
=== 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 0x7f958c0ac730>

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: 1.8946 top1= 50.1562
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.8142 top1= 75.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4215 top1= 87.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4509 top1= 86.7989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4622 top1= 85.8974

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.5141 top1= 84.3750
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.4585 top1= 84.3750
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.3699 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2804 top1= 91.8970


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2860 top1= 91.4663


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2999 top1= 91.3061

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.2563 top1= 92.0312
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2436 top1= 92.1875
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.2337 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2365 top1= 93.1090


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2376 top1= 92.9587


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2506 top1= 92.4379

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1749 top1= 94.8438
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1562 top1= 95.6250
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1542 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2040 top1= 93.8502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2176 top1= 93.2192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2016 top1= 93.9303

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1174 top1= 96.5625
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1060 top1= 97.3438
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.1082 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1864 top1= 94.4111


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2077 top1= 93.7700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1825 top1= 94.3209

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0877 top1= 97.9688
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0758 top1= 98.2812
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0807 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1823 top1= 94.6114


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1969 top1= 94.4010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1817 top1= 94.6715

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0606 top1= 98.9062
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0484 top1= 99.0625
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0601 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1775 top1= 95.0120


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1981 top1= 94.5012


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1839 top1= 94.7817

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0434 top1= 99.2188
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0273 top1= 99.6875
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0370 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1796 top1= 94.8918


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2053 top1= 94.2808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1941 top1= 94.3610

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0303 top1= 99.6875
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0203 top1= 99.8438
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0321 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1812 top1= 95.1122


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2314 top1= 93.6699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1902 top1= 94.9720

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0306 top1= 99.0625
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0261 top1= 99.3750
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0252 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1845 top1= 95.1623


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2342 top1= 93.9303


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1833 top1= 95.2324

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0251 top1= 99.6875
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0295 top1= 99.5312
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0309 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1823 top1= 95.3025


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1861 top1= 95.1923


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1971 top1= 95.0921

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0245 top1= 99.3750
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0096 top1=100.0000
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0107 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1933 top1= 95.1122


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1925 top1= 95.2324


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2121 top1= 94.6514

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0170 top1= 99.8438
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0167 top1= 99.6875
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0079 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1871 top1= 95.3726


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1897 top1= 95.2424


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1954 top1= 95.1823

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0082 top1= 99.6875
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0043 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1828 top1= 95.5629


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1917 top1= 95.4527


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1838 top1= 95.3325

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0043 top1=100.0000
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0041 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1860 top1= 95.5329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1971 top1= 95.4828


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1836 top1= 95.4728

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0027 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1913 top1= 95.3826


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2008 top1= 95.4427


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1877 top1= 95.4026

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1946 top1= 95.5228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2045 top1= 95.4327


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1902 top1= 95.4928

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1980 top1= 95.4928


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2076 top1= 95.4127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1926 top1= 95.4828

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2011 top1= 95.4627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2104 top1= 95.4127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1957 top1= 95.4227

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2034 top1= 95.4728


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2129 top1= 95.4026


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1980 top1= 95.4127

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2056 top1= 95.4327


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2152 top1= 95.4026


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2001 top1= 95.4627

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0009 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2078 top1= 95.4327


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2175 top1= 95.3826


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2022 top1= 95.4627

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0009 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2097 top1= 95.4327


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2195 top1= 95.3726


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2041 top1= 95.4728

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0008 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2115 top1= 95.4427


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2213 top1= 95.3626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2058 top1= 95.4728

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2132 top1= 95.4327


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2231 top1= 95.3626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2075 top1= 95.4627

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2149 top1= 95.4327


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2249 top1= 95.3626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2090 top1= 95.4627

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0006 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2163 top1= 95.4327


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2264 top1= 95.3626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2105 top1= 95.4627

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0006 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2178 top1= 95.4227


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2279 top1= 95.3626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2118 top1= 95.4728

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0006 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2192 top1= 95.4127


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2294 top1= 95.3626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2132 top1= 95.4728

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0005 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2205 top1= 95.4026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2308 top1= 95.3626


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2144 top1= 95.4627

