
=== 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 0x7fbe22b152b0>

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: 1.0317 top1= 62.1875
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3980 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7212 top1= 79.0064


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9824 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7362 top1= 44.2508

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2800 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1880 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1965 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6629 top1= 84.8658


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5312 top1= 49.8798


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5346 top1= 45.7732

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1608 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1087 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1219 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5990 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4744 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6469 top1= 46.1939

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1159 top1= 96.5625
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0790 top1= 97.9688
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0776 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5356 top1= 86.9992


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6304 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7264 top1= 46.4543

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0783 top1= 98.1250
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0574 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0537 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4863 top1= 87.0192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7993 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8081 top1= 46.6647

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0571 top1= 98.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0394 top1= 99.0625
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0394 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4440 top1= 87.7704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9666 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8384 top1= 46.9151

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0397 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0257 top1= 99.5312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0339 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4121 top1= 88.6318


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1916 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8252 top1= 46.7548

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0314 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0232 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0248 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3973 top1= 88.0909


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2589 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9869 top1= 46.9952

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0223 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0178 top1= 99.6875
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0172 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3802 top1= 88.2512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2558 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3598 top1= 46.8149

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0193 top1= 99.5312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0105 top1=100.0000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0213 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3830 top1= 87.7304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0566 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5536 top1= 46.9551

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0110 top1= 99.6875
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0097 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0122 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3827 top1= 87.2396


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0735 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6051 top1= 46.8850

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0125 top1= 99.6875
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0118 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0106 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3451 top1= 89.1026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7343 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5730 top1= 47.1554

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0062 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0051 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0111 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3354 top1= 89.4331


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7175 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3234 top1= 47.1154

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0034 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0061 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3234 top1= 89.7937


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7611 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2921 top1= 47.0152

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0064 top1= 99.8438
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0033 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0048 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3234 top1= 89.5433


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8628 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3938 top1= 47.0853

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3190 top1= 89.6835


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8859 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3223 top1= 47.1354

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3235 top1= 89.3129


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8341 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3037 top1= 47.2155

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3235 top1= 89.3530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7800 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2176 top1= 47.2155

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3225 top1= 89.3129


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6997 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1178 top1= 47.2155

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3198 top1= 89.4231


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6063 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0122 top1= 47.2055

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3164 top1= 89.4732


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5029 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9077 top1= 47.1655

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3124 top1= 89.6534


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3864 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7885 top1= 47.1755

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3085 top1= 89.7736


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2673 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6556 top1= 47.1254

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3048 top1= 89.9740


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1387 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5098 top1= 47.1154

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3013 top1= 90.1242


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0069 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3562 top1= 47.1054

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2977 top1= 90.2644


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8790 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1940 top1= 47.1554

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2952 top1= 90.4647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7467 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0283 top1= 47.1655

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2920 top1= 90.5549


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6162 top1= 50.8413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8657 top1= 47.1755

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2894 top1= 90.6250


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4874 top1= 51.0116


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7042 top1= 47.1755

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2869 top1= 90.7652


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3569 top1= 51.1719


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5509 top1= 47.2155

