
=== 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 0x7f097c2952b0>

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: 1.0681 top1= 61.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3947 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6824 top1= 81.3001


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9430 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3204 top1= 44.2408

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2744 top1= 90.0000
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1989 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2038 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5694 top1= 86.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4615 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4507 top1= 45.8333

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1675 top1= 94.5312
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1232 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1605 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4783 top1= 87.3397


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1338 top1= 49.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0330 top1= 46.2440

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1422 top1= 95.3125
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1031 top1= 97.0312
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1287 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4284 top1= 87.9107


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9421 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8076 top1= 46.6446

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1226 top1= 96.5625
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0868 top1= 97.1875
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1062 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3945 top1= 88.5717


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8332 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7469 top1= 47.2756

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1071 top1= 96.7188
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0725 top1= 97.9688
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0900 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3752 top1= 89.1627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7965 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7245 top1= 47.7965

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0967 top1= 97.0312
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0627 top1= 98.4375
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0797 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3654 top1= 89.3429


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7756 top1= 50.7712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6845 top1= 48.0569

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0862 top1= 97.8125
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0580 top1= 98.5938
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0738 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3596 top1= 89.2528


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7665 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6468 top1= 48.1871

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0797 top1= 98.2812
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0561 top1= 98.7500
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0720 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3542 top1= 89.6534


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7521 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7038 top1= 47.7965

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0773 top1= 98.2812
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0513 top1= 98.9062
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0689 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3540 top1= 89.8438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7284 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7160 top1= 47.7364

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0736 top1= 98.4375
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0510 top1= 99.0625
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0678 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3580 top1= 89.7736


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7325 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7420 top1= 47.3858

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0706 top1= 98.9062
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0498 top1= 99.3750
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0639 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3628 top1= 89.6935


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7310 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7232 top1= 47.4058

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0633 top1= 99.2188
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0501 top1= 99.3750
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0633 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3883 top1= 88.9623


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7334 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7150 top1= 47.8766

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0718 top1= 98.4375
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0582 top1= 98.9062
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0685 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4016 top1= 88.7921


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7150 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7655 top1= 47.3257

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0675 top1= 99.0625
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0587 top1= 99.0625
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0930 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4277 top1= 88.3113


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7243 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7255 top1= 46.9852

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0798 top1= 98.2812
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0710 top1= 97.9688
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1010 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4217 top1= 88.9824


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7053 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8185 top1= 46.8049

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0790 top1= 98.4375
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0789 top1= 97.9688
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0727 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4393 top1= 88.2412


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6968 top1= 49.6294


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8335 top1= 46.5445

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1004 top1= 96.8750
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0718 top1= 98.4375
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0916 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4537 top1= 88.5317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5717 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7015 top1= 46.7348

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0842 top1= 97.9688
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0611 top1= 99.2188
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0887 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4506 top1= 89.1627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6172 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7227 top1= 46.8149

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0670 top1= 98.5938
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0595 top1= 99.0625
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0819 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4604 top1= 89.0224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6435 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7482 top1= 46.7047

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0751 top1= 98.4375
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0684 top1= 98.4375
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0812 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4779 top1= 88.4014


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6245 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6910 top1= 46.6246

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0934 top1= 97.5000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0769 top1= 98.1250
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0850 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5028 top1= 87.4399


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6663 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7331 top1= 46.3241

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1136 top1= 96.8750
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0893 top1= 97.3438
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1303 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5188 top1= 87.2496


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6469 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6979 top1= 46.3442

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1110 top1= 96.5625
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0929 top1= 97.3438
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0976 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5184 top1= 87.2196


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6381 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8561 top1= 46.0737

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1151 top1= 96.0938
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0790 top1= 98.2812
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0888 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5214 top1= 87.6803


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6429 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8426 top1= 46.2941

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0967 top1= 97.1875
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0769 top1= 98.2812
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0894 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5361 top1= 87.0593


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6639 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7592 top1= 46.4443

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0880 top1= 97.3438
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0818 top1= 97.9688
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0921 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5496 top1= 86.2580


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6609 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7942 top1= 46.4042

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0885 top1= 98.1250
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0795 top1= 98.4375
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0977 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5650 top1= 85.4467


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6424 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7649 top1= 46.2440

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0912 top1= 98.4375
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0858 top1= 97.9688
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1077 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5591 top1= 85.8474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6115 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8154 top1= 46.2139

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0899 top1= 97.5000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0862 top1= 97.8125
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1089 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5504 top1= 86.5084


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5921 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9536 top1= 46.1438

