
=== 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 0x7f582e64a9d0>

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: 1.2650 top1= 58.4375
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.3783 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0735 top1= 60.8273


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6302 top1= 48.7179


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7283 top1= 44.1106

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3440 top1= 90.9375
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3431 top1= 89.0625
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2133 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1466 top1= 57.1014


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0591 top1= 49.0585


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7314 top1= 45.0821

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.2415 top1= 94.0625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2644 top1= 93.1250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1871 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1834 top1= 54.6074


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9789 top1= 49.2188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5962 top1= 45.2724

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2275 top1= 93.4375
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2525 top1= 91.8750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1720 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2311 top1= 52.4239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9309 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5652 top1= 45.5429

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.2062 top1= 93.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.2555 top1= 92.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1865 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2478 top1= 52.7244


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8837 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4921 top1= 45.4127

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.2221 top1= 93.4375
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.2724 top1= 92.8125
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1856 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2044 top1= 53.9964


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8531 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5491 top1= 45.2524

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.2193 top1= 94.0625
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.2666 top1= 93.1250
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.2105 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1993 top1= 53.1851


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8298 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6569 top1= 45.1322

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1960 top1= 94.0625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.2585 top1= 92.1875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.1701 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1789 top1= 54.1567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8125 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6332 top1= 45.5429

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.1713 top1= 95.3125
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.2181 top1= 93.7500
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.1742 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2064 top1= 53.5457


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7983 top1= 49.3890


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6053 top1= 45.3826

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1968 top1= 93.4375
[E10B10 |   4224/60000 (  7%) ] Loss: 0.2033 top1= 93.4375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.1948 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1919 top1= 53.1150


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7843 top1= 49.3990


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4017 top1= 45.9535

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.1720 top1= 95.3125
[E11B10 |   4224/60000 (  7%) ] Loss: 0.2213 top1= 93.1250
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.1767 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1661 top1= 54.9679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7734 top1= 49.4291


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6070 top1= 44.5913

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.2421 top1= 92.8125
[E12B10 |   4224/60000 (  7%) ] Loss: 0.2563 top1= 91.8750
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.1860 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1402 top1= 56.4904


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7671 top1= 49.4391


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6777 top1= 43.6599

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.2628 top1= 92.8125
[E13B10 |   4224/60000 (  7%) ] Loss: 0.2506 top1= 93.1250
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.2274 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1246 top1= 57.7624


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7576 top1= 49.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5196 top1= 44.5513

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.2485 top1= 92.1875
[E14B10 |   4224/60000 (  7%) ] Loss: 0.2782 top1= 93.1250
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.1938 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0842 top1= 59.2949


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7544 top1= 49.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6576 top1= 45.5829

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.1870 top1= 93.7500
[E15B10 |   4224/60000 (  7%) ] Loss: 0.2638 top1= 92.5000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.1641 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1262 top1= 56.0497


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7499 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7290 top1= 45.3425

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.2004 top1= 93.4375
[E16B10 |   4224/60000 (  7%) ] Loss: 0.2418 top1= 93.1250
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.1911 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1931 top1= 54.2468


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7421 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6035 top1= 44.7616

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.2332 top1= 92.5000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.2163 top1= 93.7500
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.1801 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1844 top1= 53.6258


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7390 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5878 top1= 45.2624

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.2253 top1= 93.1250
[E18B10 |   4224/60000 (  7%) ] Loss: 0.2300 top1= 92.5000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.2133 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1821 top1= 53.8662


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7351 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5050 top1= 44.8618

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.2462 top1= 92.1875
[E19B10 |   4224/60000 (  7%) ] Loss: 0.2349 top1= 92.5000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1910 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1354 top1= 55.7091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7267 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5988 top1= 45.3025

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.2337 top1= 94.3750
[E20B10 |   4224/60000 (  7%) ] Loss: 0.2530 top1= 92.5000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.2173 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1679 top1= 55.4087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7160 top1= 49.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6662 top1= 43.7901

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.2867 top1= 90.3125
[E21B10 |   4224/60000 (  7%) ] Loss: 0.2506 top1= 92.8125
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.2061 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1229 top1= 56.4704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7079 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5436 top1= 45.0120

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.2335 top1= 92.8125
[E22B10 |   4224/60000 (  7%) ] Loss: 0.2278 top1= 93.4375
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.1825 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1400 top1= 55.4287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6987 top1= 49.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4762 top1= 44.9920

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.2218 top1= 94.0625
[E23B10 |   4224/60000 (  7%) ] Loss: 0.2349 top1= 93.1250
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.2055 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1331 top1= 56.6106


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6989 top1= 49.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4080 top1= 45.2123

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.2203 top1= 93.4375
[E24B10 |   4224/60000 (  7%) ] Loss: 0.2336 top1= 93.7500
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.2017 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1036 top1= 59.1146


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6899 top1= 49.5192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7007 top1= 44.7616

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.2107 top1= 94.3750
[E25B10 |   4224/60000 (  7%) ] Loss: 0.2468 top1= 92.5000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.1821 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1229 top1= 56.6707


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6927 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5987 top1= 45.2624

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.2092 top1= 94.3750
[E26B10 |   4224/60000 (  7%) ] Loss: 0.2477 top1= 92.5000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.2226 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1362 top1= 56.3101


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6791 top1= 49.5092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4607 top1= 45.2624

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.2558 top1= 91.8750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.2628 top1= 91.8750
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.2113 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1180 top1= 58.5938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6782 top1= 49.4291


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5312 top1= 44.3510

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.2708 top1= 91.2500
[E28B10 |   4224/60000 (  7%) ] Loss: 0.2384 top1= 93.7500
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.1897 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1141 top1= 59.5453


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6648 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5253 top1= 44.8518

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.2414 top1= 93.4375
[E29B10 |   4224/60000 (  7%) ] Loss: 0.2557 top1= 92.8125
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.1816 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0873 top1= 60.7772


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6669 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8048 top1= 44.5513

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.2044 top1= 94.0625
[E30B10 |   4224/60000 (  7%) ] Loss: 0.2731 top1= 91.2500
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.1832 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0788 top1= 60.0661


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6552 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7464 top1= 44.4611

