
=== 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 0x7efd682aa2b0>

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: 1.0368 top1= 61.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4003 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7378 top1= 78.1851


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.1187 top1= 49.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7745 top1= 44.2107

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2863 top1= 90.6250
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1929 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1980 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6909 top1= 83.9343


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6127 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4790 top1= 45.7632

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1626 top1= 94.3750
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1094 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1243 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6266 top1= 85.2764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5481 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6626 top1= 46.1639

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1168 top1= 96.7188
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0803 top1= 97.9688
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0811 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5775 top1= 85.5669


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7442 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6414 top1= 46.4744

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0812 top1= 98.1250
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0629 top1= 98.2812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0579 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5396 top1= 85.9776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8470 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7712 top1= 46.7147

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0582 top1= 98.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0430 top1= 98.7500
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0492 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5052 top1= 86.6987


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0032 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8294 top1= 46.7548

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0465 top1= 99.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0306 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0342 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4809 top1= 86.3982


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1092 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0765 top1= 46.9251

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0347 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0223 top1= 99.3750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0246 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4678 top1= 85.8574


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1728 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5982 top1= 46.7748

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0288 top1= 98.9062
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0145 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0228 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4816 top1= 84.6855


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2243 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8618 top1= 46.8450

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0204 top1= 99.5312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0144 top1= 99.8438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0120 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4666 top1= 85.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3845 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1599 top1= 46.7548

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0124 top1= 99.6875
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0108 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0106 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4580 top1= 85.2564


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5389 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3134 top1= 46.9752

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0077 top1= 99.8438
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0085 top1=100.0000
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0163 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4299 top1= 86.3381


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8022 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1021 top1= 47.0152

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0072 top1= 99.8438
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0055 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0196 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4167 top1= 86.9491


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1186 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7939 top1= 47.1855

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0048 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0033 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0063 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3906 top1= 88.1611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3802 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8793 top1= 46.7548

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0163 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0068 top1= 99.8438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0084 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4154 top1= 86.3782


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5490 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8953 top1= 47.0152

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0030 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4071 top1= 86.4483


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7178 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1085 top1= 47.2155

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4192 top1= 85.8674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8590 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3064 top1= 47.2356

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4084 top1= 86.2280


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9920 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5208 top1= 47.2957

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3912 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1216 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7193 top1= 47.2957

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3922 top1= 86.8289


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2415 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8581 top1= 47.2456

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0009 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3934 top1= 86.6987


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3471 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0096 top1= 47.2556

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3928 top1= 86.6987


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4505 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1285 top1= 47.2656

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0008 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3926 top1= 86.7188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5482 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2357 top1= 47.2656

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0007 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3921 top1= 86.7388


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6382 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3313 top1= 47.2556

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3922 top1= 86.7087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7221 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4206 top1= 47.2656

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3923 top1= 86.7488


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8001 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5052 top1= 47.2656

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3919 top1= 86.7488


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8776 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5827 top1= 47.2556

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3922 top1= 86.7188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9487 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6562 top1= 47.2656

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3923 top1= 86.7188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0148 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.7273 top1= 47.2656

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3923 top1= 86.6987


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0804 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.7941 top1= 47.2556

