
=== 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.Dumbbell object at 0x7f97f79a8490>

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: 1.4594 top1= 50.0000
[E 1B20 |  14784/60000 ( 25%) ] Loss: 1.0674 top1= 65.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4025 top1= 71.4443


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4992 top1= 48.1671


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7380 top1= 43.1390

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.7350 top1= 74.3750
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.5282 top1= 83.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.4948 top1= 84.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1986 top1= 55.8193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2606 top1= 49.2188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2310 top1= 44.1506

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.4363 top1= 87.0312
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.3315 top1= 90.4688
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.3488 top1= 89.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2269 top1= 52.7244


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9383 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7287 top1= 44.7716

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.3564 top1= 88.7500
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.2927 top1= 91.7188
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.3614 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2675 top1= 51.6927


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8965 top1= 52.0633


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2282 top1= 45.1823

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.3854 top1= 88.7500
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.3381 top1= 89.6875
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.3310 top1= 89.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2252 top1= 53.1150


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7036 top1= 54.3670


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0631 top1= 45.4728

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.3046 top1= 90.3125
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.3378 top1= 89.6875
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.2635 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2427 top1= 52.5541


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6018 top1= 56.2500


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0527 top1= 45.7933

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.2581 top1= 92.8125
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.2846 top1= 90.4688
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.3045 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2261 top1= 53.0749


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5218 top1= 57.6322


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0728 top1= 46.1438

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.2275 top1= 93.1250
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.2304 top1= 92.9688
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.2327 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2279 top1= 53.7159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4843 top1= 58.7841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1133 top1= 46.1939

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.2458 top1= 91.8750
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1934 top1= 95.1562
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.3263 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2117 top1= 54.2067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4649 top1= 59.6054


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1727 top1= 46.2740

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.2293 top1= 92.6562
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.2416 top1= 92.6562
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.2159 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2496 top1= 53.4856


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5014 top1= 59.9359


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3072 top1= 46.3642

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.2350 top1= 93.4375
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1808 top1= 94.6875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.3092 top1= 90.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1861 top1= 55.3686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4914 top1= 60.2564


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2270 top1= 46.3542

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.2728 top1= 91.0938
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.2455 top1= 92.6562
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.2048 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1215 top1= 57.7224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5189 top1= 60.2564


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1461 top1= 46.5244

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.2452 top1= 92.0312
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.2374 top1= 92.5000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.2873 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1164 top1= 57.8926


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4485 top1= 61.1478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2712 top1= 46.5244

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.2333 top1= 93.1250
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1769 top1= 95.3125
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.2372 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0930 top1= 58.8241


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4585 top1= 61.5485


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1869 top1= 46.6146

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.2062 top1= 93.5938
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.2429 top1= 92.5000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.2177 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0752 top1= 59.1847


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4216 top1= 61.5084


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1631 top1= 46.7648

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.2486 top1= 92.8125
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1271 top1= 96.8750
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1783 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1127 top1= 58.5938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4646 top1= 62.1995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3513 top1= 46.7548

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1607 top1= 95.4688
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.2265 top1= 92.3438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.2758 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0267 top1= 61.7087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4870 top1= 62.1595


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2218 top1= 46.6446

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.2914 top1= 93.5938
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.2047 top1= 93.7500
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1727 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0505 top1= 61.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4787 top1= 61.8490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2105 top1= 46.8850

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.2487 top1= 93.2812
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1879 top1= 93.1250
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1947 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9916 top1= 62.9006


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4877 top1= 62.2196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3121 top1= 46.9351

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1925 top1= 94.3750
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1704 top1= 94.8438
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1898 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9759 top1= 63.1611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4445 top1= 62.5501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0981 top1= 46.8850

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.2557 top1= 93.1250
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1281 top1= 97.0312
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.2027 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0110 top1= 62.3798


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4227 top1= 62.9006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1679 top1= 47.0052

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.2266 top1= 94.3750
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.2192 top1= 93.7500
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.2085 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9611 top1= 64.1226


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4844 top1= 62.4800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2438 top1= 47.0553

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1977 top1= 94.6875
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.1561 top1= 95.1562
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1826 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9815 top1= 64.5433


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4158 top1= 62.9006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2967 top1= 46.9251

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.2337 top1= 94.5312
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1921 top1= 95.3125
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.2168 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9113 top1= 66.3762


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4610 top1= 62.7304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1253 top1= 47.1254

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1838 top1= 94.5312
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1369 top1= 96.0938
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1708 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9284 top1= 65.5749


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4348 top1= 63.2212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2785 top1= 47.1454

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1981 top1= 94.5312
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.2014 top1= 93.9062
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1483 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9249 top1= 65.6150


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4392 top1= 63.7821


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1080 top1= 47.1154

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1672 top1= 95.9375
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1680 top1= 95.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.2037 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9010 top1= 66.5966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4461 top1= 63.6018


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0141 top1= 47.0052

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.3035 top1= 92.8125
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.1184 top1= 96.4062
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1771 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8953 top1= 66.9872


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4228 top1= 63.6518


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2195 top1= 47.2055

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1738 top1= 96.0938
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0914 top1= 97.3438
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.2130 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8761 top1= 67.9287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4462 top1= 63.4115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2335 top1= 47.2055

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1583 top1= 95.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1930 top1= 94.6875
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.2153 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8715 top1= 68.5597


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4335 top1= 63.9323


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1660 top1= 47.2857

