
=== 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.Dumbbell object at 0x7fa70726a490>

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: 1.0355 top1= 62.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3949 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7159 top1= 78.7460


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7478 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6104 top1= 44.2208

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2808 top1= 91.0938
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1924 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1946 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6358 top1= 84.4451


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1968 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1695 top1= 45.8033

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1607 top1= 94.5312
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1077 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1269 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5616 top1= 85.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9984 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8955 top1= 46.2841

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1227 top1= 96.5625
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0792 top1= 97.8125
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0863 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4968 top1= 86.1378


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8925 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6585 top1= 46.4643

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0857 top1= 97.9688
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0609 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0614 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4418 top1= 86.7288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8714 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5354 top1= 46.4643

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0695 top1= 98.2812
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0440 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0454 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4091 top1= 87.2296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7459 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3571 top1= 46.5946

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0521 top1= 98.9062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0330 top1= 99.5312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0376 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3840 top1= 87.3998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6359 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1135 top1= 46.7348

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0345 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0238 top1= 99.3750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0273 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3490 top1= 88.5817


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5987 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9946 top1= 46.8950

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0244 top1= 99.5312
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0190 top1= 99.6875
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0228 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3246 top1= 89.4131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4440 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6993 top1= 47.0853

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0209 top1= 99.5312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0186 top1= 99.3750
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0217 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3035 top1= 90.0140


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1988 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3405 top1= 47.5661

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0149 top1= 99.8438
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0124 top1=100.0000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0180 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2852 top1= 90.5649


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9129 top1= 51.0317


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2522 top1= 47.7865

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0144 top1= 99.8438
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0167 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0603 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3113 top1= 90.0942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6588 top1= 51.7127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0711 top1= 48.3974

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0422 top1= 98.7500
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0197 top1= 99.6875
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0217 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2782 top1= 90.4447


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5569 top1= 52.0933


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8944 top1= 49.8197

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0236 top1= 99.3750
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0130 top1= 99.8438
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0129 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2688 top1= 90.9856


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4907 top1= 52.7544


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8195 top1= 51.1018

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0099 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0094 top1= 99.8438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0224 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2618 top1= 91.1258


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1431 top1= 53.6158


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6798 top1= 52.2937

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0112 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0082 top1= 99.8438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0075 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2750 top1= 90.6751


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9582 top1= 54.3369


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5031 top1= 54.0966

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0175 top1= 99.5312
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0088 top1= 99.6875
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0089 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2660 top1= 90.9655


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6690 top1= 56.0196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4804 top1= 54.8678

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0063 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0109 top1= 99.6875
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0081 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2559 top1= 91.3562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4761 top1= 57.0513


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5177 top1= 53.9163

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0062 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0043 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0138 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2550 top1= 91.3962


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2831 top1= 58.4836


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5612 top1= 54.2768

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0098 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0058 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0061 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2348 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2222 top1= 59.6655


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1385 top1= 57.5120

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0035 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0096 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2303 top1= 92.4679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1151 top1= 60.7973


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0080 top1= 59.1146

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0035 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2263 top1= 92.6883


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9883 top1= 62.1294


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7528 top1= 61.8490

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0043 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0037 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2257 top1= 92.8385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9105 top1= 63.1510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7274 top1= 62.0192

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0050 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0033 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2235 top1= 92.8886


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7347 top1= 64.9239


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7057 top1= 63.5617

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0044 top1= 99.8438
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0072 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2235 top1= 92.9988


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7001 top1= 65.6651


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7162 top1= 64.5933

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0032 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2259 top1= 92.9988


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5599 top1= 67.3277


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7044 top1= 65.6851

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0034 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0037 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2169 top1= 93.3393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4970 top1= 68.2592


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4526 top1= 68.2792

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2174 top1= 93.4696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4007 top1= 69.6915


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4058 top1= 69.5112

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2166 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3188 top1= 71.0737


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3431 top1= 70.7933

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2163 top1= 93.5797


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2730 top1= 71.7949


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2760 top1= 72.2556

