
=== 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 0x7f6b29cd62e0>

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: 1.0341 top1= 61.5625
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3944 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6770 top1= 80.3586


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2441 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4319 top1= 44.2608

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2878 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1919 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1960 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5928 top1= 85.9175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8257 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8689 top1= 45.7732

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1562 top1= 95.0000
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1071 top1= 96.7188
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1330 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4973 top1= 87.2296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4580 top1= 49.9299


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4985 top1= 46.2640

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1246 top1= 96.2500
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0766 top1= 98.2812
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0980 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4273 top1= 88.3313


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1334 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0603 top1= 46.5044

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0861 top1= 97.8125
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0580 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0691 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3706 top1= 89.0325


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8531 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7627 top1= 46.5645

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0671 top1= 98.4375
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0420 top1= 99.0625
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0502 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3329 top1= 89.6134


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5736 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4492 top1= 46.6647

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0536 top1= 99.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0320 top1= 99.6875
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0384 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3092 top1= 90.1142


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3388 top1= 51.3321


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2624 top1= 47.1855

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0413 top1= 99.5312
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0266 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0296 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2926 top1= 90.5248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1372 top1= 52.9247


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0278 top1= 48.1470

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0292 top1= 99.5312
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0196 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0248 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2807 top1= 90.9555


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0413 top1= 54.0665


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9683 top1= 49.0785

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0216 top1= 99.5312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0160 top1=100.0000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0214 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2781 top1= 91.0357


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0817 top1= 54.7075


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9419 top1= 50.3506

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0225 top1= 99.5312
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0145 top1=100.0000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0339 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2726 top1= 91.1058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1772 top1= 55.2083


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9300 top1= 51.7528

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0313 top1= 99.2188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0278 top1= 99.3750
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0283 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3102 top1= 89.5032


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0213 top1= 56.1899


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9554 top1= 52.5541

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0843 top1= 96.7188
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0481 top1= 98.4375
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0708 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3174 top1= 89.1226


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8910 top1= 56.9511


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8925 top1= 52.1534

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0378 top1= 98.9062
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0172 top1= 99.6875
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0164 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2610 top1= 91.3161


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9260 top1= 56.8209


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7555 top1= 52.1334

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0194 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0209 top1= 99.5312
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0232 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2441 top1= 91.9571


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7116 top1= 57.9227


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3062 top1= 55.4487

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0142 top1= 99.5312
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0108 top1= 99.8438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0104 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2557 top1= 91.5765


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3594 top1= 59.5353


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3636 top1= 56.6607

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0087 top1= 99.8438
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0074 top1= 99.8438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0100 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2415 top1= 92.0172


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1898 top1= 60.4667


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2968 top1= 57.1915

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0075 top1= 99.8438
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0049 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0084 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2331 top1= 92.6883


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3374 top1= 60.6571


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0160 top1= 60.1963

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0068 top1= 99.6875
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0052 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0060 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2298 top1= 92.6783


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0604 top1= 62.6302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9677 top1= 61.0076

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0030 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0135 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2239 top1= 93.0088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9962 top1= 63.1811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8299 top1= 62.8506

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0039 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2270 top1= 93.0389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8510 top1= 64.2728


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7861 top1= 62.7905

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0042 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0050 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2237 top1= 93.0889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8376 top1= 64.7436


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6250 top1= 64.8838

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0037 top1= 99.8438
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2219 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7987 top1= 65.3846


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7300 top1= 64.5232

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0034 top1= 99.8438
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0108 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2303 top1= 92.9287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7323 top1= 66.2961


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0103 top1= 62.2596

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2246 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7147 top1= 66.7869


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8665 top1= 64.0425

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2243 top1= 93.1991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6848 top1= 67.3478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7397 top1= 66.0557

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: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2260 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6561 top1= 67.9888


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6698 top1= 67.2376

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2271 top1= 93.3093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6216 top1= 68.5897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6113 top1= 68.3393

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2276 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5967 top1= 69.0505


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5728 top1= 69.3710

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2277 top1= 93.3994


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5738 top1= 69.4812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5433 top1= 70.0621

