
=== 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.DumbbellVariant object at 0x7fabfbaf32b0>

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: 1.2161 top1= 57.0312
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4238 top1= 85.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8289 top1= 81.6506


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6494 top1= 49.1086


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7154 top1= 43.7099

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2877 top1= 90.1562
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2408 top1= 93.5938
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2538 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8733 top1= 84.2548


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1476 top1= 49.5493


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3272 top1= 45.2123

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2388 top1= 92.8125
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1917 top1= 95.6250
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2182 top1= 92.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8080 top1= 83.5337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9617 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3174 top1= 45.4227

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2134 top1= 92.5000
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1820 top1= 94.3750
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2094 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7914 top1= 83.1430


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8611 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2033 top1= 45.4327

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2012 top1= 93.1250
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1717 top1= 95.1562
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2085 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7926 top1= 82.2616


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8057 top1= 49.5693


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1495 top1= 45.5028

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1909 top1= 93.5938
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1660 top1= 95.0000
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1996 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7986 top1= 80.6991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7703 top1= 49.5192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1319 top1= 45.5729

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1898 top1= 93.4375
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1661 top1= 95.3125
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1873 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8008 top1= 80.6991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7391 top1= 49.5393


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1444 top1= 45.3225

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1937 top1= 93.4375
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1644 top1= 95.1562
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1793 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8013 top1= 80.7592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7081 top1= 49.5192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1150 top1= 45.5429

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1890 top1= 93.7500
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1616 top1= 95.6250
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1739 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8039 top1= 80.8894


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6884 top1= 49.3890


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0425 top1= 45.6430

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1882 top1= 93.7500
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1580 top1= 95.7812
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1721 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8049 top1= 81.1298


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6798 top1= 49.3890


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9612 top1= 45.7031

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1879 top1= 94.0625
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1559 top1= 95.6250
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1796 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8064 top1= 81.3101


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6654 top1= 49.4992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8880 top1= 45.7532

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1908 top1= 93.5938
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1560 top1= 95.6250
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1825 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8018 top1= 81.6807


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6362 top1= 49.6194


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8639 top1= 45.9635

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1749 top1= 94.6875
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1531 top1= 96.2500
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1800 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8049 top1= 79.9880


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6064 top1= 49.7196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0082 top1= 45.7632

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1727 top1= 94.8438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1455 top1= 96.4062
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1611 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8004 top1= 80.7993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5912 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0343 top1= 45.8534

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1661 top1= 94.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1355 top1= 96.5625
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1600 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7992 top1= 80.7692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5754 top1= 49.9099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9631 top1= 46.0437

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1483 top1= 95.9375
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1336 top1= 96.5625
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1695 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8099 top1= 79.9679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5744 top1= 49.9299


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8515 top1= 46.2039

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1426 top1= 95.6250
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1378 top1= 96.8750
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1736 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8110 top1= 79.2869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5566 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8497 top1= 46.1639

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1415 top1= 95.9375
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1327 top1= 96.2500
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1687 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8124 top1= 78.9263


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5332 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8610 top1= 46.0136

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1460 top1= 95.9375
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1325 top1= 96.5625
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1669 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8110 top1= 79.5773


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5327 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8455 top1= 45.8333

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1512 top1= 95.4688
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1359 top1= 96.4062
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1649 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8107 top1= 79.1967


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5294 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8472 top1= 45.7232

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1538 top1= 95.3125
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1474 top1= 96.5625
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1685 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8133 top1= 80.4187


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5338 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8224 top1= 45.6530

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1622 top1= 94.5312
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.1606 top1= 95.1562
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1727 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8140 top1= 81.1398


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5454 top1= 49.5693


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8293 top1= 45.5028

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1749 top1= 93.9062
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.1602 top1= 95.7812
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1620 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8128 top1= 81.7208


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5554 top1= 49.1887


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8630 top1= 45.4928

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1814 top1= 93.9062
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1350 top1= 96.0938
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1504 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7912 top1= 82.6723


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5717 top1= 49.7396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8744 top1= 45.7732

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1602 top1= 94.5312
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1280 top1= 97.3438
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1428 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7958 top1= 82.2917


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5691 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8368 top1= 45.7632

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1477 top1= 95.4688
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.1285 top1= 96.7188
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1461 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7917 top1= 82.8025


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5359 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8099 top1= 46.1238

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1354 top1= 96.0938
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1270 top1= 97.0312
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1492 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7875 top1= 83.2031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5167 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7850 top1= 46.1739

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1320 top1= 96.2500
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.1277 top1= 97.0312
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1560 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7902 top1= 82.8025


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4944 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7597 top1= 46.2540

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1323 top1= 96.2500
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.1299 top1= 96.2500
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1609 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7974 top1= 82.0212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5029 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7369 top1= 46.2941

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1315 top1= 96.2500
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1324 top1= 96.2500
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1582 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7968 top1= 82.3317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4994 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7498 top1= 46.3141

