
=== 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.Dumbbell object at 0x7ff12b9fb490>

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: 1.0413 top1= 61.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3926 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7355 top1= 78.0849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2193 top1= 49.2588


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1709 top1= 44.0905

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2838 top1= 90.6250
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1928 top1= 94.0625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1949 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6653 top1= 84.4451


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9309 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7660 top1= 45.7732

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1612 top1= 95.3125
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1153 top1= 96.7188
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1391 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5928 top1= 85.5869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6095 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4341 top1= 46.2740

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1312 top1= 95.6250
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0848 top1= 97.6562
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1075 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5231 top1= 86.8289


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4916 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3083 top1= 46.4143

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0953 top1= 97.5000
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0685 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0812 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4720 top1= 87.8806


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3793 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2301 top1= 46.5244

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0707 top1= 98.4375
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0500 top1= 98.5938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0618 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4279 top1= 88.5216


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3850 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2389 top1= 46.6747

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0557 top1= 98.9062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0394 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0442 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3963 top1= 88.9824


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3998 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2919 top1= 46.6847

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0451 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0327 top1= 99.2188
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0347 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3690 top1= 89.4631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3634 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3528 top1= 46.6747

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0378 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0274 top1= 99.0625
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0272 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3524 top1= 89.8538


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3482 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4214 top1= 46.7648

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0329 top1= 99.3750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0236 top1= 99.6875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0242 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3453 top1= 89.7636


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3299 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2949 top1= 46.7548

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0280 top1= 99.3750
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0228 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0212 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3428 top1= 89.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2299 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0693 top1= 46.5345

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0261 top1= 99.3750
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0170 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0386 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3176 top1= 90.3345


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2502 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8580 top1= 46.8550

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0202 top1= 99.5312
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0271 top1= 99.2188
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0380 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3204 top1= 90.1342


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1921 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8665 top1= 46.7849

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0306 top1= 99.2188
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0183 top1= 99.6875
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0377 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3574 top1= 88.0208


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0203 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9780 top1= 46.3241

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0610 top1= 97.6562
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0214 top1= 99.3750
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0190 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3097 top1= 90.1242


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7116 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8167 top1= 46.9451

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0131 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0285 top1= 98.7500
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0192 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2936 top1= 90.8854


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6003 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8568 top1= 46.9952

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0132 top1= 99.6875
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0167 top1= 99.6875
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0144 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2995 top1= 90.3846


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6446 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7395 top1= 47.1554

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0152 top1= 99.6875
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0143 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0167 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3178 top1= 89.8738


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5990 top1= 49.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6812 top1= 47.1755

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0230 top1= 99.2188
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0096 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0249 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3012 top1= 90.1943


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1467 top1= 50.8213


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5977 top1= 47.2256

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0106 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0138 top1= 99.5312
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0151 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2860 top1= 90.8153


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4349 top1= 50.7913


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3659 top1= 46.8450

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0232 top1= 99.2188
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0078 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0172 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2916 top1= 90.4948


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2866 top1= 51.0016


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4207 top1= 46.7648

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0198 top1= 99.6875
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0102 top1= 99.8438
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0153 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2880 top1= 90.6150


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5164 top1= 50.8614


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2607 top1= 47.4459

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0089 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0146 top1= 99.3750
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0114 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2706 top1= 91.1058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4484 top1= 50.8914


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3658 top1= 47.8566

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0099 top1= 99.8438
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0067 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0065 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2784 top1= 90.4147


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3954 top1= 50.9315


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4645 top1= 47.4359

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0103 top1= 99.6875
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0043 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0066 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2747 top1= 90.6550


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3839 top1= 50.9916


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4198 top1= 47.8065

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0057 top1= 99.8438
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2802 top1= 90.6150


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3941 top1= 51.0617


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2992 top1= 47.9067

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0078 top1= 99.8438
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0048 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0055 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2761 top1= 90.9355


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4059 top1= 51.1518


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2557 top1= 48.3073

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0074 top1= 99.8438
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0044 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0078 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2603 top1= 91.1258


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4238 top1= 51.1819


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5554 top1= 47.5060

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0037 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2529 top1= 91.6767


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4186 top1= 51.2320


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3629 top1= 48.1270

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0042 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0037 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2528 top1= 91.6867


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4084 top1= 51.3121


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4262 top1= 48.0769

