
=== 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 ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f56376337f0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.2959 top1= 10.0000

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


[E 1B10 |   4224/60000 (  7%) ] Loss: 2.1270 top1= 38.1250
[E 1B20 |   8064/60000 ( 13%) ] Loss: 1.7705 top1= 50.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1648 top1= 77.2937


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1708 top1= 78.0048


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1666 top1= 75.9215

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 1.2980 top1= 60.6250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.9456 top1= 69.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.7482 top1= 79.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5396 top1= 85.6070


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5543 top1= 84.6254


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5393 top1= 86.0577

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.7107 top1= 76.8750
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.5671 top1= 84.6875
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.5198 top1= 84.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4172 top1= 87.9708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4377 top1= 86.5585


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4132 top1= 88.5817

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.5673 top1= 80.0000
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.4810 top1= 86.2500
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.4708 top1= 85.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3486 top1= 90.3646


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3508 top1= 90.1242


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3537 top1= 90.2444

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.4751 top1= 85.3125
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.3694 top1= 89.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.3794 top1= 86.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3249 top1= 90.7051


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3306 top1= 90.4247


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3269 top1= 90.5749

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.4037 top1= 86.5625
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.3186 top1= 91.2500
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.3326 top1= 89.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2946 top1= 91.6366


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2959 top1= 91.4363


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3036 top1= 91.4363

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.3412 top1= 89.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.2468 top1= 93.4375
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.2911 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2700 top1= 92.2676


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2735 top1= 92.0373


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2724 top1= 92.1675

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.2965 top1= 91.5625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.3064 top1= 89.0625
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.2471 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2587 top1= 92.4079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2643 top1= 92.1575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2591 top1= 92.4079

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.2453 top1= 91.8750
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.2093 top1= 96.2500
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.2214 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2474 top1= 92.7684


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2500 top1= 92.7985


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2501 top1= 92.6082

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.2654 top1= 91.2500
[E10B10 |   4224/60000 (  7%) ] Loss: 0.1959 top1= 95.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.2338 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2311 top1= 93.2792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2310 top1= 93.1290


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2396 top1= 93.2091

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.2451 top1= 92.5000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.1996 top1= 95.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.1893 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2211 top1= 93.5797


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2245 top1= 93.2993


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2234 top1= 93.5497

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.2220 top1= 93.7500
[E12B10 |   4224/60000 (  7%) ] Loss: 0.1708 top1= 95.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.1842 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2110 top1= 93.8802


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2145 top1= 93.8101


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2122 top1= 93.8602

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.1806 top1= 93.4375
[E13B10 |   4224/60000 (  7%) ] Loss: 0.1455 top1= 96.2500
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.1692 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2006 top1= 93.9603


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2043 top1= 93.8101


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2018 top1= 94.1506

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.1510 top1= 95.6250
[E14B10 |   4224/60000 (  7%) ] Loss: 0.1219 top1= 97.1875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.1458 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1984 top1= 94.0304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2016 top1= 93.8802


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2011 top1= 94.0104

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.1807 top1= 95.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.1227 top1= 96.8750
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.1545 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1858 top1= 94.5813


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1900 top1= 94.4211


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1863 top1= 94.6114

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.1563 top1= 95.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.1336 top1= 96.2500
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.1400 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1859 top1= 94.5112


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1844 top1= 94.4411


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1937 top1= 94.2308

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.1423 top1= 95.3125
[E17B10 |   4224/60000 (  7%) ] Loss: 0.1096 top1= 98.1250
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.1406 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1757 top1= 94.7416


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1787 top1= 94.6214


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1774 top1= 94.9219

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.1439 top1= 95.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.1102 top1= 96.2500
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1142 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1693 top1= 94.9619


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1730 top1= 94.6615


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1716 top1= 95.0321

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.1307 top1= 95.3125
[E19B10 |   4224/60000 (  7%) ] Loss: 0.1151 top1= 97.8125
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1176 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1668 top1= 94.9920


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1675 top1= 94.7216


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1706 top1= 94.9419

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0978 top1= 96.2500
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0736 top1= 98.4375
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0905 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1626 top1= 95.1122


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1624 top1= 95.0020


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1711 top1= 94.9920

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.1148 top1= 96.5625
[E21B10 |   4224/60000 (  7%) ] Loss: 0.1081 top1= 96.8750
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1089 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1656 top1= 94.9419


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1686 top1= 94.8417


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1665 top1= 95.0020

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.1060 top1= 96.8750
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0950 top1= 97.5000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0957 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1559 top1= 95.4227


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1542 top1= 95.3826


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1619 top1= 95.3425

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0865 top1= 97.5000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0909 top1= 98.4375
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0966 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1513 top1= 95.5128


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1487 top1= 95.5429


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1594 top1= 95.1823

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.1075 top1= 95.9375
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0846 top1= 98.1250
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0852 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1473 top1= 95.6130


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1532 top1= 95.3626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1464 top1= 95.6731

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0966 top1= 96.5625
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0748 top1= 98.1250
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0934 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1438 top1= 95.6731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1446 top1= 95.4828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1469 top1= 95.7332

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0314 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0290 top1= 99.6875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0307 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1467 top1= 95.4728


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1490 top1= 95.4026


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1510 top1= 95.4327

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0717 top1= 98.4375
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0724 top1= 98.4375
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0702 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1413 top1= 95.7532


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1402 top1= 95.6831


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1460 top1= 95.5929

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0800 top1= 97.5000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0821 top1= 97.8125
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0605 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1404 top1= 95.6931


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1449 top1= 95.5429


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1420 top1= 95.7632

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0629 top1= 98.4375
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0553 top1= 99.0625
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0550 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1323 top1= 96.0337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1326 top1= 95.8033


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1364 top1= 96.0236

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0755 top1= 97.1875
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0592 top1= 98.4375
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0658 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1288 top1= 96.0136


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1306 top1= 96.0437


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1314 top1= 95.8333

