
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7ff1ea7759d0>

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: 1.0913 top1= 65.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2830 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5634 top1= 83.5637


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7506 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2428 top1= 44.2107

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3252 top1= 91.5625
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3296 top1= 89.6875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1775 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4648 top1= 86.9892


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8792 top1= 54.3670


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0587 top1= 47.1955

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1793 top1= 95.0000
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2040 top1= 93.4375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1309 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4203 top1= 87.7003


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7088 top1= 56.5605


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9588 top1= 49.1286

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1468 top1= 95.6250
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1503 top1= 94.6875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1052 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4018 top1= 88.1410


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6786 top1= 57.0112


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9083 top1= 50.2704

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1228 top1= 96.5625
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1210 top1= 96.5625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0913 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3989 top1= 88.1711


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6853 top1= 57.1615


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8671 top1= 50.6410

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1106 top1= 96.8750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1059 top1= 96.8750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0805 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3967 top1= 88.3814


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7057 top1= 56.8009


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8848 top1= 50.7011

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1016 top1= 97.1875
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0975 top1= 97.1875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0743 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4009 top1= 88.4515


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7305 top1= 56.3502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9010 top1= 50.3906

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0969 top1= 97.5000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0990 top1= 96.8750
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0752 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4087 top1= 88.5016


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7522 top1= 55.8193


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9298 top1= 49.8698

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0956 top1= 97.8125
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1047 top1= 96.8750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0741 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4231 top1= 88.4115


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8014 top1= 55.2183


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9578 top1= 49.1787

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1013 top1= 97.5000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.1169 top1= 96.2500
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0803 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4421 top1= 88.1310


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8091 top1= 54.6074


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9899 top1= 48.1070

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.1141 top1= 97.5000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.1269 top1= 95.9375
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0897 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4662 top1= 87.4900


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8153 top1= 53.8361


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9905 top1= 47.6262

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.1204 top1= 96.8750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.1464 top1= 95.3125
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0949 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4863 top1= 87.1394


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8153 top1= 53.2252


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0415 top1= 47.4159

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.1104 top1= 97.8125
[E13B10 |   4224/60000 (  7%) ] Loss: 0.1545 top1= 94.3750
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.1065 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5038 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8202 top1= 52.7544


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0809 top1= 46.7348

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.1228 top1= 96.8750
[E14B10 |   4224/60000 (  7%) ] Loss: 0.1478 top1= 95.3125
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.1162 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5160 top1= 87.3998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8220 top1= 52.5942


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1406 top1= 45.9235

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.1363 top1= 96.5625
[E15B10 |   4224/60000 (  7%) ] Loss: 0.1597 top1= 94.6875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.1123 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5290 top1= 86.9692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8179 top1= 52.4339


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1707 top1= 45.7432

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.1524 top1= 96.2500
[E16B10 |   4224/60000 (  7%) ] Loss: 0.1695 top1= 95.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.1251 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5447 top1= 86.6587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7845 top1= 52.2736


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2268 top1= 45.4527

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.1653 top1= 95.6250
[E17B10 |   4224/60000 (  7%) ] Loss: 0.1720 top1= 94.3750
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.1204 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5497 top1= 86.8690


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7788 top1= 52.1735


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2092 top1= 45.4627

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.1571 top1= 95.6250
[E18B10 |   4224/60000 (  7%) ] Loss: 0.1858 top1= 93.4375
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1231 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5514 top1= 86.8389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7724 top1= 52.3938


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1209 top1= 45.7031

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.1524 top1= 95.6250
[E19B10 |   4224/60000 (  7%) ] Loss: 0.1821 top1= 93.7500
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1267 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5570 top1= 86.4784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7564 top1= 52.4740


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1474 top1= 45.6430

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.1495 top1= 95.3125
[E20B10 |   4224/60000 (  7%) ] Loss: 0.1780 top1= 93.7500
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.1273 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5615 top1= 86.5184


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7350 top1= 52.5341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1873 top1= 45.3826

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.1541 top1= 95.3125
[E21B10 |   4224/60000 (  7%) ] Loss: 0.1824 top1= 93.4375
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1378 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5705 top1= 85.9876


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7303 top1= 52.6643


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2450 top1= 45.0321

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.1599 top1= 95.6250
[E22B10 |   4224/60000 (  7%) ] Loss: 0.1884 top1= 94.0625
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.1479 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5767 top1= 85.7272


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7116 top1= 52.6242


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2465 top1= 44.9619

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.1598 top1= 95.6250
[E23B10 |   4224/60000 (  7%) ] Loss: 0.1953 top1= 94.0625
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.1482 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5879 top1= 85.2163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6971 top1= 52.9447


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2243 top1= 45.1322

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.1582 top1= 95.3125
[E24B10 |   4224/60000 (  7%) ] Loss: 0.2024 top1= 93.4375
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.1500 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5907 top1= 85.5068


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7013 top1= 52.7544


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1228 top1= 45.4127

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.1634 top1= 95.3125
[E25B10 |   4224/60000 (  7%) ] Loss: 0.1850 top1= 92.8125
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.1530 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5951 top1= 85.4467


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7013 top1= 52.7644


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0930 top1= 45.6130

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.1501 top1= 95.9375
[E26B10 |   4224/60000 (  7%) ] Loss: 0.1675 top1= 94.6875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.1314 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5903 top1= 85.6370


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7033 top1= 52.7444


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0853 top1= 45.8834

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.1447 top1= 95.3125
[E27B10 |   4224/60000 (  7%) ] Loss: 0.1584 top1= 95.3125
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.1308 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5848 top1= 85.6370


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6895 top1= 52.6442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0643 top1= 45.9034

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.1454 top1= 96.2500
[E28B10 |   4224/60000 (  7%) ] Loss: 0.1530 top1= 95.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.1273 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5901 top1= 85.3365


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6920 top1= 52.4239


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1873 top1= 45.4127

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.1537 top1= 95.6250
[E29B10 |   4224/60000 (  7%) ] Loss: 0.1499 top1= 95.3125
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.1274 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5957 top1= 85.3666


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6702 top1= 52.3137


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2076 top1= 45.2023

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.1632 top1= 95.3125
[E30B10 |   4224/60000 (  7%) ] Loss: 0.1536 top1= 95.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.1223 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6101 top1= 84.8858


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6620 top1= 52.4038


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3159 top1= 43.8702

