
=== 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 ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f97b8c659d0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0069 top1= 64.6875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2625 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6960 top1= 79.1366


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0645 top1= 48.7179


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8662 top1= 43.9203

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3748 top1= 91.2500
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2717 top1= 91.8750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1539 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7182 top1= 84.1747


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1638 top1= 49.8397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8486 top1= 45.6130

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1447 top1= 95.6250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1359 top1= 94.3750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0874 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6191 top1= 84.7055


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6598 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9821 top1= 46.0036

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0883 top1= 97.1875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0776 top1= 96.5625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0517 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5495 top1= 86.0276


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7465 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1813 top1= 45.9135

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0555 top1= 97.8125
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0460 top1= 98.4375
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0354 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5017 top1= 86.9191


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8744 top1= 50.2404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3333 top1= 46.2440

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0390 top1= 98.4375
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0353 top1= 99.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0257 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4646 top1= 87.3898


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9527 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6040 top1= 46.3842

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0185 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0259 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0128 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4749 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1636 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8987 top1= 46.0337

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0147 top1= 99.6875
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0156 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0142 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4611 top1= 86.1178


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4379 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7467 top1= 46.2139

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0089 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0129 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4445 top1= 86.2580


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7741 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8435 top1= 46.4042

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0085 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0077 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0064 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4228 top1= 86.9992


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0496 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0622 top1= 46.6146

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0101 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0185 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0075 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4325 top1= 86.3982


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2006 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9009 top1= 46.5645

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0309 top1= 99.0625
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4463 top1= 85.9375


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2981 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9105 top1= 46.6046

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4478 top1= 85.7572


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3952 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8113 top1= 46.5445

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4183 top1= 86.3882


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4605 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8349 top1= 46.8049

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0081 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4056 top1= 86.7788


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5456 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1754 top1= 46.7849

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4121 top1= 86.4183


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6555 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3217 top1= 46.8550

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0019 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4308 top1= 85.8373


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7616 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3717 top1= 46.7548

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4234 top1= 86.0577


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8445 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4892 top1= 46.8149

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4243 top1= 86.0176


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9270 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5824 top1= 46.8249

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4245 top1= 85.9275


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9958 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6600 top1= 46.8349

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4217 top1= 86.0777


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0600 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7477 top1= 46.8450

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4202 top1= 86.1378


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1245 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8280 top1= 46.8650

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4203 top1= 86.1679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1798 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8991 top1= 46.8550

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4210 top1= 86.1679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2344 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9632 top1= 46.8450

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4211 top1= 86.1779


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2834 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0237 top1= 46.8450

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4210 top1= 86.1979


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3285 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0793 top1= 46.8450

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4216 top1= 86.1679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3754 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1300 top1= 46.8349

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4218 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4171 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1788 top1= 46.8349

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4224 top1= 86.1879


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4583 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2231 top1= 46.8349

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4225 top1= 86.1779


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4979 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2673 top1= 46.8450

