
=== 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 0x7ff4b56577f0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.2959 top1= 10.0000

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


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.9644 top1= 44.6875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.9585 top1= 69.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5255 top1= 83.2232


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5320 top1= 82.0813


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5550 top1= 82.7624

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.7042 top1= 80.9375
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4720 top1= 84.0625
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.4048 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3162 top1= 90.8954


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3234 top1= 90.4447


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3305 top1= 90.4848

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3748 top1= 87.8125
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3062 top1= 88.7500
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2975 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2833 top1= 91.8169


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2816 top1= 91.6967


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3018 top1= 91.2460

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2833 top1= 92.1875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2405 top1= 92.5000
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.2358 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2548 top1= 92.5581


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2585 top1= 92.2276


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2678 top1= 92.1374

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.2239 top1= 94.6875
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1716 top1= 94.6875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1957 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2361 top1= 93.1090


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2332 top1= 93.2492


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2547 top1= 92.5481

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1828 top1= 95.6250
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1307 top1= 96.5625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1654 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2288 top1= 93.3193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2260 top1= 93.2692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2473 top1= 92.8285

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1627 top1= 94.6875
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1171 top1= 97.1875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.1447 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2261 top1= 93.2993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2229 top1= 93.3994


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2456 top1= 92.8886

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1458 top1= 95.3125
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1109 top1= 97.1875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.1361 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2243 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2226 top1= 93.3594


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2468 top1= 92.8686

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.1322 top1= 95.9375
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1100 top1= 98.4375
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.1329 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2277 top1= 93.2192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2270 top1= 93.1891


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2490 top1= 92.8986

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1259 top1= 96.2500
[E10B10 |   4224/60000 (  7%) ] Loss: 0.1052 top1= 98.4375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.1324 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2296 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2403 top1= 92.5681


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2444 top1= 92.9988

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.1344 top1= 95.3125
[E11B10 |   4224/60000 (  7%) ] Loss: 0.1072 top1= 98.1250
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.1198 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2386 top1= 92.7284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2434 top1= 92.5881


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2546 top1= 92.4880

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.1438 top1= 95.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.1119 top1= 96.8750
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.1682 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2414 top1= 92.7985


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2545 top1= 92.1174


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2696 top1= 92.1474

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.1709 top1= 95.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.1272 top1= 96.8750
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.1606 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2542 top1= 92.2676


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2520 top1= 92.3478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2919 top1= 91.3762

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.1805 top1= 94.0625
[E14B10 |   4224/60000 (  7%) ] Loss: 0.1344 top1= 95.3125
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.1463 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2357 top1= 93.0589


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2366 top1= 93.0589


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2667 top1= 91.8369

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.1593 top1= 95.6250
[E15B10 |   4224/60000 (  7%) ] Loss: 0.1682 top1= 95.3125
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.1451 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2375 top1= 93.1691


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2432 top1= 92.9187


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2585 top1= 92.7083

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.1799 top1= 94.6875
[E16B10 |   4224/60000 (  7%) ] Loss: 0.1297 top1= 97.8125
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.1727 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2511 top1= 92.7885


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2581 top1= 92.3177


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2729 top1= 92.3978

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.1747 top1= 95.9375
[E17B10 |   4224/60000 (  7%) ] Loss: 0.1628 top1= 95.9375
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.1800 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2582 top1= 92.5080


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2570 top1= 92.5781


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2932 top1= 91.5665

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.1804 top1= 95.3125
[E18B10 |   4224/60000 (  7%) ] Loss: 0.1488 top1= 96.5625
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1729 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2508 top1= 92.6783


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2503 top1= 92.6482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2926 top1= 91.2560

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.2092 top1= 93.4375
[E19B10 |   4224/60000 (  7%) ] Loss: 0.1693 top1= 96.8750
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.2008 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2532 top1= 92.4679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2656 top1= 91.9772


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2700 top1= 92.0773

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.1745 top1= 94.0625
[E20B10 |   4224/60000 (  7%) ] Loss: 0.1959 top1= 95.6250
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.2008 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2644 top1= 92.1274


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2863 top1= 90.7953


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2812 top1= 91.8670

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.1869 top1= 93.7500
[E21B10 |   4224/60000 (  7%) ] Loss: 0.1499 top1= 96.8750
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1855 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2587 top1= 92.5481


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2670 top1= 91.9471


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2831 top1= 92.1575

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.2199 top1= 93.4375
[E22B10 |   4224/60000 (  7%) ] Loss: 0.1793 top1= 95.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.1983 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2722 top1= 92.0773


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2784 top1= 91.4764


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3032 top1= 91.3061

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.2617 top1= 91.8750
[E23B10 |   4224/60000 (  7%) ] Loss: 0.2121 top1= 95.3125
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.2099 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2777 top1= 91.6967


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3040 top1= 90.4848


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2923 top1= 91.5966

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.2036 top1= 93.4375
[E24B10 |   4224/60000 (  7%) ] Loss: 0.1904 top1= 95.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.2071 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2784 top1= 91.6366


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3066 top1= 90.1643


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2873 top1= 91.9471

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.2371 top1= 92.5000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.1701 top1= 96.2500
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.1955 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2645 top1= 92.1474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2616 top1= 92.2175


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2990 top1= 91.1458

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.1919 top1= 93.7500
[E26B10 |   4224/60000 (  7%) ] Loss: 0.1903 top1= 95.3125
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.1943 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2489 top1= 92.8285


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2631 top1= 92.0172


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2607 top1= 92.2977

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.1880 top1= 94.3750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.1804 top1= 95.6250
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.1951 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2539 top1= 92.7684


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2546 top1= 92.4980


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2917 top1= 91.6567

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.2085 top1= 94.0625
[E28B10 |   4224/60000 (  7%) ] Loss: 0.1540 top1= 95.9375
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.2072 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2819 top1= 91.4663


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3153 top1= 90.3446


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2873 top1= 91.7768

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.1967 top1= 94.0625
[E29B10 |   4224/60000 (  7%) ] Loss: 0.1697 top1= 95.6250
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.1848 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2613 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2695 top1= 92.0272


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3060 top1= 91.2861

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.1967 top1= 94.0625
[E30B10 |   4224/60000 (  7%) ] Loss: 0.1811 top1= 94.3750
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.1984 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2458 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2477 top1= 92.8986


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2734 top1= 92.6382

