
=== 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 0x7efcf4ed0490>

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: 1.1653 top1= 58.4375
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4141 top1= 86.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7528 top1= 81.1699


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5286 top1= 49.1386


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4825 top1= 43.7400

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2978 top1= 90.0000
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2286 top1= 94.0625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2404 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7098 top1= 85.8874


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0266 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1627 top1= 45.5529

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2207 top1= 93.5938
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1747 top1= 96.0938
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2016 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6338 top1= 86.0677


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8015 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0580 top1= 45.7031

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1945 top1= 94.2188
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1609 top1= 96.0938
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1818 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6056 top1= 85.9675


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6733 top1= 49.7997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9711 top1= 45.6831

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1851 top1= 93.9062
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1494 top1= 96.0938
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1695 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5956 top1= 85.7472


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5883 top1= 49.7396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9595 top1= 45.6731

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1779 top1= 94.3750
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1419 top1= 96.5625
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1611 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5903 top1= 85.7672


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5574 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9467 top1= 45.6530

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1737 top1= 94.6875
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1363 top1= 97.1875
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1550 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5836 top1= 85.7873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5323 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9202 top1= 45.7131

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1610 top1= 95.1562
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1304 top1= 97.0312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1487 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5826 top1= 85.7973


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5181 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8684 top1= 45.8734

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1565 top1= 95.1562
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1240 top1= 97.3438
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1407 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5817 top1= 85.6871


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5198 top1= 49.8397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8260 top1= 45.8834

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1508 top1= 95.9375
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1186 top1= 97.1875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1328 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5772 top1= 85.9075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4773 top1= 49.9299


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8356 top1= 45.9635

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1438 top1= 95.7812
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1136 top1= 97.8125
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1279 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5719 top1= 85.8774


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4605 top1= 50.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8592 top1= 45.9736

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1381 top1= 96.4062
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1100 top1= 97.8125
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1253 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5711 top1= 85.6971


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4435 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8693 top1= 45.9936

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1333 top1= 96.2500
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1055 top1= 97.8125
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1250 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5730 top1= 85.4768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4382 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8329 top1= 46.0136

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1278 top1= 96.5625
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1034 top1= 97.9688
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1216 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5737 top1= 85.6370


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4154 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7688 top1= 46.0637

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1259 top1= 96.5625
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1041 top1= 97.6562
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1232 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5775 top1= 85.3666


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3822 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7671 top1= 45.9836

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1292 top1= 96.5625
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1086 top1= 97.5000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1229 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5791 top1= 84.7356


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3713 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8707 top1= 45.7933

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1401 top1= 95.7812
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1101 top1= 97.6562
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1216 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5899 top1= 83.8141


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3947 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9204 top1= 45.1422

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1543 top1= 94.5312
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1084 top1= 97.5000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1301 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5906 top1= 84.4651


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4004 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8287 top1= 45.5929

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1395 top1= 96.0938
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1190 top1= 96.4062
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1352 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5843 top1= 85.4667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4144 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7181 top1= 45.8433

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1339 top1= 96.4062
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1294 top1= 95.7812
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1494 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5810 top1= 85.3365


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4593 top1= 49.2288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6842 top1= 46.0737

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1408 top1= 95.7812
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1067 top1= 97.0312
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1362 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5607 top1= 86.5184


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3801 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8359 top1= 45.9535

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1214 top1= 96.2500
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0992 top1= 97.9688
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1266 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5693 top1= 86.4083


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3529 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7069 top1= 46.2340

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1124 top1= 96.8750
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0991 top1= 97.8125
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1067 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5622 top1= 86.5585


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3857 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7018 top1= 46.3041

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0992 top1= 97.6562
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0935 top1= 97.6562
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1147 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5679 top1= 86.0978


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3766 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6622 top1= 46.4042

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1066 top1= 96.7188
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0918 top1= 97.6562
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1109 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5677 top1= 85.8674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3775 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7417 top1= 46.2941

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1032 top1= 96.8750
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0904 top1= 97.8125
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1143 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5706 top1= 85.7973


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3737 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7189 top1= 46.3141

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0985 top1= 97.3438
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0911 top1= 97.5000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1198 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5732 top1= 85.6871


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3760 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6347 top1= 46.3341

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1016 top1= 97.1875
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0939 top1= 97.3438
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1185 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5803 top1= 85.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3981 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6313 top1= 46.1138

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1148 top1= 96.0938
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.1086 top1= 96.5625
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1213 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5832 top1= 84.6955


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4060 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8251 top1= 45.7933

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1288 top1= 95.7812
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1222 top1= 96.7188
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1288 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5990 top1= 84.0645


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4489 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7618 top1= 45.6831

