
=== 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.Dumbbell object at 0x7f857aaf8490>

Train epoch 1
[E 1B0  |    704/60000 (  1%) ] Loss: 2.3066 top1=  9.2188

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 2, 2, 4, 3], device='cuda:0')
Worker 1 has targets: tensor([1, 0, 0, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([4, 1, 0, 1, 0], device='cuda:0')
Worker 3 has targets: tensor([0, 1, 4, 1, 3], device='cuda:0')
Worker 4 has targets: tensor([0, 4, 1, 2, 4], device='cuda:0')
Worker 5 has targets: tensor([2, 2, 4, 4, 4], device='cuda:0')
Worker 6 has targets: tensor([1, 1, 4, 4, 3], device='cuda:0')
Worker 7 has targets: tensor([4, 4, 1, 3, 0], device='cuda:0')
Worker 8 has targets: tensor([1, 3, 1, 0, 4], device='cuda:0')
Worker 9 has targets: tensor([1, 3, 3, 3, 1], device='cuda:0')
Worker 10 has targets: tensor([8, 9, 7, 7, 9], device='cuda:0')
Worker 11 has targets: tensor([8, 9, 6, 6, 7], device='cuda:0')
Worker 12 has targets: tensor([8, 6, 5, 7, 8], device='cuda:0')
Worker 13 has targets: tensor([7, 6, 9, 6, 5], device='cuda:0')
Worker 14 has targets: tensor([8, 5, 8, 6, 7], device='cuda:0')
Worker 15 has targets: tensor([9, 5, 6, 8, 6], device='cuda:0')
Worker 16 has targets: tensor([7, 7, 8, 5, 8], device='cuda:0')
Worker 17 has targets: tensor([9, 7, 5, 6, 6], device='cuda:0')
Worker 18 has targets: tensor([7, 7, 7, 6, 6], device='cuda:0')
Worker 19 has targets: tensor([5, 7, 9, 9, 7], device='cuda:0')
Worker 20 has targets: tensor([3, 2, 2, 4, 3], device='cuda:0')
Worker 21 has targets: tensor([8, 9, 7, 7, 9], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 1.2354 top1= 56.8750
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4404 top1= 85.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8861 top1= 79.2368


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8649 top1= 49.0184


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8290 top1= 43.4095

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.3111 top1= 89.8438
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2503 top1= 94.0625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2623 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9437 top1= 84.2248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3789 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4863 top1= 45.0020

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2532 top1= 92.5000
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2074 top1= 94.5312
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2252 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8852 top1= 84.1647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1474 top1= 49.6294


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4683 top1= 45.3626

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2315 top1= 92.8125
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.2062 top1= 93.9062
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2253 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8739 top1= 83.2131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0302 top1= 49.7396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2844 top1= 45.5329

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2227 top1= 93.5938
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1997 top1= 94.6875
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2170 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8792 top1= 80.8794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9630 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3117 top1= 45.5128

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.2144 top1= 93.4375
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1897 top1= 94.5312
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.2111 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8763 top1= 80.2083


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9106 top1= 49.7997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2998 top1= 45.5829

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.2051 top1= 94.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1846 top1= 94.5312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.2046 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8697 top1= 80.1182


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8715 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2504 top1= 45.7933

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1957 top1= 94.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1807 top1= 94.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1997 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8687 top1= 79.7877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8530 top1= 49.7296


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1940 top1= 45.8934

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1914 top1= 94.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1819 top1= 93.9062
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1945 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8702 top1= 79.5773


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8030 top1= 49.6995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1717 top1= 45.9335

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1889 top1= 94.3750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1775 top1= 94.0625
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1914 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8725 top1= 80.1282


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7900 top1= 49.6394


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0990 top1= 45.9535

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1922 top1= 94.0625
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1750 top1= 93.7500
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1842 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8753 top1= 80.2284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7758 top1= 49.5793


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0795 top1= 46.0036

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1941 top1= 93.5938
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1715 top1= 94.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1866 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8750 top1= 80.4287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7680 top1= 49.5593


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0295 top1= 45.9335

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1916 top1= 93.5938
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1684 top1= 94.8438
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1851 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8788 top1= 79.8478


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7439 top1= 49.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0494 top1= 45.8233

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1938 top1= 93.5938
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1665 top1= 95.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1864 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8847 top1= 79.0865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7168 top1= 49.8397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0241 top1= 45.7332

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1883 top1= 93.9062
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1652 top1= 94.6875
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1833 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8890 top1= 78.3954


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7051 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0261 top1= 45.6631

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1850 top1= 94.5312
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1588 top1= 95.1562
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1819 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8934 top1= 77.9547


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7009 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0081 top1= 45.7432

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1803 top1= 94.3750
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1560 top1= 95.6250
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1748 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8942 top1= 78.2051


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6901 top1= 49.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0125 top1= 45.7532

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1777 top1= 95.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1547 top1= 95.6250
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1755 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8976 top1= 78.1150


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6786 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9904 top1= 45.9535

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1759 top1= 94.8438
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1513 top1= 95.7812
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1798 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8927 top1= 78.9764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6726 top1= 50.0300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9665 top1= 46.0837

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1717 top1= 94.6875
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1570 top1= 95.7812
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1861 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8934 top1= 78.9363


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6680 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9513 top1= 46.0136

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1697 top1= 95.1562
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1546 top1= 95.7812
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1856 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8971 top1= 78.2552


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6559 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9652 top1= 45.9936

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1699 top1= 95.3125
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.1548 top1= 95.3125
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1784 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8967 top1= 77.9748


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6359 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9767 top1= 46.0036

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1672 top1= 95.1562
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.1526 top1= 95.1562
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1746 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8997 top1= 77.7143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6413 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9851 top1= 45.9736

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1672 top1= 95.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1539 top1= 95.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1719 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9006 top1= 78.0349


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6204 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9525 top1= 46.0136

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1644 top1= 95.4688
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1559 top1= 95.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1697 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9012 top1= 78.3454


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6425 top1= 50.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9427 top1= 45.9936

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1632 top1= 95.3125
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.1552 top1= 95.3125
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1712 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9000 top1= 78.5457


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6380 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9240 top1= 45.9635

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1667 top1= 95.1562
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1566 top1= 95.1562
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1722 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9011 top1= 78.4956


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6327 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8851 top1= 45.9635

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1667 top1= 95.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.1602 top1= 95.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1713 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9021 top1= 78.6358


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6468 top1= 49.7196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8898 top1= 45.9635

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1732 top1= 94.5312
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.1708 top1= 94.2188
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1732 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9042 top1= 78.6959


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6462 top1= 49.5994


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8546 top1= 45.8133

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1792 top1= 94.5312
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1723 top1= 94.3750
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1697 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9055 top1= 78.6058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6419 top1= 49.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9148 top1= 45.7131

