
=== 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 0x7f1f058762b0>

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=0.8005 top1= 80.4087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1765 top1= 49.1687


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1105 top1= 43.8602

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2887 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= 85.1462


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4112 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5447 top1= 45.3726

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2105 top1= 94.0625
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1717 top1= 95.7812
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1950 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7613 top1= 85.5168


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1691 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4716 top1= 45.5429

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1931 top1= 93.2812
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1562 top1= 95.7812
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1755 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7315 top1= 85.1162


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0224 top1= 49.7296


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3392 top1= 45.5929

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1813 top1= 93.5938
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1499 top1= 95.7812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1665 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7214 top1= 84.8157


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9437 top1= 49.7396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3005 top1= 45.6230

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1713 top1= 94.0625
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1415 top1= 95.7812
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1592 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7203 top1= 84.0745


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8769 top1= 49.6595


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2651 top1= 45.7833

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1645 top1= 94.5312
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1375 top1= 96.4062
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1474 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7187 top1= 83.8041


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8460 top1= 49.5292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2821 top1= 45.8033

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1600 top1= 95.0000
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1338 top1= 96.7188
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1412 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7205 top1= 83.5136


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8423 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2497 top1= 45.7632

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1580 top1= 95.0000
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1253 top1= 97.0312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1332 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7151 top1= 83.7841


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8098 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2165 top1= 45.7232

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1499 top1= 95.3125
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1179 top1= 97.1875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1287 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7117 top1= 83.4235


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8002 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1961 top1= 45.7632

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1409 top1= 95.6250
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1137 top1= 97.3438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1267 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7078 top1= 83.5337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7706 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2098 top1= 45.8734

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1316 top1= 96.2500
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1117 top1= 97.3438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1249 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7059 top1= 83.5437


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7438 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2130 top1= 45.7632

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1324 top1= 96.2500
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1107 top1= 97.5000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1232 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7122 top1= 83.1230


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7139 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1826 top1= 45.6230

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1363 top1= 95.7812
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1097 top1= 97.6562
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1250 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7193 top1= 82.9227


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6779 top1= 50.1102


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1557 top1= 45.5829

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1351 top1= 95.6250
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1142 top1= 97.1875
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1297 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7376 top1= 81.7107


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6816 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1158 top1= 45.3926

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1432 top1= 95.3125
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1283 top1= 96.7188
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1437 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7166 top1= 82.4519


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6749 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1755 top1= 45.7732

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1304 top1= 95.7812
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1237 top1= 97.0312
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1461 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7180 top1= 82.0513


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6753 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0611 top1= 46.2440

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1178 top1= 96.5625
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1309 top1= 96.8750
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1270 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7320 top1= 81.2800


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7107 top1= 49.3490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0359 top1= 46.3041

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1318 top1= 96.0938
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1084 top1= 97.5000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1279 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7152 top1= 82.3017


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6496 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9620 top1= 46.2039

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1121 top1= 96.7188
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1009 top1= 97.5000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1122 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6963 top1= 83.5337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6803 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0552 top1= 46.2640

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1048 top1= 97.0312
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0971 top1= 97.8125
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1194 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7073 top1= 83.8141


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6653 top1= 50.2704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9747 top1= 46.2941

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1051 top1= 96.8750
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0971 top1= 97.5000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1264 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7168 top1= 82.8926


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6442 top1= 50.2404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9040 top1= 46.2240

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1100 top1= 96.5625
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.1001 top1= 97.5000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1202 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7254 top1= 81.8910


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6347 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9848 top1= 46.0236

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1185 top1= 96.4062
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1111 top1= 97.3438
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1257 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7378 top1= 81.1398


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6347 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0975 top1= 45.4828

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1413 top1= 95.1562
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1232 top1= 96.2500
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1381 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7261 top1= 82.5120


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6412 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1769 top1= 45.6430

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1349 top1= 95.7812
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.1312 top1= 95.6250
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1447 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7047 top1= 84.2348


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6756 top1= 49.9299


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1183 top1= 45.9235

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1264 top1= 96.0938
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1196 top1= 96.5625
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1102 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7059 top1= 84.2047


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6896 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0172 top1= 46.1438

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1305 top1= 95.9375
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0965 top1= 97.5000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1116 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7049 top1= 84.1546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6459 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9310 top1= 46.1939

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1056 top1= 97.0312
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0930 top1= 97.5000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1109 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7150 top1= 83.2332


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6584 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9607 top1= 46.1939

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1084 top1= 97.0312
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0987 top1= 97.5000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1110 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7270 top1= 82.2616


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6500 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0142 top1= 45.8433

