarity: 0.9422, KL Loss: 18616.036133, Classification Loss: 0.000000
493
+ Iteration 984000, MSE: 0.095243, L1: 0.240956, Cosine Similarity: 0.9422, KL Loss: 18625.759766, Classification Loss: 0.000000
494
+ Iteration 986000, MSE: 0.095157, L1: 0.240844, Cosine Similarity: 0.9422, KL Loss: 18619.836426, Classification Loss: 0.000000
495
+ Iteration 988000, MSE: 0.095103, L1: 0.240777, Cosine Similarity: 0.9423, KL Loss: 18629.792969, Classification Loss: 0.000000
496
+ Iteration 990000, MSE: 0.095068, L1: 0.240721, Cosine Similarity: 0.9423, KL Loss: 18626.257324, Classification Loss: 0.000000
497
+ Iteration 992000, MSE: 0.095040, L1: 0.240681, Cosine Similarity: 0.9423, KL Loss: 18613.380859, Classification Loss: 0.000000
498
+ Iteration 994000, MSE: 0.095049, L1: 0.240683, Cosine Similarity: 0.9423, KL Loss: 18612.806396, Classification Loss: 0.000000
499
+ Iteration 996000, MSE: 0.095033, L1: 0.240648, Cosine Similarity: 0.9423, KL Loss: 18621.040771, Classification Loss: 0.000000
500
+ Iteration 998000, MSE: 0.095005, L1: 0.240647, Cosine Similarity: 0.9423, KL Loss: 18615.116455, Classification Loss: 0.000000
501
+ Iteration 1000000, MSE: 0.094997, L1: 0.240629, Cosine Similarity: 0.9423, KL Loss: 18640.995361, Classification Loss: 0.000000
semantic_vae/dinov2_vitb14_reg/transformer_ch16/semantic_vae_training_log_20251208_165804.txt ADDED
The diff for this file is too large to render. See raw diff