
=== 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 0x7f95c3cf02b0>

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: 1.1633 top1= 58.5938
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4092 top1= 86.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7454 top1= 81.6306


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4171 top1= 49.2388


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3688 top1= 43.8401

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2880 top1= 89.8438
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2279 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2392 top1= 92.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6990 top1= 86.0677


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8964 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1013 top1= 45.4026

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2215 top1= 92.8125
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1720 top1= 96.2500
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1980 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6246 top1= 86.1378


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7164 top1= 49.7296


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0068 top1= 45.6030

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1922 top1= 93.5938
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1591 top1= 95.9375
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1818 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6030 top1= 85.8474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5847 top1= 49.6895


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9137 top1= 45.5529

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1821 top1= 93.9062
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1499 top1= 96.2500
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1692 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5912 top1= 85.7572


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5112 top1= 49.6895


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9026 top1= 45.7632

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1751 top1= 94.2188
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1429 top1= 96.0938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1586 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5874 top1= 85.7272


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4836 top1= 49.6294


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8674 top1= 45.6330

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1703 top1= 94.3750
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1375 top1= 96.8750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1506 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5840 top1= 85.7372


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4676 top1= 49.6294


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8415 top1= 45.8233

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1623 top1= 94.8438
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1339 top1= 97.1875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1447 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5834 top1= 85.6270


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4578 top1= 49.6695


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8142 top1= 45.7432

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1609 top1= 95.0000
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1261 top1= 97.1875
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1366 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5800 top1= 85.6871


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4534 top1= 49.7095


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7986 top1= 45.8233

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1507 top1= 95.4688
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1197 top1= 97.3438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1303 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5792 top1= 85.7372


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4305 top1= 49.8798


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7538 top1= 45.8333

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1469 top1= 95.6250
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1167 top1= 97.6562
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1255 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5758 top1= 85.5569


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4180 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8221 top1= 45.7833

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1381 top1= 95.6250
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1150 top1= 97.3438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1245 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5760 top1= 85.3866


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4023 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8078 top1= 45.7432

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1377 top1= 95.7812
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1103 top1= 97.5000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1226 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5774 top1= 85.1462


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3844 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7924 top1= 45.6631

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1344 top1= 96.0938
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1092 top1= 97.6562
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1232 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5813 top1= 84.9459


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3936 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7809 top1= 45.6230

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1359 top1= 95.6250
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1120 top1= 97.5000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1224 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5864 top1= 84.8257


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3891 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7592 top1= 45.5329

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1416 top1= 95.6250
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1190 top1= 97.3438
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1251 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5836 top1= 85.1963


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3977 top1= 50.0300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7441 top1= 45.5429

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1443 top1= 95.3125
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1245 top1= 97.0312
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1337 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5821 top1= 85.4567


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3750 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7614 top1= 45.7732

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1369 top1= 95.7812
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1158 top1= 96.5625
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1336 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5747 top1= 85.7672


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4136 top1= 49.6494


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7330 top1= 45.9836

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1302 top1= 96.0938
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1055 top1= 97.9688
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1333 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5711 top1= 86.0076


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3703 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6638 top1= 46.0437

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1177 top1= 96.8750
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0978 top1= 97.8125
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1164 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5656 top1= 86.1979


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3688 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6505 top1= 46.1839

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1108 top1= 97.0312
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1013 top1= 97.8125
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1123 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5666 top1= 86.2079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3543 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6594 top1= 46.1839

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1130 top1= 96.7188
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0969 top1= 97.8125
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1054 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5629 top1= 85.6270


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3298 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7345 top1= 46.2039

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1125 top1= 96.0938
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0932 top1= 97.9688
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1163 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5688 top1= 85.8774


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3213 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6231 top1= 46.2941

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1029 top1= 96.8750
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0916 top1= 97.5000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1259 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5746 top1= 85.5469


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3229 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5295 top1= 46.3842

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1038 top1= 96.8750
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0933 top1= 97.8125
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1203 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5814 top1= 84.9359


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3220 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6359 top1= 46.1038

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1070 top1= 96.5625
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0951 top1= 97.8125
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1123 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5837 top1= 84.3249


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3331 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7659 top1= 45.8634

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1254 top1= 95.4688
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1057 top1= 97.1875
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1170 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5991 top1= 83.6038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3311 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7315 top1= 45.4828

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1364 top1= 95.4688
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.1099 top1= 96.7188
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1201 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5919 top1= 84.5853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3425 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6903 top1= 45.6530

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1301 top1= 95.4688
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.1245 top1= 95.7812
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1588 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5794 top1= 85.5669


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3722 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6379 top1= 46.0837

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1146 top1= 96.5625
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1082 top1= 97.3438
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1387 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5644 top1= 86.0877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3879 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7544 top1= 45.6130

