
=== 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 0x7efcc415e2e0>

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=4.6562 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=4.2588 top1= 46.1939

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1347 top1= 95.7812
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0861 top1= 97.6562
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1148 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4794 top1= 87.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9679 top1= 50.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9096 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= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4342 top1= 88.1310


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6567 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5663 top1= 46.5845

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0830 top1= 97.9688
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0527 top1= 98.7500
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0751 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3973 top1= 88.7720


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4367 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2955 top1= 46.7548

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0664 top1= 98.9062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0414 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0606 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3669 top1= 89.1426


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2634 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1134 top1= 46.9451

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0546 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0353 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0512 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3473 top1= 89.3429


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1219 top1= 50.8814


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9494 top1= 47.4659

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0459 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0310 top1= 99.5312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0463 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3302 top1= 89.7636


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0504 top1= 51.1719


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8836 top1= 48.0769

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0395 top1= 99.3750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0270 top1= 99.5312
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0427 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3197 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9971 top1= 51.5325


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8605 top1= 48.3974

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0327 top1= 99.5312
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0250 top1= 99.5312
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0396 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3101 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9901 top1= 51.6627


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9416 top1= 48.3173

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0366 top1= 99.0625
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0227 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0485 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3138 top1= 89.6334


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9478 top1= 51.4323


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9727 top1= 48.5176

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0427 top1= 98.5938
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0339 top1= 99.3750
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0591 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3307 top1= 88.6719


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7953 top1= 52.5541


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7801 top1= 50.1402

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0521 top1= 97.8125
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0349 top1= 99.2188
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0495 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3443 top1= 87.9908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7443 top1= 52.5040


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9213 top1= 47.8566

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0622 top1= 97.1875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0490 top1= 98.4375
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0665 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3857 top1= 85.7372


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5398 top1= 53.0449


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2328 top1= 47.6162

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0345 top1= 99.2188
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0276 top1= 99.3750
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0412 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3301 top1= 88.6418


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6229 top1= 53.1250


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7252 top1= 48.3073

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0344 top1= 99.0625
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0341 top1= 99.2188
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0314 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3055 top1= 89.6735


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4160 top1= 53.9764


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8725 top1= 48.4575

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0214 top1= 99.3750
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0246 top1= 99.6875
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0240 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2994 top1= 90.2544


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6644 top1= 51.8930


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8225 top1= 48.1971

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0381 top1= 98.7500
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0170 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0201 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2870 top1= 90.7252


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4582 top1= 52.7945


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7911 top1= 48.5076

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0182 top1= 99.6875
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0232 top1= 99.6875
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0199 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2912 top1= 90.4447


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4445 top1= 53.8462


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7668 top1= 48.7680

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0233 top1= 99.3750
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0189 top1= 99.8438
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0221 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2940 top1= 90.3446


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4058 top1= 54.0164


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7919 top1= 48.9183

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0182 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0171 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0205 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2951 top1= 90.2244


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3504 top1= 54.4171


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7314 top1= 48.7881

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0218 top1= 99.6875
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0157 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0187 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2962 top1= 90.2845


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3617 top1= 54.2869


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7246 top1= 48.3474

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0177 top1= 99.5312
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0163 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0190 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2931 top1= 90.3045


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3878 top1= 54.0865


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5524 top1= 49.1486

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0148 top1= 99.8438
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0192 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0222 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3059 top1= 90.2544


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4021 top1= 53.9964


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8477 top1= 47.7664

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0253 top1= 99.2188
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0213 top1= 99.8438
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0260 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3186 top1= 89.6234


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3943 top1= 54.1667


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9917 top1= 47.3257

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0397 top1= 99.3750
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0257 top1= 99.6875
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0214 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3250 top1= 88.9022


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3837 top1= 54.0465


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9146 top1= 48.0669

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0288 top1= 99.3750
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0175 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0247 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3090 top1= 89.7636


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3946 top1= 54.0865


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7849 top1= 47.6663

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0169 top1= 99.6875
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0161 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0313 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2946 top1= 90.4447


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4168 top1= 53.6458


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4856 top1= 49.2688

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0157 top1= 99.8438
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0204 top1= 99.8438
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0257 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3099 top1= 89.7436


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4150 top1= 53.5958


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7421 top1= 48.5577

