
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7faf0771d2b0>

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: 1.4851 top1= 48.4375
[E 1B20 |  14784/60000 ( 25%) ] Loss: 1.0066 top1= 68.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4801 top1= 77.3638


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6438 top1= 48.1470


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5597 top1= 42.3978

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.6732 top1= 78.4375
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.6043 top1= 79.2188
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.4776 top1= 84.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0901 top1= 82.3417


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3261 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9599 top1= 44.1006

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.3463 top1= 88.4375
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2991 top1= 90.1562
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.3328 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9716 top1= 81.9111


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5952 top1= 49.6094


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4180 top1= 44.7416

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2691 top1= 91.0938
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.2057 top1= 94.2188
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2375 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8564 top1= 82.9127


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0283 top1= 49.7296


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9374 top1= 45.1022

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2086 top1= 93.2812
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.2142 top1= 93.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2386 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8560 top1= 83.2232


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0599 top1= 49.9099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5657 top1= 45.4127

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1974 top1= 93.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1492 top1= 95.6250
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1900 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8097 top1= 83.7440


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1426 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8883 top1= 45.7031

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1670 top1= 94.5312
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1490 top1= 95.3125
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1911 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7865 top1= 84.1346


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1976 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9849 top1= 45.9034

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1616 top1= 95.0000
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1167 top1= 96.4062
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1420 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7622 top1= 84.2448


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2542 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1040 top1= 46.1138

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1421 top1= 96.0938
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1128 top1= 97.0312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1413 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7418 top1= 84.5853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3103 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1738 top1= 46.2139

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1181 top1= 96.8750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1004 top1= 97.5000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1225 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7140 top1= 85.1062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4809 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3406 top1= 46.3942

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1115 top1= 97.1875
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1008 top1= 97.0312
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1847 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7518 top1= 85.3365


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4138 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5884 top1= 46.4143

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1087 top1= 97.1875
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0874 top1= 97.8125
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1050 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7165 top1= 84.9559


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4763 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9676 top1= 46.5345

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1084 top1= 97.1875
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0833 top1= 97.8125
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1024 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6893 top1= 85.3065


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6079 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1816 top1= 46.5845

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0997 top1= 97.3438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0716 top1= 98.2812
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0854 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6865 top1= 85.3966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5774 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2567 top1= 46.6647

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0875 top1= 97.8125
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0678 top1= 97.9688
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0881 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6757 top1= 85.3165


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5766 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3282 top1= 46.7648

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0889 top1= 97.5000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0618 top1= 98.4375
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0795 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6503 top1= 85.8173


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7375 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4700 top1= 46.8249

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0779 top1= 97.8125
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0550 top1= 98.2812
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0782 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6514 top1= 85.7572


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6583 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4906 top1= 46.8950

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0742 top1= 98.2812
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0517 top1= 98.5938
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0699 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6490 top1= 85.4267


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6812 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5336 top1= 46.8850

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0754 top1= 97.8125
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0470 top1= 99.0625
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0640 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6219 top1= 86.1278


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8443 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6110 top1= 46.9551

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0688 top1= 98.1250
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0488 top1= 98.5938
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0575 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6208 top1= 86.4383


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8190 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6272 top1= 46.9952

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0706 top1= 98.5938
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0412 top1= 98.7500
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0572 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6250 top1= 85.5369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7718 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6761 top1= 46.9952

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0736 top1= 97.8125
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0412 top1= 98.9062
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0525 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5999 top1= 86.3482


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9230 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7825 top1= 47.0252

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0632 top1= 98.1250
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0316 top1= 99.3750
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0558 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5990 top1= 86.5385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8949 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7902 top1= 47.1054

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0569 top1= 98.7500
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0301 top1= 99.0625
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0499 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5981 top1= 85.8674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8852 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7871 top1= 47.1554

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0574 top1= 98.5938
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0285 top1= 99.3750
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0429 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5811 top1= 86.4683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0526 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9215 top1= 47.1054

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0481 top1= 98.7500
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0337 top1= 99.0625
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0414 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5861 top1= 86.3081


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0161 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9442 top1= 47.1655

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0519 top1= 98.9062
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0265 top1= 99.6875
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0413 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5805 top1= 86.1679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0156 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9236 top1= 47.1955

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0493 top1= 99.2188
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0260 top1= 99.5312
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0354 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5636 top1= 86.5485


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1265 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0419 top1= 47.2155

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0464 top1= 98.9062
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0260 top1= 99.3750
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0472 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5654 top1= 86.7188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1165 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0677 top1= 47.2055

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0492 top1= 99.0625
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0218 top1= 99.5312
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0382 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5632 top1= 86.3281


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1234 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0568 top1= 47.2656

