
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f159fa752b0>

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: 1.0538 top1= 61.5625
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3922 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6708 top1= 81.1599


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0983 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5097 top1= 44.3610

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2801 top1= 90.6250
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1944 top1= 94.0625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1998 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5655 top1= 86.3381


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8064 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7184 top1= 45.8634

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1589 top1= 95.0000
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1193 top1= 97.1875
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1575 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4564 top1= 87.6703


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1584 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9140 top1= 46.2240

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1402 top1= 96.0938
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0981 top1= 97.0312
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1267 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3852 top1= 88.5317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7749 top1= 51.0116


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6090 top1= 47.3858

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1217 top1= 96.4062
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0805 top1= 97.5000
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1049 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3445 top1= 89.3029


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6674 top1= 52.2135


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5031 top1= 48.5877

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1019 top1= 97.8125
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0615 top1= 98.4375
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0835 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3195 top1= 89.7236


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6535 top1= 53.2051


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4102 top1= 49.7296

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0833 top1= 98.4375
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0494 top1= 99.0625
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0736 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3019 top1= 90.0240


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6254 top1= 53.8862


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3579 top1= 50.7412

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0693 top1= 98.7500
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0432 top1= 99.0625
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0619 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2953 top1= 90.1242


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6353 top1= 54.5773


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2432 top1= 52.4840

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0558 top1= 99.0625
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0382 top1= 98.9062
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0547 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2960 top1= 90.2444


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5944 top1= 55.4487


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1749 top1= 54.0865

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0507 top1= 99.0625
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0364 top1= 99.3750
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0468 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3030 top1= 90.1542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5013 top1= 56.0597


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1149 top1= 54.8478

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0470 top1= 98.5938
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0341 top1= 99.3750
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0478 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2911 top1= 90.4046


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2900 top1= 57.2616


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2268 top1= 53.5357

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0339 top1= 99.2188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0404 top1= 98.9062
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0557 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2849 top1= 90.3546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1424 top1= 57.9728


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2827 top1= 52.2035

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0367 top1= 98.4375
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0348 top1= 99.2188
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0579 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3010 top1= 89.5433


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0099 top1= 58.6739


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4329 top1= 52.9848

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0590 top1= 97.5000
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0406 top1= 98.2812
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0619 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2788 top1= 90.6751


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0973 top1= 57.1915


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3294 top1= 52.6743

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0555 top1= 98.7500
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0231 top1= 99.5312
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0282 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2819 top1= 90.8053


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1724 top1= 57.2316


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0169 top1= 54.8077

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0584 top1= 98.1250
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0236 top1= 99.8438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0330 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2608 top1= 91.2861


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1154 top1= 57.5421


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2183 top1= 52.6843

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0228 top1= 99.2188
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0215 top1= 99.8438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0208 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2689 top1= 90.9655


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0493 top1= 58.8442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1737 top1= 53.1350

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0203 top1= 99.5312
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0164 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0197 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2702 top1= 90.9355


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9610 top1= 59.1146


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3204 top1= 51.3421

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0383 top1= 98.5938
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0220 top1= 99.5312
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0174 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2615 top1= 91.2660


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9912 top1= 59.2548


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1344 top1= 53.3854

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0206 top1= 99.6875
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0196 top1= 99.8438
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0260 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2634 top1= 91.1058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9553 top1= 59.6154


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1849 top1= 53.3954

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0208 top1= 99.5312
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0159 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0150 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2587 top1= 91.3161


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9415 top1= 59.7055


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1000 top1= 53.7360

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0189 top1= 99.6875
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0168 top1= 99.8438
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0192 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2598 top1= 91.2159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9732 top1= 59.5653


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1556 top1= 52.8746

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0170 top1= 99.8438
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0166 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0147 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2586 top1= 91.2360


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9945 top1= 59.5252


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1362 top1= 52.8946

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0168 top1= 99.6875
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0161 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0172 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2573 top1= 91.5365


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9873 top1= 59.3550


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2624 top1= 51.6326

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0183 top1= 99.8438
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0161 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0163 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2559 top1= 91.6767


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0140 top1= 59.1446


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2159 top1= 53.1751

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0185 top1= 99.8438
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0155 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0267 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2553 top1= 91.7368


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0007 top1= 59.4251


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1167 top1= 53.5657

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0152 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0204 top1= 99.6875
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0159 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2610 top1= 91.4363


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0403 top1= 58.8542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0901 top1= 53.0549

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0267 top1= 99.3750
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0147 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0173 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2629 top1= 91.3662


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0157 top1= 58.8542


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3281 top1= 52.1935

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0276 top1= 99.3750
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0175 top1= 99.8438
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0252 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2647 top1= 91.1358


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0381 top1= 58.5737


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4389 top1= 50.9716

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0191 top1= 99.8438
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0139 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0240 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2611 top1= 91.6466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0597 top1= 58.3534


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2556 top1= 51.7829

