
=== 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 0x7f326a0c06d0>

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: 1.0343 top1= 62.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4010 top1= 88.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7256 top1= 78.3053


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9275 top1= 49.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6623 top1= 44.3409

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2830 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1957 top1= 93.5938
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1918 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6600 top1= 84.5252


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4964 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5472 top1= 45.8133

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1639 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1100 top1= 96.5625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1172 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5901 top1= 85.7973


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5325 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7679 top1= 46.1839

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1154 top1= 96.7188
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0780 top1= 97.6562
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0778 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5414 top1= 86.2580


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8727 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8041 top1= 46.5345

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0775 top1= 98.2812
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0580 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0541 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4949 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1549 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0763 top1= 46.7348

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0544 top1= 98.9062
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0366 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0395 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4600 top1= 87.5901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4843 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2550 top1= 46.8750

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0413 top1= 99.3750
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0251 top1= 99.5312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0293 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4341 top1= 87.5601


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7171 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6898 top1= 46.8650

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0315 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0187 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0203 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4210 top1= 86.9992


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8748 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2615 top1= 46.7748

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0282 top1= 99.3750
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0129 top1=100.0000
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0245 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4245 top1= 86.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7849 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6687 top1= 46.8850

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0137 top1= 99.6875
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0099 top1= 99.8438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0133 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4417 top1= 85.5569


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9293 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9330 top1= 46.7548

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0177 top1= 99.3750
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0090 top1= 99.6875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0095 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4226 top1= 86.3582


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0922 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1594 top1= 46.7949

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0121 top1= 99.6875
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0095 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0110 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4046 top1= 87.1094


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2547 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2484 top1= 47.0954

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0069 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0062 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3743 top1= 87.9207


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6777 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9339 top1= 47.1254

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0068 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3636 top1= 88.5216


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9370 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9791 top1= 46.9752

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0089 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0070 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3701 top1= 87.8906


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1430 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1694 top1= 47.2456

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3718 top1= 87.6002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3249 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3867 top1= 47.2656

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3808 top1= 87.0593


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4818 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5909 top1= 47.2957

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3729 top1= 87.4599


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6329 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.8336 top1= 47.2756

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3642 top1= 87.7905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7674 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=9.0510 top1= 47.2857

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3620 top1= 87.8405

