
=== 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 0x7f655b4122e0>

Train epoch 1
[E 1B0  |    704/60000 (  1%) ] Loss: 2.3080 top1=  8.4375

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')
Worker 2 has targets: tensor([3, 0, 3, 2, 7], device='cuda:0')
Worker 3 has targets: tensor([1, 4, 8, 2, 8], device='cuda:0')
Worker 4 has targets: tensor([9, 5, 0, 1, 3], device='cuda:0')
Worker 5 has targets: tensor([5, 6, 2, 4, 3], device='cuda:0')
Worker 6 has targets: tensor([2, 5, 0, 9, 9], device='cuda:0')
Worker 7 has targets: tensor([2, 2, 1, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([3, 8, 7, 0, 3], device='cuda:0')
Worker 9 has targets: tensor([1, 7, 1, 7, 2], device='cuda:0')
Worker 10 has targets: tensor([8, 4, 4, 3, 9], device='cuda:0')
Worker 11 has targets: tensor([3, 4, 7, 7, 9], device='cuda:0')
Worker 12 has targets: tensor([7, 4, 3, 9, 4], device='cuda:0')
Worker 13 has targets: tensor([4, 5, 0, 7, 1], device='cuda:0')
Worker 14 has targets: tensor([4, 2, 3, 5, 5], device='cuda:0')
Worker 15 has targets: tensor([4, 7, 5, 4, 7], device='cuda:0')
Worker 16 has targets: tensor([1, 1, 5, 7, 9], device='cuda:0')
Worker 17 has targets: tensor([8, 7, 2, 2, 0], device='cuda:0')
Worker 18 has targets: tensor([7, 8, 0, 0, 6], device='cuda:0')
Worker 19 has targets: tensor([9, 9, 5, 2, 8], device='cuda:0')
Worker 20 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 21 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 2.1290 top1= 30.3125
[E 1B20 |  14784/60000 ( 25%) ] Loss: 1.7888 top1= 51.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2016 top1= 77.7845


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1974 top1= 79.1767


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2161 top1= 75.0601

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 1.2769 top1= 64.6875
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.9730 top1= 72.9688
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.7962 top1= 76.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5272 top1= 87.5200


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5187 top1= 87.7404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5403 top1= 86.9992

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.6596 top1= 77.8125
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.6431 top1= 79.0625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.5645 top1= 81.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3968 top1= 89.3830


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3946 top1= 89.5933


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4047 top1= 89.0425

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.4467 top1= 87.3438
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.4369 top1= 87.0312
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.4774 top1= 84.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3420 top1= 90.5950


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3449 top1= 90.5349


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3447 top1= 90.4447

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.3905 top1= 87.6562
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.3814 top1= 86.8750
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.3966 top1= 87.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3124 top1= 91.1759


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3132 top1= 91.1959


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3139 top1= 91.2360

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.3195 top1= 90.4688
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.3314 top1= 90.1562
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.3670 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2869 top1= 91.8870


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2873 top1= 91.7768


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2890 top1= 91.7969

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.2841 top1= 91.4062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.3058 top1= 90.9375
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.3182 top1= 91.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2718 top1= 92.1274


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2739 top1= 92.1274


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2733 top1= 92.0673

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.2779 top1= 92.3438
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.2660 top1= 92.3438
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.2977 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2549 top1= 92.6182


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2570 top1= 92.5581


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2555 top1= 92.6282

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.2469 top1= 93.1250
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.2506 top1= 92.8125
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.2845 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2403 top1= 92.9487


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2402 top1= 93.0188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2431 top1= 92.8886

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.2331 top1= 93.7500
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.2215 top1= 93.4375
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.2416 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2288 top1= 93.2492


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2314 top1= 93.2392


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2291 top1= 93.2692

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.2117 top1= 93.4375
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1935 top1= 94.2188
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.2337 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2186 top1= 93.6899


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2210 top1= 93.3994


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2228 top1= 93.4195

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.2134 top1= 94.0625
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1942 top1= 94.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.2143 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2080 top1= 93.9603


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2102 top1= 93.8802


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2082 top1= 93.9002

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1811 top1= 95.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1925 top1= 94.2188
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.2116 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2003 top1= 94.2007


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2043 top1= 93.9503


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2002 top1= 94.2208

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1599 top1= 95.6250
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1747 top1= 94.5312
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1808 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1945 top1= 94.3109


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1940 top1= 94.1607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1979 top1= 94.3109

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1618 top1= 95.9375
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1654 top1= 95.4688
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1787 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1879 top1= 94.4411


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1895 top1= 94.4111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1893 top1= 94.3510

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1600 top1= 95.4688
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1541 top1= 95.9375
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1570 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1798 top1= 94.5613


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1832 top1= 94.3610


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1791 top1= 94.6314

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1369 top1= 96.7188
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1202 top1= 96.8750
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1542 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1745 top1= 94.8017


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1767 top1= 94.7516


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1762 top1= 94.6915

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1598 top1= 95.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1306 top1= 96.7188
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1420 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1693 top1= 94.9219


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1707 top1= 94.8317


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1705 top1= 94.9219

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1301 top1= 96.5625
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1267 top1= 96.2500
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1267 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1634 top1= 94.9920


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1654 top1= 94.8918


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1640 top1= 94.9720

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1117 top1= 97.3438
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1159 top1= 96.7188
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1147 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1613 top1= 94.9820


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1625 top1= 95.0321


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1631 top1= 94.9619

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1203 top1= 96.7188
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1023 top1= 96.8750
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1195 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1544 top1= 95.3125


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1571 top1= 95.2123


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1550 top1= 95.3926

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1205 top1= 97.0312
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.1010 top1= 97.1875
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1190 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1522 top1= 95.2724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1553 top1= 95.1122


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1522 top1= 95.2424

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1029 top1= 97.3438
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0874 top1= 97.5000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0986 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1483 top1= 95.4026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1489 top1= 95.3225


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1503 top1= 95.2925

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0967 top1= 97.8125
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0972 top1= 97.5000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0944 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1448 top1= 95.5529


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1450 top1= 95.5529


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1465 top1= 95.3926

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1040 top1= 97.0312
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0855 top1= 97.1875
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1005 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1410 top1= 95.4828


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1429 top1= 95.4627


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1414 top1= 95.4728

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0815 top1= 98.1250
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0732 top1= 97.6562
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0778 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1381 top1= 95.7031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1406 top1= 95.6230


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1380 top1= 95.6130

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0909 top1= 97.9688
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0808 top1= 97.6562
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0905 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1350 top1= 95.8534


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1360 top1= 95.7131


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1358 top1= 95.7732

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0847 top1= 98.2812
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0708 top1= 98.2812
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0809 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1316 top1= 95.7833


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1330 top1= 95.8033


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1320 top1= 95.8433

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0551 top1= 99.2188
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0456 top1= 99.8438
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0518 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1305 top1= 95.9736


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1326 top1= 95.9435


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1316 top1= 95.9135

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1028 top1= 96.8750
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0937 top1= 97.3438
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0763 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1292 top1= 95.9435


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1300 top1= 95.9135


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1300 top1= 95.9535

