
=== 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 0x7f4c7a23b250>

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: 1.0349 top1= 62.0312
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3896 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6561 top1= 80.6991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5212 top1= 49.3990


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7631 top1= 44.2208

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2774 top1= 91.2500
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1965 top1= 94.0625
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1951 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5206 top1= 86.9091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7476 top1= 49.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8553 top1= 45.8934

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1569 top1= 95.1562
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1104 top1= 97.0312
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1419 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4263 top1= 87.8205


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3474 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1911 top1= 46.3642

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1300 top1= 95.9375
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0800 top1= 97.9688
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1108 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3727 top1= 88.6919


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1470 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9143 top1= 47.2656

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1014 top1= 97.3438
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0611 top1= 98.4375
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0892 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3390 top1= 89.1526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9622 top1= 52.1735


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7191 top1= 49.5292

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0730 top1= 97.9688
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0446 top1= 99.0625
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0669 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3164 top1= 89.7837


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8741 top1= 53.5256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6519 top1= 50.9315

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0537 top1= 98.9062
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0346 top1= 99.0625
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0552 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3064 top1= 89.8438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8305 top1= 54.5272


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5710 top1= 52.3638

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0410 top1= 98.9062
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0318 top1= 99.0625
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0417 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3014 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7374 top1= 55.7192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4831 top1= 53.9463

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0338 top1= 99.0625
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0331 top1= 99.0625
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0337 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2815 top1= 90.6951


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7051 top1= 56.3502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4111 top1= 54.3670

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0248 top1= 99.3750
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0429 top1= 98.2812
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0625 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2771 top1= 90.6450


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5017 top1= 57.7524


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5286 top1= 51.5725

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0651 top1= 97.8125
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0300 top1= 98.9062
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0258 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2739 top1= 91.0156


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5248 top1= 59.0745


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3557 top1= 53.6759

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0286 top1= 99.0625
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0171 top1= 99.5312
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0166 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2548 top1= 91.5565


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6197 top1= 59.2348


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4900 top1= 53.9964

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0157 top1= 99.6875
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0126 top1= 99.8438
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0128 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2444 top1= 91.9972


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2179 top1= 61.6086


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2770 top1= 55.9395

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0080 top1=100.0000
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0131 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0096 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2386 top1= 92.2877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5228 top1= 59.8257


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1154 top1= 59.4752

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0102 top1= 99.6875
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0062 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0082 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2342 top1= 92.4880


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3350 top1= 60.9475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9976 top1= 61.4683

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0072 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0072 top1= 99.8438
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0066 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2471 top1= 92.1274


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1639 top1= 62.7003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9495 top1= 62.8305

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0116 top1= 99.6875
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0053 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0085 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2375 top1= 92.5581


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0746 top1= 63.6819


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0858 top1= 60.7672

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0043 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2333 top1= 92.7985


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9552 top1= 64.4531


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7651 top1= 64.5433

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0036 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2374 top1= 92.6983


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9102 top1= 65.0341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7914 top1= 65.0841

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0024 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0085 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2334 top1= 92.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8253 top1= 66.1859


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8039 top1= 65.0140

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0051 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2320 top1= 93.0489


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8196 top1= 66.5565


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6509 top1= 67.2075

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0023 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2337 top1= 93.0990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7750 top1= 67.1875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5123 top1= 68.2692

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2356 top1= 93.1290


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7137 top1= 68.0689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4821 top1= 68.7800

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2365 top1= 93.2292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6767 top1= 68.6198


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4979 top1= 68.5897

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0044 top1= 99.8438
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2381 top1= 93.2592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6244 top1= 69.3610


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5756 top1= 67.7784

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0040 top1= 99.8438
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2365 top1= 93.3093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5903 top1= 69.8417


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6958 top1= 66.7668

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0030 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0148 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2391 top1= 93.1290


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5445 top1= 70.4227


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8664 top1= 66.0557

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0078 top1= 99.6875
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0022 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2360 top1= 93.3093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5382 top1= 70.7833


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7304 top1= 67.4780

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0021 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2486 top1= 92.8886


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4988 top1= 71.2440


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8898 top1= 67.4880

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0067 top1= 99.8438
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0085 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2363 top1= 93.2893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4567 top1= 71.9151


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7211 top1= 68.1991

