
=== 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 0x7f403e8e89d0>

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: 0.9969 top1= 63.7500
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2654 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8657 top1= 67.6082


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.9627 top1= 48.6378


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1644 top1= 43.9303

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3900 top1= 90.9375
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2683 top1= 92.5000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1534 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7581 top1= 75.8113


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1480 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8083 top1= 45.4828

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1468 top1= 95.3125
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1218 top1= 95.6250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0830 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7223 top1= 73.3674


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8379 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7284 top1= 46.0236

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0848 top1= 96.8750
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0699 top1= 97.5000
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0540 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7109 top1= 72.6863


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9337 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5157 top1= 45.9736

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0477 top1= 98.1250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0445 top1= 98.7500
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0278 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7146 top1= 72.5361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0769 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3604 top1= 46.3442

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0256 top1= 99.6875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0340 top1= 98.7500
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0212 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7600 top1= 71.5244


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2470 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1898 top1= 47.2556

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0143 top1=100.0000
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0169 top1=100.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0252 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7558 top1= 72.3157


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3643 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0490 top1= 48.1270

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0106 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0161 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0115 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7558 top1= 72.9667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4657 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9589 top1= 49.4191

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0135 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0189 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0154 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6902 top1= 75.3205


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4103 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7082 top1= 51.6526

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0077 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0184 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0091 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6106 top1= 77.8045


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2267 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3991 top1= 52.4539

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0107 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0208 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0111 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5392 top1= 81.5805


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9882 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2584 top1= 54.9780

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0067 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0089 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0097 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4712 top1= 84.3049


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6750 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2105 top1= 55.5389

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0121 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0075 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0116 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4357 top1= 85.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3354 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0185 top1= 57.3618

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0067 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0110 top1= 99.6875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0069 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4117 top1= 86.0577


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9868 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8748 top1= 59.3950

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0062 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3793 top1= 87.3798


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5834 top1= 51.1118


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7868 top1= 61.9191

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3497 top1= 88.8622


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2476 top1= 52.2035


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7866 top1= 62.0593

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0092 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0074 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3386 top1= 89.2428


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9429 top1= 53.8762


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7232 top1= 61.9892

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0053 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0169 top1= 99.6875
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0096 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3173 top1= 90.1342


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7061 top1= 55.5990


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7684 top1= 61.9591

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0098 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0123 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3104 top1= 90.2744


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5944 top1= 56.9511


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6236 top1= 65.2143

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0072 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0128 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0189 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2881 top1= 90.9856


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4432 top1= 58.3534


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7300 top1= 62.8506

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0094 top1= 99.6875
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0187 top1= 99.6875
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0104 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2845 top1= 91.1058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3435 top1= 59.0144


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8657 top1= 62.1394

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0114 top1= 99.6875
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0110 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2922 top1= 91.0357


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2299 top1= 60.2764


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7797 top1= 62.9407

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0101 top1= 99.6875
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0212 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2890 top1= 91.2560


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2026 top1= 61.0477


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8733 top1= 61.3181

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0041 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0117 top1= 99.6875
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0352 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2875 top1= 91.4463


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1141 top1= 61.6987


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8499 top1= 58.1731

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0116 top1= 99.6875
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0081 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2766 top1= 91.3862


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9878 top1= 62.6903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5773 top1= 63.5016

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2700 top1= 91.8069


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8547 top1= 63.9323


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2560 top1= 70.5629

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0050 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2722 top1= 91.7468


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6746 top1= 65.4247


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0406 top1= 74.3389

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0030 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2661 top1= 92.1675


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5153 top1= 67.2175


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0453 top1= 74.8498

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0030 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2688 top1= 92.1875


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3787 top1= 69.2808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8968 top1= 78.2652

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0024 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2669 top1= 92.3678


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2715 top1= 71.0837


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8358 top1= 79.6374

