
=== 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 0x7fde920489d0>

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: 1.4141 top1= 57.1875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.5386 top1= 86.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8136 top1= 82.4119


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6490 top1= 48.8081


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0682 top1= 43.4996

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3652 top1= 90.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3686 top1= 88.7500
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2532 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7690 top1= 83.0729


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9669 top1= 49.4992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3323 top1= 44.0004

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3243 top1= 92.1875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3350 top1= 90.6250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2283 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7529 top1= 83.0329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8736 top1= 49.7296


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2339 top1= 44.3409

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2956 top1= 92.8125
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.3173 top1= 91.2500
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.2155 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7516 top1= 83.0028


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8537 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2049 top1= 44.4912

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.2787 top1= 93.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.3078 top1= 91.2500
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.2069 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7543 top1= 82.9026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8472 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2027 top1= 44.5813

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.2679 top1= 92.8125
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.2993 top1= 91.5625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.2028 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7558 top1= 82.9627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8330 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2027 top1= 44.6314

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.2613 top1= 93.4375
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.2991 top1= 91.2500
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.2023 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7579 top1= 83.1030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8213 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1874 top1= 44.6915

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.2562 top1= 93.4375
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.3018 top1= 90.9375
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.2041 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7604 top1= 83.0329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8189 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1786 top1= 44.7316

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.2530 top1= 93.7500
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.2930 top1= 91.2500
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.2053 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7616 top1= 83.1130


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8041 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1741 top1= 44.7616

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.2541 top1= 93.7500
[E10B10 |   4224/60000 (  7%) ] Loss: 0.2992 top1= 90.9375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.2024 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7619 top1= 82.8826


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7977 top1= 50.1102


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1695 top1= 44.8518

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.2491 top1= 93.7500
[E11B10 |   4224/60000 (  7%) ] Loss: 0.2959 top1= 91.2500
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.2055 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7644 top1= 83.1230


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7837 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1492 top1= 44.8117

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.2477 top1= 94.6875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.2939 top1= 91.8750
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.2047 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7634 top1= 83.2332


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7812 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1270 top1= 44.9419

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.2420 top1= 95.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.2953 top1= 90.9375
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.2035 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7644 top1= 83.2833


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7687 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1162 top1= 44.9018

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.2404 top1= 95.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.2893 top1= 91.5625
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.2036 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7643 top1= 83.4635


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7665 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0941 top1= 44.9720

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.2384 top1= 94.6875
[E15B10 |   4224/60000 (  7%) ] Loss: 0.2843 top1= 90.9375
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.2017 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7638 top1= 83.5537


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7572 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0967 top1= 45.0120

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.2362 top1= 94.3750
[E16B10 |   4224/60000 (  7%) ] Loss: 0.2792 top1= 91.5625
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.1996 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7644 top1= 83.7139


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7574 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0883 top1= 44.9720

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.2398 top1= 93.7500
[E17B10 |   4224/60000 (  7%) ] Loss: 0.2777 top1= 91.2500
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.2006 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7641 top1= 83.9343


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7535 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0847 top1= 45.0020

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.2378 top1= 93.7500
[E18B10 |   4224/60000 (  7%) ] Loss: 0.2766 top1= 91.2500
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1963 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7660 top1= 83.8542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7514 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0793 top1= 44.9519

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.2392 top1= 93.7500
[E19B10 |   4224/60000 (  7%) ] Loss: 0.2719 top1= 92.1875
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1966 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7654 top1= 84.0645


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7430 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0823 top1= 45.0721

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.2381 top1= 93.7500
[E20B10 |   4224/60000 (  7%) ] Loss: 0.2715 top1= 92.1875
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.1952 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7683 top1= 83.7941


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7281 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1076 top1= 44.9319

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.2416 top1= 94.3750
[E21B10 |   4224/60000 (  7%) ] Loss: 0.2765 top1= 91.8750
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1913 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7685 top1= 84.0845


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7320 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0867 top1= 44.9419

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.2393 top1= 93.7500
[E22B10 |   4224/60000 (  7%) ] Loss: 0.2717 top1= 92.5000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.1904 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7690 top1= 83.9543


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7309 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0953 top1= 44.8918

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.2412 top1= 93.1250
[E23B10 |   4224/60000 (  7%) ] Loss: 0.2748 top1= 92.1875
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.1892 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7689 top1= 84.3950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7285 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0786 top1= 44.9720

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.2406 top1= 93.7500
[E24B10 |   4224/60000 (  7%) ] Loss: 0.2749 top1= 92.5000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.1900 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7719 top1= 83.8241


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7244 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0911 top1= 44.9820

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.2407 top1= 93.7500
[E25B10 |   4224/60000 (  7%) ] Loss: 0.2688 top1= 92.8125
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.1897 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7720 top1= 83.9844


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7223 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0777 top1= 44.9018

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.2450 top1= 93.4375
[E26B10 |   4224/60000 (  7%) ] Loss: 0.2688 top1= 92.8125
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.1896 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7738 top1= 83.8942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7172 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0835 top1= 44.8918

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.2484 top1= 92.5000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.2732 top1= 92.8125
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.1880 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7728 top1= 84.1346


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7152 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0765 top1= 44.9119

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.2466 top1= 93.4375
[E28B10 |   4224/60000 (  7%) ] Loss: 0.2728 top1= 92.8125
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.1893 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7736 top1= 83.9143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7148 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0895 top1= 44.8918

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.2481 top1= 92.8125
[E29B10 |   4224/60000 (  7%) ] Loss: 0.2721 top1= 93.1250
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.1877 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7733 top1= 84.0445


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7171 top1= 50.1703


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0729 top1= 44.8718

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.2467 top1= 93.4375
[E30B10 |   4224/60000 (  7%) ] Loss: 0.2787 top1= 92.5000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.1903 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7730 top1= 83.8141


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7131 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0806 top1= 44.9219

