
=== 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 0x7fb0f66d67f0>

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=2.7926 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=1.0114 top1= 79.2969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3524 top1= 49.1587


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7644 top1= 43.9704

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.3179 top1= 92.1875
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.3431 top1= 91.2500
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.2389 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=2.7285 top1= 43.9503

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.3138 top1= 92.1875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.3436 top1= 91.8750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.2384 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0237 top1= 77.8946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2858 top1= 49.2688


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7009 top1= 44.0104

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.3089 top1= 92.8125
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.3475 top1= 91.8750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.2402 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0286 top1= 77.5841


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2647 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6721 top1= 44.1807

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.3058 top1= 93.1250
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.3471 top1= 90.9375
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.2448 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0337 top1= 77.5140


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2472 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6502 top1= 44.3209

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.3005 top1= 93.1250
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.3335 top1= 91.8750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.2404 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0396 top1= 77.4639


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2373 top1= 49.3990


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6259 top1= 44.3510

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.2986 top1= 93.1250
[E10B10 |   4224/60000 (  7%) ] Loss: 0.3298 top1= 91.8750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.2384 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0442 top1= 77.5140


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2256 top1= 49.4091


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6109 top1= 44.3009

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.3033 top1= 93.1250
[E11B10 |   4224/60000 (  7%) ] Loss: 0.3280 top1= 91.8750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.2385 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0491 top1= 77.4439


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2138 top1= 49.4191


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5912 top1= 44.2107

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.3067 top1= 92.5000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.3318 top1= 91.8750
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.2383 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0526 top1= 77.3738


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1995 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5700 top1= 44.1406

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.3125 top1= 92.5000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.3357 top1= 91.2500
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.2417 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0571 top1= 77.0433


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1887 top1= 49.4091


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5535 top1= 44.0204

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.3162 top1= 91.5625
[E14B10 |   4224/60000 (  7%) ] Loss: 0.3326 top1= 91.5625
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.2455 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0586 top1= 76.9331


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1793 top1= 49.3890


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5480 top1= 44.0905

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.3126 top1= 91.8750
[E15B10 |   4224/60000 (  7%) ] Loss: 0.3369 top1= 91.2500
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.2478 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0602 top1= 76.6526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1708 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5444 top1= 44.2208

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.3091 top1= 92.1875
[E16B10 |   4224/60000 (  7%) ] Loss: 0.3293 top1= 91.2500
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.2498 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0628 top1= 76.8029


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1610 top1= 49.3690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5345 top1= 44.0905

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.3140 top1= 91.8750
[E17B10 |   4224/60000 (  7%) ] Loss: 0.3290 top1= 91.8750
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.2440 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0624 top1= 76.8329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1583 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5352 top1= 44.0304

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.3130 top1= 92.5000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.3265 top1= 91.8750
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.2430 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0637 top1= 76.7228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1532 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5232 top1= 44.0505

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.3134 top1= 91.5625
[E19B10 |   4224/60000 (  7%) ] Loss: 0.3242 top1= 91.8750
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.2416 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0671 top1= 76.3622


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1478 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5278 top1= 43.9704

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.3169 top1= 91.5625
[E20B10 |   4224/60000 (  7%) ] Loss: 0.3251 top1= 91.8750
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.2458 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0691 top1= 76.1018


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1428 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5130 top1= 43.9503

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.3178 top1= 91.8750
[E21B10 |   4224/60000 (  7%) ] Loss: 0.3252 top1= 91.8750
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.2451 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0690 top1= 75.9115


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1365 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5166 top1= 43.9704

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.3152 top1= 91.8750
[E22B10 |   4224/60000 (  7%) ] Loss: 0.3290 top1= 92.1875
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.2422 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0687 top1= 76.0817


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1319 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5027 top1= 44.0805

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.3109 top1= 92.5000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.3265 top1= 91.8750
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.2406 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0692 top1= 75.8413


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1314 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5008 top1= 44.0605

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.3103 top1= 92.1875
[E24B10 |   4224/60000 (  7%) ] Loss: 0.3212 top1= 91.8750
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.2412 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0685 top1= 75.7712


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1280 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5048 top1= 43.9904

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.3139 top1= 91.8750
[E25B10 |   4224/60000 (  7%) ] Loss: 0.3192 top1= 92.1875
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.2391 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0689 top1= 75.8514


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1267 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4988 top1= 43.9303

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.3148 top1= 92.1875
[E26B10 |   4224/60000 (  7%) ] Loss: 0.3259 top1= 91.8750
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.2436 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0708 top1= 75.3405


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1254 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4975 top1= 44.0405

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.3125 top1= 91.8750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.3238 top1= 91.8750
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.2416 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0689 top1= 75.5409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1268 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4871 top1= 44.0605

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.3120 top1= 92.1875
[E28B10 |   4224/60000 (  7%) ] Loss: 0.3157 top1= 91.8750
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.2369 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0695 top1= 75.7712


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1275 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4891 top1= 44.0405

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.3161 top1= 91.8750
[E29B10 |   4224/60000 (  7%) ] Loss: 0.3166 top1= 92.5000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.2335 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0700 top1= 75.6110


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1218 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4809 top1= 44.1206

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.3119 top1= 92.1875
[E30B10 |   4224/60000 (  7%) ] Loss: 0.3212 top1= 91.8750
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.2386 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0730 top1= 75.0801


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1217 top1= 49.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4904 top1= 44.0004

