
=== 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)
=> Add worker BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f34d5e5a2b0>

Train epoch 1
[E 1B0  |    704/60000 (  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')
Worker 20 has targets: tensor([3, 2, 2, 4, 3], device='cuda:0')
Worker 21 has targets: tensor([8, 9, 7, 7, 9], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 1.0347 top1= 62.1875
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3960 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7256 top1= 78.6859


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9189 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7978 top1= 44.2208

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2828 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1921 top1= 93.5938
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1982 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6741 top1= 84.8558


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4255 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5287 top1= 45.8033

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1634 top1= 95.0000
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1119 top1= 96.2500
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1246 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6125 top1= 85.8574


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3507 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5632 top1= 46.1639

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1224 top1= 96.4062
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0810 top1= 97.9688
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0812 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5500 top1= 86.8890


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4626 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5482 top1= 46.4143

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0849 top1= 97.9688
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0624 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0580 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5043 top1= 87.1695


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5698 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5989 top1= 46.5345

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0636 top1= 98.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0463 top1= 98.5938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0455 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4655 top1= 87.8806


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7071 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5999 top1= 46.7748

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0436 top1= 99.0625
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0308 top1= 99.5312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0381 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4336 top1= 88.6318


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8118 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5112 top1= 46.8349

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0329 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0252 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0337 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4075 top1= 89.0625


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9202 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4784 top1= 46.8850

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0248 top1= 99.5312
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0189 top1= 99.5312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0207 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4009 top1= 87.9808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8866 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4964 top1= 46.9151

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0245 top1= 99.0625
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0196 top1= 99.5312
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0150 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3705 top1= 89.2127


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7992 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6492 top1= 46.8149

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0179 top1= 99.5312
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0115 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0141 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3659 top1= 89.1426


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5982 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7823 top1= 46.9752

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0088 top1=100.0000
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0104 top1=100.0000
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0224 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3660 top1= 88.7821


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2162 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7875 top1= 46.9651

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0103 top1= 99.8438
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0097 top1= 99.8438
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0117 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3653 top1= 88.7220


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0963 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7258 top1= 47.1454

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0143 top1= 99.6875
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0120 top1= 99.8438
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0107 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3371 top1= 89.9038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8235 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5186 top1= 47.0954

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0126 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3298 top1= 90.1943


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7614 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2976 top1= 47.2155

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0060 top1= 99.8438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0092 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3289 top1= 90.1242


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7613 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1049 top1= 46.9852

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0087 top1= 99.8438
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0039 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0087 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3227 top1= 90.4347


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7311 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9628 top1= 46.9151

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0080 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0059 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0061 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3098 top1= 90.5950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7091 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9665 top1= 47.2356

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0059 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0086 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3216 top1= 89.8438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6547 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8589 top1= 47.0252

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0117 top1= 99.8438
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0040 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3124 top1= 90.2644


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5607 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7161 top1= 47.1454

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0039 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3052 top1= 90.7151


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4653 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7296 top1= 47.2556

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3001 top1= 90.7652


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3740 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6128 top1= 47.1554

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2966 top1= 90.9054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2778 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5049 top1= 47.1254

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0030 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2946 top1= 90.8654


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1884 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3678 top1= 47.2055

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2918 top1= 90.9555


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1004 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2506 top1= 47.1955

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2896 top1= 91.0256


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0133 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1463 top1= 47.1955

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0032 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2876 top1= 90.9756


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9396 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0468 top1= 47.1955

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0033 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2858 top1= 90.9555


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8628 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9609 top1= 47.2155

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0033 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2840 top1= 91.0757


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7964 top1= 50.8013


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8864 top1= 47.2256

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0034 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2822 top1= 91.0958


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7317 top1= 50.9115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8154 top1= 47.2656

