
=== 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 0x7f9361da12b0>

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: 1.0341 top1= 61.5625
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3934 top1= 88.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6616 top1= 80.8093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5892 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9497 top1= 44.2508

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2837 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1899 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1981 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5356 top1= 86.7989


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0733 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0679 top1= 45.8433

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1563 top1= 94.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1085 top1= 97.0312
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1438 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4440 top1= 87.5401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6248 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3401 top1= 46.3642

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1275 top1= 95.9375
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0811 top1= 97.5000
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1117 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3845 top1= 88.3714


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3503 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0414 top1= 46.7348

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0985 top1= 97.0312
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0609 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0882 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3442 top1= 89.0825


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1199 top1= 51.4223


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8284 top1= 48.0970

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0695 top1= 98.1250
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0400 top1= 99.2188
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0671 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3200 top1= 89.5733


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9783 top1= 52.5240


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7676 top1= 49.5192

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0500 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0321 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0461 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3044 top1= 89.9740


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9681 top1= 53.5757


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6781 top1= 50.9014

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0371 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0275 top1= 99.3750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0409 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2940 top1= 90.2845


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8867 top1= 54.6274


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6520 top1= 52.2636

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0309 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0293 top1= 99.0625
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0312 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2942 top1= 90.2344


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8571 top1= 55.4387


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4209 top1= 53.6959

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0329 top1= 98.7500
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0253 top1= 99.6875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0360 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2745 top1= 90.6751


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7381 top1= 56.7308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7539 top1= 50.3606

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0451 top1= 98.7500
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0145 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0222 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2794 top1= 90.7452


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8291 top1= 57.3017


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5968 top1= 53.3153

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0312 top1= 99.0625
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0192 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0152 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2585 top1= 91.5465


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7081 top1= 57.8225


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7131 top1= 52.5942

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0154 top1= 99.3750
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0158 top1= 99.6875
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0229 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2560 top1= 91.3662


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4960 top1= 59.9559


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5499 top1= 54.2768

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0176 top1= 99.3750
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0142 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0150 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2476 top1= 91.8770


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5553 top1= 59.5753


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4183 top1= 57.2416

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0105 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0107 top1= 99.6875
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0170 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2391 top1= 92.1775


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7014 top1= 58.8742


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1014 top1= 60.3566

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0088 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0063 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0201 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2546 top1= 92.0072


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3325 top1= 60.4267


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9716 top1= 60.6470

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0102 top1= 99.8438
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0063 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0115 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2431 top1= 92.3878


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3972 top1= 61.2079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0747 top1= 60.9375

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0125 top1= 99.6875
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0101 top1= 99.6875
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2399 top1= 92.4479


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1382 top1= 62.6002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2747 top1= 57.7524

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0081 top1= 99.8438
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0036 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2268 top1= 92.9587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9959 top1= 63.4415


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8644 top1= 63.1010

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0030 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2257 top1= 93.0188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9747 top1= 63.6719


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7498 top1= 64.4131

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2252 top1= 93.1090


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9068 top1= 64.5433


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6418 top1= 66.6066

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2273 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9111 top1= 64.8638


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6359 top1= 67.3277

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2262 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8216 top1= 65.9655


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5860 top1= 68.3494

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2273 top1= 93.2292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8048 top1= 66.3662


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5606 top1= 68.9303

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2280 top1= 93.2292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7403 top1= 67.2276


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5452 top1= 69.4712

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2285 top1= 93.2592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7232 top1= 67.6583


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5243 top1= 70.0521

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2292 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6868 top1= 68.1791


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5145 top1= 70.2825

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2300 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6641 top1= 68.5897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4977 top1= 70.7332

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2307 top1= 93.2792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6365 top1= 69.0905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4867 top1= 71.1438

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2314 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6103 top1= 69.6314


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4753 top1= 71.5745

