
=== 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.Dumbbell object at 0x7ff5771e3490>

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: 1.1275 top1= 60.7812
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3976 top1= 87.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7401 top1= 80.6090


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8179 top1= 49.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8099 top1= 43.7600

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2867 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2159 top1= 94.2188
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2226 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6885 top1= 85.9175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1201 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2480 top1= 45.6130

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2024 top1= 94.3750
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1630 top1= 96.2500
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1857 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6124 top1= 86.5785


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8812 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1640 top1= 45.8734

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1777 top1= 95.0000
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1474 top1= 95.9375
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1641 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5715 top1= 87.0092


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7661 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0351 top1= 45.8834

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1690 top1= 94.5312
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1397 top1= 96.5625
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1556 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5582 top1= 86.8490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7008 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0058 top1= 45.8734

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1631 top1= 95.1562
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1309 top1= 97.3438
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1498 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5558 top1= 86.7087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6852 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9855 top1= 45.8834

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1565 top1= 95.3125
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1261 top1= 97.3438
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1428 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5491 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6627 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0240 top1= 45.9936

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1471 top1= 95.4688
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1199 top1= 97.3438
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1401 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5508 top1= 86.7388


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6432 top1= 49.7997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0258 top1= 46.0837

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1409 top1= 95.7812
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1137 top1= 97.6562
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1362 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5536 top1= 86.4583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6310 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0089 top1= 46.1138

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1378 top1= 96.0938
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1081 top1= 97.9688
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1284 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5551 top1= 86.4583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6138 top1= 49.7997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0126 top1= 46.1438

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1327 top1= 96.7188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1041 top1= 98.1250
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1213 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5519 top1= 86.4283


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6053 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9987 top1= 46.2240

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1294 top1= 96.5625
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0984 top1= 98.2812
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1168 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5467 top1= 86.6587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5785 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0233 top1= 46.1238

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1260 top1= 96.0938
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0999 top1= 97.8125
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1190 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5552 top1= 86.1679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5792 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9508 top1= 46.1438

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1186 top1= 96.7188
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0966 top1= 97.6562
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1323 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5656 top1= 85.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5627 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8481 top1= 46.0737

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1113 top1= 97.0312
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0917 top1= 97.8125
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1284 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5678 top1= 85.3265


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5399 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8048 top1= 45.7332

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1203 top1= 96.5625
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1028 top1= 97.5000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1157 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5778 top1= 83.5036


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4917 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1363 top1= 45.5028

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1409 top1= 95.1562
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1116 top1= 96.7188
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1276 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5994 top1= 81.9010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4752 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1342 top1= 45.1923

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1494 top1= 95.1562
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0977 top1= 97.5000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1438 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5819 top1= 83.3834


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4747 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0511 top1= 45.9435

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1175 top1= 96.7188
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1000 top1= 96.8750
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1291 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5626 top1= 85.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4845 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0394 top1= 46.2540

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0989 top1= 97.9688
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0851 top1= 97.9688
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1188 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5572 top1= 84.9659


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5192 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9881 top1= 46.3041

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1028 top1= 96.8750
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0802 top1= 97.9688
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1048 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5513 top1= 85.1562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4979 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0392 top1= 45.8834

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1142 top1= 96.4062
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0783 top1= 98.1250
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1066 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5455 top1= 86.1879


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4440 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0161 top1= 46.0938

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1057 top1= 97.0312
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0824 top1= 97.9688
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1114 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5543 top1= 85.7171


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4818 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9155 top1= 46.3241

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1023 top1= 97.6562
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0785 top1= 97.9688
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1146 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5550 top1= 85.7372


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5251 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8707 top1= 46.2841

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0996 top1= 97.3438
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0776 top1= 98.2812
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1016 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5378 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5493 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8907 top1= 46.4143

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0903 top1= 97.9688
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0834 top1= 97.9688
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1005 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5301 top1= 88.0409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5339 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9146 top1= 46.2240

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0971 top1= 97.6562
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0894 top1= 97.3438
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1100 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5432 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5012 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8358 top1= 46.1538

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1052 top1= 96.7188
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0851 top1= 97.3438
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1267 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5715 top1= 85.0461


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4958 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7188 top1= 46.0537

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1220 top1= 96.4062
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0796 top1= 98.1250
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1264 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5888 top1= 84.0645


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5009 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8679 top1= 45.8433

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1264 top1= 95.7812
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0893 top1= 97.5000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1372 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5881 top1= 84.7556


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5306 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9436 top1= 45.6330

