
=== 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 0x7f6ec2e642b0>

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: 1.0380 top1= 62.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3929 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6375 top1= 82.5120


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4473 top1= 49.3890


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9268 top1= 44.2408

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2792 top1= 90.6250
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1927 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1946 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5247 top1= 86.6086


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6788 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1412 top1= 45.8433

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1612 top1= 94.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1093 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1458 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4323 top1= 87.3197


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2417 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4588 top1= 46.3642

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1313 top1= 95.3125
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0804 top1= 97.9688
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1118 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3756 top1= 88.1010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0517 top1= 51.0517


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1621 top1= 46.6847

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1056 top1= 96.5625
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0621 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0888 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3404 top1= 88.9623


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9542 top1= 52.5341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9213 top1= 47.9667

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0755 top1= 97.9688
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0454 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0655 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3187 top1= 89.6134


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8923 top1= 53.8862


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7655 top1= 49.5994

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0550 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0335 top1= 99.0625
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0490 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3087 top1= 89.7937


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7729 top1= 55.1783


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7054 top1= 50.7812

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0403 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0258 top1= 99.3750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0424 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3118 top1= 89.2328


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7237 top1= 56.3802


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6626 top1= 52.1034

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0336 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0329 top1= 99.2188
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0334 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3135 top1= 89.1727


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7216 top1= 56.8610


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5686 top1= 53.7861

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0422 top1= 98.7500
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0362 top1= 98.5938
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0574 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3019 top1= 89.6434


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5692 top1= 58.3834


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9068 top1= 49.5693

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0516 top1= 98.5938
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0322 top1= 99.2188
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0259 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2846 top1= 90.4848


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4491 top1= 59.1246


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6914 top1= 51.8730

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0324 top1= 98.9062
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0129 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0157 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2573 top1= 91.6066


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4577 top1= 59.4351


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3507 top1= 54.0565

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0176 top1= 99.5312
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0137 top1= 99.6875
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0162 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2571 top1= 91.6066


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2582 top1= 61.3882


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4386 top1= 55.1583

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0103 top1= 99.8438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0123 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0131 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2527 top1= 91.6967


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3628 top1= 60.7472


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3060 top1= 58.0829

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0157 top1= 99.3750
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0054 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2409 top1= 92.2476


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3267 top1= 60.8474


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1704 top1= 59.3450

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0080 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0084 top1= 99.8438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0072 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2401 top1= 92.3277


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1026 top1= 62.8506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3307 top1= 57.8726

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0055 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0087 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2425 top1= 92.1775


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0229 top1= 63.8822


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2240 top1= 59.8357

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0059 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0073 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2368 top1= 92.6082


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9004 top1= 64.5733


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9883 top1= 61.9391

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0044 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0063 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2356 top1= 92.7484


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8953 top1= 64.8237


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8531 top1= 63.0008

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2365 top1= 92.8385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7468 top1= 66.4864


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7753 top1= 63.5917

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2359 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7792 top1= 66.5966


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7428 top1= 64.4331

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0026 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0041 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2371 top1= 92.8786


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7141 top1= 67.4079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8619 top1= 64.4832

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2563 top1= 92.2877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6776 top1= 68.1490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2307 top1= 61.6486

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2299 top1= 93.1691


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6684 top1= 68.4395


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7369 top1= 66.1458

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2367 top1= 92.9688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6385 top1= 68.9704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8336 top1= 65.9054

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2400 top1= 93.0188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6009 top1= 69.6014


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6817 top1= 68.1090

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2410 top1= 93.0489


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5726 top1= 70.0921


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6463 top1= 69.2208

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2417 top1= 93.1190


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5377 top1= 70.5529


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6068 top1= 70.0521

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2400 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5121 top1= 71.0837


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5794 top1= 70.4227

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2380 top1= 93.3293


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4895 top1= 71.4844


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5432 top1= 70.9135

