
=== 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 0x7f656f40c2e0>

Train epoch 1
[E 1B0  |    704/60000 (  1%) ] Loss: 2.3080 top1=  8.4375

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')
Worker 2 has targets: tensor([3, 0, 3, 2, 7], device='cuda:0')
Worker 3 has targets: tensor([1, 4, 8, 2, 8], device='cuda:0')
Worker 4 has targets: tensor([9, 5, 0, 1, 3], device='cuda:0')
Worker 5 has targets: tensor([5, 6, 2, 4, 3], device='cuda:0')
Worker 6 has targets: tensor([2, 5, 0, 9, 9], device='cuda:0')
Worker 7 has targets: tensor([2, 2, 1, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([3, 8, 7, 0, 3], device='cuda:0')
Worker 9 has targets: tensor([1, 7, 1, 7, 2], device='cuda:0')
Worker 10 has targets: tensor([8, 4, 4, 3, 9], device='cuda:0')
Worker 11 has targets: tensor([3, 4, 7, 7, 9], device='cuda:0')
Worker 12 has targets: tensor([7, 4, 3, 9, 4], device='cuda:0')
Worker 13 has targets: tensor([4, 5, 0, 7, 1], device='cuda:0')
Worker 14 has targets: tensor([4, 2, 3, 5, 5], device='cuda:0')
Worker 15 has targets: tensor([4, 7, 5, 4, 7], device='cuda:0')
Worker 16 has targets: tensor([1, 1, 5, 7, 9], device='cuda:0')
Worker 17 has targets: tensor([8, 7, 2, 2, 0], device='cuda:0')
Worker 18 has targets: tensor([7, 8, 0, 0, 6], device='cuda:0')
Worker 19 has targets: tensor([9, 9, 5, 2, 8], device='cuda:0')
Worker 20 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 21 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 1.9058 top1= 48.9062
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8355 top1= 74.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4260 top1= 87.4700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4548 top1= 86.7087


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4641 top1= 85.7873

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5182 top1= 84.5312
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.4547 top1= 84.0625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3770 top1= 87.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2826 top1= 91.9872


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2916 top1= 91.3962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2993 top1= 91.5064

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2674 top1= 92.9688
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2477 top1= 92.1875
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2487 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2376 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2381 top1= 93.0689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2558 top1= 92.4880

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1917 top1= 93.7500
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1863 top1= 94.3750
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1797 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2151 top1= 93.6098


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2138 top1= 93.5597


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2349 top1= 92.8886

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1529 top1= 95.4688
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1375 top1= 96.2500
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1365 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1982 top1= 93.9403


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2063 top1= 93.5296


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2033 top1= 93.9002

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1183 top1= 96.8750
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1041 top1= 97.5000
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1020 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1754 top1= 94.7616


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1913 top1= 94.0905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1751 top1= 94.7015

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0892 top1= 97.9688
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0789 top1= 98.1250
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0802 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1655 top1= 95.0821


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1780 top1= 94.7015


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1638 top1= 95.0621

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0711 top1= 98.1250
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0590 top1= 99.0625
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0647 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1625 top1= 95.0921


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1786 top1= 94.7216


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1624 top1= 95.1222

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0563 top1= 98.7500
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0480 top1= 99.5312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0543 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1625 top1= 95.0721


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1846 top1= 94.5513


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1630 top1= 95.0321

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0536 top1= 98.7500
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0440 top1= 99.5312
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0507 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1592 top1= 95.1623


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1873 top1= 94.4812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1592 top1= 95.2424

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0462 top1= 99.0625
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0407 top1= 99.3750
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0478 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1584 top1= 95.3225


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1849 top1= 94.6214


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1589 top1= 95.3526

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0465 top1= 99.2188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0558 top1= 98.2812
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0494 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1551 top1= 95.3826


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1832 top1= 94.5713


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1506 top1= 95.5629

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0416 top1= 99.3750
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0347 top1= 99.6875
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0430 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1551 top1= 95.3626


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1663 top1= 95.0521


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1664 top1= 95.1122

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0337 top1= 99.3750
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0355 top1= 99.5312
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0339 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1496 top1= 95.6931


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1563 top1= 95.5128


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1561 top1= 95.4527

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0358 top1= 99.2188
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0217 top1= 99.8438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0322 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1419 top1= 95.7732


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1566 top1= 95.4527


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1455 top1= 95.6230

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0293 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0252 top1= 99.6875
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0300 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1419 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1667 top1= 95.1222


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1487 top1= 95.6731

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0284 top1= 99.5312
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0184 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0452 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1433 top1= 95.6430


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1660 top1= 94.9920


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1499 top1= 95.6330

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0247 top1= 99.6875
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0187 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0213 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1445 top1= 95.7332


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1805 top1= 94.5513


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1584 top1= 95.2925

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0236 top1= 99.8438
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0204 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0206 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1396 top1= 95.6831


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1722 top1= 94.7216


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1502 top1= 95.5429

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0197 top1= 99.8438
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0234 top1= 99.8438
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0184 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1380 top1= 95.8233


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1662 top1= 94.9219


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1452 top1= 95.6631

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0185 top1= 99.8438
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0153 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0187 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1370 top1= 95.8634


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1653 top1= 95.0120


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1467 top1= 95.7232

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0229 top1= 99.6875
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0173 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0179 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1413 top1= 95.7432


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1620 top1= 95.1422


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1454 top1= 95.8033

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0226 top1= 99.5312
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0189 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0216 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1408 top1= 95.8033


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1578 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1379 top1= 95.8233

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0155 top1= 99.8438
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0224 top1= 99.8438
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0220 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1457 top1= 95.6631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1634 top1= 95.2123


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1435 top1= 95.7232

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0172 top1= 99.8438
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0164 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0211 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1627 top1= 95.1222


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1997 top1= 94.2408


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1567 top1= 95.2925

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0229 top1= 99.8438
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0180 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0249 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1575 top1= 95.2624


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1922 top1= 94.3209


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1511 top1= 95.5128

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0214 top1= 99.6875
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0306 top1= 99.5312
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0222 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1527 top1= 95.3425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1621 top1= 95.1022


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1552 top1= 95.3626

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0215 top1= 99.6875
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0281 top1= 99.6875
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0326 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1616 top1= 95.1222


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1916 top1= 94.4712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1513 top1= 95.4327

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0353 top1= 98.9062
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0251 top1= 99.8438
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0339 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1405 top1= 95.8033


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1642 top1= 95.2324


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1501 top1= 95.4527

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0262 top1= 99.5312
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0340 top1= 99.0625
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0347 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1357 top1= 95.8133


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1652 top1= 94.8217


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1523 top1= 95.4828

