
=== 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 0x7fe7d43119d0>

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: 1.0301 top1= 67.1875
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2586 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4990 top1= 84.7857


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9683 top1= 50.9916


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2615 top1= 44.9519

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3396 top1= 92.1875
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3338 top1= 90.3125
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1692 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3911 top1= 88.3313


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8109 top1= 56.5104


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8657 top1= 50.7913

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1414 top1= 95.6250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1427 top1= 95.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1003 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3410 top1= 89.5333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5952 top1= 59.4251


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6849 top1= 55.0180

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1107 top1= 95.9375
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0878 top1= 97.8125
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0833 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3106 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6191 top1= 60.7772


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5027 top1= 57.8325

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0614 top1= 98.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0780 top1= 97.1875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0717 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2908 top1= 90.5849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5826 top1= 62.3898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2381 top1= 63.8522

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0436 top1= 98.7500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0600 top1= 97.8125
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0272 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2809 top1= 90.9655


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7408 top1= 61.7889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1418 top1= 67.4379

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0513 top1= 97.8125
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0389 top1= 99.0625
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0306 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2862 top1= 90.7051


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8236 top1= 62.9307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0405 top1= 70.4828

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0218 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0471 top1= 98.1250
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0134 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2751 top1= 91.5164


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6325 top1= 64.9139


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1009 top1= 71.3942

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0140 top1= 99.6875
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0140 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0126 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2930 top1= 91.1959


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6065 top1= 66.3462


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0053 top1= 74.0585

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0099 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0083 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0140 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2889 top1= 91.4463


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3328 top1= 70.2023


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9083 top1= 76.8229

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0128 top1= 99.6875
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0185 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0201 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2846 top1= 91.7067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1079 top1= 73.4776


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9165 top1= 76.6126

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0069 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0340 top1= 98.7500
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0113 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2964 top1= 91.5064


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1985 top1= 72.1855


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9865 top1= 77.4840

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0083 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2793 top1= 92.2075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8076 top1= 79.4671


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0647 top1= 75.5409

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0079 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0059 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2711 top1= 92.4980


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7802 top1= 80.4587


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7186 top1= 82.3618

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0036 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2752 top1= 92.6883


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6772 top1= 83.0629


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7916 top1= 81.2901

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0037 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2756 top1= 92.8786


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6573 top1= 83.7640


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7523 top1= 82.2416

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0024 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2806 top1= 92.7183


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6194 top1= 84.7456


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7679 top1= 82.1314

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0020 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2803 top1= 92.8486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5890 top1= 85.6470


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7022 top1= 83.4535

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2797 top1= 92.9387


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5742 top1= 86.1779


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6559 top1= 84.5553

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2799 top1= 92.9988


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5647 top1= 86.4984


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6234 top1= 85.3365

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2803 top1= 93.0489


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5604 top1= 86.7788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5979 top1= 85.9175

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2810 top1= 93.1691


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5532 top1= 87.0192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5798 top1= 86.3381

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2819 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5469 top1= 87.4099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5651 top1= 86.8590

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2829 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5398 top1= 87.7404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5538 top1= 87.1995

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2840 top1= 93.2792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5323 top1= 88.0509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5456 top1= 87.4299

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2851 top1= 93.2492


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5243 top1= 88.3413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5389 top1= 87.6502

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2862 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5154 top1= 88.5517


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5345 top1= 87.8205

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2872 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5069 top1= 88.7720


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5312 top1= 87.9607

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2884 top1= 93.2993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4980 top1= 88.9824


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5291 top1= 88.1410

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2896 top1= 93.3193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4895 top1= 89.2027


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5276 top1= 88.2612

