
=== 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 0x7fee1712a250>

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: 1.0398 top1= 62.0312
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3896 top1= 88.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6301 top1= 81.5605


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4166 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8540 top1= 44.1607

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2770 top1= 90.7812
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1985 top1= 93.9062
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.2018 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4652 top1= 87.1595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9294 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9099 top1= 45.9135

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1577 top1= 95.6250
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1203 top1= 97.0312
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1567 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3752 top1= 88.6819


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7143 top1= 51.8830


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6010 top1= 48.0769

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1332 top1= 95.7812
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0890 top1= 97.3438
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1168 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3302 top1= 89.4331


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6032 top1= 53.8261


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2972 top1= 50.6110

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1067 top1= 97.0312
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0632 top1= 98.4375
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0933 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3064 top1= 89.9339


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6257 top1= 54.8978


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1805 top1= 53.7260

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0823 top1= 97.9688
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0461 top1= 99.0625
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0704 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2950 top1= 90.2845


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6261 top1= 55.8894


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0894 top1= 56.0897

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0659 top1= 98.5938
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0395 top1= 99.0625
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0561 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2969 top1= 90.2444


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5605 top1= 57.4519


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0501 top1= 58.1931

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0558 top1= 98.4375
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0320 top1= 99.3750
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0530 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2807 top1= 90.5248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5163 top1= 58.6038


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0948 top1= 57.3317

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0396 top1= 98.9062
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0247 top1= 99.5312
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0489 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2602 top1= 91.3562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2623 top1= 59.9259


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4322 top1= 54.7977

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0430 top1= 98.5938
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0333 top1= 98.4375
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0469 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2660 top1= 90.9856


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0622 top1= 60.9375


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1869 top1= 58.2933

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0470 top1= 98.1250
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0404 top1= 98.2812
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0326 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2505 top1= 91.6767


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8914 top1= 62.4199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0629 top1= 58.4635

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0166 top1= 99.5312
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0133 top1= 99.8438
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0145 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2370 top1= 92.1575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0061 top1= 62.2696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1075 top1= 57.8526

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0331 top1= 98.5938
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0119 top1= 99.8438
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0119 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2375 top1= 92.2776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7180 top1= 65.3546


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8712 top1= 61.1078

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0154 top1= 99.5312
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0109 top1= 99.8438
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0094 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2253 top1= 92.9888


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0872 top1= 62.9808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8124 top1= 62.4700

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0078 top1=100.0000
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0062 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0122 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2304 top1= 92.8285


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7620 top1= 65.8353


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6884 top1= 65.0641

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0091 top1= 99.8438
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0046 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2341 top1= 92.9287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5255 top1= 68.3093


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5890 top1= 67.9287

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0083 top1= 99.8438
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0039 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0054 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2264 top1= 93.0088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4895 top1= 68.9603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5076 top1= 69.0805

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0041 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2315 top1= 92.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3996 top1= 70.3926


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4987 top1= 69.7015

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0054 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2317 top1= 92.9888


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3670 top1= 71.2841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5101 top1= 70.1022

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0046 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2312 top1= 93.1290


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3363 top1= 71.9551


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4131 top1= 71.3742

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0027 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2272 top1= 93.3393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3255 top1= 72.4159


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3247 top1= 72.5361

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0026 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2254 top1= 93.4595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2892 top1= 73.2171


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2277 top1= 73.9283

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2274 top1= 93.5096


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2404 top1= 74.0084


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2876 top1= 73.5477

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2273 top1= 93.5998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2016 top1= 74.7196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2525 top1= 73.8281

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2278 top1= 93.5497


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1824 top1= 75.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2362 top1= 74.7897

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2359 top1= 93.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1595 top1= 75.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3276 top1= 74.4291

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: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2331 top1= 93.4996


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1401 top1= 75.9115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1734 top1= 76.2520

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2357 top1= 93.5797


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1066 top1= 76.4523


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1820 top1= 76.4924

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2365 top1= 93.5597


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0837 top1= 76.9932


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1595 top1= 76.8630

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0011 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=0.2368 top1= 93.5897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0654 top1= 77.3738


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1482 top1= 77.1034

