
=== 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.RandomSmallWorldGraph object at 0x7f134bc68400>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3054 top1= 10.0000

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



=== Log global consensus distance @ E1B0 ===
consensus_distance=3.142



=== Log average shortest path distance for small world @ E1B0 ===
2.7777777777777777


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.8637 top1= 75.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.4981 top1= 80.3125
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.2805 top1= 97.5000
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.2180 top1= 97.5000
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.1905 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8633 top1= 53.8862

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.2760 top1= 95.3125

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.544


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1791 top1= 98.7500
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1777 top1= 98.4375
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.1600 top1= 97.8125
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1870 top1= 98.1250
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.1642 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8615 top1= 39.7336

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.2767 top1= 94.6875

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.260


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1856 top1= 98.1250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1654 top1= 98.1250
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.1520 top1= 98.1250
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.1785 top1= 98.1250
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.1583 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8611 top1= 32.4119

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2550 top1= 94.6875

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.242


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1831 top1= 98.1250
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1634 top1= 97.8125
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.1478 top1= 98.4375
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.1758 top1= 97.8125
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.1563 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8608 top1= 32.5521

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.2513 top1= 94.6875

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.238


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1828 top1= 97.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1631 top1= 97.8125
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.1457 top1= 98.4375
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.1749 top1= 97.8125
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.1554 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8604 top1= 35.8874

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.2491 top1= 95.6250

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.237


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1791 top1= 97.8125
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1625 top1= 97.8125
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.1452 top1= 98.4375
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.1728 top1= 97.8125
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.1552 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8600 top1= 39.2228

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.2495 top1= 95.6250

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.238


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1737 top1= 98.1250
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.1606 top1= 97.8125
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.1456 top1= 98.4375
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.1708 top1= 97.8125
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.1541 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8615 top1= 40.7953

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.2508 top1= 95.3125

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.238


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1673 top1= 98.4375
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.1599 top1= 98.1250
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.1461 top1= 98.7500
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.1694 top1= 98.1250
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.1528 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8658 top1= 40.6651

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.2467 top1= 95.3125

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.239


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1633 top1= 98.7500
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.1587 top1= 98.4375
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.1465 top1= 98.4375
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.1678 top1= 98.1250
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.1522 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8721 top1= 39.7135

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.2392 top1= 95.3125

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.239


[E10B10 |   4224/60000 (  7%) ] Loss: 0.1637 top1= 98.7500
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.1573 top1= 98.4375
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.1456 top1= 98.4375
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.1670 top1= 98.1250
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.1514 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8778 top1= 39.4131

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.2330 top1= 95.6250

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.239


[E11B10 |   4224/60000 (  7%) ] Loss: 0.1637 top1= 98.7500
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.1565 top1= 98.4375
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.1447 top1= 98.4375
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.1665 top1= 98.1250
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.1514 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8801 top1= 39.4431

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.2309 top1= 95.6250

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.239


[E12B10 |   4224/60000 (  7%) ] Loss: 0.1634 top1= 98.7500
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.1562 top1= 98.4375
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.1442 top1= 98.4375
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.1661 top1= 98.4375
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.1517 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8819 top1= 39.8037

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.2287 top1= 95.6250

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.240


[E13B10 |   4224/60000 (  7%) ] Loss: 0.1632 top1= 98.7500
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.1558 top1= 98.7500
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.1437 top1= 98.4375
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.1658 top1= 98.4375
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.1522 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8819 top1= 39.8237

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.2291 top1= 95.6250

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.241


[E14B10 |   4224/60000 (  7%) ] Loss: 0.1643 top1= 98.7500
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.1554 top1= 98.7500
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.1434 top1= 98.4375
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.1658 top1= 98.4375
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.1528 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8820 top1= 40.1743

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.2294 top1= 95.6250

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.242


[E15B10 |   4224/60000 (  7%) ] Loss: 0.1643 top1= 98.7500
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.1545 top1= 98.7500
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.1434 top1= 98.4375
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.1658 top1= 98.4375
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.1528 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8815 top1= 40.5849

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.2301 top1= 95.6250

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.243


[E16B10 |   4224/60000 (  7%) ] Loss: 0.1648 top1= 98.7500
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.1541 top1= 98.7500
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.1435 top1= 98.4375
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.1659 top1= 98.4375
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.1535 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8797 top1= 40.8854

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.2320 top1= 95.6250

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.244


[E17B10 |   4224/60000 (  7%) ] Loss: 0.1653 top1= 98.7500
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.1537 top1= 98.7500
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.1436 top1= 98.4375
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.1663 top1= 98.4375
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.1530 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8797 top1= 41.2059

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.2327 top1= 95.3125

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.245


[E18B10 |   4224/60000 (  7%) ] Loss: 0.1651 top1= 98.7500
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1538 top1= 98.7500
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.1443 top1= 98.4375
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.1664 top1= 98.4375
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.1535 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8778 top1= 41.1959

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.2348 top1= 94.6875

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.247


[E19B10 |   4224/60000 (  7%) ] Loss: 0.1660 top1= 98.7500
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1541 top1= 98.7500
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.1457 top1= 98.4375
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.1666 top1= 98.4375
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.1544 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8718 top1= 41.6266

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.2414 top1= 94.6875

=== Log global consensus distance @ E20B0 ===
consensus_distance=0.248


[E20B10 |   4224/60000 (  7%) ] Loss: 0.1645 top1= 98.7500
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.1539 top1= 98.4375
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.1474 top1= 98.4375
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.1668 top1= 98.4375
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.1550 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8683 top1= 42.0373

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.2453 top1= 94.6875

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.250


[E21B10 |   4224/60000 (  7%) ] Loss: 0.1629 top1= 98.7500
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1539 top1= 98.4375
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.1479 top1= 98.4375
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.1668 top1= 98.4375
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.1550 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8671 top1= 42.1174

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.2451 top1= 94.6875

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.251


[E22B10 |   4224/60000 (  7%) ] Loss: 0.1637 top1= 98.7500
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.1519 top1= 98.4375
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.1473 top1= 98.4375
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.1669 top1= 98.4375
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.1549 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8711 top1= 41.7268

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.2431 top1= 94.6875

=== Log global consensus distance @ E23B0 ===
consensus_distance=0.251


[E23B10 |   4224/60000 (  7%) ] Loss: 0.1654 top1= 98.7500
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.1518 top1= 98.4375
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.1480 top1= 98.4375
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.1666 top1= 98.4375
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.1541 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8726 top1= 41.5164

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.2444 top1= 94.6875

=== Log global consensus distance @ E24B0 ===
consensus_distance=0.252


[E24B10 |   4224/60000 (  7%) ] Loss: 0.1656 top1= 98.7500
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.1524 top1= 98.4375
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.1506 top1= 98.1250
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.1663 top1= 98.4375
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.1540 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8729 top1= 41.2159

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.2454 top1= 94.6875

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.253


[E25B10 |   4224/60000 (  7%) ] Loss: 0.1655 top1= 98.7500
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.1536 top1= 98.4375
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.1526 top1= 98.1250
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.1662 top1= 98.4375
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.1535 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8716 top1= 40.8554

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.2453 top1= 94.6875

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.252


[E26B10 |   4224/60000 (  7%) ] Loss: 0.1639 top1= 98.4375
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.1521 top1= 98.4375
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.1504 top1= 98.1250
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.1663 top1= 98.4375
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.1538 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8749 top1= 40.7552

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.2428 top1= 94.6875

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.253


[E27B10 |   4224/60000 (  7%) ] Loss: 0.1646 top1= 98.4375
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.1534 top1= 98.4375
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.1515 top1= 98.1250
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.1662 top1= 98.4375
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.1533 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8750 top1= 41.0757

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.2451 top1= 94.6875

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.252


[E28B10 |   4224/60000 (  7%) ] Loss: 0.1661 top1= 98.4375
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.1569 top1= 98.4375
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.1551 top1= 98.1250
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.1659 top1= 98.4375
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.1515 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8718 top1= 41.4964

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.2469 top1= 94.6875

=== Log global consensus distance @ E29B0 ===
consensus_distance=0.247


[E29B10 |   4224/60000 (  7%) ] Loss: 0.1628 top1= 98.4375
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.1560 top1= 98.4375
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.1512 top1= 98.1250
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.1662 top1= 98.4375
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.1528 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8732 top1= 40.8554

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.2426 top1= 94.6875

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.250


[E30B10 |   4224/60000 (  7%) ] Loss: 0.1658 top1= 98.4375
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.1559 top1= 98.4375
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.1522 top1= 98.1250
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.1663 top1= 98.4375
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.1527 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8715 top1= 40.8854

