
=== 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 0x7f185ddc2490>

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: 1.0372 top1= 61.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3996 top1= 88.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7352 top1= 78.2552


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9784 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6752 top1= 44.1607

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2867 top1= 90.9375
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1933 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1977 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6824 top1= 84.0244


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4583 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3218 top1= 45.7732

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1604 top1= 94.5312
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1101 top1= 96.5625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1258 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6164 top1= 85.4868


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3083 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3721 top1= 46.1238

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1191 top1= 96.5625
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0805 top1= 98.1250
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0842 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5563 top1= 86.3281


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4028 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4105 top1= 46.3542

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0839 top1= 97.8125
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0657 top1= 98.2812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0604 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5125 top1= 87.0092


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4082 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4262 top1= 46.5745

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0628 top1= 98.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0485 top1= 98.7500
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0476 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4751 top1= 87.6903


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4644 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3482 top1= 46.8249

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0436 top1= 99.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0320 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0456 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4488 top1= 88.4115


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5464 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1828 top1= 46.7047

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0393 top1= 99.0625
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0284 top1= 99.2188
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0315 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4375 top1= 87.6502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5719 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1795 top1= 47.0252

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0298 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0237 top1= 99.0625
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0240 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4138 top1= 88.2111


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4676 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4076 top1= 46.8349

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0299 top1= 99.0625
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0133 top1=100.0000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0250 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4306 top1= 86.7288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2748 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6083 top1= 46.9651

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0162 top1= 99.5312
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0139 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0120 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4020 top1= 88.0409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3287 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8130 top1= 47.0052

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0084 top1=100.0000
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0103 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0104 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3924 top1= 88.3313


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2817 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8351 top1= 47.1955

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0063 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0070 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0134 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3807 top1= 88.6719


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4074 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7112 top1= 47.1955

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0042 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0101 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3624 top1= 89.4631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5468 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6158 top1= 47.1054

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0067 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0036 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3491 top1= 89.6534


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7414 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6952 top1= 47.1755

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0047 top1= 99.8438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0047 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3601 top1= 88.6619


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8775 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8731 top1= 47.0553

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0035 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3478 top1= 89.2628


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9484 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9245 top1= 47.2155

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3587 top1= 88.5417


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0306 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9813 top1= 47.2256

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3598 top1= 88.3614


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0918 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0750 top1= 47.2155

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3601 top1= 88.2913


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1342 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1636 top1= 47.2055

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3595 top1= 88.2612


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1788 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2406 top1= 47.1855

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3570 top1= 88.3113


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2283 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3215 top1= 47.1354

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3537 top1= 88.4315


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2802 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3878 top1= 47.1354

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3505 top1= 88.5317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3210 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4320 top1= 47.1554

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3483 top1= 88.6418


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3614 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4552 top1= 47.2055

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3458 top1= 88.7720


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3999 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4586 top1= 47.2155

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3424 top1= 89.0124


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4315 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4620 top1= 47.2756

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3387 top1= 89.1627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4644 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4679 top1= 47.2356

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3365 top1= 89.2728


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4969 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4821 top1= 47.2155

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3358 top1= 89.2228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5250 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5093 top1= 47.1955

