
=== 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 0x7f1f3a62e490>

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: 1.1682 top1= 58.4375
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4157 top1= 87.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8122 top1= 80.1482


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3043 top1= 49.1286


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2141 top1= 43.6498

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.3007 top1= 89.6875
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2261 top1= 94.2188
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2309 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8425 top1= 85.3065


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5776 top1= 49.7997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6646 top1= 45.4627

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2091 top1= 93.9062
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1751 top1= 95.3125
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2001 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7826 top1= 85.6771


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3414 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6299 top1= 45.5629

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1923 top1= 93.4375
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1568 top1= 96.4062
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1781 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7528 top1= 85.1462


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1730 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5017 top1= 45.7532

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1780 top1= 94.3750
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1461 top1= 96.0938
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1649 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7404 top1= 84.7656


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0853 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4357 top1= 45.8333

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1721 top1= 94.3750
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1387 top1= 96.0938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1586 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7399 top1= 83.8341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0219 top1= 49.6895


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4359 top1= 45.7732

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1702 top1= 94.5312
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1377 top1= 96.5625
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1536 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7409 top1= 82.8526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9803 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4293 top1= 45.7833

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1664 top1= 95.1562
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1314 top1= 96.4062
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1449 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7380 top1= 82.2616


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9773 top1= 49.5693


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3947 top1= 45.9034

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1544 top1= 95.4688
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1191 top1= 96.7188
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1388 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7288 top1= 82.7524


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9590 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3322 top1= 45.9335

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1375 top1= 95.9375
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1105 top1= 97.1875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1290 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7275 top1= 82.9227


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9270 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2965 top1= 45.9836

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1293 top1= 96.5625
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1067 top1= 97.5000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1274 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7266 top1= 83.0529


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8989 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3073 top1= 46.0637

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1269 top1= 96.7188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1045 top1= 97.9688
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1213 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7222 top1= 83.0729


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8627 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3556 top1= 46.0437

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1261 top1= 96.2500
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1047 top1= 97.6562
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1245 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7226 top1= 83.2532


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8224 top1= 50.1703


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3136 top1= 46.0437

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1316 top1= 96.2500
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1016 top1= 97.9688
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1266 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7239 top1= 82.9928


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8022 top1= 50.1703


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3298 top1= 45.9736

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1262 top1= 96.4062
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1024 top1= 97.3438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1257 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7353 top1= 82.3217


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8009 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3135 top1= 45.8033

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1309 top1= 96.4062
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1099 top1= 97.3438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1271 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7469 top1= 80.9796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8000 top1= 50.1703


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3477 top1= 45.5228

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1457 top1= 95.6250
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1308 top1= 96.2500
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1317 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7477 top1= 82.1214


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7844 top1= 49.6895


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3330 top1= 45.6831

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1582 top1= 95.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1342 top1= 96.2500
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1507 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7311 top1= 83.5938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7226 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2950 top1= 46.0337

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1300 top1= 95.9375
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1118 top1= 97.1875
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1570 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7162 top1= 83.4736


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7204 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2761 top1= 46.0437

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1106 top1= 96.8750
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1002 top1= 97.9688
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1208 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7206 top1= 83.6338


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7508 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1783 top1= 46.2941

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1027 top1= 97.1875
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1014 top1= 97.3438
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1152 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7206 top1= 83.6939


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7383 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1645 top1= 46.2740

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1114 top1= 96.7188
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0966 top1= 97.6562
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1191 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7234 top1= 83.2031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7322 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1779 top1= 46.2240

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1126 top1= 96.8750
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0954 top1= 97.9688
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1288 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7396 top1= 81.9211


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7288 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1047 top1= 46.2540

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1108 top1= 96.5625
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1023 top1= 97.5000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1338 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7454 top1= 81.9010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7364 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0066 top1= 46.1939

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1184 top1= 96.8750
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1283 top1= 96.4062
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1308 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7730 top1= 79.6975


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7127 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2960 top1= 45.0120

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1764 top1= 94.0625
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.1442 top1= 95.1562
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1634 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7436 top1= 82.5321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6775 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2140 top1= 46.2240

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1338 top1= 95.6250
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1039 top1= 97.3438
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1304 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7193 top1= 84.1046


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6928 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1964 top1= 46.0837

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1142 top1= 96.4062
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.1022 top1= 97.3438
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1169 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7323 top1= 82.9928


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7027 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1316 top1= 46.0637

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1109 top1= 97.3438
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0993 top1= 97.1875
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1143 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7370 top1= 82.4419


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7162 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1578 top1= 46.0337

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1112 top1= 96.2500
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1010 top1= 97.3438
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1144 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7519 top1= 80.8794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7005 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1577 top1= 45.8433

