
=== 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 0x7f7fccf7e250>

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: 1.0347 top1= 62.1875
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3938 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7060 top1= 78.9764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1718 top1= 49.3289


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1833 top1= 44.2208

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2784 top1= 90.9375
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1929 top1= 93.9062
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1967 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5977 top1= 85.3566


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6395 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6299 top1= 45.8033

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1597 top1= 94.6875
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1104 top1= 96.8750
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1354 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5025 top1= 86.5585


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2286 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0864 top1= 46.3542

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1262 top1= 96.4062
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0829 top1= 97.9688
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1044 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4295 top1= 87.8105


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9305 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7620 top1= 46.5144

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0906 top1= 97.3438
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0627 top1= 98.4375
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0771 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3804 top1= 88.5517


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7794 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5390 top1= 46.6446

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0670 top1= 98.2812
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0439 top1= 98.4375
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0551 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3403 top1= 89.4231


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6254 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4358 top1= 46.8149

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0540 top1= 99.0625
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0354 top1= 99.0625
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0395 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3201 top1= 89.7035


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5410 top1= 50.7712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3216 top1= 47.1454

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0447 top1= 99.0625
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0292 top1= 99.3750
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0278 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2994 top1= 90.3045


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4440 top1= 51.4724


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3219 top1= 47.3357

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0389 top1= 99.2188
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0227 top1= 99.6875
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0221 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2861 top1= 90.9255


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3817 top1= 52.0232


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3489 top1= 47.4760

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0291 top1= 99.2188
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0249 top1= 99.2188
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0245 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2858 top1= 90.7552


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3774 top1= 52.4840


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9765 top1= 48.6178

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0192 top1= 99.3750
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0192 top1= 99.8438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0347 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2744 top1= 90.9956


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3239 top1= 53.0649


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9552 top1= 50.1102

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0270 top1= 98.9062
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0292 top1= 99.3750
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0595 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2894 top1= 90.3946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3060 top1= 53.8562


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0287 top1= 50.5108

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0444 top1= 98.7500
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0133 top1= 99.6875
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0145 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2581 top1= 91.2660


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1370 top1= 54.9479


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8277 top1= 51.0917

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0100 top1= 99.8438
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0171 top1= 99.5312
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0169 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2467 top1= 91.6867


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8823 top1= 55.7792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8349 top1= 50.8113

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0083 top1= 99.8438
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0166 top1= 99.5312
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0265 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2595 top1= 91.4563


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9698 top1= 55.5689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4258 top1= 55.0080

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0168 top1= 99.5312
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0132 top1= 99.8438
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0145 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2665 top1= 91.2059


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6580 top1= 56.8710


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3850 top1= 55.6490

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0086 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0070 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0161 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2439 top1= 91.9271


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4450 top1= 57.7724


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4162 top1= 55.0881

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0082 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0095 top1= 99.8438
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0103 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2338 top1= 92.2376


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5488 top1= 56.7007


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4885 top1= 55.3085

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0130 top1= 99.6875
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0079 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0202 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2293 top1= 92.5080


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2950 top1= 58.4435


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3534 top1= 56.0296

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0082 top1= 99.6875
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0040 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0050 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2239 top1= 92.7584


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3107 top1= 58.5136


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1906 top1= 57.4920

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0027 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2266 top1= 92.6783


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2720 top1= 59.5753


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0742 top1= 58.8842

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0022 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2250 top1= 92.8285


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3223 top1= 59.9459


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1121 top1= 59.3950

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0024 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2248 top1= 92.7985


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2233 top1= 60.9876


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0464 top1= 60.3165

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2262 top1= 92.8385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1760 top1= 61.5184


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0180 top1= 61.0276

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2270 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1526 top1= 61.8690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9959 top1= 61.7688

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2273 top1= 92.8986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1305 top1= 62.2196


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9675 top1= 62.3197

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2282 top1= 93.0088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1127 top1= 62.5901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9457 top1= 62.9207

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2288 top1= 93.0589


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0948 top1= 63.0709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9314 top1= 63.4315

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2296 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0749 top1= 63.4716


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9140 top1= 63.7921

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2304 top1= 93.0990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0569 top1= 63.7821


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8991 top1= 64.3129

