
=== 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 0x7fbcc80e19d0>

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: 0.9953 top1= 63.7500
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2591 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6736 top1= 79.1667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9585 top1= 48.6278


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6374 top1= 43.5998

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3938 top1= 90.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2596 top1= 92.5000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1532 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7081 top1= 84.5453


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0928 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1321 top1= 45.5529

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1432 top1= 95.3125
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1230 top1= 95.9375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0815 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5841 top1= 85.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8890 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1627 top1= 45.9736

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0798 top1= 97.1875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0634 top1= 96.8750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0494 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5035 top1= 86.7889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9665 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3625 top1= 46.1639

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0438 top1= 98.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0440 top1= 99.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0269 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4447 top1= 87.7404


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0571 top1= 50.2404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8158 top1= 46.3442

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0221 top1=100.0000
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0263 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0143 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4286 top1= 87.2496


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1971 top1= 50.2404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0119 top1= 46.0337

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0137 top1=100.0000
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0163 top1=100.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0140 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4039 top1= 87.5300


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3075 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9794 top1= 46.2841

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0088 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0134 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0065 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3777 top1= 88.1611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3692 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0429 top1= 46.5645

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0114 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0165 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3683 top1= 88.2111


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3629 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0508 top1= 46.5946

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0076 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0157 top1= 99.0625
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0063 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3632 top1= 88.3213


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2042 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8638 top1= 46.5345

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0065 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0046 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3899 top1= 87.3598


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9898 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6239 top1= 46.0837

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0102 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0071 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3574 top1= 88.3413


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7408 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4782 top1= 46.5645

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0066 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0119 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3496 top1= 88.5216


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4540 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1242 top1= 47.3257

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0046 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0087 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3639 top1= 87.6402


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2066 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0886 top1= 47.1955

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0048 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0038 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3620 top1= 87.6803


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9316 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9233 top1= 47.8365

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0064 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3380 top1= 89.0224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6761 top1= 51.1819


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6403 top1= 48.4375

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0061 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3358 top1= 89.3930


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4714 top1= 51.8229


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5383 top1= 49.0585

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0035 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3298 top1= 89.5833


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2871 top1= 52.7143


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4111 top1= 49.3890

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0032 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3258 top1= 90.0240


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1097 top1= 54.1166


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1965 top1= 50.2204

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0035 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3183 top1= 90.1743


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9711 top1= 55.2784


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9883 top1= 51.0016

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0033 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3117 top1= 90.3546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8532 top1= 56.3401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7169 top1= 52.7244

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0034 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3092 top1= 90.4647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7165 top1= 57.5521


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4509 top1= 54.5473

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0033 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3080 top1= 90.4948


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6057 top1= 58.4736


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2472 top1= 56.4704

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3053 top1= 90.7853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4845 top1= 59.4752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0931 top1= 57.9928

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3034 top1= 90.9555


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3526 top1= 60.3566


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9590 top1= 59.4852

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0029 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3017 top1= 91.1058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2265 top1= 61.4583


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8429 top1= 61.0577

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0028 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2998 top1= 91.3161


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0931 top1= 62.5300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7483 top1= 62.6703

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2987 top1= 91.3862


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9721 top1= 63.6518


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6567 top1= 64.2628

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2981 top1= 91.4964


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8570 top1= 64.7236


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5652 top1= 65.8854

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2977 top1= 91.6166


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7499 top1= 65.9455


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4849 top1= 67.3978

