
=== 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 0x7f441366a2b0>

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: 1.1238 top1= 60.6250
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3932 top1= 87.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7162 top1= 81.4002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8069 top1= 49.2388


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7748 top1= 43.8301

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2751 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2190 top1= 93.5938
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2176 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6598 top1= 86.0377


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0124 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1356 top1= 45.6230

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1987 top1= 93.9062
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1583 top1= 96.7188
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1809 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5832 top1= 86.9491


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7853 top1= 49.9299


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0155 top1= 45.7933

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1732 top1= 94.6875
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1417 top1= 96.0938
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1596 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5493 top1= 87.0493


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6694 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9086 top1= 45.8534

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1616 top1= 94.8438
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1338 top1= 96.0938
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1477 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5351 top1= 87.0292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5984 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8606 top1= 45.8834

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1537 top1= 95.0000
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1271 top1= 97.0312
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1390 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5259 top1= 86.9091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5710 top1= 49.8798


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8493 top1= 46.0136

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1458 top1= 95.6250
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1208 top1= 97.3438
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1326 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5243 top1= 86.8690


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5695 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8534 top1= 46.0036

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1402 top1= 95.9375
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1152 top1= 97.6562
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1260 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5183 top1= 86.8089


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5588 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8571 top1= 46.0938

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1289 top1= 96.5625
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1083 top1= 97.9688
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1168 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5135 top1= 87.1094


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5596 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8731 top1= 46.1739

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1253 top1= 96.7188
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1045 top1= 98.1250
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1116 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5137 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5278 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8798 top1= 46.1338

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1191 top1= 96.5625
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0965 top1= 98.2812
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1072 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5179 top1= 86.6987


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5085 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9161 top1= 46.0537

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1183 top1= 96.4062
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0949 top1= 98.1250
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1101 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5125 top1= 86.7188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5059 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9346 top1= 46.1839

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1113 top1= 96.7188
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0975 top1= 97.9688
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1017 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5080 top1= 86.6486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4719 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9263 top1= 46.1639

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1146 top1= 96.4062
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0921 top1= 97.6562
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1035 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5189 top1= 85.7572


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4399 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8330 top1= 46.2139

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1027 top1= 97.3438
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0898 top1= 97.6562
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1165 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5221 top1= 85.7772


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4286 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7205 top1= 46.3041

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1027 top1= 97.3438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0913 top1= 98.1250
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1115 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5402 top1= 84.6454


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4074 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8816 top1= 45.3325

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1327 top1= 96.2500
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0932 top1= 97.8125
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1022 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5517 top1= 82.8526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3982 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0010 top1= 44.9419

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1435 top1= 95.1562
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1115 top1= 96.2500
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1372 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5335 top1= 84.7857


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4151 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0207 top1= 45.6931

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1166 top1= 96.5625
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1121 top1= 96.5625
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1327 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5141 top1= 86.5986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4081 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0073 top1= 45.9936

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1085 top1= 96.5625
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0938 top1= 97.5000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0932 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5135 top1= 86.5385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4604 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8722 top1= 46.3442

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1127 top1= 96.0938
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1057 top1= 96.8750
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0928 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5154 top1= 87.0593


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4453 top1= 49.3990


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7519 top1= 46.4243

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1226 top1= 96.2500
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0817 top1= 98.1250
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1029 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4961 top1= 87.7404


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3852 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7111 top1= 46.5345

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0817 top1= 97.6562
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0726 top1= 98.5938
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0916 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5057 top1= 87.4900


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4342 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7238 top1= 46.5445

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0832 top1= 97.9688
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0739 top1= 98.4375
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0960 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5109 top1= 86.9091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4275 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7205 top1= 46.3241

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0888 top1= 97.8125
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0759 top1= 97.9688
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0909 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5111 top1= 86.0076


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3797 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8259 top1= 46.1138

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1078 top1= 97.0312
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0863 top1= 98.1250
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1013 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5399 top1= 83.0329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3551 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8924 top1= 45.7933

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1081 top1= 96.7188
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0998 top1= 97.1875
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1374 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5228 top1= 85.9675


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3735 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6777 top1= 46.3742

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0856 top1= 97.3438
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0841 top1= 97.1875
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1267 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5306 top1= 85.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3731 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8716 top1= 46.2139

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1103 top1= 96.5625
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0959 top1= 97.0312
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1364 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5376 top1= 84.7055


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3777 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0047 top1= 45.8934

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1157 top1= 96.4062
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0999 top1= 96.8750
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1003 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5310 top1= 84.7756


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3963 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9956 top1= 45.4728

