
=== 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 0x7f80271b72b0>

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: 1.0481 top1= 62.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3930 top1= 87.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5697 top1= 83.9744


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0826 top1= 49.2388


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1933 top1= 44.0405

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2815 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2031 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2092 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4314 top1= 87.6603


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4703 top1= 52.2336


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6615 top1= 47.0353

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1731 top1= 94.0625
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1229 top1= 97.0312
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1556 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3533 top1= 88.9223


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2848 top1= 55.2985


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4209 top1= 50.0300

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1356 top1= 95.4688
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0925 top1= 97.5000
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1158 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3118 top1= 90.1042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3119 top1= 56.6907


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2184 top1= 51.9631

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1055 top1= 96.8750
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0691 top1= 98.2812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0967 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2888 top1= 90.5749


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2658 top1= 57.9427


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1034 top1= 54.7075

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0821 top1= 97.9688
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0523 top1= 98.5938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0741 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2829 top1= 90.6050


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3609 top1= 58.5337


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9682 top1= 58.2332

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0661 top1= 98.2812
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0447 top1= 98.9062
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0565 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2751 top1= 90.8253


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2111 top1= 60.0661


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0042 top1= 59.3249

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0592 top1= 98.4375
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0314 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0502 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2654 top1= 91.3061


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2466 top1= 60.4968


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0256 top1= 59.1146

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0580 top1= 98.2812
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0264 top1= 99.3750
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0383 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2603 top1= 91.4163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1013 top1= 61.8690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1754 top1= 57.1014

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0528 top1= 98.5938
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0366 top1= 99.0625
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0331 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2564 top1= 91.6366


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0955 top1= 62.5000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8598 top1= 60.3566

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0447 top1= 98.5938
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0194 top1= 99.3750
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0255 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2545 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9854 top1= 64.0725


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9377 top1= 60.0861

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0251 top1= 99.3750
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0153 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0208 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2483 top1= 92.0773


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9050 top1= 64.9639


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9305 top1= 61.6887

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0189 top1= 99.3750
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0110 top1= 99.8438
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0112 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2405 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8026 top1= 65.5349


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6428 top1= 64.1827

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0200 top1= 99.5312
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0097 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0095 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2320 top1= 92.6783


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6179 top1= 68.0088


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7048 top1= 63.8822

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0090 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0100 top1= 99.8438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0072 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2312 top1= 93.0288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5496 top1= 68.7800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4932 top1= 68.1791

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0066 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0043 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0070 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2292 top1= 93.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5123 top1= 69.5613


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3941 top1= 70.6931

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0054 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2394 top1= 93.0088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3867 top1= 70.6931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4672 top1= 70.4828

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0091 top1= 99.6875
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0052 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2293 top1= 93.4495


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3557 top1= 71.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3474 top1= 71.8850

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0046 top1= 99.8438
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0059 top1= 99.8438
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0045 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2282 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3487 top1= 71.4744


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2732 top1= 73.6579

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0033 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0078 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2345 top1= 93.3894


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3066 top1= 72.4659


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2413 top1= 74.1787

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0037 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2341 top1= 93.3393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5099 top1= 70.6530


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0855 top1= 76.4323

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2390 top1= 93.3494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4209 top1= 71.3942


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1367 top1= 76.0216

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0083 top1= 99.6875
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2400 top1= 93.4595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0875 top1= 75.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1947 top1= 75.4908

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2330 top1= 93.5296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9697 top1= 77.2937


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1160 top1= 76.7027

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2387 top1= 93.4696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0783 top1= 77.0132


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1098 top1= 76.9531

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2323 top1= 93.5897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9521 top1= 78.7159


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0637 top1= 77.8145

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2336 top1= 93.6198


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9123 top1= 79.5172


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0561 top1= 78.0950

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2340 top1= 93.6799


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8786 top1= 80.1783


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0391 top1= 78.5357

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2346 top1= 93.7099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8535 top1= 80.7292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0311 top1= 78.7360

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2353 top1= 93.7099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8293 top1= 81.2400


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0249 top1= 78.9163

