
=== 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 0x7f678dc876d0>

Train epoch 1
[E 1B0  |    640/60000 (  1%) ] Loss: 2.3080 top1=  8.4375

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')
Worker 2 has targets: tensor([3, 0, 3, 2, 7], device='cuda:0')
Worker 3 has targets: tensor([1, 4, 8, 2, 8], device='cuda:0')
Worker 4 has targets: tensor([9, 5, 0, 1, 3], device='cuda:0')
Worker 5 has targets: tensor([5, 6, 2, 4, 3], device='cuda:0')
Worker 6 has targets: tensor([2, 5, 0, 9, 9], device='cuda:0')
Worker 7 has targets: tensor([2, 2, 1, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([3, 8, 7, 0, 3], device='cuda:0')
Worker 9 has targets: tensor([1, 7, 1, 7, 2], device='cuda:0')
Worker 10 has targets: tensor([8, 4, 4, 3, 9], device='cuda:0')
Worker 11 has targets: tensor([3, 4, 7, 7, 9], device='cuda:0')
Worker 12 has targets: tensor([7, 4, 3, 9, 4], device='cuda:0')
Worker 13 has targets: tensor([4, 5, 0, 7, 1], device='cuda:0')
Worker 14 has targets: tensor([4, 2, 3, 5, 5], device='cuda:0')
Worker 15 has targets: tensor([4, 7, 5, 4, 7], device='cuda:0')
Worker 16 has targets: tensor([1, 1, 5, 7, 9], device='cuda:0')
Worker 17 has targets: tensor([8, 7, 2, 2, 0], device='cuda:0')
Worker 18 has targets: tensor([7, 8, 0, 0, 6], device='cuda:0')
Worker 19 has targets: tensor([9, 9, 5, 2, 8], device='cuda:0')


[E 1B10 |   7040/60000 ( 12%) ] Loss: 1.8908 top1= 50.0000
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.8097 top1= 75.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4188 top1= 87.7103


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4507 top1= 86.8189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4648 top1= 85.9275

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.5111 top1= 82.9688
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.4583 top1= 84.2188
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.3737 top1= 88.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2750 top1= 92.1975


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2847 top1= 91.6066


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2939 top1= 91.5064

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.2620 top1= 92.0312
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2424 top1= 92.3438
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.2349 top1= 92.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2321 top1= 93.2392


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2347 top1= 93.0489


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2504 top1= 92.4079

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1654 top1= 95.1562
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1524 top1= 95.7812
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1491 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2007 top1= 94.1106


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2151 top1= 93.3894


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2002 top1= 93.9403

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1147 top1= 96.5625
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1032 top1= 97.3438
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.1030 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1832 top1= 94.5413


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2037 top1= 93.9303


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1790 top1= 94.4211

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0773 top1= 97.9688
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0632 top1= 98.7500
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0665 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1756 top1= 94.8618


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1921 top1= 94.5012


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1801 top1= 94.6014

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0542 top1= 98.7500
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0441 top1= 99.3750
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0584 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1765 top1= 95.1522


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1972 top1= 94.6114


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1765 top1= 94.9820

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0340 top1= 99.5312
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0298 top1= 99.3750
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0383 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1777 top1= 95.0621


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2090 top1= 94.5513


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1842 top1= 94.8918

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0261 top1= 99.5312
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0163 top1= 99.8438
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0232 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1815 top1= 95.1823


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2293 top1= 93.8301


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2027 top1= 94.6715

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0238 top1= 99.5312
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0183 top1= 99.3750
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0213 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1861 top1= 95.0721


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2423 top1= 93.7700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1967 top1= 94.9419

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0175 top1=100.0000
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0252 top1= 99.5312
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0166 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1797 top1= 95.2925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2113 top1= 94.4812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1870 top1= 95.1522

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0173 top1= 99.5312
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0231 top1= 99.5312
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0355 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1868 top1= 95.1823


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1950 top1= 94.7817


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2003 top1= 95.0220

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0145 top1=100.0000
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0092 top1= 99.8438
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0086 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1926 top1= 95.2023


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1895 top1= 95.4828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2089 top1= 95.0421

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0096 top1= 99.8438
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0099 top1= 99.6875
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0106 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1813 top1= 95.5729


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1846 top1= 95.4828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1949 top1= 95.2524

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0061 top1= 99.8438
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0052 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1817 top1= 95.7131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1892 top1= 95.5128


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1825 top1= 95.4828

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1859 top1= 95.6430


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1900 top1= 95.6230


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1900 top1= 95.4227

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1879 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1932 top1= 95.5629


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1856 top1= 95.5829

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1894 top1= 95.6731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1959 top1= 95.5629


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1858 top1= 95.6530

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0013 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1940 top1= 95.5829


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1984 top1= 95.5829


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1948 top1= 95.5929

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1957 top1= 95.5329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2005 top1= 95.5729


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1967 top1= 95.6030

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1976 top1= 95.5829


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2022 top1= 95.5729


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1959 top1= 95.6030

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1980 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2038 top1= 95.5629


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1981 top1= 95.5529

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0009 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1993 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2053 top1= 95.5429


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1972 top1= 95.5829

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0008 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2003 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2065 top1= 95.5429


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1982 top1= 95.6030

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2014 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2076 top1= 95.5329


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1991 top1= 95.5929

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2023 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2087 top1= 95.5228


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2000 top1= 95.6330

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2031 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2096 top1= 95.5529


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2008 top1= 95.6230

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2039 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2105 top1= 95.5629


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2015 top1= 95.6330

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0006 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2046 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2113 top1= 95.5629


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2021 top1= 95.6230

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0006 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2052 top1= 95.6731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2119 top1= 95.5629


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2027 top1= 95.6330

