
=== 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 0x7f8f4d35a490>

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: 1.0424 top1= 62.1875
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3940 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6937 top1= 76.6627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5581 top1= 49.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2920 top1= 44.0905

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2771 top1= 90.9375
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1959 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2037 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5283 top1= 81.9712


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5949 top1= 51.6126


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3071 top1= 45.9736

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1600 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1195 top1= 97.0312
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1551 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4083 top1= 86.3782


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3937 top1= 54.6374


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8249 top1= 46.7648

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1308 top1= 95.3125
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0873 top1= 97.6562
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1218 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3496 top1= 88.3614


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3246 top1= 56.4804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5278 top1= 48.7981

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0985 top1= 97.3438
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0633 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0950 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3191 top1= 89.1126


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3348 top1= 57.5521


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4619 top1= 51.1719

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0753 top1= 98.4375
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0499 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0743 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3045 top1= 89.5833


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3448 top1= 58.3534


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5145 top1= 52.3738

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0671 top1= 98.4375
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0385 top1= 99.0625
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0622 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2977 top1= 89.8037


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3325 top1= 58.8542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6039 top1= 52.8245

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0625 top1= 98.2812
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0408 top1= 98.7500
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0529 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3136 top1= 89.1026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3367 top1= 59.6554


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6000 top1= 53.0849

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1023 top1= 96.8750
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0355 top1= 98.7500
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0639 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3108 top1= 89.2528


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2268 top1= 61.0377


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7143 top1= 52.0633

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0572 top1= 98.9062
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0208 top1= 99.6875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0296 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2580 top1= 91.6166


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2416 top1= 61.6987


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2519 top1= 55.4788

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0248 top1= 99.0625
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0190 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0286 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2551 top1= 91.5966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0436 top1= 62.8506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0948 top1= 57.1514

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0202 top1= 99.6875
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0204 top1= 99.3750
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0200 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2466 top1= 91.9772


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8569 top1= 64.4030


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8313 top1= 60.0861

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0193 top1= 99.5312
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0119 top1= 99.8438
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0118 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2559 top1= 91.7468


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6992 top1= 66.0256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7108 top1= 63.1811

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0121 top1= 99.8438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0082 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0079 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2377 top1= 92.3377


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7843 top1= 66.0156


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7308 top1= 63.4816

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0083 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0080 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0085 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2316 top1= 92.6783


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6351 top1= 66.9171


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7791 top1= 62.9708

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0060 top1= 99.8438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2256 top1= 93.0889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7367 top1= 66.9271


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5614 top1= 66.7167

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0041 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0045 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2304 top1= 93.0889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6334 top1= 67.9688


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5006 top1= 68.1691

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0034 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2343 top1= 93.1390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6070 top1= 68.2292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4688 top1= 69.1707

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0052 top1= 99.8438
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0050 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2345 top1= 93.1390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5934 top1= 68.6699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4001 top1= 70.5729

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2362 top1= 93.2292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6071 top1= 69.1206


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3915 top1= 71.2440

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0041 top1= 99.8438
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2359 top1= 93.3494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2642 top1= 72.9567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3586 top1= 71.9752

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2332 top1= 93.4796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2882 top1= 72.0753


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2978 top1= 73.1170

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2382 top1= 93.2993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3098 top1= 72.2857


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2822 top1= 73.8181

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2364 top1= 93.4095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2869 top1= 72.4960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2577 top1= 74.2087

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0037 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2402 top1= 93.3494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1512 top1= 74.7396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2586 top1= 74.4491

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0043 top1= 99.8438
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2302 top1= 93.5296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2226 top1= 73.5978


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2230 top1= 75.1603

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0053 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2391 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2444 top1= 74.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2063 top1= 75.6711

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2344 top1= 93.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0293 top1= 77.2736


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2023 top1= 75.7312

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0014 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=0.2331 top1= 93.4696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0291 top1= 77.3237


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1882 top1= 76.1418

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2332 top1= 93.5096


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9752 top1= 78.2652


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1805 top1= 76.2620

