
=== 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 0x7fc819216490>

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: 1.0422 top1= 62.1875
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3908 top1= 88.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7205 top1= 75.1402


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5140 top1= 49.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3531 top1= 44.1607

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2776 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1957 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2036 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5523 top1= 80.8494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5978 top1= 51.6526


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4112 top1= 45.9936

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1602 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1197 top1= 97.0312
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1549 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4232 top1= 85.5369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3653 top1= 54.7977


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8867 top1= 46.6446

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1313 top1= 95.6250
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0891 top1= 97.6562
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1199 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3602 top1= 87.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2951 top1= 56.5505


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6176 top1= 48.4475

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1000 top1= 97.0312
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0638 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0946 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3307 top1= 88.6418


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3047 top1= 57.6923


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5778 top1= 50.9716

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0770 top1= 98.4375
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0506 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0736 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3119 top1= 89.2027


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3304 top1= 58.3333


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5969 top1= 52.2035

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0674 top1= 97.9688
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0401 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0625 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3096 top1= 89.4231


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2941 top1= 59.3049


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7129 top1= 52.2736

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0643 top1= 98.4375
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0469 top1= 98.2812
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0528 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3241 top1= 88.9623


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2645 top1= 60.0962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7451 top1= 52.1234

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0818 top1= 97.1875
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0366 top1= 98.9062
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0470 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3133 top1= 89.1627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1803 top1= 61.0076


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5593 top1= 52.9647

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0603 top1= 98.5938
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0215 top1= 99.6875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0283 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2723 top1= 90.9355


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1114 top1= 62.4900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3796 top1= 54.1967

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0293 top1= 99.2188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0201 top1= 99.5312
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0283 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2611 top1= 91.6466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2328 top1= 62.3498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0888 top1= 57.5721

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0141 top1= 99.6875
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0175 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0229 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2506 top1= 91.7969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8813 top1= 64.4732


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8633 top1= 60.4467

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0175 top1= 99.5312
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0109 top1= 99.8438
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0106 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2588 top1= 91.7668


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6306 top1= 66.7869


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8563 top1= 61.9792

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0079 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0087 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0106 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2425 top1= 92.2877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7080 top1= 66.9872


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8743 top1= 61.0577

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0125 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0072 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0069 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2343 top1= 92.7083


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8813 top1= 65.5950


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7756 top1= 63.7320

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0062 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0063 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2293 top1= 92.9888


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6530 top1= 67.4980


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5933 top1= 66.3462

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0044 top1= 99.8438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2339 top1= 92.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6053 top1= 68.5296


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6275 top1= 66.7969

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0032 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0037 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2375 top1= 92.9587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5227 top1= 69.2608


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5280 top1= 68.4395

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2357 top1= 93.1290


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4667 top1= 69.7516


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4781 top1= 69.5212

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2390 top1= 93.1591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4129 top1= 70.5729


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4610 top1= 70.2123

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2422 top1= 93.1090


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3131 top1= 72.0853


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4219 top1= 71.1338

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2406 top1= 93.3193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3348 top1= 71.5244


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3827 top1= 72.0753

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0034 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2431 top1= 93.1390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4672 top1= 70.4427


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3614 top1= 72.6562

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2453 top1= 93.1591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4460 top1= 71.3141


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3596 top1= 73.0068

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2428 top1= 92.9688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2901 top1= 72.7364


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3457 top1= 73.4275

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0043 top1= 99.8438
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0040 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2440 top1= 93.2292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2716 top1= 73.9383


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3070 top1= 74.0785

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0030 top1= 99.8438
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0037 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2479 top1= 93.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2885 top1= 74.2188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2806 top1= 74.5593

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2450 top1= 93.1991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1012 top1= 76.6426


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2786 top1= 74.8097

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2420 top1= 93.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0688 top1= 76.8029


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2633 top1= 75.1703

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2399 top1= 93.4195


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9931 top1= 78.1651


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2541 top1= 75.3105

