
=== 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 0x7eff8066b2b0>

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: 1.0301 top1= 62.1875
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3950 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7229 top1= 78.5256


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0040 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8538 top1= 44.2608

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2841 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1924 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1962 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6665 top1= 84.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4995 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5401 top1= 45.8233

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1624 top1= 94.8438
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1094 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1220 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5975 top1= 85.8273


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4236 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6932 top1= 46.1639

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1189 top1= 96.5625
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0785 top1= 97.6562
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0785 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5362 top1= 86.9591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6079 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6874 top1= 46.4042

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0810 top1= 97.9688
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0592 top1= 98.2812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0557 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4841 top1= 87.2396


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7497 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7827 top1= 46.6146

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0569 top1= 99.0625
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0410 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0407 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4444 top1= 88.1110


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9027 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7585 top1= 46.9251

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0394 top1= 99.3750
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0271 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0384 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4105 top1= 88.9022


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1234 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6707 top1= 46.7348

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0324 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0247 top1= 99.0625
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0250 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3909 top1= 88.4215


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1889 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6945 top1= 47.0453

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0231 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0183 top1= 99.5312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0176 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3724 top1= 88.3514


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1806 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0205 top1= 46.8049

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0236 top1= 99.5312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0117 top1= 99.8438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0164 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3620 top1= 88.7921


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9238 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1954 top1= 46.9952

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0087 top1= 99.8438
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0096 top1=100.0000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0237 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3658 top1= 88.2512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5979 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2480 top1= 46.9952

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0146 top1= 99.5312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0122 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0098 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3367 top1= 89.4631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5971 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1603 top1= 47.1354

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0049 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0100 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3290 top1= 89.6534


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5563 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9716 top1= 47.0553

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0037 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0068 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3192 top1= 89.8337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6113 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9532 top1= 47.1655

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3193 top1= 89.4531


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7399 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0496 top1= 47.0853

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0025 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3101 top1= 89.8037


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7179 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9667 top1= 47.1855

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3125 top1= 89.6134


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6657 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9042 top1= 47.1855

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3119 top1= 89.6534


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5925 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7868 top1= 47.1755

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3103 top1= 89.6635


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4937 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6590 top1= 47.2155

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3080 top1= 89.6835


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3867 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5221 top1= 47.1755

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3048 top1= 89.7736


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2721 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3830 top1= 47.1454

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3012 top1= 89.9038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1468 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2378 top1= 47.1254

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2978 top1= 90.0140


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0124 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0804 top1= 47.1354

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2943 top1= 90.1442


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8814 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9187 top1= 47.1454

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2912 top1= 90.3045


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7499 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7600 top1= 47.1655

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2883 top1= 90.4647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6147 top1= 50.8313


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5987 top1= 47.1855

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2852 top1= 90.5950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4844 top1= 50.9515


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4383 top1= 47.2356

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2822 top1= 90.7552


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3604 top1= 51.1619


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2797 top1= 47.3658

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2793 top1= 90.8854


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2375 top1= 51.3722


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1420 top1= 47.5561

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2765 top1= 91.0757


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1205 top1= 51.5925


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9995 top1= 47.7965

