
=== 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)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7f22a242b250>

Train epoch 1
[E 1B0  |    640/60000 (  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')


[E 1B10 |   7040/60000 ( 12%) ] Loss: 1.0407 top1= 62.8125
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3876 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6088 top1= 82.7524


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4179 top1= 49.3690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1129 top1= 44.2708

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2722 top1= 91.4062
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1975 top1= 93.4375
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1982 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4719 top1= 86.5685


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8539 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0892 top1= 45.9135

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1578 top1= 95.0000
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1175 top1= 96.8750
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1515 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3784 top1= 88.3213


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6704 top1= 52.0833


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6922 top1= 47.7764

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1304 top1= 95.9375
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0869 top1= 97.0312
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1134 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3342 top1= 89.2628


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5485 top1= 54.4071


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4368 top1= 50.1002

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1012 top1= 97.1875
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0637 top1= 98.2812
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0911 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3089 top1= 89.9940


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5778 top1= 55.5689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4014 top1= 52.2035

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0813 top1= 97.8125
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0471 top1= 98.9062
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0674 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2973 top1= 90.1643


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6344 top1= 56.1198


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2356 top1= 55.0681

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0583 top1= 98.9062
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0393 top1= 99.0625
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0522 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3000 top1= 90.1743


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5603 top1= 57.3017


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2414 top1= 56.1799

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0580 top1= 98.5938
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0288 top1= 99.3750
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0393 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2763 top1= 90.7853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5552 top1= 58.3534


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3370 top1= 55.0280

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0441 top1= 98.9062
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0212 top1= 99.8438
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0511 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2831 top1= 90.6050


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3725 top1= 59.6154


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4741 top1= 55.3886

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0455 top1= 98.7500
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0262 top1= 99.0625
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0318 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2652 top1= 91.2260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3092 top1= 60.5068


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2039 top1= 58.8341

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0198 top1= 99.3750
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0322 top1= 98.9062
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0302 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2518 top1= 91.6667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2366 top1= 59.6054


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1290 top1= 59.9058

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0179 top1= 99.5312
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0161 top1= 99.8438
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0159 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2535 top1= 91.8670


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9929 top1= 62.6002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3575 top1= 56.2400

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0242 top1= 99.5312
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0138 top1= 99.8438
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0142 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2458 top1= 92.0673


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0611 top1= 63.4415


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0451 top1= 59.2248

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0154 top1= 99.5312
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0099 top1= 99.6875
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0203 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2550 top1= 92.0272


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9221 top1= 64.0525


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3863 top1= 57.5521

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0280 top1= 99.2188
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0108 top1= 99.6875
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0182 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2456 top1= 92.1274


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8034 top1= 65.3946


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1164 top1= 61.0577

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0116 top1= 99.6875
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0110 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2412 top1= 92.4780


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6324 top1= 67.4279


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9770 top1= 61.6887

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0106 top1= 99.8438
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0102 top1= 99.8438
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0117 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2540 top1= 92.1875


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5780 top1= 68.0990


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7978 top1= 66.1258

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0172 top1= 99.5312
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0063 top1= 99.8438
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0085 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2446 top1= 92.7083


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4849 top1= 69.2909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7079 top1= 65.7853

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0061 top1= 99.6875
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0049 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0059 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2395 top1= 92.6182


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4204 top1= 70.4627


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8397 top1= 65.3946

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0035 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0068 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2270 top1= 93.0990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4162 top1= 70.6530


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5189 top1= 69.2408

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0024 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0053 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2260 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3827 top1= 71.5946


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3546 top1= 71.8249

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2290 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3228 top1= 72.4459


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3496 top1= 72.7564

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2298 top1= 93.3694


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2923 top1= 73.1070


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2490 top1= 74.3289

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2299 top1= 93.4495


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2592 top1= 73.7179


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2399 top1= 74.6394

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2299 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2258 top1= 74.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2154 top1= 75.2003

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2301 top1= 93.5497


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1970 top1= 74.7997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2010 top1= 75.6110

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2300 top1= 93.5497


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1699 top1= 75.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1821 top1= 76.0417

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2303 top1= 93.6398


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1408 top1= 75.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1671 top1= 76.3421

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2302 top1= 93.7600


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1168 top1= 76.0717


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1473 top1= 76.7027

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2303 top1= 93.7700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0956 top1= 76.5224


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1307 top1= 77.0232

