
=== 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.DumbbellVariant object at 0x7f6f087002b0>

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: 1.0341 top1= 61.5625
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3944 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6770 top1= 80.3586


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2441 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4319 top1= 44.2608

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2878 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1919 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1959 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5928 top1= 85.9075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8257 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8709 top1= 45.7833

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1564 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1069 top1= 96.7188
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1334 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4969 top1= 87.2095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4576 top1= 49.9299


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5130 top1= 46.2640

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1240 top1= 96.4062
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0768 top1= 98.2812
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0977 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4263 top1= 88.3614


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1328 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0622 top1= 46.4844

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0857 top1= 97.8125
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0583 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0694 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3703 top1= 89.0825


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8516 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7660 top1= 46.5545

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0672 top1= 98.2812
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0416 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0517 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3329 top1= 89.6434


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5698 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4767 top1= 46.7248

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0528 top1= 99.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0324 top1= 99.6875
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0387 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3099 top1= 90.0741


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3427 top1= 51.3021


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2631 top1= 47.1955

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0411 top1= 99.5312
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0275 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0297 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2931 top1= 90.5449


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1470 top1= 52.8846


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0199 top1= 48.1170

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0291 top1= 99.3750
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0199 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0241 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2810 top1= 90.9054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0217 top1= 54.1567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9627 top1= 49.1687

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0206 top1= 99.6875
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0156 top1= 99.8438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0242 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2745 top1= 91.2159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0778 top1= 54.6374


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8795 top1= 50.7312

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0199 top1= 99.8438
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0151 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0245 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2726 top1= 91.0457


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0643 top1= 55.6190


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0319 top1= 51.1819

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0448 top1= 98.2812
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0264 top1= 99.3750
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0439 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2654 top1= 91.2159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9668 top1= 56.1799


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5942 top1= 53.2752

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0164 top1= 99.6875
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0289 top1= 99.5312
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0254 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2796 top1= 90.5950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8325 top1= 56.7608


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9283 top1= 51.1919

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0172 top1= 99.3750
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0164 top1= 99.8438
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0135 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2453 top1= 91.7969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0890 top1= 56.7408


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6565 top1= 53.4655

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0176 top1= 99.5312
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0183 top1= 99.5312
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0265 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2457 top1= 91.9071


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9049 top1= 57.6823


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6487 top1= 53.9263

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0127 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0125 top1= 99.6875
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0272 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2367 top1= 92.2075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4222 top1= 59.5052


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4609 top1= 55.0982

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0168 top1= 99.2188
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0295 top1= 98.9062
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0164 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2486 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3374 top1= 60.6971


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1121 top1= 58.8141

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0216 top1= 99.3750
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0069 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0257 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2440 top1= 92.2576


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0876 top1= 61.6987


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1141 top1= 59.0845

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0111 top1= 99.8438
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0077 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0077 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2290 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2530 top1= 60.6971


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2996 top1= 57.3117

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0131 top1= 99.6875
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0050 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2255 top1= 92.7284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0415 top1= 61.7087


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0927 top1= 60.2063

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0038 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0087 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2117 top1= 93.3393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9801 top1= 63.6518


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7161 top1= 63.6619

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2161 top1= 93.3594


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8609 top1= 64.4732


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6517 top1= 65.6651

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2153 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7653 top1= 65.2744


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5988 top1= 66.8369

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2155 top1= 93.2592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7204 top1= 66.0056


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5202 top1= 68.2392

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2123 top1= 93.4395


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6488 top1= 67.0373


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5007 top1= 68.8902

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2125 top1= 93.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5956 top1= 68.0689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4735 top1= 69.5813

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2134 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5578 top1= 68.7800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4530 top1= 70.1923

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2136 top1= 93.5196


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5272 top1= 69.2708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4316 top1= 70.6931

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2138 top1= 93.5397


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5040 top1= 69.7716


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4106 top1= 71.1538

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2140 top1= 93.5797


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4764 top1= 70.2724


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3903 top1= 71.6647

