
=== 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 0x7f0d9509f490>

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: 1.0299 top1= 62.1875
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3989 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7235 top1= 78.8962


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9822 top1= 49.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7269 top1= 44.2808

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2805 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1882 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1972 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6697 top1= 84.6554


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4991 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5326 top1= 45.8133

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1601 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1094 top1= 96.4062
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1211 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6006 top1= 85.9776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4671 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6469 top1= 46.1739

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1164 top1= 96.5625
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0783 top1= 97.9688
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0786 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5390 top1= 86.7989


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6402 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7118 top1= 46.4643

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0787 top1= 98.1250
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0577 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0549 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4914 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7862 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8173 top1= 46.6847

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0556 top1= 98.9062
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0406 top1= 99.2188
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0401 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4536 top1= 87.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9683 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7723 top1= 46.9351

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0392 top1= 99.3750
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0265 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0335 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4183 top1= 88.4716


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1763 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8407 top1= 46.7748

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0303 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0230 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0241 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3977 top1= 87.9407


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2962 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0294 top1= 47.0353

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0204 top1= 99.3750
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0160 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0177 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3832 top1= 87.7404


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2557 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3171 top1= 46.7548

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0244 top1= 99.3750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0114 top1=100.0000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0224 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3691 top1= 88.4716


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0856 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4659 top1= 46.9852

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0098 top1= 99.8438
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0090 top1=100.0000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0132 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3765 top1= 87.6903


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9718 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6141 top1= 46.9351

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0146 top1= 99.5312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0115 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0090 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3474 top1= 89.0325


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7012 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5853 top1= 47.1054

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0064 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0111 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3413 top1= 89.0525


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6443 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4544 top1= 47.1855

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0041 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0089 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3301 top1= 89.5933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6882 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2522 top1= 47.0853

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3127 top1= 90.2744


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8238 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2902 top1= 46.9050

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0083 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0040 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0059 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3202 top1= 89.4231


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8665 top1= 50.7712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1905 top1= 47.0954

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3173 top1= 89.5933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8165 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2133 top1= 47.1154

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3199 top1= 89.4431


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7557 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1240 top1= 47.2556

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3191 top1= 89.3730


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6760 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0566 top1= 47.2256

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3181 top1= 89.3930


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5804 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9435 top1= 47.1655

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3155 top1= 89.5032


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4753 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8361 top1= 47.1554

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3127 top1= 89.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3606 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7142 top1= 47.1554

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0017 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=0.3092 top1= 89.6534


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2413 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5859 top1= 47.1454

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=0.3054 top1= 89.8438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1167 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4477 top1= 47.1354

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=0.3017 top1= 89.9940


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9911 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3016 top1= 47.1354

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0016 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=0.2981 top1= 90.1442


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8638 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1494 top1= 47.1354

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= 90.3446


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7360 top1= 50.8113


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9923 top1= 47.1454

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0016 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= 90.4347


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6071 top1= 50.9415


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8413 top1= 47.1655

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=0.2893 top1= 90.5649


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4800 top1= 51.1018


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6857 top1= 47.1855

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0017 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=0.2864 top1= 90.6851


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3588 top1= 51.3421


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5421 top1= 47.2356

