
=== 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 0x7fd2f7d0c2b0>

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: 1.0482 top1= 62.5000
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3940 top1= 87.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5741 top1= 83.7640


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0661 top1= 49.2488


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2413 top1= 44.2608

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2802 top1= 90.9375
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2018 top1= 93.4375
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2100 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4290 top1= 87.8205


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4864 top1= 52.2736


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6583 top1= 47.0553

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1738 top1= 94.0625
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1230 top1= 97.0312
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1549 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3499 top1= 89.1426


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2983 top1= 55.3085


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4295 top1= 49.7897

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1383 top1= 95.6250
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0924 top1= 97.5000
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1205 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3089 top1= 90.2244


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3106 top1= 56.7208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2931 top1= 51.5525

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1092 top1= 96.4062
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0681 top1= 98.2812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1014 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2890 top1= 90.4147


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3217 top1= 57.7524


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1556 top1= 54.8878

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0805 top1= 97.9688
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0509 top1= 98.5938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0732 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2818 top1= 90.7252


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3140 top1= 58.8141


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9841 top1= 58.2432

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0643 top1= 98.2812
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0403 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0549 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2718 top1= 91.0056


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3086 top1= 59.6655


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9339 top1= 60.1562

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0558 top1= 98.9062
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0336 top1= 99.3750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0483 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2685 top1= 91.1058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3517 top1= 59.9159


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0265 top1= 59.6855

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0509 top1= 99.0625
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0212 top1= 99.8438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0374 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2591 top1= 91.3361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2698 top1= 61.1779


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0651 top1= 58.1130

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0575 top1= 98.5938
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0302 top1= 98.9062
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0316 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2661 top1= 91.4062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1695 top1= 61.8590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0214 top1= 58.8041

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0577 top1= 98.2812
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0200 top1= 99.6875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0332 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2518 top1= 91.7969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7670 top1= 64.7035


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8629 top1= 60.5268

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0217 top1= 99.2188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0191 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0212 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2485 top1= 91.8570


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9433 top1= 64.9940


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0214 top1= 58.4736

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0509 top1= 98.4375
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0132 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0100 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2428 top1= 92.2576


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7024 top1= 66.5164


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8535 top1= 61.9992

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0225 top1= 99.0625
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0165 top1= 99.5312
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0111 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2438 top1= 92.3978


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7637 top1= 67.1074


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0542 top1= 61.2580

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0125 top1= 99.8438
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0099 top1= 99.8438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0180 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2248 top1= 93.0088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5315 top1= 68.9002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4011 top1= 68.2792

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0099 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0074 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0106 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2287 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5263 top1= 69.2208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4384 top1= 69.5813

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0089 top1= 99.8438
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0083 top1= 99.8438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2290 top1= 93.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3624 top1= 71.0637


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3929 top1= 70.6831

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0067 top1= 99.8438
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0040 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2250 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2824 top1= 71.9451


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2766 top1= 73.4075

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0043 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0064 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2243 top1= 93.4696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3898 top1= 71.2740


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2239 top1= 74.0885

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0043 top1= 99.8438
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2299 top1= 93.4395


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2116 top1= 73.6779


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1321 top1= 75.5909

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0044 top1= 99.8438
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2296 top1= 93.4595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1545 top1= 74.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2229 top1= 74.7396

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2286 top1= 93.4996


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9942 top1= 77.2837


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1140 top1= 76.4323

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2282 top1= 93.6198


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9987 top1= 77.4439


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0848 top1= 76.8830

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2295 top1= 93.6098


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9476 top1= 78.3654


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0610 top1= 77.5841

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2301 top1= 93.6198


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9092 top1= 79.2969


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0486 top1= 77.9347

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2308 top1= 93.6498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8830 top1= 79.9179


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0368 top1= 78.2652

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2311 top1= 93.7300


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8664 top1= 80.2584


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0229 top1= 78.5557

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2315 top1= 93.7600


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8489 top1= 80.6290


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0092 top1= 78.9062

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2320 top1= 93.7901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8316 top1= 80.9896


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0012 top1= 79.1466

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2324 top1= 93.7901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8145 top1= 81.3702


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9907 top1= 79.3970

