
=== 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 0x7f0d506d09d0>

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: 1.3714 top1= 52.5000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.9099 top1= 70.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3996 top1= 79.1667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9831 top1= 48.2672


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7516 top1= 43.0789

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.5727 top1= 83.1250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4671 top1= 85.6250
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2278 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0431 top1= 81.1498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7145 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5266 top1= 44.3109

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.2529 top1= 93.4375
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2873 top1= 90.3125
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1770 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9348 top1= 83.0128


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0169 top1= 49.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5574 top1= 44.5012

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.3543 top1= 88.4375
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2157 top1= 92.8125
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1449 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8775 top1= 83.8542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1237 top1= 49.8798


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8529 top1= 45.3626

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1723 top1= 95.9375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1746 top1= 93.4375
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1199 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8245 top1= 84.2047


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2482 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0188 top1= 45.5228

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1526 top1= 95.0000
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1552 top1= 93.4375
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1056 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7852 top1= 85.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3038 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1883 top1= 45.7532

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1354 top1= 96.5625
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1268 top1= 95.3125
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0992 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7459 top1= 85.5168


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5139 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3515 top1= 45.8834

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1222 top1= 95.6250
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1138 top1= 95.3125
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0843 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7449 top1= 85.1763


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4597 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2624 top1= 45.9936

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.1084 top1= 96.8750
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1374 top1= 95.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0742 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7305 top1= 85.2764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4770 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2148 top1= 46.1038

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0909 top1= 96.8750
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0859 top1= 97.1875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0602 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7186 top1= 85.7672


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5562 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3459 top1= 46.1839

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0891 top1= 97.1875
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0713 top1= 97.1875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0685 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7018 top1= 86.1378


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5671 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4427 top1= 46.3041

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0809 top1= 97.1875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0680 top1= 98.7500
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0534 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6809 top1= 86.7188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5756 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4927 top1= 46.4042

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0665 top1= 98.1250
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0713 top1= 97.8125
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0454 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6664 top1= 86.0978


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7366 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7463 top1= 46.4343

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0620 top1= 98.4375
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0548 top1= 98.4375
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0463 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6486 top1= 86.8590


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7532 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6785 top1= 46.4643

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0572 top1= 98.4375
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0559 top1= 97.5000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0386 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6565 top1= 86.8389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7875 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7106 top1= 46.6246

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0598 top1= 98.1250
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0525 top1= 98.4375
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0324 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6355 top1= 87.5300


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8320 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5839 top1= 46.6146

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0468 top1= 99.3750
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0478 top1= 99.0625
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0280 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6370 top1= 87.3598


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7066 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6672 top1= 46.7748

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0443 top1= 99.6875
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0399 top1= 98.7500
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0349 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6321 top1= 87.5601


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8183 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7834 top1= 46.8149

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0568 top1= 98.7500
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0375 top1= 98.7500
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0218 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6085 top1= 87.1795


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9314 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9796 top1= 46.9050

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0352 top1= 99.3750
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0355 top1= 99.0625
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0224 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6025 top1= 87.3998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9560 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0498 top1= 46.8550

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0388 top1= 99.0625
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0403 top1= 98.7500
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0217 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6006 top1= 87.3898


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9856 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0225 top1= 47.0052

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0345 top1= 99.3750
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0319 top1= 99.3750
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0260 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6007 top1= 87.4700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0075 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9770 top1= 47.0453

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0361 top1= 99.3750
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0323 top1= 99.0625
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0169 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6032 top1= 87.2296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9762 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9399 top1= 47.0954

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0351 top1= 99.3750
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0275 top1= 99.3750
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0192 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5959 top1= 87.3998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9024 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9616 top1= 47.1454

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0296 top1= 99.6875
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0265 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0147 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5731 top1= 87.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0453 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1339 top1= 47.1154

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0201 top1= 99.6875
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0184 top1= 99.6875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0127 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5717 top1= 87.2095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1141 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2131 top1= 47.0753

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0281 top1= 99.3750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0220 top1= 99.6875
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0221 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5616 top1= 88.1010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0463 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1774 top1= 47.2155

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0231 top1= 99.3750
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0195 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0110 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5613 top1= 87.8806


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1040 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1198 top1= 47.2256

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0243 top1= 99.3750
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0304 top1= 99.0625
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0118 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5739 top1= 87.9808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1825 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1172 top1= 47.2256

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0249 top1= 99.6875
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0185 top1= 99.6875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0109 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5610 top1= 87.9708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0103 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1261 top1= 47.2356

