
=== 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 0x7f6b1b6dc250>

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: 1.0358 top1= 62.5000
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3948 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7085 top1= 79.0865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7935 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7473 top1= 44.2608

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2826 top1= 90.9375
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1940 top1= 93.9062
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1926 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6376 top1= 85.1062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2789 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3928 top1= 45.8333

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1597 top1= 95.0000
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1087 top1= 96.5625
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1235 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5623 top1= 86.0978


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0955 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2898 top1= 46.2340

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1207 top1= 96.7188
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0785 top1= 98.1250
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0819 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4972 top1= 86.9992


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0956 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1452 top1= 46.4643

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0827 top1= 98.1250
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0598 top1= 98.5938
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0575 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4409 top1= 87.5801


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1270 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1427 top1= 46.4643

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0657 top1= 98.9062
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0437 top1= 98.9062
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0424 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4047 top1= 87.7905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0657 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9984 top1= 46.7147

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0466 top1= 98.9062
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0311 top1= 99.3750
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0322 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3687 top1= 88.6318


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0491 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8654 top1= 46.8450

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0288 top1= 99.5312
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0218 top1= 99.6875
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0266 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3403 top1= 89.7035


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0299 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5774 top1= 46.9852

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0191 top1= 99.5312
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0175 top1= 99.6875
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0398 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3283 top1= 89.9940


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8614 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0335 top1= 46.5445

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0234 top1= 99.3750
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0224 top1= 99.3750
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0303 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3327 top1= 89.2428


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6559 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7732 top1= 46.6647

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0310 top1= 99.5312
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0139 top1= 99.8438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0133 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3144 top1= 89.4131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3342 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8684 top1= 47.0353

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0148 top1= 99.8438
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0124 top1= 99.6875
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0132 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2949 top1= 90.2344


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1412 top1= 50.8614


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7458 top1= 47.1855

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0068 top1=100.0000
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0076 top1=100.0000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0239 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2782 top1= 90.7652


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7959 top1= 51.4824


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5790 top1= 47.3758

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0067 top1=100.0000
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0061 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0143 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2759 top1= 90.9155


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5502 top1= 51.5224


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3829 top1= 47.7865

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0122 top1= 99.6875
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0054 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0051 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2755 top1= 90.9856


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5038 top1= 51.4223


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2358 top1= 48.5978

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0102 top1= 99.6875
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0171 top1= 99.0625
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0064 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2575 top1= 91.2961


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0997 top1= 53.0048


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1010 top1= 49.6194

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0054 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0076 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0081 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2543 top1= 91.7368


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9998 top1= 53.5156


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9120 top1= 50.5409

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0050 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0043 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0065 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2486 top1= 91.6867


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6102 top1= 54.9079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7262 top1= 51.5725

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0050 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0038 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0054 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2456 top1= 91.9371


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6045 top1= 55.7792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5500 top1= 53.1050

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0054 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2436 top1= 92.0072


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5202 top1= 56.9611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4341 top1= 54.4071

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0041 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0035 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2393 top1= 92.2676


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3445 top1= 58.5437


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3145 top1= 55.8594

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0038 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0051 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2341 top1= 92.4780


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2496 top1= 59.7256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1932 top1= 57.3117

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0039 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2325 top1= 92.5681


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1549 top1= 60.9575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0769 top1= 58.8341

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0038 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2308 top1= 92.6983


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9807 top1= 62.2796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9807 top1= 60.2163

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0038 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2304 top1= 92.8586


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9371 top1= 63.3213


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8668 top1= 62.0593

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0036 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2296 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7611 top1= 64.7336


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7801 top1= 63.6218

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2289 top1= 92.9888


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7339 top1= 65.4647


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6720 top1= 65.3446

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0031 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2277 top1= 93.1390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6054 top1= 67.1074


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5774 top1= 66.7167

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2264 top1= 93.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5534 top1= 67.9287


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4868 top1= 68.2292

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0026 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2246 top1= 93.3193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4661 top1= 69.1306


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4148 top1= 69.4812

