
=== 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 0x7fab18f529d0>

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: 1.0273 top1= 63.7500
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2650 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8788 top1= 68.4996


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7877 top1= 48.7680


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5566 top1= 44.2007

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3835 top1= 90.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3331 top1= 89.0625
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1722 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4438 top1= 86.0677


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3579 top1= 52.3237


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9087 top1= 51.1518

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1616 top1= 95.0000
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1346 top1= 95.9375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1144 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3671 top1= 88.2612


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0411 top1= 55.2183


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6239 top1= 56.1899

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1029 top1= 96.2500
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0952 top1= 97.8125
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0856 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3335 top1= 88.9724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0576 top1= 56.0897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4102 top1= 60.0761

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0742 top1= 97.5000
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0912 top1= 97.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0691 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3156 top1= 89.5032


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1566 top1= 56.6707


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3557 top1= 62.8405

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0427 top1= 98.7500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0613 top1= 98.1250
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0527 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3058 top1= 89.9840


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1539 top1= 58.1430


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1843 top1= 67.1074

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0293 top1= 99.6875
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0366 top1= 99.0625
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0279 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2909 top1= 90.7051


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9830 top1= 60.0361


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2249 top1= 67.9387

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0325 top1= 98.7500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0170 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0329 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2755 top1= 91.4263


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7326 top1= 63.4515


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4400 top1= 65.3646

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0350 top1= 99.0625
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0493 top1= 98.1250
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0249 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2753 top1= 91.3161


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7823 top1= 62.9307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1355 top1= 72.2857

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0219 top1= 99.3750
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0482 top1= 98.7500
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0215 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2667 top1= 91.5565


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6470 top1= 64.8337


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1964 top1= 71.9151

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0212 top1= 99.0625
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0262 top1= 99.0625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0152 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2704 top1= 91.7067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4505 top1= 68.9904


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1594 top1= 72.2556

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0105 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0365 top1= 97.8125
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0168 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2723 top1= 91.9471


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2226 top1= 71.2039


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9167 top1= 76.3321

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0095 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0165 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0066 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2791 top1= 91.5966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1679 top1= 72.1855


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0862 top1= 74.9099

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0089 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0072 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0063 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2686 top1= 92.1875


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0817 top1= 73.9283


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0596 top1= 76.1118

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0144 top1= 99.6875
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0086 top1= 99.6875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2626 top1= 92.4179


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9801 top1= 76.0116


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9728 top1= 77.7644

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0035 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2690 top1= 92.4079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9627 top1= 76.7328


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8581 top1= 80.5489

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2645 top1= 92.8085


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9457 top1= 77.5441


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7295 top1= 82.7724

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0021 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2662 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9130 top1= 78.2452


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6970 top1= 83.5136

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0019 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2674 top1= 92.9287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8810 top1= 78.9363


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6713 top1= 84.1346

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2691 top1= 92.9587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8543 top1= 79.5573


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6465 top1= 84.7456

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2709 top1= 92.9387


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8357 top1= 80.0881


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6280 top1= 85.1763

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2725 top1= 92.9587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8174 top1= 80.6090


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6069 top1= 85.5469

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2741 top1= 93.0288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8008 top1= 80.9996


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5894 top1= 85.9575

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2756 top1= 93.0188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7848 top1= 81.5104


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5756 top1= 86.4884

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2769 top1= 93.0389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7693 top1= 81.9311


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5624 top1= 86.8690

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2781 top1= 93.0689


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7544 top1= 82.4519


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5529 top1= 87.1494

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2791 top1= 93.0990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7400 top1= 82.8125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5441 top1= 87.4499

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2801 top1= 93.1390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7276 top1= 83.1831


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5365 top1= 87.8706

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2811 top1= 93.1390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7146 top1= 83.5537


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5297 top1= 88.0108

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2819 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7036 top1= 83.8842


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5248 top1= 88.1310

