
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f78eb9489d0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0620 top1= 64.3750
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2776 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6807 top1= 79.2167


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5540 top1= 48.8782


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9633 top1= 43.7901

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3442 top1= 90.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3199 top1= 90.0000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1774 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5368 top1= 86.5485


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5188 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6004 top1= 45.5729

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1621 top1= 96.2500
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1592 top1= 95.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1189 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4728 top1= 86.9491


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2773 top1= 52.5341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3377 top1= 46.8450

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1352 top1= 96.2500
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1178 top1= 95.9375
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0936 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4428 top1= 87.1995


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2078 top1= 52.9147


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2011 top1= 48.0268

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1108 top1= 96.5625
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0984 top1= 96.8750
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0771 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4295 top1= 87.4199


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1875 top1= 53.2853


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1696 top1= 48.4275

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0987 top1= 97.1875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0871 top1= 97.1875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0670 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4249 top1= 87.6603


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1752 top1= 53.5156


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1543 top1= 48.6879

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0904 top1= 97.5000
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0783 top1= 98.1250
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0633 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4241 top1= 87.6502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1743 top1= 53.3053


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1637 top1= 48.7480

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0874 top1= 98.1250
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0770 top1= 98.1250
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0617 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4298 top1= 87.5401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1538 top1= 52.7945


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1841 top1= 48.4475

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0812 top1= 98.4375
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0784 top1= 97.5000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0623 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4492 top1= 86.5385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1933 top1= 52.2236


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2027 top1= 48.0369

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0824 top1= 97.8125
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0816 top1= 97.1875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0642 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4672 top1= 86.1879


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2237 top1= 51.6727


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2377 top1= 47.6362

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0781 top1= 98.7500
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0810 top1= 97.5000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0701 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4869 top1= 85.8674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2470 top1= 51.2220


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2481 top1= 47.2857

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0865 top1= 98.1250
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0929 top1= 97.1875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0720 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5044 top1= 85.3866


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2440 top1= 50.7913


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3227 top1= 46.6947

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0984 top1= 97.5000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.1044 top1= 96.5625
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0762 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5258 top1= 85.2664


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2503 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3860 top1= 46.0236

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.1150 top1= 96.5625
[E14B10 |   4224/60000 (  7%) ] Loss: 0.1403 top1= 95.3125
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.1136 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5893 top1= 82.9026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2192 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4383 top1= 45.3125

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.1183 top1= 96.5625
[E15B10 |   4224/60000 (  7%) ] Loss: 0.1186 top1= 96.2500
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0929 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5780 top1= 84.5353


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2412 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3521 top1= 45.8634

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.1127 top1= 96.8750
[E16B10 |   4224/60000 (  7%) ] Loss: 0.1363 top1= 95.9375
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0995 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5864 top1= 84.8658


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2335 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4870 top1= 45.3626

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.1359 top1= 96.5625
[E17B10 |   4224/60000 (  7%) ] Loss: 0.1512 top1= 95.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.1015 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6160 top1= 83.6939


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2166 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6533 top1= 44.5713

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.1531 top1= 95.9375
[E18B10 |   4224/60000 (  7%) ] Loss: 0.1955 top1= 93.4375
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1645 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6510 top1= 82.0513


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1887 top1= 49.8798


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5657 top1= 45.2324

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.1248 top1= 95.9375
[E19B10 |   4224/60000 (  7%) ] Loss: 0.1392 top1= 95.6250
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1125 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6318 top1= 83.9944


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2288 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5251 top1= 45.2424

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.1313 top1= 97.1875
[E20B10 |   4224/60000 (  7%) ] Loss: 0.1541 top1= 94.3750
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.1133 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6428 top1= 83.5136


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2258 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6452 top1= 44.3209

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.1762 top1= 94.6875
[E21B10 |   4224/60000 (  7%) ] Loss: 0.1652 top1= 94.0625
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1109 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6407 top1= 83.0729


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1991 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5362 top1= 44.9820

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.1447 top1= 96.2500
[E22B10 |   4224/60000 (  7%) ] Loss: 0.1895 top1= 93.1250
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.1533 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6573 top1= 82.8225


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1644 top1= 49.7496


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5914 top1= 45.4728

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.1123 top1= 98.1250
[E23B10 |   4224/60000 (  7%) ] Loss: 0.1646 top1= 95.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.1376 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6669 top1= 82.6322


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1875 top1= 49.7396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5359 top1= 45.1623

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.1390 top1= 96.8750
[E24B10 |   4224/60000 (  7%) ] Loss: 0.1516 top1= 95.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.1268 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6531 top1= 83.6238


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2012 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6396 top1= 44.9619

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.1529 top1= 96.5625
[E25B10 |   4224/60000 (  7%) ] Loss: 0.1717 top1= 94.3750
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.1191 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6598 top1= 82.9127


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1743 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6098 top1= 44.4411

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.1665 top1= 95.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.1771 top1= 94.0625
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.1163 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6553 top1= 83.3033


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1654 top1= 49.7496


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5596 top1= 44.9519

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.1459 top1= 96.5625
[E27B10 |   4224/60000 (  7%) ] Loss: 0.1862 top1= 93.7500
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.1400 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6803 top1= 81.7608


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1362 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5438 top1= 45.1022

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.1270 top1= 97.1875
[E28B10 |   4224/60000 (  7%) ] Loss: 0.1781 top1= 93.7500
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.1628 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6886 top1= 81.8109


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1573 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4681 top1= 45.0721

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.1233 top1= 97.8125
[E29B10 |   4224/60000 (  7%) ] Loss: 0.1549 top1= 94.3750
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.1418 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6747 top1= 82.8225


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1523 top1= 49.6895


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4592 top1= 45.0321

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.1360 top1= 96.2500
[E30B10 |   4224/60000 (  7%) ] Loss: 0.1660 top1= 94.6875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.1276 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6679 top1= 83.4736


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1631 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6026 top1= 44.5813

