
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7fd8022297f0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0620 top1= 64.3750
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2776 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6807 top1= 79.2167


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5540 top1= 48.8782


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9633 top1= 43.7901

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3442 top1= 90.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3199 top1= 90.0000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1774 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5368 top1= 86.5485


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5188 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6004 top1= 45.5729

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1621 top1= 96.2500
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1592 top1= 95.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1190 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4728 top1= 86.9591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2769 top1= 52.5341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3378 top1= 46.8450

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1352 top1= 96.2500
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1178 top1= 95.9375
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0937 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4426 top1= 87.2095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2049 top1= 52.9147


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2019 top1= 48.0268

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1106 top1= 96.5625
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0983 top1= 96.8750
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0772 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4290 top1= 87.4099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1885 top1= 53.2853


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1753 top1= 48.3574

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0987 top1= 97.1875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0875 top1= 96.8750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0675 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4246 top1= 87.5901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1672 top1= 53.5457


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1595 top1= 48.7079

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0900 top1= 97.8125
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0786 top1= 97.5000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0640 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4253 top1= 87.5401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1628 top1= 53.2853


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1533 top1= 48.7881

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0863 top1= 98.4375
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0766 top1= 97.8125
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0589 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4300 top1= 87.5501


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1560 top1= 52.8345


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1499 top1= 48.5877

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0801 top1= 98.4375
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0775 top1= 97.5000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0624 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4479 top1= 86.6486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2018 top1= 52.1635


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1577 top1= 48.3574

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0769 top1= 98.4375
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0734 top1= 97.8125
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0632 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4649 top1= 86.1879


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2045 top1= 51.7728


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1971 top1= 48.0869

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0801 top1= 98.4375
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0788 top1= 97.5000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0652 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4877 top1= 85.5268


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2264 top1= 51.3321


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2546 top1= 46.9251

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0994 top1= 97.1875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0988 top1= 96.2500
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0687 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5071 top1= 85.2664


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2237 top1= 51.0417


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3203 top1= 46.3942

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.1086 top1= 96.5625
[E13B10 |   4224/60000 (  7%) ] Loss: 0.1232 top1= 95.3125
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0882 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5407 top1= 84.4651


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2043 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3948 top1= 45.8634

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.1167 top1= 97.1875
[E14B10 |   4224/60000 (  7%) ] Loss: 0.1265 top1= 95.9375
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.1089 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5749 top1= 83.5337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2319 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5867 top1= 45.5329

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.1114 top1= 96.5625
[E15B10 |   4224/60000 (  7%) ] Loss: 0.1148 top1= 96.5625
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0990 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5759 top1= 84.5453


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2534 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5357 top1= 45.4828

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.1257 top1= 96.5625
[E16B10 |   4224/60000 (  7%) ] Loss: 0.1332 top1= 95.3125
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0967 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5958 top1= 83.9143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2474 top1= 49.9099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6427 top1= 44.2208

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.1681 top1= 95.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.1517 top1= 94.3750
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.1277 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6169 top1= 83.4034


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2058 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4146 top1= 45.1723

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.1247 top1= 96.8750
[E18B10 |   4224/60000 (  7%) ] Loss: 0.1497 top1= 95.3125
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1100 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6172 top1= 84.3950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2145 top1= 49.9099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4433 top1= 45.6831

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.1137 top1= 98.1250
[E19B10 |   4224/60000 (  7%) ] Loss: 0.1456 top1= 96.2500
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1029 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6202 top1= 84.6354


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2334 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6029 top1= 44.9820

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.1461 top1= 96.5625
[E20B10 |   4224/60000 (  7%) ] Loss: 0.1600 top1= 95.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.1197 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6431 top1= 83.4034


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2127 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6566 top1= 44.2508

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.1726 top1= 95.6250
[E21B10 |   4224/60000 (  7%) ] Loss: 0.1945 top1= 93.4375
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1855 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6580 top1= 82.6122


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1596 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5771 top1= 45.5929

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.1177 top1= 96.8750
[E22B10 |   4224/60000 (  7%) ] Loss: 0.1629 top1= 95.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.1249 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6471 top1= 83.7640


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1754 top1= 49.7496


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5048 top1= 45.5228

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.1238 top1= 97.1875
[E23B10 |   4224/60000 (  7%) ] Loss: 0.1570 top1= 95.3125
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.1124 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6436 top1= 83.9443


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1764 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6092 top1= 44.9119

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.1503 top1= 95.9375
[E24B10 |   4224/60000 (  7%) ] Loss: 0.1734 top1= 94.3750
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.1088 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6434 top1= 84.1346


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1811 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6248 top1= 44.5713

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.1668 top1= 95.6250
[E25B10 |   4224/60000 (  7%) ] Loss: 0.1831 top1= 93.4375
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.1223 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6604 top1= 82.9527


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1574 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6215 top1= 44.6915

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.1499 top1= 96.5625
[E26B10 |   4224/60000 (  7%) ] Loss: 0.1872 top1= 94.0625
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.1659 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6716 top1= 82.4820


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1356 top1= 49.7396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4834 top1= 45.4627

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.1122 top1= 98.4375
[E27B10 |   4224/60000 (  7%) ] Loss: 0.1568 top1= 95.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.1393 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6674 top1= 82.9026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1526 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5063 top1= 45.2224

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.1280 top1= 97.1875
[E28B10 |   4224/60000 (  7%) ] Loss: 0.1643 top1= 94.6875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.1281 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6575 top1= 83.6338


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1634 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5850 top1= 45.0020

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.1487 top1= 95.9375
[E29B10 |   4224/60000 (  7%) ] Loss: 0.1777 top1= 94.0625
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.1230 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6550 top1= 84.3450


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1527 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6514 top1= 44.7416

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.1551 top1= 96.2500
[E30B10 |   4224/60000 (  7%) ] Loss: 0.1619 top1= 94.3750
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.1303 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6638 top1= 83.5637


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1264 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5969 top1= 44.6715

