
=== 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 0x7fb925a3e2e0>

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: 1.4160 top1= 52.5000
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.8527 top1= 71.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3780 top1= 78.0549


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1435 top1= 48.5377


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9240 top1= 42.8385

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.5383 top1= 83.1250
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.3914 top1= 87.9688
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.3628 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0354 top1= 81.6907


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8160 top1= 49.5092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6202 top1= 44.3209

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2937 top1= 91.4062
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2336 top1= 93.2812
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2621 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9193 top1= 83.0829


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1316 top1= 49.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0284 top1= 44.8217

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2532 top1= 92.8125
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1822 top1= 94.8438
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2248 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8193 top1= 83.3934


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5401 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5863 top1= 45.2524

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2066 top1= 93.9062
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1723 top1= 95.0000
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2350 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8076 top1= 83.4635


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4778 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3068 top1= 45.4026

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1971 top1= 93.9062
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1474 top1= 95.3125
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1846 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7831 top1= 83.9143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5103 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3291 top1= 45.7532

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1694 top1= 95.0000
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1382 top1= 95.1562
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1750 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7392 top1= 84.5653


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6769 top1= 50.1102


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5518 top1= 46.0136

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1443 top1= 95.9375
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1160 top1= 96.4062
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1460 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7325 top1= 85.0561


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6106 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4505 top1= 46.0938

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1633 top1= 94.8438
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1103 top1= 96.7188
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1360 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7143 top1= 85.9075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6299 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4957 top1= 46.2640

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1244 top1= 96.4062
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0992 top1= 97.3438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1199 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6860 top1= 86.0577


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8068 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6600 top1= 46.3341

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1178 top1= 96.7188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0928 top1= 97.1875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1211 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6858 top1= 86.3281


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7109 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5283 top1= 46.3842

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1085 top1= 96.7188
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0841 top1= 97.1875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0974 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6692 top1= 86.6186


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7502 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5098 top1= 46.5445

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1220 top1= 96.0938
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0770 top1= 97.5000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1023 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6480 top1= 86.8389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8879 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6445 top1= 46.5745

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0928 top1= 97.8125
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0801 top1= 97.8125
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0799 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6518 top1= 86.7788


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8106 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5988 top1= 46.5345

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0911 top1= 97.5000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0639 top1= 97.8125
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0844 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6395 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8563 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6316 top1= 46.7047

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0841 top1= 97.8125
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0613 top1= 98.1250
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0721 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6190 top1= 87.1094


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9664 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7523 top1= 46.7548

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0805 top1= 97.8125
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0527 top1= 97.9688
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0741 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6180 top1= 87.4199


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8670 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6814 top1= 46.8149

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0789 top1= 97.9688
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0521 top1= 98.2812
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0632 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6191 top1= 86.8189


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9166 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7592 top1= 46.8850

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0733 top1= 98.5938
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0459 top1= 98.9062
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0575 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5954 top1= 87.2396


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0424 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8484 top1= 46.9351

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0679 top1= 98.4375
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0534 top1= 98.1250
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0550 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5926 top1= 87.8305


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0060 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8120 top1= 46.9551

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0724 top1= 98.1250
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0479 top1= 98.4375
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0576 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5942 top1= 86.9792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9838 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8544 top1= 46.9451

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0644 top1= 97.9688
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0351 top1= 98.7500
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0445 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5722 top1= 87.5801


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1196 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9633 top1= 46.9852

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0626 top1= 98.2812
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0376 top1= 99.2188
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0529 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5745 top1= 87.6502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0948 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9572 top1= 47.0553

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0565 top1= 98.9062
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0311 top1= 99.2188
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0536 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5739 top1= 87.1595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0596 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9401 top1= 47.0553

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0594 top1= 98.9062
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0278 top1= 99.6875
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0401 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5561 top1= 87.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2073 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1376 top1= 47.0653

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0411 top1= 99.2188
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0352 top1= 99.0625
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0341 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5577 top1= 87.7204


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1818 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1122 top1= 47.1254

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0465 top1= 98.9062
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0280 top1= 99.2188
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0381 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5573 top1= 87.5000


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1546 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0778 top1= 47.1855

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0403 top1= 99.3750
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0230 top1= 99.6875
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0304 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5407 top1= 87.8506


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2639 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2533 top1= 47.1354

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0393 top1= 98.9062
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0338 top1= 98.7500
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0529 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5413 top1= 87.8205


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2324 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2508 top1= 47.1655

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0471 top1= 98.9062
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0198 top1= 99.3750
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0344 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5433 top1= 87.5401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2531 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2532 top1= 47.2155

