
=== 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 0x7f8c75ce02b0>

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: 1.0642 top1= 61.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3930 top1= 87.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8817 top1= 66.1358


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4474 top1= 49.2588


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0479 top1= 44.1707

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2726 top1= 90.9375
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2020 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2096 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5636 top1= 81.2600


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4844 top1= 52.0132


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3365 top1= 45.9034

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1772 top1= 94.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1304 top1= 97.1875
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1592 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4523 top1= 84.8758


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2393 top1= 55.0180


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0099 top1= 46.2139

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1424 top1= 95.6250
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1051 top1= 97.0312
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1275 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3942 top1= 86.9591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1956 top1= 55.9495


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7923 top1= 46.8650

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1166 top1= 96.8750
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0856 top1= 97.6562
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1051 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3560 top1= 88.2212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2259 top1= 56.5104


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6186 top1= 48.0769

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0948 top1= 97.6562
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0685 top1= 98.4375
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0877 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3305 top1= 89.1627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2610 top1= 56.8209


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4666 top1= 49.0986

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0789 top1= 98.1250
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0593 top1= 98.4375
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0793 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3200 top1= 89.5433


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2672 top1= 57.1214


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4040 top1= 50.1502

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0668 top1= 98.7500
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0537 top1= 98.9062
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0678 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3125 top1= 89.7135


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2607 top1= 57.3217


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3847 top1= 50.9315

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0603 top1= 98.1250
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0507 top1= 99.0625
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0602 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3087 top1= 89.8237


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1931 top1= 57.6422


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3729 top1= 51.5325

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0593 top1= 98.1250
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0410 top1= 99.2188
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0533 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3109 top1= 89.5633


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1069 top1= 57.8526


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5439 top1= 49.2488

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0557 top1= 98.9062
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0387 top1= 99.0625
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0571 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3135 top1= 89.2428


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1790 top1= 57.7825


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6570 top1= 49.0485

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0635 top1= 97.8125
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0443 top1= 98.9062
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0653 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3153 top1= 89.1326


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0925 top1= 58.7540


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5883 top1= 50.4006

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0569 top1= 98.9062
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0354 top1= 99.5312
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0509 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3022 top1= 89.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0340 top1= 59.0645


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3156 top1= 51.0016

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0401 top1= 99.2188
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0300 top1= 99.5312
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0575 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3008 top1= 90.0441


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0043 top1= 58.8842


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2900 top1= 49.6995

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0480 top1= 99.3750
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0300 top1= 99.5312
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0324 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3071 top1= 89.6234


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0327 top1= 58.5938


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4802 top1= 50.1603

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0676 top1= 98.1250
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0275 top1= 99.5312
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0363 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2886 top1= 90.3245


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0368 top1= 58.6839


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4374 top1= 50.0200

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0360 top1= 99.2188
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0244 top1= 99.8438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0385 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2820 top1= 90.7352


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0142 top1= 58.8041


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2648 top1= 51.2320

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0288 top1= 99.6875
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0292 top1= 99.6875
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0524 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2880 top1= 90.4547


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0394 top1= 58.5537


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3024 top1= 50.9515

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0315 top1= 99.6875
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0253 top1= 99.5312
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0319 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2911 top1= 90.4447


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0598 top1= 58.1631


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1561 top1= 51.5825

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0351 top1= 99.3750
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0273 top1= 99.6875
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0266 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3107 top1= 89.4631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9598 top1= 58.7039


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5294 top1= 49.5092

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0677 top1= 98.4375
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0251 top1= 99.8438
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0306 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3025 top1= 89.7636


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9755 top1= 58.4034


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5486 top1= 48.4375

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0358 top1= 99.2188
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0338 top1= 99.5312
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0417 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2946 top1= 90.2744


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0368 top1= 57.9527


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3849 top1= 49.7997

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0280 top1= 99.6875
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0263 top1= 99.6875
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0400 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2977 top1= 90.1843


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0356 top1= 57.8826


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2477 top1= 50.7212

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0329 top1= 99.3750
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0308 top1= 99.8438
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0405 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3189 top1= 89.6835


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0742 top1= 57.2817


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2255 top1= 50.4307

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0589 top1= 97.9688
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0285 top1= 99.8438
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0329 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3072 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9865 top1= 58.0329


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3988 top1= 49.1787

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0432 top1= 99.5312
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0280 top1= 99.8438
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0383 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2975 top1= 90.3546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9027 top1= 58.3534


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3224 top1= 49.1787

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0350 top1= 99.0625
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0261 top1= 99.8438
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0423 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3026 top1= 90.0942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9401 top1= 57.1815


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2597 top1= 49.9099

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0295 top1= 99.3750
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0350 top1= 99.3750
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0429 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3109 top1= 89.5633


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0996 top1= 56.4503


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2702 top1= 50.2304

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0410 top1= 99.3750
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0453 top1= 98.9062
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0376 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3123 top1= 89.6635


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0753 top1= 55.9395


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4573 top1= 48.4776

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0515 top1= 98.2812
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0442 top1= 99.0625
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0512 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3159 top1= 89.6835


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1945 top1= 54.8377


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4043 top1= 48.3474

