
=== 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 0x7f72c8b6c9d0>

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: 1.4418 top1= 48.4375
[E 1B20 |   8064/60000 ( 13%) ] Loss: 1.1593 top1= 56.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4622 top1= 65.6751


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6801 top1= 47.6062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3088 top1= 39.8938

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.8995 top1= 69.6875
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4847 top1= 87.1875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.4350 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0710 top1= 73.3073


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2577 top1= 49.1386


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6417 top1= 44.1807

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3569 top1= 91.5625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3316 top1= 89.3750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2354 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9277 top1= 75.0501


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7825 top1= 49.6294


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0786 top1= 44.7015

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2849 top1= 90.9375
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.3079 top1= 88.4375
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.2986 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9277 top1= 70.2424


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9705 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6087 top1= 45.1222

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.2166 top1= 94.3750
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.2403 top1= 92.1875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.2260 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9011 top1= 68.2091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0882 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7215 top1= 45.3526

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.3389 top1= 89.3750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.3039 top1= 89.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1609 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8856 top1= 66.2360


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2153 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5330 top1= 45.5829

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.2026 top1= 91.8750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1669 top1= 95.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.1711 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8918 top1= 65.0040


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4250 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7048 top1= 45.7632

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1760 top1= 95.3125
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1821 top1= 93.7500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.1729 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9134 top1= 63.3113


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5154 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4027 top1= 45.2224

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.3505 top1= 88.7500
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1721 top1= 95.3125
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.1297 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9065 top1= 63.8421


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4635 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2627 top1= 46.0136

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1831 top1= 93.7500
[E10B10 |   4224/60000 (  7%) ] Loss: 0.4052 top1= 88.4375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.1980 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8682 top1= 66.2660


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9193 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9760 top1= 47.5761

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.1457 top1= 95.9375
[E11B10 |   4224/60000 (  7%) ] Loss: 0.1456 top1= 96.5625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.1615 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8698 top1= 65.6150


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0555 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2309 top1= 46.8349

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.1709 top1= 94.3750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.2421 top1= 93.7500
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.1375 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8839 top1= 64.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2399 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2334 top1= 46.9651

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.2421 top1= 91.5625
[E13B10 |   4224/60000 (  7%) ] Loss: 0.1482 top1= 95.6250
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.1397 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9341 top1= 62.5401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4799 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1611 top1= 47.7664

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.1506 top1= 94.3750
[E14B10 |   4224/60000 (  7%) ] Loss: 0.1414 top1= 95.3125
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.2607 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9623 top1= 61.3181


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4861 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9111 top1= 49.2288

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.1500 top1= 95.9375
[E15B10 |   4224/60000 (  7%) ] Loss: 0.2007 top1= 95.3125
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.1157 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9830 top1= 60.7772


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5775 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9892 top1= 48.6078

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.1909 top1= 93.1250
[E16B10 |   4224/60000 (  7%) ] Loss: 0.3429 top1= 91.2500
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.3436 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9372 top1= 62.6002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6033 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7129 top1= 50.0801

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.1586 top1= 95.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.1459 top1= 95.9375
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.1224 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8499 top1= 65.3045


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4347 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0770 top1= 48.8582

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.1086 top1= 95.9375
[E18B10 |   4224/60000 (  7%) ] Loss: 0.1212 top1= 95.6250
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1429 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9230 top1= 63.1410


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6042 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1184 top1= 48.8081

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.1938 top1= 92.1875
[E19B10 |   4224/60000 (  7%) ] Loss: 0.2439 top1= 92.1875
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1064 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9202 top1= 62.4099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7058 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8434 top1= 50.7913

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.1008 top1= 96.2500
[E20B10 |   4224/60000 (  7%) ] Loss: 0.1253 top1= 96.2500
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.1119 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9412 top1= 62.9107


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7517 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9801 top1= 49.0485

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.2409 top1= 91.5625
[E21B10 |   4224/60000 (  7%) ] Loss: 0.2004 top1= 94.6875
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1275 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9313 top1= 62.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8031 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9342 top1= 50.5909

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.1303 top1= 96.2500
[E22B10 |   4224/60000 (  7%) ] Loss: 0.2321 top1= 94.6875
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.1350 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0222 top1= 59.4952


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8188 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8385 top1= 51.2220

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.1948 top1= 92.8125
[E23B10 |   4224/60000 (  7%) ] Loss: 0.2417 top1= 94.6875
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.1257 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0433 top1= 61.4984


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6376 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7421 top1= 51.6126

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.1947 top1= 94.6875
[E24B10 |   4224/60000 (  7%) ] Loss: 0.1720 top1= 94.6875
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.1181 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9151 top1= 63.1510


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7276 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7455 top1= 51.8129

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0814 top1= 97.8125
[E25B10 |   4224/60000 (  7%) ] Loss: 0.1483 top1= 94.6875
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0901 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9184 top1= 63.7119


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8683 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9586 top1= 50.3906

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.1493 top1= 94.0625
[E26B10 |   4224/60000 (  7%) ] Loss: 0.1605 top1= 95.6250
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.1175 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0101 top1= 61.3181


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9193 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8054 top1= 51.7728

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.1650 top1= 95.3125
[E27B10 |   4224/60000 (  7%) ] Loss: 0.1566 top1= 95.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.1623 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0227 top1= 60.1262


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9578 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7195 top1= 53.4655

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.1160 top1= 95.3125
[E28B10 |   4224/60000 (  7%) ] Loss: 0.4219 top1= 92.5000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.1177 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9091 top1= 63.1611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9057 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6355 top1= 53.1350

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0904 top1= 97.5000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.1837 top1= 96.2500
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0949 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9642 top1= 61.4183


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9426 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6729 top1= 53.0849

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.1223 top1= 95.3125
[E30B10 |   4224/60000 (  7%) ] Loss: 0.1720 top1= 94.0625
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.1104 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9070 top1= 63.6518


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8264 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9143 top1= 51.8530

