
=== 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 0x7fa05c0342e0>

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: 1.0294 top1= 62.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3995 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7285 top1= 78.8361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0849 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8186 top1= 44.2408

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2818 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1875 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1967 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6782 top1= 84.5954


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6242 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6146 top1= 45.8133

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1618 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1089 top1= 96.5625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1206 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6170 top1= 85.9675


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6037 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7800 top1= 46.1939

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1140 top1= 96.8750
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0782 top1= 97.8125
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0769 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5559 top1= 86.7388


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8572 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9134 top1= 46.4844

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0793 top1= 98.1250
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0581 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0539 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5122 top1= 86.8790


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0645 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0127 top1= 46.6847

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0555 top1= 98.9062
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0383 top1= 99.0625
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0407 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4745 top1= 87.5100


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3182 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0424 top1= 46.8650

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0411 top1= 99.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0275 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0305 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4425 top1= 87.7404


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5987 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2887 top1= 46.9651

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0276 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0202 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0211 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4243 top1= 87.2997


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7587 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8069 top1= 46.8049

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0264 top1= 99.0625
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0132 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0185 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4076 top1= 87.7404


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7385 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1466 top1= 46.8850

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0118 top1= 99.8438
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0109 top1=100.0000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0161 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4233 top1= 86.3281


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6896 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3869 top1= 46.8249

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0152 top1= 99.5312
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0111 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0091 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3990 top1= 87.1995


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7370 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5850 top1= 46.8550

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0086 top1= 99.8438
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0094 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0087 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3784 top1= 88.2312


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7671 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5378 top1= 47.1655

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0050 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0097 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3701 top1= 88.3814


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8832 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3648 top1= 47.1054

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0030 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0054 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3503 top1= 89.1326


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1667 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4151 top1= 47.0353

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0064 top1= 99.8438
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3546 top1= 88.5517


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3239 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6582 top1= 47.1454

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3953 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7221 top1= 47.2256

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3573 top1= 88.1510


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4653 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7971 top1= 47.2055

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3555 top1= 88.1010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5051 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8731 top1= 47.2155

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3520 top1= 88.2512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5358 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9437 top1= 47.2055

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3478 top1= 88.3113


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5527 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9932 top1= 47.1554

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3451 top1= 88.4014


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5596 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0147 top1= 47.1554

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3425 top1= 88.4615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5604 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9992 top1= 47.1855

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3398 top1= 88.6418


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5501 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9716 top1= 47.1955

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3368 top1= 88.7320


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5350 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9371 top1= 47.1955

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3342 top1= 88.8221


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5125 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8976 top1= 47.2055

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3319 top1= 88.9724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4811 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8516 top1= 47.2155

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3300 top1= 89.0124


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4483 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8054 top1= 47.2155

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3288 top1= 89.0925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4080 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7529 top1= 47.2256

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0007 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=0.3272 top1= 89.1627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3677 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7019 top1= 47.2256

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3262 top1= 89.1927


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3202 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6452 top1= 47.2356

