
=== 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 0x7fa71bc332b0>

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: 1.0348 top1= 62.0312
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3929 top1= 88.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7009 top1= 79.2668


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1872 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2562 top1= 44.2208

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2785 top1= 91.0938
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1949 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1967 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5935 top1= 85.7772


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6121 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6848 top1= 45.8534

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1601 top1= 94.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1096 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1363 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4978 top1= 86.6486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2136 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1199 top1= 46.3742

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1250 top1= 96.2500
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0810 top1= 97.8125
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1052 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4275 top1= 87.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9541 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8333 top1= 46.5044

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0912 top1= 97.1875
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0612 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0777 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3782 top1= 88.6719


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7682 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5531 top1= 46.5946

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0689 top1= 98.4375
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0441 top1= 98.4375
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0563 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3436 top1= 89.3229


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6251 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4478 top1= 46.8349

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0526 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0348 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0397 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3206 top1= 89.6635


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5171 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3195 top1= 47.3257

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0395 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0276 top1= 99.3750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0293 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3095 top1= 89.9840


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4185 top1= 51.5825


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1953 top1= 47.8566

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0334 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0205 top1=100.0000
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0208 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2856 top1= 90.7352


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3695 top1= 52.1835


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2854 top1= 47.8265

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0326 top1= 99.0625
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0224 top1= 99.0625
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0196 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2764 top1= 90.8053


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3940 top1= 52.4439


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2947 top1= 47.9067

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0342 top1= 99.0625
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0265 top1= 99.0625
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0304 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2744 top1= 90.9155


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3317 top1= 53.0849


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3431 top1= 47.8866

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0403 top1= 98.5938
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0211 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0244 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2761 top1= 90.9756


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3240 top1= 53.7560


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7287 top1= 52.4539

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0245 top1= 99.3750
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0496 top1= 98.4375
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0561 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2896 top1= 89.9038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1156 top1= 54.7776


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0496 top1= 50.1903

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0277 top1= 99.2188
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0180 top1= 99.5312
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0135 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2727 top1= 90.8654


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8026 top1= 56.6607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8441 top1= 51.1619

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0116 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0163 top1= 99.6875
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0177 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2645 top1= 91.2961


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7663 top1= 56.2800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4752 top1= 53.3754

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0132 top1= 99.6875
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0094 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0357 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2710 top1= 91.2460


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5713 top1= 58.0128


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3476 top1= 55.0982

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0131 top1= 99.6875
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0136 top1= 99.6875
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0101 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2526 top1= 91.5966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5664 top1= 57.2216


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7743 top1= 52.7043

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0137 top1= 99.6875
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0049 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0078 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2437 top1= 91.9171


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5157 top1= 57.8526


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4570 top1= 54.6374

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0094 top1= 99.6875
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0090 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2278 top1= 92.6683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2956 top1= 58.9944


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2791 top1= 56.1999

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0099 top1= 99.8438
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0153 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2378 top1= 92.3478


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3155 top1= 59.1647


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1239 top1= 58.1430

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0054 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0032 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2280 top1= 92.6282


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3187 top1= 59.8057


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1095 top1= 59.0144

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2262 top1= 92.6983


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2617 top1= 60.5168


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0826 top1= 59.6554

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0020 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=0.2250 top1= 92.7985


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2179 top1= 60.9876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0334 top1= 60.6971

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2262 top1= 92.7784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1608 top1= 61.6486


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0024 top1= 61.4583

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2270 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1292 top1= 62.2095


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9893 top1= 61.9491

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2274 top1= 92.8986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1042 top1= 62.6402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9609 top1= 62.5000

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2279 top1= 92.9688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0808 top1= 63.0409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9486 top1= 63.0709

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2284 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0618 top1= 63.3213


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9316 top1= 63.5016

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2289 top1= 93.1290


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0417 top1= 63.6919


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9146 top1= 63.9824

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=0.2298 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0247 top1= 63.9323


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9023 top1= 64.5533

