
=== 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 0x7efd697a39d0>

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: 1.4818 top1= 53.1250
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.7073 top1= 80.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0861 top1= 78.2452


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6693 top1= 48.4075


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7991 top1= 42.3377

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.4115 top1= 89.6875
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4175 top1= 88.4375
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2916 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0311 top1= 81.0196


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5105 top1= 48.9083


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8580 top1= 44.1206

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3406 top1= 92.1875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3791 top1= 90.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2579 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0135 top1= 80.0581


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4005 top1= 49.0585


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7927 top1= 43.9002

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.3303 top1= 92.5000
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.3593 top1= 90.6250
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.2430 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0115 top1= 79.2668


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3523 top1= 49.1587


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7644 top1= 43.9603

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.3179 top1= 92.1875
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.3432 top1= 91.5625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.2384 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0161 top1= 78.5757


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3122 top1= 49.2288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7270 top1= 43.9603

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.3132 top1= 92.1875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.3397 top1= 91.8750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.2395 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0234 top1= 77.8946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2866 top1= 49.2788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6945 top1= 43.9603

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.3097 top1= 92.8125
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.3485 top1= 91.5625
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.2420 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0294 top1= 77.3438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2643 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6737 top1= 44.1506

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.3044 top1= 93.4375
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.3525 top1= 90.9375
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.2437 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0339 top1= 77.5641


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2473 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6484 top1= 44.3009

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.3011 top1= 93.4375
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.3447 top1= 90.9375
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.2378 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0385 top1= 77.7845


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2383 top1= 49.4191


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6266 top1= 44.3209

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.3036 top1= 92.8125
[E10B10 |   4224/60000 (  7%) ] Loss: 0.3389 top1= 91.2500
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.2374 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0436 top1= 77.5040


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2254 top1= 49.4091


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6080 top1= 44.2508

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.3039 top1= 92.5000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.3344 top1= 91.5625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.2375 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0469 top1= 77.5741


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2091 top1= 49.3890


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5875 top1= 44.1106

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.3054 top1= 92.8125
[E12B10 |   4224/60000 (  7%) ] Loss: 0.3319 top1= 91.5625
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.2444 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0534 top1= 77.0333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1955 top1= 49.3690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5699 top1= 44.2408

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.3051 top1= 92.8125
[E13B10 |   4224/60000 (  7%) ] Loss: 0.3301 top1= 91.5625
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.2437 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0562 top1= 77.0232


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1912 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5567 top1= 44.1106

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.3102 top1= 92.1875
[E14B10 |   4224/60000 (  7%) ] Loss: 0.3291 top1= 91.8750
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.2451 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0585 top1= 76.8530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1804 top1= 49.3890


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5551 top1= 44.0905

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.3122 top1= 91.8750
[E15B10 |   4224/60000 (  7%) ] Loss: 0.3337 top1= 91.2500
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.2446 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0603 top1= 76.6226


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1709 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5442 top1= 44.1406

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.3130 top1= 91.5625
[E16B10 |   4224/60000 (  7%) ] Loss: 0.3315 top1= 91.2500
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.2446 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0622 top1= 76.7027


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1633 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5358 top1= 44.0505

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.3121 top1= 91.5625
[E17B10 |   4224/60000 (  7%) ] Loss: 0.3254 top1= 91.5625
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.2431 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0632 top1= 76.6426


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1591 top1= 49.3690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5327 top1= 44.0405

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.3117 top1= 91.8750
[E18B10 |   4224/60000 (  7%) ] Loss: 0.3242 top1= 91.8750
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.2429 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0657 top1= 76.2220


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1520 top1= 49.3690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5339 top1= 43.9904

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.3148 top1= 91.8750
[E19B10 |   4224/60000 (  7%) ] Loss: 0.3249 top1= 91.8750
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.2412 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0659 top1= 76.0817


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1496 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5230 top1= 44.0304

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.3141 top1= 91.8750
[E20B10 |   4224/60000 (  7%) ] Loss: 0.3279 top1= 91.2500
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.2407 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0681 top1= 75.9716


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1374 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5326 top1= 43.9002

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.3159 top1= 91.5625
[E21B10 |   4224/60000 (  7%) ] Loss: 0.3276 top1= 91.5625
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.2450 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0707 top1= 75.4808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1346 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5257 top1= 43.9103

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.3164 top1= 91.8750
[E22B10 |   4224/60000 (  7%) ] Loss: 0.3266 top1= 91.8750
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.2438 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0691 top1= 75.8213


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1319 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5186 top1= 44.0104

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.3115 top1= 92.1875
[E23B10 |   4224/60000 (  7%) ] Loss: 0.3282 top1= 91.8750
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.2432 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0688 top1= 75.7612


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1304 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5091 top1= 44.0805

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.3105 top1= 91.8750
[E24B10 |   4224/60000 (  7%) ] Loss: 0.3269 top1= 91.8750
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.2449 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0716 top1= 75.3105


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1259 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5019 top1= 44.0304

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.3130 top1= 92.1875
[E25B10 |   4224/60000 (  7%) ] Loss: 0.3200 top1= 91.8750
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.2385 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0704 top1= 75.8213


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1256 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4982 top1= 44.0304

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.3120 top1= 91.8750
[E26B10 |   4224/60000 (  7%) ] Loss: 0.3143 top1= 92.1875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.2377 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0727 top1= 75.4908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1251 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5016 top1= 43.8702

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.3167 top1= 91.8750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.3164 top1= 91.8750
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.2395 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0725 top1= 75.5709


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1242 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4791 top1= 43.9804

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.3154 top1= 92.1875
[E28B10 |   4224/60000 (  7%) ] Loss: 0.3200 top1= 92.1875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.2424 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0725 top1= 75.2504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1228 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4750 top1= 44.0705

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.3111 top1= 92.1875
[E29B10 |   4224/60000 (  7%) ] Loss: 0.3195 top1= 92.1875
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.2415 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0713 top1= 75.2304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1226 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4765 top1= 44.2007

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.3077 top1= 91.8750
[E30B10 |   4224/60000 (  7%) ] Loss: 0.3146 top1= 92.5000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.2382 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0716 top1= 75.2304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1258 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4788 top1= 43.9804

