
=== 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 0x7f1af370c2b0>

Train epoch 1
[E 1B0  |    704/60000 (  1%) ] Loss: 2.3066 top1=  9.2188

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


[E 1B10 |   7744/60000 ( 13%) ] Loss: 1.4954 top1= 47.1875
[E 1B20 |  14784/60000 ( 25%) ] Loss: 1.0329 top1= 66.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4476 top1= 56.1498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1126 top1= 48.2372


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7503 top1= 43.2091

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.7160 top1= 76.7188
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.6382 top1= 79.3750
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.5647 top1= 82.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3052 top1= 50.7011


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6285 top1= 52.2135


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2092 top1= 44.1006

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.4867 top1= 84.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.4049 top1= 88.1250
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.4904 top1= 85.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3238 top1= 50.2905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4111 top1= 56.8409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5300 top1= 44.9119

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.3791 top1= 88.7500
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.3804 top1= 88.9062
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.4304 top1= 88.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3587 top1= 50.1002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3324 top1= 59.7957


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8204 top1= 45.1422

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.4450 top1= 85.6250
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.3133 top1= 91.2500
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.4255 top1= 86.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2867 top1= 51.3221


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3198 top1= 61.2179


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7284 top1= 45.4026

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.3086 top1= 91.0938
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.3027 top1= 90.6250
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.3523 top1= 89.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3080 top1= 50.8213


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2282 top1= 62.8506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9202 top1= 45.7732

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.3056 top1= 90.6250
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.3149 top1= 91.0938
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.3505 top1= 89.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2498 top1= 53.0349


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3080 top1= 61.9792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8988 top1= 45.8033

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.3373 top1= 90.0000
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.2665 top1= 92.0312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.3485 top1= 90.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2581 top1= 52.6142


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2020 top1= 63.6919


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9456 top1= 46.0837

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.3033 top1= 90.7812
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.2482 top1= 92.6562
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.3177 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2511 top1= 52.9147


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2042 top1= 63.7220


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0272 top1= 46.2340

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.2424 top1= 92.0312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.3944 top1= 87.5000
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.2687 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1741 top1= 54.9379


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2678 top1= 63.3814


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7848 top1= 46.3642

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.2604 top1= 92.9688
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.2313 top1= 93.2812
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.3048 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1321 top1= 56.6406


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2630 top1= 63.5116


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8591 top1= 46.4143

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.2423 top1= 92.6562
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.2200 top1= 93.9062
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.2685 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1895 top1= 55.2183


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1950 top1= 65.2043


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9413 top1= 46.5144

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.2571 top1= 92.0312
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.2366 top1= 93.5938
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.3537 top1= 90.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1005 top1= 58.0929


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2086 top1= 64.4431


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9900 top1= 46.5244

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.2334 top1= 93.1250
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1859 top1= 95.1562
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.2903 top1= 91.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0860 top1= 58.6138


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1418 top1= 65.4848


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9477 top1= 46.6146

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.2053 top1= 93.7500
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.2044 top1= 93.9062
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.2854 top1= 91.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0903 top1= 58.4535


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1541 top1= 65.4748


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0004 top1= 46.7348

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.2426 top1= 92.3438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.2224 top1= 92.8125
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.2413 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0966 top1= 58.6238


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2025 top1= 65.7352


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0237 top1= 46.7648

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1831 top1= 95.4688
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.2781 top1= 92.6562
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.3136 top1= 91.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9711 top1= 63.1010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1196 top1= 66.1659


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4809 top1= 46.8349

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.2257 top1= 93.5938
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.2414 top1= 93.4375
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.2034 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9579 top1= 63.8021


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2246 top1= 64.8137


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6566 top1= 46.8249

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.2240 top1= 93.5938
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1909 top1= 94.5312
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.2016 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0024 top1= 62.4299


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0803 top1= 67.6683


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7577 top1= 46.9050

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.2381 top1= 93.4375
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1486 top1= 95.7812
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.2312 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9124 top1= 65.6550


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2001 top1= 65.2644


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7186 top1= 46.9752

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1716 top1= 94.6875
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1575 top1= 95.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1926 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9545 top1= 64.3029


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1127 top1= 67.2075


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8054 top1= 46.9251

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.2746 top1= 92.8125
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.1550 top1= 96.0938
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.2520 top1= 92.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8838 top1= 66.9371


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1954 top1= 65.8854


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8562 top1= 47.0052

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1851 top1= 94.3750
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.1404 top1= 96.4062
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.2383 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8993 top1= 67.1474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1686 top1= 66.5164


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8436 top1= 47.1154

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1901 top1= 93.9062
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1581 top1= 95.6250
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1838 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9043 top1= 66.9271


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2015 top1= 66.8670


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8177 top1= 47.1254

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1956 top1= 94.2188
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1638 top1= 94.2188
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.2302 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8818 top1= 67.2476


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1563 top1= 67.2977


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8452 top1= 47.1354

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1777 top1= 95.1562
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.1626 top1= 95.4688
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.2233 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7769 top1= 71.6546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1609 top1= 66.9471


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3761 top1= 47.0252

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.3123 top1= 92.0312
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.2183 top1= 93.2812
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.2399 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7827 top1= 71.3542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1967 top1= 65.9856


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3233 top1= 47.1254

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1690 top1= 95.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.1186 top1= 97.0312
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.2129 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8426 top1= 68.8802


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1522 top1= 67.1775


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6451 top1= 47.1655

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1621 top1= 95.6250
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.1382 top1= 96.5625
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.2089 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8190 top1= 69.8718


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2098 top1= 66.6166


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6883 top1= 47.2356

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1579 top1= 95.4688
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1441 top1= 96.4062
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1721 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8356 top1= 69.6815


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1557 top1= 67.7985


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7004 top1= 47.2155

