
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f1a389422e0>

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: 1.8951 top1= 50.1562
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8154 top1= 75.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4208 top1= 87.6102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4504 top1= 86.8690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4624 top1= 85.9475

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5120 top1= 83.7500
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.4567 top1= 84.8438
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3720 top1= 87.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2801 top1= 92.0473


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2872 top1= 91.4062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3003 top1= 91.3361

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2615 top1= 92.1875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2433 top1= 92.0312
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2381 top1= 92.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2357 top1= 93.2292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2379 top1= 92.9587


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2520 top1= 92.3578

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1782 top1= 94.5312
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1618 top1= 94.8438
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1614 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2063 top1= 93.8502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2163 top1= 93.3894


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2101 top1= 93.7099

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1253 top1= 96.5625
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1055 top1= 97.5000
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1163 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1872 top1= 94.3510


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2096 top1= 93.7099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1847 top1= 94.3610

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0919 top1= 97.3438
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0754 top1= 98.4375
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0750 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1795 top1= 94.6915


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1983 top1= 94.1907


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1842 top1= 94.4211

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0653 top1= 98.4375
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0513 top1= 98.9062
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0664 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1778 top1= 95.0020


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1938 top1= 94.5813


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1764 top1= 94.9619

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0406 top1= 99.5312
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0305 top1= 99.8438
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0443 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1801 top1= 95.0220


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2053 top1= 94.4611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1965 top1= 94.4411

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0361 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0228 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0312 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1790 top1= 95.0721


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2171 top1= 94.0304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1935 top1= 94.6514

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0274 top1= 99.3750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0238 top1= 99.3750
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0202 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1828 top1= 95.1222


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2400 top1= 93.7700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1855 top1= 95.1823

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0214 top1= 99.6875
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0237 top1= 99.6875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0290 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1798 top1= 95.2524


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2048 top1= 94.5212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1820 top1= 95.2825

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0335 top1= 99.2188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0219 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0238 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1816 top1= 95.3726


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1870 top1= 95.0921


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2094 top1= 94.5212

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0284 top1= 99.0625
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0170 top1= 99.5312
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0067 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1776 top1= 95.4227


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1776 top1= 95.4627


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1854 top1= 95.2624

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0059 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0082 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1807 top1= 95.5128


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1858 top1= 95.4227


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1944 top1= 94.9619

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0050 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0048 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1775 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1877 top1= 95.5929


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1757 top1= 95.5429

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1826 top1= 95.6030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1915 top1= 95.5929


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1813 top1= 95.4627

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1867 top1= 95.5529


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1951 top1= 95.5128


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1834 top1= 95.5128

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1900 top1= 95.5128


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1983 top1= 95.4828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1874 top1= 95.4327

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2012 top1= 95.5028


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1899 top1= 95.4427

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1960 top1= 95.5929


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2038 top1= 95.5028


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1926 top1= 95.4427

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1982 top1= 95.6230


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2061 top1= 95.5028


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1948 top1= 95.4026

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2002 top1= 95.6130


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2083 top1= 95.5128


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1968 top1= 95.4427

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2022 top1= 95.6030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2103 top1= 95.4828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1988 top1= 95.4327

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: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2041 top1= 95.6030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2123 top1= 95.4828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2006 top1= 95.4427

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2058 top1= 95.5929


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2140 top1= 95.4928


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2022 top1= 95.4427

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

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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2158 top1= 95.5028


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2038 top1= 95.4527

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2089 top1= 95.5829


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2174 top1= 95.4928


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2053 top1= 95.4427

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2103 top1= 95.5729


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2188 top1= 95.4928


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2067 top1= 95.4527

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2117 top1= 95.5729


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2202 top1= 95.4828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2080 top1= 95.4427

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2130 top1= 95.5729


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2216 top1= 95.4828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2092 top1= 95.4427

