
=== Start adding workers ===
=> Add worker SGDMWorker(index=0, momentum=0.9)
=> Add worker SGDMWorker(index=1, momentum=0.9)
=> Add worker SGDMWorker(index=2, momentum=0.9)
=> Add worker SGDMWorker(index=3, momentum=0.9)
=> Add worker SGDMWorker(index=4, momentum=0.9)
=> Add worker SGDMWorker(index=5, momentum=0.9)
=> Add worker SGDMWorker(index=6, momentum=0.9)
=> Add worker SGDMWorker(index=7, momentum=0.9)
=> Add worker SGDMWorker(index=8, momentum=0.9)
=> Add worker SGDMWorker(index=9, momentum=0.9)
=> Add worker SGDMWorker(index=10, momentum=0.9)
=> Add worker SGDMWorker(index=11, momentum=0.9)
=> Add worker SGDMWorker(index=12, momentum=0.9)
=> Add worker SGDMWorker(index=13, momentum=0.9)
=> Add worker SGDMWorker(index=14, momentum=0.9)
=> Add worker SGDMWorker(index=15, momentum=0.9)
=> Add worker SGDMWorker(index=16, momentum=0.9)
=> Add worker SGDMWorker(index=17, momentum=0.9)
=> Add worker SGDMWorker(index=18, momentum=0.9)
=> Add worker SGDMWorker(index=19, momentum=0.9)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7fb1532f8730>

Train epoch 1
[E 1B0  |    640/60000 (  1%) ] Loss: 2.3080 top1=  8.4375

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')
Worker 2 has targets: tensor([3, 0, 3, 2, 7], device='cuda:0')
Worker 3 has targets: tensor([1, 4, 8, 2, 8], device='cuda:0')
Worker 4 has targets: tensor([9, 5, 0, 1, 3], device='cuda:0')
Worker 5 has targets: tensor([5, 6, 2, 4, 3], device='cuda:0')
Worker 6 has targets: tensor([2, 5, 0, 9, 9], device='cuda:0')
Worker 7 has targets: tensor([2, 2, 1, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([3, 8, 7, 0, 3], device='cuda:0')
Worker 9 has targets: tensor([1, 7, 1, 7, 2], device='cuda:0')
Worker 10 has targets: tensor([8, 4, 4, 3, 9], device='cuda:0')
Worker 11 has targets: tensor([3, 4, 7, 7, 9], device='cuda:0')
Worker 12 has targets: tensor([7, 4, 3, 9, 4], device='cuda:0')
Worker 13 has targets: tensor([4, 5, 0, 7, 1], device='cuda:0')
Worker 14 has targets: tensor([4, 2, 3, 5, 5], device='cuda:0')
Worker 15 has targets: tensor([4, 7, 5, 4, 7], device='cuda:0')
Worker 16 has targets: tensor([1, 1, 5, 7, 9], device='cuda:0')
Worker 17 has targets: tensor([8, 7, 2, 2, 0], device='cuda:0')
Worker 18 has targets: tensor([7, 8, 0, 0, 6], device='cuda:0')
Worker 19 has targets: tensor([9, 9, 5, 2, 8], device='cuda:0')


[E 1B10 |   7040/60000 ( 12%) ] Loss: 1.9002 top1= 49.5312
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.8210 top1= 74.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4230 top1= 87.5501


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4538 top1= 86.6386


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4627 top1= 85.7672

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.5240 top1= 83.1250
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.4653 top1= 83.7500
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.3812 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2839 top1= 91.7768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2890 top1= 91.3161


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3068 top1= 91.0657

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.2652 top1= 91.4062
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2516 top1= 92.1875
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.2396 top1= 92.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2406 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2451 top1= 92.6182


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2505 top1= 92.4079

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1785 top1= 95.0000
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1561 top1= 95.4688
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1619 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2078 top1= 93.6899


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2222 top1= 93.1691


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2044 top1= 93.9303

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1265 top1= 97.0312
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1128 top1= 97.0312
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.1076 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1934 top1= 94.1607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2097 top1= 93.8201


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1892 top1= 94.3510

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0920 top1= 97.6562
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0758 top1= 98.2812
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0861 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1890 top1= 94.4211


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2009 top1= 94.2107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1875 top1= 94.5112

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0630 top1= 98.7500
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0490 top1= 99.0625
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0705 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1867 top1= 94.7015


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2057 top1= 94.1206


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2005 top1= 94.2107

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0529 top1= 98.9062
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0384 top1= 99.0625
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0514 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1856 top1= 94.9119


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2312 top1= 93.6198


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1947 top1= 94.6114

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0489 top1= 98.5938
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0324 top1= 99.2188
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0290 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1877 top1= 94.9319


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2279 top1= 93.8802


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1884 top1= 94.7917

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0360 top1= 99.2188
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0375 top1= 99.2188
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0323 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1841 top1= 95.0921


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1872 top1= 94.8317


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1911 top1= 95.0020

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0239 top1= 99.5312
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0168 top1= 99.8438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0283 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1917 top1= 95.0120


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1859 top1= 95.2424


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2095 top1= 94.6214

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0209 top1= 99.3750
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0169 top1= 99.6875
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0166 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1908 top1= 95.0721


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1965 top1= 95.2023


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1939 top1= 95.0020

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0154 top1= 99.3750
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0093 top1=100.0000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0072 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1863 top1= 95.2925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1977 top1= 95.3025


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1806 top1= 95.3926

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0055 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0061 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1902 top1= 95.2424


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2026 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1811 top1= 95.3726

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0044 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1978 top1= 95.2724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2075 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1908 top1= 95.3425

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2006 top1= 95.2424


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2102 top1= 95.2724


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1917 top1= 95.2524

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0024 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2049 top1= 95.1923


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2136 top1= 95.3025


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1944 top1= 95.3626

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2082 top1= 95.2224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2172 top1= 95.3225


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1974 top1= 95.3526

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2114 top1= 95.2023


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2206 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2004 top1= 95.3025

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2139 top1= 95.2023


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2236 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2026 top1= 95.3626

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0013 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2164 top1= 95.1923


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2262 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2050 top1= 95.3325

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2188 top1= 95.1923


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2287 top1= 95.3225


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2071 top1= 95.3526

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2209 top1= 95.1923


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2310 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2091 top1= 95.3526

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2230 top1= 95.1823


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2333 top1= 95.2925


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2109 top1= 95.3425

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2249 top1= 95.1823


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2354 top1= 95.3025


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2127 top1= 95.3526

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0009 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2267 top1= 95.1923


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2373 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2143 top1= 95.3526

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0008 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2285 top1= 95.1823


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2392 top1= 95.2925


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2160 top1= 95.3526

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0008 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2300 top1= 95.1923


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2409 top1= 95.2925


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2174 top1= 95.3526

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2317 top1= 95.1923


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2426 top1= 95.2925


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2189 top1= 95.3526

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2332 top1= 95.1923


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2443 top1= 95.3025


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2203 top1= 95.3325

