
=== 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 0x7f2c132b5250>

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: 1.0344 top1= 62.3438
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3921 top1= 88.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6787 top1= 80.0781


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2708 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3904 top1= 44.2308

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2842 top1= 90.6250
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1932 top1= 93.7500
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1959 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5835 top1= 86.1679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7668 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8142 top1= 45.7833

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1571 top1= 95.0000
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1063 top1= 96.8750
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1358 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4921 top1= 86.9692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3106 top1= 49.9099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3293 top1= 46.3041

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1242 top1= 96.5625
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0786 top1= 97.9688
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0984 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4223 top1= 88.0509


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9927 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8692 top1= 46.5545

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0876 top1= 97.5000
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0589 top1= 98.4375
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0718 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3652 top1= 89.0625


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6679 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5005 top1= 46.5946

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0667 top1= 98.1250
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0432 top1= 98.7500
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0544 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3275 top1= 89.7035


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3552 top1= 50.8413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2351 top1= 46.9050

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0553 top1= 98.9062
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0361 top1= 99.2188
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0414 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3051 top1= 90.1843


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1195 top1= 52.0333


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0007 top1= 47.9167

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0436 top1= 99.3750
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0278 top1= 99.6875
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0312 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2902 top1= 90.6150


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0510 top1= 53.5357


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9463 top1= 48.7881

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0319 top1= 99.5312
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0213 top1= 99.8438
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0228 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2845 top1= 90.7352


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9466 top1= 54.8978


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7869 top1= 49.9399

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0221 top1= 99.5312
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0188 top1= 99.8438
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0228 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2686 top1= 91.3862


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9070 top1= 55.7592


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8145 top1= 50.6711

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0163 top1= 99.6875
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0136 top1= 99.8438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0708 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2778 top1= 90.8854


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9721 top1= 56.4704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6872 top1= 51.4022

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0457 top1= 98.2812
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0230 top1= 99.5312
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0275 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2841 top1= 90.4948


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8318 top1= 57.5421


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8003 top1= 52.6442

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0188 top1= 99.8438
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0230 top1= 99.5312
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0206 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2586 top1= 91.5064


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8295 top1= 58.1430


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6649 top1= 53.3454

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0123 top1= 99.8438
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0125 top1= 99.8438
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0279 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2593 top1= 91.6366


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8795 top1= 57.9527


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7162 top1= 54.2969

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0199 top1= 99.6875
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0095 top1= 99.8438
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0246 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2397 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0212 top1= 58.6639


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5382 top1= 55.6490

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0088 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0162 top1= 99.8438
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0067 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2331 top1= 92.4079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6896 top1= 59.3149


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3118 top1= 57.8025

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0115 top1= 99.8438
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0127 top1= 99.8438
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0184 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2456 top1= 92.3478


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4415 top1= 60.9675


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1636 top1= 59.9259

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0102 top1= 99.6875
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0069 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0082 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2554 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1902 top1= 62.1895


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3181 top1= 59.1847

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0112 top1= 99.8438
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0070 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0092 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2624 top1= 91.9071


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4786 top1= 61.4483


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0745 top1= 61.2580

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0352 top1= 98.9062
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0063 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0065 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2242 top1= 92.8986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4001 top1= 59.7556


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7973 top1= 64.4331

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0035 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0067 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2247 top1= 92.8486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1497 top1= 62.0192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6481 top1= 65.3546

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0047 top1= 99.8438
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0031 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2230 top1= 93.2792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8613 top1= 64.3229


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5517 top1= 66.4964

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0029 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2158 top1= 93.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7581 top1= 65.2744


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7344 top1= 65.8954

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0026 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2180 top1= 93.3894


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6837 top1= 66.6266


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7377 top1= 66.3361

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: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2171 top1= 93.3994


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5980 top1= 67.7384


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5943 top1= 68.0990

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2188 top1= 93.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5669 top1= 68.5096


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5561 top1= 68.9503

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2192 top1= 93.5196


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5258 top1= 69.2608


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5133 top1= 69.9419

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0013 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2190 top1= 93.5597


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5125 top1= 69.6114


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4793 top1= 70.5729

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2188 top1= 93.6498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4769 top1= 70.3225


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4538 top1= 71.1238

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2186 top1= 93.7099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4605 top1= 70.7432


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4256 top1= 71.5345

