
=== 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 0x7ff2c53cc250>

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: 1.0345 top1= 62.3438
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3876 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6521 top1= 81.0998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5410 top1= 49.3690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8688 top1= 44.2708

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2783 top1= 91.0938
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1943 top1= 94.2188
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1949 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5262 top1= 86.7288


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7704 top1= 50.0300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9973 top1= 45.9034

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1561 top1= 95.3125
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1096 top1= 96.8750
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1450 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4284 top1= 87.7504


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3614 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3009 top1= 46.3442

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1298 top1= 95.6250
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0799 top1= 97.6562
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1132 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3756 top1= 88.4916


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1328 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0184 top1= 46.9151

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1030 top1= 97.0312
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0612 top1= 98.5938
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0891 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3404 top1= 89.1226


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0130 top1= 52.0433


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8101 top1= 48.8982

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0757 top1= 97.9688
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0456 top1= 99.2188
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0685 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3194 top1= 89.6134


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9336 top1= 53.4555


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7589 top1= 50.2504

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0553 top1= 98.9062
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0335 top1= 99.5312
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0517 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3081 top1= 89.7837


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8304 top1= 54.4471


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6704 top1= 51.3522

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0421 top1= 99.2188
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0281 top1= 99.2188
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0391 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3085 top1= 89.7135


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7635 top1= 55.8093


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6307 top1= 52.8646

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0347 top1= 99.0625
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0291 top1= 99.2188
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0319 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2879 top1= 90.3045


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7221 top1= 56.3301


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4684 top1= 53.8462

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0288 top1= 99.0625
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0466 top1= 98.5938
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0725 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2799 top1= 90.4547


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5415 top1= 57.3718


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8400 top1= 49.2989

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0739 top1= 97.6562
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0258 top1= 99.5312
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0300 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2856 top1= 90.3546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4796 top1= 58.1731


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5667 top1= 52.1935

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0330 top1= 99.0625
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0191 top1= 99.5312
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0208 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2607 top1= 91.4163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4369 top1= 59.5753


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4078 top1= 54.0164

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0150 top1= 99.5312
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0124 top1= 99.8438
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0229 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2512 top1= 91.7969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1715 top1= 61.5685


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1844 top1= 57.0012

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0086 top1=100.0000
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0139 top1= 99.6875
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0091 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2475 top1= 92.0072


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5567 top1= 59.7155


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1360 top1= 58.4936

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0100 top1=100.0000
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0063 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0083 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2362 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1784 top1= 62.1795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0710 top1= 58.9143

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0067 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0072 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0065 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2371 top1= 92.5381


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1126 top1= 62.7504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0196 top1= 60.7272

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0057 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2388 top1= 92.5581


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9714 top1= 64.0625


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9553 top1= 62.0393

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0037 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0118 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2479 top1= 92.2376


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9274 top1= 64.3530


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0316 top1= 62.1494

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0069 top1= 99.8438
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0039 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0051 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2377 top1= 92.7885


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8454 top1= 65.4547


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7866 top1= 64.5733

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0036 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2343 top1= 92.9988


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8359 top1= 65.9355


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5826 top1= 66.3662

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0022 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0047 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2345 top1= 93.0489


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8211 top1= 66.3862


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6189 top1= 66.2059

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0023 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2319 top1= 93.0889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7824 top1= 67.0573


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5882 top1= 67.1675

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0022 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0067 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2369 top1= 92.9587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7428 top1= 67.5881


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7613 top1= 66.4764

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0021 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2358 top1= 93.1691


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7264 top1= 68.1290


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6737 top1= 67.7284

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2371 top1= 93.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6933 top1= 68.5397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6152 top1= 68.8001

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2389 top1= 93.1991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6562 top1= 69.1206


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5722 top1= 69.6615

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2402 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6172 top1= 69.7917


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5369 top1= 70.5929

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0013 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2413 top1= 93.2993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5870 top1= 70.1322


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5107 top1= 71.1639

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2412 top1= 93.3093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5538 top1= 70.6931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4879 top1= 71.5946

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2407 top1= 93.2993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5275 top1= 71.2740


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4711 top1= 71.9752

