
=== 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 0x7f4cf4524490>

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: 1.1836 top1= 58.2812
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4151 top1= 86.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8445 top1= 73.4876


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8070 top1= 49.1386


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8162 top1= 43.6198

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2980 top1= 90.1562
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2343 top1= 94.0625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2394 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7507 top1= 80.7692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7343 top1= 49.6294


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2804 top1= 45.5429

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2267 top1= 92.9688
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1812 top1= 95.3125
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2016 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6648 top1= 82.8425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5492 top1= 49.6094


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1611 top1= 45.7632

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1998 top1= 93.7500
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1623 top1= 95.3125
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1823 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6278 top1= 83.8041


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4558 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0500 top1= 45.7532

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1850 top1= 94.6875
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1463 top1= 95.9375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1691 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6145 top1= 83.8542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4123 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0022 top1= 45.8534

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1744 top1= 95.0000
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1343 top1= 96.8750
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1633 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6043 top1= 84.5553


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3972 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9662 top1= 45.9435

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1657 top1= 95.9375
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1253 top1= 97.3438
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1531 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6011 top1= 84.4752


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3806 top1= 49.8798


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9478 top1= 46.0036

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1574 top1= 95.6250
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1187 top1= 97.6562
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1482 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5972 top1= 84.4952


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3621 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9294 top1= 46.0637

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1541 top1= 95.6250
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1133 top1= 97.5000
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1424 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5947 top1= 84.5353


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3581 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9340 top1= 46.0938

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1476 top1= 96.0938
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1092 top1= 97.6562
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1344 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5963 top1= 84.3650


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3369 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9265 top1= 46.0537

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1442 top1= 95.6250
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1069 top1= 97.5000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1327 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5936 top1= 84.6454


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3170 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9268 top1= 46.1839

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1396 top1= 96.2500
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1062 top1= 97.1875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1295 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5938 top1= 84.4952


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3027 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9117 top1= 46.1038

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1400 top1= 95.4688
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1027 top1= 97.8125
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1290 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5970 top1= 83.9844


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2859 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9256 top1= 45.9535

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1462 top1= 95.3125
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1045 top1= 97.5000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1282 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5962 top1= 83.8041


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2770 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9883 top1= 45.9235

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1417 top1= 95.4688
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1074 top1= 97.3438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1307 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5997 top1= 83.8942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2633 top1= 50.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8206 top1= 46.1038

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1351 top1= 96.4062
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1081 top1= 97.3438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1348 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6030 top1= 84.2748


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2425 top1= 50.0300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8490 top1= 45.6931

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1524 top1= 95.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1178 top1= 97.0312
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1360 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6025 top1= 83.4335


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2516 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0218 top1= 45.5028

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1633 top1= 94.2188
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1153 top1= 96.7188
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1495 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6006 top1= 83.8041


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2502 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9417 top1= 45.8433

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1424 top1= 95.4688
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1302 top1= 95.9375
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1637 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5957 top1= 84.8658


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2429 top1= 50.1102


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8451 top1= 46.0637

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1277 top1= 96.2500
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1164 top1= 96.8750
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1626 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5828 top1= 85.7973


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2486 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8568 top1= 46.0136

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1306 top1= 95.7812
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1164 top1= 96.8750
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1343 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5782 top1= 86.0276


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2796 top1= 49.9299


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7650 top1= 46.3141

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1273 top1= 96.4062
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.1188 top1= 97.0312
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1314 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5821 top1= 85.9475


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2997 top1= 49.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7456 top1= 46.3041

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1315 top1= 96.5625
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.1178 top1= 96.7188
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1190 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5948 top1= 85.0561


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3195 top1= 49.2188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7058 top1= 46.2540

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1421 top1= 95.9375
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1088 top1= 96.7188
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1193 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6052 top1= 84.5453


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3065 top1= 49.1286


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6792 top1= 46.1038

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1487 top1= 95.9375
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1027 top1= 97.0312
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1259 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6071 top1= 84.2548


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3004 top1= 49.6394


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7377 top1= 46.0537

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1490 top1= 95.9375
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.1136 top1= 96.4062
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1492 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5994 top1= 84.7756


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3134 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6948 top1= 46.1438

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1329 top1= 96.0938
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1198 top1= 95.9375
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1784 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5932 top1= 85.0160


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2742 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6980 top1= 46.1739

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1224 top1= 96.0938
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.1121 top1= 96.5625
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1200 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5946 top1= 84.3650


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2427 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8430 top1= 45.4627

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1493 top1= 95.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.1132 top1= 96.4062
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1213 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6012 top1= 83.9944


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2312 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7801 top1= 45.9435

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1407 top1= 95.3125
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1016 top1= 97.3438
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1259 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6079 top1= 83.7540


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2335 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8317 top1= 45.7833

