
=== 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 SGDMWorker(index=10, momentum=0.9)
=> Add worker SGDMWorker(index=11, momentum=0.9)
=> Add worker SGDMWorker(index=12, momentum=0.9)
=> Add worker SGDMWorker(index=13, momentum=0.9)
=> Add worker SGDMWorker(index=14, momentum=0.9)
=> Add worker SGDMWorker(index=15, momentum=0.9)
=> Add worker SGDMWorker(index=16, momentum=0.9)
=> Add worker SGDMWorker(index=17, momentum=0.9)
=> Add worker SGDMWorker(index=18, momentum=0.9)
=> Add worker SGDMWorker(index=19, momentum=0.9)
=> Add worker ByzantineWorker(index=20)
=> Add worker ByzantineWorker(index=21)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f3587f3b2e0>

Train epoch 1
[E 1B0  |    704/60000 (  1%) ] Loss: 2.3080 top1=  8.4375

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')
Worker 2 has targets: tensor([3, 0, 3, 2, 7], device='cuda:0')
Worker 3 has targets: tensor([1, 4, 8, 2, 8], device='cuda:0')
Worker 4 has targets: tensor([9, 5, 0, 1, 3], device='cuda:0')
Worker 5 has targets: tensor([5, 6, 2, 4, 3], device='cuda:0')
Worker 6 has targets: tensor([2, 5, 0, 9, 9], device='cuda:0')
Worker 7 has targets: tensor([2, 2, 1, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([3, 8, 7, 0, 3], device='cuda:0')
Worker 9 has targets: tensor([1, 7, 1, 7, 2], device='cuda:0')
Worker 10 has targets: tensor([8, 4, 4, 3, 9], device='cuda:0')
Worker 11 has targets: tensor([3, 4, 7, 7, 9], device='cuda:0')
Worker 12 has targets: tensor([7, 4, 3, 9, 4], device='cuda:0')
Worker 13 has targets: tensor([4, 5, 0, 7, 1], device='cuda:0')
Worker 14 has targets: tensor([4, 2, 3, 5, 5], device='cuda:0')
Worker 15 has targets: tensor([4, 7, 5, 4, 7], device='cuda:0')
Worker 16 has targets: tensor([1, 1, 5, 7, 9], device='cuda:0')
Worker 17 has targets: tensor([8, 7, 2, 2, 0], device='cuda:0')
Worker 18 has targets: tensor([7, 8, 0, 0, 6], device='cuda:0')
Worker 19 has targets: tensor([9, 9, 5, 2, 8], device='cuda:0')
Worker 20 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 21 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 1.8931 top1= 49.3750
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8119 top1= 75.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4195 top1= 87.7704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4535 top1= 86.7188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4564 top1= 86.0377

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5168 top1= 84.2188
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.4518 top1= 83.2812
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3752 top1= 87.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2746 top1= 92.1775


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2796 top1= 91.7268


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2934 top1= 91.5865

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2558 top1= 92.5000
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2393 top1= 92.6562
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2346 top1= 92.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2294 top1= 93.2993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2290 top1= 93.2091


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2463 top1= 92.5881

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1817 top1= 94.6875
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1563 top1= 96.4062
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1532 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1974 top1= 94.1006


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2085 top1= 93.5797


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1976 top1= 94.0505

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1284 top1= 96.2500
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1114 top1= 97.0312
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1094 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1736 top1= 94.7416


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1890 top1= 94.3009


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1725 top1= 94.8217

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0922 top1= 97.1875
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0776 top1= 98.2812
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0772 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1629 top1= 95.1322


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1779 top1= 94.7416


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1643 top1= 95.0921

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0669 top1= 98.2812
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0540 top1= 98.5938
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0624 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1595 top1= 95.4026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1749 top1= 94.9319


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1614 top1= 95.2524

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0487 top1= 99.0625
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0389 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0441 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1545 top1= 95.6030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1669 top1= 95.2324


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1581 top1= 95.3425

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0367 top1= 99.3750
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0259 top1= 99.6875
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0344 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1535 top1= 95.5829


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1788 top1= 94.9720


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1638 top1= 95.3125

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0318 top1= 99.5312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0181 top1=100.0000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0334 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1541 top1= 95.6030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1855 top1= 94.8718


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1602 top1= 95.5329

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0280 top1= 99.6875
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0186 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0298 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1549 top1= 95.7031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1892 top1= 94.9619


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1750 top1= 95.3025

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0296 top1= 99.2188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0191 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0162 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1569 top1= 95.6430


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2209 top1= 94.2308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1680 top1= 95.6430

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0258 top1= 99.3750
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0278 top1= 99.0625
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0255 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1415 top1= 96.0036


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1683 top1= 95.3626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1497 top1= 95.9836

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0204 top1= 99.2188
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0279 top1= 98.9062
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0291 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1432 top1= 96.0337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1451 top1= 96.0136


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1620 top1= 95.6931

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0176 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0092 top1= 99.8438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0134 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1470 top1= 96.0437


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1617 top1= 95.8433


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1452 top1= 96.2740

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0080 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0114 top1= 99.6875
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0112 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1448 top1= 96.2340


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1565 top1= 95.9635


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1504 top1= 96.2340

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0175 top1= 99.5312
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0051 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0071 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1541 top1= 96.1438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1834 top1= 95.2825


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1519 top1= 96.1939

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0140 top1= 99.6875
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0176 top1= 99.6875
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0073 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1428 top1= 96.3842


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1445 top1= 96.2340


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1462 top1= 96.2841

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0034 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0052 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1404 top1= 96.4042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1431 top1= 96.4042


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1426 top1= 96.4042

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0026 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1433 top1= 96.3542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1447 top1= 96.3241


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1450 top1= 96.4042

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1452 top1= 96.3341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1450 top1= 96.2841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1481 top1= 96.3542

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0017 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1469 top1= 96.3141


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1467 top1= 96.3241


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1502 top1= 96.3241

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1482 top1= 96.3542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1487 top1= 96.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1512 top1= 96.4143

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1486 top1= 96.3442


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1498 top1= 96.3542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1493 top1= 96.4042

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1504 top1= 96.3942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1512 top1= 96.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1509 top1= 96.4243

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1518 top1= 96.4143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1524 top1= 96.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1523 top1= 96.4443

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1530 top1= 96.3942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1536 top1= 96.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1534 top1= 96.4143

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1542 top1= 96.4042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1549 top1= 96.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1545 top1= 96.4042

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1554 top1= 96.4143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1561 top1= 96.3542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1556 top1= 96.4143

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1566 top1= 96.4343


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1572 top1= 96.3742


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1568 top1= 96.4042

