
=== 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 0x7ff4227442b0>

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: 1.0357 top1= 62.5000
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3953 top1= 88.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7061 top1= 79.2167


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8300 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7596 top1= 44.2107

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2806 top1= 90.6250
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1934 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1938 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6309 top1= 85.5869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2615 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3972 top1= 45.8534

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1583 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1088 top1= 96.5625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1242 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5514 top1= 86.8089


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0938 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3324 top1= 46.2139

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1205 top1= 96.4062
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0791 top1= 98.1250
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0817 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4875 top1= 87.5601


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0986 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2313 top1= 46.4443

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0836 top1= 97.8125
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0599 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0581 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4339 top1= 88.1110


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1035 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2115 top1= 46.5044

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0641 top1= 98.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0438 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0430 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3970 top1= 88.3413


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0525 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0922 top1= 46.7448

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0444 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0313 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0321 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3621 top1= 89.1927


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0221 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9497 top1= 46.8149

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0275 top1= 99.5312
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0220 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0252 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3372 top1= 89.8337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0153 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6064 top1= 46.9852

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0193 top1= 99.5312
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0180 top1= 99.6875
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0427 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3322 top1= 89.7736


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8407 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1678 top1= 46.5445

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0242 top1= 99.2188
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0191 top1= 99.8438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0254 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3431 top1= 88.7520


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6425 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8050 top1= 46.5545

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0276 top1= 99.6875
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0155 top1= 99.6875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0143 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3234 top1= 88.9724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3244 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9445 top1= 47.0453

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0161 top1= 99.5312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0113 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0127 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3080 top1= 89.4932


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1290 top1= 50.9115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9225 top1= 47.1554

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0073 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0077 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0252 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2902 top1= 90.3145


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7454 top1= 51.3221


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7208 top1= 47.2556

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0075 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0063 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0143 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2819 top1= 90.8253


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5615 top1= 51.2019


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5020 top1= 47.4459

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0171 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0059 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2748 top1= 90.8654


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4185 top1= 51.7127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3600 top1= 48.2672

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0061 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0156 top1= 99.5312
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2672 top1= 90.8353


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1307 top1= 52.6042


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2438 top1= 49.0084

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0060 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0088 top1= 99.8438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0105 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2555 top1= 91.5465


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8453 top1= 53.4255


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0180 top1= 49.9700

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0062 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0051 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0060 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2537 top1= 91.5465


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6489 top1= 54.1266


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8179 top1= 51.0517

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0034 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2469 top1= 91.9872


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5797 top1= 55.6190


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6628 top1= 52.4239

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0033 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2440 top1= 92.1775


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5122 top1= 57.0212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5331 top1= 53.5256

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0035 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0050 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2411 top1= 92.2877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3465 top1= 58.5737


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4046 top1= 54.9679

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0038 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2363 top1= 92.3878


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2514 top1= 59.5653


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2586 top1= 56.6807

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0038 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2347 top1= 92.4880


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1426 top1= 60.9375


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1395 top1= 58.1230

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0038 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2332 top1= 92.5080


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9913 top1= 62.2596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0238 top1= 59.6855

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0036 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2325 top1= 92.6883


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9278 top1= 63.1611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9139 top1= 61.1879

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0034 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2309 top1= 92.7284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7732 top1= 64.6534


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8005 top1= 62.7404

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2298 top1= 92.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7231 top1= 65.4848


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7011 top1= 64.4431

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2287 top1= 93.0990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6252 top1= 66.7668


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6198 top1= 65.9455

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2274 top1= 93.2492


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5480 top1= 67.8986


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5394 top1= 67.2877

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0025 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2264 top1= 93.2792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4833 top1= 68.9403


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4738 top1= 68.5497

