
=== 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.Dumbbell object at 0x7f66e2b75490>

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: 1.0496 top1= 61.5625
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3912 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6976 top1= 80.5288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7754 top1= 49.2688


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1031 top1= 44.2808

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2834 top1= 91.0938
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1939 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1996 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6332 top1= 86.0276


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6607 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7432 top1= 45.7632

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1610 top1= 94.2188
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1153 top1= 97.0312
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1446 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5501 top1= 86.6286


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3073 top1= 49.7496


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2846 top1= 46.1639

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1347 top1= 95.7812
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0872 top1= 97.8125
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1150 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4832 top1= 87.5901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9700 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9101 top1= 46.4844

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1028 top1= 96.8750
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0704 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0914 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4335 top1= 88.4615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6498 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5924 top1= 46.5946

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0809 top1= 97.9688
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0518 top1= 98.7500
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0758 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3945 top1= 88.9423


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4358 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3590 top1= 46.7448

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0656 top1= 98.4375
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0407 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0613 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3718 top1= 89.0725


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2623 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1983 top1= 46.8850

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0540 top1= 99.0625
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0351 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0526 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3501 top1= 89.4131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1114 top1= 50.8814


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0194 top1= 47.3458

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0494 top1= 99.0625
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0303 top1= 99.5312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0432 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3353 top1= 89.5333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0400 top1= 51.2921


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9738 top1= 47.7264

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0397 top1= 99.3750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0265 top1= 99.5312
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0411 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3232 top1= 89.8037


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9954 top1= 51.6126


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9779 top1= 48.0569

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0345 top1= 99.3750
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0243 top1= 99.6875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0380 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3145 top1= 90.0240


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9576 top1= 52.0433


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0082 top1= 48.0970

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0333 top1= 99.3750
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0282 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0459 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3187 top1= 89.8738


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9347 top1= 52.1434


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8483 top1= 48.7680

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0420 top1= 99.0625
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0283 top1= 99.3750
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0368 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3196 top1= 89.4832


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8450 top1= 51.8930


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8669 top1= 48.4475

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0384 top1= 98.9062
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0391 top1= 98.5938
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0565 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3251 top1= 89.1627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8333 top1= 52.3438


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7995 top1= 48.5076

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0451 top1= 99.0625
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0465 top1= 98.5938
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0556 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3049 top1= 89.8438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6373 top1= 52.6643


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8158 top1= 49.1787

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0186 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0223 top1= 99.6875
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0382 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3006 top1= 90.1743


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5699 top1= 52.9848


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6723 top1= 49.6494

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0211 top1= 99.8438
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0205 top1= 99.6875
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0241 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2997 top1= 90.0741


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4835 top1= 53.5958


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8129 top1= 49.4692

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0237 top1= 99.6875
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0190 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0238 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2829 top1= 90.9956


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7035 top1= 51.8329


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9666 top1= 48.7380

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0302 top1= 98.9062
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0233 top1= 99.2188
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0269 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3153 top1= 89.3229


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5442 top1= 52.9547


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8983 top1= 48.6378

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0315 top1= 99.2188
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0204 top1= 99.5312
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0194 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2849 top1= 90.7552


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4861 top1= 53.5958


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6640 top1= 48.5677

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0232 top1= 99.2188
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0215 top1= 99.8438
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0301 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2860 top1= 90.8754


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4683 top1= 54.0064


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6859 top1= 48.9283

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0215 top1= 99.3750
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0224 top1= 99.8438
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0337 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3043 top1= 89.8838


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3965 top1= 54.1166


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9266 top1= 47.3157

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0294 top1= 98.4375
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0240 top1= 99.3750
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0217 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3114 top1= 89.2428


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4175 top1= 54.0064


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9201 top1= 48.1971

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0375 top1= 98.9062
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0159 top1= 99.8438
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0225 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3075 top1= 89.6835


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4227 top1= 54.2468


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7426 top1= 48.5176

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0277 top1= 99.3750
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0192 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0250 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3058 top1= 89.7336


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4262 top1= 54.2869


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7656 top1= 48.6579

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0172 top1= 99.8438
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0295 top1= 99.3750
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0382 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3222 top1= 88.9824


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4061 top1= 54.1366


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9276 top1= 48.9183

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0302 top1= 99.0625
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0174 top1= 99.8438
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0329 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3263 top1= 88.6518


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3872 top1= 54.2368


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9605 top1= 47.5060

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0328 top1= 99.0625
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0162 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0186 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3456 top1= 87.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4151 top1= 53.9463


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8812 top1= 47.6462

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0385 top1= 98.7500
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0235 top1= 99.8438
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0213 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3085 top1= 89.6835


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4323 top1= 53.6258


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8278 top1= 47.8265

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0135 top1= 99.8438
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0204 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0318 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3044 top1= 89.8538


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4324 top1= 53.4756


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8607 top1= 47.8866

