
=== 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 0x7f3578790490>

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: 1.0403 top1= 61.8750
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3925 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6283 top1= 82.1114


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4384 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9718 top1= 44.2408

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2797 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1955 top1= 94.2188
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1997 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4744 top1= 87.2596


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0325 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0440 top1= 45.9535

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1576 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1171 top1= 97.3438
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1551 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3803 top1= 88.6118


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7943 top1= 51.4323


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6925 top1= 47.7264

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1366 top1= 95.7812
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0863 top1= 97.5000
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1165 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3360 top1= 89.4431


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6322 top1= 53.3954


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4055 top1= 50.3305

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1051 top1= 97.5000
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0608 top1= 98.5938
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0931 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3099 top1= 89.8337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6343 top1= 54.6975


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2967 top1= 52.5240

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0801 top1= 98.2812
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0458 top1= 99.0625
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0676 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2963 top1= 90.2845


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6066 top1= 55.8293


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1083 top1= 55.6691

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0617 top1= 98.7500
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0365 top1= 99.0625
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0561 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2908 top1= 90.5248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6249 top1= 57.0312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0582 top1= 57.0312

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0462 top1= 99.0625
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0291 top1= 99.8438
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0451 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2861 top1= 90.5148


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5097 top1= 58.4736


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3922 top1= 53.9964

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0483 top1= 98.5938
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0283 top1= 99.2188
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0677 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2815 top1= 90.4948


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1814 top1= 59.8858


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3953 top1= 55.3185

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0645 top1= 97.8125
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0390 top1= 98.4375
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0487 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2599 top1= 91.2159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2439 top1= 59.7356


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1999 top1= 57.5220

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0181 top1= 99.5312
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0187 top1= 99.5312
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0204 top1= 99.3750

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


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1110 top1= 60.8774


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1716 top1= 55.6591

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0240 top1= 99.6875
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0153 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0128 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2412 top1= 92.1575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2213 top1= 61.7889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1431 top1= 58.0529

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0247 top1= 99.2188
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0122 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0135 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2521 top1= 91.6667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8249 top1= 64.0224


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1978 top1= 57.9527

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0218 top1= 99.2188
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0123 top1= 99.8438
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0163 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2369 top1= 92.5581


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8963 top1= 64.1226


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7699 top1= 63.5917

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0094 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0123 top1= 99.8438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0096 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2363 top1= 92.6683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7473 top1= 65.1943


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7199 top1= 64.1827

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0093 top1= 99.6875
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0051 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0141 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2480 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6386 top1= 66.7668


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7971 top1= 64.2027

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0170 top1= 99.3750
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0046 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0059 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2440 top1= 92.4880


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6220 top1= 67.2676


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7751 top1= 65.3245

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0139 top1= 99.5312
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0045 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0060 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2364 top1= 92.8586


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5539 top1= 68.5998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5937 top1= 67.9988

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0038 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2389 top1= 92.9287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4942 top1= 69.5012


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4952 top1= 70.0421

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0030 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0057 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2283 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4914 top1= 69.9018


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3791 top1= 71.2540

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2282 top1= 93.3193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4343 top1= 70.8133


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3191 top1= 72.2656

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2310 top1= 93.3994


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4057 top1= 71.4543


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3351 top1= 72.9567

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: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2317 top1= 93.4495


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3718 top1= 72.0553


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2672 top1= 74.1486

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2334 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3326 top1= 72.7564


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2553 top1= 74.6595

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2341 top1= 93.4996


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3003 top1= 73.3774


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2258 top1= 75.2404

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0012 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=0.2349 top1= 93.5096


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2673 top1= 74.0084


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2167 top1= 75.5108

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0011 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=0.2354 top1= 93.5397


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2384 top1= 74.5192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2020 top1= 75.8514

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0011 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=0.2360 top1= 93.5897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2131 top1= 74.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1935 top1= 76.1418

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2365 top1= 93.6398


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1888 top1= 75.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1823 top1= 76.4123

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=0.2369 top1= 93.6398


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1671 top1= 75.8113


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1721 top1= 76.6827

