
=== 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 0x7f841db359d0>

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: 1.9142 top1= 37.5000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 1.5758 top1= 40.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9866 top1= 52.3838


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1703 top1= 42.7183


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3183 top1= 37.5100

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 1.0704 top1= 72.8125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.6812 top1= 84.0625
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.4844 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3374 top1= 68.3594


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4486 top1= 48.5276


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3463 top1= 42.8486

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.5675 top1= 83.7500
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.5563 top1= 88.1250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.5295 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3245 top1= 71.9651


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3245 top1= 48.3674


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2370 top1= 43.0589

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.5737 top1= 83.4375
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.5502 top1= 88.4375
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.5193 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3168 top1= 72.0753


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2340 top1= 48.4375


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1881 top1= 43.2192

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.5462 top1= 85.9375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.5503 top1= 87.1875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.5114 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3188 top1= 71.9852


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2004 top1= 48.4175


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1674 top1= 43.3594

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.5330 top1= 85.6250
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.5441 top1= 87.8125
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.5058 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3223 top1= 72.1054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1843 top1= 48.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1571 top1= 43.3894

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.5272 top1= 86.2500
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.5412 top1= 87.8125
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.4997 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3261 top1= 72.2256


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1718 top1= 48.4275


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1476 top1= 43.4095

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.5228 top1= 85.9375
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.5364 top1= 87.8125
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.4959 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3287 top1= 72.3658


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1624 top1= 48.3974


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1512 top1= 43.4896

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.5210 top1= 85.9375
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.5291 top1= 87.8125
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.4948 top1= 90.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3326 top1= 72.4760


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1550 top1= 48.3774


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1446 top1= 43.3794

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.5230 top1= 85.9375
[E10B10 |   4224/60000 (  7%) ] Loss: 0.5281 top1= 87.5000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.4965 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3356 top1= 72.4659


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1508 top1= 48.3474


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1502 top1= 43.4996

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.5228 top1= 86.5625
[E11B10 |   4224/60000 (  7%) ] Loss: 0.5259 top1= 88.1250
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.4936 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3377 top1= 72.3558


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1508 top1= 48.3373


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1493 top1= 43.3293

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.5235 top1= 85.6250
[E12B10 |   4224/60000 (  7%) ] Loss: 0.5267 top1= 88.4375
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.4936 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3394 top1= 72.2656


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1505 top1= 48.3574


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1490 top1= 43.3794

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.5216 top1= 85.3125
[E13B10 |   4224/60000 (  7%) ] Loss: 0.5272 top1= 88.1250
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.4941 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3411 top1= 72.2055


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1490 top1= 48.3474


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1474 top1= 43.4095

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.5215 top1= 85.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.5275 top1= 88.4375
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.4926 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3422 top1= 72.0954


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1538 top1= 48.3373


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1475 top1= 43.3894

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.5224 top1= 85.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.5269 top1= 88.1250
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.4925 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3432 top1= 72.1554


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1528 top1= 48.3173


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1445 top1= 43.3494

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.5223 top1= 85.3125
[E16B10 |   4224/60000 (  7%) ] Loss: 0.5270 top1= 87.8125
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.4927 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3437 top1= 72.0453


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1518 top1= 48.3073


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1468 top1= 43.3694

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.5214 top1= 85.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.5263 top1= 87.8125
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.4924 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3448 top1= 72.1254


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1530 top1= 48.2973


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1510 top1= 43.3594

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.5230 top1= 84.6875
[E18B10 |   4224/60000 (  7%) ] Loss: 0.5251 top1= 87.8125
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.4908 top1= 89.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3455 top1= 72.1554


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1524 top1= 48.3273


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1466 top1= 43.3794

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.5222 top1= 85.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.5251 top1= 87.8125
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.4900 top1= 89.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3463 top1= 72.0653


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1531 top1= 48.3273


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1446 top1= 43.3694

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.5252 top1= 84.3750
[E20B10 |   4224/60000 (  7%) ] Loss: 0.5235 top1= 88.1250
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.4880 top1= 89.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3474 top1= 71.9451


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1524 top1= 48.3173


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1404 top1= 43.3694

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.5262 top1= 84.3750
[E21B10 |   4224/60000 (  7%) ] Loss: 0.5221 top1= 88.1250
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.4865 top1= 89.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3472 top1= 71.9952


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1526 top1= 48.3273


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1440 top1= 43.3594

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.5249 top1= 85.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.5212 top1= 87.8125
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.4865 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3472 top1= 71.9151


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1526 top1= 48.3273


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1425 top1= 43.3494

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.5250 top1= 85.3125
[E23B10 |   4224/60000 (  7%) ] Loss: 0.5198 top1= 87.8125
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.4856 top1= 89.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3484 top1= 72.1054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1517 top1= 48.3073


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1411 top1= 43.3093

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.5262 top1= 85.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.5201 top1= 88.1250
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.4846 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3482 top1= 72.0052


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1532 top1= 48.3273


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1403 top1= 43.3894

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.5245 top1= 85.6250
[E25B10 |   4224/60000 (  7%) ] Loss: 0.5162 top1= 88.4375
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.4829 top1= 89.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3483 top1= 72.0853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1537 top1= 48.2873


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1427 top1= 43.3494

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.5257 top1= 85.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.5149 top1= 88.4375
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.4819 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3480 top1= 72.1354


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1532 top1= 48.2772


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1423 top1= 43.4195

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.5241 top1= 85.3125
[E27B10 |   4224/60000 (  7%) ] Loss: 0.5148 top1= 88.7500
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.4817 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3485 top1= 72.3057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1536 top1= 48.2772


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1442 top1= 43.4696

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.5228 top1= 85.3125
[E28B10 |   4224/60000 (  7%) ] Loss: 0.5133 top1= 88.1250
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.4803 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3475 top1= 72.3057


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1513 top1= 48.3173


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1426 top1= 43.4796

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.5217 top1= 85.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.5118 top1= 88.1250
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.4803 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3486 top1= 72.4359


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1522 top1= 48.3173


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1395 top1= 43.4896

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.5232 top1= 84.3750
[E30B10 |   4224/60000 (  7%) ] Loss: 0.5120 top1= 88.4375
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.4799 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3478 top1= 72.2556


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1533 top1= 48.2873


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1384 top1= 43.4595

