
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f4ab3e809d0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0176 top1= 62.8125
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2684 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8275 top1= 69.6414


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.2744 top1= 48.4575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0281 top1= 43.7300

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3944 top1= 91.2500
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2743 top1= 92.1875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1568 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7624 top1= 76.5124


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0604 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7974 top1= 45.5028

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1514 top1= 95.3125
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1247 top1= 95.6250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0797 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7170 top1= 74.8798


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4629 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6600 top1= 45.9435

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0985 top1= 96.5625
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0835 top1= 96.8750
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0570 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6670 top1= 75.3305


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4117 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4945 top1= 45.9836

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0627 top1= 97.8125
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0465 top1= 99.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0405 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6254 top1= 76.2821


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3852 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4388 top1= 46.1739

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0417 top1= 98.7500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0356 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0302 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6310 top1= 75.5108


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2996 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2284 top1= 46.3742

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0280 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0404 top1= 98.7500
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0231 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6314 top1= 75.2905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2296 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0222 top1= 47.0753

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0193 top1= 99.6875
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0243 top1= 99.3750
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0200 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6180 top1= 76.0517


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1387 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8733 top1= 47.9167

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0151 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0243 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0169 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5451 top1= 78.8261


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0123 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0240 top1= 48.5176

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0193 top1= 99.6875
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0283 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5020 top1= 80.8994


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8289 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9192 top1= 48.8582

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0145 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0277 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0224 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4706 top1= 82.8626


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6822 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8266 top1= 48.6879

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0244 top1= 99.6875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0294 top1= 99.3750
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0240 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4065 top1= 86.5785


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7204 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9425 top1= 48.1070

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0377 top1= 99.0625
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0412 top1= 98.7500
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0382 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4067 top1= 85.8373


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5129 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6862 top1= 48.8381

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0346 top1= 99.3750
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0330 top1= 99.0625
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0201 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3778 top1= 88.0208


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3269 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5579 top1= 49.7596

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0170 top1= 99.6875
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0164 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0295 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4074 top1= 85.9675


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2736 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3098 top1= 50.4006

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0175 top1= 99.6875
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0165 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0401 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4391 top1= 84.9058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0314 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2200 top1= 51.7628

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0215 top1= 99.6875
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0143 top1= 99.6875
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0125 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4611 top1= 83.5136


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9641 top1= 50.2404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1341 top1= 52.1434

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0130 top1= 99.6875
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0202 top1= 99.3750
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0081 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4715 top1= 82.7925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1448 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1764 top1= 51.7027

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0126 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0112 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0108 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4649 top1= 83.0529


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9962 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1017 top1= 52.8446

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0107 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0141 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0101 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4322 top1= 84.5353


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9740 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0597 top1= 53.3554

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0103 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0136 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0110 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3981 top1= 86.3582


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9185 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1969 top1= 52.5741

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0131 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0154 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0136 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4197 top1= 85.7472


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8644 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1235 top1= 53.1751

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0117 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0115 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0125 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3915 top1= 86.1679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8344 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0374 top1= 53.3854

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0138 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0200 top1= 99.6875
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0177 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3708 top1= 87.2696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7869 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1467 top1= 52.5040

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0141 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0211 top1= 99.6875
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0167 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3662 top1= 87.6402


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7638 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1298 top1= 52.6542

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0128 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0251 top1= 99.3750
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0192 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3627 top1= 87.4800


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7377 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2637 top1= 51.4623

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0193 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0169 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0201 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3562 top1= 88.7220


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7219 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4278 top1= 51.2520

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0177 top1= 99.6875
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0426 top1= 99.0625
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0234 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3603 top1= 88.4916


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7220 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4062 top1= 51.0216

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0269 top1= 99.3750
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0213 top1= 99.6875
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0165 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3620 top1= 88.5817


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7081 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3069 top1= 51.6927

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0122 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0311 top1= 98.7500
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0149 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3468 top1= 88.8421


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7126 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2182 top1= 51.1418

