
=== 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 0x7f3540a612b0>

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: 1.0395 top1= 62.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3935 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6573 top1= 81.0697


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4611 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6589 top1= 44.3209

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2781 top1= 90.3125
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1933 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1940 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5144 top1= 86.7989


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7634 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7165 top1= 45.9535

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1598 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1100 top1= 97.3438
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1457 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4246 top1= 87.5701


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2998 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0565 top1= 46.4744

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1308 top1= 95.7812
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0813 top1= 97.6562
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1086 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3690 top1= 88.5116


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1367 top1= 50.8514


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7709 top1= 47.9467

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1028 top1= 96.7188
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0607 top1= 98.5938
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0865 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3343 top1= 89.2628


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0051 top1= 52.2636


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5667 top1= 50.3005

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0776 top1= 97.8125
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0429 top1= 99.3750
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0654 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3132 top1= 89.9940


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9011 top1= 53.7560


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4913 top1= 52.0032

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0589 top1= 98.7500
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0311 top1= 99.5312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0533 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3027 top1= 90.1242


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8350 top1= 54.7877


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4937 top1= 52.8145

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0511 top1= 98.7500
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0296 top1= 99.2188
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0407 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2918 top1= 90.1542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8378 top1= 55.8694


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4604 top1= 54.0365

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0369 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0360 top1= 99.0625
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0738 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2838 top1= 90.3546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8265 top1= 56.3001


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4152 top1= 55.6490

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0475 top1= 98.4375
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0302 top1= 98.7500
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0741 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3184 top1= 89.0625


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5890 top1= 57.7724


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6821 top1= 53.5457

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0670 top1= 97.3438
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0356 top1= 98.9062
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0313 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2647 top1= 91.1458


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4327 top1= 59.4251


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3896 top1= 53.0950

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0252 top1= 99.2188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0187 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0172 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2605 top1= 91.5164


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4239 top1= 60.3265


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3424 top1= 54.7977

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0181 top1= 99.3750
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0111 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0194 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2448 top1= 92.0873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3540 top1= 60.7171


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1877 top1= 55.9996

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0099 top1= 99.8438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0123 top1= 99.8438
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0120 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2371 top1= 92.2276


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2597 top1= 61.2480


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1269 top1= 59.0545

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0115 top1= 99.8438
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0058 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0075 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2329 top1= 92.6382


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2796 top1= 61.5485


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9363 top1= 61.5885

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0061 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0065 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0066 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2338 top1= 92.7684


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2263 top1= 61.6286


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9318 top1= 61.7989

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0063 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0078 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2345 top1= 92.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2318 top1= 61.7588


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8584 top1= 63.3113

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0070 top1= 99.8438
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0092 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0100 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2299 top1= 92.8886


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9658 top1= 64.0525


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7462 top1= 64.7336

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0050 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0112 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2387 top1= 92.8486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9481 top1= 65.0841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5879 top1= 66.5264

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0050 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2342 top1= 93.0589


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9137 top1= 65.1843


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4827 top1= 68.0188

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2293 top1= 93.1190


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7473 top1= 66.9872


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4934 top1= 68.1791

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0035 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2278 top1= 93.2091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7225 top1= 67.4279


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6069 top1= 68.0689

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0079 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2353 top1= 92.9688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6443 top1= 68.5998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8186 top1= 66.5264

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0052 top1= 99.8438
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2354 top1= 92.9888


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6244 top1= 69.0204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8025 top1= 67.0773

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2285 top1= 93.4696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5882 top1= 69.7416


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4658 top1= 69.9219

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2321 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5594 top1= 70.2825


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4763 top1= 70.6731

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2342 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5258 top1= 70.8433


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4396 top1= 71.7648

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2351 top1= 93.5196


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5014 top1= 71.3141


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4072 top1= 72.5461

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2364 top1= 93.4996


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4721 top1= 71.7949


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3742 top1= 73.3273

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2366 top1= 93.5196


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4496 top1= 72.1855


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3502 top1= 73.7079

