
=== 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.Dumbbell object at 0x7ff16a951490>

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: 1.0340 top1= 61.4062
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3916 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6572 top1= 81.5104


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5478 top1= 49.3490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9117 top1= 44.2708

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2846 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1918 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1997 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5370 top1= 86.7488


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0406 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0736 top1= 45.8333

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1549 top1= 95.0000
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1075 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1444 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4465 top1= 87.6102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6025 top1= 49.7997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3226 top1= 46.3742

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1303 top1= 96.0938
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0789 top1= 97.8125
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1111 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3839 top1= 88.3213


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3632 top1= 50.1703


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0753 top1= 46.7348

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0979 top1= 97.0312
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0599 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0894 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3438 top1= 89.1727


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1143 top1= 51.4523


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9035 top1= 47.8165

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0707 top1= 97.9688
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0414 top1= 99.2188
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0681 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3212 top1= 89.5032


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0164 top1= 52.4038


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8296 top1= 49.1687

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0508 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0311 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0519 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3058 top1= 89.9439


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9874 top1= 53.5457


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7021 top1= 50.8013

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0377 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0265 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0406 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2974 top1= 90.4247


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8691 top1= 54.6274


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5601 top1= 52.7143

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0307 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0279 top1= 99.2188
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0361 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3038 top1= 90.0741


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8608 top1= 55.4187


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3863 top1= 54.2167

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0351 top1= 98.5938
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0283 top1= 99.2188
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0404 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2755 top1= 90.6550


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8833 top1= 56.1198


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7706 top1= 50.3906

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0442 top1= 99.2188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0178 top1= 99.5312
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0229 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2775 top1= 90.7652


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7086 top1= 57.8626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5545 top1= 52.8746

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0230 top1= 99.2188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0191 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0145 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2606 top1= 91.3061


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5777 top1= 58.5036


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5474 top1= 53.3454

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0176 top1= 99.2188
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0164 top1= 99.6875
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0251 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2524 top1= 91.6867


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4676 top1= 59.8357


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4167 top1= 54.8377

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0101 top1= 99.8438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0137 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0165 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2494 top1= 91.8670


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9751 top1= 57.9828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2600 top1= 58.2432

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0090 top1= 99.8438
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0077 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0138 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2465 top1= 92.0974


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4818 top1= 60.0260


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2129 top1= 59.2147

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0091 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0088 top1= 99.8438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0073 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2603 top1= 91.8770


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4974 top1= 60.1062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0894 top1= 59.8558

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0131 top1= 99.5312
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0074 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0149 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2374 top1= 92.3177


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1970 top1= 62.1995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1900 top1= 58.4635

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0128 top1= 99.8438
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0071 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0045 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2462 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0694 top1= 63.1210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2100 top1= 60.0361

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0055 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2352 top1= 92.5881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0069 top1= 63.7019


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9468 top1= 62.7003

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0039 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2363 top1= 92.6382


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0230 top1= 63.9123


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8776 top1= 64.3429

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0080 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2367 top1= 92.5080


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9903 top1= 64.3930


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9012 top1= 64.3029

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2281 top1= 92.9688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9725 top1= 65.0942


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6859 top1= 66.0056

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0049 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0038 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2277 top1= 93.0889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8971 top1= 65.8454


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5926 top1= 66.8169

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0055 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2283 top1= 93.1591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8571 top1= 66.3862


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5932 top1= 66.8169

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2281 top1= 93.2592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8005 top1= 67.0974


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6357 top1= 67.4679

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2334 top1= 93.1090


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7607 top1= 67.6382


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6890 top1= 68.0389

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2323 top1= 93.2292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7439 top1= 68.0389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5734 top1= 69.1907

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2340 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7141 top1= 68.4996


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5581 top1= 70.0020

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2344 top1= 93.3594


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6898 top1= 68.8001


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5267 top1= 70.6530

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2341 top1= 93.3494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6619 top1= 69.2608


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5090 top1= 71.0337

