
=== 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 ByzantineWorker(index=20)
=> Add worker ByzantineWorker(index=21)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f9ccd68b2b0>

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: 1.4200 top1= 51.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8638 top1= 72.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3700 top1= 77.5441


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1625 top1= 48.4075


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9569 top1= 42.3978

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5354 top1= 82.9688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.3779 top1= 87.6562
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3584 top1= 88.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0323 top1= 81.5104


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8432 top1= 49.5192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6465 top1= 44.3510

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2859 top1= 91.4062
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2349 top1= 93.1250
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2693 top1= 92.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9157 top1= 82.8325


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1974 top1= 49.6394


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0447 top1= 44.8618

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2511 top1= 92.3438
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1787 top1= 94.5312
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2268 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8204 top1= 83.1731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5809 top1= 49.7997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5985 top1= 45.2524

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2009 top1= 93.9062
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1715 top1= 95.0000
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2319 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8025 top1= 83.4135


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5238 top1= 49.9299


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3332 top1= 45.4527

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.2012 top1= 93.5938
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1457 top1= 95.7812
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1874 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7783 top1= 83.7941


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5589 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3343 top1= 45.7532

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1733 top1= 94.6875
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1436 top1= 95.3125
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1772 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7345 top1= 84.5553


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7450 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5874 top1= 45.9635

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1485 top1= 95.6250
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1196 top1= 96.4062
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1447 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7283 top1= 84.8458


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6848 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4920 top1= 46.1038

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1623 top1= 94.6875
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1155 top1= 96.4062
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1376 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7019 top1= 85.9375


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7275 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5173 top1= 46.2540

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1312 top1= 96.0938
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1024 top1= 97.3438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1250 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6768 top1= 85.8774


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8716 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6816 top1= 46.3842

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1253 top1= 96.7188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0917 top1= 97.0312
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1246 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6790 top1= 86.0677


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7712 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5440 top1= 46.3341

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1104 top1= 96.7188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0862 top1= 97.3438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1055 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6619 top1= 86.5986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8109 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5306 top1= 46.5345

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1285 top1= 96.0938
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0807 top1= 97.5000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1011 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6389 top1= 86.8189


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9120 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7138 top1= 46.5244

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0943 top1= 97.8125
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0801 top1= 97.8125
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0824 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6441 top1= 86.7488


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8667 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6277 top1= 46.5745

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0926 top1= 97.6562
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0660 top1= 97.8125
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0922 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6337 top1= 87.0192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8999 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6604 top1= 46.7248

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0829 top1= 97.3438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0666 top1= 98.1250
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0743 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6100 top1= 87.1094


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0287 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8487 top1= 46.7949

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0844 top1= 97.6562
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0569 top1= 98.1250
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0747 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6088 top1= 87.5601


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9128 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7503 top1= 46.7949

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0782 top1= 97.8125
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0524 top1= 98.2812
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0661 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6111 top1= 86.9792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9692 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8116 top1= 46.9050

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0745 top1= 97.9688
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0473 top1= 98.5938
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0605 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5875 top1= 87.4199


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0864 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9391 top1= 46.9251

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0705 top1= 97.6562
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0568 top1= 97.8125
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0602 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5845 top1= 87.9307


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0440 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8738 top1= 46.9151

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0798 top1= 97.8125
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0512 top1= 98.2812
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0615 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5884 top1= 86.9792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9933 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9460 top1= 46.8650

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0708 top1= 98.1250
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0419 top1= 98.4375
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0444 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5629 top1= 87.8506


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1523 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0521 top1= 47.0152

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0621 top1= 98.5938
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0474 top1= 98.5938
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0563 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5632 top1= 87.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1138 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0707 top1= 47.0353

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0593 top1= 98.7500
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0322 top1= 99.0625
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0556 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5674 top1= 87.0092


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0793 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0363 top1= 47.0653

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0631 top1= 98.7500
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0303 top1= 99.0625
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0395 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5483 top1= 87.8706


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2408 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2070 top1= 47.0553

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0446 top1= 99.2188
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0398 top1= 98.5938
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0359 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5487 top1= 87.8205


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2456 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1860 top1= 47.1755

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0452 top1= 99.2188
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0306 top1= 98.9062
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0418 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5505 top1= 87.3698


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2290 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1533 top1= 47.1254

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0432 top1= 99.0625
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0254 top1= 99.5312
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0318 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5313 top1= 87.9307


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3230 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3459 top1= 47.1554

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0435 top1= 99.0625
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0377 top1= 98.5938
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0580 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5356 top1= 87.8405


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3410 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3266 top1= 47.1755

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0511 top1= 98.5938
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0219 top1= 99.3750
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0359 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5394 top1= 87.4199


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3326 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2874 top1= 47.2256

