
=== 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 0x7f42cf863490>

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: 1.4163 top1= 52.5000
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8649 top1= 71.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3743 top1= 77.0533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1519 top1= 48.4175


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9348 top1= 42.7784

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5297 top1= 83.2812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.3848 top1= 88.1250
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3685 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0308 top1= 82.2115


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8313 top1= 49.5092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6564 top1= 44.4912

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2912 top1= 91.0938
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2354 top1= 93.1250
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2704 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9174 top1= 82.8726


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1435 top1= 49.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0389 top1= 44.8518

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2533 top1= 91.7188
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1784 top1= 94.6875
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2244 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8197 top1= 83.3634


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5798 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5851 top1= 45.2624

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2210 top1= 93.9062
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1676 top1= 95.0000
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2325 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8026 top1= 83.5036


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5238 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3575 top1= 45.3726

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.2013 top1= 93.5938
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1516 top1= 95.7812
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1860 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7794 top1= 83.6939


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5699 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3256 top1= 45.6931

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1734 top1= 94.6875
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1371 top1= 95.4688
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1752 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7307 top1= 84.6154


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7498 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5927 top1= 46.0236

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1453 top1= 95.7812
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1215 top1= 96.0938
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1474 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7243 top1= 84.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7157 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4730 top1= 46.1138

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1621 top1= 95.3125
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1168 top1= 96.2500
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1385 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7050 top1= 85.7372


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7174 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5221 top1= 46.2240

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1263 top1= 96.4062
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1044 top1= 97.0312
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1228 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6787 top1= 85.6470


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8899 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6943 top1= 46.3842

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1187 top1= 97.0312
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0942 top1= 97.5000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1359 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6786 top1= 85.9075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8099 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5332 top1= 46.3742

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1075 top1= 97.0312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0876 top1= 97.1875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1036 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6643 top1= 86.3782


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8266 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5563 top1= 46.5345

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1259 top1= 95.7812
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0815 top1= 97.5000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1041 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6408 top1= 86.4583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9470 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6979 top1= 46.5144

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0948 top1= 97.9688
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0765 top1= 97.6562
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0869 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6461 top1= 86.6086


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8925 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6392 top1= 46.5545

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0937 top1= 97.3438
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0721 top1= 97.8125
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0904 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6338 top1= 86.8590


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9009 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6829 top1= 46.6947

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0848 top1= 97.3438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0659 top1= 98.2812
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0764 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6112 top1= 87.0893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0356 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8477 top1= 46.7047

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0895 top1= 97.3438
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0573 top1= 98.1250
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0841 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6115 top1= 87.3097


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9455 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7490 top1= 46.7949

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0782 top1= 97.9688
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0577 top1= 98.1250
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0645 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6108 top1= 86.7989


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9865 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8244 top1= 46.8249

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0717 top1= 97.8125
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0497 top1= 98.4375
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0619 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5880 top1= 87.3698


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0855 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9374 top1= 46.9651

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0743 top1= 98.2812
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0642 top1= 97.6562
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0580 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5851 top1= 87.8105


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0505 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9234 top1= 46.9852

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0739 top1= 97.8125
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0537 top1= 98.2812
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0581 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5861 top1= 87.1194


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0193 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9659 top1= 46.8750

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0658 top1= 98.2812
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0448 top1= 98.5938
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0452 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5632 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1678 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0616 top1= 46.9952

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0598 top1= 98.4375
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0516 top1= 98.5938
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0546 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5642 top1= 87.9908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1238 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0448 top1= 47.0252

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0542 top1= 98.9062
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0365 top1= 98.7500
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0557 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5680 top1= 87.2496


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0989 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0820 top1= 47.0152

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0628 top1= 98.7500
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0334 top1= 98.7500
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0393 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5478 top1= 87.8906


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2641 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2406 top1= 47.0353

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0428 top1= 99.2188
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0487 top1= 98.1250
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0378 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5508 top1= 87.6703


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2711 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1958 top1= 47.0653

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0471 top1= 98.9062
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0341 top1= 98.5938
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0597 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5503 top1= 87.4399


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2308 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1870 top1= 47.1254

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0416 top1= 99.2188
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0261 top1= 99.5312
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0300 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5320 top1= 88.0208


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3220 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3511 top1= 47.0954

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0411 top1= 98.9062
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0387 top1= 98.1250
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0555 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5375 top1= 87.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3340 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3320 top1= 47.1154

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0502 top1= 98.4375
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0230 top1= 99.3750
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0356 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5383 top1= 87.5000


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3018 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3230 top1= 47.2055

