
=== 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 0x7f4194b48490>

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: 1.0384 top1= 61.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3987 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7301 top1= 78.2352


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8395 top1= 49.2788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5639 top1= 44.1506

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2845 top1= 90.9375
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1926 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1967 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6781 top1= 83.5236


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3779 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1961 top1= 45.7732

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1604 top1= 94.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1102 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1278 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6059 top1= 85.2063


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1655 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1776 top1= 46.1639

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1203 top1= 96.4062
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0811 top1= 98.1250
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0856 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5436 top1= 86.6286


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1951 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1592 top1= 46.3642

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0853 top1= 97.9688
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0653 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0610 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4972 top1= 87.1294


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2319 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2003 top1= 46.4944

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0660 top1= 98.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0514 top1= 98.7500
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0476 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4626 top1= 87.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2387 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1091 top1= 46.7248

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0460 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0337 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0404 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4317 top1= 88.2512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2886 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9551 top1= 46.9151

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0321 top1= 99.5312
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0248 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0445 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4118 top1= 88.9323


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3372 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8242 top1= 46.6747

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0362 top1= 99.0625
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0234 top1= 99.3750
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0305 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4019 top1= 88.6018


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2868 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5573 top1= 47.0653

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0238 top1= 99.3750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0248 top1= 99.0625
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0280 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3784 top1= 89.2628


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1030 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6539 top1= 46.8850

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0232 top1= 99.2188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0145 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0246 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3850 top1= 88.4615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8074 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9305 top1= 47.0152

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0146 top1= 99.6875
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0127 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0119 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3611 top1= 89.3930


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7819 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0582 top1= 47.0954

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0084 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0081 top1= 99.6875
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0071 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3534 top1= 89.3930


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8162 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1095 top1= 47.1655

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0053 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0050 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0065 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3537 top1= 89.0124


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8638 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2982 top1= 47.1254

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0035 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3403 top1= 89.4631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9723 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3441 top1= 47.2055

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0037 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3313 top1= 89.5032


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1421 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4061 top1= 47.1955

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0026 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3297 top1= 89.3730


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2217 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4506 top1= 47.1755

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0025 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3315 top1= 89.2628


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2477 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4936 top1= 47.1955

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3305 top1= 89.2528


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2892 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5169 top1= 47.1955

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3287 top1= 89.2228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3122 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5418 top1= 47.1655

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3252 top1= 89.2728


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3311 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5636 top1= 47.1554

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3223 top1= 89.3329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3452 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5949 top1= 47.1454

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3190 top1= 89.5132


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3628 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6189 top1= 47.1154

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3170 top1= 89.5733


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3747 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6351 top1= 47.0853

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3156 top1= 89.5933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3812 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6486 top1= 47.1254

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3148 top1= 89.6635


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3838 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6532 top1= 47.1354

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3141 top1= 89.5733


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3832 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6496 top1= 47.1354

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3138 top1= 89.6234


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3875 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6460 top1= 47.1454

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3133 top1= 89.6835


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3840 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6308 top1= 47.1655

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: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3135 top1= 89.7536


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3812 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6169 top1= 47.2055

