
=== 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 0x7fb2e96457f0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.2959 top1= 10.0000

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 8, 8, 6, 9], device='cuda:0')
Worker 1 has targets: tensor([5, 3, 6, 0, 9], device='cuda:0')
Worker 2 has targets: tensor([2, 9, 9, 3, 1], device='cuda:0')
Worker 3 has targets: tensor([6, 9, 8, 1, 2], device='cuda:0')
Worker 4 has targets: tensor([5, 8, 9, 1, 8], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 5, 2, 3], device='cuda:0')
Worker 6 has targets: tensor([3, 2, 8, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([3, 8, 7, 8, 7], device='cuda:0')
Worker 8 has targets: tensor([8, 0, 2, 4, 8], device='cuda:0')
Worker 9 has targets: tensor([5, 3, 4, 6, 3], device='cuda:0')
Worker 10 has targets: tensor([4, 8, 8, 6, 9], device='cuda:0')
Worker 11 has targets: tensor([5, 3, 6, 0, 9], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 2.1275 top1= 37.5000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 1.7814 top1= 50.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1867 top1= 76.8630


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1936 top1= 77.4139


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1875 top1= 75.8113

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 1.3230 top1= 62.1875
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.9551 top1= 71.2500
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.7345 top1= 78.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5393 top1= 85.7873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5538 top1= 84.6454


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5369 top1= 86.3281

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.7136 top1= 76.8750
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.5495 top1= 82.8125
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.5293 top1= 82.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4166 top1= 88.1010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4334 top1= 86.8089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4148 top1= 88.7220

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.5697 top1= 80.3125
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.4948 top1= 82.8125
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.4485 top1= 86.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3508 top1= 90.1943


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3529 top1= 90.0441


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3554 top1= 90.1643

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.4663 top1= 85.6250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.3756 top1= 90.3125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.3822 top1= 86.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3259 top1= 90.6851


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3347 top1= 90.1943


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3259 top1= 90.6751

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.4022 top1= 86.8750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.3156 top1= 91.5625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.3366 top1= 89.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2961 top1= 91.6066


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2984 top1= 91.4163


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3040 top1= 91.4463

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.3459 top1= 89.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.2574 top1= 93.4375
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.2841 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2725 top1= 92.0172


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2753 top1= 91.8470


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2760 top1= 92.0373

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.2978 top1= 90.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.3073 top1= 89.3750
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.2453 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2605 top1= 92.3277


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2648 top1= 92.1374


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2614 top1= 92.3377

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.2481 top1= 91.8750
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.2164 top1= 95.6250
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.2193 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2483 top1= 92.7584


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2503 top1= 92.6683


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2505 top1= 92.5982

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.2643 top1= 91.5625
[E10B10 |   4224/60000 (  7%) ] Loss: 0.2119 top1= 94.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.2335 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2338 top1= 93.2091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2333 top1= 93.1290


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2422 top1= 93.0589

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.2374 top1= 92.5000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.2104 top1= 94.0625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.1972 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2224 top1= 93.5597


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2254 top1= 93.2292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2252 top1= 93.5196

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.2280 top1= 94.0625
[E12B10 |   4224/60000 (  7%) ] Loss: 0.1721 top1= 95.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.1846 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2119 top1= 93.8602


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2133 top1= 93.7500


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2140 top1= 93.7700

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.1954 top1= 93.1250
[E13B10 |   4224/60000 (  7%) ] Loss: 0.1495 top1= 96.2500
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.1701 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2030 top1= 93.9403


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2093 top1= 93.6599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2021 top1= 94.1006

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.1661 top1= 96.2500
[E14B10 |   4224/60000 (  7%) ] Loss: 0.1289 top1= 97.1875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.1430 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1978 top1= 94.1106


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2000 top1= 93.9103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2031 top1= 94.0304

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.1882 top1= 94.6875
[E15B10 |   4224/60000 (  7%) ] Loss: 0.1316 top1= 97.1875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.1545 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1868 top1= 94.6114


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1908 top1= 94.3910


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1873 top1= 94.5713

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.1656 top1= 94.3750
[E16B10 |   4224/60000 (  7%) ] Loss: 0.1291 top1= 96.5625
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.1407 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1870 top1= 94.4611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1860 top1= 94.4611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1941 top1= 94.2808

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.1505 top1= 95.6250
[E17B10 |   4224/60000 (  7%) ] Loss: 0.1149 top1= 97.8125
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.1371 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1780 top1= 94.7115


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1801 top1= 94.5012


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1804 top1= 94.7917

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.1485 top1= 95.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.1127 top1= 97.5000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1110 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1703 top1= 94.9619


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1750 top1= 94.5413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1738 top1= 94.8618

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.1394 top1= 95.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.1148 top1= 97.8125
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1156 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1678 top1= 94.9319


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1681 top1= 94.7716


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1716 top1= 94.9419

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.1032 top1= 95.9375
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0757 top1= 98.1250
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0877 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1645 top1= 95.0521


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1635 top1= 94.9920


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1724 top1= 94.8217

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.1180 top1= 96.5625
[E21B10 |   4224/60000 (  7%) ] Loss: 0.1078 top1= 97.8125
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1072 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1675 top1= 94.8718


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1714 top1= 94.7917


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1674 top1= 95.0120

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.1106 top1= 96.2500
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0974 top1= 97.5000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0991 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1568 top1= 95.3526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1551 top1= 95.3826


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1627 top1= 95.2424

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0905 top1= 97.1875
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0898 top1= 98.1250
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0963 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1521 top1= 95.4828


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1493 top1= 95.5429


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1595 top1= 95.2624

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.1044 top1= 96.2500
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0862 top1= 97.8125
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0793 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1485 top1= 95.5228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1542 top1= 95.3425


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1484 top1= 95.5929

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0950 top1= 96.8750
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0761 top1= 98.1250
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0902 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1443 top1= 95.6430


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1452 top1= 95.4828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1469 top1= 95.7332

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0317 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0301 top1= 99.6875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0311 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1479 top1= 95.4427


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1510 top1= 95.3726


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1516 top1= 95.4427

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0708 top1= 98.7500
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0698 top1= 98.4375
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0716 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1425 top1= 95.7332


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1417 top1= 95.6530


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1463 top1= 95.5228

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0873 top1= 97.8125
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0868 top1= 98.1250
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0607 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1404 top1= 95.7833


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1437 top1= 95.5228


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1431 top1= 95.7532

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0615 top1= 98.1250
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0566 top1= 99.0625
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0540 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1327 top1= 96.0236


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1332 top1= 95.8534


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1369 top1= 95.9936

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0733 top1= 97.1875
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0625 top1= 98.7500
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0615 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1300 top1= 95.9936


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1330 top1= 95.9335


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1316 top1= 95.8534

