
=== 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 0x7f95e279b490>

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: 1.0334 top1= 62.1875
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3941 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6962 top1= 79.5573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0676 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2021 top1= 44.2308

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2784 top1= 90.9375
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1932 top1= 94.0625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1971 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5870 top1= 85.9275


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5395 top1= 49.9099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6155 top1= 45.7632

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1603 top1= 94.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1110 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1361 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4899 top1= 86.8790


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1243 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0483 top1= 46.3642

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1270 top1= 96.2500
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0819 top1= 97.9688
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1048 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4195 top1= 88.2812


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8208 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7373 top1= 46.5645

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0922 top1= 97.1875
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0629 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0786 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3715 top1= 88.8321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6290 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4939 top1= 46.6446

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0683 top1= 98.2812
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0450 top1= 98.5938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0576 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3367 top1= 89.5933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4955 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4065 top1= 46.8750

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0523 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0351 top1= 99.0625
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0397 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3158 top1= 89.8938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3953 top1= 51.1218


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3030 top1= 47.3057

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0420 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0284 top1= 99.3750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0290 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3045 top1= 90.1542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3330 top1= 51.9030


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3724 top1= 47.6663

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0362 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0206 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0213 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2952 top1= 90.3045


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2618 top1= 52.7444


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3690 top1= 47.8165

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0280 top1= 99.3750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0180 top1=100.0000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0202 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2895 top1= 90.5148


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2544 top1= 53.5357


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0730 top1= 48.4876

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0230 top1= 99.2188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0196 top1= 99.6875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0321 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2743 top1= 91.2260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1921 top1= 54.0665


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9567 top1= 50.3205

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0174 top1= 99.3750
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0230 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0411 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2873 top1= 90.5048


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1637 top1= 54.5873


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9690 top1= 50.0901

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0320 top1= 98.9062
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0253 top1= 99.3750
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0373 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2889 top1= 90.3846


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2028 top1= 54.9880


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0150 top1= 50.7111

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0476 top1= 98.2812
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0108 top1= 99.8438
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0185 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2671 top1= 90.8053


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0688 top1= 55.9796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0754 top1= 50.0901

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0209 top1= 99.2188
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0187 top1= 99.6875
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0161 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2514 top1= 91.6366


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7839 top1= 57.8626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5998 top1= 52.8045

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0074 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0218 top1= 99.5312
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0138 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2611 top1= 91.4563


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8712 top1= 57.0312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6271 top1= 53.6959

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0115 top1= 99.5312
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0099 top1= 99.8438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0367 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2786 top1= 90.9655


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6296 top1= 58.2833


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3504 top1= 56.4002

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0101 top1= 99.6875
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0110 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0154 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2488 top1= 91.7067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5280 top1= 58.3133


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2341 top1= 56.8209

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0179 top1= 99.2188
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0089 top1= 99.8438
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0142 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2424 top1= 92.1274


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6134 top1= 58.0329


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3986 top1= 55.6290

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0079 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0038 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0088 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2418 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2734 top1= 59.5653


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2173 top1= 57.4619

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0090 top1= 99.6875
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0117 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2300 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2865 top1= 60.2163


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0943 top1= 59.3049

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0039 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2331 top1= 92.4980


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1340 top1= 60.9776


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0123 top1= 60.3566

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2321 top1= 92.4980


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1571 top1= 61.4784


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9584 top1= 61.4283

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2255 top1= 92.8085


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1828 top1= 61.9091


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9274 top1= 62.1394

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2243 top1= 92.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0902 top1= 62.7103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9061 top1= 62.8606

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2255 top1= 92.9287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0294 top1= 63.4515


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8882 top1= 63.4215

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2259 top1= 93.0489


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0038 top1= 63.9123


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8679 top1= 63.8922

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2265 top1= 92.9888


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9790 top1= 64.2127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8566 top1= 64.5533

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2271 top1= 92.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9548 top1= 64.6334


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8423 top1= 65.0240

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2277 top1= 92.9888


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9361 top1= 65.0441


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8269 top1= 65.5649

