
=== 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 0x7f8af744f250>

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: 1.0452 top1= 62.3438
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3901 top1= 87.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6396 top1= 79.1066


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4981 top1= 49.3690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1197 top1= 44.1707

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2781 top1= 90.9375
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1979 top1= 94.0625
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.2015 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4867 top1= 84.8558


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5572 top1= 51.7027


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0844 top1= 45.9034

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1614 top1= 95.0000
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1198 top1= 97.0312
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1557 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3877 top1= 87.4399


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3862 top1= 54.4371


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6876 top1= 47.5761

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1280 top1= 95.9375
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0902 top1= 97.1875
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1185 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3381 top1= 88.8522


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3615 top1= 56.2800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3990 top1= 49.8297

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0996 top1= 96.8750
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0633 top1= 98.1250
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0949 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3096 top1= 89.7135


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4248 top1= 57.2115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2865 top1= 52.3638

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0753 top1= 98.1250
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0469 top1= 98.5938
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0748 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2954 top1= 90.0942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4644 top1= 57.9026


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2082 top1= 54.9279

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0610 top1= 98.4375
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0359 top1= 99.3750
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0503 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2797 top1= 90.4647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4229 top1= 58.6438


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2334 top1= 55.5288

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0501 top1= 98.7500
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0280 top1= 99.5312
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0436 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2779 top1= 90.5248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4483 top1= 59.2248


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5971 top1= 53.6158

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0524 top1= 98.7500
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0271 top1= 99.2188
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0901 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3151 top1= 89.0224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4275 top1= 59.6254


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5892 top1= 54.8878

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0683 top1= 98.1250
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0721 top1= 97.5000
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0565 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2827 top1= 90.4547


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1031 top1= 62.1795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2485 top1= 55.7392

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0149 top1= 99.6875
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0266 top1= 99.5312
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0276 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2640 top1= 91.1458


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0365 top1= 62.6202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2456 top1= 55.8494

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0199 top1= 99.2188
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0282 top1= 99.0625
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0220 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2379 top1= 92.2376


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9717 top1= 63.6518


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9506 top1= 58.9042

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0218 top1= 99.5312
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0093 top1= 99.8438
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0119 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2377 top1= 92.3077


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9254 top1= 63.8021


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7931 top1= 61.1579

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0105 top1= 99.8438
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0070 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0069 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2364 top1= 92.6282


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9756 top1= 64.4431


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8152 top1= 63.1110

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0078 top1=100.0000
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0072 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2398 top1= 92.5881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5161 top1= 68.3894


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6926 top1= 66.2660

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0073 top1= 99.8438
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0052 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0072 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2405 top1= 92.6783


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5316 top1= 68.8502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6961 top1= 66.6867

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0050 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0058 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2490 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4369 top1= 70.4227


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6088 top1= 68.7099

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0118 top1= 99.6875
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0041 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2321 top1= 93.2192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3663 top1= 71.3642


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4391 top1= 69.3209

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0032 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0061 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2272 top1= 93.3193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3388 top1= 71.9451


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3490 top1= 70.5028

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0024 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0051 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2288 top1= 93.3293


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2513 top1= 73.3373


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2420 top1= 72.7464

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0021 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2292 top1= 93.4595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2059 top1= 74.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2341 top1= 73.4275

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0021 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2312 top1= 93.4095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1846 top1= 74.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2570 top1= 73.6879

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2317 top1= 93.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1506 top1= 75.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2144 top1= 74.5092

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2325 top1= 93.3894


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1145 top1= 75.9515


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2031 top1= 74.8698

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2328 top1= 93.4595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0887 top1= 76.4223


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1822 top1= 75.4207

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0013 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2330 top1= 93.4996


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0681 top1= 76.8630


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1680 top1= 75.7712

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2331 top1= 93.5397


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0510 top1= 77.1835


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1523 top1= 76.1919

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2333 top1= 93.6198


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0325 top1= 77.5942


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1371 top1= 76.5725

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2333 top1= 93.6498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0135 top1= 78.1150


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1195 top1= 77.0433

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0010 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=0.2333 top1= 93.6899


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9948 top1= 78.5156


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1039 top1= 77.3538

