
=== 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 0x7f393c8c62e0>

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: 1.1655 top1= 57.9688
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4106 top1= 86.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8000 top1= 80.4688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1766 top1= 49.1687


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1117 top1= 43.8502

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2886 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2257 top1= 94.0625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2252 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8272 top1= 85.1362


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4122 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5413 top1= 45.3626

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2103 top1= 94.0625
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1711 top1= 95.7812
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1948 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7619 top1= 85.3966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1685 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4881 top1= 45.5128

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1932 top1= 93.2812
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1557 top1= 95.9375
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1751 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7331 top1= 85.2063


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0256 top1= 49.7196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3558 top1= 45.6030

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1818 top1= 93.5938
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1500 top1= 95.7812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1680 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7227 top1= 84.6554


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9446 top1= 49.7196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3213 top1= 45.6731

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1719 top1= 94.2188
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1418 top1= 95.7812
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1585 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7204 top1= 84.1747


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8746 top1= 49.6394


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2837 top1= 45.7632

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1651 top1= 94.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1384 top1= 96.4062
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1482 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7187 top1= 83.6538


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8488 top1= 49.4992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2955 top1= 45.7732

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1623 top1= 94.8438
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1329 top1= 96.4062
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1408 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7188 top1= 83.4836


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8369 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2687 top1= 45.7432

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1575 top1= 95.3125
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1234 top1= 97.0312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1341 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7182 top1= 83.2933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8241 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1973 top1= 45.7732

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1494 top1= 95.0000
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1157 top1= 96.8750
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1310 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7100 top1= 83.6038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8083 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2240 top1= 45.8433

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1397 top1= 95.9375
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1134 top1= 97.1875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1283 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7003 top1= 84.0445


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7738 top1= 50.1102


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2323 top1= 45.9135

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1308 top1= 96.0938
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1108 top1= 97.3438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1241 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7062 top1= 83.5938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7410 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1925 top1= 45.7632

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1326 top1= 95.6250
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1084 top1= 97.8125
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1220 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7047 top1= 83.8141


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6992 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2158 top1= 45.8133

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1310 top1= 96.0938
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1077 top1= 97.6562
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1234 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7138 top1= 83.1530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6924 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1857 top1= 45.7232

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1315 top1= 96.0938
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1109 top1= 97.6562
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1258 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7214 top1= 82.4319


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6626 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1752 top1= 45.6130

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1347 top1= 95.9375
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1234 top1= 96.8750
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1306 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7272 top1= 82.4319


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6759 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1598 top1= 45.4527

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1471 top1= 95.3125
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1316 top1= 96.4062
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1417 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7223 top1= 83.1030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6891 top1= 49.6194


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1713 top1= 45.8934

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1475 top1= 95.6250
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1258 top1= 96.5625
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1442 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7191 top1= 81.5405


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6651 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0814 top1= 46.2340

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1185 top1= 96.7188
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1003 top1= 97.8125
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1342 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7143 top1= 82.0212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6316 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0524 top1= 46.3642

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1033 top1= 96.5625
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1020 top1= 97.6562
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1174 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7004 top1= 84.0745


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6570 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0301 top1= 46.3642

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1026 top1= 97.0312
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0979 top1= 97.6562
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1122 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6874 top1= 84.9659


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6304 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0960 top1= 46.2340

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1055 top1= 96.5625
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0973 top1= 97.6562
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1212 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7033 top1= 83.7740


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6321 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9875 top1= 46.4042

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1038 top1= 97.0312
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0949 top1= 98.1250
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1337 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7152 top1= 82.1314


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6425 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9418 top1= 46.2440

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1067 top1= 96.4062
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1061 top1= 97.3438
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1224 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7131 top1= 81.9511


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6794 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9989 top1= 46.1739

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1084 top1= 96.7188
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1174 top1= 96.7188
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1211 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7209 top1= 82.3618


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6760 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0587 top1= 45.8333

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1321 top1= 95.6250
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.1291 top1= 95.9375
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1245 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7669 top1= 80.4988


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6875 top1= 49.5893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0197 top1= 45.2424

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1647 top1= 93.5938
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1212 top1= 96.5625
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1555 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7064 top1= 84.1546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6167 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0947 top1= 45.7732

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1260 top1= 96.0938
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0966 top1= 97.1875
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1123 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6954 top1= 84.2748


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6179 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0698 top1= 46.2039

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1009 top1= 97.3438
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0933 top1= 97.8125
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1063 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7103 top1= 82.8425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6636 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9596 top1= 46.2240

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1045 top1= 97.0312
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0966 top1= 97.5000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1110 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7126 top1= 82.7724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6394 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9089 top1= 46.2640

