
=== 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 0x7f7f9be5c490>

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: 1.0340 top1= 61.4062
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3923 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6741 top1= 80.5789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1413 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3482 top1= 44.2608

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2863 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1927 top1= 94.0625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1987 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5891 top1= 85.9075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6998 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7464 top1= 45.8033

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1577 top1= 94.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1058 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1353 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4909 top1= 87.0593


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3167 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3266 top1= 46.2740

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1246 top1= 96.5625
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0776 top1= 98.2812
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0997 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4204 top1= 88.3814


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9759 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9052 top1= 46.5244

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0863 top1= 97.5000
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0593 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0721 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3646 top1= 89.0024


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6825 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5850 top1= 46.5745

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0669 top1= 98.5938
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0427 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0529 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3280 top1= 89.7536


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3859 top1= 50.8514


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3269 top1= 46.8550

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0537 top1= 98.9062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0335 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0395 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3067 top1= 90.1643


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2111 top1= 51.9732


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2137 top1= 47.5160

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0434 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0262 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0326 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2905 top1= 90.6050


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0793 top1= 53.4655


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1188 top1= 48.2372

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0315 top1= 99.5312
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0213 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0257 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2875 top1= 90.7151


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0123 top1= 54.5873


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9535 top1= 49.1286

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0277 top1= 99.2188
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0229 top1= 99.6875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0259 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2785 top1= 90.9756


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9814 top1= 55.6490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9226 top1= 50.2304

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0228 top1= 99.3750
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0156 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0387 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2882 top1= 90.2845


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0879 top1= 56.1498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7749 top1= 52.6843

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0445 top1= 98.2812
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0189 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0379 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2745 top1= 90.8554


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8077 top1= 57.1014


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8382 top1= 51.6026

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0185 top1= 99.3750
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0196 top1= 99.8438
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0232 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2499 top1= 91.8069


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9420 top1= 56.7308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7953 top1= 52.4940

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0131 top1= 99.6875
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0170 top1= 99.5312
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0136 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2457 top1= 92.0773


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8148 top1= 57.5821


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6637 top1= 53.4956

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0191 top1= 99.0625
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0132 top1= 99.8438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0235 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2430 top1= 92.1875


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0379 top1= 57.1615


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3599 top1= 55.9095

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0125 top1= 99.6875
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0157 top1= 99.5312
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0187 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2419 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6848 top1= 59.1847


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2906 top1= 57.8025

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0099 top1= 99.6875
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0082 top1= 99.8438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0248 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2489 top1= 92.1174


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3061 top1= 61.0877


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1558 top1= 58.2532

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0088 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0106 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0097 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2404 top1= 92.2476


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1347 top1= 61.3081


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1205 top1= 59.7256

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0107 top1= 99.8438
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0091 top1= 99.8438
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0059 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2279 top1= 92.8085


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1324 top1= 61.4884


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2101 top1= 58.1631

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0066 top1= 99.8438
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0045 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0060 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2214 top1= 93.0889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2439 top1= 62.2897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8545 top1= 62.3598

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2231 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8867 top1= 63.9824


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7879 top1= 64.0725

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2207 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8661 top1= 64.7436


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7074 top1= 65.3846

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2193 top1= 93.3494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8323 top1= 65.1442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6657 top1= 66.3161

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2204 top1= 93.3293


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7402 top1= 66.2961


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6372 top1= 67.1875

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: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2212 top1= 93.3594


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7188 top1= 66.9171


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6063 top1= 67.9587

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2219 top1= 93.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6710 top1= 67.8285


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5802 top1= 68.6799

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2223 top1= 93.4595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6504 top1= 68.2292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5558 top1= 69.2708

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2228 top1= 93.4796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6207 top1= 68.7600


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5331 top1= 69.9219

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2229 top1= 93.5296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5977 top1= 69.1907


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5107 top1= 70.3325

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2234 top1= 93.5497


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5727 top1= 69.5613


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4932 top1= 70.8233

