
=== 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)
=> Add worker ByzantineWorker(index=20)
=> Add worker ByzantineWorker(index=21)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7fcfebfef2e0>

Train epoch 1
[E 1B0  |    704/60000 (  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')
Worker 20 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 21 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 1.8908 top1= 50.0000
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8097 top1= 75.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4187 top1= 87.6703


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4509 top1= 86.8089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4647 top1= 85.9375

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5114 top1= 82.9688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.4587 top1= 84.3750
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3743 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2750 top1= 92.1374


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2848 top1= 91.5966


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2941 top1= 91.5264

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2614 top1= 91.2500
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2412 top1= 92.5000
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2345 top1= 92.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2309 top1= 93.2592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2340 top1= 93.0889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2493 top1= 92.5080

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1668 top1= 94.8438
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1520 top1= 95.7812
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1523 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2005 top1= 94.0304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2165 top1= 93.2792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2002 top1= 93.9704

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1158 top1= 96.5625
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1013 top1= 97.3438
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1054 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1837 top1= 94.5312


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2042 top1= 93.9103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1796 top1= 94.3710

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0793 top1= 98.1250
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0680 top1= 98.4375
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0665 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1762 top1= 94.8518


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1936 top1= 94.5212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1804 top1= 94.6514

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0552 top1= 98.5938
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0455 top1= 99.0625
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0612 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1772 top1= 95.1222


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1965 top1= 94.6915


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1764 top1= 94.9820

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0357 top1= 99.5312
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0288 top1= 99.3750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0447 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1777 top1= 95.1122


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2172 top1= 94.3510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1862 top1= 94.8117

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0302 top1= 99.3750
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0166 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0244 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1800 top1= 95.1022


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2301 top1= 93.9103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2083 top1= 94.4411

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0245 top1= 99.5312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0271 top1= 99.2188
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0207 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1841 top1= 95.0521


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2513 top1= 93.4896


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1951 top1= 94.9820

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0204 top1= 99.8438
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0269 top1= 99.2188
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0188 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1766 top1= 95.3926


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1936 top1= 94.9519


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1829 top1= 95.2424

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0124 top1= 99.6875
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0163 top1=100.0000
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0273 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1881 top1= 95.2123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1916 top1= 95.0321


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2014 top1= 94.8718

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0223 top1= 99.2188
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0160 top1= 99.3750
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0116 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1860 top1= 95.3225


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1862 top1= 95.4527


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2036 top1= 94.8818

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0147 top1= 99.5312
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0093 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1826 top1= 95.5128


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1873 top1= 95.6230


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1920 top1= 95.2023

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0051 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0064 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0040 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1787 top1= 95.7332


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1904 top1= 95.6230


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1751 top1= 95.6330

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1812 top1= 95.7532


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1932 top1= 95.5729


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1762 top1= 95.6530

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1847 top1= 95.7532


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1963 top1= 95.6030


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1777 top1= 95.7432

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1881 top1= 95.6731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1986 top1= 95.5829


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1814 top1= 95.6731

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1905 top1= 95.7332


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2005 top1= 95.5829


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1848 top1= 95.6731

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1924 top1= 95.7131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2022 top1= 95.5829


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1865 top1= 95.6831

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1940 top1= 95.7031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2037 top1= 95.5629


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1882 top1= 95.6731

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1953 top1= 95.6931


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2050 top1= 95.5729


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1896 top1= 95.6731

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1966 top1= 95.6731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2063 top1= 95.5929


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1908 top1= 95.6731

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1977 top1= 95.6831


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2074 top1= 95.5929


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1920 top1= 95.6831

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1987 top1= 95.6931


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2084 top1= 95.6030


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1931 top1= 95.7031

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1996 top1= 95.7031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2092 top1= 95.5929


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1941 top1= 95.6931

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2005 top1= 95.7031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2100 top1= 95.6330


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1950 top1= 95.7131

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2012 top1= 95.7131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2107 top1= 95.6130


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1958 top1= 95.7232

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2019 top1= 95.7332


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2114 top1= 95.6130


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1966 top1= 95.7432

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2026 top1= 95.7432


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2119 top1= 95.6430


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1973 top1= 95.7532

