
=== 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 0x7f84c0a9a2b0>

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: 1.0405 top1= 61.8750
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3948 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6554 top1= 80.8093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4538 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7810 top1= 44.2508

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2847 top1= 90.9375
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1911 top1= 94.2188
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1985 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5324 top1= 86.6186


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8771 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8005 top1= 45.8634

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1542 top1= 95.3125
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1102 top1= 96.7188
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1485 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4246 top1= 87.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1786 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9095 top1= 46.4042

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1353 top1= 95.9375
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0844 top1= 97.5000
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1195 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3583 top1= 88.8522


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7590 top1= 51.9631


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4980 top1= 48.7280

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1103 top1= 96.8750
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0672 top1= 98.2812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0951 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3168 top1= 89.9439


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6298 top1= 53.9062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3707 top1= 50.8013

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0838 top1= 97.8125
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0501 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0722 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2950 top1= 90.4547


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6258 top1= 55.3786


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1924 top1= 54.2067

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0618 top1= 98.7500
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0348 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0567 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2939 top1= 90.2945


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6810 top1= 56.5505


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1329 top1= 55.9696

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0450 top1= 99.0625
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0256 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0456 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2782 top1= 90.7853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4608 top1= 58.3934


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2347 top1= 55.9696

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0363 top1= 98.9062
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0256 top1= 99.2188
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0402 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2801 top1= 90.9756


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4328 top1= 59.4251


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5370 top1= 54.5673

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0344 top1= 99.5312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0287 top1= 99.3750
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0440 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2775 top1= 90.8554


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4647 top1= 58.6138


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4508 top1= 56.0797

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0574 top1= 97.9688
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0344 top1= 99.0625
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0371 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2663 top1= 91.3662


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2870 top1= 59.1246


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0798 top1= 58.8341

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0241 top1= 99.2188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0306 top1= 98.9062
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0380 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2582 top1= 91.2961


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2045 top1= 61.1278


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1060 top1= 59.4551

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0357 top1= 99.2188
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0228 top1= 99.2188
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0277 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2499 top1= 91.7268


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0977 top1= 62.9908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1949 top1= 56.8209

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0228 top1= 99.5312
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0168 top1= 99.6875
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0131 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2415 top1= 92.0773


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8711 top1= 64.1226


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0951 top1= 59.5152

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0128 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0146 top1= 99.5312
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0242 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2245 top1= 92.8486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4422 top1= 61.5785


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6550 top1= 64.0925

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0074 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0058 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0142 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2271 top1= 92.9688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8106 top1= 65.5649


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5673 top1= 65.7752

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0065 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0070 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2281 top1= 92.9187


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6109 top1= 67.3177


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5883 top1= 67.7384

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0084 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0038 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2213 top1= 93.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5367 top1= 67.9587


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4912 top1= 68.2392

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0057 top1= 99.8438
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0035 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2154 top1= 93.4796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4487 top1= 69.5613


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3079 top1= 70.8433

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2177 top1= 93.3994


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4160 top1= 70.2925


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2851 top1= 72.0653

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2184 top1= 93.4495


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4059 top1= 70.8934


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2466 top1= 73.0869

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2196 top1= 93.4696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3573 top1= 71.7248


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1910 top1= 74.3189

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2208 top1= 93.5296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3176 top1= 72.4960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1703 top1= 74.9099

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2214 top1= 93.5597


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2828 top1= 73.1971


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1477 top1= 75.4207

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2220 top1= 93.6699


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2516 top1= 73.6779


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1370 top1= 75.8914

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2225 top1= 93.7099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2231 top1= 74.0885


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1236 top1= 76.3522

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2232 top1= 93.7500


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1978 top1= 74.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1128 top1= 76.7628

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2237 top1= 93.7400


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1734 top1= 75.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1036 top1= 77.0733

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2242 top1= 93.7700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1524 top1= 75.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0950 top1= 77.3337

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2246 top1= 93.7901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1320 top1= 75.7712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0879 top1= 77.6042

