
=== 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 ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7fd8d84a59d0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0116 top1= 64.0625
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2561 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7035 top1= 75.2003


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2882 top1= 48.7780


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5670 top1= 43.5497

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3979 top1= 90.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3230 top1= 90.0000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1533 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5433 top1= 85.3666


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0605 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6940 top1= 45.6430

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1384 top1= 95.6250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1277 top1= 95.3125
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0912 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4167 top1= 87.9107


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5992 top1= 51.2620


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2289 top1= 47.4860

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1030 top1= 96.5625
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0861 top1= 96.8750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0650 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3464 top1= 89.3830


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1765 top1= 54.6875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8271 top1= 52.6542

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0709 top1= 97.8125
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0688 top1= 97.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0509 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3158 top1= 89.8037


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0236 top1= 57.3317


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5784 top1= 57.0112

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0527 top1= 98.1250
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0477 top1= 98.7500
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0388 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3016 top1= 90.2644


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0094 top1= 58.7139


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4468 top1= 60.7071

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0414 top1= 99.0625
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0403 top1= 99.0625
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0250 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2912 top1= 90.6951


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9977 top1= 60.0260


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4694 top1= 62.4599

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0329 top1= 99.6875
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0186 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0183 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2860 top1= 91.1659


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7288 top1= 63.7019


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2730 top1= 66.7268

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0117 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0530 top1= 98.4375
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0153 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2852 top1= 91.2961


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3796 top1= 68.4495


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8607 top1= 75.7412

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0144 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0131 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0219 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2662 top1= 91.8470


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2599 top1= 70.5028


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1642 top1= 70.7031

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0114 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0218 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0151 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2679 top1= 92.1975


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3074 top1= 70.6030


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0113 top1= 74.0184

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0089 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0143 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0151 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2896 top1= 91.6366


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2072 top1= 72.6162


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8230 top1= 78.7360

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0137 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0154 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0091 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2891 top1= 91.9571


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2532 top1= 71.9752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7607 top1= 80.2484

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0186 top1= 99.0625
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0284 top1= 98.4375
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0158 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2859 top1= 91.7969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0660 top1= 74.3690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9354 top1= 78.4756

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0067 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0082 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2705 top1= 92.4479


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9617 top1= 76.8530


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7481 top1= 81.6907

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0063 top1= 99.6875
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2798 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9596 top1= 77.2536


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5189 top1= 86.3482

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0043 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0034 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2549 top1= 93.2392


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7282 top1= 81.7007


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5488 top1= 85.7071

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0027 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2481 top1= 93.4395


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6641 top1= 83.1631


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5427 top1= 85.9976

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0034 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2488 top1= 93.5697


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5838 top1= 85.0962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5390 top1= 86.6286

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2546 top1= 93.4595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5244 top1= 86.7188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5480 top1= 86.6286

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2628 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4826 top1= 87.9307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5974 top1= 85.6470

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2583 top1= 93.4595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4467 top1= 88.9724


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5198 top1= 87.2997

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2577 top1= 93.5797


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4181 top1= 89.8438


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4921 top1= 88.1310

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2583 top1= 93.6599


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4057 top1= 90.2444


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4821 top1= 88.4215

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2590 top1= 93.6999


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3975 top1= 90.4948


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4726 top1= 88.7119

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2595 top1= 93.7200


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3920 top1= 90.5849


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4615 top1= 89.0825

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2599 top1= 93.7300


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3887 top1= 90.7652


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4494 top1= 89.4131

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2602 top1= 93.7700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3872 top1= 90.8854


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4375 top1= 89.7636

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2605 top1= 93.8001


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3870 top1= 90.9255


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4255 top1= 90.0641

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2609 top1= 93.8301


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3872 top1= 91.0156


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4140 top1= 90.4647

