
=== 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 0x7fce7702c2b0>

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: 1.4955 top1= 45.7812
[E 1B20 |  14784/60000 ( 25%) ] Loss: 1.0970 top1= 62.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4600 top1= 77.7644


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6323 top1= 48.0769


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5583 top1= 42.3578

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.7220 top1= 75.3125
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.6035 top1= 78.5938
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.4419 top1= 86.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1024 top1= 82.2516


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3054 top1= 49.3490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9855 top1= 44.0204

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.3476 top1= 89.2188
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.3029 top1= 90.1562
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.3177 top1= 90.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9691 top1= 82.9627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5421 top1= 49.6094


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2976 top1= 44.5913

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2727 top1= 91.0938
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1953 top1= 94.5312
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2312 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8504 top1= 83.6839


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0305 top1= 49.6995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0359 top1= 45.1022

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2142 top1= 93.7500
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.2214 top1= 93.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2107 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8347 top1= 83.8041


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0626 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7885 top1= 45.4127

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1774 top1= 94.5312
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1529 top1= 95.7812
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1923 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8006 top1= 84.7356


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1097 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9385 top1= 45.6731

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1774 top1= 94.6875
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1898 top1= 93.2812
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1996 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8003 top1= 84.4551


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1605 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7745 top1= 45.8734

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1633 top1= 95.6250
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1167 top1= 96.4062
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1420 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7690 top1= 84.4952


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1830 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0108 top1= 46.0337

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1394 top1= 95.7812
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1096 top1= 97.1875
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1428 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7448 top1= 84.7957


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2589 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1067 top1= 46.1939

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1191 top1= 96.8750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0980 top1= 97.5000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1208 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7151 top1= 85.4267


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4334 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3006 top1= 46.3642

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1112 top1= 97.5000
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0911 top1= 97.6562
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1204 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7171 top1= 85.5970


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3944 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2060 top1= 46.4243

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1543 top1= 95.3125
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1306 top1= 96.5625
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1029 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7158 top1= 85.6971


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4537 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9074 top1= 46.5244

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1035 top1= 97.0312
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0786 top1= 97.8125
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1013 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6880 top1= 85.9275


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5712 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1716 top1= 46.5645

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0947 top1= 97.5000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0702 top1= 98.1250
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0854 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6853 top1= 85.8574


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5233 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2757 top1= 46.6246

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0840 top1= 97.6562
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0680 top1= 97.8125
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0868 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6743 top1= 85.8273


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5190 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3308 top1= 46.7248

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0926 top1= 97.0312
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0610 top1= 98.4375
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0782 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6511 top1= 86.2480


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6560 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4590 top1= 46.8049

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0747 top1= 97.9688
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0520 top1= 98.5938
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0749 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6499 top1= 86.3882


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6212 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4777 top1= 46.8850

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0691 top1= 98.2812
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0481 top1= 98.5938
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0677 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6477 top1= 85.9776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6548 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5391 top1= 46.8950

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0728 top1= 97.8125
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0477 top1= 99.0625
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0640 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6218 top1= 86.7388


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8050 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6007 top1= 46.9151

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0631 top1= 98.4375
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0484 top1= 98.4375
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0565 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6211 top1= 86.8389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7980 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6202 top1= 46.9752

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0667 top1= 98.4375
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0404 top1= 98.9062
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0580 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6224 top1= 86.2580


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7593 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6833 top1= 47.0553

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0708 top1= 97.6562
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0421 top1= 98.7500
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0501 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5999 top1= 86.9692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8527 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7723 top1= 47.0653

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0570 top1= 98.2812
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0310 top1= 99.2188
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0502 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5973 top1= 87.0292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8465 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7868 top1= 47.0853

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0506 top1= 98.5938
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0292 top1= 99.2188
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0460 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5968 top1= 86.6687


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8464 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8034 top1= 47.1154

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0508 top1= 98.7500
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0308 top1= 99.3750
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0421 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5786 top1= 87.0493


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0167 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9226 top1= 47.1554

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0432 top1= 98.9062
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0300 top1= 98.7500
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0373 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5795 top1= 87.0493


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0188 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9244 top1= 47.1554

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0458 top1= 98.9062
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0245 top1= 99.5312
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0382 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5774 top1= 86.9992


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0032 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9207 top1= 47.1955

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0443 top1= 99.0625
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0251 top1= 99.5312
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0320 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5621 top1= 87.3197


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1113 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0455 top1= 47.1554

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0406 top1= 98.7500
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0246 top1= 99.5312
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0418 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5613 top1= 87.3998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0975 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0559 top1= 47.2256

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0424 top1= 99.0625
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0210 top1= 99.3750
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0355 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5605 top1= 87.1895


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1199 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0711 top1= 47.2656

