
=== 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 0x7f1651fed490>

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: 1.0690 top1= 61.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3895 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6878 top1= 81.1799


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9607 top1= 49.2388


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5498 top1= 44.2107

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2790 top1= 90.9375
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1973 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2027 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6073 top1= 86.0978


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5352 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8197 top1= 45.8033

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1710 top1= 94.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1272 top1= 96.7188
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1567 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5133 top1= 87.0693


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1673 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3446 top1= 46.2139

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1459 top1= 95.0000
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1041 top1= 96.8750
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1254 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4634 top1= 88.0108


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0112 top1= 50.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0774 top1= 46.4844

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1264 top1= 96.0938
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0861 top1= 97.6562
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1060 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4333 top1= 88.4615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9216 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9598 top1= 46.5946

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1097 top1= 96.5625
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0736 top1= 98.2812
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0926 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4169 top1= 88.7520


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8784 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8717 top1= 46.7748

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0955 top1= 97.3438
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0664 top1= 98.5938
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0843 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4075 top1= 88.9423


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8270 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8506 top1= 46.9852

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0894 top1= 97.9688
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0621 top1= 98.7500
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0777 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4069 top1= 88.8321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7898 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8510 top1= 47.0353

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0796 top1= 98.5938
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0598 top1= 98.7500
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0728 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4094 top1= 88.6518


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7913 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8605 top1= 47.0453

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0734 top1= 98.5938
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0585 top1= 98.7500
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0719 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4132 top1= 88.7821


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7960 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8725 top1= 46.9451

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0727 top1= 98.7500
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0603 top1= 98.9062
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0694 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4252 top1= 88.5016


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7975 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9452 top1= 46.7448

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0764 top1= 98.2812
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0627 top1= 98.5938
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0735 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4420 top1= 88.0108


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7817 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0360 top1= 46.4944

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0870 top1= 97.8125
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0702 top1= 98.1250
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0791 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4644 top1= 87.0994


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7760 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1756 top1= 46.2740

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1012 top1= 96.8750
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0719 top1= 98.2812
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1018 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4802 top1= 87.2496


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8062 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1635 top1= 46.2139

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1109 top1= 96.4062
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0792 top1= 97.5000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1075 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4885 top1= 87.6002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8188 top1= 49.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9945 top1= 46.3341

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1031 top1= 97.0312
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0849 top1= 97.5000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0939 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5159 top1= 87.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7226 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8098 top1= 46.7849

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0823 top1= 98.4375
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0723 top1= 98.4375
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0883 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5372 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6808 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9575 top1= 46.6446

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0800 top1= 98.1250
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0764 top1= 98.1250
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1087 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5559 top1= 86.5885


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7027 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0414 top1= 46.3542

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0927 top1= 97.5000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0812 top1= 98.5938
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1047 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5630 top1= 86.5986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6981 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2226 top1= 45.8634

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1106 top1= 97.1875
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0803 top1= 98.1250
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1006 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5801 top1= 86.2981


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6668 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1089 top1= 46.1839

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1011 top1= 97.5000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0838 top1= 98.1250
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1046 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5891 top1= 86.1979


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6573 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0926 top1= 46.2841

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1024 top1= 97.0312
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.1013 top1= 97.5000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1156 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6029 top1= 86.1378


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6812 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0150 top1= 46.3942

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1171 top1= 96.7188
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.1242 top1= 96.5625
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1391 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6117 top1= 86.2079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7172 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0352 top1= 46.3942

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1334 top1= 95.7812
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1034 top1= 97.3438
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1244 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6149 top1= 86.7488


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6835 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1172 top1= 46.1538

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1071 top1= 97.5000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0892 top1= 97.6562
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1178 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6354 top1= 85.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6901 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1253 top1= 46.1538

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1106 top1= 96.7188
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0874 top1= 97.8125
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1115 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6371 top1= 85.0661


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7038 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1050 top1= 46.3442

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1015 top1= 97.1875
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0923 top1= 98.1250
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1168 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6339 top1= 85.2564


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6928 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0863 top1= 46.3442

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1026 top1= 97.0312
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0971 top1= 97.9688
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1291 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6390 top1= 84.8157


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6965 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0647 top1= 46.3442

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1063 top1= 96.7188
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0969 top1= 97.3438
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1292 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6451 top1= 84.2348


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7119 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0300 top1= 46.3642

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1059 top1= 97.1875
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1066 top1= 97.1875
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1240 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6473 top1= 84.1046


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7220 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0591 top1= 46.3141

