
=== 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 0x7f3314d946d0>

Train epoch 1
[E 1B0  |    640/60000 (  1%) ] Loss: 2.3007 top1=  9.6875

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


[E 1B10 |   7040/60000 ( 12%) ] Loss: 1.0183 top1= 64.6875
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3641 top1= 88.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7446 top1= 76.3421


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=10.0742 top1= 49.4291


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3810 top1= 43.7800

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2507 top1= 92.0312
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.2092 top1= 92.9688
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1681 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7259 top1= 82.0413


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0951 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0951 top1= 45.7131

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1457 top1= 95.9375
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1250 top1= 95.1562
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1063 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6597 top1= 83.5337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0414 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1771 top1= 46.0637

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1128 top1= 96.2500
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0864 top1= 96.7188
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0717 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6081 top1= 84.4050


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2986 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2625 top1= 46.4143

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0840 top1= 97.6562
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0609 top1= 97.9688
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0468 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5664 top1= 85.2163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4326 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4662 top1= 46.7147

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0633 top1= 98.1250
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0446 top1= 98.5938
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0353 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5341 top1= 85.2764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5412 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7830 top1= 46.6146

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0527 top1= 98.9062
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0312 top1= 98.9062
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0269 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5146 top1= 84.9960


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7256 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9623 top1= 46.6146

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0541 top1= 98.9062
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0279 top1= 99.2188
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0191 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4991 top1= 84.8658


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6642 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2097 top1= 46.5244

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0526 top1= 98.7500
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0358 top1= 98.5938
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0186 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4801 top1= 85.2364


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3198 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3667 top1= 46.8750

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0373 top1= 99.0625
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0384 top1= 99.2188
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0445 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4574 top1= 86.9892


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8618 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2457 top1= 46.8850

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0238 top1= 99.5312
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0099 top1= 99.8438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0097 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4409 top1= 87.3097


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8748 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2315 top1= 47.0252

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0134 top1= 99.5312
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0088 top1=100.0000
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4078 top1= 88.2212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2880 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6739 top1= 47.1955

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0079 top1= 99.8438
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0053 top1=100.0000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3931 top1= 88.3413


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5145 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8706 top1= 47.1454

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0055 top1= 99.8438
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0030 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3820 top1= 88.4515


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7328 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1293 top1= 47.2155

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0027 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3747 top1= 88.2212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9102 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1621 top1= 47.2857

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0025 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3708 top1= 88.2913


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0456 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2424 top1= 47.2756

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0021 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3684 top1= 88.2011


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1613 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3492 top1= 47.2756

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3652 top1= 88.2512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2096 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4077 top1= 47.2857

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3616 top1= 88.3614


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2305 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4500 top1= 47.2756

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3594 top1= 88.3113


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2453 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4733 top1= 47.2656

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0013 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3575 top1= 88.3714


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2544 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4889 top1= 47.2356

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3554 top1= 88.4315


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2532 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4902 top1= 47.2356

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3533 top1= 88.4716


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2443 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4870 top1= 47.2256

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3517 top1= 88.5717


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2295 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4751 top1= 47.2256

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3498 top1= 88.6018


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2073 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4536 top1= 47.2155

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3481 top1= 88.6218


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1791 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.4283 top1= 47.2155

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3464 top1= 88.6819


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1473 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3980 top1= 47.2055

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3445 top1= 88.7019


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1115 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3617 top1= 47.2356

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0009 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3431 top1= 88.7420


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0719 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3239 top1= 47.2356

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0009 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3414 top1= 88.7320


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0264 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2783 top1= 47.2456

