
=== 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 0x7f86a67172b0>

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: 1.0481 top1= 61.5625
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3915 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6960 top1= 80.5088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8020 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1388 top1= 44.3109

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2823 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1938 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1975 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6305 top1= 85.9876


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6561 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6964 top1= 45.7632

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1613 top1= 94.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1151 top1= 96.7188
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1429 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5462 top1= 86.6587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2944 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2590 top1= 46.1839

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1347 top1= 95.7812
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0862 top1= 97.6562
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1148 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4795 top1= 87.5901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9667 top1= 50.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9117 top1= 46.4844

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1038 top1= 96.7188
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0691 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0925 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4348 top1= 88.1310


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6582 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5646 top1= 46.5845

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0824 top1= 97.9688
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0530 top1= 98.7500
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0743 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3982 top1= 88.6518


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4404 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2910 top1= 46.7448

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0663 top1= 98.9062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0414 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0618 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3681 top1= 89.0825


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2642 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0961 top1= 46.9551

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0533 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0349 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0525 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3467 top1= 89.4030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1220 top1= 50.9014


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9542 top1= 47.5160

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0459 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0314 top1= 99.5312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0459 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3324 top1= 89.7236


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0731 top1= 51.1819


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8842 top1= 48.1370

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0404 top1= 99.3750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0278 top1= 99.5312
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0436 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3193 top1= 89.9539


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0063 top1= 51.6126


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9306 top1= 48.3173

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0349 top1= 99.2188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0240 top1= 99.5312
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0385 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3152 top1= 89.8538


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9897 top1= 51.7127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9234 top1= 48.5677

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0353 top1= 99.2188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0248 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0522 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3189 top1= 89.3830


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9262 top1= 51.2119


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9215 top1= 48.5276

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0427 top1= 99.0625
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0284 top1= 99.5312
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0462 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3325 top1= 88.4916


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7992 top1= 52.4840


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9413 top1= 49.1687

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0633 top1= 97.8125
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0342 top1= 99.5312
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0396 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3449 top1= 87.7304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7357 top1= 52.3938


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0065 top1= 47.4559

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0753 top1= 97.3438
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0423 top1= 98.9062
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0713 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3710 top1= 86.6787


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6263 top1= 53.1150


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2282 top1= 47.5561

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0460 top1= 98.5938
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0382 top1= 99.2188
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0326 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3345 top1= 88.5417


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5640 top1= 53.1751


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6555 top1= 48.3474

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0630 top1= 97.6562
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0359 top1= 99.3750
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0420 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3170 top1= 89.1126


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4666 top1= 53.4655


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8434 top1= 48.6779

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0165 top1= 99.8438
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0253 top1= 99.5312
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0298 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2938 top1= 90.5849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5588 top1= 51.9732


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7998 top1= 48.2171

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0374 top1= 98.7500
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0248 top1= 99.5312
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0236 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2883 top1= 90.7051


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4124 top1= 53.1350


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7410 top1= 48.2672

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0200 top1= 99.6875
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0221 top1= 99.6875
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0261 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2989 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4290 top1= 53.5357


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7654 top1= 48.5377

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0298 top1= 99.2188
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0225 top1= 99.5312
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0254 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2963 top1= 90.2244


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3543 top1= 54.3770


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6376 top1= 49.2588

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0237 top1= 99.6875
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0172 top1= 99.8438
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0211 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2933 top1= 90.4447


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3026 top1= 54.6575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6288 top1= 48.6879

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0224 top1= 99.5312
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0216 top1= 99.8438
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0183 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2931 top1= 90.5549


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2855 top1= 54.6074


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6708 top1= 48.1871

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0178 top1= 99.6875
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0200 top1= 99.6875
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0189 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3031 top1= 90.4147


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3535 top1= 54.3870


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7436 top1= 47.9567

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0228 top1= 99.8438
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0183 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0208 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3024 top1= 89.9639


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3633 top1= 54.4872


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7191 top1= 48.3574

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0217 top1= 99.8438
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0164 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0310 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3223 top1= 88.8321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3375 top1= 54.3870


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8124 top1= 47.7364

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0423 top1= 98.9062
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0204 top1= 99.8438
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0404 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3125 top1= 89.3530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3468 top1= 54.3970


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5888 top1= 48.3874

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0242 top1= 99.5312
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0248 top1= 99.8438
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0341 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3109 top1= 89.8037


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3499 top1= 54.3470


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5259 top1= 49.1787

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0175 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0248 top1= 99.6875
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0279 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3209 top1= 89.2428


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3672 top1= 54.1867


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6313 top1= 48.5577

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0249 top1= 99.8438
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0177 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0220 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3213 top1= 89.2728


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3656 top1= 53.8261


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9452 top1= 47.1955

