
=== 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 0x7f6d1ac0d9d0>

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: 1.3766 top1= 52.1875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.8016 top1= 73.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3641 top1= 75.7712


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0443 top1= 48.3474


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0389 top1= 41.2760

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.4857 top1= 86.2500
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4063 top1= 88.1250
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2431 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0287 top1= 80.8794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8729 top1= 49.3890


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6197 top1= 44.3810

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.2479 top1= 94.0625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2850 top1= 90.9375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2062 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9097 top1= 83.6038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1448 top1= 49.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9064 top1= 44.9319

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2320 top1= 93.1250
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2199 top1= 92.1875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1652 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8596 top1= 83.8542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3381 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1066 top1= 45.4627

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1783 top1= 95.3125
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1745 top1= 93.4375
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1419 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8112 top1= 84.2849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3753 top1= 49.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2186 top1= 45.5629

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1394 top1= 95.0000
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1481 top1= 94.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1098 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7690 top1= 85.2764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4924 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3212 top1= 45.6631

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1324 top1= 96.5625
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1331 top1= 95.6250
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.1120 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7368 top1= 85.1262


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6740 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5405 top1= 45.5629

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1242 top1= 96.2500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1143 top1= 95.3125
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0994 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7361 top1= 85.3466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6001 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4160 top1= 45.9635

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.1211 top1= 96.2500
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1201 top1= 95.6250
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0718 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7142 top1= 85.6771


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6075 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3974 top1= 46.1238

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0982 top1= 96.2500
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0940 top1= 96.2500
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0595 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7095 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6222 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4665 top1= 46.2340

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0892 top1= 97.5000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0836 top1= 96.5625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0723 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6907 top1= 86.2881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6442 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5863 top1= 46.3041

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0812 top1= 97.1875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0713 top1= 98.4375
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0590 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6649 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7037 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6182 top1= 46.4143

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0633 top1= 98.1250
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0716 top1= 97.5000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0648 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6602 top1= 86.2981


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8546 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8465 top1= 46.3942

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0603 top1= 97.8125
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0629 top1= 98.1250
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0570 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6398 top1= 87.2596


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8906 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7361 top1= 46.4744

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0620 top1= 98.1250
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0642 top1= 98.4375
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0390 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6445 top1= 86.9491


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9219 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7115 top1= 46.5946

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0635 top1= 97.8125
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0564 top1= 98.7500
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0294 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6351 top1= 87.0493


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9606 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7166 top1= 46.6046

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0473 top1= 98.7500
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0505 top1= 98.7500
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0313 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6255 top1= 87.3498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8545 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7991 top1= 46.6747

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0426 top1= 99.0625
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0463 top1= 98.1250
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0340 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6230 top1= 87.3598


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9582 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8727 top1= 46.7047

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0497 top1= 98.1250
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0406 top1= 98.7500
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0229 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6002 top1= 87.4399


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0567 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0574 top1= 46.8650

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0349 top1= 98.7500
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0390 top1= 99.0625
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0228 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5915 top1= 87.6002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1034 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1110 top1= 46.8550

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0436 top1= 98.4375
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0354 top1= 99.3750
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0225 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5885 top1= 87.6903


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1669 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0714 top1= 46.8850

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0346 top1= 98.4375
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0332 top1= 98.7500
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5839 top1= 87.7905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1326 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9965 top1= 47.0252

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0360 top1= 99.0625
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0323 top1= 99.0625
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0184 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5874 top1= 87.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1112 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0339 top1= 47.0052

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0344 top1= 99.3750
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0276 top1= 99.3750
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0198 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5852 top1= 87.4199


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0669 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0820 top1= 47.0453

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0280 top1= 99.6875
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0301 top1= 99.3750
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0149 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5648 top1= 87.7304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2114 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3040 top1= 47.0753

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0183 top1= 99.6875
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0184 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0140 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5660 top1= 87.2796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2664 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3197 top1= 47.0252

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0258 top1= 99.3750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0264 top1= 99.3750
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0121 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5524 top1= 88.3313


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2882 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2376 top1= 47.1755

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0196 top1= 99.3750
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0226 top1= 99.3750
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0118 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5448 top1= 88.0709


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2346 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2048 top1= 47.0753

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0215 top1= 99.3750
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0217 top1= 99.3750
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0131 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5567 top1= 88.2812


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3474 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2109 top1= 47.1855

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0215 top1= 99.3750
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0163 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0102 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5393 top1= 88.9223


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2116 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2614 top1= 47.1755

