
=== 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 0x7f087de2c7f0>

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: 1.3836 top1= 51.2500
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.8139 top1= 74.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3632 top1= 76.8429


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0117 top1= 48.3373


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9812 top1= 41.5565

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.5036 top1= 84.3750
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3883 top1= 87.5000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2241 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0285 top1= 81.1799


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7844 top1= 49.4291


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6463 top1= 44.2508

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.2756 top1= 92.1875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3123 top1= 90.9375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1913 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9131 top1= 83.7540


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0642 top1= 49.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8700 top1= 44.7817

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2384 top1= 92.1875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2205 top1= 92.5000
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1640 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8565 top1= 84.4952


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2659 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0869 top1= 45.3225

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1787 top1= 95.6250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1789 top1= 93.1250
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1465 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8110 top1= 84.3650


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2890 top1= 50.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1709 top1= 45.6030

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1498 top1= 95.6250
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1504 top1= 95.0000
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1110 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7726 top1= 85.5268


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3773 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2796 top1= 45.7732

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1371 top1= 96.8750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1357 top1= 94.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.1147 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7371 top1= 85.5369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6022 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5390 top1= 45.7732

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1212 top1= 96.2500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1163 top1= 95.3125
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.1000 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7309 top1= 85.6571


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5787 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4058 top1= 45.9235

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.1097 top1= 96.8750
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1238 top1= 96.2500
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0734 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7145 top1= 85.9575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5286 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3981 top1= 46.1338

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1002 top1= 96.5625
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0958 top1= 96.5625
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0674 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7108 top1= 85.8474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5953 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4597 top1= 46.2139

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0839 top1= 97.1875
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0872 top1= 96.5625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0806 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6936 top1= 86.3482


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6074 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5311 top1= 46.2340

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0820 top1= 96.8750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0740 top1= 97.8125
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0592 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6671 top1= 87.0994


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6118 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5968 top1= 46.4343

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0651 top1= 97.5000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0796 top1= 96.5625
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0557 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6580 top1= 86.6587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7974 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7986 top1= 46.4543

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0639 top1= 98.4375
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0624 top1= 97.1875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0552 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6396 top1= 87.4800


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8073 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7037 top1= 46.4443

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0652 top1= 98.1250
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0658 top1= 97.1875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0396 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6492 top1= 87.2696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8263 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7256 top1= 46.5946

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0640 top1= 98.1250
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0622 top1= 98.1250
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0306 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6325 top1= 87.4199


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8939 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6732 top1= 46.5946

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0470 top1= 98.7500
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0579 top1= 98.4375
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0312 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6255 top1= 87.5401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7508 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7819 top1= 46.7648

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0428 top1= 99.3750
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0466 top1= 98.4375
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0414 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6188 top1= 88.1310


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8656 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8683 top1= 46.7348

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0524 top1= 98.4375
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0448 top1= 99.0625
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0242 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5981 top1= 87.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9938 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0605 top1= 46.8950

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0359 top1= 98.7500
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0407 top1= 98.7500
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0229 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5974 top1= 87.7704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0135 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0522 top1= 46.8149

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0537 top1= 98.1250
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0381 top1= 99.0625
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0214 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5955 top1= 87.9808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0352 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0512 top1= 46.8850

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0380 top1= 99.0625
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0339 top1= 98.7500
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0192 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5877 top1= 88.0909


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0719 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0138 top1= 47.0353

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0368 top1= 99.0625
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0400 top1= 98.1250
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0187 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5893 top1= 88.1811


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0389 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9785 top1= 47.0152

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0347 top1= 99.0625
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0266 top1= 99.6875
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0202 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5830 top1= 88.0008


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0080 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0310 top1= 47.0954

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0276 top1= 99.3750
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0288 top1= 99.6875
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0136 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5630 top1= 88.2913


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1390 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2488 top1= 47.0753

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0196 top1= 99.6875
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0193 top1= 99.6875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0131 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5665 top1= 87.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1751 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2948 top1= 47.0252

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0307 top1= 99.3750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0252 top1= 99.3750
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0131 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5568 top1= 88.9022


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1711 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1964 top1= 47.1454

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0225 top1= 99.3750
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0234 top1= 99.3750
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0122 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5476 top1= 88.6318


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1701 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1619 top1= 47.1755

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0246 top1= 99.3750
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0221 top1= 99.3750
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0125 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5559 top1= 88.8822


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2506 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1510 top1= 47.2155

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0215 top1= 99.6875
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0176 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0117 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5421 top1= 89.0425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1073 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2182 top1= 47.2055

